Merge tag '5.17-rc-part2-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs fixes from Steve French:
- multichannel fixes, addressing additional reconnect and DFS scenarios
- reenabling fscache support (indexing rewrite, metadata caching e.g.)
- send additional version information during NTLMSSP negotiate to
improve debugging
- fix for a mount race
- DFS fixes
- fix for a memory leak for stable
* tag '5.17-rc-part2-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
cifs: update internal module number
smb3: send NTLMSSP version information
cifs: Support fscache indexing rewrite
cifs: cifs_ses_mark_for_reconnect should also update reconnect bits
cifs: update tcpStatus during negotiate and sess setup
cifs: make status checks in version independent callers
cifs: remove repeated state change in dfs tree connect
cifs: fix the cifs_reconnect path for DFS
cifs: remove unused variable ses_selected
cifs: protect all accesses to chan_* with chan_lock
cifs: fix the connection state transitions with multichannel
cifs: check reconnects for channels of active tcons too
smb3: add new defines from protocol specification
cifs: serialize all mount attempts
cifs: quirk for STATUS_OBJECT_NAME_INVALID returned for non-ASCII dfs refs
cifs: alloc_path_with_tree_prefix: do not append sep. if the path is empty
cifs: clean up an inconsistent indenting
cifs: free ntlmsspblob allocated in negotiate
diff --git a/CREDITS b/CREDITS
index d8f63e83..b97256d 100644
--- a/CREDITS
+++ b/CREDITS
@@ -315,6 +315,11 @@
S: Terni 05100
S: Italy
+N: Ohad Ben Cohen
+E: ohad@wizery.com
+D: Remote Processor (remoteproc) subsystem
+D: Remote Processor Messaging (rpmsg) subsystem
+
N: Krzysztof Benedyczak
E: golbi@mat.uni.torun.pl
W: http://www.mat.uni.torun.pl/~golbi
diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd
index df4afbc..0c2b613 100644
--- a/Documentation/ABI/stable/sysfs-driver-dma-idxd
+++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd
@@ -41,14 +41,14 @@
Contact: dmaengine@vger.kernel.org
Description: The maximum number of groups can be created under this device.
-What: /sys/bus/dsa/devices/dsa<m>/max_tokens
-Date: Oct 25, 2019
-KernelVersion: 5.6.0
+What: /sys/bus/dsa/devices/dsa<m>/max_read_buffers
+Date: Dec 10, 2021
+KernelVersion: 5.17.0
Contact: dmaengine@vger.kernel.org
-Description: The total number of bandwidth tokens supported by this device.
- The bandwidth tokens represent resources within the DSA
+Description: The total number of read buffers supported by this device.
+ The read buffers represent resources within the DSA
implementation, and these resources are allocated by engines to
- support operations.
+ support operations. See DSA spec v1.2 9.2.4 Total Read Buffers.
What: /sys/bus/dsa/devices/dsa<m>/max_transfer_size
Date: Oct 25, 2019
@@ -115,13 +115,13 @@
Contact: dmaengine@vger.kernel.org
Description: To indicate if this device is configurable or not.
-What: /sys/bus/dsa/devices/dsa<m>/token_limit
-Date: Oct 25, 2019
-KernelVersion: 5.6.0
+What: /sys/bus/dsa/devices/dsa<m>/read_buffer_limit
+Date: Dec 10, 2021
+KernelVersion: 5.17.0
Contact: dmaengine@vger.kernel.org
-Description: The maximum number of bandwidth tokens that may be in use at
+Description: The maximum number of read buffers that may be in use at
one time by operations that access low bandwidth memory in the
- device.
+ device. See DSA spec v1.2 9.2.8 GENCFG on Global Read Buffer Limit.
What: /sys/bus/dsa/devices/dsa<m>/cmd_status
Date: Aug 28, 2020
@@ -220,8 +220,38 @@
Description: Show the current number of entries in this WQ if WQ Occupancy
Support bit WQ capabilities is 1.
+What: /sys/bus/dsa/devices/wq<m>.<n>/enqcmds_retries
+Date Oct 29, 2021
+KernelVersion: 5.17.0
+Contact: dmaengine@vger.kernel.org
+Description: Indicate the number of retires for an enqcmds submission on a sharedwq.
+ A max value to set attribute is capped at 64.
+
What: /sys/bus/dsa/devices/engine<m>.<n>/group_id
Date: Oct 25, 2019
KernelVersion: 5.6.0
Contact: dmaengine@vger.kernel.org
Description: The group that this engine belongs to.
+
+What: /sys/bus/dsa/devices/group<m>.<n>/use_read_buffer_limit
+Date: Dec 10, 2021
+KernelVersion: 5.17.0
+Contact: dmaengine@vger.kernel.org
+Description: Enable the use of global read buffer limit for the group. See DSA
+ spec v1.2 9.2.18 GRPCFG Use Global Read Buffer Limit.
+
+What: /sys/bus/dsa/devices/group<m>.<n>/read_buffers_allowed
+Date: Dec 10, 2021
+KernelVersion: 5.17.0
+Contact: dmaengine@vger.kernel.org
+Description: Indicates max number of read buffers that may be in use at one time
+ by all engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read
+ Buffers Allowed.
+
+What: /sys/bus/dsa/devices/group<m>.<n>/read_buffers_reserved
+Date: Dec 10, 2021
+KernelVersion: 5.17.0
+Contact: dmaengine@vger.kernel.org
+Description: Indicates the number of Read Buffers reserved for the use of
+ engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read Buffers
+ Reserved.
diff --git a/Documentation/ABI/testing/sysfs-bus-vdpa b/Documentation/ABI/testing/sysfs-bus-vdpa
new file mode 100644
index 0000000..28a6111
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-vdpa
@@ -0,0 +1,57 @@
+What: /sys/bus/vdpa/driver_autoprobe
+Date: March 2020
+Contact: virtualization@lists.linux-foundation.org
+Description:
+ This file determines whether new devices are immediately bound
+ to a driver after the creation. It initially contains 1, which
+ means the kernel automatically binds devices to a compatible
+ driver immediately after they are created.
+
+ Writing "0" to this file disable this feature, any other string
+ enable it.
+
+What: /sys/bus/vdpa/driver_probe
+Date: March 2020
+Contact: virtualization@lists.linux-foundation.org
+Description:
+ Writing a device name to this file will cause the kernel binds
+ devices to a compatible driver.
+
+ This can be useful when /sys/bus/vdpa/driver_autoprobe is
+ disabled.
+
+What: /sys/bus/vdpa/drivers/.../bind
+Date: March 2020
+Contact: virtualization@lists.linux-foundation.org
+Description:
+ Writing a device name to this file will cause the driver to
+ attempt to bind to the device. This is useful for overriding
+ default bindings.
+
+What: /sys/bus/vdpa/drivers/.../unbind
+Date: March 2020
+Contact: virtualization@lists.linux-foundation.org
+Description:
+ Writing a device name to this file will cause the driver to
+ attempt to unbind from the device. This may be useful when
+ overriding default bindings.
+
+What: /sys/bus/vdpa/devices/.../driver_override
+Date: November 2021
+Contact: virtualization@lists.linux-foundation.org
+Description:
+ This file allows the driver for a device to be specified.
+ When specified, only a driver with a name matching the value
+ written to driver_override will have an opportunity to bind to
+ the device. The override is specified by writing a string to the
+ driver_override file (echo vhost-vdpa > driver_override) and may
+ be cleared with an empty string (echo > driver_override).
+ This returns the device to standard matching rules binding.
+ Writing to driver_override does not automatically unbind the
+ device from its current driver or make any attempt to
+ automatically load the specified driver. If no driver with a
+ matching name is currently loaded in the kernel, the device will
+ not bind to any driver. This also allows devices to opt-out of
+ driver binding using a driver_override name such as "none".
+ Only a single driver may be specified in the override, there is
+ no support for parsing delimiters.
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index b268e3e..2416b03 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -112,6 +112,11 @@
Description: Set timeout to issue discard commands during umount.
Default: 5 secs
+What: /sys/fs/f2fs/<disk>/pending_discard
+Date: November 2021
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description: Shows the number of pending discard commands in the queue.
+
What: /sys/fs/f2fs/<disk>/max_victim_search
Date: January 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
@@ -528,3 +533,10 @@
f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
in the length of 1..<max_fragment_hole> by turns. This value can be set
between 1..512 and the default value is 4.
+
+What: /sys/fs/f2fs/<disk>/gc_urgent_high_remaining
+Date: December 2021
+Contact: "Daeho Jeong" <daehojeong@google.com>
+Description: You can set the trial count limit for GC urgent high mode with this value.
+ If GC thread gets to the limit, the mode will turn back to GC normal mode.
+ By default, the value is zero, which means there is no limit like before.
diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst
index 1b8b46d..197fe31 100644
--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -13,6 +13,8 @@
b) completion of synchronous block I/O initiated by the task
c) swapping in pages
d) memory reclaim
+e) thrashing page cache
+f) direct compact
and makes these statistics available to userspace through
the taskstats interface.
@@ -41,11 +43,12 @@
statistics. The delay accounting functionality populates specific fields of
this structure. See
- include/linux/taskstats.h
+ include/uapi/linux/taskstats.h
for a description of the fields pertaining to delay accounting.
It will generally be in the form of counters returning the cumulative
-delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
+delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page
+cache, direct compact etc.
Taking the difference of two successive readings of a given
counter (say cpu_delay_total) for a task will give the delay
@@ -88,41 +91,37 @@
General format of the getdelays command::
- getdelays [-t tgid] [-p pid] [-c cmd...]
-
+ getdelays [-dilv] [-t tgid] [-p pid]
Get delays, since system boot, for pid 10::
- # ./getdelays -p 10
+ # ./getdelays -d -p 10
(output similar to next case)
Get sum of delays, since system boot, for all pids with tgid 5::
- # ./getdelays -t 5
+ # ./getdelays -d -t 5
+ print delayacct stats ON
+ TGID 5
- CPU count real total virtual total delay total
- 7876 92005750 100000000 24001500
- IO count delay total
- 0 0
- SWAP count delay total
- 0 0
- RECLAIM count delay total
- 0 0
+ CPU count real total virtual total delay total delay average
+ 8 7000000 6872122 3382277 0.423ms
+ IO count delay total delay average
+ 0 0 0ms
+ SWAP count delay total delay average
+ 0 0 0ms
+ RECLAIM count delay total delay average
+ 0 0 0ms
+ THRASHING count delay total delay average
+ 0 0 0ms
+ COMPACT count delay total delay average
+ 0 0 0ms
-Get delays seen in executing a given simple command::
+Get IO accounting for pid 1, it works only with -p::
- # ./getdelays -c ls /
+ # ./getdelays -i -p 1
+ printing IO accounting
+ linuxrc: read=65536, write=0, cancelled_write=0
- bin data1 data3 data5 dev home media opt root srv sys usr
- boot data2 data4 data6 etc lib mnt proc sbin subdomain tmp var
-
-
- CPU count real total virtual total delay total
- 6 4000250 4000000 0
- IO count delay total
- 0 0
- SWAP count delay total
- 0 0
- RECLAIM count delay total
- 0 0
+The above command can be used with -v to get more debug information.
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml b/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
index 8e13f27..bce96b5 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
@@ -7,7 +7,9 @@
title: Analogix ANX7814 SlimPort (Full-HD Transmitter)
maintainers:
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
+ - Andrzej Hajda <andrzej.hajda@intel.com>
+ - Neil Armstrong <narmstrong@baylibre.com>
+ - Robert Foss <robert.foss@linaro.org>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/bridge/google,cros-ec-anx7688.yaml b/Documentation/devicetree/bindings/display/bridge/google,cros-ec-anx7688.yaml
index 9f7cc6b..a88a5d8 100644
--- a/Documentation/devicetree/bindings/display/bridge/google,cros-ec-anx7688.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/google,cros-ec-anx7688.yaml
@@ -8,7 +8,6 @@
maintainers:
- Nicolas Boichat <drinkcat@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
ChromeOS EC ANX7688 is a display bridge that converts HDMI 2.0 to
diff --git a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
index cdaf7a7..186e17b 100644
--- a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
@@ -8,7 +8,6 @@
maintainers:
- Nicolas Boichat <drinkcat@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
The PS8640 is a low power MIPI-to-eDP video format converter supporting
diff --git a/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml b/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
index a108029..acd2f3f 100644
--- a/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
+++ b/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
@@ -6,15 +6,12 @@
title: Asia Better Technology 3.0" (320x480 pixels) 24-bit IPS LCD panel
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Paul Cercueil <paul@crapouillou.net>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.yaml b/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.yaml
index e89c1ea..7d221ef 100644
--- a/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.yaml
+++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.yaml
@@ -15,11 +15,9 @@
960 TFT source driver pins and 240 TFT gate driver pins, VCOM, VCOML and
VCOMH outputs.
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml b/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml
index cda36c0..72788e3 100644
--- a/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml
+++ b/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml
@@ -6,15 +6,12 @@
title: Innolux EJ030NA 3.0" (320x480 pixels) 24-bit TFT LCD panel
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Paul Cercueil <paul@crapouillou.net>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd035g6-54nt.yaml b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd035g6-54nt.yaml
index c45c92a..2a2756d 100644
--- a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd035g6-54nt.yaml
+++ b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd035g6-54nt.yaml
@@ -6,15 +6,12 @@
title: King Display KD035G6-54NT 3.5" (320x240 pixels) 24-bit TFT LCD panel
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Paul Cercueil <paul@crapouillou.net>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/lgphilips,lb035q02.yaml b/Documentation/devicetree/bindings/display/panel/lgphilips,lb035q02.yaml
index 830e335..5e4e0e5 100644
--- a/Documentation/devicetree/bindings/display/panel/lgphilips,lb035q02.yaml
+++ b/Documentation/devicetree/bindings/display/panel/lgphilips,lb035q02.yaml
@@ -6,15 +6,12 @@
title: LG.Philips LB035Q02 Panel
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Tomi Valkeinen <tomi.valkeinen@ti.com>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/samsung,ld9040.yaml b/Documentation/devicetree/bindings/display/panel/samsung,ld9040.yaml
index 060ee27..d525165 100644
--- a/Documentation/devicetree/bindings/display/panel/samsung,ld9040.yaml
+++ b/Documentation/devicetree/bindings/display/panel/samsung,ld9040.yaml
@@ -6,15 +6,12 @@
title: Samsung LD9040 AMOLED LCD parallel RGB panel with SPI control bus
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Andrzej Hajda <a.hajda@samsung.com>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
@@ -63,8 +60,6 @@
lcd@0 {
compatible = "samsung,ld9040";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
vdd3-supply = <&ldo7_reg>;
diff --git a/Documentation/devicetree/bindings/display/panel/samsung,s6e63m0.yaml b/Documentation/devicetree/bindings/display/panel/samsung,s6e63m0.yaml
index ea58df4..940f7f8 100644
--- a/Documentation/devicetree/bindings/display/panel/samsung,s6e63m0.yaml
+++ b/Documentation/devicetree/bindings/display/panel/samsung,s6e63m0.yaml
@@ -12,6 +12,7 @@
allOf:
- $ref: panel-common.yaml#
- $ref: /schemas/leds/backlight/common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/sitronix,st7789v.yaml b/Documentation/devicetree/bindings/display/panel/sitronix,st7789v.yaml
index fa46d15..9e1d707 100644
--- a/Documentation/devicetree/bindings/display/panel/sitronix,st7789v.yaml
+++ b/Documentation/devicetree/bindings/display/panel/sitronix,st7789v.yaml
@@ -6,15 +6,12 @@
title: Sitronix ST7789V RGB panel with SPI control bus
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Maxime Ripard <mripard@kernel.org>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/sony,acx565akm.yaml b/Documentation/devicetree/bindings/display/panel/sony,acx565akm.yaml
index 95d053c..98abdf4 100644
--- a/Documentation/devicetree/bindings/display/panel/sony,acx565akm.yaml
+++ b/Documentation/devicetree/bindings/display/panel/sony,acx565akm.yaml
@@ -6,15 +6,12 @@
title: Sony ACX565AKM SDI Panel
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Tomi Valkeinen <tomi.valkeinen@ti.com>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/panel/tpo,td.yaml b/Documentation/devicetree/bindings/display/panel/tpo,td.yaml
index 4aa6056..f902a9d 100644
--- a/Documentation/devicetree/bindings/display/panel/tpo,td.yaml
+++ b/Documentation/devicetree/bindings/display/panel/tpo,td.yaml
@@ -6,16 +6,13 @@
title: Toppoly TD Panels
-description: |
- The panel must obey the rules for a SPI slave device as specified in
- spi/spi-controller.yaml
-
maintainers:
- Marek Belisko <marek@goldelico.com>
- H. Nikolaus Schaller <hns@goldelico.com>
allOf:
- $ref: panel-common.yaml#
+ - $ref: /schemas/spi/spi-peripheral-props.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.yaml
index 008c144..1a68a94 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.yaml
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.yaml
@@ -26,14 +26,6 @@
clock-names:
const: hclk
- pinctrl-0:
- maxItems: 2
-
- pinctrl-names:
- const: default
- description:
- Switch the iomux for the HPD/I2C pins to HDMI function.
-
power-domains:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/dma/arm,pl330.yaml b/Documentation/devicetree/bindings/dma/arm,pl330.yaml
new file mode 100644
index 0000000..decab18
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/arm,pl330.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/arm,pl330.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM PrimeCell PL330 DMA Controller
+
+maintainers:
+ - Vinod Koul <vkoul@kernel.org>
+
+description:
+ The ARM PrimeCell PL330 DMA controller can move blocks of memory contents
+ between memory and peripherals or memory to memory.
+
+# We need a select here so we don't match all nodes with 'arm,primecell'
+select:
+ properties:
+ compatible:
+ contains:
+ const: arm,pl330
+ required:
+ - compatible
+
+allOf:
+ - $ref: dma-controller.yaml#
+ - $ref: /schemas/arm/primecell.yaml#
+
+properties:
+ compatible:
+ items:
+ - enum:
+ - arm,pl330
+ - const: arm,primecell
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ minItems: 1
+ maxItems: 32
+ description: A single combined interrupt or an interrupt per event
+
+ '#dma-cells':
+ const: 1
+ description: Contains the DMA request number for the consumer
+
+ arm,pl330-broken-no-flushp:
+ type: boolean
+ description: quirk for avoiding to execute DMAFLUSHP
+
+ arm,pl330-periph-burst:
+ type: boolean
+ description: quirk for performing burst transfer only
+
+ dma-coherent: true
+
+ resets:
+ minItems: 1
+ maxItems: 2
+
+ reset-names:
+ minItems: 1
+ items:
+ - const: dma
+ - const: dma-ocp
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ dma-controller@12680000 {
+ compatible = "arm,pl330", "arm,primecell";
+ reg = <0x12680000 0x1000>;
+ interrupts = <99>;
+ #dma-cells = <1>;
+ };
+...
diff --git a/Documentation/devicetree/bindings/dma/arm-pl08x.yaml b/Documentation/devicetree/bindings/dma/arm-pl08x.yaml
index 3bd9eea..9193b18 100644
--- a/Documentation/devicetree/bindings/dma/arm-pl08x.yaml
+++ b/Documentation/devicetree/bindings/dma/arm-pl08x.yaml
@@ -10,6 +10,7 @@
- Vinod Koul <vkoul@kernel.org>
allOf:
+ - $ref: /schemas/arm/primecell.yaml#
- $ref: "dma-controller.yaml#"
# We need a select here so we don't match all nodes with 'arm,primecell'
@@ -89,6 +90,9 @@
- 64
description: bus width used for memcpy in bits. FTDMAC020 also accept 64 bits
+ resets:
+ maxItems: 1
+
required:
- reg
- interrupts
diff --git a/Documentation/devicetree/bindings/dma/arm-pl330.txt b/Documentation/devicetree/bindings/dma/arm-pl330.txt
deleted file mode 100644
index 315e901..0000000
--- a/Documentation/devicetree/bindings/dma/arm-pl330.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-* ARM PrimeCell PL330 DMA Controller
-
-The ARM PrimeCell PL330 DMA controller can move blocks of memory contents
-between memory and peripherals or memory to memory.
-
-Required properties:
- - compatible: should include both "arm,pl330" and "arm,primecell".
- - reg: physical base address of the controller and length of memory mapped
- region.
- - interrupts: interrupt number to the cpu.
-
-Optional properties:
- - dma-coherent : Present if dma operations are coherent
- - #dma-cells: must be <1>. used to represent the number of integer
- cells in the dmas property of client device.
- - dma-channels: contains the total number of DMA channels supported by the DMAC
- - dma-requests: contains the total number of DMA requests supported by the DMAC
- - arm,pl330-broken-no-flushp: quirk for avoiding to execute DMAFLUSHP
- - arm,pl330-periph-burst: quirk for performing burst transfer only
- - resets: contains an entry for each entry in reset-names.
- See ../reset/reset.txt for details.
- - reset-names: must contain at least "dma", and optional is "dma-ocp".
-
-Example:
-
- pdma0: pdma@12680000 {
- compatible = "arm,pl330", "arm,primecell";
- reg = <0x12680000 0x1000>;
- interrupts = <99>;
- #dma-cells = <1>;
- #dma-channels = <8>;
- #dma-requests = <32>;
- };
-
-Client drivers (device nodes requiring dma transfers from dev-to-mem or
-mem-to-dev) should specify the DMA channel numbers and dma channel names
-as shown below.
-
- [property name] = <[phandle of the dma controller] [dma request id]>;
- [property name] = <[dma channel name]>
-
- where 'dma request id' is the dma request number which is connected
- to the client controller. The 'property name' 'dmas' and 'dma-names'
- as required by the generic dma device tree binding helpers. The dma
- names correspond 1:1 with the dma request ids in the dmas property.
-
- Example: dmas = <&pdma0 12
- &pdma1 11>;
- dma-names = "tx", "rx";
diff --git a/Documentation/devicetree/bindings/dma/dma-controller.yaml b/Documentation/devicetree/bindings/dma/dma-controller.yaml
index 0043b91d..6d37272 100644
--- a/Documentation/devicetree/bindings/dma/dma-controller.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-controller.yaml
@@ -24,10 +24,10 @@
dma: dma-controller@48000000 {
compatible = "ti,omap-sdma";
reg = <0x48000000 0x1000>;
- interrupts = <0 12 0x4
- 0 13 0x4
- 0 14 0x4
- 0 15 0x4>;
+ interrupts = <0 12 0x4>,
+ <0 13 0x4>,
+ <0 14 0x4>,
+ <0 15 0x4>;
#dma-cells = <1>;
dma-channels = <32>;
dma-requests = <127>;
diff --git a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
index dc059d6..3b0b3b9 100644
--- a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
+++ b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
@@ -14,15 +14,23 @@
properties:
compatible:
- enum:
- - ingenic,jz4740-dma
- - ingenic,jz4725b-dma
- - ingenic,jz4760-dma
- - ingenic,jz4760b-dma
- - ingenic,jz4770-dma
- - ingenic,jz4780-dma
- - ingenic,x1000-dma
- - ingenic,x1830-dma
+ oneOf:
+ - enum:
+ - ingenic,jz4740-dma
+ - ingenic,jz4725b-dma
+ - ingenic,jz4760-dma
+ - ingenic,jz4760-bdma
+ - ingenic,jz4760-mdma
+ - ingenic,jz4760b-dma
+ - ingenic,jz4760b-bdma
+ - ingenic,jz4760b-mdma
+ - ingenic,jz4770-dma
+ - ingenic,jz4780-dma
+ - ingenic,x1000-dma
+ - ingenic,x1830-dma
+ - items:
+ - const: ingenic,jz4770-bdma
+ - const: ingenic,jz4760b-bdma
reg:
items:
@@ -36,13 +44,19 @@
maxItems: 1
"#dma-cells":
- const: 2
+ enum: [2, 3]
description: >
DMA clients must use the format described in dma.txt, giving a phandle
- to the DMA controller plus the following 2 integer cells:
+ to the DMA controller plus the following integer cells:
- - Request type: The DMA request type for transfers to/from the
- device on the allocated channel, as defined in the SoC documentation.
+ - Request type: The DMA request type specifies the device endpoint that
+ will be the source or destination of the DMA transfer.
+ If "#dma-cells" is 2, the request type is a single cell, and the
+ direction will be unidirectional (either RX or TX but not both).
+ If "#dma-cells" is 3, the request type has two cells; the first
+ one corresponds to the host to device direction (TX), the second one
+ corresponds to the device to host direction (RX). The DMA channel is
+ then bidirectional.
- Channel: If set to 0xffffffff, any available channel will be allocated
for the client. Otherwise, the exact channel specified will be used.
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
index d8142cb..7c6badf 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
@@ -44,6 +44,10 @@
- items:
- const: renesas,dmac-r8a779a0 # R-Car V3U
+ - items:
+ - const: renesas,dmac-r8a779f0 # R-Car S4-8
+ - const: renesas,rcar-gen4-dmac
+
reg: true
interrupts:
@@ -118,6 +122,7 @@
contains:
enum:
- renesas,dmac-r8a779a0
+ - renesas,rcar-gen4-dmac
then:
properties:
reg:
diff --git a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml
index 79e2414..4324a94 100644
--- a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml
@@ -53,6 +53,9 @@
minimum: 1
maximum: 8
+ resets:
+ maxItems: 1
+
snps,dma-masters:
description: |
Number of AXI masters supported by the hardware.
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index df29d59..08627d9 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -30,6 +30,7 @@
allOf:
- $ref: /schemas/dma/dma-controller.yaml#
+ - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index ea19d12..507d16d 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -25,6 +25,7 @@
allOf:
- $ref: /schemas/dma/dma-controller.yaml#
+ - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/extcon/extcon-usbc-cros-ec.yaml b/Documentation/devicetree/bindings/extcon/extcon-usbc-cros-ec.yaml
index 20e1ccf..2d82b44 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-usbc-cros-ec.yaml
+++ b/Documentation/devicetree/bindings/extcon/extcon-usbc-cros-ec.yaml
@@ -8,7 +8,6 @@
maintainers:
- Benson Leung <bleung@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
On ChromeOS systems with USB Type C ports, the ChromeOS Embedded Controller is
diff --git a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml
index b386e41..6e1c70e 100644
--- a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml
+++ b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml
@@ -10,7 +10,6 @@
maintainers:
- Doug Anderson <dianders@chromium.org>
- Benson Leung <bleung@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
On some ChromeOS board designs we've got a connection to the EC
diff --git a/Documentation/devicetree/bindings/iio/proximity/google,cros-ec-mkbp-proximity.yaml b/Documentation/devicetree/bindings/iio/proximity/google,cros-ec-mkbp-proximity.yaml
index 099b4be..00e3b59 100644
--- a/Documentation/devicetree/bindings/iio/proximity/google,cros-ec-mkbp-proximity.yaml
+++ b/Documentation/devicetree/bindings/iio/proximity/google,cros-ec-mkbp-proximity.yaml
@@ -10,7 +10,6 @@
maintainers:
- Stephen Boyd <swboyd@chromium.org>
- Benson Leung <bleung@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
Google's ChromeOS EC sometimes has the ability to detect user proximity.
diff --git a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml
index 5377b23..e8f137a 100644
--- a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml
+++ b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml
@@ -10,7 +10,6 @@
maintainers:
- Simon Glass <sjg@chromium.org>
- Benson Leung <bleung@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
description: |
Google's ChromeOS EC Keyboard is a simple matrix keyboard
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index dbe7ecc1..7fe1966 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -88,12 +88,6 @@
which can be disabled to suppress events from the button.
type: boolean
- pinctrl-0:
- maxItems: 1
-
- pinctrl-names:
- maxItems: 1
-
required:
- linux,code
diff --git a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
index 1ef849d..e2e6e9a 100644
--- a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
+++ b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
@@ -81,14 +81,12 @@
data-lanes:
description:
Note that 'fsl,imx7-mipi-csi2' only supports up to 2 data lines.
+ minItems: 1
items:
- minItems: 1
- maxItems: 4
- items:
- - const: 1
- - const: 2
- - const: 3
- - const: 4
+ - const: 1
+ - const: 2
+ - const: 3
+ - const: 4
required:
- data-lanes
diff --git a/Documentation/devicetree/bindings/media/nxp,imx8mq-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/nxp,imx8mq-mipi-csi2.yaml
index 9c04fa8..1b3e1c4 100644
--- a/Documentation/devicetree/bindings/media/nxp,imx8mq-mipi-csi2.yaml
+++ b/Documentation/devicetree/bindings/media/nxp,imx8mq-mipi-csi2.yaml
@@ -87,14 +87,12 @@
properties:
data-lanes:
+ minItems: 1
items:
- minItems: 1
- maxItems: 4
- items:
- - const: 1
- - const: 2
- - const: 3
- - const: 4
+ - const: 1
+ - const: 2
+ - const: 3
+ - const: 4
required:
- data-lanes
diff --git a/Documentation/devicetree/bindings/mfd/cirrus,madera.yaml b/Documentation/devicetree/bindings/mfd/cirrus,madera.yaml
index 5dce62a..68c75a5 100644
--- a/Documentation/devicetree/bindings/mfd/cirrus,madera.yaml
+++ b/Documentation/devicetree/bindings/mfd/cirrus,madera.yaml
@@ -245,8 +245,7 @@
interrupt-controller;
#interrupt-cells = <2>;
- interrupts = <&host_irq1>;
- interrupt-parent = <&gic>;
+ interrupts = <4 1 0>;
gpio-controller;
#gpio-cells = <2>;
diff --git a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
index 0faa4da..d1f53bd 100644
--- a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
+++ b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
@@ -8,7 +8,6 @@
maintainers:
- Benson Leung <bleung@chromium.org>
- - Enric Balletbo i Serra <enric.balletbo@collabora.com>
- Guenter Roeck <groeck@chromium.org>
description:
diff --git a/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml b/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
index a4f74be..1e69a5a 100644
--- a/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
+++ b/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
@@ -185,6 +185,9 @@
clock-names = "mclk", "apb_pclk";
};
+ - |
+ #include <dt-bindings/interrupt-controller/irq.h>
+
mmc@80126000 {
compatible = "arm,pl18x", "arm,primecell";
reg = <0x80126000 0x1000>;
@@ -206,12 +209,12 @@
vqmmc-supply = <&vmmci>;
};
+ - |
mmc@101f6000 {
compatible = "arm,pl18x", "arm,primecell";
reg = <0x101f6000 0x1000>;
clocks = <&sdiclk>, <&pclksdi>;
clock-names = "mclk", "apb_pclk";
- interrupt-parent = <&vica>;
interrupts = <22>;
max-frequency = <400000>;
bus-width = <4>;
@@ -226,6 +229,7 @@
vmmc-supply = <&vmmc_regulator>;
};
+ - |
mmc@52007000 {
compatible = "arm,pl18x", "arm,primecell";
arm,primecell-periphid = <0x10153180>;
diff --git a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
index fb547e2..401ab7c 100644
--- a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
+++ b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
@@ -76,33 +76,31 @@
M_CAN user manual for details.
$ref: /schemas/types.yaml#/definitions/int32-array
items:
- items:
- - description: The 'offset' is an address offset of the Message RAM where
- the following elements start from. This is usually set to 0x0 if
- you're using a private Message RAM.
- default: 0
- - description: 11-bit Filter 0-128 elements / 0-128 words
- minimum: 0
- maximum: 128
- - description: 29-bit Filter 0-64 elements / 0-128 words
- minimum: 0
- maximum: 64
- - description: Rx FIFO 0 0-64 elements / 0-1152 words
- minimum: 0
- maximum: 64
- - description: Rx FIFO 1 0-64 elements / 0-1152 words
- minimum: 0
- maximum: 64
- - description: Rx Buffers 0-64 elements / 0-1152 words
- minimum: 0
- maximum: 64
- - description: Tx Event FIFO 0-32 elements / 0-64 words
- minimum: 0
- maximum: 32
- - description: Tx Buffers 0-32 elements / 0-576 words
- minimum: 0
- maximum: 32
- maxItems: 1
+ - description: The 'offset' is an address offset of the Message RAM where
+ the following elements start from. This is usually set to 0x0 if
+ you're using a private Message RAM.
+ default: 0
+ - description: 11-bit Filter 0-128 elements / 0-128 words
+ minimum: 0
+ maximum: 128
+ - description: 29-bit Filter 0-64 elements / 0-128 words
+ minimum: 0
+ maximum: 64
+ - description: Rx FIFO 0 0-64 elements / 0-1152 words
+ minimum: 0
+ maximum: 64
+ - description: Rx FIFO 1 0-64 elements / 0-1152 words
+ minimum: 0
+ maximum: 64
+ - description: Rx Buffers 0-64 elements / 0-1152 words
+ minimum: 0
+ maximum: 64
+ - description: Tx Event FIFO 0-32 elements / 0-64 words
+ minimum: 0
+ maximum: 32
+ - description: Tx Buffers 0-32 elements / 0-576 words
+ minimum: 0
+ maximum: 32
power-domains:
description:
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 47b5f72..34c5463 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -17,9 +17,8 @@
description:
Specifies the MAC address that was assigned to the network device.
$ref: /schemas/types.yaml#/definitions/uint8-array
- items:
- - minItems: 6
- maxItems: 6
+ minItems: 6
+ maxItems: 6
mac-address:
description:
@@ -28,9 +27,8 @@
to the device by the boot program is different from the
local-mac-address property.
$ref: /schemas/types.yaml#/definitions/uint8-array
- items:
- - minItems: 6
- maxItems: 6
+ minItems: 6
+ maxItems: 6
max-frame-size:
$ref: /schemas/types.yaml#/definitions/uint32
@@ -164,33 +162,30 @@
type: array
then:
deprecated: true
- minItems: 1
- maxItems: 1
items:
- items:
- - minimum: 0
- maximum: 31
- description:
- Emulated PHY ID, choose any but unique to the all
- specified fixed-links
+ - minimum: 0
+ maximum: 31
+ description:
+ Emulated PHY ID, choose any but unique to the all
+ specified fixed-links
- - enum: [0, 1]
- description:
- Duplex configuration. 0 for half duplex or 1 for
- full duplex
+ - enum: [0, 1]
+ description:
+ Duplex configuration. 0 for half duplex or 1 for
+ full duplex
- - enum: [10, 100, 1000, 2500, 10000]
- description:
- Link speed in Mbits/sec.
+ - enum: [10, 100, 1000, 2500, 10000]
+ description:
+ Link speed in Mbits/sec.
- - enum: [0, 1]
- description:
- Pause configuration. 0 for no pause, 1 for pause
+ - enum: [0, 1]
+ description:
+ Pause configuration. 0 for no pause, 1 for pause
- - enum: [0, 1]
- description:
- Asymmetric pause configuration. 0 for no asymmetric
- pause, 1 for asymmetric pause
+ - enum: [0, 1]
+ description:
+ Asymmetric pause configuration. 0 for no asymmetric
+ pause, 1 for asymmetric pause
- if:
diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index c00fb0d..020337f 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -410,6 +410,15 @@
The settings and programming routines for internal/external
MDIO are different. Must be included for internal MDIO.
+- fsl,erratum-a009885
+ Usage: optional
+ Value type: <boolean>
+ Definition: Indicates the presence of the A009885
+ erratum describing that the contents of MDIO_DATA may
+ become corrupt unless it is read within 16 MDC cycles
+ of MDIO_CFG[BSY] being cleared, when performing an
+ MDIO read operation.
+
- fsl,erratum-a011043
Usage: optional
Value type: <boolean>
diff --git a/Documentation/devicetree/bindings/net/oxnas-dwmac.txt b/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
index d7117a2..27db496 100644
--- a/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
@@ -9,6 +9,9 @@
- compatible: For the OX820 SoC, it should be :
- "oxsemi,ox820-dwmac" to select glue
- "snps,dwmac-3.512" to select IP version.
+ For the OX810SE SoC, it should be :
+ - "oxsemi,ox810se-dwmac" to select glue
+ - "snps,dwmac-3.512" to select IP version.
- clocks: Should contain phandles to the following clocks
- clock-names: Should contain the following:
diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.yaml b/Documentation/devicetree/bindings/nvmem/nvmem.yaml
index 456fb80..43ed7e3 100644
--- a/Documentation/devicetree/bindings/nvmem/nvmem.yaml
+++ b/Documentation/devicetree/bindings/nvmem/nvmem.yaml
@@ -50,16 +50,15 @@
Offset and size in bytes within the storage device.
bits:
- maxItems: 1
+ $ref: /schemas/types.yaml#/definitions/uint32-array
items:
- items:
- - minimum: 0
- maximum: 7
- description:
- Offset in bit within the address range specified by reg.
- - minimum: 1
- description:
- Size in bit within the address range specified by reg.
+ - minimum: 0
+ maximum: 7
+ description:
+ Offset in bit within the address range specified by reg.
+ - minimum: 1
+ description:
+ Size in bit within the address range specified by reg.
required:
- reg
diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml
index 8002053..5cd512b 100644
--- a/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml
@@ -51,15 +51,6 @@
appropriate of the LOCHNAGARx_PIN_NUM_GPIOS define, see [3].
maxItems: 1
- pinctrl-0:
- description:
- A phandle to the default pinctrl state.
-
- pinctrl-names:
- description:
- A pinctrl state named "default" must be defined.
- const: default
-
pin-settings:
type: object
patternProperties:
diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml
index e50d7ad..c85f759 100644
--- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml
@@ -30,16 +30,6 @@
Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
properties:
- pinctrl-0:
- description:
- A phandle to the node containing the subnodes containing default
- configurations.
-
- pinctrl-names:
- description:
- A pinctrl state named "default" must be defined.
- const: default
-
pin-settings:
description:
One subnode is required to contain the default settings. It
diff --git a/Documentation/devicetree/bindings/power/reset/gpio-restart.yaml b/Documentation/devicetree/bindings/power/reset/gpio-restart.yaml
index 3dd2222..a72d5c7 100644
--- a/Documentation/devicetree/bindings/power/reset/gpio-restart.yaml
+++ b/Documentation/devicetree/bindings/power/reset/gpio-restart.yaml
@@ -43,7 +43,7 @@
priority:
$ref: /schemas/types.yaml#/definitions/uint32
description: |
- A priority ranging from 0 to 255 (default 128) according to the following guidelines:
+ A priority ranging from 0 to 255 (default 129) according to the following guidelines:
0: Restart handler of last resort, with limited restart capabilities.
128: Default restart handler; use if no other restart handler is expected to be available,
@@ -51,7 +51,7 @@
255: Highest priority restart handler, will preempt all other restart handlers.
minimum: 0
maximum: 255
- default: 128
+ default: 129
active-delay:
$ref: /schemas/types.yaml#/definitions/uint32
diff --git a/Documentation/devicetree/bindings/pwm/pwm.yaml b/Documentation/devicetree/bindings/pwm/pwm.yaml
index 2effe6c..3c01f85 100644
--- a/Documentation/devicetree/bindings/pwm/pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/pwm.yaml
@@ -9,6 +9,8 @@
maintainers:
- Thierry Reding <thierry.reding@gmail.com>
+select: false
+
properties:
$nodename:
pattern: "^pwm(@.*|-[0-9a-f])*$"
diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml
index 63e06d9..c635c18 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml
@@ -33,6 +33,9 @@
- qcom,sdm845-adsp-pas
- qcom,sdm845-cdsp-pas
- qcom,sdx55-mpss-pas
+ - qcom,sm6350-adsp-pas
+ - qcom,sm6350-cdsp-pas
+ - qcom,sm6350-mpss-pas
- qcom,sm8150-adsp-pas
- qcom,sm8150-cdsp-pas
- qcom,sm8150-mpss-pas
@@ -158,6 +161,9 @@
- qcom,sc8180x-mpss-pas
- qcom,sdm845-adsp-pas
- qcom,sdm845-cdsp-pas
+ - qcom,sm6350-adsp-pas
+ - qcom,sm6350-cdsp-pas
+ - qcom,sm6350-mpss-pas
- qcom,sm8150-adsp-pas
- qcom,sm8150-cdsp-pas
- qcom,sm8150-mpss-pas
@@ -266,6 +272,8 @@
- qcom,sc8180x-cdsp-pas
- qcom,sdm845-adsp-pas
- qcom,sdm845-cdsp-pas
+ - qcom,sm6350-adsp-pas
+ - qcom,sm6350-cdsp-pas
- qcom,sm8150-adsp-pas
- qcom,sm8150-cdsp-pas
- qcom,sm8150-slpi-pas
@@ -301,6 +309,7 @@
- qcom,sc7280-mpss-pas
- qcom,sc8180x-mpss-pas
- qcom,sdx55-mpss-pas
+ - qcom,sm6350-mpss-pas
- qcom,sm8150-mpss-pas
- qcom,sm8350-mpss-pas
then:
@@ -390,6 +399,23 @@
compatible:
contains:
enum:
+ - qcom,sm6350-cdsp-pas
+ then:
+ properties:
+ power-domains:
+ items:
+ - description: CX power domain
+ - description: MX power domain
+ power-domain-names:
+ items:
+ - const: cx
+ - const: mx
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
- qcom,sm8150-adsp-pas
- qcom,sm8150-cdsp-pas
then:
@@ -405,6 +431,7 @@
enum:
- qcom,sc7280-mpss-pas
- qcom,sdx55-mpss-pas
+ - qcom,sm6350-mpss-pas
- qcom,sm8150-mpss-pas
- qcom,sm8350-mpss-pas
then:
@@ -425,6 +452,7 @@
enum:
- qcom,sc8180x-adsp-pas
- qcom,sc8180x-cdsp-pas
+ - qcom,sm6350-adsp-pas
- qcom,sm8150-slpi-pas
- qcom,sm8250-adsp-pas
- qcom,sm8250-slpi-pas
diff --git a/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml
new file mode 100644
index 0000000..a7d25fa
--- /dev/null
+++ b/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/remoteproc/renesas,rcar-rproc.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Renesas R-Car remote processor controller bindings
+
+maintainers:
+ - Julien Massot <julien.massot@iot.bzh>
+
+description: |
+ This document defines the bindings for the remoteproc component that loads and
+ boots firmwares on the Renesas R-Car family chipset.
+ R-Car gen3 family may have a realtime processor, this processor shares peripheral
+ and RAM with the host processor with the same address map.
+
+properties:
+ compatible:
+ const: renesas,rcar-cr7
+
+ resets:
+ maxItems: 1
+
+ power-domains:
+ maxItems: 1
+
+ memory-region:
+ description:
+ List of phandles to the reserved memory regions associated with the
+ remoteproc device. This is variable and describes the memories shared with
+ the remote processor (e.g. remoteproc firmware and carveouts, rpmsg
+ vrings, ...).
+ (see ../reserved-memory/reserved-memory.yaml)
+
+required:
+ - compatible
+ - resets
+ - memory-region
+ - power-domains
+
+additionalProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/clock/r8a7795-cpg-mssr.h>
+ #include <dt-bindings/power/r8a7795-sysc.h>
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cr7_ram: cr7_ram@40040000 {
+ no-map;
+ reg = <0x0 0x40040000 0x0 0x1fc0000>;
+ };
+ };
+
+ cr7_rproc: cr7 {
+ compatible = "renesas,rcar-cr7";
+ memory-region = <&cr7_ram>;
+ power-domains = <&sysc R8A7795_PD_CR7>;
+ resets = <&cpg 222>;
+ };
+
+...
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml
index 5ec6505..7b56497 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml
@@ -33,9 +33,11 @@
enum:
- ti,j721e-c66-dsp
- ti,j721e-c71-dsp
+ - ti,j721s2-c71-dsp
description:
Use "ti,j721e-c66-dsp" for C66x DSPs on K3 J721E SoCs
Use "ti,j721e-c71-dsp" for C71x DSPs on K3 J721E SoCs
+ Use "ti,j721s2-c71-dsp" for C71x DSPs on K3 J721S2 SoCs
resets:
description: |
@@ -106,6 +108,7 @@
compatible:
enum:
- ti,j721e-c71-dsp
+ - ti,j721s2-c71-dsp
then:
properties:
reg:
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml
index eeef255..d9c7e8c 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml
@@ -38,6 +38,7 @@
- ti,j721e-r5fss
- ti,j7200-r5fss
- ti,am64-r5fss
+ - ti,j721s2-r5fss
power-domains:
description: |
@@ -64,9 +65,9 @@
description: |
Configuration Mode for the Dual R5F cores within the R5F cluster.
Should be either a value of 1 (LockStep mode) or 0 (Split mode) on
- most SoCs (AM65x, J721E, J7200), default is LockStep mode if omitted;
- and should be either a value of 0 (Split mode) or 2 (Single-CPU mode)
- on AM64x SoCs, default is Split mode if omitted.
+ most SoCs (AM65x, J721E, J7200, J721s2), default is LockStep mode if
+ omitted; and should be either a value of 0 (Split mode) or 2
+ (Single-CPU mode) on AM64x SoCs, default is Split mode if omitted.
# R5F Processor Child Nodes:
# ==========================
@@ -104,6 +105,7 @@
- ti,j721e-r5f
- ti,j7200-r5f
- ti,am64-r5f
+ - ti,j721s2-r5f
reg:
items:
diff --git a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
index 29fe39b..d12855e 100644
--- a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
+++ b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
@@ -15,6 +15,7 @@
properties:
compatible:
enum:
+ - epson,rx8804
- epson,rx8900
- microcrystal,rv8803
diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
index 4fba6db..6fa7d9f 100644
--- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
@@ -19,7 +19,14 @@
- qcom,pmk8350-rtc
reg:
- maxItems: 1
+ minItems: 1
+ maxItems: 2
+
+ reg-names:
+ minItems: 1
+ items:
+ - const: rtc
+ - const: alarm
interrupts:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
index 2359f54..764717c 100644
--- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
@@ -127,6 +127,7 @@
st,syscfg = <&pwrcfg 0x00 0x100>;
};
+ - |
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/clock/stm32mp1-clks.h>
rtc@5c004000 {
diff --git a/Documentation/devicetree/bindings/rtc/sunplus,sp7021-rtc.yaml b/Documentation/devicetree/bindings/rtc/sunplus,sp7021-rtc.yaml
new file mode 100644
index 0000000..fd1b3e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/sunplus,sp7021-rtc.yaml
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) Sunplus Co., Ltd. 2021
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/sunplus,sp7021-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sunplus SP7021 Real Time Clock controller
+
+maintainers:
+ - Vincent Shih <vincent.sunplus@gmail.com>
+
+properties:
+ compatible:
+ const: sunplus,sp7021-rtc
+
+ reg:
+ maxItems: 1
+
+ reg-names:
+ items:
+ - const: rtc
+
+ clocks:
+ maxItems: 1
+
+ resets:
+ maxItems: 1
+
+ interrupts:
+ maxItems: 1
+
+required:
+ - compatible
+ - reg
+ - reg-names
+ - clocks
+ - resets
+ - interrupts
+
+additionalProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/interrupt-controller/irq.h>
+
+ rtc: serial@9c003a00 {
+ compatible = "sunplus,sp7021-rtc";
+ reg = <0x9c003a00 0x80>;
+ reg-names = "rtc";
+ clocks = <&clkc 0x12>;
+ resets = <&rstc 0x02>;
+ interrupt-parent = <&intc>;
+ interrupts = <163 IRQ_TYPE_EDGE_RISING>;
+ };
+...
diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.yaml b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
index 2e3628e..84c4d6c 100644
--- a/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
+++ b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
@@ -110,12 +110,6 @@
Internal DMA register base address of the audio
subsystem (used in secondary sound source).
- pinctrl-0:
- description: Should specify pin control groups used for this controller.
-
- pinctrl-names:
- const: default
-
power-domains:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 9af1b0f4..091792b 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -31,7 +31,7 @@
- enum:
# SMBus/I2C Digital Temperature Sensor in 6-Pin SOT with SMBus Alert and Over Temperature Pin
- ad,ad7414
- # ADM9240: Complete System Hardware Monitor for uProcessor-Based Systems
+ # ADM9240: Complete System Hardware Monitor for uProcessor-Based Systems
- ad,adm9240
# AD5110 - Nonvolatile Digital Potentiometer
- adi,ad5110
@@ -43,7 +43,7 @@
- adi,adp5589
# AMS iAQ-Core VOC Sensor
- ams,iaq-core
- # i2c serial eeprom (24cxx)
+ # i2c serial eeprom (24cxx)
- at,24c08
# i2c trusted platform module (TPM)
- atmel,at97sc3204t
@@ -303,9 +303,9 @@
- skyworks,sky81452
# Socionext SynQuacer TPM MMIO module
- socionext,synquacer-tpm-mmio
- # i2c serial eeprom (24cxx)
- - sparkfun,qwiic-joystick
# SparkFun Qwiic Joystick (COM-15168) with i2c interface
+ - sparkfun,qwiic-joystick
+ # i2c serial eeprom (24cxx)
- st,24c256
# Ambient Light Sensor with SMBUS/Two Wire Serial Interface
- taos,tsl2550
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index c48ce3c..294093d 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -25,6 +25,8 @@
# Keep list in alphabetical order.
"^70mai,.*":
description: 70mai Co., Ltd.
+ "^8dev,.*":
+ description: 8devices, UAB
"^abb,.*":
description: ABB
"^abilis,.*":
@@ -441,6 +443,8 @@
description: Freescale Semiconductor
"^fujitsu,.*":
description: Fujitsu Ltd.
+ "^fxtec,.*":
+ description: FX Technology Ltd.
"^gardena,.*":
description: GARDENA GmbH
"^gateworks,.*":
@@ -515,6 +519,8 @@
description: HannStar Display Co.
"^holtek,.*":
description: Holtek Semiconductor, Inc.
+ "^huawei,.*":
+ description: Huawei Technologies Co., Ltd.
"^hugsun,.*":
description: Shenzhen Hugsun Technology Co. Ltd.
"^hwacom,.*":
@@ -1207,6 +1213,8 @@
description: THine Electronics, Inc.
"^thingyjp,.*":
description: thingy.jp
+ "^thundercomm,.*":
+ description: Thundercomm Technology Co., Ltd.
"^ti,.*":
description: Texas Instruments
"^tianma,.*":
@@ -1334,6 +1342,8 @@
description: Wiligear, Ltd.
"^winbond,.*":
description: Winbond Electronics corp.
+ "^wingtech,.*":
+ description: Wingtech Technology Co., Ltd.
"^winlink,.*":
description: WinLink Co., Ltd
"^winstar,.*":
diff --git a/Documentation/driver-api/dmaengine/dmatest.rst b/Documentation/driver-api/dmaengine/dmatest.rst
index ee268d4..cf9859c 100644
--- a/Documentation/driver-api/dmaengine/dmatest.rst
+++ b/Documentation/driver-api/dmaengine/dmatest.rst
@@ -6,6 +6,16 @@
This small document introduces how to test DMA drivers using dmatest module.
+The dmatest module tests DMA memcpy, memset, XOR and RAID6 P+Q operations using
+various lengths and various offsets into the source and destination buffers. It
+will initialize both buffers with a repeatable pattern and verify that the DMA
+engine copies the requested region and nothing more. It will also verify that
+the bytes aren't swapped around, and that the source buffer isn't modified.
+
+The dmatest module can be configured to test a specific channel. It can also
+test multiple channels at the same time, and it can start multiple threads
+competing for the same channel.
+
.. note::
The test suite works only on the channels that have at least one
capability of the following: DMA_MEMCPY (memory-to-memory), DMA_MEMSET
@@ -143,13 +153,14 @@
Allocating Channels
-------------------
-Channels are required to be configured prior to starting the test run.
-Attempting to run the test without configuring the channels will fail.
+Channels do not need to be configured prior to starting a test run. Attempting
+to run the test without configuring the channels will result in testing any
+channels that are available.
Example::
% echo 1 > /sys/module/dmatest/parameters/run
- dmatest: Could not start test, no channels configured
+ dmatest: No channels configured, continue with any
Channels are registered using the "channel" parameter. Channels can be requested by their
name, once requested, the channel is registered and a pending thread is added to the test list.
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index ddb0a81..0072c9c 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -162,6 +162,29 @@
- The device is able to do memory to memory copies
+- - DMA_MEMCPY_SG
+
+ - The device supports memory to memory scatter-gather transfers.
+
+ - Even though a plain memcpy can look like a particular case of a
+ scatter-gather transfer, with a single chunk to copy, it's a distinct
+ transaction type in the mem2mem transfer case. This is because some very
+ simple devices might be able to do contiguous single-chunk memory copies,
+ but have no support for more complex SG transfers.
+
+ - No matter what the overall size of the combined chunks for source and
+ destination is, only as many bytes as the smallest of the two will be
+ transmitted. That means the number and size of the scatter-gather buffers in
+ both lists need not be the same, and that the operation functionally is
+ equivalent to a ``strncpy`` where the ``count`` argument equals the smallest
+ total size of the two scatter-gather list buffers.
+
+ - It's usually used for copying pixel data between host memory and
+ memory-mapped GPU device memory, such as found on modern PCI video graphics
+ cards. The most immediate example is the OpenGL API function
+ ``glReadPielx()``, which might require a verbatim copy of a huge framebuffer
+ from local device memory onto host memory.
+
- DMA_XOR
- The device is able to perform XOR operations on memory areas
diff --git a/Documentation/driver-api/firewire.rst b/Documentation/driver-api/firewire.rst
index 94a2d7f..d3cfa73 100644
--- a/Documentation/driver-api/firewire.rst
+++ b/Documentation/driver-api/firewire.rst
@@ -19,7 +19,7 @@
Firewire char device data structures
====================================
-.. include:: /ABI/stable/firewire-cdev
+.. include:: ../ABI/stable/firewire-cdev
:literal:
.. kernel-doc:: include/uapi/linux/firewire-cdev.h
@@ -28,7 +28,7 @@
Firewire device probing and sysfs interfaces
============================================
-.. include:: /ABI/stable/sysfs-bus-firewire
+.. include:: ../ABI/stable/sysfs-bus-firewire
:literal:
.. kernel-doc:: drivers/firewire/core-device.c
diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst
index 7d2ef4e..4942e01 100644
--- a/Documentation/filesystems/ceph.rst
+++ b/Documentation/filesystems/ceph.rst
@@ -82,7 +82,7 @@
The basic mount syntax is::
- # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+ # mount -t ceph user@fsid.fs_name=/[subdir] mnt -o mon_addr=monip1[:port][/monip2[:port]]
You only need to specify a single monitor, as the client will get the
full list when it connects. (However, if the monitor you specify
@@ -90,16 +90,35 @@
off if the monitor is using the default. So if the monitor is at
1.2.3.4::
- # mount -t ceph 1.2.3.4:/ /mnt/ceph
+ # mount -t ceph cephuser@07fe3187-00d9-42a3-814b-72a4d5e7d5be.cephfs=/ /mnt/ceph -o mon_addr=1.2.3.4
is sufficient. If /sbin/mount.ceph is installed, a hostname can be
-used instead of an IP address.
+used instead of an IP address and the cluster FSID can be left out
+(as the mount helper will fill it in by reading the ceph configuration
+file)::
+ # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=mon-addr
+Multiple monitor addresses can be passed by separating each address with a slash (`/`)::
+
+ # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=192.168.1.100/192.168.1.101
+
+When using the mount helper, monitor address can be read from ceph
+configuration file if available. Note that, the cluster FSID (passed as part
+of the device string) is validated by checking it with the FSID reported by
+the monitor.
Mount Options
=============
+ mon_addr=ip_address[:port][/ip_address[:port]]
+ Monitor address to the cluster. This is used to bootstrap the
+ connection to the cluster. Once connection is established, the
+ monitor addresses in the monitor map are followed.
+
+ fsid=cluster-id
+ FSID of the cluster (from `ceph fsid` command).
+
ip=A.B.C.D[:N]
Specify the IP and/or port the client should bind to locally.
There is normally not much reason to do this. If the IP is not
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index d7b8469..4a2426f 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -198,6 +198,7 @@
FAULT_WRITE_IO 0x000004000
FAULT_SLAB_ALLOC 0x000008000
FAULT_DQUOT_INIT 0x000010000
+ FAULT_LOCK_OP 0x000020000
=================== ===========
mode=%s Control block allocation mode which supports "adaptive"
and "lfs". In "lfs" mode, there should be no random
diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst
index 98c2418..93a5b6e 100644
--- a/Documentation/kbuild/kconfig-language.rst
+++ b/Documentation/kbuild/kconfig-language.rst
@@ -176,7 +176,7 @@
y y y Y/m/n
n m n N/m
m m m M/n
- y m n M/n
+ y m m M/n
y n * N
=== === ============= ==============
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index cf908d7..a337e8e 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -30,7 +30,7 @@
Program Minimal version Command to check the version
====================== =============== ========================================
GNU C 5.1 gcc --version
-Clang/LLVM (optional) 10.0.1 clang --version
+Clang/LLVM (optional) 11.0.0 clang --version
GNU make 3.81 make --version
binutils 2.23 ld -v
flex 2.5.35 flex --version
diff --git a/Documentation/riscv/vm-layout.rst b/Documentation/riscv/vm-layout.rst
index b7f9893..1bd687b 100644
--- a/Documentation/riscv/vm-layout.rst
+++ b/Documentation/riscv/vm-layout.rst
@@ -47,12 +47,12 @@
| Kernel-space virtual memory, shared between all processes:
____________________________________________________________|___________________________________________________________
| | | |
- ffffffc000000000 | -256 GB | ffffffc7ffffffff | 32 GB | kasan
- ffffffcefee00000 | -196 GB | ffffffcefeffffff | 2 MB | fixmap
- ffffffceff000000 | -196 GB | ffffffceffffffff | 16 MB | PCI io
- ffffffcf00000000 | -196 GB | ffffffcfffffffff | 4 GB | vmemmap
- ffffffd000000000 | -192 GB | ffffffdfffffffff | 64 GB | vmalloc/ioremap space
- ffffffe000000000 | -128 GB | ffffffff7fffffff | 124 GB | direct mapping of all physical memory
+ ffffffc6fee00000 | -228 GB | ffffffc6feffffff | 2 MB | fixmap
+ ffffffc6ff000000 | -228 GB | ffffffc6ffffffff | 16 MB | PCI io
+ ffffffc700000000 | -228 GB | ffffffc7ffffffff | 4 GB | vmemmap
+ ffffffc800000000 | -224 GB | ffffffd7ffffffff | 64 GB | vmalloc/ioremap space
+ ffffffd800000000 | -160 GB | fffffff6ffffffff | 124 GB | direct mapping of all physical memory
+ fffffff700000000 | -36 GB | fffffffeffffffff | 32 GB | kasan
__________________|____________|__________________|_________|____________________________________________________________
|
|
diff --git a/Documentation/staging/tee.rst b/Documentation/staging/tee.rst
index 3c63d8d..498343c 100644
--- a/Documentation/staging/tee.rst
+++ b/Documentation/staging/tee.rst
@@ -255,7 +255,7 @@
+--------------------------+ +---------+--------------------+
At the lowest level (in x86), the AMD Secure Processor (ASP) driver uses the
-CPU to PSP mailbox regsister to submit commands to the PSP. The format of the
+CPU to PSP mailbox register to submit commands to the PSP. The format of the
command buffer is opaque to the ASP driver. It's role is to submit commands to
the secure processor and return results to AMD-TEE driver. The interface
between AMD-TEE driver and AMD Secure Processor driver can be found in [6].
@@ -290,7 +290,7 @@
The GlobalPlatform TEE Client API [5] can be used by the user space (client) to
talk to AMD's TEE. AMD's TEE provides a secure environment for loading, opening
-a session, invoking commands and clossing session with TA.
+a session, invoking commands and closing session with TA.
References
==========
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index b3166c4..45b8c56 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -3370,7 +3370,7 @@
Instances
---------
-In the tracefs tracing directory is a directory called "instances".
+In the tracefs tracing directory, there is a directory called "instances".
This directory can have new directories created inside of it using
mkdir, and removing directories with rmdir. The directory created
with mkdir in this directory will already contain files and other
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index cfe6ccc..687efcf 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -367,6 +367,7 @@
<mailto:aherrman@de.ibm.com>
0xE5 00-3F linux/fuse.h
0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver
+0xEE 00-09 uapi/linux/pfrut.h Platform Firmware Runtime Update and Telemetry
0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development)
<mailto:thomas@winischhofer.net>
0xF6 all LTTng Linux Trace Toolkit Next Generation
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d3791a1..bb8cfdd 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5545,8 +5545,8 @@
The Stats Data block contains an array of 64-bit values in the same order
as the descriptors in Descriptors block.
-4.42 KVM_GET_XSAVE2
-------------------
+4.134 KVM_GET_XSAVE2
+--------------------
:Capability: KVM_CAP_XSAVE2
:Architectures: x86
@@ -7363,7 +7363,7 @@
limit the attack surface on KVM's MSR emulation code.
8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
------------------------------
+-------------------------------------
Architectures: x86
diff --git a/MAINTAINERS b/MAINTAINERS
index a58544f..6c08cbe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4467,7 +4467,6 @@
S: Maintained
F: Documentation/admin-guide/module-signing.rst
F: certs/
-F: scripts/extract-cert.c
F: scripts/sign-file.c
CFAG12864B LCD DRIVER
@@ -16400,7 +16399,6 @@
F: fs/reiserfs/
REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM
-M: Ohad Ben-Cohen <ohad@wizery.com>
M: Bjorn Andersson <bjorn.andersson@linaro.org>
M: Mathieu Poirier <mathieu.poirier@linaro.org>
L: linux-remoteproc@vger.kernel.org
@@ -16414,7 +16412,6 @@
F: include/linux/remoteproc/
REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM
-M: Ohad Ben-Cohen <ohad@wizery.com>
M: Bjorn Andersson <bjorn.andersson@linaro.org>
M: Mathieu Poirier <mathieu.poirier@linaro.org>
L: linux-remoteproc@vger.kernel.org
@@ -16810,6 +16807,7 @@
M: Vasily Gorbik <gor@linux.ibm.com>
M: Christian Borntraeger <borntraeger@linux.ibm.com>
R: Alexander Gordeev <agordeev@linux.ibm.com>
+R: Sven Schnelle <svens@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
@@ -18493,6 +18491,13 @@
S: Maintained
F: drivers/net/ethernet/dlink/sundance.c
+SUNPLUS RTC DRIVER
+M: Vincent Shih <vincent.sunplus@gmail.com>
+L: linux-rtc@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/rtc/sunplus,sp7021-rtc.yaml
+F: drivers/rtc/rtc-sunplus.c
+
SUPERH
M: Yoshinori Sato <ysato@users.sourceforge.jp>
M: Rich Felker <dalias@libc.org>
@@ -20379,6 +20384,7 @@
M: Jason Wang <jasowang@redhat.com>
L: virtualization@lists.linux-foundation.org
S: Maintained
+F: Documentation/ABI/testing/sysfs-bus-vdpa
F: Documentation/devicetree/bindings/virtio/
F: drivers/block/virtio_blk.c
F: drivers/crypto/virtio/
diff --git a/Makefile b/Makefile
index 0fc511a..3f07f0f 100644
--- a/Makefile
+++ b/Makefile
@@ -1278,15 +1278,6 @@
$(Q)$(MAKE) $(hdr-inst)=include/uapi
$(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
-# Deprecated. It is no-op now.
-PHONY += headers_check
-headers_check:
- @echo >&2 "=================== WARNING ==================="
- @echo >&2 "Since Linux 5.5, 'make headers_check' is no-op,"
- @echo >&2 "and will be removed after Linux 5.15 release."
- @echo >&2 "Please remove headers_check from your scripts."
- @echo >&2 "==============================================="
-
ifdef CONFIG_HEADERS_INSTALL
prepare: headers
endif
@@ -1497,7 +1488,7 @@
debian snap tar-install \
.config .config.old .version \
Module.symvers \
- certs/signing_key.pem certs/signing_key.x509 \
+ certs/signing_key.pem \
certs/x509.genkey \
vmlinux-gdb.py \
*.spec
@@ -1723,9 +1714,9 @@
# now expand this into a simple variable to reduce the cost of shell evaluations
prepare: CC_VERSION_TEXT := $(CC_VERSION_TEXT)
prepare:
- @if [ "$(CC_VERSION_TEXT)" != $(CONFIG_CC_VERSION_TEXT) ]; then \
+ @if [ "$(CC_VERSION_TEXT)" != "$(CONFIG_CC_VERSION_TEXT)" ]; then \
echo >&2 "warning: the compiler differs from the one used to build the kernel"; \
- echo >&2 " The kernel was built by: "$(CONFIG_CC_VERSION_TEXT); \
+ echo >&2 " The kernel was built by: $(CONFIG_CC_VERSION_TEXT)"; \
echo >&2 " You are using: $(CC_VERSION_TEXT)"; \
fi
diff --git a/arch/Kconfig b/arch/Kconfig
index 5a16923..678a807 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -648,8 +648,7 @@
config HAS_LTO_CLANG
def_bool y
- # Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
- depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD && AS_IS_LLVM
+ depends on CC_IS_CLANG && LD_IS_LLD && AS_IS_LLVM
depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
depends on ARCH_SUPPORTS_LTO_CLANG
@@ -998,6 +997,10 @@
depends on !PAGE_SIZE_64KB
depends on !PARISC_PAGE_SIZE_64KB
depends on !PPC_64K_PAGES
+ depends on PAGE_SIZE_LESS_THAN_256KB
+
+config PAGE_SIZE_LESS_THAN_256KB
+ def_bool y
depends on !PPC_256K_PAGES
depends on !PAGE_SIZE_256KB
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index ce30779..fb30253 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -80,7 +80,12 @@ init_rtc_epoch(void)
static int
alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
- mc146818_get_time(tm);
+ int ret = mc146818_get_time(tm);
+
+ if (ret < 0) {
+ dev_err_ratelimited(dev, "unable to read current time\n");
+ return ret;
+ }
/* Adjust for non-default epochs. It's easier to depend on the
generic __get_rtc_time and adjust the epoch here than create
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index f252e7b..efc54f3 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -14,10 +14,10 @@
tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT) := -mcpu=arc700
tune-mcpu-def-$(CONFIG_ISA_ARCV2) := -mcpu=hs38
-ifeq ($(CONFIG_ARC_TUNE_MCPU),"")
+ifeq ($(CONFIG_ARC_TUNE_MCPU),)
cflags-y += $(tune-mcpu-def-y)
else
-tune-mcpu := $(shell echo $(CONFIG_ARC_TUNE_MCPU))
+tune-mcpu := $(CONFIG_ARC_TUNE_MCPU)
ifneq ($(call cc-option,$(tune-mcpu)),)
cflags-y += $(tune-mcpu)
else
diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile
index 8483a86..4237aa5 100644
--- a/arch/arc/boot/dts/Makefile
+++ b/arch/arc/boot/dts/Makefile
@@ -2,8 +2,8 @@
# Built-in dtb
builtindtb-y := nsim_700
-ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),"")
- builtindtb-y := $(patsubst "%",%,$(CONFIG_ARC_BUILTIN_DTB_NAME))
+ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),)
+ builtindtb-y := $(CONFIG_ARC_BUILTIN_DTB_NAME)
endif
obj-y += $(builtindtb-y).dtb.o
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 863d63a..0d63e56 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -50,8 +50,12 @@
* are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
*
* Noted at the time of Abilis Timer List corruption
- * Orig Bug + Rejected solution : https://lkml.org/lkml/2013/3/29/67
- * Reasoning : https://lkml.org/lkml/2013/4/8/15
+ *
+ * Orig Bug + Rejected solution:
+ * https://lore.kernel.org/lkml/1364553218-31255-1-git-send-email-vgupta@synopsys.com
+ *
+ * Reasoning:
+ * https://lore.kernel.org/lkml/CA+55aFyFWjpSVQM6M266tKrG_ZXJzZ-nYejpmXYQXbrr42mGPQ@mail.gmail.com
*
******************************************************************/
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index e1971d3..4c919c0 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -63,166 +63,4 @@ struct arc_reg_cc_build {
#define PERF_COUNT_ARC_HW_MAX (PERF_COUNT_HW_MAX + 8)
-/*
- * Some ARC pct quirks:
- *
- * PERF_COUNT_HW_STALLED_CYCLES_BACKEND
- * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
- * The ARC 700 can either measure stalls per pipeline stage, or all stalls
- * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND
- * and all pipeline flushes (e.g. caused by mispredicts, etc.) to
- * STALLED_CYCLES_FRONTEND.
- *
- * We could start multiple performance counters and combine everything
- * afterwards, but that makes it complicated.
- *
- * Note that I$ cache misses aren't counted by either of the two!
- */
-
-/*
- * ARC PCT has hardware conditions with fixed "names" but variable "indexes"
- * (based on a specific RTL build)
- * Below is the static map between perf generic/arc specific event_id and
- * h/w condition names.
- * At the time of probe, we loop thru each index and find it's name to
- * complete the mapping of perf event_id to h/w index as latter is needed
- * to program the counter really
- */
-static const char * const arc_pmu_ev_hw_map[] = {
- /* count cycles */
- [PERF_COUNT_HW_CPU_CYCLES] = "crun",
- [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun",
- [PERF_COUNT_HW_BUS_CYCLES] = "crun",
-
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush",
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall",
-
- /* counts condition */
- [PERF_COUNT_HW_INSTRUCTIONS] = "iall",
- /* All jump instructions that are taken */
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
-#ifdef CONFIG_ISA_ARCV2
- [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
-#else
- [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */
- [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
-#endif
- [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */
- [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */
-
- [PERF_COUNT_ARC_DCLM] = "dclm", /* D-cache Load Miss */
- [PERF_COUNT_ARC_DCSM] = "dcsm", /* D-cache Store Miss */
- [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */
- [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */
- [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */
-
- [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */
- [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */
-};
-
-#define C(_x) PERF_COUNT_HW_CACHE_##_x
-#define CACHE_OP_UNSUPPORTED 0xffff
-
-static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
- [C(L1D)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
- [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = PERF_COUNT_ARC_STC,
- [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = PERF_COUNT_HW_INSTRUCTIONS,
- [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
- [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB,
- },
- /* DTLB LD/ST Miss not segregated by h/w*/
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS,
- [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(NODE)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
#endif /* __ASM_PERF_EVENT_H */
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index c0942c2..d36863e 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -99,8 +99,8 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
/*
* _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
- * syscall, so all that reamins to be tested is _TIF_WORK_MASK
+ * SYSCALL_TRACE is anyway separately/unconditionally tested right after a
+ * syscall, so all that remains to be tested is _TIF_WORK_MASK
*/
#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 145722f..adff957 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -17,6 +17,168 @@
/* HW holds 8 symbols + one for null terminator */
#define ARCPMU_EVENT_NAME_LEN 9
+/*
+ * Some ARC pct quirks:
+ *
+ * PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+ * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+ * The ARC 700 can either measure stalls per pipeline stage, or all stalls
+ * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND
+ * and all pipeline flushes (e.g. caused by mispredicts, etc.) to
+ * STALLED_CYCLES_FRONTEND.
+ *
+ * We could start multiple performance counters and combine everything
+ * afterwards, but that makes it complicated.
+ *
+ * Note that I$ cache misses aren't counted by either of the two!
+ */
+
+/*
+ * ARC PCT has hardware conditions with fixed "names" but variable "indexes"
+ * (based on a specific RTL build)
+ * Below is the static map between perf generic/arc specific event_id and
+ * h/w condition names.
+ * At the time of probe, we loop thru each index and find it's name to
+ * complete the mapping of perf event_id to h/w index as latter is needed
+ * to program the counter really
+ */
+static const char * const arc_pmu_ev_hw_map[] = {
+ /* count cycles */
+ [PERF_COUNT_HW_CPU_CYCLES] = "crun",
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun",
+ [PERF_COUNT_HW_BUS_CYCLES] = "crun",
+
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush",
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall",
+
+ /* counts condition */
+ [PERF_COUNT_HW_INSTRUCTIONS] = "iall",
+ /* All jump instructions that are taken */
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
+#ifdef CONFIG_ISA_ARCV2
+ [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
+#else
+ [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */
+ [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
+#endif
+ [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */
+ [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */
+
+ [PERF_COUNT_ARC_DCLM] = "dclm", /* D-cache Load Miss */
+ [PERF_COUNT_ARC_DCSM] = "dcsm", /* D-cache Store Miss */
+ [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */
+ [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */
+ [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */
+
+ [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */
+ [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */
+};
+
+#define C(_x) PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED 0xffff
+
+static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
+ [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PERF_COUNT_ARC_STC,
+ [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PERF_COUNT_HW_INSTRUCTIONS,
+ [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
+ [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB,
+ },
+ /* DTLB LD/ST Miss not segregated by h/w*/
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS,
+ [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
enum arc_pmu_attr_groups {
ARCPMU_ATTR_GR_EVENTS,
ARCPMU_ATTR_GR_FORMATS,
@@ -328,7 +490,7 @@ static void arc_pmu_stop(struct perf_event *event, int flags)
}
if (!(event->hw.state & PERF_HES_STOPPED)) {
- /* stop ARC pmu here */
+ /* stop hw counter here */
write_aux_reg(ARC_REG_PCT_INDEX, idx);
/* condition code #0 is always "never" */
@@ -361,7 +523,7 @@ static int arc_pmu_add(struct perf_event *event, int flags)
{
struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
+ int idx;
idx = ffz(pmu_cpu->used_mask[0]);
if (idx == arc_pmu->n_counters)
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 9e28058..200270a 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -245,14 +245,9 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
{
struct eh_frame_hdr_table_entry *e1 = p1;
struct eh_frame_hdr_table_entry *e2 = p2;
- unsigned long v;
- v = e1->start;
- e1->start = e2->start;
- e2->start = v;
- v = e1->fde;
- e1->fde = e2->fde;
- e2->fde = v;
+ swap(e1->start, e2->start);
+ swap(e1->fde, e2->fde);
}
static void init_unwind_hdr(struct unwind_table *table,
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 517988e..2a7fbbb 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -32,7 +32,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
/*
* Cache operations depending on function and direction argument, inspired by
- * https://lkml.org/lkml/2018/5/18/979
+ * https://lore.kernel.org/lkml/20180518175004.GF17671@n2100.armlinux.org.uk
* "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
* dma-mapping: provide a generic dma-noncoherent implementation)"
*
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index 63ea5a6..b821df7 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -50,7 +50,7 @@ static void __init axs10x_enable_gpio_intc_wire(void)
* Current implementation of "irq-dw-apb-ictl" driver doesn't work well
* with stacked INTCs. In particular problem happens if its master INTC
* not yet instantiated. See discussion here -
- * https://lkml.org/lkml/2015/3/4/755
+ * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com
*
* So setup the first gpio block as a passive pass thru and hide it from
* DT hardware topology - connect MB intc directly to cpu intc
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index b3ea1fa..c4a875b 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -52,7 +52,7 @@ static void __init hsdk_enable_gpio_intc_wire(void)
* Current implementation of "irq-dw-apb-ictl" driver doesn't work well
* with stacked INTCs. In particular problem happens if its master INTC
* not yet instantiated. See discussion here -
- * https://lkml.org/lkml/2015/3/4/755
+ * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com
*
* So setup the first gpio block as a passive pass thru and hide it from
* DT hardware topology - connect intc directly to cpu intc
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index cb9e48d..976315d 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -66,8 +66,6 @@
config UNWINDER_ARM
bool "ARM EABI stack unwinder"
depends on AEABI && !FUNCTION_GRAPH_TRACER
- # https://github.com/ClangBuiltLinux/linux/issues/732
- depends on !LD_IS_LLD || LLD_VERSION >= 110000
select ARM_UNWIND
help
This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 74d2f14..954eee8 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -76,10 +76,10 @@
CPPFLAGS_vmlinux.lds += -DMALLOC_SIZE="$(MALLOC_SIZE)"
compress-$(CONFIG_KERNEL_GZIP) = gzip
-compress-$(CONFIG_KERNEL_LZO) = lzo
-compress-$(CONFIG_KERNEL_LZMA) = lzma
-compress-$(CONFIG_KERNEL_XZ) = xzkern
-compress-$(CONFIG_KERNEL_LZ4) = lz4
+compress-$(CONFIG_KERNEL_LZO) = lzo_with_size
+compress-$(CONFIG_KERNEL_LZMA) = lzma_with_size
+compress-$(CONFIG_KERNEL_XZ) = xzkern_with_size
+compress-$(CONFIG_KERNEL_LZ4) = lz4_with_size
libfdt_objs := fdt_rw.o fdt_ro.o fdt_wip.o fdt.o
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f6e333b..dc10d26 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1136,6 +1136,10 @@
select GENERIC_ARCH_NUMA
select ACPI_NUMA if ACPI
select OF_NUMA
+ select HAVE_SETUP_PER_CPU_AREA
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK
+ select NEED_PER_CPU_PAGE_FIRST_CHUNK
+ select USE_PERCPU_NUMA_NODE_ID
help
Enable NUMA (Non-Uniform Memory Access) support.
@@ -1152,22 +1156,6 @@
Specify the maximum number of NUMA Nodes available on the target
system. Increases memory reserved to accommodate various tables.
-config USE_PERCPU_NUMA_NODE_ID
- def_bool y
- depends on NUMA
-
-config HAVE_SETUP_PER_CPU_AREA
- def_bool y
- depends on NUMA
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y
- depends on NUMA
-
-config NEED_PER_CPU_PAGE_FIRST_CHUNK
- def_bool y
- depends on NUMA
-
source "kernel/Kconfig.hz"
config ARCH_SPARSEMEM_ENABLE
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index d955ade..5d460f6 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -249,7 +249,7 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr, \
" mov %" #w "[tmp], %" #w "[old]\n" \
" cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n" \
" mov %" #w "[ret], %" #w "[tmp]" \
- : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr), \
+ : [ret] "+r" (x0), [v] "+Q" (*(u##sz *)ptr), \
[tmp] "=&r" (tmp) \
: [old] "r" (x1), [new] "r" (x2) \
: cl); \
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index f9bef42..497acf1 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -243,7 +243,7 @@ static inline void __cmpwait_case_##sz(volatile void *ptr, \
" cbnz %" #w "[tmp], 1f\n" \
" wfe\n" \
"1:" \
- : [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr) \
+ : [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr) \
: [val] "r" (val)); \
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index a883443..db63cc8 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -172,7 +172,7 @@ int pfn_is_map_memory(unsigned long pfn)
}
EXPORT_SYMBOL(pfn_is_map_memory);
-static phys_addr_t memory_limit = PHYS_ADDR_MAX;
+static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX;
/*
* Limit the memory size that was specified via FDT.
diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile
index 5942793..6ab2fa5 100644
--- a/arch/h8300/boot/compressed/Makefile
+++ b/arch/h8300/boot/compressed/Makefile
@@ -30,9 +30,11 @@
suffix-$(CONFIG_KERNEL_GZIP) := gzip
suffix-$(CONFIG_KERNEL_LZO) := lzo
+compress-$(CONFIG_KERNEL_GZIP) := gzip
+compress-$(CONFIG_KERNEL_LZO) := lzo_with_size
$(obj)/vmlinux.bin.$(suffix-y): $(obj)/vmlinux.bin FORCE
- $(call if_changed,$(suffix-y))
+ $(call if_changed,$(compress-y))
LDFLAGS_piggy.o := -r --format binary --oformat elf32-h8300-linux -T
OBJCOPYFLAGS := -O binary
diff --git a/arch/h8300/boot/dts/Makefile b/arch/h8300/boot/dts/Makefile
index 69fcd81..c36bbd1 100644
--- a/arch/h8300/boot/dts/Makefile
+++ b/arch/h8300/boot/dts/Makefile
@@ -1,9 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-ifneq '$(CONFIG_H8300_BUILTIN_DTB)' '""'
-BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_H8300_BUILTIN_DTB)).dtb.o
-endif
-
-obj-y += $(BUILTIN_DTB)
+obj-y += $(addsuffix .dtb.o, $(CONFIG_H8300_BUILTIN_DTB))
dtb-$(CONFIG_H8300H_SIM) := h8300h_sim.dtb
dtb-$(CONFIG_H8S_SIM) := h8s_sim.dtb
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1e33666..7039528 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -32,6 +32,7 @@
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_DYNAMIC_FTRACE if (!ITANIUM)
select HAVE_FUNCTION_TRACER
+ select HAVE_SETUP_PER_CPU_AREA
select TTY
select HAVE_ARCH_TRACEHOOK
select HAVE_VIRT_CPU_ACCOUNTING
@@ -88,9 +89,6 @@
bool
default y
-config HAVE_SETUP_PER_CPU_AREA
- def_bool y
-
config DMI
bool
default y
@@ -292,6 +290,7 @@
bool "NUMA support"
depends on !FLATMEM
select SMP
+ select USE_PERCPU_NUMA_NODE_ID
help
Say Y to compile the kernel to support NUMA (Non-Uniform Memory
Access). This option is for configuring high-end multiprocessor
@@ -311,10 +310,6 @@
def_bool y
depends on NUMA
-config USE_PERCPU_NUMA_NODE_ID
- def_bool y
- depends on NUMA
-
config HAVE_MEMORYLESS_NODES
def_bool NUMA
diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile
index e775a69..1826d9c 100644
--- a/arch/microblaze/Makefile
+++ b/arch/microblaze/Makefile
@@ -5,10 +5,10 @@
# What CPU version are we building for, and crack it open
# as major.minor.rev
-CPU_VER := $(shell echo $(CONFIG_XILINX_MICROBLAZE0_HW_VER))
-CPU_MAJOR := $(shell echo $(CPU_VER) | cut -d '.' -f 1)
-CPU_MINOR := $(shell echo $(CPU_VER) | cut -d '.' -f 2)
-CPU_REV := $(shell echo $(CPU_VER) | cut -d '.' -f 3)
+CPU_VER := $(CONFIG_XILINX_MICROBLAZE0_HW_VER)
+CPU_MAJOR := $(word 1, $(subst ., , $(CPU_VER)))
+CPU_MINOR := $(word 2, $(subst ., , $(CPU_VER)))
+CPU_REV := $(word 3, $(subst ., , $(CPU_VER)))
export CPU_VER CPU_MAJOR CPU_MINOR CPU_REV
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 3dd8c46..edf6c15 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2674,6 +2674,8 @@
bool "NUMA Support"
depends on SYS_SUPPORTS_NUMA
select SMP
+ select HAVE_SETUP_PER_CPU_AREA
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK
help
Say Y to compile the kernel to support NUMA (Non-Uniform Memory
Access). This option improves performance on systems with more
@@ -2684,14 +2686,6 @@
config SYS_SUPPORTS_NUMA
bool
-config HAVE_SETUP_PER_CPU_AREA
- def_bool y
- depends on NUMA
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y
- depends on NUMA
-
config RELOCATABLE
bool "Relocatable kernel"
depends on SYS_SUPPORTS_RELOCATABLE
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 8b03ef1..5a15d51 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -64,12 +64,12 @@
$(call if_changed,objcopy)
tool_$(CONFIG_KERNEL_GZIP) = gzip
-tool_$(CONFIG_KERNEL_BZIP2) = bzip2
-tool_$(CONFIG_KERNEL_LZ4) = lz4
-tool_$(CONFIG_KERNEL_LZMA) = lzma
-tool_$(CONFIG_KERNEL_LZO) = lzo
-tool_$(CONFIG_KERNEL_XZ) = xzkern
-tool_$(CONFIG_KERNEL_ZSTD) = zstd22
+tool_$(CONFIG_KERNEL_BZIP2) = bzip2_with_size
+tool_$(CONFIG_KERNEL_LZ4) = lz4_with_size
+tool_$(CONFIG_KERNEL_LZMA) = lzma_with_size
+tool_$(CONFIG_KERNEL_LZO) = lzo_with_size
+tool_$(CONFIG_KERNEL_XZ) = xzkern_with_size
+tool_$(CONFIG_KERNEL_ZSTD) = zstd22_with_size
targets += vmlinux.bin.z
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 325e155..5a80028 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -519,17 +519,9 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
return node_distance(cpu_to_node(from), cpu_to_node(to));
}
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
- size_t align)
+static int __init pcpu_cpu_to_node(int cpu)
{
- return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
- MEMBLOCK_ALLOC_ACCESSIBLE,
- cpu_to_node(cpu));
-}
-
-static void __init pcpu_fc_free(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
+ return cpu_to_node(cpu);
}
void __init setup_per_cpu_areas(void)
@@ -545,7 +537,7 @@ void __init setup_per_cpu_areas(void)
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
pcpu_cpu_distance,
- pcpu_fc_alloc, pcpu_fc_free);
+ pcpu_cpu_to_node);
if (rc < 0)
panic("Failed to initialize percpu areas.");
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 797ad9b..b33d5d8 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -31,12 +31,6 @@
core-$(CONFIG_FPU) += arch/nds32/math-emu/
libs-y += arch/nds32/lib/
-ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
-BUILTIN_DTB := y
-else
-BUILTIN_DTB := n
-endif
-
ifdef CONFIG_CPU_LITTLE_ENDIAN
KBUILD_CFLAGS += $(call cc-option, -EL)
KBUILD_AFLAGS += $(call cc-option, -EL)
diff --git a/arch/nds32/boot/dts/Makefile b/arch/nds32/boot/dts/Makefile
index f84bd52..4fc6956 100644
--- a/arch/nds32/boot/dts/Makefile
+++ b/arch/nds32/boot/dts/Makefile
@@ -1,7 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
-BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_NDS32_BUILTIN_DTB)).dtb.o
-else
-BUILTIN_DTB :=
-endif
-obj-$(CONFIG_OF) += $(BUILTIN_DTB)
+obj-$(CONFIG_OF) += $(addsuffix .dtb.o, $(CONFIG_NDS32_BUILTIN_DTB))
diff --git a/arch/nios2/boot/dts/Makefile b/arch/nios2/boot/dts/Makefile
index a91a0b0..e9e31bb 100644
--- a/arch/nios2/boot/dts/Makefile
+++ b/arch/nios2/boot/dts/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-obj-y := $(patsubst "%.dts",%.dtb.o,$(CONFIG_NIOS2_DTB_SOURCE))
+obj-y := $(patsubst %.dts,%.dtb.o,$(CONFIG_NIOS2_DTB_SOURCE))
dtstree := $(srctree)/$(src)
dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
diff --git a/arch/openrisc/boot/dts/Makefile b/arch/openrisc/boot/dts/Makefile
index 17dd791..13db5a2 100644
--- a/arch/openrisc/boot/dts/Makefile
+++ b/arch/openrisc/boot/dts/Makefile
@@ -1,9 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
-ifneq '$(CONFIG_OPENRISC_BUILTIN_DTB)' '""'
-BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_OPENRISC_BUILTIN_DTB)).dtb.o
-else
-BUILTIN_DTB :=
-endif
-obj-y += $(BUILTIN_DTB)
+obj-y += $(addsuffix .dtb.o, $(CONFIG_OPENRISC_BUILTIN_DTB))
#DTC_FLAGS ?= -p 1024
diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile
index 116bd5c..a294a1b 100644
--- a/arch/parisc/boot/compressed/Makefile
+++ b/arch/parisc/boot/compressed/Makefile
@@ -50,8 +50,6 @@
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
-vmlinux.bin.all-y := $(obj)/vmlinux.bin
-
suffix-$(CONFIG_KERNEL_GZIP) := gz
suffix-$(CONFIG_KERNEL_BZIP2) := bz2
suffix-$(CONFIG_KERNEL_LZ4) := lz4
@@ -59,18 +57,18 @@
suffix-$(CONFIG_KERNEL_LZO) := lzo
suffix-$(CONFIG_KERNEL_XZ) := xz
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lz4)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzma)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzo)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,xzkern)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,bzip2_with_size)
+$(obj)/vmlinux.bin.lz4: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lz4_with_size)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzma_with_size)
+$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzo_with_size)
+$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,xzkern_with_size)
LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index b669f4b..3a3d054 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -289,6 +289,7 @@ extern int _parisc_requires_coherency;
extern int running_on_qemu;
+extern void __noreturn toc_intr(struct pt_regs *regs);
extern void toc_handler(void);
extern unsigned int toc_handler_size;
extern unsigned int toc_handler_csum;
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index cceb098..b91cb45 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -48,6 +48,7 @@ struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL;
void __init setup_cmdline(char **cmdline_p)
{
extern unsigned int boot_args[];
+ char *p;
/* Collect stuff passed in from the boot loader */
@@ -56,9 +57,19 @@ void __init setup_cmdline(char **cmdline_p)
/* called from hpux boot loader */
boot_command_line[0] = '\0';
} else {
- strlcpy(boot_command_line, (char *)__va(boot_args[1]),
+ strscpy(boot_command_line, (char *)__va(boot_args[1]),
COMMAND_LINE_SIZE);
+ /* autodetect console type (if not done by palo yet) */
+ p = boot_command_line;
+ if (!str_has_prefix(p, "console=") && !strstr(p, " console=")) {
+ strlcat(p, " console=", COMMAND_LINE_SIZE);
+ if (PAGE0->mem_cons.cl_class == CL_DUPLEX)
+ strlcat(p, "ttyS0", COMMAND_LINE_SIZE);
+ else
+ strlcat(p, "tty0", COMMAND_LINE_SIZE);
+ }
+
#ifdef CONFIG_BLK_DEV_INITRD
if (boot_args[2] != 0) /* did palo pass us a ramdisk? */
{
@@ -68,7 +79,7 @@ void __init setup_cmdline(char **cmdline_p)
#endif
}
- strcpy(command_line, boot_command_line);
+ strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
}
diff --git a/arch/parisc/kernel/toc.c b/arch/parisc/kernel/toc.c
index be9a0beb..e4b48d0 100644
--- a/arch/parisc/kernel/toc.c
+++ b/arch/parisc/kernel/toc.c
@@ -10,9 +10,10 @@
#include <asm/pdc.h>
#include <asm/pdc_chassis.h>
#include <asm/ldcw.h>
+#include <asm/processor.h>
static unsigned int __aligned(16) toc_lock = 1;
-DEFINE_PER_CPU_PAGE_ALIGNED(char [16384], toc_stack);
+DEFINE_PER_CPU_PAGE_ALIGNED(char [16384], toc_stack) __visible;
static void toc20_to_pt_regs(struct pt_regs *regs, struct pdc_toc_pim_20 *toc)
{
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 0631c92..b779603 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -55,15 +55,6 @@
default 9 if PPC_16K_PAGES # 9 = 23 (8MB) - 14 (16K)
default 11 # 11 = 23 (8MB) - 12 (4K)
-config HAVE_SETUP_PER_CPU_AREA
- def_bool PPC64
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y if PPC64
-
-config NEED_PER_CPU_PAGE_FIRST_CHUNK
- def_bool y if PPC64
-
config NR_IRQS
int "Number of virtual interrupt numbers"
range 32 1048576
@@ -241,6 +232,7 @@
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE
select HAVE_RSEQ
+ select HAVE_SETUP_PER_CPU_AREA if PPC64
select HAVE_SOFTIRQ_ON_OWN_STACK
select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
@@ -255,6 +247,8 @@
select MMU_GATHER_RCU_TABLE_FREE
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64
+ select NEED_PER_CPU_PAGE_FIRST_CHUNK if PPC64
select NEED_SG_DMA_LENGTH
select OF
select OF_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE
@@ -660,6 +654,7 @@
bool "NUMA Memory Allocation and Scheduler Support"
depends on PPC64 && SMP
default y if PPC_PSERIES || PPC_POWERNV
+ select USE_PERCPU_NUMA_NODE_ID
help
Enable NUMA (Non-Uniform Memory Access) support.
@@ -673,10 +668,6 @@
default "4"
depends on NUMA
-config USE_PERCPU_NUMA_NODE_ID
- def_bool y
- depends on NUMA
-
config HAVE_MEMORYLESS_NODES
def_bool y
depends on NUMA
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 9993c62..4b4827c 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -365,7 +365,7 @@
endif
# Allow extra targets to be added to the defconfig
-image-y += $(subst ",,$(CONFIG_EXTRA_TARGETS))
+image-y += $(CONFIG_EXTRA_TARGETS)
initrd- := $(patsubst zImage%, zImage.initrd%, $(image-))
initrd-y := $(patsubst zImage%, zImage.initrd%, \
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
index c90702b..48e5cd6 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
@@ -79,6 +79,7 @@ mdio0: mdio@fc000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfc000 0x1000>;
+ fsl,erratum-a009885;
};
xmdio0: mdio@fd000 {
@@ -86,6 +87,7 @@ xmdio0: mdio@fd000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfd000 0x1000>;
+ fsl,erratum-a009885;
};
};
diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts
index e9c945b..e46143c 100644
--- a/arch/powerpc/boot/dts/wii.dts
+++ b/arch/powerpc/boot/dts/wii.dts
@@ -168,6 +168,11 @@ PIC1: pic1@d800030 {
interrupts = <14>;
};
+ srnprot@d800060 {
+ compatible = "nintendo,hollywood-srnprot";
+ reg = <0x0d800060 0x4>;
+ };
+
GPIO: gpio@d8000c0 {
#gpio-cells = <2>;
compatible = "nintendo,hollywood-gpio";
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index 24c0e0e..91a1b99 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -68,7 +68,7 @@
CONFIG_SND_SEQUENCER_OSS=y
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_GENERIC=y
+CONFIG_RTC_DRV_GAMECUBE=y
CONFIG_EXT2_FS=y
CONFIG_EXT4_FS=y
CONFIG_ISO9660_FS=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index a0c45bf..0ab78c5 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -98,7 +98,7 @@
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_PANIC=y
CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_GENERIC=y
+CONFIG_RTC_DRV_GAMECUBE=y
CONFIG_NVMEM_NINTENDO_OTP=y
CONFIG_EXT2_FS=y
CONFIG_EXT4_FS=y
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index d87f7c1..be8577a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -771,50 +771,6 @@ void __init emergency_stack_init(void)
}
#ifdef CONFIG_SMP
-/**
- * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
- * @cpu: cpu to allocate for
- * @size: size allocation in bytes
- * @align: alignment
- *
- * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
- * does the right thing for NUMA regardless of the current
- * configuration.
- *
- * RETURNS:
- * Pointer to the allocated area on success, NULL on failure.
- */
-static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
- size_t align)
-{
- const unsigned long goal = __pa(MAX_DMA_ADDRESS);
-#ifdef CONFIG_NUMA
- int node = early_cpu_to_node(cpu);
- void *ptr;
-
- if (!node_online(node) || !NODE_DATA(node)) {
- ptr = memblock_alloc_from(size, align, goal);
- pr_info("cpu %d has no node %d or node-local memory\n",
- cpu, node);
- pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
- cpu, size, __pa(ptr));
- } else {
- ptr = memblock_alloc_try_nid(size, align, goal,
- MEMBLOCK_ALLOC_ACCESSIBLE, node);
- pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
- "%016lx\n", cpu, size, node, __pa(ptr));
- }
- return ptr;
-#else
- return memblock_alloc_from(size, align, goal);
-#endif
-}
-
-static void __init pcpu_free_bootmem(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
static int pcpu_cpu_distance(unsigned int from, unsigned int to)
{
if (early_cpu_to_node(from) == early_cpu_to_node(to))
@@ -823,53 +779,13 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
return REMOTE_DISTANCE;
}
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
-
-static void __init pcpu_populate_pte(unsigned long addr)
+static __init int pcpu_cpu_to_node(int cpu)
{
- pgd_t *pgd = pgd_offset_k(addr);
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
-
- p4d = p4d_offset(pgd, addr);
- if (p4d_none(*p4d)) {
- pud_t *new;
-
- new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
- if (!new)
- goto err_alloc;
- p4d_populate(&init_mm, p4d, new);
- }
-
- pud = pud_offset(p4d, addr);
- if (pud_none(*pud)) {
- pmd_t *new;
-
- new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
- if (!new)
- goto err_alloc;
- pud_populate(&init_mm, pud, new);
- }
-
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd)) {
- pte_t *new;
-
- new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
- if (!new)
- goto err_alloc;
- pmd_populate_kernel(&init_mm, pmd, new);
- }
-
- return;
-
-err_alloc:
- panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
- __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+ return early_cpu_to_node(cpu);
}
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
void __init setup_per_cpu_areas(void)
{
@@ -900,7 +816,7 @@ void __init setup_per_cpu_areas(void)
if (pcpu_chosen_fc != PCPU_FC_PAGE) {
rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
- pcpu_alloc_bootmem, pcpu_free_bootmem);
+ pcpu_cpu_to_node);
if (rc)
pr_warn("PERCPU: %s allocator failed (%d), "
"falling back to page size\n",
@@ -908,8 +824,7 @@ void __init setup_per_cpu_areas(void)
}
if (rc < 0)
- rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem,
- pcpu_populate_pte);
+ rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 09abf62..5adcbd9 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -14,6 +14,7 @@
def_bool y
select ARCH_CLOCKSOURCE_INIT
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
+ select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_HAS_BINFMT_FLAT
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_VIRTUAL if MMU
@@ -75,6 +76,7 @@
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
+ select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
select HAVE_ASM_MODVERSIONS
@@ -145,27 +147,16 @@
Select if you want MMU-based virtualised addressing space
support by paged memory management. If unsure, say 'Y'.
-config VA_BITS
- int
- default 32 if 32BIT
- default 39 if 64BIT
-
-config PA_BITS
- int
- default 34 if 32BIT
- default 56 if 64BIT
-
config PAGE_OFFSET
hex
- default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
+ default 0xC0000000 if 32BIT
default 0x80000000 if 64BIT && !MMU
- default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
- default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
+ default 0xffffaf8000000000 if 64BIT
config KASAN_SHADOW_OFFSET
hex
depends on KASAN_GENERIC
- default 0xdfffffc800000000 if 64BIT
+ default 0xdfffffff00000000 if 64BIT
default 0xffffffff if 32BIT
config ARCH_FLATMEM_ENABLE
@@ -211,7 +202,7 @@
config PGTABLE_LEVELS
int
- default 3 if 64BIT
+ default 4 if 64BIT
default 2
config LOCKDEP_SUPPORT
@@ -269,24 +260,6 @@
bool
select HAVE_MOD_ARCH_SPECIFIC
-choice
- prompt "Maximum Physical Memory"
- default MAXPHYSMEM_1GB if 32BIT
- default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
- default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
-
- config MAXPHYSMEM_1GB
- depends on 32BIT
- bool "1GiB"
- config MAXPHYSMEM_2GB
- depends on 64BIT && CMODEL_MEDLOW
- bool "2GiB"
- config MAXPHYSMEM_128GB
- depends on 64BIT && CMODEL_MEDANY
- bool "128GiB"
-endchoice
-
-
config SMP
bool "Symmetric Multi-Processing"
help
@@ -333,6 +306,8 @@
select GENERIC_ARCH_NUMA
select OF_NUMA
select ARCH_SUPPORTS_NUMA_BALANCING
+ select USE_PERCPU_NUMA_NODE_ID
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK
help
Enable NUMA (Non-Uniform Memory Access) support.
@@ -348,14 +323,6 @@
Specify the maximum number of NUMA Nodes available on the target
system. Increases memory reserved to accommodate various tables.
-config USE_PERCPU_NUMA_NODE_ID
- def_bool y
- depends on NUMA
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y
- depends on NUMA
-
config RISCV_ISA_C
bool "Emit compressed instructions when building Linux"
default y
@@ -396,12 +363,25 @@
config RISCV_SBI_V01
bool "SBI v0.1 support"
- default y
depends on RISCV_SBI
help
This config allows kernel to use SBI v0.1 APIs. This will be
deprecated in future once legacy M-mode software are no longer in use.
+config RISCV_BOOT_SPINWAIT
+ bool "Spinwait booting method"
+ depends on SMP
+ default y
+ help
+ This enables support for booting Linux via spinwait method. In the
+ spinwait method, all cores randomly jump to Linux. One of the cores
+ gets chosen via lottery and all other keep spinning on a percpu
+ variable. This method cannot support CPU hotplug and sparse hartid
+ scheme. It should be only enabled for M-mode Linux or platforms relying
+ on older firmware without SBI HSM extension. All other platforms should
+ rely on ordered booting via SBI HSM extension which gets chosen
+ dynamically at runtime if the firmware supports it.
+
config KEXEC
bool "Kexec system call"
select KEXEC_CORE
diff --git a/arch/riscv/boot/dts/canaan/Makefile b/arch/riscv/boot/dts/canaan/Makefile
index 9ee7156..c61b08a 100644
--- a/arch/riscv/boot/dts/canaan/Makefile
+++ b/arch/riscv/boot/dts/canaan/Makefile
@@ -1,5 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
-ifneq ($(CONFIG_SOC_CANAAN_K210_DTB_SOURCE),"")
-dtb-y += $(strip $(shell echo $(CONFIG_SOC_CANAAN_K210_DTB_SOURCE))).dtb
+dtb-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += $(addsuffix .dtb, $(CONFIG_SOC_CANAAN_K210_DTB_SOURCE))
obj-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += $(addsuffix .o, $(dtb-y))
-endif
diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi
index 5e8ca81..56f5711 100644
--- a/arch/riscv/boot/dts/canaan/k210.dtsi
+++ b/arch/riscv/boot/dts/canaan/k210.dtsi
@@ -103,8 +103,8 @@ rom0: nvmem@1000 {
clint0: timer@2000000 {
compatible = "canaan,k210-clint", "sifive,clint0";
reg = <0x2000000 0xC000>;
- interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7
- &cpu1_intc 3 &cpu1_intc 7>;
+ interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>,
+ <&cpu1_intc 3>, <&cpu1_intc 7>;
};
plic0: interrupt-controller@c000000 {
@@ -113,7 +113,7 @@ plic0: interrupt-controller@c000000 {
compatible = "canaan,k210-plic", "sifive,plic-1.0.0";
reg = <0xC000000 0x4000000>;
interrupt-controller;
- interrupts-extended = <&cpu0_intc 11 &cpu1_intc 11>;
+ interrupts-extended = <&cpu0_intc 11>, <&cpu1_intc 11>;
riscv,ndev = <65>;
};
@@ -130,10 +130,11 @@ gpio0: gpio-controller@38001000 {
compatible = "canaan,k210-gpiohs", "sifive,gpio0";
reg = <0x38001000 0x1000>;
interrupt-controller;
- interrupts = <34 35 36 37 38 39 40 41
- 42 43 44 45 46 47 48 49
- 50 51 52 53 54 55 56 57
- 58 59 60 61 62 63 64 65>;
+ interrupts = <34>, <35>, <36>, <37>, <38>, <39>, <40>,
+ <41>, <42>, <43>, <44>, <45>, <46>, <47>,
+ <48>, <49>, <50>, <51>, <52>, <53>, <54>,
+ <55>, <56>, <57>, <58>, <59>, <60>, <61>,
+ <62>, <63>, <64>, <65>;
gpio-controller;
ngpios = <32>;
};
@@ -141,7 +142,7 @@ gpio0: gpio-controller@38001000 {
dmac0: dma-controller@50000000 {
compatible = "snps,axi-dma-1.01a";
reg = <0x50000000 0x1000>;
- interrupts = <27 28 29 30 31 32>;
+ interrupts = <27>, <28>, <29>, <30>, <31>, <32>;
#dma-cells = <1>;
clocks = <&sysclk K210_CLK_DMA>, <&sysclk K210_CLK_DMA>;
clock-names = "core-clk", "cfgr-clk";
@@ -316,7 +317,7 @@ fpioa: pinmux@502b0000 {
timer0: timer@502d0000 {
compatible = "snps,dw-apb-timer";
reg = <0x502D0000 0x100>;
- interrupts = <14 15>;
+ interrupts = <14>, <15>;
clocks = <&sysclk K210_CLK_TIMER0>,
<&sysclk K210_CLK_APB0>;
clock-names = "timer", "pclk";
@@ -326,7 +327,7 @@ timer0: timer@502d0000 {
timer1: timer@502e0000 {
compatible = "snps,dw-apb-timer";
reg = <0x502E0000 0x100>;
- interrupts = <16 17>;
+ interrupts = <16>, <17>;
clocks = <&sysclk K210_CLK_TIMER1>,
<&sysclk K210_CLK_APB0>;
clock-names = "timer", "pclk";
@@ -336,7 +337,7 @@ timer1: timer@502e0000 {
timer2: timer@502f0000 {
compatible = "snps,dw-apb-timer";
reg = <0x502F0000 0x100>;
- interrupts = <18 19>;
+ interrupts = <18>, <19>;
clocks = <&sysclk K210_CLK_TIMER2>,
<&sysclk K210_CLK_APB0>;
clock-names = "timer", "pclk";
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
index 0bcaf35..984872f 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
@@ -199,7 +199,7 @@ slot@0 {
};
&spi3 {
- spi-flash@0 {
+ flash@0 {
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
index ac8a03f..7ba99b4d 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
@@ -201,7 +201,7 @@ slot@0 {
};
&spi3 {
- spi-flash@0 {
+ flash@0 {
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
index 6239981..be9b12c 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
@@ -209,7 +209,7 @@ slot@0 {
};
&spi3 {
- spi-flash@0 {
+ flash@0 {
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
index cf605ba..031c0c2 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
@@ -174,7 +174,7 @@ slot@0 {
};
&spi3 {
- spi-flash@0 {
+ flash@0 {
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
index fc1e586..0c748ae 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
@@ -35,6 +35,10 @@ memory@80000000 {
};
};
+&refclk {
+ clock-frequency = <600000000>;
+};
+
&serial0 {
status = "okay";
};
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
index c9f6d20..869aaf0 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
@@ -9,9 +9,6 @@ / {
model = "Microchip PolarFire SoC";
compatible = "microchip,mpfs";
- chosen {
- };
-
cpus {
#address-cells = <1>;
#size-cells = <0>;
@@ -142,6 +139,11 @@ cpu4_intc: interrupt-controller {
};
};
+ refclk: msspllclk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ };
+
soc {
#address-cells = <2>;
#size-cells = <2>;
@@ -156,62 +158,48 @@ cache-controller@2010000 {
cache-size = <2097152>;
cache-unified;
interrupt-parent = <&plic>;
- interrupts = <1 2 3>;
+ interrupts = <1>, <2>, <3>;
reg = <0x0 0x2010000 0x0 0x1000>;
};
clint@2000000 {
compatible = "sifive,fu540-c000-clint", "sifive,clint0";
reg = <0x0 0x2000000 0x0 0xC000>;
- interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7
- &cpu1_intc 3 &cpu1_intc 7
- &cpu2_intc 3 &cpu2_intc 7
- &cpu3_intc 3 &cpu3_intc 7
- &cpu4_intc 3 &cpu4_intc 7>;
+ interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>,
+ <&cpu1_intc 3>, <&cpu1_intc 7>,
+ <&cpu2_intc 3>, <&cpu2_intc 7>,
+ <&cpu3_intc 3>, <&cpu3_intc 7>,
+ <&cpu4_intc 3>, <&cpu4_intc 7>;
};
plic: interrupt-controller@c000000 {
- #interrupt-cells = <1>;
compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
reg = <0x0 0xc000000 0x0 0x4000000>;
- riscv,ndev = <186>;
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
interrupt-controller;
- interrupts-extended = <&cpu0_intc 11
- &cpu1_intc 11 &cpu1_intc 9
- &cpu2_intc 11 &cpu2_intc 9
- &cpu3_intc 11 &cpu3_intc 9
- &cpu4_intc 11 &cpu4_intc 9>;
+ interrupts-extended = <&cpu0_intc 11>,
+ <&cpu1_intc 11>, <&cpu1_intc 9>,
+ <&cpu2_intc 11>, <&cpu2_intc 9>,
+ <&cpu3_intc 11>, <&cpu3_intc 9>,
+ <&cpu4_intc 11>, <&cpu4_intc 9>;
+ riscv,ndev = <186>;
};
dma@3000000 {
compatible = "sifive,fu540-c000-pdma";
reg = <0x0 0x3000000 0x0 0x8000>;
interrupt-parent = <&plic>;
- interrupts = <23 24 25 26 27 28 29 30>;
+ interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>,
+ <30>;
#dma-cells = <1>;
};
- refclk: refclk {
- compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <600000000>;
- clock-output-names = "msspllclk";
- };
-
clkcfg: clkcfg@20002000 {
compatible = "microchip,mpfs-clkcfg";
reg = <0x0 0x20002000 0x0 0x1000>;
- reg-names = "mss_sysreg";
clocks = <&refclk>;
#clock-cells = <1>;
- clock-output-names = "cpu", "axi", "ahb", "envm", /* 0-3 */
- "mac0", "mac1", "mmc", "timer", /* 4-7 */
- "mmuart0", "mmuart1", "mmuart2", "mmuart3", /* 8-11 */
- "mmuart4", "spi0", "spi1", "i2c0", /* 12-15 */
- "i2c1", "can0", "can1", "usb", /* 16-19 */
- "rsvd", "rtc", "qspi", "gpio0", /* 20-23 */
- "gpio1", "gpio2", "ddrc", "fic0", /* 24-27 */
- "fic1", "fic2", "fic3", "athena", "cfm"; /* 28-32 */
};
serial0: serial@20000000 {
@@ -267,7 +255,7 @@ mmc: mmc@20008000 {
compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc";
reg = <0x0 0x20008000 0x0 0x1000>;
interrupt-parent = <&plic>;
- interrupts = <88 89>;
+ interrupts = <88>, <89>;
clocks = <&clkcfg 6>;
max-frequency = <200000000>;
status = "disabled";
@@ -277,7 +265,7 @@ emac0: ethernet@20110000 {
compatible = "cdns,macb";
reg = <0x0 0x20110000 0x0 0x2000>;
interrupt-parent = <&plic>;
- interrupts = <64 65 66 67>;
+ interrupts = <64>, <65>, <66>, <67>;
local-mac-address = [00 00 00 00 00 00];
clocks = <&clkcfg 4>, <&clkcfg 2>;
clock-names = "pclk", "hclk";
@@ -290,7 +278,7 @@ emac1: ethernet@20112000 {
compatible = "cdns,macb";
reg = <0x0 0x20112000 0x0 0x2000>;
interrupt-parent = <&plic>;
- interrupts = <70 71 72 73>;
+ interrupts = <70>, <71>, <72>, <73>;
local-mac-address = [00 00 00 00 00 00];
clocks = <&clkcfg 5>, <&clkcfg 2>;
status = "disabled";
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
index 0655b5c..3eef52b 100644
--- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -137,20 +137,21 @@ cpu4_intc: interrupt-controller {
soc {
#address-cells = <2>;
#size-cells = <2>;
- compatible = "sifive,fu540-c000", "sifive,fu540", "simple-bus";
+ compatible = "simple-bus";
ranges;
plic0: interrupt-controller@c000000 {
- #interrupt-cells = <1>;
compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
reg = <0x0 0xc000000 0x0 0x4000000>;
- riscv,ndev = <53>;
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
interrupt-controller;
- interrupts-extended = <
- &cpu0_intc 0xffffffff
- &cpu1_intc 0xffffffff &cpu1_intc 9
- &cpu2_intc 0xffffffff &cpu2_intc 9
- &cpu3_intc 0xffffffff &cpu3_intc 9
- &cpu4_intc 0xffffffff &cpu4_intc 9>;
+ interrupts-extended =
+ <&cpu0_intc 0xffffffff>,
+ <&cpu1_intc 0xffffffff>, <&cpu1_intc 9>,
+ <&cpu2_intc 0xffffffff>, <&cpu2_intc 9>,
+ <&cpu3_intc 0xffffffff>, <&cpu3_intc 9>,
+ <&cpu4_intc 0xffffffff>, <&cpu4_intc 9>;
+ riscv,ndev = <53>;
};
prci: clock-controller@10000000 {
compatible = "sifive,fu540-c000-prci";
@@ -170,7 +171,8 @@ dma: dma@3000000 {
compatible = "sifive,fu540-c000-pdma";
reg = <0x0 0x3000000 0x0 0x8000>;
interrupt-parent = <&plic0>;
- interrupts = <23 24 25 26 27 28 29 30>;
+ interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>,
+ <30>;
#dma-cells = <1>;
};
uart1: serial@10011000 {
@@ -195,8 +197,8 @@ i2c0: i2c@10030000 {
};
qspi0: spi@10040000 {
compatible = "sifive,fu540-c000-spi", "sifive,spi0";
- reg = <0x0 0x10040000 0x0 0x1000
- 0x0 0x20000000 0x0 0x10000000>;
+ reg = <0x0 0x10040000 0x0 0x1000>,
+ <0x0 0x20000000 0x0 0x10000000>;
interrupt-parent = <&plic0>;
interrupts = <51>;
clocks = <&prci PRCI_CLK_TLCLK>;
@@ -206,8 +208,8 @@ qspi0: spi@10040000 {
};
qspi1: spi@10041000 {
compatible = "sifive,fu540-c000-spi", "sifive,spi0";
- reg = <0x0 0x10041000 0x0 0x1000
- 0x0 0x30000000 0x0 0x10000000>;
+ reg = <0x0 0x10041000 0x0 0x1000>,
+ <0x0 0x30000000 0x0 0x10000000>;
interrupt-parent = <&plic0>;
interrupts = <52>;
clocks = <&prci PRCI_CLK_TLCLK>;
@@ -229,8 +231,8 @@ eth0: ethernet@10090000 {
compatible = "sifive,fu540-c000-gem";
interrupt-parent = <&plic0>;
interrupts = <53>;
- reg = <0x0 0x10090000 0x0 0x2000
- 0x0 0x100a0000 0x0 0x1000>;
+ reg = <0x0 0x10090000 0x0 0x2000>,
+ <0x0 0x100a0000 0x0 0x1000>;
local-mac-address = [00 00 00 00 00 00];
clock-names = "pclk", "hclk";
clocks = <&prci PRCI_CLK_GEMGXLPLL>,
@@ -243,7 +245,7 @@ pwm0: pwm@10020000 {
compatible = "sifive,fu540-c000-pwm", "sifive,pwm0";
reg = <0x0 0x10020000 0x0 0x1000>;
interrupt-parent = <&plic0>;
- interrupts = <42 43 44 45>;
+ interrupts = <42>, <43>, <44>, <45>;
clocks = <&prci PRCI_CLK_TLCLK>;
#pwm-cells = <3>;
status = "disabled";
@@ -252,7 +254,7 @@ pwm1: pwm@10021000 {
compatible = "sifive,fu540-c000-pwm", "sifive,pwm0";
reg = <0x0 0x10021000 0x0 0x1000>;
interrupt-parent = <&plic0>;
- interrupts = <46 47 48 49>;
+ interrupts = <46>, <47>, <48>, <49>;
clocks = <&prci PRCI_CLK_TLCLK>;
#pwm-cells = <3>;
status = "disabled";
@@ -265,7 +267,7 @@ l2cache: cache-controller@2010000 {
cache-size = <2097152>;
cache-unified;
interrupt-parent = <&plic0>;
- interrupts = <1 2 3>;
+ interrupts = <1>, <2>, <3>;
reg = <0x0 0x2010000 0x0 0x1000>;
};
gpio: gpio@10060000 {
diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
index abbb960..8464b0e 100644
--- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
@@ -147,12 +147,12 @@ plic0: interrupt-controller@c000000 {
reg = <0x0 0xc000000 0x0 0x4000000>;
riscv,ndev = <69>;
interrupt-controller;
- interrupts-extended = <
- &cpu0_intc 0xffffffff
- &cpu1_intc 0xffffffff &cpu1_intc 9
- &cpu2_intc 0xffffffff &cpu2_intc 9
- &cpu3_intc 0xffffffff &cpu3_intc 9
- &cpu4_intc 0xffffffff &cpu4_intc 9>;
+ interrupts-extended =
+ <&cpu0_intc 0xffffffff>,
+ <&cpu1_intc 0xffffffff>, <&cpu1_intc 9>,
+ <&cpu2_intc 0xffffffff>, <&cpu2_intc 9>,
+ <&cpu3_intc 0xffffffff>, <&cpu3_intc 9>,
+ <&cpu4_intc 0xffffffff>, <&cpu4_intc 9>;
};
prci: clock-controller@10000000 {
compatible = "sifive,fu740-c000-prci";
@@ -273,7 +273,7 @@ ccache: cache-controller@2010000 {
cache-size = <2097152>;
cache-unified;
interrupt-parent = <&plic0>;
- interrupts = <19 21 22 20>;
+ interrupts = <19>, <21>, <22>, <20>;
reg = <0x0 0x2010000 0x0 0x1000>;
};
gpio: gpio@10060000 {
diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
index 6bfa1f2..c4ed9ef 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
@@ -39,6 +39,11 @@ rtcclk: rtcclk {
clock-frequency = <RTCCLK_FREQ>;
clock-output-names = "rtcclk";
};
+
+ gpio-poweroff {
+ compatible = "gpio-poweroff";
+ gpios = <&gpio 2 GPIO_ACTIVE_LOW>;
+ };
};
&uart0 {
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index ef473e2..f120fcc 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -2,6 +2,7 @@
CONFIG_POSIX_MQUEUE=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_CGROUPS=y
@@ -13,10 +14,10 @@
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
-CONFIG_BPF_SYSCALL=y
+# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_SOC_MICROCHIP_POLARFIRE=y
CONFIG_SOC_SIFIVE=y
CONFIG_SOC_VIRT=y
-CONFIG_SOC_MICROCHIP_POLARFIRE=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
CONFIG_VIRTUALIZATION=y
@@ -70,14 +71,14 @@
CONFIG_HW_RANDOM_VIRTIO=y
CONFIG_SPI=y
CONFIG_SPI_SIFIVE=y
+# CONFIG_PTP_1588_CLOCK is not set
CONFIG_GPIOLIB=y
CONFIG_GPIO_SIFIVE=y
-# CONFIG_PTP_1588_CLOCK is not set
-CONFIG_POWER_RESET=y
CONFIG_DRM=m
CONFIG_DRM_RADEON=m
CONFIG_DRM_NOUVEAU=m
CONFIG_DRM_VIRTIO_GPU=m
+CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_USB=y
CONFIG_USB_XHCI_HCD=y
@@ -88,10 +89,10 @@
CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_STORAGE=y
CONFIG_USB_UAS=y
+CONFIG_MMC=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI_CADENCE=y
-CONFIG_MMC=y
CONFIG_MMC_SPI=y
CONFIG_RTC_CLASS=y
CONFIG_VIRTIO_PCI=y
@@ -142,5 +143,3 @@
# CONFIG_FTRACE is not set
# CONFIG_RUNTIME_TESTING_MENU is not set
CONFIG_MEMTEST=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_EFI=y
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
index b16a2a1..3f42ed8 100644
--- a/arch/riscv/configs/nommu_k210_defconfig
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -29,8 +29,6 @@
CONFIG_SLOB=y
# CONFIG_MMU is not set
CONFIG_SOC_CANAAN=y
-CONFIG_SOC_CANAAN_K210_DTB_SOURCE="k210_generic"
-CONFIG_MAXPHYSMEM_2GB=y
CONFIG_SMP=y
CONFIG_NR_CPUS=2
CONFIG_CMDLINE="earlycon console=ttySIF0"
@@ -75,7 +73,6 @@
CONFIG_LEDS_USER=y
# CONFIG_VIRTIO_MENU is not set
# CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
# CONFIG_FILE_LOCKING is not set
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY_USER is not set
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
index 61f887f..2a82a3b 100644
--- a/arch/riscv/configs/nommu_k210_sdcard_defconfig
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -21,8 +21,6 @@
CONFIG_SLOB=y
# CONFIG_MMU is not set
CONFIG_SOC_CANAAN=y
-CONFIG_SOC_CANAAN_K210_DTB_SOURCE="k210_generic"
-CONFIG_MAXPHYSMEM_2GB=y
CONFIG_SMP=y
CONFIG_NR_CPUS=2
CONFIG_CMDLINE="earlycon console=ttySIF0 rootdelay=2 root=/dev/mmcblk0p1 ro"
@@ -30,7 +28,6 @@
# CONFIG_SECCOMP is not set
# CONFIG_STACKPROTECTOR is not set
# CONFIG_GCC_PLUGINS is not set
-# CONFIG_BLK_DEV_BSG is not set
# CONFIG_MQ_IOSCHED_DEADLINE is not set
# CONFIG_MQ_IOSCHED_KYBER is not set
CONFIG_BINFMT_FLAT=y
@@ -72,7 +69,6 @@
CONFIG_LEDS_USER=y
# CONFIG_VIRTIO_MENU is not set
# CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_EXT2_FS=y
# CONFIG_FILE_LOCKING is not set
# CONFIG_DNOTIFY is not set
diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig
index e046a0b..e1c9864 100644
--- a/arch/riscv/configs/nommu_virt_defconfig
+++ b/arch/riscv/configs/nommu_virt_defconfig
@@ -24,15 +24,12 @@
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_SLOB=y
-# CONFIG_SLAB_MERGE_DEFAULT is not set
# CONFIG_MMU is not set
CONFIG_SOC_VIRT=y
-CONFIG_MAXPHYSMEM_2GB=y
CONFIG_SMP=y
CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0"
CONFIG_CMDLINE_FORCE=y
CONFIG_JUMP_LABEL=y
-# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
# CONFIG_MSDOS_PARTITION is not set
# CONFIG_EFI_PARTITION is not set
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index 6e9f12f..8b56a7f 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -2,6 +2,7 @@
CONFIG_POSIX_MQUEUE=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_CGROUPS=y
@@ -13,7 +14,7 @@
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
-CONFIG_BPF_SYSCALL=y
+# CONFIG_SYSFS_SYSCALL is not set
CONFIG_SOC_SIFIVE=y
CONFIG_SOC_VIRT=y
CONFIG_ARCH_RV32I=y
@@ -69,10 +70,10 @@
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_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_USB=y
CONFIG_USB_XHCI_HCD=y
@@ -132,4 +133,3 @@
# CONFIG_FTRACE is not set
# CONFIG_RUNTIME_TESTING_MENU is not set
CONFIG_MEMTEST=y
-# CONFIG_SYSFS_SYSCALL is not set
diff --git a/arch/riscv/errata/alternative.c b/arch/riscv/errata/alternative.c
index 3b15885d..e8b4a0f 100644
--- a/arch/riscv/errata/alternative.c
+++ b/arch/riscv/errata/alternative.c
@@ -22,7 +22,8 @@ static struct cpu_manufacturer_info_t {
} cpu_mfr_info;
static void (*vendor_patch_func)(struct alt_entry *begin, struct alt_entry *end,
- unsigned long archid, unsigned long impid);
+ unsigned long archid,
+ unsigned long impid) __initdata;
static inline void __init riscv_fill_cpu_mfr_info(void)
{
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 445ccc9..57b86fd 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -1,6 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
generic-y += early_ioremap.h
-generic-y += extable.h
generic-y += flat.h
generic-y += kvm_para.h
generic-y += user.h
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
new file mode 100644
index 0000000..14be067
--- /dev/null
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_ASM_EXTABLE_H
+#define __ASM_ASM_EXTABLE_H
+
+#define EX_TYPE_NONE 0
+#define EX_TYPE_FIXUP 1
+#define EX_TYPE_BPF 2
+#define EX_TYPE_UACCESS_ERR_ZERO 3
+
+#ifdef __ASSEMBLY__
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data) \
+ .pushsection __ex_table, "a"; \
+ .balign 4; \
+ .long ((insn) - .); \
+ .long ((fixup) - .); \
+ .short (type); \
+ .short (data); \
+ .popsection;
+
+ .macro _asm_extable, insn, fixup
+ __ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0)
+ .endm
+
+#else /* __ASSEMBLY__ */
+
+#include <linux/bits.h>
+#include <linux/stringify.h>
+#include <asm/gpr-num.h>
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data) \
+ ".pushsection __ex_table, \"a\"\n" \
+ ".balign 4\n" \
+ ".long ((" insn ") - .)\n" \
+ ".long ((" fixup ") - .)\n" \
+ ".short (" type ")\n" \
+ ".short (" data ")\n" \
+ ".popsection\n"
+
+#define _ASM_EXTABLE(insn, fixup) \
+ __ASM_EXTABLE_RAW(#insn, #fixup, __stringify(EX_TYPE_FIXUP), "0")
+
+#define EX_DATA_REG_ERR_SHIFT 0
+#define EX_DATA_REG_ERR GENMASK(4, 0)
+#define EX_DATA_REG_ZERO_SHIFT 5
+#define EX_DATA_REG_ZERO GENMASK(9, 5)
+
+#define EX_DATA_REG(reg, gpr) \
+ "((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
+
+#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) \
+ __DEFINE_ASM_GPR_NUMS \
+ __ASM_EXTABLE_RAW(#insn, #fixup, \
+ __stringify(EX_TYPE_UACCESS_ERR_ZERO), \
+ "(" \
+ EX_DATA_REG(ERR, err) " | " \
+ EX_DATA_REG(ZERO, zero) \
+ ")")
+
+#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \
+ _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_ASM_EXTABLE_H */
diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index a8ec3c5..134590f 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -40,7 +40,5 @@ struct cpu_operations {
extern const struct cpu_operations *cpu_ops[NR_CPUS];
void __init cpu_set_ops(int cpu);
-void cpu_update_secondary_bootdata(unsigned int cpuid,
- struct task_struct *tidle);
#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/riscv/include/asm/cpu_ops_sbi.h b/arch/riscv/include/asm/cpu_ops_sbi.h
new file mode 100644
index 0000000..56e4b76
--- /dev/null
+++ b/arch/riscv/include/asm/cpu_ops_sbi.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 by Rivos Inc.
+ */
+#ifndef __ASM_CPU_OPS_SBI_H
+#define __ASM_CPU_OPS_SBI_H
+
+#ifndef __ASSEMBLY__
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+/**
+ * struct sbi_hart_boot_data - Hart specific boot used during booting and
+ * cpu hotplug.
+ * @task_ptr: A pointer to the hart specific tp
+ * @stack_ptr: A pointer to the hart specific sp
+ */
+struct sbi_hart_boot_data {
+ void *task_ptr;
+ void *stack_ptr;
+};
+#endif
+
+#endif /* ifndef __ASM_CPU_OPS_SBI_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 5046f43..ae71169 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -40,14 +40,13 @@
#ifndef CONFIG_64BIT
#define SATP_PPN _AC(0x003FFFFF, UL)
#define SATP_MODE_32 _AC(0x80000000, UL)
-#define SATP_MODE SATP_MODE_32
#define SATP_ASID_BITS 9
#define SATP_ASID_SHIFT 22
#define SATP_ASID_MASK _AC(0x1FF, UL)
#else
#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL)
#define SATP_MODE_39 _AC(0x8000000000000000, UL)
-#define SATP_MODE SATP_MODE_39
+#define SATP_MODE_48 _AC(0x9000000000000000, UL)
#define SATP_ASID_BITS 16
#define SATP_ASID_SHIFT 44
#define SATP_ASID_MASK _AC(0xFFFF, UL)
diff --git a/arch/riscv/include/asm/extable.h b/arch/riscv/include/asm/extable.h
new file mode 100644
index 0000000..512012d
--- /dev/null
+++ b/arch/riscv/include/asm/extable.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_EXTABLE_H
+#define _ASM_RISCV_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+ int insn, fixup;
+ short type, data;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#define swap_ex_entry_fixup(a, b, tmp, delta) \
+do { \
+ (a)->fixup = (b)->fixup + (delta); \
+ (b)->fixup = (tmp).fixup - (delta); \
+ (a)->type = (b)->type; \
+ (b)->type = (tmp).type; \
+ (a)->data = (b)->data; \
+ (b)->data = (tmp).data; \
+} while (0)
+
+bool fixup_exception(struct pt_regs *regs);
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
+bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs);
+#else
+static inline bool
+ex_handler_bpf(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
+{
+ return false;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index 54cbf07..58a7185 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -24,6 +24,7 @@ enum fixed_addresses {
FIX_HOLE,
FIX_PTE,
FIX_PMD,
+ FIX_PUD,
FIX_TEXT_POKE1,
FIX_TEXT_POKE0,
FIX_EARLYCON_MEM_BASE,
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 1b00bad..fc8130f 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -11,6 +11,7 @@
#include <linux/uaccess.h>
#include <linux/errno.h>
#include <asm/asm.h>
+#include <asm/asm-extable.h>
/* We don't even really need the extable code, but for now keep it simple */
#ifndef CONFIG_MMU
@@ -20,23 +21,14 @@
#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
{ \
- uintptr_t tmp; \
__enable_user_access(); \
__asm__ __volatile__ ( \
"1: " insn " \n" \
"2: \n" \
- " .section .fixup,\"ax\" \n" \
- " .balign 4 \n" \
- "3: li %[r],%[e] \n" \
- " jump 2b,%[t] \n" \
- " .previous \n" \
- " .section __ex_table,\"a\" \n" \
- " .balign " RISCV_SZPTR " \n" \
- " " RISCV_PTR " 1b, 3b \n" \
- " .previous \n" \
+ _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %[r]) \
: [r] "+r" (ret), [ov] "=&r" (oldval), \
- [u] "+m" (*uaddr), [t] "=&r" (tmp) \
- : [op] "Jr" (oparg), [e] "i" (-EFAULT) \
+ [u] "+m" (*uaddr) \
+ : [op] "Jr" (oparg) \
: "memory"); \
__disable_user_access(); \
}
@@ -98,18 +90,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
"2: sc.w.aqrl %[t],%z[nv],%[u] \n"
" bnez %[t],1b \n"
"3: \n"
- " .section .fixup,\"ax\" \n"
- " .balign 4 \n"
- "4: li %[r],%[e] \n"
- " jump 3b,%[t] \n"
- " .previous \n"
- " .section __ex_table,\"a\" \n"
- " .balign " RISCV_SZPTR " \n"
- " " RISCV_PTR " 1b, 4b \n"
- " " RISCV_PTR " 2b, 4b \n"
- " .previous \n"
+ _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \
+ _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \
: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
- : [ov] "Jr" (oldval), [nv] "Jr" (newval), [e] "i" (-EFAULT)
+ : [ov] "Jr" (oldval), [nv] "Jr" (newval)
: "memory");
__disable_user_access();
diff --git a/arch/riscv/include/asm/gpr-num.h b/arch/riscv/include/asm/gpr-num.h
new file mode 100644
index 0000000..dfee282
--- /dev/null
+++ b/arch/riscv/include/asm/gpr-num.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GPR_NUM_H
+#define __ASM_GPR_NUM_H
+
+#ifdef __ASSEMBLY__
+ .equ .L__gpr_num_zero, 0
+ .equ .L__gpr_num_ra, 1
+ .equ .L__gpr_num_sp, 2
+ .equ .L__gpr_num_gp, 3
+ .equ .L__gpr_num_tp, 4
+ .equ .L__gpr_num_t0, 5
+ .equ .L__gpr_num_t1, 6
+ .equ .L__gpr_num_t2, 7
+ .equ .L__gpr_num_s0, 8
+ .equ .L__gpr_num_s1, 9
+ .equ .L__gpr_num_a0, 10
+ .equ .L__gpr_num_a1, 11
+ .equ .L__gpr_num_a2, 12
+ .equ .L__gpr_num_a3, 13
+ .equ .L__gpr_num_a4, 14
+ .equ .L__gpr_num_a5, 15
+ .equ .L__gpr_num_a6, 16
+ .equ .L__gpr_num_a7, 17
+ .equ .L__gpr_num_s2, 18
+ .equ .L__gpr_num_s3, 19
+ .equ .L__gpr_num_s4, 20
+ .equ .L__gpr_num_s5, 21
+ .equ .L__gpr_num_s6, 22
+ .equ .L__gpr_num_s7, 23
+ .equ .L__gpr_num_s8, 24
+ .equ .L__gpr_num_s9, 25
+ .equ .L__gpr_num_s10, 26
+ .equ .L__gpr_num_s11, 27
+ .equ .L__gpr_num_t3, 28
+ .equ .L__gpr_num_t4, 29
+ .equ .L__gpr_num_t5, 30
+ .equ .L__gpr_num_t6, 31
+
+#else /* __ASSEMBLY__ */
+
+#define __DEFINE_ASM_GPR_NUMS \
+" .equ .L__gpr_num_zero, 0\n" \
+" .equ .L__gpr_num_ra, 1\n" \
+" .equ .L__gpr_num_sp, 2\n" \
+" .equ .L__gpr_num_gp, 3\n" \
+" .equ .L__gpr_num_tp, 4\n" \
+" .equ .L__gpr_num_t0, 5\n" \
+" .equ .L__gpr_num_t1, 6\n" \
+" .equ .L__gpr_num_t2, 7\n" \
+" .equ .L__gpr_num_s0, 8\n" \
+" .equ .L__gpr_num_s1, 9\n" \
+" .equ .L__gpr_num_a0, 10\n" \
+" .equ .L__gpr_num_a1, 11\n" \
+" .equ .L__gpr_num_a2, 12\n" \
+" .equ .L__gpr_num_a3, 13\n" \
+" .equ .L__gpr_num_a4, 14\n" \
+" .equ .L__gpr_num_a5, 15\n" \
+" .equ .L__gpr_num_a6, 16\n" \
+" .equ .L__gpr_num_a7, 17\n" \
+" .equ .L__gpr_num_s2, 18\n" \
+" .equ .L__gpr_num_s3, 19\n" \
+" .equ .L__gpr_num_s4, 20\n" \
+" .equ .L__gpr_num_s5, 21\n" \
+" .equ .L__gpr_num_s6, 22\n" \
+" .equ .L__gpr_num_s7, 23\n" \
+" .equ .L__gpr_num_s8, 24\n" \
+" .equ .L__gpr_num_s9, 25\n" \
+" .equ .L__gpr_num_s10, 26\n" \
+" .equ .L__gpr_num_s11, 27\n" \
+" .equ .L__gpr_num_t3, 28\n" \
+" .equ .L__gpr_num_t4, 29\n" \
+" .equ .L__gpr_num_t5, 30\n" \
+" .equ .L__gpr_num_t6, 31\n"
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_GPR_NUM_H */
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
index b00f503..0b85e36 100644
--- a/arch/riscv/include/asm/kasan.h
+++ b/arch/riscv/include/asm/kasan.h
@@ -27,13 +27,18 @@
*/
#define KASAN_SHADOW_SCALE_SHIFT 3
-#define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
-#define KASAN_SHADOW_START KERN_VIRT_START
-#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
+#define KASAN_SHADOW_SIZE (UL(1) << ((VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
+/*
+ * Depending on the size of the virtual address space, the region may not be
+ * aligned on PGDIR_SIZE, so force its alignment to ease its population.
+ */
+#define KASAN_SHADOW_START ((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK)
+#define KASAN_SHADOW_END MODULES_LOWEST_VADDR
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
void kasan_init(void);
asmlinkage void kasan_early_init(void);
+void kasan_swapper_init(void);
#endif
#endif
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index b3e5ff0..160e3a1 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -31,9 +31,20 @@
* When not using MMU this corresponds to the first free page in
* physical memory (aligned on a page boundary).
*/
+#ifdef CONFIG_64BIT
+#ifdef CONFIG_MMU
+#define PAGE_OFFSET kernel_map.page_offset
+#else
#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
-
-#define KERN_VIRT_SIZE (-PAGE_OFFSET)
+#endif
+/*
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
+ * define the PAGE_OFFSET value for SV39.
+ */
+#define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL)
+#else
+#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
+#endif /* CONFIG_64BIT */
#ifndef __ASSEMBLY__
@@ -86,6 +97,7 @@ extern unsigned long riscv_pfn_base;
#endif /* CONFIG_MMU */
struct kernel_mapping {
+ unsigned long page_offset;
unsigned long virt_addr;
uintptr_t phys_addr;
uintptr_t size;
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index 0af6933..1182300 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -11,6 +11,8 @@
#include <asm/tlb.h>
#ifdef CONFIG_MMU
+#define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PUD_FREE
#include <asm-generic/pgalloc.h>
static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -36,6 +38,44 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
+{
+ if (pgtable_l4_enabled) {
+ unsigned long pfn = virt_to_pfn(pud);
+
+ set_p4d(p4d, __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+ }
+}
+
+static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d,
+ pud_t *pud)
+{
+ if (pgtable_l4_enabled) {
+ unsigned long pfn = virt_to_pfn(pud);
+
+ set_p4d_safe(p4d,
+ __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+ }
+}
+
+#define pud_alloc_one pud_alloc_one
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ if (pgtable_l4_enabled)
+ return __pud_alloc_one(mm, addr);
+
+ return NULL;
+}
+
+#define pud_free pud_free
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+ if (pgtable_l4_enabled)
+ __pud_free(mm, pud);
+}
+
+#define __pud_free_tlb(tlb, pud, addr) pud_free((tlb)->mm, pud)
#endif /* __PAGETABLE_PMD_FOLDED */
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 228261a..bbbdd66 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -8,16 +8,36 @@
#include <linux/const.h>
-#define PGDIR_SHIFT 30
+extern bool pgtable_l4_enabled;
+
+#define PGDIR_SHIFT_L3 30
+#define PGDIR_SHIFT_L4 39
+#define PGDIR_SIZE_L3 (_AC(1, UL) << PGDIR_SHIFT_L3)
+
+#define PGDIR_SHIFT (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)
/* Size of region mapped by a page global directory */
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+/* pud is folded into pgd in case of 3-level page table */
+#define PUD_SHIFT 30
+#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE - 1))
+
#define PMD_SHIFT 21
/* Size of region mapped by a page middle directory */
#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE - 1))
+/* Page Upper Directory entry */
+typedef struct {
+ unsigned long pud;
+} pud_t;
+
+#define pud_val(x) ((x).pud)
+#define __pud(x) ((pud_t) { (x) })
+#define PTRS_PER_PUD (PAGE_SIZE / sizeof(pud_t))
+
/* Page Middle Directory entry */
typedef struct {
unsigned long pmd;
@@ -59,6 +79,16 @@ static inline void pud_clear(pud_t *pudp)
set_pud(pudp, __pud(0));
}
+static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot)
+{
+ return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline unsigned long _pud_pfn(pud_t pud)
+{
+ return pud_val(pud) >> _PAGE_PFN_SHIFT;
+}
+
static inline pmd_t *pud_pgtable(pud_t pud)
{
return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
@@ -69,6 +99,17 @@ static inline struct page *pud_page(pud_t pud)
return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT);
}
+#define mm_pud_folded mm_pud_folded
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+ if (pgtable_l4_enabled)
+ return false;
+
+ return true;
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
{
return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
@@ -84,4 +125,69 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pud_ERROR(e) \
+ pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
+
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+ if (pgtable_l4_enabled)
+ *p4dp = p4d;
+ else
+ set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
+}
+
+static inline int p4d_none(p4d_t p4d)
+{
+ if (pgtable_l4_enabled)
+ return (p4d_val(p4d) == 0);
+
+ return 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+ if (pgtable_l4_enabled)
+ return (p4d_val(p4d) & _PAGE_PRESENT);
+
+ return 1;
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+ if (pgtable_l4_enabled)
+ return !p4d_present(p4d);
+
+ return 0;
+}
+
+static inline void p4d_clear(p4d_t *p4d)
+{
+ if (pgtable_l4_enabled)
+ set_p4d(p4d, __p4d(0));
+}
+
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+ if (pgtable_l4_enabled)
+ return (pud_t *)pfn_to_virt(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+
+ return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) });
+}
+
+static inline struct page *p4d_page(p4d_t p4d)
+{
+ return pfn_to_page(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+}
+
+#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+#define pud_offset pud_offset
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+ if (pgtable_l4_enabled)
+ return p4d_pgtable(*p4d) + pud_index(address);
+
+ return (pud_t *)p4d;
+}
+
#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index 2ee4139..a6b0c89 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -31,7 +31,7 @@
* _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to
* distinguish them from swapped out pages
*/
-#define _PAGE_PROT_NONE _PAGE_READ
+#define _PAGE_PROT_NONE _PAGE_GLOBAL
#define _PAGE_PFN_SHIFT 10
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index bf204e7..7e949f2 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -24,8 +24,19 @@
#define KERNEL_LINK_ADDR PAGE_OFFSET
#endif
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+
+/*
+ * Half of the kernel address space (half of the entries of the page global
+ * directory) is for the direct mapping.
+ */
+#define KERN_VIRT_SIZE ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2)
+
#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
-#define VMALLOC_END (PAGE_OFFSET - 1)
+#define VMALLOC_END PAGE_OFFSET
#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
#define BPF_JIT_REGION_SIZE (SZ_128M)
@@ -39,8 +50,10 @@
/* Modules always live before the kernel */
#ifdef CONFIG_64BIT
-#define MODULES_VADDR (PFN_ALIGN((unsigned long)&_end) - SZ_2G)
-#define MODULES_END (PFN_ALIGN((unsigned long)&_start))
+/* This is used to define the end of the KASAN shadow region */
+#define MODULES_LOWEST_VADDR (KERNEL_LINK_ADDR - SZ_2G)
+#define MODULES_VADDR (PFN_ALIGN((unsigned long)&_end) - SZ_2G)
+#define MODULES_END (PFN_ALIGN((unsigned long)&_start))
#endif
/*
@@ -48,10 +61,16 @@
* struct pages to map half the virtual address space. Then
* position vmemmap directly below the VMALLOC region.
*/
+#ifdef CONFIG_64BIT
+#define VA_BITS (pgtable_l4_enabled ? 48 : 39)
+#else
+#define VA_BITS 32
+#endif
+
#define VMEMMAP_SHIFT \
- (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
+ (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT)
-#define VMEMMAP_END (VMALLOC_START - 1)
+#define VMEMMAP_END VMALLOC_START
#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE)
/*
@@ -83,8 +102,7 @@
#ifndef __ASSEMBLY__
-/* Page Upper Directory not used in RISC-V */
-#include <asm-generic/pgtable-nopud.h>
+#include <asm-generic/pgtable-nop4d.h>
#include <asm/page.h>
#include <asm/tlbflush.h>
#include <linux/mm_types.h>
@@ -107,19 +125,27 @@
#define XIP_FIXUP(addr) (addr)
#endif /* CONFIG_XIP_KERNEL */
-#ifdef CONFIG_MMU
-/* Number of entries in the page global directory */
-#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t))
-/* Number of entries in the page table */
-#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+struct pt_alloc_ops {
+ pte_t *(*get_pte_virt)(phys_addr_t pa);
+ phys_addr_t (*alloc_pte)(uintptr_t va);
+#ifndef __PAGETABLE_PMD_FOLDED
+ pmd_t *(*get_pmd_virt)(phys_addr_t pa);
+ phys_addr_t (*alloc_pmd)(uintptr_t va);
+ pud_t *(*get_pud_virt)(phys_addr_t pa);
+ phys_addr_t (*alloc_pud)(uintptr_t va);
+#endif
+};
+extern struct pt_alloc_ops pt_ops __initdata;
+
+#ifdef CONFIG_MMU
/* Number of PGD entries that a user-mode program can use */
#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
/* Page protection bits */
#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)
-#define PAGE_NONE __pgprot(_PAGE_PROT_NONE)
+#define PAGE_NONE __pgprot(_PAGE_PROT_NONE | _PAGE_READ)
#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ)
#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC)
@@ -628,11 +654,12 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
*
* Format of swap PTE:
* bit 0: _PAGE_PRESENT (zero)
- * bit 1: _PAGE_PROT_NONE (zero)
- * bits 2 to 6: swap type
- * bits 7 to XLEN-1: swap offset
+ * bit 1 to 3: _PAGE_LEAF (zero)
+ * bit 5: _PAGE_PROT_NONE (zero)
+ * bits 6 to 10: swap type
+ * bits 10 to XLEN-1: swap offset
*/
-#define __SWP_TYPE_SHIFT 2
+#define __SWP_TYPE_SHIFT 6
#define __SWP_TYPE_BITS 5
#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -648,12 +675,17 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
+#define __swp_entry_to_pmd(swp) __pmd((swp).val)
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
/*
* In the RV64 Linux scheme, we give the user half of the virtual-address space
* and give the kernel the other (upper) half.
*/
#ifdef CONFIG_64BIT
-#define KERN_VIRT_START (-(BIT(CONFIG_VA_BITS)) + TASK_SIZE)
+#define KERN_VIRT_START (-(BIT(VA_BITS)) + TASK_SIZE)
#else
#define KERN_VIRT_START FIXADDR_START
#endif
@@ -661,11 +693,22 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
/*
* Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
* Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ * Task size is:
+ * - 0x9fc00000 (~2.5GB) for RV32.
+ * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu
+ * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ *
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V
+ * Instruction Set Manual Volume II: Privileged Architecture" states that
+ * "load and store effective addresses, which are 64bits, must have bits
+ * 63–48 all equal to bit 47, or else a page-fault exception will occur."
*/
#ifdef CONFIG_64BIT
-#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
#else
-#define TASK_SIZE FIXADDR_START
+#define TASK_SIZE FIXADDR_START
+#define TASK_SIZE_MIN TASK_SIZE
#endif
#else /* CONFIG_MMU */
@@ -691,6 +734,8 @@ extern uintptr_t _dtb_early_pa;
#define dtb_early_va _dtb_early_va
#define dtb_early_pa _dtb_early_pa
#endif /* CONFIG_XIP_KERNEL */
+extern u64 satp_mode;
+extern bool pgtable_l4_enabled;
void paging_init(void);
void misc_mem_init(void);
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 9c46dd3..d1c37479 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -8,6 +8,7 @@
#define _ASM_RISCV_SBI_H
#include <linux/types.h>
+#include <linux/cpumask.h>
#ifdef CONFIG_RISCV_SBI
enum sbi_ext_id {
@@ -27,6 +28,7 @@ enum sbi_ext_id {
SBI_EXT_IPI = 0x735049,
SBI_EXT_RFENCE = 0x52464E43,
SBI_EXT_HSM = 0x48534D,
+ SBI_EXT_SRST = 0x53525354,
/* Experimentals extensions must lie within this range */
SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -78,6 +80,21 @@ enum sbi_hsm_hart_status {
SBI_HSM_HART_STATUS_STOP_PENDING,
};
+enum sbi_ext_srst_fid {
+ SBI_EXT_SRST_RESET = 0,
+};
+
+enum sbi_srst_reset_type {
+ SBI_SRST_RESET_TYPE_SHUTDOWN = 0,
+ SBI_SRST_RESET_TYPE_COLD_REBOOT,
+ SBI_SRST_RESET_TYPE_WARM_REBOOT,
+};
+
+enum sbi_srst_reset_reason {
+ SBI_SRST_RESET_REASON_NONE = 0,
+ SBI_SRST_RESET_REASON_SYS_FAILURE,
+};
+
#define SBI_SPEC_VERSION_DEFAULT 0x1
#define SBI_SPEC_VERSION_MAJOR_SHIFT 24
#define SBI_SPEC_VERSION_MAJOR_MASK 0x7f
@@ -112,27 +129,27 @@ long sbi_get_mimpid(void);
void sbi_set_timer(uint64_t stime_value);
void sbi_shutdown(void);
void sbi_clear_ipi(void);
-int sbi_send_ipi(const unsigned long *hart_mask);
-int sbi_remote_fence_i(const unsigned long *hart_mask);
-int sbi_remote_sfence_vma(const unsigned long *hart_mask,
+int sbi_send_ipi(const struct cpumask *cpu_mask);
+int sbi_remote_fence_i(const struct cpumask *cpu_mask);
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size);
-int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long asid);
-int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size);
-int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long vmid);
-int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size);
-int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long asid);
@@ -157,9 +174,17 @@ static inline unsigned long sbi_minor_version(void)
return sbi_spec_version & SBI_SPEC_VERSION_MINOR_MASK;
}
+/* Make SBI version */
+static inline unsigned long sbi_mk_version(unsigned long major,
+ unsigned long minor)
+{
+ return ((major & SBI_SPEC_VERSION_MAJOR_MASK) <<
+ SBI_SPEC_VERSION_MAJOR_SHIFT) | minor;
+}
+
int sbi_err_map_linux_errno(int err);
#else /* CONFIG_RISCV_SBI */
-static inline int sbi_remote_fence_i(const unsigned long *hart_mask) { return -1; }
+static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
static inline void sbi_init(void) {}
#endif /* CONFIG_RISCV_SBI */
#endif /* _ASM_RISCV_SBI_H */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index a7d2811..23170c9 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -43,7 +43,6 @@ void arch_send_call_function_ipi_mask(struct cpumask *mask);
void arch_send_call_function_single_ipi(int cpu);
int riscv_hartid_to_cpuid(int hartid);
-void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
/* Set custom IPI operations */
void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops);
@@ -63,8 +62,6 @@ asmlinkage void smp_callin(void);
#if defined CONFIG_HOTPLUG_CPU
int __cpu_disable(void);
void __cpu_die(unsigned int cpu);
-void cpu_stop(void);
-#else
#endif /* CONFIG_HOTPLUG_CPU */
#else
@@ -85,13 +82,6 @@ static inline unsigned long cpuid_to_hartid_map(int cpu)
return boot_cpu_hartid;
}
-static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
- struct cpumask *out)
-{
- cpumask_clear(out);
- cpumask_set_cpu(boot_cpu_hartid, out);
-}
-
static inline void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
{
}
diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h
index 45a7018..63acaec 100644
--- a/arch/riscv/include/asm/sparsemem.h
+++ b/arch/riscv/include/asm/sparsemem.h
@@ -4,7 +4,11 @@
#define _ASM_RISCV_SPARSEMEM_H
#ifdef CONFIG_SPARSEMEM
-#define MAX_PHYSMEM_BITS CONFIG_PA_BITS
+#ifdef CONFIG_64BIT
+#define MAX_PHYSMEM_BITS 56
+#else
+#define MAX_PHYSMEM_BITS 34
+#endif /* CONFIG_64BIT */
#define SECTION_SIZE_BITS 27
#endif /* CONFIG_SPARSEMEM */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index f314ff4..c701a5e 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -8,6 +8,7 @@
#ifndef _ASM_RISCV_UACCESS_H
#define _ASM_RISCV_UACCESS_H
+#include <asm/asm-extable.h>
#include <asm/pgtable.h> /* for TASK_SIZE */
/*
@@ -80,25 +81,14 @@ static inline int __access_ok(unsigned long addr, unsigned long size)
#define __get_user_asm(insn, x, ptr, err) \
do { \
- uintptr_t __tmp; \
__typeof__(x) __x; \
__asm__ __volatile__ ( \
"1:\n" \
- " " insn " %1, %3\n" \
+ " " insn " %1, %2\n" \
"2:\n" \
- " .section .fixup,\"ax\"\n" \
- " .balign 4\n" \
- "3:\n" \
- " li %0, %4\n" \
- " li %1, 0\n" \
- " jump 2b, %2\n" \
- " .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 3b\n" \
- " .previous" \
- : "+r" (err), "=&r" (__x), "=r" (__tmp) \
- : "m" (*(ptr)), "i" (-EFAULT)); \
+ _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %0, %1) \
+ : "+r" (err), "=&r" (__x) \
+ : "m" (*(ptr))); \
(x) = __x; \
} while (0)
@@ -110,30 +100,18 @@ do { \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u32 __lo, __hi; \
- uintptr_t __tmp; \
__asm__ __volatile__ ( \
"1:\n" \
- " lw %1, %4\n" \
+ " lw %1, %3\n" \
"2:\n" \
- " lw %2, %5\n" \
+ " lw %2, %4\n" \
"3:\n" \
- " .section .fixup,\"ax\"\n" \
- " .balign 4\n" \
- "4:\n" \
- " li %0, %6\n" \
- " li %1, 0\n" \
- " li %2, 0\n" \
- " jump 3b, %3\n" \
- " .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 4b\n" \
- " " RISCV_PTR " 2b, 4b\n" \
- " .previous" \
- : "+r" (err), "=&r" (__lo), "=r" (__hi), \
- "=r" (__tmp) \
- : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]), \
- "i" (-EFAULT)); \
+ _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1) \
+ _ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1) \
+ : "+r" (err), "=&r" (__lo), "=r" (__hi) \
+ : "m" (__ptr[__LSW]), "m" (__ptr[__MSW])); \
+ if (err) \
+ __hi = 0; \
(x) = (__typeof__(x))((__typeof__((x)-(x)))( \
(((u64)__hi << 32) | __lo))); \
} while (0)
@@ -221,24 +199,14 @@ do { \
#define __put_user_asm(insn, x, ptr, err) \
do { \
- uintptr_t __tmp; \
__typeof__(*(ptr)) __x = x; \
__asm__ __volatile__ ( \
"1:\n" \
- " " insn " %z3, %2\n" \
+ " " insn " %z2, %1\n" \
"2:\n" \
- " .section .fixup,\"ax\"\n" \
- " .balign 4\n" \
- "3:\n" \
- " li %0, %4\n" \
- " jump 2b, %1\n" \
- " .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 3b\n" \
- " .previous" \
- : "+r" (err), "=r" (__tmp), "=m" (*(ptr)) \
- : "rJ" (__x), "i" (-EFAULT)); \
+ _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %0) \
+ : "+r" (err), "=m" (*(ptr)) \
+ : "rJ" (__x)); \
} while (0)
#ifdef CONFIG_64BIT
@@ -249,28 +217,18 @@ do { \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u64 __x = (__typeof__((x)-(x)))(x); \
- uintptr_t __tmp; \
__asm__ __volatile__ ( \
"1:\n" \
- " sw %z4, %2\n" \
+ " sw %z3, %1\n" \
"2:\n" \
- " sw %z5, %3\n" \
+ " sw %z4, %2\n" \
"3:\n" \
- " .section .fixup,\"ax\"\n" \
- " .balign 4\n" \
- "4:\n" \
- " li %0, %6\n" \
- " jump 3b, %1\n" \
- " .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 4b\n" \
- " " RISCV_PTR " 2b, 4b\n" \
- " .previous" \
- : "+r" (err), "=r" (__tmp), \
+ _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %0) \
+ _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %0) \
+ : "+r" (err), \
"=m" (__ptr[__LSW]), \
"=m" (__ptr[__MSW]) \
- : "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT)); \
+ : "rJ" (__x), "rJ" (__x >> 32)); \
} while (0)
#endif /* CONFIG_64BIT */
@@ -388,81 +346,6 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
__clear_user(to, n) : n;
}
-/*
- * Atomic compare-and-exchange, but with a fixup for userspace faults. Faults
- * will set "err" to -EFAULT, while successful accesses return the previous
- * value.
- */
-#define __cmpxchg_user(ptr, old, new, err, size, lrb, scb) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- __typeof__(err) __err = 0; \
- register unsigned int __rc; \
- __enable_user_access(); \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- "0:\n" \
- " lr.w" #scb " %[ret], %[ptr]\n" \
- " bne %[ret], %z[old], 1f\n" \
- " sc.w" #lrb " %[rc], %z[new], %[ptr]\n" \
- " bnez %[rc], 0b\n" \
- "1:\n" \
- ".section .fixup,\"ax\"\n" \
- ".balign 4\n" \
- "2:\n" \
- " li %[err], %[efault]\n" \
- " jump 1b, %[rc]\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- ".balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 2b\n" \
- ".previous\n" \
- : [ret] "=&r" (__ret), \
- [rc] "=&r" (__rc), \
- [ptr] "+A" (*__ptr), \
- [err] "=&r" (__err) \
- : [old] "rJ" (__old), \
- [new] "rJ" (__new), \
- [efault] "i" (-EFAULT)); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- "0:\n" \
- " lr.d" #scb " %[ret], %[ptr]\n" \
- " bne %[ret], %z[old], 1f\n" \
- " sc.d" #lrb " %[rc], %z[new], %[ptr]\n" \
- " bnez %[rc], 0b\n" \
- "1:\n" \
- ".section .fixup,\"ax\"\n" \
- ".balign 4\n" \
- "2:\n" \
- " li %[err], %[efault]\n" \
- " jump 1b, %[rc]\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- ".balign " RISCV_SZPTR "\n" \
- " " RISCV_PTR " 1b, 2b\n" \
- ".previous\n" \
- : [ret] "=&r" (__ret), \
- [rc] "=&r" (__rc), \
- [ptr] "+A" (*__ptr), \
- [err] "=&r" (__err) \
- : [old] "rJ" (__old), \
- [new] "rJ" (__new), \
- [efault] "i" (-EFAULT)); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __disable_user_access(); \
- (err) = __err; \
- __ret; \
-})
-
#define HAVE_GET_KERNEL_NOFAULT
#define __get_kernel_nofault(dst, src, type, err_label) \
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 3397dda..612556f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -43,7 +43,8 @@
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SMP) += cpu_ops.o
-obj-$(CONFIG_SMP) += cpu_ops_spinwait.o
+
+obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 253126e..df0519a 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -12,6 +12,7 @@
#include <asm/kvm_host.h>
#include <asm/thread_info.h>
#include <asm/ptrace.h>
+#include <asm/cpu_ops_sbi.h>
void asm_offsets(void);
@@ -468,4 +469,6 @@ void asm_offsets(void)
DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
+ OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr);
+ OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
}
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index df84e0c..be7f05b 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -14,12 +14,6 @@
#include <asm/cpu_ops.h>
#include <asm/sbi.h>
-void cpu_stop(void);
-void arch_cpu_idle_dead(void)
-{
- cpu_stop();
-}
-
bool cpu_has_hotplug(unsigned int cpu)
{
if (cpu_ops[cpu]->cpu_stop)
@@ -75,7 +69,7 @@ void __cpu_die(unsigned int cpu)
/*
* Called from the idle thread for the CPU which has been shutdown.
*/
-void cpu_stop(void)
+void arch_cpu_idle_dead(void)
{
idle_task_exit();
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index f13b2c9..ad0a7e9 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -7,6 +7,7 @@
#include <linux/seq_file.h>
#include <linux/of.h>
#include <asm/smp.h>
+#include <asm/pgtable.h>
/*
* Returns the hart ID of the given device tree node, or -ENODEV if the node
@@ -71,18 +72,19 @@ static void print_isa(struct seq_file *f, const char *isa)
seq_puts(f, "\n");
}
-static void print_mmu(struct seq_file *f, const char *mmu_type)
+static void print_mmu(struct seq_file *f)
{
-#if defined(CONFIG_32BIT)
- if (strcmp(mmu_type, "riscv,sv32") != 0)
- return;
-#elif defined(CONFIG_64BIT)
- if (strcmp(mmu_type, "riscv,sv39") != 0 &&
- strcmp(mmu_type, "riscv,sv48") != 0)
- return;
-#endif
+ char sv_type[16];
- seq_printf(f, "mmu\t\t: %s\n", mmu_type+6);
+#if defined(CONFIG_32BIT)
+ strncpy(sv_type, "sv32", 5);
+#elif defined(CONFIG_64BIT)
+ if (pgtable_l4_enabled)
+ strncpy(sv_type, "sv48", 5);
+ else
+ strncpy(sv_type, "sv39", 5);
+#endif
+ seq_printf(f, "mmu\t\t: %s\n", sv_type);
}
static void *c_start(struct seq_file *m, loff_t *pos)
@@ -107,14 +109,13 @@ static int c_show(struct seq_file *m, void *v)
{
unsigned long cpu_id = (unsigned long)v - 1;
struct device_node *node = of_get_cpu_node(cpu_id, NULL);
- const char *compat, *isa, *mmu;
+ const char *compat, *isa;
seq_printf(m, "processor\t: %lu\n", cpu_id);
seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
if (!of_property_read_string(node, "riscv,isa", &isa))
print_isa(m, isa);
- if (!of_property_read_string(node, "mmu-type", &mmu))
- print_mmu(m, mmu);
+ print_mmu(m);
if (!of_property_read_string(node, "compatible", &compat)
&& strcmp(compat, "riscv"))
seq_printf(m, "uarch\t\t: %s\n", compat);
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index 1985884..170d07e 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -8,37 +8,29 @@
#include <linux/of.h>
#include <linux/string.h>
#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
#include <asm/cpu_ops.h>
#include <asm/sbi.h>
#include <asm/smp.h>
const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
-void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
-void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
-
extern const struct cpu_operations cpu_ops_sbi;
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
extern const struct cpu_operations cpu_ops_spinwait;
-
-void cpu_update_secondary_bootdata(unsigned int cpuid,
- struct task_struct *tidle)
-{
- int hartid = cpuid_to_hartid_map(cpuid);
-
- /* Make sure tidle is updated */
- smp_mb();
- WRITE_ONCE(__cpu_up_stack_pointer[hartid],
- task_stack_page(tidle) + THREAD_SIZE);
- WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
-}
+#else
+const struct cpu_operations cpu_ops_spinwait = {
+ .name = "",
+ .cpu_prepare = NULL,
+ .cpu_start = NULL,
+};
+#endif
void __init cpu_set_ops(int cpuid)
{
#if IS_ENABLED(CONFIG_RISCV_SBI)
if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
if (!cpuid)
- pr_info("SBI v0.2 HSM extension detected\n");
+ pr_info("SBI HSM extension detected\n");
cpu_ops[cpuid] = &cpu_ops_sbi;
} else
#endif
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 685fae7..dae29cb 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -7,13 +7,22 @@
#include <linux/init.h>
#include <linux/mm.h>
+#include <linux/sched/task_stack.h>
#include <asm/cpu_ops.h>
+#include <asm/cpu_ops_sbi.h>
#include <asm/sbi.h>
#include <asm/smp.h>
extern char secondary_start_sbi[];
const struct cpu_operations cpu_ops_sbi;
+/*
+ * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
+ * be invoked from multiple threads in parallel. Define a per cpu data
+ * to handle that.
+ */
+DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+
static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
unsigned long priv)
{
@@ -55,14 +64,19 @@ static int sbi_hsm_hart_get_status(unsigned long hartid)
static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
{
- int rc;
unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
int hartid = cpuid_to_hartid_map(cpuid);
+ unsigned long hsm_data;
+ struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
- cpu_update_secondary_bootdata(cpuid, tidle);
- rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
-
- return rc;
+ /* Make sure tidle is updated */
+ smp_mb();
+ bdata->task_ptr = tidle;
+ bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+ /* Make sure boot data is updated */
+ smp_mb();
+ hsm_data = __pa(bdata);
+ return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
}
static int sbi_cpu_prepare(unsigned int cpuid)
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index b2c957b..346847f 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -6,11 +6,36 @@
#include <linux/errno.h>
#include <linux/of.h>
#include <linux/string.h>
+#include <linux/sched/task_stack.h>
#include <asm/cpu_ops.h>
#include <asm/sbi.h>
#include <asm/smp.h>
const struct cpu_operations cpu_ops_spinwait;
+void *__cpu_spinwait_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_spinwait_task_pointer[NR_CPUS] __section(".data");
+
+static void cpu_update_secondary_bootdata(unsigned int cpuid,
+ struct task_struct *tidle)
+{
+ int hartid = cpuid_to_hartid_map(cpuid);
+
+ /*
+ * The hartid must be less than NR_CPUS to avoid out-of-bound access
+ * errors for __cpu_spinwait_stack/task_pointer. That is not always possible
+ * for platforms with discontiguous hartid numbering scheme. That's why
+ * spinwait booting is not the recommended approach for any platforms
+ * booting Linux in S-mode and can be disabled in the future.
+ */
+ if (hartid == INVALID_HARTID || hartid >= NR_CPUS)
+ return;
+
+ /* Make sure tidle is updated */
+ smp_mb();
+ WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
+ task_stack_page(tidle) + THREAD_SIZE);
+ WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
+}
static int spinwait_cpu_prepare(unsigned int cpuid)
{
@@ -28,7 +53,7 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
* selects the first cpu to boot the kernel and causes the remainder
* of the cpus to spin in a loop waiting for their stack pointer to be
* setup by that main cpu. Writing to bootdata
- * (i.e __cpu_up_stack_pointer) signals to the spinning cpus that they
+ * (i.e __cpu_spinwait_stack_pointer) signals to the spinning cpus that they
* can continue the boot process.
*/
cpu_update_secondary_bootdata(cpuid, tidle);
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index f52f01e..2363b43 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -11,6 +11,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/csr.h>
+#include <asm/cpu_ops_sbi.h>
#include <asm/hwcap.h>
#include <asm/image.h>
#include "efi-header.S"
@@ -105,7 +106,8 @@
/* Compute satp for kernel page tables, but don't load it yet */
srl a2, a0, PAGE_SHIFT
- li a1, SATP_MODE
+ la a1, satp_mode
+ REG_L a1, 0(a1)
or a2, a2, a1
/*
@@ -135,7 +137,7 @@
/*
* Switch to kernel page tables. A full fence is necessary in order to
* avoid using the trampoline translations, which are only correct for
- * the first superpage. Fetching the fence is guarnteed to work
+ * the first superpage. Fetching the fence is guaranteed to work
* because that first superpage is translated the same way.
*/
csrw CSR_SATP, a2
@@ -167,18 +169,17 @@
la a3, .Lsecondary_park
csrw CSR_TVEC, a3
- slli a3, a0, LGREG
- la a4, __cpu_up_stack_pointer
- XIP_FIXUP_OFFSET a4
- la a5, __cpu_up_task_pointer
- XIP_FIXUP_OFFSET a5
- add a4, a3, a4
- add a5, a3, a5
- REG_L sp, (a4)
- REG_L tp, (a5)
+ /* a0 contains the hartid & a1 contains boot data */
+ li a2, SBI_HART_BOOT_TASK_PTR_OFFSET
+ XIP_FIXUP_OFFSET a2
+ add a2, a2, a1
+ REG_L tp, (a2)
+ li a3, SBI_HART_BOOT_STACK_PTR_OFFSET
+ XIP_FIXUP_OFFSET a3
+ add a3, a3, a1
+ REG_L sp, (a3)
- .global secondary_start_common
-secondary_start_common:
+.Lsecondary_start_common:
#ifdef CONFIG_MMU
/* Enable virtual memory and relocate to virtual address */
@@ -258,13 +259,13 @@
li t0, SR_FS
csrc CSR_STATUS, t0
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
li t0, CONFIG_NR_CPUS
blt a0, t0, .Lgood_cores
tail .Lsecondary_park
.Lgood_cores:
-#endif
+ /* The lottery system is only required for spinwait booting method */
#ifndef CONFIG_XIP_KERNEL
/* Pick one hart to run the main boot sequence */
la a3, hart_lottery
@@ -283,6 +284,10 @@
/* first time here if hart_lottery in RAM is not set */
beq t0, t1, .Lsecondary_start
+#endif /* CONFIG_XIP */
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
+
+#ifdef CONFIG_XIP_KERNEL
la sp, _end + THREAD_SIZE
XIP_FIXUP_OFFSET sp
mv s0, a0
@@ -339,16 +344,16 @@
call soc_early_init
tail start_kernel
+#if CONFIG_RISCV_BOOT_SPINWAIT
.Lsecondary_start:
-#ifdef CONFIG_SMP
/* Set trap vector to spin forever to help debug */
la a3, .Lsecondary_park
csrw CSR_TVEC, a3
slli a3, a0, LGREG
- la a1, __cpu_up_stack_pointer
+ la a1, __cpu_spinwait_stack_pointer
XIP_FIXUP_OFFSET a1
- la a2, __cpu_up_task_pointer
+ la a2, __cpu_spinwait_task_pointer
XIP_FIXUP_OFFSET a2
add a1, a3, a1
add a2, a3, a2
@@ -365,8 +370,8 @@
beqz tp, .Lwait_for_cpu_up
fence
- tail secondary_start_common
-#endif
+ tail .Lsecondary_start_common
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
END(_start_kernel)
@@ -448,7 +453,3 @@
ret
END(reset_regs)
#endif /* CONFIG_RISCV_M_MODE */
-
-__PAGE_ALIGNED_BSS
- /* Empty zero page */
- .balign PAGE_SIZE
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
index aabbc3a..726731a 100644
--- a/arch/riscv/kernel/head.h
+++ b/arch/riscv/kernel/head.h
@@ -16,7 +16,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa);
asmlinkage void __init __copy_data(void);
#endif
-extern void *__cpu_up_stack_pointer[];
-extern void *__cpu_up_task_pointer[];
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
+extern void *__cpu_spinwait_stack_pointer[];
+extern void *__cpu_spinwait_task_pointer[];
+#endif
#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S
index a80b52a..059c5e2 100644
--- a/arch/riscv/kernel/kexec_relocate.S
+++ b/arch/riscv/kernel/kexec_relocate.S
@@ -159,25 +159,15 @@
* s0: (const) Phys address to jump to
* s1: (const) Phys address of the FDT image
* s2: (const) The hartid of the current hart
- * s3: (const) kernel_map.va_pa_offset, used when switching MMU off
*/
mv s0, a1
mv s1, a2
mv s2, a3
- mv s3, a4
/* Disable / cleanup interrupts */
csrw CSR_SIE, zero
csrw CSR_SIP, zero
- /* Switch to physical addressing */
- la s4, 1f
- sub s4, s4, s3
- csrw CSR_STVEC, s4
- csrw CSR_SATP, zero
-
-.align 2
-1:
/* Pass the arguments to the next kernel / Cleanup*/
mv a0, s2
mv a1, s1
@@ -214,7 +204,15 @@
csrw CSR_SCAUSE, zero
csrw CSR_SSCRATCH, zero
- jalr zero, a2, 0
+ /*
+ * Switch to physical addressing
+ * This will also trigger a jump to CSR_STVEC
+ * which in this case is the address of the new
+ * kernel.
+ */
+ csrw CSR_STVEC, a2
+ csrw CSR_SATP, zero
+
SYM_CODE_END(riscv_kexec_norelocate)
.section ".rodata"
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index e6eca27..cbef0fc 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -169,7 +169,8 @@ machine_kexec(struct kimage *image)
struct kimage_arch *internal = &image->arch;
unsigned long jump_addr = (unsigned long) image->start;
unsigned long first_ind_entry = (unsigned long) &image->head;
- unsigned long this_hart_id = raw_smp_processor_id();
+ unsigned long this_cpu_id = smp_processor_id();
+ unsigned long this_hart_id = cpuid_to_hartid_map(this_cpu_id);
unsigned long fdt_addr = internal->fdt_addr;
void *control_code_buffer = page_address(image->control_code_page);
riscv_kexec_method kexec_method = NULL;
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 9c05111..a892437 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -42,12 +42,10 @@ static int riscv_gpr_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- int ret;
struct pt_regs *regs;
regs = task_pt_regs(target);
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
- return ret;
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
}
#ifdef CONFIG_FPU
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 7402a41..f72527f 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
#include <linux/init.h>
#include <linux/pm.h>
+#include <linux/reboot.h>
#include <asm/sbi.h>
#include <asm/smp.h>
@@ -15,8 +16,8 @@ unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
EXPORT_SYMBOL(sbi_spec_version);
static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init;
-static int (*__sbi_send_ipi)(const unsigned long *hart_mask) __ro_after_init;
-static int (*__sbi_rfence)(int fid, const unsigned long *hart_mask,
+static int (*__sbi_send_ipi)(const struct cpumask *cpu_mask) __ro_after_init;
+static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask,
unsigned long start, unsigned long size,
unsigned long arg4, unsigned long arg5) __ro_after_init;
@@ -66,6 +67,30 @@ int sbi_err_map_linux_errno(int err)
EXPORT_SYMBOL(sbi_err_map_linux_errno);
#ifdef CONFIG_RISCV_SBI_V01
+static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask)
+{
+ unsigned long cpuid, hartid;
+ unsigned long hmask = 0;
+
+ /*
+ * There is no maximum hartid concept in RISC-V and NR_CPUS must not be
+ * associated with hartid. As SBI v0.1 is only kept for backward compatibility
+ * and will be removed in the future, there is no point in supporting hartid
+ * greater than BITS_PER_LONG (32 for RV32 and 64 for RV64). Ideally, SBI v0.2
+ * should be used for platforms with hartid greater than BITS_PER_LONG.
+ */
+ for_each_cpu(cpuid, cpu_mask) {
+ hartid = cpuid_to_hartid_map(cpuid);
+ if (hartid >= BITS_PER_LONG) {
+ pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n");
+ break;
+ }
+ hmask |= 1 << hartid;
+ }
+
+ return hmask;
+}
+
/**
* sbi_console_putchar() - Writes given character to the console device.
* @ch: The data to be written to the console.
@@ -131,33 +156,44 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
#endif
}
-static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
{
- sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)hart_mask,
+ unsigned long hart_mask;
+
+ if (!cpu_mask)
+ cpu_mask = cpu_online_mask;
+ hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
+
+ sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask),
0, 0, 0, 0, 0);
return 0;
}
-static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
unsigned long start, unsigned long size,
unsigned long arg4, unsigned long arg5)
{
int result = 0;
+ unsigned long hart_mask;
+
+ if (!cpu_mask)
+ cpu_mask = cpu_online_mask;
+ hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
/* v0.2 function IDs are equivalent to v0.1 extension IDs */
switch (fid) {
case SBI_EXT_RFENCE_REMOTE_FENCE_I:
sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0,
- (unsigned long)hart_mask, 0, 0, 0, 0, 0);
+ (unsigned long)&hart_mask, 0, 0, 0, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0,
- (unsigned long)hart_mask, start, size,
+ (unsigned long)&hart_mask, start, size,
0, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0,
- (unsigned long)hart_mask, start, size,
+ (unsigned long)&hart_mask, start, size,
arg4, 0, 0);
break;
default:
@@ -179,7 +215,7 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
sbi_major_version(), sbi_minor_version());
}
-static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
{
pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
sbi_major_version(), sbi_minor_version());
@@ -187,7 +223,7 @@ static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
return 0;
}
-static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
unsigned long start, unsigned long size,
unsigned long arg4, unsigned long arg5)
{
@@ -211,37 +247,33 @@ static void __sbi_set_timer_v02(uint64_t stime_value)
#endif
}
-static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask)
{
- unsigned long hartid, hmask_val, hbase;
- struct cpumask tmask;
+ unsigned long hartid, cpuid, hmask = 0, hbase = 0;
struct sbiret ret = {0};
int result;
- if (!hart_mask || !(*hart_mask)) {
- riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
- hart_mask = cpumask_bits(&tmask);
- }
+ if (!cpu_mask)
+ cpu_mask = cpu_online_mask;
- hmask_val = 0;
- hbase = 0;
- for_each_set_bit(hartid, hart_mask, NR_CPUS) {
- if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+ for_each_cpu(cpuid, cpu_mask) {
+ hartid = cpuid_to_hartid_map(cpuid);
+ if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
- hmask_val, hbase, 0, 0, 0, 0);
+ hmask, hbase, 0, 0, 0, 0);
if (ret.error)
goto ecall_failed;
- hmask_val = 0;
+ hmask = 0;
hbase = 0;
}
- if (!hmask_val)
+ if (!hmask)
hbase = hartid;
- hmask_val |= 1UL << (hartid - hbase);
+ hmask |= 1UL << (hartid - hbase);
}
- if (hmask_val) {
+ if (hmask) {
ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
- hmask_val, hbase, 0, 0, 0, 0);
+ hmask, hbase, 0, 0, 0, 0);
if (ret.error)
goto ecall_failed;
}
@@ -251,11 +283,11 @@ static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
ecall_failed:
result = sbi_err_map_linux_errno(ret.error);
pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
- __func__, hbase, hmask_val, result);
+ __func__, hbase, hmask, result);
return result;
}
-static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
+static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask,
unsigned long hbase, unsigned long start,
unsigned long size, unsigned long arg4,
unsigned long arg5)
@@ -266,31 +298,31 @@ static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
switch (fid) {
case SBI_EXT_RFENCE_REMOTE_FENCE_I:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, 0, 0, 0, 0);
+ ret = sbi_ecall(ext, fid, hmask, hbase, 0, 0, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, arg4, 0);
break;
case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, arg4, 0);
break;
case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, 0, 0);
break;
case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
- ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ ret = sbi_ecall(ext, fid, hmask, hbase, start,
size, arg4, 0);
break;
default:
@@ -302,43 +334,39 @@ static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
if (ret.error) {
result = sbi_err_map_linux_errno(ret.error);
pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
- __func__, hbase, hmask_val, result);
+ __func__, hbase, hmask, result);
}
return result;
}
-static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask,
unsigned long start, unsigned long size,
unsigned long arg4, unsigned long arg5)
{
- unsigned long hmask_val, hartid, hbase;
- struct cpumask tmask;
+ unsigned long hartid, cpuid, hmask = 0, hbase = 0;
int result;
- if (!hart_mask || !(*hart_mask)) {
- riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
- hart_mask = cpumask_bits(&tmask);
- }
+ if (!cpu_mask)
+ cpu_mask = cpu_online_mask;
- hmask_val = 0;
- hbase = 0;
- for_each_set_bit(hartid, hart_mask, NR_CPUS) {
- if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
- result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+ for_each_cpu(cpuid, cpu_mask) {
+ hartid = cpuid_to_hartid_map(cpuid);
+ if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
+ result = __sbi_rfence_v02_call(fid, hmask, hbase,
start, size, arg4, arg5);
if (result)
return result;
- hmask_val = 0;
+ hmask = 0;
hbase = 0;
}
- if (!hmask_val)
+ if (!hmask)
hbase = hartid;
- hmask_val |= 1UL << (hartid - hbase);
+ hmask |= 1UL << (hartid - hbase);
}
- if (hmask_val) {
- result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+ if (hmask) {
+ result = __sbi_rfence_v02_call(fid, hmask, hbase,
start, size, arg4, arg5);
if (result)
return result;
@@ -360,44 +388,44 @@ void sbi_set_timer(uint64_t stime_value)
/**
* sbi_send_ipi() - Send an IPI to any hart.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
*
* Return: 0 on success, appropriate linux error code otherwise.
*/
-int sbi_send_ipi(const unsigned long *hart_mask)
+int sbi_send_ipi(const struct cpumask *cpu_mask)
{
- return __sbi_send_ipi(hart_mask);
+ return __sbi_send_ipi(cpu_mask);
}
EXPORT_SYMBOL(sbi_send_ipi);
/**
* sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
*
* Return: 0 on success, appropriate linux error code otherwise.
*/
-int sbi_remote_fence_i(const unsigned long *hart_mask)
+int sbi_remote_fence_i(const struct cpumask *cpu_mask)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
- hart_mask, 0, 0, 0, 0);
+ cpu_mask, 0, 0, 0, 0);
}
EXPORT_SYMBOL(sbi_remote_fence_i);
/**
* sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
* harts for the specified virtual address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the virtual address
* @size: Total size of the virtual address range.
*
* Return: 0 on success, appropriate linux error code otherwise.
*/
-int sbi_remote_sfence_vma(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
- hart_mask, start, size, 0, 0);
+ cpu_mask, start, size, 0, 0);
}
EXPORT_SYMBOL(sbi_remote_sfence_vma);
@@ -405,38 +433,38 @@ EXPORT_SYMBOL(sbi_remote_sfence_vma);
* sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
* remote harts for a virtual address range belonging to a specific ASID.
*
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the virtual address
* @size: Total size of the virtual address range.
* @asid: The value of address space identifier (ASID).
*
* Return: 0 on success, appropriate linux error code otherwise.
*/
-int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long asid)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
- hart_mask, start, size, asid, 0);
+ cpu_mask, start, size, asid, 0);
}
EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
/**
* sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote
* harts for the specified guest physical address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the guest physical address
* @size: Total size of the guest physical address range.
*
* Return: None
*/
-int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
- hart_mask, start, size, 0, 0);
+ cpu_mask, start, size, 0, 0);
}
EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
@@ -444,38 +472,38 @@ EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
* sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given
* remote harts for a guest physical address range belonging to a specific VMID.
*
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the guest physical address
* @size: Total size of the guest physical address range.
* @vmid: The value of guest ID (VMID).
*
* Return: 0 if success, Error otherwise.
*/
-int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long vmid)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
- hart_mask, start, size, vmid, 0);
+ cpu_mask, start, size, vmid, 0);
}
EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid);
/**
* sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote
* harts for the current guest virtual address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the current guest virtual address
* @size: Total size of the current guest virtual address range.
*
* Return: None
*/
-int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
- hart_mask, start, size, 0, 0);
+ cpu_mask, start, size, 0, 0);
}
EXPORT_SYMBOL(sbi_remote_hfence_vvma);
@@ -484,23 +512,49 @@ EXPORT_SYMBOL(sbi_remote_hfence_vvma);
* remote harts for current guest virtual address range belonging to a specific
* ASID.
*
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
* @start: Start of the current guest virtual address
* @size: Total size of the current guest virtual address range.
* @asid: The value of address space identifier (ASID).
*
* Return: None
*/
-int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long asid)
{
return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
- hart_mask, start, size, asid, 0);
+ cpu_mask, start, size, asid, 0);
}
EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid);
+static void sbi_srst_reset(unsigned long type, unsigned long reason)
+{
+ sbi_ecall(SBI_EXT_SRST, SBI_EXT_SRST_RESET, type, reason,
+ 0, 0, 0, 0);
+ pr_warn("%s: type=0x%lx reason=0x%lx failed\n",
+ __func__, type, reason);
+}
+
+static int sbi_srst_reboot(struct notifier_block *this,
+ unsigned long mode, void *cmd)
+{
+ sbi_srst_reset((mode == REBOOT_WARM || mode == REBOOT_SOFT) ?
+ SBI_SRST_RESET_TYPE_WARM_REBOOT :
+ SBI_SRST_RESET_TYPE_COLD_REBOOT,
+ SBI_SRST_RESET_REASON_NONE);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block sbi_srst_reboot_nb;
+
+static void sbi_srst_power_off(void)
+{
+ sbi_srst_reset(SBI_SRST_RESET_TYPE_SHUTDOWN,
+ SBI_SRST_RESET_REASON_NONE);
+}
+
/**
* sbi_probe_extension() - Check if an SBI extension ID is supported or not.
* @extid: The extension ID to be probed.
@@ -564,11 +618,7 @@ long sbi_get_mimpid(void)
static void sbi_send_cpumask_ipi(const struct cpumask *target)
{
- struct cpumask hartid_mask;
-
- riscv_cpuid_to_hartid_mask(target, &hartid_mask);
-
- sbi_send_ipi(cpumask_bits(&hartid_mask));
+ sbi_send_ipi(target);
}
static const struct riscv_ipi_ops sbi_ipi_ops = {
@@ -608,6 +658,14 @@ void __init sbi_init(void)
} else {
__sbi_rfence = __sbi_rfence_v01;
}
+ if ((sbi_spec_version >= sbi_mk_version(0, 3)) &&
+ (sbi_probe_extension(SBI_EXT_SRST) > 0)) {
+ pr_info("SBI SRST extension detected\n");
+ pm_power_off = sbi_srst_power_off;
+ sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot;
+ sbi_srst_reboot_nb.priority = 192;
+ register_restart_handler(&sbi_srst_reboot_nb);
+ }
} else {
__sbi_set_timer = __sbi_set_timer_v01;
__sbi_send_ipi = __sbi_send_ipi_v01;
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 2f6da84..b5d30ea 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -59,16 +59,6 @@ int riscv_hartid_to_cpuid(int hartid)
return -ENOENT;
}
-void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
-{
- int cpu;
-
- cpumask_clear(out);
- for_each_cpu(cpu, in)
- cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
-}
-EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
-
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
return phys_id == cpuid_to_hartid_map(cpu);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index bd82375..622f226 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -96,7 +96,7 @@ void __init setup_smp(void)
if (cpuid >= NR_CPUS) {
pr_warn("Invalid cpuid [%d] for hartid [%d]\n",
cpuid, hart);
- break;
+ continue;
}
cpuid_to_hartid_map(cpuid) = hart;
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index f5ed082..75e0fa8 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -45,7 +45,6 @@
ENTRY_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
- *(.fixup)
_etext = .;
}
RO_DATA(L1_CACHE_BYTES)
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 5104f3a..4e6c88a 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -4,7 +4,7 @@
* Copyright (C) 2017 SiFive
*/
-#define RO_EXCEPTION_TABLE_ALIGN 16
+#define RO_EXCEPTION_TABLE_ALIGN 4
#ifdef CONFIG_XIP_KERNEL
#include "vmlinux-xip.lds.S"
@@ -48,7 +48,6 @@
ENTRY_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
- *(.fixup)
_etext = .;
}
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 9af67db..f80a34f 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -114,7 +114,6 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr,
static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
{
- struct cpumask hmask;
unsigned long size = PAGE_SIZE;
struct kvm_vmid *vmid = &kvm->arch.vmid;
@@ -127,8 +126,7 @@ static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
* where the Guest/VM is running.
*/
preempt_disable();
- riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask);
- sbi_remote_hfence_gvma_vmid(cpumask_bits(&hmask), addr, size,
+ sbi_remote_hfence_gvma_vmid(cpu_online_mask, addr, size,
READ_ONCE(vmid->vmid));
preempt_enable();
}
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 00036b7..1bc0608 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -82,7 +82,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
{
int ret = 0;
unsigned long i;
- struct cpumask cm, hm;
+ struct cpumask cm;
struct kvm_vcpu *tmp;
struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
unsigned long hmask = cp->a0;
@@ -90,7 +90,6 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
unsigned long funcid = cp->a6;
cpumask_clear(&cm);
- cpumask_clear(&hm);
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
if (hbase != -1UL) {
if (tmp->vcpu_id < hbase)
@@ -103,17 +102,15 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
cpumask_set_cpu(tmp->cpu, &cm);
}
- riscv_cpuid_to_hartid_mask(&cm, &hm);
-
switch (funcid) {
case SBI_EXT_RFENCE_REMOTE_FENCE_I:
- ret = sbi_remote_fence_i(cpumask_bits(&hm));
+ ret = sbi_remote_fence_i(&cm);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
- ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), cp->a2, cp->a3);
+ ret = sbi_remote_hfence_vvma(&cm, cp->a2, cp->a3);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
- ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), cp->a2,
+ ret = sbi_remote_hfence_vvma_asid(&cm, cp->a2,
cp->a3, cp->a4);
break;
case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c
index 4c7e13e..07e2de1 100644
--- a/arch/riscv/kvm/vcpu_sbi_v01.c
+++ b/arch/riscv/kvm/vcpu_sbi_v01.c
@@ -38,7 +38,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
int i, ret = 0;
u64 next_cycle;
struct kvm_vcpu *rvcpu;
- struct cpumask cm, hm;
+ struct cpumask cm;
struct kvm *kvm = vcpu->kvm;
struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
@@ -101,15 +101,12 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
continue;
cpumask_set_cpu(rvcpu->cpu, &cm);
}
- riscv_cpuid_to_hartid_mask(&cm, &hm);
if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I)
- ret = sbi_remote_fence_i(cpumask_bits(&hm));
+ ret = sbi_remote_fence_i(&cm);
else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA)
- ret = sbi_remote_hfence_vvma(cpumask_bits(&hm),
- cp->a1, cp->a2);
+ ret = sbi_remote_hfence_vvma(&cm, cp->a1, cp->a2);
else
- ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm),
- cp->a1, cp->a2, cp->a3);
+ ret = sbi_remote_hfence_vvma_asid(&cm, cp->a1, cp->a2, cp->a3);
break;
default:
ret = -EINVAL;
diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c
index 807228f..2fa4f7b 100644
--- a/arch/riscv/kvm/vmid.c
+++ b/arch/riscv/kvm/vmid.c
@@ -67,7 +67,6 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu)
{
unsigned long i;
struct kvm_vcpu *v;
- struct cpumask hmask;
struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid;
if (!kvm_riscv_stage2_vmid_ver_changed(vmid))
@@ -102,8 +101,7 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu)
* running, we force VM exits on all host CPUs using IPI and
* flush all Guest TLBs.
*/
- riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask);
- sbi_remote_hfence_gvma(cpumask_bits(&hmask), 0, 0);
+ sbi_remote_hfence_gvma(cpu_online_mask, 0, 0);
}
vmid->vmid = vmid_next;
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 63bc691c..8c475f4 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -1,15 +1,13 @@
#include <linux/linkage.h>
#include <asm-generic/export.h>
#include <asm/asm.h>
+#include <asm/asm-extable.h>
#include <asm/csr.h>
.macro fixup op reg addr lbl
100:
\op \reg, \addr
- .section __ex_table,"a"
- .balign RISCV_SZPTR
- RISCV_PTR 100b, \lbl
- .previous
+ _asm_extable 100b, \lbl
.endm
ENTRY(__asm_copy_to_user)
@@ -173,6 +171,13 @@
csrc CSR_STATUS, t6
li a0, 0
ret
+
+ /* Exception fixup code */
+10:
+ /* Disable access to user memory */
+ csrs CSR_STATUS, t6
+ mv a0, t5
+ ret
ENDPROC(__asm_copy_to_user)
ENDPROC(__asm_copy_from_user)
EXPORT_SYMBOL(__asm_copy_to_user)
@@ -218,19 +223,12 @@
addi a0, a0, 1
bltu a0, a3, 5b
j 3b
-ENDPROC(__clear_user)
-EXPORT_SYMBOL(__clear_user)
- .section .fixup,"ax"
- .balign 4
- /* Fixup code for __copy_user(10) and __clear_user(11) */
-10:
- /* Disable access to user memory */
- csrs CSR_STATUS, t6
- mv a0, t5
- ret
+ /* Exception fixup code */
11:
+ /* Disable access to user memory */
csrs CSR_STATUS, t6
mv a0, a1
ret
- .previous
+ENDPROC(__clear_user)
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 89f8106..6cb7d96 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -67,10 +67,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
*/
smp_mb();
} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
- cpumask_t hartid_mask;
-
- riscv_cpuid_to_hartid_mask(&others, &hartid_mask);
- sbi_remote_fence_i(cpumask_bits(&hartid_mask));
+ sbi_remote_fence_i(&others);
} else {
on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
}
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index ea54cc0..7acbfbd 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -192,7 +192,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
switch_mm_fast:
csr_write(CSR_SATP, virt_to_pfn(mm->pgd) |
((cntx & asid_mask) << SATP_ASID_SHIFT) |
- SATP_MODE);
+ satp_mode);
if (need_flush_tlb)
local_flush_tlb_all();
@@ -201,7 +201,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
static void set_mm_noasid(struct mm_struct *mm)
{
/* Switch the page table and blindly nuke entire local TLB */
- csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | SATP_MODE);
+ csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
local_flush_tlb_all();
}
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index ddb7d3b..05978f7 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -7,27 +7,65 @@
*/
+#include <linux/bitfield.h>
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <asm/asm-extable.h>
+#include <asm/ptrace.h>
-#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
-int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs);
-#endif
-
-int fixup_exception(struct pt_regs *regs)
+static inline unsigned long
+get_ex_fixup(const struct exception_table_entry *ex)
{
- const struct exception_table_entry *fixup;
+ return ((unsigned long)&ex->fixup + ex->fixup);
+}
- fixup = search_exception_tables(regs->epc);
- if (!fixup)
- return 0;
+static bool ex_handler_fixup(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
+{
+ regs->epc = get_ex_fixup(ex);
+ return true;
+}
-#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
- if (regs->epc >= BPF_JIT_REGION_START && regs->epc < BPF_JIT_REGION_END)
- return rv_bpf_fixup_exception(fixup, regs);
-#endif
+static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
+ unsigned long val)
+{
+ if (unlikely(offset > MAX_REG_OFFSET))
+ return;
- regs->epc = fixup->fixup;
- return 1;
+ if (!offset)
+ *(unsigned long *)((unsigned long)regs + offset) = val;
+}
+
+static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
+{
+ int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
+ int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data);
+
+ regs_set_gpr(regs, reg_err, -EFAULT);
+ regs_set_gpr(regs, reg_zero, 0);
+
+ regs->epc = get_ex_fixup(ex);
+ return true;
+}
+
+bool fixup_exception(struct pt_regs *regs)
+{
+ const struct exception_table_entry *ex;
+
+ ex = search_exception_tables(regs->epc);
+ if (!ex)
+ return false;
+
+ switch (ex->type) {
+ case EX_TYPE_FIXUP:
+ return ex_handler_fixup(ex, regs);
+ case EX_TYPE_BPF:
+ return ex_handler_bpf(ex, regs);
+ case EX_TYPE_UACCESS_ERR_ZERO:
+ return ex_handler_uaccess_err_zero(ex, regs);
+ }
+
+ BUG();
}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 02a0ee2..4e9efbe 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -235,7 +235,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
* only copy the information from the master page table,
* nothing more.
*/
- if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END))) {
+ if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
vmalloc_fault(regs, code, addr);
return;
}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 24b2b80..cf4d018 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -37,13 +37,19 @@ EXPORT_SYMBOL(kernel_map);
#define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
#endif
+#ifdef CONFIG_64BIT
+u64 satp_mode = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_48 : SATP_MODE_39;
+#else
+u64 satp_mode = SATP_MODE_32;
+#endif
+EXPORT_SYMBOL(satp_mode);
+
+bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+EXPORT_SYMBOL(pgtable_l4_enabled);
+
phys_addr_t phys_ram_base __ro_after_init;
EXPORT_SYMBOL(phys_ram_base);
-#ifdef CONFIG_XIP_KERNEL
-extern char _xiprom[], _exiprom[], __data_loc;
-#endif
-
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
__page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
@@ -53,15 +59,6 @@ extern char _start[];
void *_dtb_early_va __initdata;
uintptr_t _dtb_early_pa __initdata;
-struct pt_alloc_ops {
- pte_t *(*get_pte_virt)(phys_addr_t pa);
- phys_addr_t (*alloc_pte)(uintptr_t va);
-#ifndef __PAGETABLE_PMD_FOLDED
- pmd_t *(*get_pmd_virt)(phys_addr_t pa);
- phys_addr_t (*alloc_pmd)(uintptr_t va);
-#endif
-};
-
static phys_addr_t dma32_phys_limit __initdata;
static void __init zone_sizes_init(void)
@@ -102,10 +99,14 @@ static void __init print_vm_layout(void)
(unsigned long)VMALLOC_END);
print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
(unsigned long)high_memory);
-#ifdef CONFIG_64BIT
- print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
- (unsigned long)ADDRESS_SPACE_END);
+ if (IS_ENABLED(CONFIG_64BIT)) {
+#ifdef CONFIG_KASAN
+ print_mlm("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
#endif
+
+ print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
+ (unsigned long)ADDRESS_SPACE_END);
+ }
}
#else
static void print_vm_layout(void) { }
@@ -130,18 +131,8 @@ void __init mem_init(void)
print_vm_layout();
}
-/*
- * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
- * whereas for 64-bit kernel, the end of the virtual address space is occupied
- * by the modules/BPF/kernel mappings which reduces the available size of the
- * linear mapping.
- * Limit the memory size via mem.
- */
-#ifdef CONFIG_64BIT
-static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
-#else
-static phys_addr_t memory_limit = -PAGE_OFFSET;
-#endif
+/* Limit the memory size via mem. */
+static phys_addr_t memory_limit;
static int __init early_mem(char *p)
{
@@ -162,35 +153,31 @@ early_param("mem", early_mem);
static void __init setup_bootmem(void)
{
phys_addr_t vmlinux_end = __pa_symbol(&_end);
- phys_addr_t vmlinux_start = __pa_symbol(&_start);
- phys_addr_t __maybe_unused max_mapped_addr;
- phys_addr_t phys_ram_end;
+ phys_addr_t max_mapped_addr;
+ phys_addr_t phys_ram_end, vmlinux_start;
-#ifdef CONFIG_XIP_KERNEL
- vmlinux_start = __pa_symbol(&_sdata);
-#endif
+ if (IS_ENABLED(CONFIG_XIP_KERNEL))
+ vmlinux_start = __pa_symbol(&_sdata);
+ else
+ vmlinux_start = __pa_symbol(&_start);
memblock_enforce_memory_limit(memory_limit);
/*
- * Reserve from the start of the kernel to the end of the kernel
- */
-#if defined(CONFIG_64BIT) && defined(CONFIG_STRICT_KERNEL_RWX)
- /*
* Make sure we align the reservation on PMD_SIZE since we will
* map the kernel in the linear mapping as read-only: we do not want
* any allocation to happen between _end and the next pmd aligned page.
*/
- vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
-#endif
+ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+ vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
+ /*
+ * Reserve from the start of the kernel to the end of the kernel
+ */
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
-
phys_ram_end = memblock_end_of_DRAM();
-#ifndef CONFIG_64BIT
-#ifndef CONFIG_XIP_KERNEL
- phys_ram_base = memblock_start_of_DRAM();
-#endif
+ if (!IS_ENABLED(CONFIG_XIP_KERNEL))
+ phys_ram_base = memblock_start_of_DRAM();
/*
* memblock allocator is not aware of the fact that last 4K bytes of
* the addressable memory can not be mapped because of IS_ERR_VALUE
@@ -200,10 +187,11 @@ static void __init setup_bootmem(void)
* address space is occupied by the kernel mapping then this check must
* be done as soon as the kernel mapping base address is determined.
*/
- max_mapped_addr = __pa(~(ulong)0);
- if (max_mapped_addr == (phys_ram_end - 1))
- memblock_set_current_limit(max_mapped_addr - 4096);
-#endif
+ if (!IS_ENABLED(CONFIG_64BIT)) {
+ max_mapped_addr = __pa(~(ulong)0);
+ if (max_mapped_addr == (phys_ram_end - 1))
+ memblock_set_current_limit(max_mapped_addr - 4096);
+ }
min_low_pfn = PFN_UP(phys_ram_base);
max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
@@ -229,13 +217,7 @@ static void __init setup_bootmem(void)
}
#ifdef CONFIG_MMU
-static struct pt_alloc_ops _pt_ops __initdata;
-
-#ifdef CONFIG_XIP_KERNEL
-#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&_pt_ops))
-#else
-#define pt_ops _pt_ops
-#endif
+struct pt_alloc_ops pt_ops __initdata;
unsigned long riscv_pfn_base __ro_after_init;
EXPORT_SYMBOL(riscv_pfn_base);
@@ -245,9 +227,11 @@ pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
#ifdef CONFIG_XIP_KERNEL
+#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
#define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
#define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte))
#define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir))
@@ -333,6 +317,16 @@ static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
#define early_pmd ((pmd_t *)XIP_FIXUP(early_pmd))
#endif /* CONFIG_XIP_KERNEL */
+static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_pud ((pud_t *)XIP_FIXUP(trampoline_pud))
+#define fixmap_pud ((pud_t *)XIP_FIXUP(fixmap_pud))
+#define early_pud ((pud_t *)XIP_FIXUP(early_pud))
+#endif /* CONFIG_XIP_KERNEL */
+
static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
{
/* Before MMU is enabled */
@@ -352,7 +346,7 @@ static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
static phys_addr_t __init alloc_pmd_early(uintptr_t va)
{
- BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+ BUG_ON((va - kernel_map.virt_addr) >> PUD_SHIFT);
return (uintptr_t)early_pmd;
}
@@ -367,7 +361,8 @@ static phys_addr_t __init alloc_pmd_late(uintptr_t va)
unsigned long vaddr;
vaddr = __get_free_page(GFP_KERNEL);
- BUG_ON(!vaddr);
+ BUG_ON(!vaddr || !pgtable_pmd_page_ctor(virt_to_page(vaddr)));
+
return __pa(vaddr);
}
@@ -398,21 +393,97 @@ static void __init create_pmd_mapping(pmd_t *pmdp,
create_pte_mapping(ptep, va, pa, sz, prot);
}
-#define pgd_next_t pmd_t
-#define alloc_pgd_next(__va) pt_ops.alloc_pmd(__va)
-#define get_pgd_next_virt(__pa) pt_ops.get_pmd_virt(__pa)
+static pud_t *__init get_pud_virt_early(phys_addr_t pa)
+{
+ return (pud_t *)((uintptr_t)pa);
+}
+
+static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa)
+{
+ clear_fixmap(FIX_PUD);
+ return (pud_t *)set_fixmap_offset(FIX_PUD, pa);
+}
+
+static pud_t *__init get_pud_virt_late(phys_addr_t pa)
+{
+ return (pud_t *)__va(pa);
+}
+
+static phys_addr_t __init alloc_pud_early(uintptr_t va)
+{
+ /* Only one PUD is available for early mapping */
+ BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+
+ return (uintptr_t)early_pud;
+}
+
+static phys_addr_t __init alloc_pud_fixmap(uintptr_t va)
+{
+ return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t alloc_pud_late(uintptr_t va)
+{
+ unsigned long vaddr;
+
+ vaddr = __get_free_page(GFP_KERNEL);
+ BUG_ON(!vaddr);
+ return __pa(vaddr);
+}
+
+static void __init create_pud_mapping(pud_t *pudp,
+ uintptr_t va, phys_addr_t pa,
+ phys_addr_t sz, pgprot_t prot)
+{
+ pmd_t *nextp;
+ phys_addr_t next_phys;
+ uintptr_t pud_index = pud_index(va);
+
+ if (sz == PUD_SIZE) {
+ if (pud_val(pudp[pud_index]) == 0)
+ pudp[pud_index] = pfn_pud(PFN_DOWN(pa), prot);
+ return;
+ }
+
+ if (pud_val(pudp[pud_index]) == 0) {
+ next_phys = pt_ops.alloc_pmd(va);
+ pudp[pud_index] = pfn_pud(PFN_DOWN(next_phys), PAGE_TABLE);
+ nextp = pt_ops.get_pmd_virt(next_phys);
+ memset(nextp, 0, PAGE_SIZE);
+ } else {
+ next_phys = PFN_PHYS(_pud_pfn(pudp[pud_index]));
+ nextp = pt_ops.get_pmd_virt(next_phys);
+ }
+
+ create_pmd_mapping(nextp, va, pa, sz, prot);
+}
+
+#define pgd_next_t pud_t
+#define alloc_pgd_next(__va) (pgtable_l4_enabled ? \
+ pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va))
+#define get_pgd_next_virt(__pa) (pgtable_l4_enabled ? \
+ pt_ops.get_pud_virt(__pa) : (pgd_next_t *)pt_ops.get_pmd_virt(__pa))
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \
- create_pmd_mapping(__nextp, __va, __pa, __sz, __prot)
-#define fixmap_pgd_next fixmap_pmd
+ (pgtable_l4_enabled ? \
+ create_pud_mapping(__nextp, __va, __pa, __sz, __prot) : \
+ create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot))
+#define fixmap_pgd_next (pgtable_l4_enabled ? \
+ (uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd)
+#define trampoline_pgd_next (pgtable_l4_enabled ? \
+ (uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)
+#define early_dtb_pgd_next (pgtable_l4_enabled ? \
+ (uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)
#else
#define pgd_next_t pte_t
#define alloc_pgd_next(__va) pt_ops.alloc_pte(__va)
#define get_pgd_next_virt(__pa) pt_ops.get_pte_virt(__pa)
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \
create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
-#define fixmap_pgd_next fixmap_pte
+#define fixmap_pgd_next ((uintptr_t)fixmap_pte)
+#define early_dtb_pgd_next ((uintptr_t)early_dtb_pmd)
+#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot)
#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot)
-#endif
+#endif /* __PAGETABLE_PMD_FOLDED */
void __init create_pgd_mapping(pgd_t *pgdp,
uintptr_t va, phys_addr_t pa,
@@ -451,6 +522,8 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
}
#ifdef CONFIG_XIP_KERNEL
+extern char _xiprom[], _exiprom[], __data_loc;
+
/* called from head.S with MMU off */
asmlinkage void __init __copy_data(void)
{
@@ -499,6 +572,57 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
}
#endif /* CONFIG_STRICT_KERNEL_RWX */
+#ifdef CONFIG_64BIT
+static void __init disable_pgtable_l4(void)
+{
+ pgtable_l4_enabled = false;
+ kernel_map.page_offset = PAGE_OFFSET_L3;
+ satp_mode = SATP_MODE_39;
+}
+
+/*
+ * There is a simple way to determine if 4-level is supported by the
+ * underlying hardware: establish 1:1 mapping in 4-level page table mode
+ * then read SATP to see if the configuration was taken into account
+ * meaning sv48 is supported.
+ */
+static __init void set_satp_mode(void)
+{
+ u64 identity_satp, hw_satp;
+ uintptr_t set_satp_mode_pmd;
+
+ set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
+ create_pgd_mapping(early_pg_dir,
+ set_satp_mode_pmd, (uintptr_t)early_pud,
+ PGDIR_SIZE, PAGE_TABLE);
+ create_pud_mapping(early_pud,
+ set_satp_mode_pmd, (uintptr_t)early_pmd,
+ PUD_SIZE, PAGE_TABLE);
+ /* Handle the case where set_satp_mode straddles 2 PMDs */
+ create_pmd_mapping(early_pmd,
+ set_satp_mode_pmd, set_satp_mode_pmd,
+ PMD_SIZE, PAGE_KERNEL_EXEC);
+ create_pmd_mapping(early_pmd,
+ set_satp_mode_pmd + PMD_SIZE,
+ set_satp_mode_pmd + PMD_SIZE,
+ PMD_SIZE, PAGE_KERNEL_EXEC);
+
+ identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
+
+ local_flush_tlb_all();
+ csr_write(CSR_SATP, identity_satp);
+ hw_satp = csr_swap(CSR_SATP, 0ULL);
+ local_flush_tlb_all();
+
+ if (hw_satp != identity_satp)
+ disable_pgtable_l4();
+
+ memset(early_pg_dir, 0, PAGE_SIZE);
+ memset(early_pud, 0, PAGE_SIZE);
+ memset(early_pmd, 0, PAGE_SIZE);
+}
+#endif
+
/*
* setup_vm() is called from head.S with MMU-off.
*
@@ -563,10 +687,15 @@ static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
- IS_ENABLED(CONFIG_64BIT) ? (uintptr_t)early_dtb_pmd : pa,
+ IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa,
PGDIR_SIZE,
IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
+ if (pgtable_l4_enabled) {
+ create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
+ (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
+ }
+
if (IS_ENABLED(CONFIG_64BIT)) {
create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
pa, PMD_SIZE, PAGE_KERNEL);
@@ -588,11 +717,64 @@ static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
dtb_early_pa = dtb_pa;
}
+/*
+ * MMU is not enabled, the page tables are allocated directly using
+ * early_pmd/pud/p4d and the address returned is the physical one.
+ */
+void __init pt_ops_set_early(void)
+{
+ pt_ops.alloc_pte = alloc_pte_early;
+ pt_ops.get_pte_virt = get_pte_virt_early;
+#ifndef __PAGETABLE_PMD_FOLDED
+ pt_ops.alloc_pmd = alloc_pmd_early;
+ pt_ops.get_pmd_virt = get_pmd_virt_early;
+ pt_ops.alloc_pud = alloc_pud_early;
+ pt_ops.get_pud_virt = get_pud_virt_early;
+#endif
+}
+
+/*
+ * MMU is enabled but page table setup is not complete yet.
+ * fixmap page table alloc functions must be used as a means to temporarily
+ * map the allocated physical pages since the linear mapping does not exist yet.
+ *
+ * Note that this is called with MMU disabled, hence kernel_mapping_pa_to_va,
+ * but it will be used as described above.
+ */
+void __init pt_ops_set_fixmap(void)
+{
+ pt_ops.alloc_pte = kernel_mapping_pa_to_va((uintptr_t)alloc_pte_fixmap);
+ pt_ops.get_pte_virt = kernel_mapping_pa_to_va((uintptr_t)get_pte_virt_fixmap);
+#ifndef __PAGETABLE_PMD_FOLDED
+ pt_ops.alloc_pmd = kernel_mapping_pa_to_va((uintptr_t)alloc_pmd_fixmap);
+ pt_ops.get_pmd_virt = kernel_mapping_pa_to_va((uintptr_t)get_pmd_virt_fixmap);
+ pt_ops.alloc_pud = kernel_mapping_pa_to_va((uintptr_t)alloc_pud_fixmap);
+ pt_ops.get_pud_virt = kernel_mapping_pa_to_va((uintptr_t)get_pud_virt_fixmap);
+#endif
+}
+
+/*
+ * MMU is enabled and page table setup is complete, so from now, we can use
+ * generic page allocation functions to setup page table.
+ */
+void __init pt_ops_set_late(void)
+{
+ pt_ops.alloc_pte = alloc_pte_late;
+ pt_ops.get_pte_virt = get_pte_virt_late;
+#ifndef __PAGETABLE_PMD_FOLDED
+ pt_ops.alloc_pmd = alloc_pmd_late;
+ pt_ops.get_pmd_virt = get_pmd_virt_late;
+ pt_ops.alloc_pud = alloc_pud_late;
+ pt_ops.get_pud_virt = get_pud_virt_late;
+#endif
+}
+
asmlinkage void __init setup_vm(uintptr_t dtb_pa)
{
pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;
kernel_map.virt_addr = KERNEL_LINK_ADDR;
+ kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
#ifdef CONFIG_XIP_KERNEL
kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
@@ -607,11 +789,24 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
kernel_map.phys_addr = (uintptr_t)(&_start);
kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
#endif
+
+#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+ set_satp_mode();
+#endif
+
kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
+ /*
+ * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
+ * kernel, whereas for 64-bit kernel, the end of the virtual address
+ * space is occupied by the modules/BPF/kernel mappings which reduces
+ * the available size of the linear mapping.
+ */
+ memory_limit = KERN_VIRT_SIZE - (IS_ENABLED(CONFIG_64BIT) ? SZ_4G : 0);
+
/* Sanity check alignment and size */
BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0);
@@ -624,23 +819,25 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
#endif
- pt_ops.alloc_pte = alloc_pte_early;
- pt_ops.get_pte_virt = get_pte_virt_early;
-#ifndef __PAGETABLE_PMD_FOLDED
- pt_ops.alloc_pmd = alloc_pmd_early;
- pt_ops.get_pmd_virt = get_pmd_virt_early;
-#endif
+ pt_ops_set_early();
+
/* Setup early PGD for fixmap */
create_pgd_mapping(early_pg_dir, FIXADDR_START,
- (uintptr_t)fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+ fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
#ifndef __PAGETABLE_PMD_FOLDED
- /* Setup fixmap PMD */
+ /* Setup fixmap PUD and PMD */
+ if (pgtable_l4_enabled)
+ create_pud_mapping(fixmap_pud, FIXADDR_START,
+ (uintptr_t)fixmap_pmd, PUD_SIZE, PAGE_TABLE);
create_pmd_mapping(fixmap_pmd, FIXADDR_START,
(uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
/* Setup trampoline PGD and PMD */
create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
- (uintptr_t)trampoline_pmd, PGDIR_SIZE, PAGE_TABLE);
+ trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+ if (pgtable_l4_enabled)
+ create_pud_mapping(trampoline_pud, kernel_map.virt_addr,
+ (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE);
#ifdef CONFIG_XIP_KERNEL
create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
@@ -668,7 +865,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
* Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
* range can not span multiple pmds.
*/
- BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+ BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
!= (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
#ifndef __PAGETABLE_PMD_FOLDED
@@ -693,6 +890,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
pr_warn("FIX_BTMAP_BEGIN: %d\n", FIX_BTMAP_BEGIN);
}
#endif
+
+ pt_ops_set_fixmap();
}
static void __init setup_vm_final(void)
@@ -701,16 +900,6 @@ static void __init setup_vm_final(void)
phys_addr_t pa, start, end;
u64 i;
- /**
- * MMU is enabled at this point. But page table setup is not complete yet.
- * fixmap page table alloc functions should be used at this point
- */
- pt_ops.alloc_pte = alloc_pte_fixmap;
- pt_ops.get_pte_virt = get_pte_virt_fixmap;
-#ifndef __PAGETABLE_PMD_FOLDED
- pt_ops.alloc_pmd = alloc_pmd_fixmap;
- pt_ops.get_pmd_virt = get_pmd_virt_fixmap;
-#endif
/* Setup swapper PGD for fixmap */
create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
__pa_symbol(fixmap_pgd_next),
@@ -735,26 +924,24 @@ static void __init setup_vm_final(void)
}
}
-#ifdef CONFIG_64BIT
/* Map the kernel */
- create_kernel_page_table(swapper_pg_dir, false);
+ if (IS_ENABLED(CONFIG_64BIT))
+ create_kernel_page_table(swapper_pg_dir, false);
+
+#ifdef CONFIG_KASAN
+ kasan_swapper_init();
#endif
/* Clear fixmap PTE and PMD mappings */
clear_fixmap(FIX_PTE);
clear_fixmap(FIX_PMD);
+ clear_fixmap(FIX_PUD);
/* Move to swapper page table */
- csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
+ csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode);
local_flush_tlb_all();
- /* generic page allocation functions must be used to setup page table */
- pt_ops.alloc_pte = alloc_pte_late;
- pt_ops.get_pte_virt = get_pte_virt_late;
-#ifndef __PAGETABLE_PMD_FOLDED
- pt_ops.alloc_pmd = alloc_pmd_late;
- pt_ops.get_pmd_virt = get_pmd_virt_late;
-#endif
+ pt_ops_set_late();
}
#else
asmlinkage void __init setup_vm(uintptr_t dtb_pa)
@@ -790,12 +977,10 @@ static void __init reserve_crashkernel(void)
* since it doesn't make much sense and we have limited memory
* resources.
*/
-#ifdef CONFIG_CRASH_DUMP
if (is_kdump_kernel()) {
pr_info("crashkernel: ignoring reservation request\n");
return;
}
-#endif
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base);
@@ -812,13 +997,22 @@ static void __init reserve_crashkernel(void)
/*
* Current riscv boot protocol requires 2MB alignment for
* RV64 and 4MB alignment for RV32 (hugepage size)
+ *
+ * Try to alloc from 32bit addressible physical memory so that
+ * swiotlb can work on the crash kernel.
*/
crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
- search_start, search_end);
+ search_start,
+ min(search_end, (unsigned long) SZ_4G));
if (crash_base == 0) {
- pr_warn("crashkernel: couldn't allocate %lldKB\n",
- crash_size >> 10);
- return;
+ /* Try again without restricting region to 32bit addressible memory */
+ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
+ search_start, search_end);
+ if (crash_base == 0) {
+ pr_warn("crashkernel: couldn't allocate %lldKB\n",
+ crash_size >> 10);
+ return;
+ }
}
pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 54294f8..f61f7ca 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -11,45 +11,27 @@
#include <asm/fixmap.h>
#include <asm/pgalloc.h>
+/*
+ * Kasan shadow region must lie at a fixed address across sv39, sv48 and sv57
+ * which is right before the kernel.
+ *
+ * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate
+ * the page global directory with kasan_early_shadow_pmd.
+ *
+ * For sv48 and sv57, the region is not aligned on PGDIR_SIZE so the mapping
+ * must be divided as follows:
+ * - the first PGD entry, although incomplete, is populated with
+ * kasan_early_shadow_pud/p4d
+ * - the PGD entries in the middle are populated with kasan_early_shadow_pud/p4d
+ * - the last PGD entry is shared with the kernel mapping so populated at the
+ * lower levels pud/p4d
+ *
+ * In addition, when shallow populating a kasan region (for example vmalloc),
+ * this region may also not be aligned on PGDIR size, so we must go down to the
+ * pud level too.
+ */
+
extern pgd_t early_pg_dir[PTRS_PER_PGD];
-asmlinkage void __init kasan_early_init(void)
-{
- uintptr_t i;
- pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
-
- BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
- KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
-
- for (i = 0; i < PTRS_PER_PTE; ++i)
- set_pte(kasan_early_shadow_pte + i,
- mk_pte(virt_to_page(kasan_early_shadow_page),
- PAGE_KERNEL));
-
- for (i = 0; i < PTRS_PER_PMD; ++i)
- set_pmd(kasan_early_shadow_pmd + i,
- pfn_pmd(PFN_DOWN
- (__pa((uintptr_t) kasan_early_shadow_pte)),
- __pgprot(_PAGE_TABLE)));
-
- for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
- i += PGDIR_SIZE, ++pgd)
- set_pgd(pgd,
- pfn_pgd(PFN_DOWN
- (__pa(((uintptr_t) kasan_early_shadow_pmd))),
- __pgprot(_PAGE_TABLE)));
-
- /* init for swapper_pg_dir */
- pgd = pgd_offset_k(KASAN_SHADOW_START);
-
- for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
- i += PGDIR_SIZE, ++pgd)
- set_pgd(pgd,
- pfn_pgd(PFN_DOWN
- (__pa(((uintptr_t) kasan_early_shadow_pmd))),
- __pgprot(_PAGE_TABLE)));
-
- local_flush_tlb_all();
-}
static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
{
@@ -73,15 +55,19 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE));
}
-static void __init kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned long end)
+static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
pmd_t *pmdp, *base_pmd;
unsigned long next;
- base_pmd = (pmd_t *)pgd_page_vaddr(*pgd);
- if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+ if (pud_none(*pud)) {
base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+ } else {
+ base_pmd = (pmd_t *)pud_pgtable(*pud);
+ if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+ base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+ }
pmdp = base_pmd + pmd_index(vaddr);
@@ -105,59 +91,207 @@ static void __init kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned
* it entirely, memblock could allocate a page at a physical address
* where KASAN is not populated yet and then we'd get a page fault.
*/
- set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+ set_pud(pud, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
}
-static void __init kasan_populate_pgd(unsigned long vaddr, unsigned long end)
+static void __init kasan_populate_pud(pgd_t *pgd,
+ unsigned long vaddr, unsigned long end,
+ bool early)
{
phys_addr_t phys_addr;
- pgd_t *pgdp = pgd_offset_k(vaddr);
+ pud_t *pudp, *base_pud;
+ unsigned long next;
+
+ if (early) {
+ /*
+ * We can't use pgd_page_vaddr here as it would return a linear
+ * mapping address but it is not mapped yet, but when populating
+ * early_pg_dir, we need the physical address and when populating
+ * swapper_pg_dir, we need the kernel virtual address so use
+ * pt_ops facility.
+ */
+ base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+ } else {
+ base_pud = (pud_t *)pgd_page_vaddr(*pgd);
+ if (base_pud == lm_alias(kasan_early_shadow_pud))
+ base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+ }
+
+ pudp = base_pud + pud_index(vaddr);
+
+ do {
+ next = pud_addr_end(vaddr, end);
+
+ if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+ if (early) {
+ phys_addr = __pa(((uintptr_t)kasan_early_shadow_pmd));
+ set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+ continue;
+ } else {
+ phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
+ if (phys_addr) {
+ set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ continue;
+ }
+ }
+ }
+
+ kasan_populate_pmd(pudp, vaddr, next);
+ } while (pudp++, vaddr = next, vaddr != end);
+
+ /*
+ * Wait for the whole PGD to be populated before setting the PGD in
+ * the page table, otherwise, if we did set the PGD before populating
+ * it entirely, memblock could allocate a page at a physical address
+ * where KASAN is not populated yet and then we'd get a page fault.
+ */
+ if (!early)
+ set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
+}
+
+#define kasan_early_shadow_pgd_next (pgtable_l4_enabled ? \
+ (uintptr_t)kasan_early_shadow_pud : \
+ (uintptr_t)kasan_early_shadow_pmd)
+#define kasan_populate_pgd_next(pgdp, vaddr, next, early) \
+ (pgtable_l4_enabled ? \
+ kasan_populate_pud(pgdp, vaddr, next, early) : \
+ kasan_populate_pmd((pud_t *)pgdp, vaddr, next))
+
+static void __init kasan_populate_pgd(pgd_t *pgdp,
+ unsigned long vaddr, unsigned long end,
+ bool early)
+{
+ phys_addr_t phys_addr;
unsigned long next;
do {
next = pgd_addr_end(vaddr, end);
- /*
- * pgdp can't be none since kasan_early_init initialized all KASAN
- * shadow region with kasan_early_shadow_pmd: if this is stillthe case,
- * that means we can try to allocate a hugepage as a replacement.
- */
- if (pgd_page_vaddr(*pgdp) == (unsigned long)lm_alias(kasan_early_shadow_pmd) &&
- IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
- phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
- if (phys_addr) {
- set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
+ if (early) {
+ phys_addr = __pa((uintptr_t)kasan_early_shadow_pgd_next);
+ set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
continue;
+ } else if (pgd_page_vaddr(*pgdp) ==
+ (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) {
+ /*
+ * pgdp can't be none since kasan_early_init
+ * initialized all KASAN shadow region with
+ * kasan_early_shadow_pud: if this is still the
+ * case, that means we can try to allocate a
+ * hugepage as a replacement.
+ */
+ phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+ if (phys_addr) {
+ set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ continue;
+ }
}
}
- kasan_populate_pmd(pgdp, vaddr, next);
+ kasan_populate_pgd_next(pgdp, vaddr, next, early);
} while (pgdp++, vaddr = next, vaddr != end);
}
+asmlinkage void __init kasan_early_init(void)
+{
+ uintptr_t i;
+
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
+ for (i = 0; i < PTRS_PER_PTE; ++i)
+ set_pte(kasan_early_shadow_pte + i,
+ mk_pte(virt_to_page(kasan_early_shadow_page),
+ PAGE_KERNEL));
+
+ for (i = 0; i < PTRS_PER_PMD; ++i)
+ set_pmd(kasan_early_shadow_pmd + i,
+ pfn_pmd(PFN_DOWN
+ (__pa((uintptr_t)kasan_early_shadow_pte)),
+ PAGE_TABLE));
+
+ if (pgtable_l4_enabled) {
+ for (i = 0; i < PTRS_PER_PUD; ++i)
+ set_pud(kasan_early_shadow_pud + i,
+ pfn_pud(PFN_DOWN
+ (__pa(((uintptr_t)kasan_early_shadow_pmd))),
+ PAGE_TABLE));
+ }
+
+ kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
+ KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+ local_flush_tlb_all();
+}
+
+void __init kasan_swapper_init(void)
+{
+ kasan_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
+ KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+ local_flush_tlb_all();
+}
+
static void __init kasan_populate(void *start, void *end)
{
unsigned long vaddr = (unsigned long)start & PAGE_MASK;
unsigned long vend = PAGE_ALIGN((unsigned long)end);
- kasan_populate_pgd(vaddr, vend);
+ kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend, false);
local_flush_tlb_all();
memset(start, KASAN_SHADOW_INIT, end - start);
}
+static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
+ unsigned long vaddr, unsigned long end,
+ bool kasan_populate)
+{
+ unsigned long next;
+ pud_t *pudp, *base_pud;
+ pmd_t *base_pmd;
+ bool is_kasan_pmd;
+
+ base_pud = (pud_t *)pgd_page_vaddr(*pgdp);
+ pudp = base_pud + pud_index(vaddr);
+
+ if (kasan_populate)
+ memcpy(base_pud, (void *)kasan_early_shadow_pgd_next,
+ sizeof(pud_t) * PTRS_PER_PUD);
+
+ do {
+ next = pud_addr_end(vaddr, end);
+ is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd));
+
+ if (is_kasan_pmd) {
+ base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+ }
+ } while (pudp++, vaddr = next, vaddr != end);
+}
+
static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
{
unsigned long next;
void *p;
pgd_t *pgd_k = pgd_offset_k(vaddr);
+ bool is_kasan_pgd_next;
do {
next = pgd_addr_end(vaddr, end);
- if (pgd_page_vaddr(*pgd_k) == (unsigned long)lm_alias(kasan_early_shadow_pmd)) {
+ is_kasan_pgd_next = (pgd_page_vaddr(*pgd_k) ==
+ (unsigned long)lm_alias(kasan_early_shadow_pgd_next));
+
+ if (is_kasan_pgd_next) {
p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
}
+
+ if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE)
+ continue;
+
+ kasan_shallow_populate_pud(pgd_k, vaddr, next, is_kasan_pgd_next);
} while (pgd_k++, vaddr = next, vaddr != end);
}
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 64f8201..37ed760 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -32,7 +32,6 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
unsigned long size, unsigned long stride)
{
struct cpumask *cmask = mm_cpumask(mm);
- struct cpumask hmask;
unsigned int cpuid;
bool broadcast;
@@ -46,9 +45,7 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
unsigned long asid = atomic_long_read(&mm->context.id);
if (broadcast) {
- riscv_cpuid_to_hartid_mask(cmask, &hmask);
- sbi_remote_sfence_vma_asid(cpumask_bits(&hmask),
- start, size, asid);
+ sbi_remote_sfence_vma_asid(cmask, start, size, asid);
} else if (size <= stride) {
local_flush_tlb_page_asid(start, asid);
} else {
@@ -56,9 +53,7 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
}
} else {
if (broadcast) {
- riscv_cpuid_to_hartid_mask(cmask, &hmask);
- sbi_remote_sfence_vma(cpumask_bits(&hmask),
- start, size);
+ sbi_remote_sfence_vma(cmask, start, size);
} else if (size <= stride) {
local_flush_tlb_page(start);
} else {
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 603630b..0bcda99 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -458,10 +458,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
#define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0)
#define BPF_FIXUP_REG_MASK GENMASK(31, 27)
-int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
- struct pt_regs *regs);
-int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
- struct pt_regs *regs)
+bool ex_handler_bpf(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
{
off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
@@ -469,7 +467,7 @@ int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
regs->epc = (unsigned long)&ex->fixup - offset;
- return 1;
+ return true;
}
/* For accesses to BTF pointers, add an entry to the exception table */
@@ -499,7 +497,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
offset = pc - (long)&ex->insn;
if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
return -ERANGE;
- ex->insn = pc;
+ ex->insn = offset;
/*
* Since the extable follows the program, the fixup offset is always
@@ -515,6 +513,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+ ex->type = EX_TYPE_BPF;
ctx->nexentries++;
return 0;
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 3b86006..d04e0e7 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -58,8 +58,6 @@
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
-vmlinux.bin.all-y := $(obj)/vmlinux.bin
-
suffix-$(CONFIG_KERNEL_GZIP) := .gz
suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
suffix-$(CONFIG_KERNEL_LZ4) := .lz4
@@ -68,20 +66,20 @@
suffix-$(CONFIG_KERNEL_XZ) := .xz
suffix-$(CONFIG_KERNEL_ZSTD) := .zst
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lz4)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzma)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzo)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,xzkern)
-$(obj)/vmlinux.bin.zst: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,zstd22)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,bzip2_with_size)
+$(obj)/vmlinux.bin.lz4: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lz4_with_size)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzma_with_size)
+$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzo_with_size)
+$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,xzkern_with_size)
+$(obj)/vmlinux.bin.zst: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,zstd22_with_size)
OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed
$(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 0d90cbe..e3f12db 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -109,7 +109,9 @@ struct hws_basic_entry {
unsigned int AS:2; /* 29-30 PSW address-space control */
unsigned int I:1; /* 31 entry valid or invalid */
unsigned int CL:2; /* 32-33 Configuration Level */
- unsigned int:14;
+ unsigned int H:1; /* 34 Host Indicator */
+ unsigned int LS:1; /* 35 Limited Sampling */
+ unsigned int:12;
unsigned int prim_asn:16; /* primary ASN */
unsigned long long ia; /* Instruction Address */
unsigned long long gpp; /* Guest Program Parameter */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index ce550d0..147cb35 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -49,51 +49,85 @@ int __get_user_bad(void) __attribute__((noreturn));
#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
-#define __put_get_user_asm(to, from, size, insn) \
-({ \
- int __rc; \
- \
- asm volatile( \
- insn " 0,%[spec]\n" \
- "0: mvcos %[_to],%[_from],%[_size]\n" \
- "1: xr %[rc],%[rc]\n" \
- "2:\n" \
- ".pushsection .fixup, \"ax\"\n" \
- "3: lhi %[rc],%[retval]\n" \
- " jg 2b\n" \
- ".popsection\n" \
- EX_TABLE(0b,3b) EX_TABLE(1b,3b) \
- : [rc] "=&d" (__rc), [_to] "+Q" (*(to)) \
- : [_size] "d" (size), [_from] "Q" (*(from)), \
- [retval] "K" (-EFAULT), [spec] "K" (0x81UL) \
- : "cc", "0"); \
- __rc; \
+union oac {
+ unsigned int val;
+ struct {
+ struct {
+ unsigned short key : 4;
+ unsigned short : 4;
+ unsigned short as : 2;
+ unsigned short : 4;
+ unsigned short k : 1;
+ unsigned short a : 1;
+ } oac1;
+ struct {
+ unsigned short key : 4;
+ unsigned short : 4;
+ unsigned short as : 2;
+ unsigned short : 4;
+ unsigned short k : 1;
+ unsigned short a : 1;
+ } oac2;
+ };
+};
+
+#define __put_get_user_asm(to, from, size, oac_spec) \
+({ \
+ int __rc; \
+ \
+ asm volatile( \
+ " lr 0,%[spec]\n" \
+ "0: mvcos %[_to],%[_from],%[_size]\n" \
+ "1: xr %[rc],%[rc]\n" \
+ "2:\n" \
+ ".pushsection .fixup, \"ax\"\n" \
+ "3: lhi %[rc],%[retval]\n" \
+ " jg 2b\n" \
+ ".popsection\n" \
+ EX_TABLE(0b,3b) EX_TABLE(1b,3b) \
+ : [rc] "=&d" (__rc), [_to] "+Q" (*(to)) \
+ : [_size] "d" (size), [_from] "Q" (*(from)), \
+ [retval] "K" (-EFAULT), [spec] "d" (oac_spec.val) \
+ : "cc", "0"); \
+ __rc; \
})
+#define __put_user_asm(to, from, size) \
+ __put_get_user_asm(to, from, size, ((union oac) { \
+ .oac1.as = PSW_BITS_AS_SECONDARY, \
+ .oac1.a = 1 \
+ }))
+
+#define __get_user_asm(to, from, size) \
+ __put_get_user_asm(to, from, size, ((union oac) { \
+ .oac2.as = PSW_BITS_AS_SECONDARY, \
+ .oac2.a = 1 \
+ })) \
+
static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
int rc;
switch (size) {
case 1:
- rc = __put_get_user_asm((unsigned char __user *)ptr,
- (unsigned char *)x,
- size, "llilh");
+ rc = __put_user_asm((unsigned char __user *)ptr,
+ (unsigned char *)x,
+ size);
break;
case 2:
- rc = __put_get_user_asm((unsigned short __user *)ptr,
- (unsigned short *)x,
- size, "llilh");
+ rc = __put_user_asm((unsigned short __user *)ptr,
+ (unsigned short *)x,
+ size);
break;
case 4:
- rc = __put_get_user_asm((unsigned int __user *)ptr,
- (unsigned int *)x,
- size, "llilh");
+ rc = __put_user_asm((unsigned int __user *)ptr,
+ (unsigned int *)x,
+ size);
break;
case 8:
- rc = __put_get_user_asm((unsigned long __user *)ptr,
- (unsigned long *)x,
- size, "llilh");
+ rc = __put_user_asm((unsigned long __user *)ptr,
+ (unsigned long *)x,
+ size);
break;
default:
__put_user_bad();
@@ -108,24 +142,24 @@ static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsign
switch (size) {
case 1:
- rc = __put_get_user_asm((unsigned char *)x,
- (unsigned char __user *)ptr,
- size, "lghi");
+ rc = __get_user_asm((unsigned char *)x,
+ (unsigned char __user *)ptr,
+ size);
break;
case 2:
- rc = __put_get_user_asm((unsigned short *)x,
- (unsigned short __user *)ptr,
- size, "lghi");
+ rc = __get_user_asm((unsigned short *)x,
+ (unsigned short __user *)ptr,
+ size);
break;
case 4:
- rc = __put_get_user_asm((unsigned int *)x,
- (unsigned int __user *)ptr,
- size, "lghi");
+ rc = __get_user_asm((unsigned int *)x,
+ (unsigned int __user *)ptr,
+ size);
break;
case 8:
- rc = __put_get_user_asm((unsigned long *)x,
- (unsigned long __user *)ptr,
- size, "lghi");
+ rc = __get_user_asm((unsigned long *)x,
+ (unsigned long __user *)ptr,
+ size);
break;
default:
__get_user_bad();
diff --git a/arch/s390/kernel/perf_cpum_cf_common.c b/arch/s390/kernel/perf_cpum_cf_common.c
index 30f0242d..8ee4867 100644
--- a/arch/s390/kernel/perf_cpum_cf_common.c
+++ b/arch/s390/kernel/perf_cpum_cf_common.c
@@ -178,7 +178,7 @@ size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset,
case CPUMF_CTR_SET_CRYPTO:
if (info->csvn >= 1 && info->csvn <= 5)
ctrset_size = 16;
- else if (info->csvn == 6)
+ else if (info->csvn == 6 || info->csvn == 7)
ctrset_size = 20;
break;
case CPUMF_CTR_SET_EXT:
@@ -188,7 +188,7 @@ size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset,
ctrset_size = 48;
else if (info->csvn >= 3 && info->csvn <= 5)
ctrset_size = 128;
- else if (info->csvn == 6)
+ else if (info->csvn == 6 || info->csvn == 7)
ctrset_size = 160;
break;
case CPUMF_CTR_SET_MT_DIAG:
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 37265f5..52c1fe2 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -344,7 +344,7 @@ static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
NULL,
};
-static struct attribute *cpumcf_svn_6_pmu_event_attr[] __initdata = {
+static struct attribute *cpumcf_svn_67_pmu_event_attr[] __initdata = {
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
@@ -715,8 +715,8 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
case 1 ... 5:
csvn = cpumcf_svn_12345_pmu_event_attr;
break;
- case 6:
- csvn = cpumcf_svn_6_pmu_event_attr;
+ case 6 ... 7:
+ csvn = cpumcf_svn_67_pmu_event_attr;
break;
default:
csvn = none;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index db62def..332a499 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1179,7 +1179,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
sample = (struct hws_basic_entry *) *sdbt;
while ((unsigned long *) sample < (unsigned long *) te) {
/* Check for an empty sample */
- if (!sample->def)
+ if (!sample->def || sample->LS)
break;
/* Update perf event period */
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index a596e69..8a5d214 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -62,10 +62,14 @@ static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr
unsigned long size)
{
unsigned long tmp1, tmp2;
+ union oac spec = {
+ .oac2.as = PSW_BITS_AS_SECONDARY,
+ .oac2.a = 1,
+ };
tmp1 = -4096UL;
asm volatile(
- " lghi 0,%[spec]\n"
+ " lr 0,%[spec]\n"
"0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
"6: jz 4f\n"
"1: algr %0,%3\n"
@@ -84,7 +88,7 @@ static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr
"5:\n"
EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
- : [spec] "K" (0x81UL)
+ : [spec] "d" (spec.val)
: "cc", "memory", "0");
return size;
}
@@ -135,10 +139,14 @@ static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
unsigned long size)
{
unsigned long tmp1, tmp2;
+ union oac spec = {
+ .oac1.as = PSW_BITS_AS_SECONDARY,
+ .oac1.a = 1,
+ };
tmp1 = -4096UL;
asm volatile(
- " llilh 0,%[spec]\n"
+ " lr 0,%[spec]\n"
"0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
"6: jz 4f\n"
"1: algr %0,%3\n"
@@ -157,7 +165,7 @@ static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
"5:\n"
EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
- : [spec] "K" (0x81UL)
+ : [spec] "d" (spec.val)
: "cc", "memory", "0");
return size;
}
@@ -207,10 +215,14 @@ EXPORT_SYMBOL(raw_copy_to_user);
static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
{
unsigned long tmp1, tmp2;
+ union oac spec = {
+ .oac1.as = PSW_BITS_AS_SECONDARY,
+ .oac1.a = 1,
+ };
tmp1 = -4096UL;
asm volatile(
- " llilh 0,%[spec]\n"
+ " lr 0,%[spec]\n"
"0: .insn ss,0xc80000000000,0(%0,%1),0(%4),0\n"
" jz 4f\n"
"1: algr %0,%2\n"
@@ -228,7 +240,7 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size
"5:\n"
EX_TABLE(0b,2b) EX_TABLE(3b,5b)
: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
- : "a" (empty_zero_page), [spec] "K" (0x81UL)
+ : "a" (empty_zero_page), [spec] "d" (spec.val)
: "cc", "memory", "0");
return size;
}
diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile
index 5c123f5..1f5d2df 100644
--- a/arch/sh/boot/Makefile
+++ b/arch/sh/boot/Makefile
@@ -19,12 +19,12 @@
CONFIG_ENTRY_OFFSET ?= 0x00001000
CONFIG_PHYSICAL_START ?= $(CONFIG_MEMORY_START)
-suffix-y := bin
-suffix-$(CONFIG_KERNEL_GZIP) := gz
-suffix-$(CONFIG_KERNEL_BZIP2) := bz2
-suffix-$(CONFIG_KERNEL_LZMA) := lzma
-suffix-$(CONFIG_KERNEL_XZ) := xz
-suffix-$(CONFIG_KERNEL_LZO) := lzo
+suffix_y := bin
+suffix_$(CONFIG_KERNEL_GZIP) := gz
+suffix_$(CONFIG_KERNEL_BZIP2) := bz2
+suffix_$(CONFIG_KERNEL_LZMA) := lzma
+suffix_$(CONFIG_KERNEL_XZ) := xz
+suffix_$(CONFIG_KERNEL_LZO) := lzo
targets := zImage vmlinux.srec romImage uImage uImage.srec uImage.gz \
uImage.bz2 uImage.lzma uImage.xz uImage.lzo uImage.bin \
@@ -106,10 +106,10 @@
$(obj)/uImage.srec: $(obj)/uImage FORCE
$(call if_changed,objcopy)
-$(obj)/uImage: $(obj)/uImage.$(suffix-y)
+$(obj)/uImage: $(obj)/uImage.$(suffix_y)
@ln -sf $(notdir $<) $@
@echo ' Image $@ is ready'
export CONFIG_PAGE_OFFSET CONFIG_MEMORY_START CONFIG_BOOT_LINK_OFFSET \
CONFIG_PHYSICAL_START CONFIG_ZERO_PAGE_OFFSET CONFIG_ENTRY_OFFSET \
- KERNEL_MEMORY suffix-y
+ KERNEL_MEMORY suffix_y
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index cf3174d..591125c 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -47,22 +47,20 @@
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
-vmlinux.bin.all-y := $(obj)/vmlinux.bin
-
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzma)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,xzkern)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzo)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,bzip2_with_size)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzma_with_size)
+$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,xzkern_with_size)
+$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzo_with_size)
OBJCOPYFLAGS += -R .empty_zero_page
LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE
+$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
$(call if_changed,ld)
diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile
index c17d65b..4a6dec9 100644
--- a/arch/sh/boot/dts/Makefile
+++ b/arch/sh/boot/dts/Makefile
@@ -1,4 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
-obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
-endif
+obj-$(CONFIG_USE_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 66fc086..1cab1b2 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -97,6 +97,9 @@
select PCI_DOMAINS if PCI
select ARCH_HAS_GIGANTIC_PAGE
select HAVE_SOFTIRQ_ON_OWN_STACK
+ select HAVE_SETUP_PER_CPU_AREA
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK
+ select NEED_PER_CPU_PAGE_FIRST_CHUNK
config ARCH_PROC_KCORE_TEXT
def_bool y
@@ -123,15 +126,6 @@
bool
default y
-config HAVE_SETUP_PER_CPU_AREA
- def_bool y if SPARC64
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y if SPARC64
-
-config NEED_PER_CPU_PAGE_FIRST_CHUNK
- def_bool y if SPARC64
-
config MMU
bool
default y
diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c
index 3a66e62..ab657b3 100644
--- a/arch/sparc/kernel/led.c
+++ b/arch/sparc/kernel/led.c
@@ -114,18 +114,16 @@ static const struct proc_ops led_proc_ops = {
};
#endif
-static struct proc_dir_entry *led;
-
#define LED_VERSION "0.1"
static int __init led_init(void)
{
timer_setup(&led_blink_timer, led_blink, 0);
- led = proc_create("led", 0, NULL, &led_proc_ops);
- if (!led)
+#ifdef CONFIG_PROC_FS
+ if (!proc_create("led", 0, NULL, &led_proc_ops))
return -ENOMEM;
-
+#endif
printk(KERN_INFO
"led: version %s, Lars Kotthoff <metalhead@metalhead.ws>\n",
LED_VERSION);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b98a7bb..a1f78e9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1526,50 +1526,6 @@ void smp_send_stop(void)
smp_call_function(stop_this_cpu, NULL, 0);
}
-/**
- * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
- * @cpu: cpu to allocate for
- * @size: size allocation in bytes
- * @align: alignment
- *
- * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
- * does the right thing for NUMA regardless of the current
- * configuration.
- *
- * RETURNS:
- * Pointer to the allocated area on success, NULL on failure.
- */
-static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
- size_t align)
-{
- const unsigned long goal = __pa(MAX_DMA_ADDRESS);
-#ifdef CONFIG_NUMA
- int node = cpu_to_node(cpu);
- void *ptr;
-
- if (!node_online(node) || !NODE_DATA(node)) {
- ptr = memblock_alloc_from(size, align, goal);
- pr_info("cpu %d has no node %d or node-local memory\n",
- cpu, node);
- pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
- cpu, size, __pa(ptr));
- } else {
- ptr = memblock_alloc_try_nid(size, align, goal,
- MEMBLOCK_ALLOC_ACCESSIBLE, node);
- pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
- "%016lx\n", cpu, size, node, __pa(ptr));
- }
- return ptr;
-#else
- return memblock_alloc_from(size, align, goal);
-#endif
-}
-
-static void __init pcpu_free_bootmem(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
{
if (cpu_to_node(from) == cpu_to_node(to))
@@ -1578,57 +1534,9 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
return REMOTE_DISTANCE;
}
-static void __init pcpu_populate_pte(unsigned long addr)
+static int __init pcpu_cpu_to_node(int cpu)
{
- pgd_t *pgd = pgd_offset_k(addr);
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
-
- if (pgd_none(*pgd)) {
- pud_t *new;
-
- new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- pgd_populate(&init_mm, pgd, new);
- }
-
- p4d = p4d_offset(pgd, addr);
- if (p4d_none(*p4d)) {
- pud_t *new;
-
- new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- p4d_populate(&init_mm, p4d, new);
- }
-
- pud = pud_offset(p4d, addr);
- if (pud_none(*pud)) {
- pmd_t *new;
-
- new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- pud_populate(&init_mm, pud, new);
- }
-
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd)) {
- pte_t *new;
-
- new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- pmd_populate_kernel(&init_mm, pmd, new);
- }
-
- return;
-
-err_alloc:
- panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
- __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+ return cpu_to_node(cpu);
}
void __init setup_per_cpu_areas(void)
@@ -1641,8 +1549,7 @@ void __init setup_per_cpu_areas(void)
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
PERCPU_DYNAMIC_RESERVE, 4 << 20,
pcpu_cpu_distance,
- pcpu_alloc_bootmem,
- pcpu_free_bootmem);
+ pcpu_cpu_to_node);
if (rc)
pr_warn("PERCPU: %s allocator failed (%d), "
"falling back to page size\n",
@@ -1650,9 +1557,7 @@ void __init setup_per_cpu_areas(void)
}
if (rc < 0)
rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
- pcpu_alloc_bootmem,
- pcpu_free_bootmem,
- pcpu_populate_pte);
+ pcpu_cpu_to_node);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index 0ab5801..5c092a9 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -616,7 +616,7 @@ static void um_pci_virtio_remove(struct virtio_device *vdev)
int i;
/* Stop all virtqueues */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
device_set_wakeup_enable(&vdev->dev, false);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 407533c..6fddb63 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -78,7 +78,7 @@
select ARCH_HAS_FILTER_PGPROT
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION
+ select ARCH_HAS_KCOV if X86_64
select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
@@ -240,6 +240,7 @@
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
select HAVE_FUNCTION_ARG_ACCESS_API
+ select HAVE_SETUP_PER_CPU_AREA
select HAVE_SOFTIRQ_ON_OWN_STACK
select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR
select HAVE_STACK_VALIDATION if X86_64
@@ -253,6 +254,8 @@
select HAVE_GENERIC_VDSO
select HOTPLUG_SMT if SMP
select IRQ_FORCED_THREADING
+ select NEED_PER_CPU_EMBED_FIRST_CHUNK
+ select NEED_PER_CPU_PAGE_FIRST_CHUNK
select NEED_SG_DMA_LENGTH
select PCI_DOMAINS if PCI
select PCI_LOCKLESS_CONFIG if PCI
@@ -333,15 +336,6 @@
config ARCH_HAS_FILTER_PGPROT
def_bool y
-config HAVE_SETUP_PER_CPU_AREA
- def_bool y
-
-config NEED_PER_CPU_EMBED_FIRST_CHUNK
- def_bool y
-
-config NEED_PER_CPU_PAGE_FIRST_CHUNK
- def_bool y
-
config ARCH_HIBERNATION_POSSIBLE
def_bool y
@@ -1575,6 +1569,7 @@
depends on SMP
depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
default y if X86_BIGSMP
+ select USE_PERCPU_NUMA_NODE_ID
help
Enable NUMA (Non-Uniform Memory Access) support.
@@ -2450,10 +2445,6 @@
config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
def_bool y
-config USE_PERCPU_NUMA_NODE_ID
- def_bool y
- depends on NUMA
-
menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e118136..6115274 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -126,17 +126,17 @@
$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
$(call if_changed,gzip)
$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,bzip2)
+ $(call if_changed,bzip2_with_size)
$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzma)
+ $(call if_changed,lzma_with_size)
$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,xzkern)
+ $(call if_changed,xzkern_with_size)
$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lzo)
+ $(call if_changed,lzo_with_size)
$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,lz4)
+ $(call if_changed,lz4_with_size)
$(obj)/vmlinux.bin.zst: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,zstd22)
+ $(call if_changed,zstd22_with_size)
suffix-$(CONFIG_KERNEL_GZIP) := gz
suffix-$(CONFIG_KERNEL_BZIP2) := bz2
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index f658bb4..631d504 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,6 +55,7 @@ KVM_X86_OP_NULL(tlb_remote_flush)
KVM_X86_OP_NULL(tlb_remote_flush_with_range)
KVM_X86_OP(tlb_flush_gva)
KVM_X86_OP(tlb_flush_guest)
+KVM_X86_OP(vcpu_pre_run)
KVM_X86_OP(run)
KVM_X86_OP_NULL(handle_exit)
KVM_X86_OP_NULL(skip_emulated_instruction)
@@ -98,8 +99,6 @@ KVM_X86_OP(handle_exit_irqoff)
KVM_X86_OP_NULL(request_immediate_exit)
KVM_X86_OP(sched_in)
KVM_X86_OP_NULL(update_cpu_dirty_logging)
-KVM_X86_OP_NULL(pre_block)
-KVM_X86_OP_NULL(post_block)
KVM_X86_OP_NULL(vcpu_blocking)
KVM_X86_OP_NULL(vcpu_unblocking)
KVM_X86_OP_NULL(update_pi_irte)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0677b9e..1384517 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1381,6 +1381,7 @@ struct kvm_x86_ops {
*/
void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
+ int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
@@ -1454,18 +1455,6 @@ struct kvm_x86_ops {
const struct kvm_pmu_ops *pmu_ops;
const struct kvm_x86_nested_ops *nested_ops;
- /*
- * Architecture specific hooks for vCPU blocking due to
- * HLT instruction.
- * Returns for .pre_block():
- * - 0 means continue to block the vCPU.
- * - 1 means we cannot block the vCPU since some event
- * happens during this period, such as, 'ON' bit in
- * posted-interrupts descriptor is set.
- */
- int (*pre_block)(struct kvm_vcpu *vcpu);
- void (*post_block)(struct kvm_vcpu *vcpu);
-
void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index fd2d3ab..dc7da08 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -515,6 +515,7 @@ static const struct intel_early_ops gen11_early_ops __initconst = {
.stolen_size = gen9_stolen_size,
};
+/* Intel integrated GPUs for which we need to reserve "stolen memory" */
static const struct pci_device_id intel_early_ids[] __initconst = {
INTEL_I830_IDS(&i830_early_ops),
INTEL_I845G_IDS(&i845_early_ops),
@@ -592,6 +593,13 @@ static void __init intel_graphics_quirks(int num, int slot, int func)
u16 device;
int i;
+ /*
+ * Reserve "stolen memory" for an integrated GPU. If we've already
+ * found one, there's nothing to do for other (discrete) GPUs.
+ */
+ if (resource_size(&intel_graphics_stolen_res))
+ return;
+
device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
for (i = 0; i < ARRAY_SIZE(intel_early_ids); i++) {
@@ -704,7 +712,7 @@ static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
- QFLAG_APPLY_ONCE, intel_graphics_quirks },
+ 0, intel_graphics_quirks },
/*
* HPET on the current version of the Baytrail platform has accuracy
* problems: it will halt in deep idle state - so we disable it.
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 882213d..71f3364 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1435,8 +1435,12 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
hpet_rtc_timer_reinit();
memset(&curr_time, 0, sizeof(struct rtc_time));
- if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
- mc146818_get_time(&curr_time);
+ if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
+ if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+ pr_err_ratelimited("unable to read current time from RTC\n");
+ return IRQ_HANDLED;
+ }
+ }
if (hpet_rtc_flags & RTC_UIE &&
curr_time.tm_sec != hpet_prev_update_sec) {
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 9b9fb78..9ae64f9 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/dmi.h>
#include <linux/ioport.h>
#include <asm/e820/api.h>
@@ -23,11 +24,31 @@ static void resource_clip(struct resource *res, resource_size_t start,
res->start = end + 1;
}
+/*
+ * Some BIOS-es contain a bug where they add addresses which map to
+ * system RAM in the PCI host bridge window returned by the ACPI _CRS
+ * method, see commit 4dc2287c1805 ("x86: avoid E820 regions when
+ * allocating address space"). To avoid this Linux by default excludes
+ * E820 reservations when allocating addresses since 2010.
+ * In 2019 some systems have shown-up with E820 reservations which cover
+ * the entire _CRS returned PCI host bridge window, causing all attempts
+ * to assign memory to PCI BARs to fail if Linux uses E820 reservations.
+ *
+ * Ideally Linux would fully stop using E820 reservations, but then
+ * the old systems this was added for will regress.
+ * Instead keep the old behavior for old systems, while ignoring the
+ * E820 reservations for any systems from now on.
+ */
static void remove_e820_regions(struct resource *avail)
{
- int i;
+ int i, year = dmi_get_bios_year();
struct e820_entry *entry;
+ if (year >= 2018)
+ return;
+
+ pr_info_once("PCI: Removing E820 reservations from host bridge windows\n");
+
for (i = 0; i < e820_table->nr_entries; i++) {
entry = &e820_table->entries[i];
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 7b65275..49325ca 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -84,60 +84,6 @@ static bool __init pcpu_need_numa(void)
}
#endif
-/**
- * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
- * @cpu: cpu to allocate for
- * @size: size allocation in bytes
- * @align: alignment
- *
- * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
- * does the right thing for NUMA regardless of the current
- * configuration.
- *
- * RETURNS:
- * Pointer to the allocated area on success, NULL on failure.
- */
-static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
- unsigned long align)
-{
- const unsigned long goal = __pa(MAX_DMA_ADDRESS);
-#ifdef CONFIG_NUMA
- int node = early_cpu_to_node(cpu);
- void *ptr;
-
- if (!node_online(node) || !NODE_DATA(node)) {
- ptr = memblock_alloc_from(size, align, goal);
- pr_info("cpu %d has no node %d or node-local memory\n",
- cpu, node);
- pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
- cpu, size, __pa(ptr));
- } else {
- ptr = memblock_alloc_try_nid(size, align, goal,
- MEMBLOCK_ALLOC_ACCESSIBLE,
- node);
-
- pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n",
- cpu, size, node, __pa(ptr));
- }
- return ptr;
-#else
- return memblock_alloc_from(size, align, goal);
-#endif
-}
-
-/*
- * Helpers for first chunk memory allocation
- */
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
-{
- return pcpu_alloc_bootmem(cpu, size, align);
-}
-
-static void __init pcpu_fc_free(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
{
#ifdef CONFIG_NUMA
@@ -150,7 +96,12 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
#endif
}
-static void __init pcpup_populate_pte(unsigned long addr)
+static int __init pcpu_cpu_to_node(int cpu)
+{
+ return early_cpu_to_node(cpu);
+}
+
+void __init pcpu_populate_pte(unsigned long addr)
{
populate_extra_pte(addr);
}
@@ -205,15 +156,14 @@ void __init setup_per_cpu_areas(void)
rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
dyn_size, atom_size,
pcpu_cpu_distance,
- pcpu_fc_alloc, pcpu_fc_free);
+ pcpu_cpu_to_node);
if (rc < 0)
pr_warn("%s allocator failed (%d), falling back to page size\n",
pcpu_fc_names[pcpu_chosen_fc], rc);
}
if (rc < 0)
rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
- pcpu_fc_alloc, pcpu_fc_free,
- pcpup_populate_pte);
+ pcpu_cpu_to_node);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c55e57b..3902c28 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -119,6 +119,28 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu,
return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures);
}
+/* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */
+static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
+ int nent)
+{
+ struct kvm_cpuid_entry2 *orig;
+ int i;
+
+ if (nent != vcpu->arch.cpuid_nent)
+ return -EINVAL;
+
+ for (i = 0; i < nent; i++) {
+ orig = &vcpu->arch.cpuid_entries[i];
+ if (e2[i].function != orig->function ||
+ e2[i].index != orig->index ||
+ e2[i].eax != orig->eax || e2[i].ebx != orig->ebx ||
+ e2[i].ecx != orig->ecx || e2[i].edx != orig->edx)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
{
u32 function;
@@ -145,14 +167,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
}
}
-static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu,
+ struct kvm_cpuid_entry2 *entries, int nent)
{
u32 base = vcpu->arch.kvm_cpuid_base;
if (!base)
return NULL;
- return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0);
+ return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, 0);
+}
+
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+{
+ return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent);
}
void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
@@ -167,11 +196,12 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
vcpu->arch.pv_cpuid.features = best->eax;
}
-void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
+ int nent)
{
struct kvm_cpuid_entry2 *best;
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
+ best = cpuid_entry2_find(entries, nent, 1, 0);
if (best) {
/* Update OSXSAVE bit */
if (boot_cpu_has(X86_FEATURE_XSAVE))
@@ -182,33 +212,38 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE);
}
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ best = cpuid_entry2_find(entries, nent, 7, 0);
if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7)
cpuid_entry_change(best, X86_FEATURE_OSPKE,
kvm_read_cr4_bits(vcpu, X86_CR4_PKE));
- best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
+ best = cpuid_entry2_find(entries, nent, 0xD, 0);
if (best)
best->ebx = xstate_required_size(vcpu->arch.xcr0, false);
- best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
+ best = cpuid_entry2_find(entries, nent, 0xD, 1);
if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) ||
cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- best = kvm_find_kvm_cpuid_features(vcpu);
+ best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
if (kvm_hlt_in_guest(vcpu->kvm) && best &&
(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
- best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+ best = cpuid_entry2_find(entries, nent, 0x1, 0);
if (best)
cpuid_entry_change(best, X86_FEATURE_MWAIT,
vcpu->arch.ia32_misc_enable_msr &
MSR_IA32_MISC_ENABLE_MWAIT);
}
}
+
+void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+{
+ __kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
+}
EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -298,6 +333,22 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
{
int r;
+ __kvm_update_cpuid_runtime(vcpu, e2, nent);
+
+ /*
+ * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+ * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+ * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page
+ * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with
+ * the core vCPU model on the fly. It would've been better to forbid any
+ * KVM_SET_CPUID{,2} calls after KVM_RUN altogether but unfortunately
+ * some VMMs (e.g. QEMU) reuse vCPU fds for CPU hotplug/unplug and do
+ * KVM_SET_CPUID{,2} again. To support this legacy behavior, check
+ * whether the supplied CPUID data is equal to what's already set.
+ */
+ if (vcpu->arch.last_vmentry_cpu != -1)
+ return kvm_cpuid_check_equal(vcpu, e2, nent);
+
r = kvm_check_cpuid(vcpu, e2, nent);
if (r)
return r;
@@ -307,7 +358,6 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
vcpu->arch.cpuid_nent = nent;
kvm_update_kvm_cpuid_base(vcpu);
- kvm_update_cpuid_runtime(vcpu);
kvm_vcpu_after_set_cpuid(vcpu);
return 0;
@@ -795,10 +845,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
perf_get_x86_pmu_capability(&cap);
/*
- * Only support guest architectural pmu on a host
- * with architectural pmu.
+ * The guest architecture pmu is only supported if the architecture
+ * pmu exists on the host and the module parameters allow it.
*/
- if (!cap.version)
+ if (!cap.version || !enable_pmu)
memset(&cap, 0, sizeof(cap));
eax.split.version_id = min(cap.version, 2);
@@ -886,6 +936,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
--array->nent;
continue;
}
+
+ if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
+ entry->ecx &= ~BIT_ULL(2);
entry->edx = 0;
}
break;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c5028e6..baca9fa 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1950,7 +1950,6 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
{
restart_apic_timer(vcpu->arch.apic);
}
-EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
{
@@ -1962,7 +1961,6 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
start_sw_timer(apic);
preempt_enable();
}
-EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1d275e9..593093b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5756,6 +5756,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
continue;
flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
+
PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
start, end - 1, true, flush);
}
@@ -5825,15 +5826,27 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
}
/*
- * We can flush all the TLBs out of the mmu lock without TLB
- * corruption since we just change the spte from writable to
- * readonly so that we only need to care the case of changing
- * spte from present to present (changing the spte from present
- * to nonpresent will flush all the TLBs immediately), in other
- * words, the only case we care is mmu_spte_update() where we
- * have checked Host-writable | MMU-writable instead of
- * PT_WRITABLE_MASK, that means it does not depend on PT_WRITABLE_MASK
- * anymore.
+ * Flush TLBs if any SPTEs had to be write-protected to ensure that
+ * guest writes are reflected in the dirty bitmap before the memslot
+ * update completes, i.e. before enabling dirty logging is visible to
+ * userspace.
+ *
+ * Perform the TLB flush outside the mmu_lock to reduce the amount of
+ * time the lock is held. However, this does mean that another CPU can
+ * now grab mmu_lock and encounter a write-protected SPTE while CPUs
+ * still have a writable mapping for the associated GFN in their TLB.
+ *
+ * This is safe but requires KVM to be careful when making decisions
+ * based on the write-protection status of an SPTE. Specifically, KVM
+ * also write-protects SPTEs to monitor changes to guest page tables
+ * during shadow paging, and must guarantee no CPUs can write to those
+ * page before the lock is dropped. As mentioned in the previous
+ * paragraph, a write-protected SPTE is no guarantee that CPU cannot
+ * perform writes. So to determine if a TLB flush is truly required, KVM
+ * will clear a separate software-only bit (MMU-writable) and skip the
+ * flush if-and-only-if this bit was already clear.
+ *
+ * See DEFAULT_SPTE_MMU_WRITEABLE for more details.
*/
if (flush)
kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 351b04a..73cfe62 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -216,6 +216,7 @@ u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
new_spte &= ~PT_WRITABLE_MASK;
new_spte &= ~shadow_host_writable_mask;
+ new_spte &= ~shadow_mmu_writable_mask;
new_spte = mark_spte_for_access_track(new_spte);
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index a4af2a4..be6a007 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -60,10 +60,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
(((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1))
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
-/* Bits 9 and 10 are ignored by all non-EPT PTEs. */
-#define DEFAULT_SPTE_HOST_WRITEABLE BIT_ULL(9)
-#define DEFAULT_SPTE_MMU_WRITEABLE BIT_ULL(10)
-
/*
* The mask/shift to use for saving the original R/X bits when marking the PTE
* as not-present for access tracking purposes. We do not save the W bit as the
@@ -79,6 +75,35 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
static_assert(!(SPTE_TDP_AD_MASK & SHADOW_ACC_TRACK_SAVED_MASK));
/*
+ * *_SPTE_HOST_WRITEABLE (aka Host-writable) indicates whether the host permits
+ * writes to the guest page mapped by the SPTE. This bit is cleared on SPTEs
+ * that map guest pages in read-only memslots and read-only VMAs.
+ *
+ * Invariants:
+ * - If Host-writable is clear, PT_WRITABLE_MASK must be clear.
+ *
+ *
+ * *_SPTE_MMU_WRITEABLE (aka MMU-writable) indicates whether the shadow MMU
+ * allows writes to the guest page mapped by the SPTE. This bit is cleared when
+ * the guest page mapped by the SPTE contains a page table that is being
+ * monitored for shadow paging. In this case the SPTE can only be made writable
+ * by unsyncing the shadow page under the mmu_lock.
+ *
+ * Invariants:
+ * - If MMU-writable is clear, PT_WRITABLE_MASK must be clear.
+ * - If MMU-writable is set, Host-writable must be set.
+ *
+ * If MMU-writable is set, PT_WRITABLE_MASK is normally set but can be cleared
+ * to track writes for dirty logging. For such SPTEs, KVM will locklessly set
+ * PT_WRITABLE_MASK upon the next write from the guest and record the write in
+ * the dirty log (see fast_page_fault()).
+ */
+
+/* Bits 9 and 10 are ignored by all non-EPT PTEs. */
+#define DEFAULT_SPTE_HOST_WRITEABLE BIT_ULL(9)
+#define DEFAULT_SPTE_MMU_WRITEABLE BIT_ULL(10)
+
+/*
* Low ignored bits are at a premium for EPT, use high ignored bits, taking care
* to not overlap the A/D type mask or the saved access bits of access-tracked
* SPTEs when A/D bits are disabled.
@@ -316,8 +341,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
static inline bool spte_can_locklessly_be_made_writable(u64 spte)
{
- return (spte & shadow_host_writable_mask) &&
- (spte & shadow_mmu_writable_mask);
+ if (spte & shadow_mmu_writable_mask) {
+ WARN_ON_ONCE(!(spte & shadow_host_writable_mask));
+ return true;
+ }
+
+ WARN_ON_ONCE(spte & PT_WRITABLE_MASK);
+ return false;
}
static inline u64 get_mmio_spte_generation(u64 spte)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 7b1bc81..bc9e355 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1442,12 +1442,12 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
!is_last_spte(iter.old_spte, iter.level))
continue;
- if (!is_writable_pte(iter.old_spte))
- break;
-
new_spte = iter.old_spte &
~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
+ if (new_spte == iter.old_spte)
+ break;
+
tdp_mmu_set_spte(kvm, &iter, new_spte);
spte_set = true;
}
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 261b39c..f614f95 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -13,6 +13,8 @@
#include <linux/types.h>
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
#include <asm/perf_event.h>
#include "x86.h"
#include "cpuid.h"
@@ -109,6 +111,9 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
.config = config,
};
+ if (type == PERF_TYPE_HARDWARE && config >= PERF_COUNT_HW_MAX)
+ return;
+
attr.sample_period = get_sample_period(pmc, pmc->counter);
if (in_tx)
@@ -169,12 +174,16 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
return true;
}
+static int cmp_u64(const void *a, const void *b)
+{
+ return *(__u64 *)a - *(__u64 *)b;
+}
+
void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
{
unsigned config, type = PERF_TYPE_RAW;
struct kvm *kvm = pmc->vcpu->kvm;
struct kvm_pmu_event_filter *filter;
- int i;
bool allow_event = true;
if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -189,16 +198,13 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
if (filter) {
- for (i = 0; i < filter->nevents; i++)
- if (filter->events[i] ==
- (eventsel & AMD64_RAW_EVENT_MASK_NB))
- break;
- if (filter->action == KVM_PMU_EVENT_ALLOW &&
- i == filter->nevents)
- allow_event = false;
- if (filter->action == KVM_PMU_EVENT_DENY &&
- i < filter->nevents)
- allow_event = false;
+ __u64 key = eventsel & AMD64_RAW_EVENT_MASK_NB;
+
+ if (bsearch(&key, filter->events, filter->nevents,
+ sizeof(__u64), cmp_u64))
+ allow_event = filter->action == KVM_PMU_EVENT_ALLOW;
+ else
+ allow_event = filter->action == KVM_PMU_EVENT_DENY;
}
if (!allow_event)
return;
@@ -573,6 +579,11 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
/* Ensure nevents can't be changed between the user copies. */
*filter = tmp;
+ /*
+ * Sort the in-kernel list so that we can search it with bsearch.
+ */
+ sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL);
+
mutex_lock(&kvm->lock);
filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
mutex_is_locked(&kvm->lock));
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 0e5b492..90364d0 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -295,13 +295,16 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
struct kvm_vcpu *vcpu;
unsigned long i;
+ /*
+ * Wake any target vCPUs that are blocking, i.e. waiting for a wake
+ * event. There's no need to signal doorbells, as hardware has handled
+ * vCPUs that were in guest at the time of the IPI, and vCPUs that have
+ * since entered the guest will have processed pending IRQs at VMRUN.
+ */
kvm_for_each_vcpu(i, vcpu, kvm) {
- bool m = kvm_apic_match_dest(vcpu, source,
- icrl & APIC_SHORT_MASK,
- GET_APIC_DEST_FIELD(icrh),
- icrl & APIC_DEST_MASK);
-
- if (m && !avic_vcpu_is_running(vcpu))
+ if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & APIC_DEST_MASK))
kvm_vcpu_wake_up(vcpu);
}
}
@@ -672,9 +675,22 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
return -1;
kvm_lapic_set_irr(vec, vcpu->arch.apic);
+
+ /*
+ * Pairs with the smp_mb_*() after setting vcpu->guest_mode in
+ * vcpu_enter_guest() to ensure the write to the vIRR is ordered before
+ * the read of guest_mode, which guarantees that either VMRUN will see
+ * and process the new vIRR entry, or that the below code will signal
+ * the doorbell if the vCPU is already running in the guest.
+ */
smp_mb__after_atomic();
- if (avic_vcpu_is_running(vcpu)) {
+ /*
+ * Signal the doorbell to tell hardware to inject the IRQ if the vCPU
+ * is in the guest. If the vCPU is not in the guest, hardware will
+ * automatically process AVIC interrupts at VMRUN.
+ */
+ if (vcpu->mode == IN_GUEST_MODE) {
int cpu = READ_ONCE(vcpu->cpu);
/*
@@ -688,8 +704,13 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
if (cpu != get_cpu())
wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
put_cpu();
- } else
+ } else {
+ /*
+ * Wake the vCPU if it was blocking. KVM will then detect the
+ * pending IRQ when checking if the vCPU has a wake event.
+ */
kvm_vcpu_wake_up(vcpu);
+ }
return 0;
}
@@ -957,6 +978,8 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
int h_physical_id = kvm_cpu_get_apicid(cpu);
struct vcpu_svm *svm = to_svm(vcpu);
+ lockdep_assert_preemption_disabled();
+
/*
* Since the host physical APIC id is 8 bits,
* we can support host APIC ID upto 255.
@@ -964,19 +987,25 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
return;
+ /*
+ * No need to update anything if the vCPU is blocking, i.e. if the vCPU
+ * is being scheduled in after being preempted. The CPU entries in the
+ * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
+ * If the vCPU was migrated, its new CPU value will be stuffed when the
+ * vCPU unblocks.
+ */
+ if (kvm_vcpu_is_blocking(vcpu))
+ return;
+
entry = READ_ONCE(*(svm->avic_physical_id_cache));
WARN_ON(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
-
- entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- if (svm->avic_is_running)
- entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+ entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
- avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
- svm->avic_is_running);
+ avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
}
void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -984,42 +1013,56 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
u64 entry;
struct vcpu_svm *svm = to_svm(vcpu);
+ lockdep_assert_preemption_disabled();
+
entry = READ_ONCE(*(svm->avic_physical_id_cache));
- if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
- avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
+ /* Nothing to do if IsRunning == '0' due to vCPU blocking. */
+ if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
+ return;
+
+ avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
}
-/*
- * This function is called during VCPU halt/unhalt.
- */
-static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
- int cpu = get_cpu();
+ if (!kvm_vcpu_apicv_active(vcpu))
+ return;
+ preempt_disable();
+
+ /*
+ * Unload the AVIC when the vCPU is about to block, _before_
+ * the vCPU actually blocks.
+ *
+ * Any IRQs that arrive before IsRunning=0 will not cause an
+ * incomplete IPI vmexit on the source, therefore vIRR will also
+ * be checked by kvm_vcpu_check_block() before blocking. The
+ * memory barrier implicit in set_current_state orders writing
+ * IsRunning=0 before reading the vIRR. The processor needs a
+ * matching memory barrier on interrupt delivery between writing
+ * IRR and reading IsRunning; the lack of this barrier might be
+ * the cause of errata #1235).
+ */
+ avic_vcpu_put(vcpu);
+
+ preempt_enable();
+}
+
+void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+ int cpu;
+
+ if (!kvm_vcpu_apicv_active(vcpu))
+ return;
+
+ cpu = get_cpu();
WARN_ON(cpu != vcpu->cpu);
- svm->avic_is_running = is_run;
- if (kvm_vcpu_apicv_active(vcpu)) {
- if (is_run)
- avic_vcpu_load(vcpu, cpu);
- else
- avic_vcpu_put(vcpu);
- }
+ avic_vcpu_load(vcpu, cpu);
+
put_cpu();
}
-
-void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
-{
- avic_set_running(vcpu, false);
-}
-
-void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
- if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
- kvm_vcpu_update_apicv(vcpu);
- avic_set_running(vcpu, true);
-}
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 12d8b30..5aa45f1 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -101,7 +101,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
{
struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
- if (!pmu)
+ if (!enable_pmu)
return NULL;
switch (msr) {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 46bcc70..2c99b18 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -192,10 +192,6 @@ module_param(vgif, int, 0444);
static int lbrv = true;
module_param(lbrv, int, 0444);
-/* enable/disable PMU virtualization */
-bool pmu = true;
-module_param(pmu, bool, 0444);
-
static int tsc_scaling = true;
module_param(tsc_scaling, int, 0444);
@@ -873,47 +869,6 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
}
}
-/*
- * The default MMIO mask is a single bit (excluding the present bit),
- * which could conflict with the memory encryption bit. Check for
- * memory encryption support and override the default MMIO mask if
- * memory encryption is enabled.
- */
-static __init void svm_adjust_mmio_mask(void)
-{
- unsigned int enc_bit, mask_bit;
- u64 msr, mask;
-
- /* If there is no memory encryption support, use existing mask */
- if (cpuid_eax(0x80000000) < 0x8000001f)
- return;
-
- /* If memory encryption is not enabled, use existing mask */
- rdmsrl(MSR_AMD64_SYSCFG, msr);
- if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
- return;
-
- enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
- mask_bit = boot_cpu_data.x86_phys_bits;
-
- /* Increment the mask bit if it is the same as the encryption bit */
- if (enc_bit == mask_bit)
- mask_bit++;
-
- /*
- * If the mask bit location is below 52, then some bits above the
- * physical addressing limit will always be reserved, so use the
- * rsvd_bits() function to generate the mask. This mask, along with
- * the present bit, will be used to generate a page fault with
- * PFER.RSV = 1.
- *
- * If the mask bit location is 52 (or above), then clear the mask.
- */
- mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
-
- kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
-}
-
static void svm_hardware_teardown(void)
{
int cpu;
@@ -928,198 +883,6 @@ static void svm_hardware_teardown(void)
iopm_base = 0;
}
-static __init void svm_set_cpu_caps(void)
-{
- kvm_set_cpu_caps();
-
- supported_xss = 0;
-
- /* CPUID 0x80000001 and 0x8000000A (SVM features) */
- if (nested) {
- kvm_cpu_cap_set(X86_FEATURE_SVM);
-
- if (nrips)
- kvm_cpu_cap_set(X86_FEATURE_NRIPS);
-
- if (npt_enabled)
- kvm_cpu_cap_set(X86_FEATURE_NPT);
-
- if (tsc_scaling)
- kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
-
- /* Nested VM can receive #VMEXIT instead of triggering #GP */
- kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
- }
-
- /* CPUID 0x80000008 */
- if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
- boot_cpu_has(X86_FEATURE_AMD_SSBD))
- kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
-
- /* AMD PMU PERFCTR_CORE CPUID */
- if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
- kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE);
-
- /* CPUID 0x8000001F (SME/SEV features) */
- sev_set_cpu_caps();
-}
-
-static __init int svm_hardware_setup(void)
-{
- int cpu;
- struct page *iopm_pages;
- void *iopm_va;
- int r;
- unsigned int order = get_order(IOPM_SIZE);
-
- /*
- * NX is required for shadow paging and for NPT if the NX huge pages
- * mitigation is enabled.
- */
- if (!boot_cpu_has(X86_FEATURE_NX)) {
- pr_err_ratelimited("NX (Execute Disable) not supported\n");
- return -EOPNOTSUPP;
- }
- kvm_enable_efer_bits(EFER_NX);
-
- iopm_pages = alloc_pages(GFP_KERNEL, order);
-
- if (!iopm_pages)
- return -ENOMEM;
-
- iopm_va = page_address(iopm_pages);
- memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
- iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
-
- init_msrpm_offsets();
-
- supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
-
- if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
- kvm_enable_efer_bits(EFER_FFXSR);
-
- if (tsc_scaling) {
- if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
- tsc_scaling = false;
- } else {
- pr_info("TSC scaling supported\n");
- kvm_has_tsc_control = true;
- kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
- kvm_tsc_scaling_ratio_frac_bits = 32;
- }
- }
-
- tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
-
- /* Check for pause filtering support */
- if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
- pause_filter_count = 0;
- pause_filter_thresh = 0;
- } else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
- pause_filter_thresh = 0;
- }
-
- if (nested) {
- printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
- kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
- }
-
- /*
- * KVM's MMU doesn't support using 2-level paging for itself, and thus
- * NPT isn't supported if the host is using 2-level paging since host
- * CR4 is unchanged on VMRUN.
- */
- if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
- npt_enabled = false;
-
- if (!boot_cpu_has(X86_FEATURE_NPT))
- npt_enabled = false;
-
- /* Force VM NPT level equal to the host's paging level */
- kvm_configure_mmu(npt_enabled, get_npt_level(),
- get_npt_level(), PG_LEVEL_1G);
- pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
-
- /* Note, SEV setup consumes npt_enabled. */
- sev_hardware_setup();
-
- svm_hv_hardware_setup();
-
- svm_adjust_mmio_mask();
-
- for_each_possible_cpu(cpu) {
- r = svm_cpu_init(cpu);
- if (r)
- goto err;
- }
-
- if (nrips) {
- if (!boot_cpu_has(X86_FEATURE_NRIPS))
- nrips = false;
- }
-
- enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC);
-
- if (enable_apicv) {
- pr_info("AVIC enabled\n");
-
- amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
- }
-
- if (vls) {
- if (!npt_enabled ||
- !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
- !IS_ENABLED(CONFIG_X86_64)) {
- vls = false;
- } else {
- pr_info("Virtual VMLOAD VMSAVE supported\n");
- }
- }
-
- if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK))
- svm_gp_erratum_intercept = false;
-
- if (vgif) {
- if (!boot_cpu_has(X86_FEATURE_VGIF))
- vgif = false;
- else
- pr_info("Virtual GIF supported\n");
- }
-
- if (lbrv) {
- if (!boot_cpu_has(X86_FEATURE_LBRV))
- lbrv = false;
- else
- pr_info("LBR virtualization supported\n");
- }
-
- if (!pmu)
- pr_info("PMU virtualization is disabled\n");
-
- svm_set_cpu_caps();
-
- /*
- * It seems that on AMD processors PTE's accessed bit is
- * being set by the CPU hardware before the NPF vmexit.
- * This is not expected behaviour and our tests fail because
- * of it.
- * A workaround here is to disable support for
- * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
- * In this case userspace can know if there is support using
- * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
- * it
- * If future AMD CPU models change the behaviour described above,
- * this variable can be changed accordingly
- */
- allow_smaller_maxphyaddr = !npt_enabled;
-
- return 0;
-
-err:
- svm_hardware_teardown();
- return r;
-}
-
static void init_seg(struct vmcb_seg *seg)
{
seg->selector = 0;
@@ -1444,12 +1207,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
if (err)
goto error_free_vmsa_page;
- /* We initialize this flag to true to make sure that the is_running
- * bit would be set the first time the vcpu is loaded.
- */
- if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm))
- svm->avic_is_running = true;
-
svm->msrpm = svm_vcpu_alloc_msrpm();
if (!svm->msrpm) {
err = -ENOMEM;
@@ -3833,6 +3590,11 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
svm_complete_interrupts(vcpu);
}
+static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+ return 1;
+}
+
static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
{
if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
@@ -4629,8 +4391,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.prepare_guest_switch = svm_prepare_guest_switch,
.vcpu_load = svm_vcpu_load,
.vcpu_put = svm_vcpu_put,
- .vcpu_blocking = svm_vcpu_blocking,
- .vcpu_unblocking = svm_vcpu_unblocking,
+ .vcpu_blocking = avic_vcpu_blocking,
+ .vcpu_unblocking = avic_vcpu_unblocking,
.update_exception_bitmap = svm_update_exception_bitmap,
.get_msr_feature = svm_get_msr_feature,
@@ -4662,6 +4424,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.tlb_flush_gva = svm_flush_tlb_gva,
.tlb_flush_guest = svm_flush_tlb,
+ .vcpu_pre_run = svm_vcpu_pre_run,
.run = svm_vcpu_run,
.handle_exit = handle_exit,
.skip_emulated_instruction = skip_emulated_instruction,
@@ -4742,6 +4505,243 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
};
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+ unsigned int enc_bit, mask_bit;
+ u64 msr, mask;
+
+ /* If there is no memory encryption support, use existing mask */
+ if (cpuid_eax(0x80000000) < 0x8000001f)
+ return;
+
+ /* If memory encryption is not enabled, use existing mask */
+ rdmsrl(MSR_AMD64_SYSCFG, msr);
+ if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
+ return;
+
+ enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+ mask_bit = boot_cpu_data.x86_phys_bits;
+
+ /* Increment the mask bit if it is the same as the encryption bit */
+ if (enc_bit == mask_bit)
+ mask_bit++;
+
+ /*
+ * If the mask bit location is below 52, then some bits above the
+ * physical addressing limit will always be reserved, so use the
+ * rsvd_bits() function to generate the mask. This mask, along with
+ * the present bit, will be used to generate a page fault with
+ * PFER.RSV = 1.
+ *
+ * If the mask bit location is 52 (or above), then clear the mask.
+ */
+ mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+ kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
+static __init void svm_set_cpu_caps(void)
+{
+ kvm_set_cpu_caps();
+
+ supported_xss = 0;
+
+ /* CPUID 0x80000001 and 0x8000000A (SVM features) */
+ if (nested) {
+ kvm_cpu_cap_set(X86_FEATURE_SVM);
+
+ if (nrips)
+ kvm_cpu_cap_set(X86_FEATURE_NRIPS);
+
+ if (npt_enabled)
+ kvm_cpu_cap_set(X86_FEATURE_NPT);
+
+ if (tsc_scaling)
+ kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
+
+ /* Nested VM can receive #VMEXIT instead of triggering #GP */
+ kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
+ }
+
+ /* CPUID 0x80000008 */
+ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
+ boot_cpu_has(X86_FEATURE_AMD_SSBD))
+ kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
+
+ /* AMD PMU PERFCTR_CORE CPUID */
+ if (enable_pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
+ kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE);
+
+ /* CPUID 0x8000001F (SME/SEV features) */
+ sev_set_cpu_caps();
+}
+
+static __init int svm_hardware_setup(void)
+{
+ int cpu;
+ struct page *iopm_pages;
+ void *iopm_va;
+ int r;
+ unsigned int order = get_order(IOPM_SIZE);
+
+ /*
+ * NX is required for shadow paging and for NPT if the NX huge pages
+ * mitigation is enabled.
+ */
+ if (!boot_cpu_has(X86_FEATURE_NX)) {
+ pr_err_ratelimited("NX (Execute Disable) not supported\n");
+ return -EOPNOTSUPP;
+ }
+ kvm_enable_efer_bits(EFER_NX);
+
+ iopm_pages = alloc_pages(GFP_KERNEL, order);
+
+ if (!iopm_pages)
+ return -ENOMEM;
+
+ iopm_va = page_address(iopm_pages);
+ memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
+ iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+
+ init_msrpm_offsets();
+
+ supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
+
+ if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
+ kvm_enable_efer_bits(EFER_FFXSR);
+
+ if (tsc_scaling) {
+ if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
+ tsc_scaling = false;
+ } else {
+ pr_info("TSC scaling supported\n");
+ kvm_has_tsc_control = true;
+ kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
+ kvm_tsc_scaling_ratio_frac_bits = 32;
+ }
+ }
+
+ tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
+
+ /* Check for pause filtering support */
+ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
+ pause_filter_count = 0;
+ pause_filter_thresh = 0;
+ } else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
+ pause_filter_thresh = 0;
+ }
+
+ if (nested) {
+ printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
+ kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
+ }
+
+ /*
+ * KVM's MMU doesn't support using 2-level paging for itself, and thus
+ * NPT isn't supported if the host is using 2-level paging since host
+ * CR4 is unchanged on VMRUN.
+ */
+ if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
+ npt_enabled = false;
+
+ if (!boot_cpu_has(X86_FEATURE_NPT))
+ npt_enabled = false;
+
+ /* Force VM NPT level equal to the host's paging level */
+ kvm_configure_mmu(npt_enabled, get_npt_level(),
+ get_npt_level(), PG_LEVEL_1G);
+ pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
+
+ /* Note, SEV setup consumes npt_enabled. */
+ sev_hardware_setup();
+
+ svm_hv_hardware_setup();
+
+ svm_adjust_mmio_mask();
+
+ for_each_possible_cpu(cpu) {
+ r = svm_cpu_init(cpu);
+ if (r)
+ goto err;
+ }
+
+ if (nrips) {
+ if (!boot_cpu_has(X86_FEATURE_NRIPS))
+ nrips = false;
+ }
+
+ enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC);
+
+ if (enable_apicv) {
+ pr_info("AVIC enabled\n");
+
+ amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+ } else {
+ svm_x86_ops.vcpu_blocking = NULL;
+ svm_x86_ops.vcpu_unblocking = NULL;
+ }
+
+ if (vls) {
+ if (!npt_enabled ||
+ !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
+ !IS_ENABLED(CONFIG_X86_64)) {
+ vls = false;
+ } else {
+ pr_info("Virtual VMLOAD VMSAVE supported\n");
+ }
+ }
+
+ if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK))
+ svm_gp_erratum_intercept = false;
+
+ if (vgif) {
+ if (!boot_cpu_has(X86_FEATURE_VGIF))
+ vgif = false;
+ else
+ pr_info("Virtual GIF supported\n");
+ }
+
+ if (lbrv) {
+ if (!boot_cpu_has(X86_FEATURE_LBRV))
+ lbrv = false;
+ else
+ pr_info("LBR virtualization supported\n");
+ }
+
+ if (!enable_pmu)
+ pr_info("PMU virtualization is disabled\n");
+
+ svm_set_cpu_caps();
+
+ /*
+ * It seems that on AMD processors PTE's accessed bit is
+ * being set by the CPU hardware before the NPF vmexit.
+ * This is not expected behaviour and our tests fail because
+ * of it.
+ * A workaround here is to disable support for
+ * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
+ * In this case userspace can know if there is support using
+ * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
+ * it
+ * If future AMD CPU models change the behaviour described above,
+ * this variable can be changed accordingly
+ */
+ allow_smaller_maxphyaddr = !npt_enabled;
+
+ return 0;
+
+err:
+ svm_hardware_teardown();
+ return r;
+}
+
+
static struct kvm_x86_init_ops svm_init_ops __initdata = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9f153c5..47ef8f4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -32,7 +32,6 @@
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
extern bool intercept_smi;
-extern bool pmu;
/*
* Clean bits in VMCB.
@@ -226,7 +225,6 @@ struct vcpu_svm {
u32 dfr_reg;
struct page *avic_backing_page;
u64 *avic_physical_id_cache;
- bool avic_is_running;
/*
* Per-vcpu list of struct amd_svm_iommu_ir:
@@ -574,17 +572,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
-static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
- u64 *entry = svm->avic_physical_id_cache;
-
- if (!entry)
- return false;
-
- return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
-}
-
int avic_ga_log_notifier(u32 ga_tag);
void avic_vm_destroy(struct kvm *kvm);
int avic_vm_init(struct kvm *kvm);
@@ -605,8 +592,8 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec);
bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu);
int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
-void svm_vcpu_blocking(struct kvm_vcpu *vcpu);
-void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);
+void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
+void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
/* sev.c */
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index c8029b7..959b59d 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -5,6 +5,7 @@
#include <asm/vmx.h>
#include "lapic.h"
+#include "x86.h"
extern bool __read_mostly enable_vpid;
extern bool __read_mostly flexpriority_enabled;
@@ -389,6 +390,9 @@ static inline u64 vmx_get_perf_capabilities(void)
{
u64 perf_cap = 0;
+ if (!enable_pmu)
+ return perf_cap;
+
if (boot_cpu_has(X86_FEATURE_PDCM))
rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 5e0ac57..466d18f 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -21,7 +21,6 @@
#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
static struct kvm_event_hw_type_mapping intel_arch_events[] = {
- /* Index must match CPUID 0x0A.EBX bit vector */
[0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
[2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES },
@@ -29,6 +28,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = {
[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+ /* The above index must match CPUID 0x0A.EBX bit vector */
[7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
};
@@ -75,11 +75,17 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
int i;
- for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
- if (intel_arch_events[i].eventsel == event_select &&
- intel_arch_events[i].unit_mask == unit_mask &&
- (pmc_is_fixed(pmc) || pmu->available_event_types & (1 << i)))
- break;
+ for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) {
+ if (intel_arch_events[i].eventsel != event_select ||
+ intel_arch_events[i].unit_mask != unit_mask)
+ continue;
+
+ /* disable event that reported as not present by cpuid */
+ if ((i < 7) && !(pmu->available_event_types & (1 << i)))
+ return PERF_COUNT_HW_MAX + 1;
+
+ break;
+ }
if (i == ARRAY_SIZE(intel_arch_events))
return PERF_COUNT_HW_MAX;
@@ -481,7 +487,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->reserved_bits = 0xffffffff00200000ull;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
- if (!entry)
+ if (!entry || !enable_pmu)
return;
eax.full = entry->eax;
edx.full = entry->edx;
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 88c53c5..aa1fe90 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -19,7 +19,7 @@
* wake the target vCPUs. vCPUs are removed from the list and the notification
* vector is reset when the vCPU is scheduled in.
*/
-static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
/*
* Protect the per-CPU list with a per-CPU spinlock to handle task migration.
* When a blocking vCPU is awakened _and_ migrated to a different pCPU, the
@@ -27,7 +27,7 @@ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
* CPU. IRQs must be disabled when taking this lock, otherwise deadlock will
* occur if a wakeup IRQ arrives and attempts to acquire the lock.
*/
-static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
@@ -51,7 +51,9 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new)
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
struct pi_desc old, new;
+ unsigned long flags;
unsigned int dest;
/*
@@ -62,23 +64,34 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
if (!enable_apicv || !lapic_in_kernel(vcpu))
return;
- /* Nothing to do if PI.SN and PI.NDST both have the desired value. */
- if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
- return;
-
/*
- * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
- * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
- * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
- * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
- * correctly.
+ * If the vCPU wasn't on the wakeup list and wasn't migrated, then the
+ * full update can be skipped as neither the vector nor the destination
+ * needs to be changed.
*/
- if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
- pi_clear_sn(pi_desc);
- goto after_clear_sn;
+ if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) {
+ /*
+ * Clear SN if it was set due to being preempted. Again, do
+ * this even if there is no assigned device for simplicity.
+ */
+ if (pi_test_and_clear_sn(pi_desc))
+ goto after_clear_sn;
+ return;
}
- /* The full case. Set the new destination and clear SN. */
+ local_irq_save(flags);
+
+ /*
+ * If the vCPU was waiting for wakeup, remove the vCPU from the wakeup
+ * list of the _previous_ pCPU, which will not be the same as the
+ * current pCPU if the task was migrated.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
+ raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ list_del(&vmx->pi_wakeup_list);
+ raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ }
+
dest = cpu_physical_id(cpu);
if (!x2apic_mode)
dest = (dest << 8) & 0xFF00;
@@ -86,10 +99,22 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
do {
old.control = new.control = READ_ONCE(pi_desc->control);
+ /*
+ * Clear SN (as above) and refresh the destination APIC ID to
+ * handle task migration (@cpu != vcpu->cpu).
+ */
new.ndst = dest;
new.sn = 0;
+
+ /*
+ * Restore the notification vector; in the blocking case, the
+ * descriptor was modified on "put" to use the wakeup vector.
+ */
+ new.nv = POSTED_INTR_VECTOR;
} while (pi_try_set_control(pi_desc, old.control, new.control));
+ local_irq_restore(flags);
+
after_clear_sn:
/*
@@ -111,83 +136,25 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
irq_remapping_cap(IRQ_POSTING_CAP);
}
-void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
-{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
- if (!vmx_can_use_vtd_pi(vcpu->kvm))
- return;
-
- /* Set SN when the vCPU is preempted */
- if (vcpu->preempted)
- pi_set_sn(pi_desc);
-}
-
-static void __pi_post_block(struct kvm_vcpu *vcpu)
-{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct pi_desc old, new;
- unsigned int dest;
-
- /*
- * Remove the vCPU from the wakeup list of the _previous_ pCPU, which
- * will not be the same as the current pCPU if the task was migrated.
- */
- spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-
- dest = cpu_physical_id(vcpu->cpu);
- if (!x2apic_mode)
- dest = (dest << 8) & 0xFF00;
-
- WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR,
- "Wakeup handler not enabled while the vCPU was blocking");
-
- do {
- old.control = new.control = READ_ONCE(pi_desc->control);
-
- new.ndst = dest;
-
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- } while (pi_try_set_control(pi_desc, old.control, new.control));
-
- vcpu->pre_pcpu = -1;
-}
-
/*
- * This routine does the following things for vCPU which is going
- * to be blocked if VT-d PI is enabled.
- * - Store the vCPU to the wakeup list, so when interrupts happen
- * we can find the right vCPU to wake up.
- * - Change the Posted-interrupt descriptor as below:
- * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR
- * - If 'ON' is set during this process, which means at least one
- * interrupt is posted for this vCPU, we cannot block it, in
- * this case, return 1, otherwise, return 0.
- *
+ * Put the vCPU on this pCPU's list of vCPUs that needs to be awakened and set
+ * WAKEUP as the notification vector in the PI descriptor.
*/
-int pi_pre_block(struct kvm_vcpu *vcpu)
+static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
{
- struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct pi_desc old, new;
unsigned long flags;
- if (!vmx_can_use_vtd_pi(vcpu->kvm) ||
- vmx_interrupt_blocked(vcpu))
- return 0;
-
local_irq_save(flags);
- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu));
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+ raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ list_add_tail(&vmx->pi_wakeup_list,
+ &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
+ raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
- WARN(pi_desc->sn == 1,
- "Posted Interrupt Suppress Notification set before blocking");
+ WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
do {
old.control = new.control = READ_ONCE(pi_desc->control);
@@ -196,24 +163,37 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
new.nv = POSTED_INTR_WAKEUP_VECTOR;
} while (pi_try_set_control(pi_desc, old.control, new.control));
- /* We should not block the vCPU if an interrupt is posted for it. */
- if (pi_test_on(pi_desc))
- __pi_post_block(vcpu);
+ /*
+ * Send a wakeup IPI to this CPU if an interrupt may have been posted
+ * before the notification vector was updated, in which case the IRQ
+ * will arrive on the non-wakeup vector. An IPI is needed as calling
+ * try_to_wake_up() from ->sched_out() isn't allowed (IRQs are not
+ * enabled until it is safe to call try_to_wake_up() on the task being
+ * scheduled out).
+ */
+ if (pi_test_on(&new))
+ apic->send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
local_irq_restore(flags);
- return (vcpu->pre_pcpu == -1);
}
-void pi_post_block(struct kvm_vcpu *vcpu)
+void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
+ struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (vcpu->pre_pcpu == -1)
+ if (!vmx_can_use_vtd_pi(vcpu->kvm))
return;
- local_irq_save(flags);
- __pi_post_block(vcpu);
- local_irq_restore(flags);
+ if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
+ pi_enable_wakeup_handler(vcpu);
+
+ /*
+ * Set SN when the vCPU is preempted. Note, the vCPU can both be seen
+ * as blocking and preempted, e.g. if it's preempted between setting
+ * its wait state and manually scheduling out.
+ */
+ if (vcpu->preempted)
+ pi_set_sn(pi_desc);
}
/*
@@ -221,24 +201,23 @@ void pi_post_block(struct kvm_vcpu *vcpu)
*/
void pi_wakeup_handler(void)
{
- struct kvm_vcpu *vcpu;
int cpu = smp_processor_id();
+ struct vcpu_vmx *vmx;
- spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
- list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
- blocked_vcpu_list) {
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
+ list_for_each_entry(vmx, &per_cpu(wakeup_vcpus_on_cpu, cpu),
+ pi_wakeup_list) {
- if (pi_test_on(pi_desc))
- kvm_vcpu_kick(vcpu);
+ if (pi_test_on(&vmx->pi_desc))
+ kvm_vcpu_wake_up(&vmx->vcpu);
}
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+ raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
}
void __init pi_init_cpu(int cpu)
{
- INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
- spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+ INIT_LIST_HEAD(&per_cpu(wakeup_vcpus_on_cpu, cpu));
+ raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
}
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -254,7 +233,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
* Bail out of the block loop if the VM has an assigned
* device, but the blocking vCPU didn't reconfigure the
* PI.NV to the wakeup vector, i.e. the assigned device
- * came along after the initial check in pi_pre_block().
+ * came along after the initial check in vmx_vcpu_pi_put().
*/
void vmx_pi_start_assignment(struct kvm *kvm)
{
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 36ae035f..eb14e76 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -40,6 +40,12 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
(unsigned long *)&pi_desc->control);
}
+static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
+{
+ return test_and_clear_bit(POSTED_INTR_SN,
+ (unsigned long *)&pi_desc->control);
+}
+
static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
{
return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
@@ -88,8 +94,6 @@ static inline bool pi_test_sn(struct pi_desc *pi_desc)
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
-int pi_pre_block(struct kvm_vcpu *vcpu);
-void pi_post_block(struct kvm_vcpu *vcpu);
void pi_wakeup_handler(void);
void __init pi_init_cpu(int cpu);
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1b2e9d8..4ac6760 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3931,12 +3931,10 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
pt_update_intercept_for_msr(vcpu);
}
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
- bool nested)
+static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+ int pi_vec)
{
#ifdef CONFIG_SMP
- int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
-
if (vcpu->mode == IN_GUEST_MODE) {
/*
* The vector of interrupt to be delivered to vcpu had
@@ -3964,10 +3962,15 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
*/
apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
- return true;
+ return;
}
#endif
- return false;
+ /*
+ * The vCPU isn't in the guest; wake the vCPU in case it is blocking,
+ * otherwise do nothing as KVM will grab the highest priority pending
+ * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest().
+ */
+ kvm_vcpu_wake_up(vcpu);
}
static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -3997,8 +4000,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
smp_mb__after_atomic();
/* the PIR and ON have been set by L1. */
- if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
- kvm_vcpu_kick(vcpu);
+ kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_NESTED_VECTOR);
return 0;
}
return -1;
@@ -4035,9 +4037,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
* guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
* posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
*/
- if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
- kvm_vcpu_kick(vcpu);
-
+ kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR);
return 0;
}
@@ -5426,6 +5426,14 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu)
return 1;
}
+static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ return vmx->emulation_required && !vmx->rmode.vm86_active &&
+ vcpu->arch.exception.pending;
+}
+
static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5445,8 +5453,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
if (!kvm_emulate_instruction(vcpu, 0))
return 0;
- if (vmx->emulation_required && !vmx->rmode.vm86_active &&
- vcpu->arch.exception.pending) {
+ if (vmx_emulation_required_with_pending_exception(vcpu)) {
kvm_prepare_emulation_failure_exit(vcpu);
return 0;
}
@@ -5468,6 +5475,16 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
return 1;
}
+static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+ if (vmx_emulation_required_with_pending_exception(vcpu)) {
+ kvm_prepare_emulation_failure_exit(vcpu);
+ return 0;
+ }
+
+ return 1;
+}
+
static void grow_ple_window(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6928,6 +6945,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
vmx = to_vmx(vcpu);
+ INIT_LIST_HEAD(&vmx->pi_wakeup_list);
+
err = -ENOMEM;
vmx->vpid = allocate_vpid();
@@ -7549,25 +7568,6 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML);
}
-static int vmx_pre_block(struct kvm_vcpu *vcpu)
-{
- if (pi_pre_block(vcpu))
- return 1;
-
- if (kvm_lapic_hv_timer_in_use(vcpu))
- kvm_lapic_switch_to_sw_timer(vcpu);
-
- return 0;
-}
-
-static void vmx_post_block(struct kvm_vcpu *vcpu)
-{
- if (kvm_x86_ops.set_hv_timer)
- kvm_lapic_switch_to_hv_timer(vcpu);
-
- pi_post_block(vcpu);
-}
-
static void vmx_setup_mce(struct kvm_vcpu *vcpu)
{
if (vcpu->arch.mcg_cap & MCG_LMCE_P)
@@ -7710,6 +7710,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.tlb_flush_gva = vmx_flush_tlb_gva,
.tlb_flush_guest = vmx_flush_tlb_guest,
+ .vcpu_pre_run = vmx_vcpu_pre_run,
.run = vmx_vcpu_run,
.handle_exit = vmx_handle_exit,
.skip_emulated_instruction = vmx_skip_emulated_instruction,
@@ -7768,9 +7769,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.cpu_dirty_log_size = PML_ENTITY_NUM,
.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
- .pre_block = vmx_pre_block,
- .post_block = vmx_post_block,
-
.pmu_ops = &intel_pmu_ops,
.nested_ops = &vmx_nested_ops,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index f8fc744..7f2c82e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -317,6 +317,9 @@ struct vcpu_vmx {
/* Posted interrupt descriptor */
struct pi_desc pi_desc;
+ /* Used if this vCPU is waiting for PI notification wakeup. */
+ struct list_head pi_wakeup_list;
+
/* Support for a guest hypervisor (nested VMX) */
struct nested_vmx nested;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 76b4803..9e43d75 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -187,6 +187,11 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
int __read_mostly pi_inject_timer = -1;
module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
+/* Enable/disable PMU virtualization */
+bool __read_mostly enable_pmu = true;
+EXPORT_SYMBOL_GPL(enable_pmu);
+module_param(enable_pmu, bool, 0444);
+
/*
* Restoring the host value for MSRs that are only consumed when running in
* usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
@@ -5230,17 +5235,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
struct kvm_cpuid __user *cpuid_arg = argp;
struct kvm_cpuid cpuid;
- /*
- * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
- * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
- * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page
- * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with
- * the core vCPU model on the fly, so fail.
- */
- r = -EINVAL;
- if (vcpu->arch.last_vmentry_cpu != -1)
- goto out;
-
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
goto out;
@@ -5251,14 +5245,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
- /*
- * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
- * KVM_SET_CPUID case above.
- */
- r = -EINVAL;
- if (vcpu->arch.last_vmentry_cpu != -1)
- goto out;
-
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
goto out;
@@ -9945,10 +9931,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
smp_mb__after_srcu_read_unlock();
/*
- * This handles the case where a posted interrupt was
- * notified with kvm_vcpu_kick. Assigned devices can
- * use the POSTED_INTR_VECTOR even if APICv is disabled,
- * so do it even if APICv is disabled on this vCPU.
+ * Process pending posted interrupts to handle the case where the
+ * notification IRQ arrived in the host, or was never sent (because the
+ * target vCPU wasn't running). Do this regardless of the vCPU's APICv
+ * status, KVM doesn't update assigned devices when APICv is inhibited,
+ * i.e. they can post interrupts even if APICv is temporarily disabled.
*/
if (kvm_lapic_enabled(vcpu))
static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
@@ -10113,8 +10100,20 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
{
- if (!kvm_arch_vcpu_runnable(vcpu) &&
- (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) {
+ bool hv_timer;
+
+ if (!kvm_arch_vcpu_runnable(vcpu)) {
+ /*
+ * Switch to the software timer before halt-polling/blocking as
+ * the guest's timer may be a break event for the vCPU, and the
+ * hypervisor timer runs only when the CPU is in guest mode.
+ * Switch before halt-polling so that KVM recognizes an expired
+ * timer before blocking.
+ */
+ hv_timer = kvm_lapic_hv_timer_in_use(vcpu);
+ if (hv_timer)
+ kvm_lapic_switch_to_sw_timer(vcpu);
+
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
kvm_vcpu_halt(vcpu);
@@ -10122,8 +10121,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
kvm_vcpu_block(vcpu);
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- if (kvm_x86_ops.post_block)
- static_call(kvm_x86_post_block)(vcpu);
+ if (hv_timer)
+ kvm_lapic_switch_to_hv_timer(vcpu);
if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
return 1;
@@ -10316,6 +10315,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
r = -EINTR;
goto out;
}
+ /*
+ * It should be impossible for the hypervisor timer to be in
+ * use before KVM has ever run the vCPU.
+ */
+ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));
kvm_vcpu_block(vcpu);
if (kvm_apic_accept_events(vcpu) < 0) {
r = 0;
@@ -10360,10 +10364,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
} else
WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
- if (kvm_run->immediate_exit)
+ if (kvm_run->immediate_exit) {
r = -EINTR;
- else
- r = vcpu_run(vcpu);
+ goto out;
+ }
+
+ r = static_call(kvm_x86_vcpu_pre_run)(vcpu);
+ if (r <= 0)
+ goto out;
+
+ r = vcpu_run(vcpu);
out:
kvm_put_guest_fpu(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index bec8ed0..635b75f9 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -336,6 +336,7 @@ extern u64 host_xcr0;
extern u64 supported_xcr0;
extern u64 host_xss;
extern u64 supported_xss;
+extern bool enable_pmu;
static inline bool kvm_mpx_supported(void)
{
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 9778216..ee27695 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -12,7 +12,7 @@
# Core configuration.
# (Use VAR=<xtensa_config> to use another default compiler.)
-variant-y := $(patsubst "%",%,$(CONFIG_XTENSA_VARIANT_NAME))
+variant-y := $(CONFIG_XTENSA_VARIANT_NAME)
VARIANT = $(variant-y)
diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile
index 0b8d00c..720628c 100644
--- a/arch/xtensa/boot/dts/Makefile
+++ b/arch/xtensa/boot/dts/Makefile
@@ -7,10 +7,7 @@
#
#
-BUILTIN_DTB_SOURCE := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
-ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
-obj-$(CONFIG_OF) += $(BUILTIN_DTB_SOURCE)
-endif
+obj-$(CONFIG_OF) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
# for CONFIG_OF_ALL_DTBS test
dtstree := $(srctree)/$(src)
diff --git a/block/bio.c b/block/bio.c
index 0d400ba..4312a80 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -569,7 +569,8 @@ static void bio_truncate(struct bio *bio, unsigned new_size)
offset = new_size - done;
else
offset = 0;
- zero_user(bv.bv_page, offset, bv.bv_len - offset);
+ zero_user(bv.bv_page, bv.bv_offset + offset,
+ bv.bv_len - offset);
truncated = true;
}
done += bv.bv_len;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index e55a683..845f74e 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -17,6 +17,21 @@
#include "blk-mq-tag.h"
/*
+ * Recalculate wakeup batch when tag is shared by hctx.
+ */
+static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
+ unsigned int users)
+{
+ if (!users)
+ return;
+
+ sbitmap_queue_recalculate_wake_batch(&tags->bitmap_tags,
+ users);
+ sbitmap_queue_recalculate_wake_batch(&tags->breserved_tags,
+ users);
+}
+
+/*
* If a previously inactive queue goes active, bump the active user count.
* We need to do this before try to allocate driver tag, then even if fail
* to get tag when first time, the other shared-tag users could reserve
@@ -24,18 +39,26 @@
*/
bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
+ unsigned int users;
+
if (blk_mq_is_shared_tags(hctx->flags)) {
struct request_queue *q = hctx->queue;
- if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
- !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
- atomic_inc(&hctx->tags->active_queues);
+ if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) ||
+ test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) {
+ return true;
+ }
} else {
- if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
- !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
- atomic_inc(&hctx->tags->active_queues);
+ if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) ||
+ test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) {
+ return true;
+ }
}
+ users = atomic_inc_return(&hctx->tags->active_queues);
+
+ blk_mq_update_wake_batch(hctx->tags, users);
+
return true;
}
@@ -56,6 +79,7 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
struct blk_mq_tags *tags = hctx->tags;
+ unsigned int users;
if (blk_mq_is_shared_tags(hctx->flags)) {
struct request_queue *q = hctx->queue;
@@ -68,7 +92,9 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
return;
}
- atomic_dec(&tags->active_queues);
+ users = atomic_dec_return(&tags->active_queues);
+
+ blk_mq_update_wake_batch(tags, users);
blk_mq_tag_wakeup_all(tags, false);
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a6d4780..b5e35e6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2976,6 +2976,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
bio = bio_clone_fast(bio_src, gfp_mask, bs);
if (!bio)
goto free_and_out;
+ bio->bi_bdev = rq->q->disk->part0;
if (bio_ctr && bio_ctr(bio, bio_src, data))
goto free_and_out;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e20eadf..9f32882 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -811,6 +811,9 @@ static void blk_release_queue(struct kobject *kobj)
bioset_exit(&q->bio_split);
+ if (blk_queue_has_srcu(q))
+ cleanup_srcu_struct(q->srcu);
+
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
@@ -887,7 +890,6 @@ int blk_register_queue(struct gendisk *disk)
kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
mutex_unlock(&q->sysfs_lock);
- ret = 0;
unlock:
mutex_unlock(&q->sysfs_dir_lock);
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 85d919b..3ed5eaf 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -865,7 +865,7 @@ SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
SHOW_JIFFIES(deadline_prio_aging_expire_show, dd->prio_aging_expire);
SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
SHOW_INT(deadline_front_merges_show, dd->front_merges);
-SHOW_INT(deadline_async_depth_show, dd->front_merges);
+SHOW_INT(deadline_async_depth_show, dd->async_depth);
SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch);
#undef SHOW_INT
#undef SHOW_JIFFIES
@@ -895,7 +895,7 @@ STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MA
STORE_JIFFIES(deadline_prio_aging_expire_store, &dd->prio_aging_expire, 0, INT_MAX);
STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
-STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
+STORE_INT(deadline_async_depth_store, &dd->async_depth, 1, INT_MAX);
STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX);
#undef STORE_FUNCTION
#undef STORE_INT
diff --git a/certs/.gitignore b/certs/.gitignore
index 8c3763f..9e42fe3 100644
--- a/certs/.gitignore
+++ b/certs/.gitignore
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
+/extract-cert
/x509_certificate_list
/x509_revocation_list
diff --git a/certs/Kconfig b/certs/Kconfig
index ae7f2e8..73d1350 100644
--- a/certs/Kconfig
+++ b/certs/Kconfig
@@ -17,21 +17,19 @@
choice
prompt "Type of module signing key to be generated"
- default MODULE_SIG_KEY_TYPE_RSA
+ depends on MODULE_SIG || (IMA_APPRAISE_MODSIG && MODULES)
help
The type of module signing key type to generate. This option
does not apply if a #PKCS11 URI is used.
config MODULE_SIG_KEY_TYPE_RSA
bool "RSA"
- depends on MODULE_SIG || (IMA_APPRAISE_MODSIG && MODULES)
help
Use an RSA key for module signing.
config MODULE_SIG_KEY_TYPE_ECDSA
bool "ECDSA"
select CRYPTO_ECDSA
- depends on MODULE_SIG || (IMA_APPRAISE_MODSIG && MODULES)
help
Use an elliptic curve key (NIST P384) for module signing. Consider
using a strong hash like sha256 or sha384 for hashing modules.
diff --git a/certs/Makefile b/certs/Makefile
index 2794337..f7041c2 100644
--- a/certs/Makefile
+++ b/certs/Makefile
@@ -6,31 +6,21 @@
obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o
obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o
obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o
-ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"")
+ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),)
obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o
else
obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_nohashes.o
endif
-ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+quiet_cmd_extract_certs = CERT $@
+ cmd_extract_certs = $(obj)/extract-cert $(2) $@
-$(eval $(call config_filename,SYSTEM_TRUSTED_KEYS))
-
-# GCC doesn't include .incbin files in -MD generated dependencies (PR#66871)
$(obj)/system_certificates.o: $(obj)/x509_certificate_list
-# Cope with signing_key.x509 existing in $(srctree) not $(objtree)
-AFLAGS_system_certificates.o := -I$(srctree)
-
-quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2))
- cmd_extract_certs = scripts/extract-cert $(2) $@
+$(obj)/x509_certificate_list: $(CONFIG_SYSTEM_TRUSTED_KEYS) $(obj)/extract-cert FORCE
+ $(call if_changed,extract_certs,$(if $(CONFIG_SYSTEM_TRUSTED_KEYS),$<,""))
targets += x509_certificate_list
-$(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(SYSTEM_TRUSTED_KEYS_FILENAME) FORCE
- $(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS))
-endif # CONFIG_SYSTEM_TRUSTED_KEYRING
-
-clean-files := x509_certificate_list .x509.list x509_revocation_list
ifeq ($(CONFIG_MODULE_SIG),y)
SIGN_KEY = y
@@ -50,103 +40,54 @@
# fail and that the kernel may be used afterwards.
#
###############################################################################
-ifndef CONFIG_MODULE_SIG_HASH
-$(error Could not determine digest type to use from kernel config)
-endif
-
-redirect_openssl = 2>&1
-quiet_redirect_openssl = 2>&1
-silent_redirect_openssl = 2>/dev/null
-openssl_available = $(shell openssl help 2>/dev/null && echo yes)
# We do it this way rather than having a boolean option for enabling an
# external private key, because 'make randconfig' might enable such a
# boolean option and we unfortunately can't make it depend on !RANDCONFIG.
-ifeq ($(CONFIG_MODULE_SIG_KEY),"certs/signing_key.pem")
+ifeq ($(CONFIG_MODULE_SIG_KEY),certs/signing_key.pem)
-ifeq ($(openssl_available),yes)
-X509TEXT=$(shell openssl x509 -in "certs/signing_key.pem" -text 2>/dev/null)
-endif
+keytype-$(CONFIG_MODULE_SIG_KEY_TYPE_ECDSA) := -newkey ec -pkeyopt ec_paramgen_curve:secp384r1
-# Support user changing key type
-ifdef CONFIG_MODULE_SIG_KEY_TYPE_ECDSA
-keytype_openssl = -newkey ec -pkeyopt ec_paramgen_curve:secp384r1
-ifeq ($(openssl_available),yes)
-$(if $(findstring id-ecPublicKey,$(X509TEXT)),,$(shell rm -f "certs/signing_key.pem"))
-endif
-endif # CONFIG_MODULE_SIG_KEY_TYPE_ECDSA
+quiet_cmd_gen_key = GENKEY $@
+ cmd_gen_key = openssl req -new -nodes -utf8 -$(CONFIG_MODULE_SIG_HASH) -days 36500 \
+ -batch -x509 -config $< \
+ -outform PEM -out $@ -keyout $@ $(keytype-y) 2>&1
-ifdef CONFIG_MODULE_SIG_KEY_TYPE_RSA
-ifeq ($(openssl_available),yes)
-$(if $(findstring rsaEncryption,$(X509TEXT)),,$(shell rm -f "certs/signing_key.pem"))
-endif
-endif # CONFIG_MODULE_SIG_KEY_TYPE_RSA
+$(obj)/signing_key.pem: $(obj)/x509.genkey FORCE
+ $(call if_changed,gen_key)
-$(obj)/signing_key.pem: $(obj)/x509.genkey
- @$(kecho) "###"
- @$(kecho) "### Now generating an X.509 key pair to be used for signing modules."
- @$(kecho) "###"
- @$(kecho) "### If this takes a long time, you might wish to run rngd in the"
- @$(kecho) "### background to keep the supply of entropy topped up. It"
- @$(kecho) "### needs to be run as root, and uses a hardware random"
- @$(kecho) "### number generator if one is available."
- @$(kecho) "###"
- $(Q)openssl req -new -nodes -utf8 -$(CONFIG_MODULE_SIG_HASH) -days 36500 \
- -batch -x509 -config $(obj)/x509.genkey \
- -outform PEM -out $(obj)/signing_key.pem \
- -keyout $(obj)/signing_key.pem \
- $(keytype_openssl) \
- $($(quiet)redirect_openssl)
- @$(kecho) "###"
- @$(kecho) "### Key pair generated."
- @$(kecho) "###"
+targets += signing_key.pem
+quiet_cmd_copy_x509_config = COPY $@
+ cmd_copy_x509_config = cat $(srctree)/$(src)/default_x509.genkey > $@
+
+# You can provide your own config file. If not present, copy the default one.
$(obj)/x509.genkey:
- @$(kecho) Generating X.509 key generation config
- @echo >$@ "[ req ]"
- @echo >>$@ "default_bits = 4096"
- @echo >>$@ "distinguished_name = req_distinguished_name"
- @echo >>$@ "prompt = no"
- @echo >>$@ "string_mask = utf8only"
- @echo >>$@ "x509_extensions = myexts"
- @echo >>$@
- @echo >>$@ "[ req_distinguished_name ]"
- @echo >>$@ "#O = Unspecified company"
- @echo >>$@ "CN = Build time autogenerated kernel key"
- @echo >>$@ "#emailAddress = unspecified.user@unspecified.company"
- @echo >>$@
- @echo >>$@ "[ myexts ]"
- @echo >>$@ "basicConstraints=critical,CA:FALSE"
- @echo >>$@ "keyUsage=digitalSignature"
- @echo >>$@ "subjectKeyIdentifier=hash"
- @echo >>$@ "authorityKeyIdentifier=keyid"
+ $(call cmd,copy_x509_config)
+
endif # CONFIG_MODULE_SIG_KEY
-$(eval $(call config_filename,MODULE_SIG_KEY))
-
# If CONFIG_MODULE_SIG_KEY isn't a PKCS#11 URI, depend on it
-ifeq ($(patsubst pkcs11:%,%,$(firstword $(MODULE_SIG_KEY_FILENAME))),$(firstword $(MODULE_SIG_KEY_FILENAME)))
-X509_DEP := $(MODULE_SIG_KEY_SRCPREFIX)$(MODULE_SIG_KEY_FILENAME)
+ifneq ($(filter-out pkcs11:%, %(CONFIG_MODULE_SIG_KEY)),)
+X509_DEP := $(CONFIG_MODULE_SIG_KEY)
endif
-# GCC PR#66871 again.
$(obj)/system_certificates.o: $(obj)/signing_key.x509
-targets += signing_key.x509
-$(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE
- $(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY))
+$(obj)/signing_key.x509: $(X509_DEP) $(obj)/extract-cert FORCE
+ $(call if_changed,extract_certs,$(if $(X509_DEP),$<,$(CONFIG_MODULE_SIG_KEY)))
endif # CONFIG_MODULE_SIG
-ifeq ($(CONFIG_SYSTEM_REVOCATION_LIST),y)
-
-$(eval $(call config_filename,SYSTEM_REVOCATION_KEYS))
+targets += signing_key.x509
$(obj)/revocation_certificates.o: $(obj)/x509_revocation_list
-quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2))
- cmd_extract_certs = scripts/extract-cert $(2) $@
+$(obj)/x509_revocation_list: $(CONFIG_SYSTEM_REVOCATION_KEYS) $(obj)/extract-cert FORCE
+ $(call if_changed,extract_certs,$(if $(CONFIG_SYSTEM_REVOCATION_KEYS),$<,""))
targets += x509_revocation_list
-$(obj)/x509_revocation_list: scripts/extract-cert $(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(SYSTEM_REVOCATION_KEYS_FILENAME) FORCE
- $(call if_changed,extract_certs,$(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_REVOCATION_KEYS))
-endif
+
+hostprogs := extract-cert
+
+HOSTCFLAGS_extract-cert.o = $(shell pkg-config --cflags libcrypto 2> /dev/null)
+HOSTLDLIBS_extract-cert = $(shell pkg-config --libs libcrypto 2> /dev/null || echo -lcrypto)
diff --git a/certs/default_x509.genkey b/certs/default_x509.genkey
new file mode 100644
index 0000000..d4c6628
--- /dev/null
+++ b/certs/default_x509.genkey
@@ -0,0 +1,17 @@
+[ req ]
+default_bits = 4096
+distinguished_name = req_distinguished_name
+prompt = no
+string_mask = utf8only
+x509_extensions = myexts
+
+[ req_distinguished_name ]
+#O = Unspecified company
+CN = Build time autogenerated kernel key
+#emailAddress = unspecified.user@unspecified.company
+
+[ myexts ]
+basicConstraints=critical,CA:FALSE
+keyUsage=digitalSignature
+subjectKeyIdentifier=hash
+authorityKeyIdentifier=keyid
diff --git a/scripts/extract-cert.c b/certs/extract-cert.c
similarity index 98%
rename from scripts/extract-cert.c
rename to certs/extract-cert.c
index 3bc48c7..f7ef786 100644
--- a/scripts/extract-cert.c
+++ b/certs/extract-cert.c
@@ -29,7 +29,7 @@ static __attribute__((noreturn))
void format(void)
{
fprintf(stderr,
- "Usage: scripts/extract-cert <source> <dest>\n");
+ "Usage: extract-cert <source> <dest>\n");
exit(2);
}
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 94bfa32..4427652 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1928,5 +1928,3 @@
source "certs/Kconfig"
endif # if CRYPTO
-
-source "lib/crypto/Kconfig"
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 705331e..ba45541b 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -520,6 +520,28 @@
userspace. The configurable ACPI groups will be visible under
/config/acpi, assuming configfs is mounted under /config.
+config ACPI_PFRUT
+ tristate "ACPI Platform Firmware Runtime Update and Telemetry"
+ depends on 64BIT
+ help
+ This mechanism allows certain pieces of the platform firmware
+ to be updated on the fly while the system is running (runtime)
+ without the need to restart it, which is key in the cases when
+ the system needs to be available 100% of the time and it cannot
+ afford the downtime related to restarting it, or when the work
+ carried out by the system is particularly important, so it cannot
+ be interrupted, and it is not practical to wait until it is complete.
+
+ The existing firmware code can be modified (driver update) or
+ extended by adding new code to the firmware (code injection).
+
+ Besides, the telemetry driver allows user space to fetch telemetry
+ data from the firmware with the help of the Platform Firmware Runtime
+ Telemetry interface.
+
+ To compile the drivers as modules, choose M here:
+ the modules will be called pfr_update and pfr_telemetry.
+
if ARM64
source "drivers/acpi/arm64/Kconfig"
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 08c2d98..bb75714 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -9,7 +9,7 @@
# ACPI Boot-Time Table Parsing
#
ifeq ($(CONFIG_ACPI_CUSTOM_DSDT),y)
-tables.o: $(src)/../../include/$(subst $\",,$(CONFIG_ACPI_CUSTOM_DSDT_FILE)) ;
+tables.o: $(src)/../../include/$(CONFIG_ACPI_CUSTOM_DSDT_FILE) ;
endif
@@ -103,6 +103,7 @@
obj-$(CONFIG_ACPI_SPCR_TABLE) += spcr.o
obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o
obj-$(CONFIG_ACPI_PPTT) += pptt.o
+obj-$(CONFIG_ACPI_PFRUT) += pfr_update.o pfr_telemetry.o
# processor has its own "processor." module_param namespace
processor-y := processor_driver.o
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index 2b958b4..e7934ba 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -102,6 +102,8 @@ static int fch_misc_setup(struct apd_private_data *pdata)
resource_size(rentry->res));
break;
}
+ if (!clk_data->base)
+ return -ENOMEM;
acpi_dev_free_resource_list(&resource_list);
diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c
index 41e3ebd..a12b55d 100644
--- a/drivers/acpi/acpi_pcc.c
+++ b/drivers/acpi/acpi_pcc.c
@@ -31,7 +31,7 @@ struct pcc_data {
struct acpi_pcc_info ctx;
};
-struct acpi_pcc_info pcc_ctx;
+static struct acpi_pcc_info pcc_ctx;
static void pcc_rx_callback(struct mbox_client *cl, void *m)
{
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a9d2de4..866560cb 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -915,30 +915,31 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
{
- int ret_val = 0;
void __iomem *vaddr = NULL;
int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
struct cpc_reg *reg = ®_res->cpc_entry.reg;
if (reg_res->type == ACPI_TYPE_INTEGER) {
*val = reg_res->cpc_entry.int_value;
- return ret_val;
+ return 0;
}
*val = 0;
if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
u32 width = 8 << (reg->access_width - 1);
+ u32 val_u32;
acpi_status status;
status = acpi_os_read_port((acpi_io_address)reg->address,
- (u32 *)val, width);
+ &val_u32, width);
if (ACPI_FAILURE(status)) {
pr_debug("Error: Failed to read SystemIO port %llx\n",
reg->address);
return -EFAULT;
}
+ *val = val_u32;
return 0;
} else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
@@ -966,10 +967,10 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
default:
pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
reg->bit_width, pcc_ss_id);
- ret_val = -EFAULT;
+ return -EFAULT;
}
- return ret_val;
+ return 0;
}
static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c
index e7ab0fc..c0da24c 100644
--- a/drivers/acpi/dptf/dptf_pch_fivr.c
+++ b/drivers/acpi/dptf/dptf_pch_fivr.c
@@ -151,6 +151,7 @@ static int pch_fivr_remove(struct platform_device *pdev)
static const struct acpi_device_id pch_fivr_device_ids[] = {
{"INTC1045", 0},
{"INTC1049", 0},
+ {"INTC10A3", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids);
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index a24d5d7..dc1f52a 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -231,6 +231,8 @@ static const struct acpi_device_id int3407_device_ids[] = {
{"INTC1050", 0},
{"INTC1060", 0},
{"INTC1061", 0},
+ {"INTC10A4", 0},
+ {"INTC10A5", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index da5d5f0..42a5563 100644
--- a/drivers/acpi/dptf/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
@@ -37,6 +37,12 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = {
{"INTC1050"},
{"INTC1060"},
{"INTC1061"},
+ {"INTC10A0"},
+ {"INTC10A1"},
+ {"INTC10A2"},
+ {"INTC10A3"},
+ {"INTC10A4"},
+ {"INTC10A5"},
{""},
};
diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h
index dc9a6ef..dd9bb8c 100644
--- a/drivers/acpi/fan.h
+++ b/drivers/acpi/fan.h
@@ -10,4 +10,5 @@
{"INT3404", }, /* Fan */ \
{"INTC1044", }, /* Fan for Tiger Lake generation */ \
{"INTC1048", }, /* Fan for Alder Lake generation */ \
+ {"INTC10A2", }, /* Fan for Raptor Lake generation */ \
{"PNP0C0B", } /* Generic ACPI fan */
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1db3a2f..457e11d 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -14,7 +14,7 @@
int early_acpi_osi_init(void);
int acpi_osi_init(void);
acpi_status acpi_os_initialize1(void);
-int acpi_scan_init(void);
+void acpi_scan_init(void);
#ifdef CONFIG_PCI
void acpi_pci_root_init(void);
void acpi_pci_link_init(void);
diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c
new file mode 100644
index 0000000..9abf350
--- /dev/null
+++ b/drivers/acpi/pfr_telemetry.c
@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACPI Platform Firmware Runtime Telemetry driver
+ *
+ * Copyright (C) 2021 Intel Corporation
+ * Author: Chen Yu <yu.c.chen@intel.com>
+ *
+ * This driver allows user space to fetch telemetry data from the
+ * firmware with the help of the Platform Firmware Runtime Telemetry
+ * interface.
+ */
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/uio.h>
+#include <linux/uuid.h>
+
+#include <uapi/linux/pfrut.h>
+
+#define PFRT_LOG_EXEC_IDX 0
+#define PFRT_LOG_HISTORY_IDX 1
+
+#define PFRT_LOG_ERR 0
+#define PFRT_LOG_WARN 1
+#define PFRT_LOG_INFO 2
+#define PFRT_LOG_VERB 4
+
+#define PFRT_FUNC_SET_LEV 1
+#define PFRT_FUNC_GET_LEV 2
+#define PFRT_FUNC_GET_DATA 3
+
+#define PFRT_REVID_1 1
+#define PFRT_REVID_2 2
+#define PFRT_DEFAULT_REV_ID PFRT_REVID_1
+
+enum log_index {
+ LOG_STATUS_IDX = 0,
+ LOG_EXT_STATUS_IDX = 1,
+ LOG_MAX_SZ_IDX = 2,
+ LOG_CHUNK1_LO_IDX = 3,
+ LOG_CHUNK1_HI_IDX = 4,
+ LOG_CHUNK1_SZ_IDX = 5,
+ LOG_CHUNK2_LO_IDX = 6,
+ LOG_CHUNK2_HI_IDX = 7,
+ LOG_CHUNK2_SZ_IDX = 8,
+ LOG_ROLLOVER_CNT_IDX = 9,
+ LOG_RESET_CNT_IDX = 10,
+ LOG_NR_IDX
+};
+
+struct pfrt_log_device {
+ int index;
+ struct pfrt_log_info info;
+ struct device *parent_dev;
+ struct miscdevice miscdev;
+};
+
+/* pfrt_guid is the parameter for _DSM method */
+static const guid_t pfrt_log_guid =
+ GUID_INIT(0x75191659, 0x8178, 0x4D9D, 0xB8, 0x8F, 0xAC, 0x5E,
+ 0x5E, 0x93, 0xE8, 0xBF);
+
+static DEFINE_IDA(pfrt_log_ida);
+
+static inline struct pfrt_log_device *to_pfrt_log_dev(struct file *file)
+{
+ return container_of(file->private_data, struct pfrt_log_device, miscdev);
+}
+
+static int get_pfrt_log_data_info(struct pfrt_log_data_info *data_info,
+ struct pfrt_log_device *pfrt_log_dev)
+{
+ acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev);
+ union acpi_object *out_obj, in_obj, in_buf;
+ int ret = -EBUSY;
+
+ memset(data_info, 0, sizeof(*data_info));
+ memset(&in_obj, 0, sizeof(in_obj));
+ memset(&in_buf, 0, sizeof(in_buf));
+ in_obj.type = ACPI_TYPE_PACKAGE;
+ in_obj.package.count = 1;
+ in_obj.package.elements = &in_buf;
+ in_buf.type = ACPI_TYPE_INTEGER;
+ in_buf.integer.value = pfrt_log_dev->info.log_type;
+
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid,
+ pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_DATA,
+ &in_obj, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return -EINVAL;
+
+ if (out_obj->package.count < LOG_NR_IDX ||
+ out_obj->package.elements[LOG_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_MAX_SZ_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK1_LO_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK1_HI_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK1_SZ_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK2_LO_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK2_HI_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_CHUNK2_SZ_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[LOG_RESET_CNT_IDX].type != ACPI_TYPE_INTEGER)
+ goto free_acpi_buffer;
+
+ data_info->status = out_obj->package.elements[LOG_STATUS_IDX].integer.value;
+ data_info->ext_status =
+ out_obj->package.elements[LOG_EXT_STATUS_IDX].integer.value;
+ if (data_info->status != DSM_SUCCEED) {
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", data_info->status);
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n",
+ data_info->ext_status);
+ goto free_acpi_buffer;
+ }
+
+ data_info->max_data_size =
+ out_obj->package.elements[LOG_MAX_SZ_IDX].integer.value;
+ data_info->chunk1_addr_lo =
+ out_obj->package.elements[LOG_CHUNK1_LO_IDX].integer.value;
+ data_info->chunk1_addr_hi =
+ out_obj->package.elements[LOG_CHUNK1_HI_IDX].integer.value;
+ data_info->chunk1_size =
+ out_obj->package.elements[LOG_CHUNK1_SZ_IDX].integer.value;
+ data_info->chunk2_addr_lo =
+ out_obj->package.elements[LOG_CHUNK2_LO_IDX].integer.value;
+ data_info->chunk2_addr_hi =
+ out_obj->package.elements[LOG_CHUNK2_HI_IDX].integer.value;
+ data_info->chunk2_size =
+ out_obj->package.elements[LOG_CHUNK2_SZ_IDX].integer.value;
+ data_info->rollover_cnt =
+ out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].integer.value;
+ data_info->reset_cnt =
+ out_obj->package.elements[LOG_RESET_CNT_IDX].integer.value;
+
+ ret = 0;
+
+free_acpi_buffer:
+ kfree(out_obj);
+
+ return ret;
+}
+
+static int set_pfrt_log_level(int level, struct pfrt_log_device *pfrt_log_dev)
+{
+ acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev);
+ union acpi_object *out_obj, *obj, in_obj, in_buf;
+ enum pfru_dsm_status status, ext_status;
+ int ret = 0;
+
+ memset(&in_obj, 0, sizeof(in_obj));
+ memset(&in_buf, 0, sizeof(in_buf));
+ in_obj.type = ACPI_TYPE_PACKAGE;
+ in_obj.package.count = 1;
+ in_obj.package.elements = &in_buf;
+ in_buf.type = ACPI_TYPE_INTEGER;
+ in_buf.integer.value = level;
+
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid,
+ pfrt_log_dev->info.log_revid, PFRT_FUNC_SET_LEV,
+ &in_obj, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return -EINVAL;
+
+ obj = &out_obj->package.elements[0];
+ status = obj->integer.value;
+ if (status != DSM_SUCCEED) {
+ obj = &out_obj->package.elements[1];
+ ext_status = obj->integer.value;
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status);
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status);
+ ret = -EBUSY;
+ }
+
+ kfree(out_obj);
+
+ return ret;
+}
+
+static int get_pfrt_log_level(struct pfrt_log_device *pfrt_log_dev)
+{
+ acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev);
+ union acpi_object *out_obj, *obj;
+ enum pfru_dsm_status status, ext_status;
+ int ret = -EBUSY;
+
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid,
+ pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_LEV,
+ NULL, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return -EINVAL;
+
+ obj = &out_obj->package.elements[0];
+ if (obj->type != ACPI_TYPE_INTEGER)
+ goto free_acpi_buffer;
+
+ status = obj->integer.value;
+ if (status != DSM_SUCCEED) {
+ obj = &out_obj->package.elements[1];
+ ext_status = obj->integer.value;
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status);
+ dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status);
+ goto free_acpi_buffer;
+ }
+
+ obj = &out_obj->package.elements[2];
+ if (obj->type != ACPI_TYPE_INTEGER)
+ goto free_acpi_buffer;
+
+ ret = obj->integer.value;
+
+free_acpi_buffer:
+ kfree(out_obj);
+
+ return ret;
+}
+
+static int valid_log_level(u32 level)
+{
+ return level == PFRT_LOG_ERR || level == PFRT_LOG_WARN ||
+ level == PFRT_LOG_INFO || level == PFRT_LOG_VERB;
+}
+
+static int valid_log_type(u32 type)
+{
+ return type == PFRT_LOG_EXEC_IDX || type == PFRT_LOG_HISTORY_IDX;
+}
+
+static inline int valid_log_revid(u32 id)
+{
+ return id == PFRT_REVID_1 || id == PFRT_REVID_2;
+}
+
+static long pfrt_log_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pfrt_log_device *pfrt_log_dev = to_pfrt_log_dev(file);
+ struct pfrt_log_data_info data_info;
+ struct pfrt_log_info info;
+ void __user *p;
+ int ret = 0;
+
+ p = (void __user *)arg;
+
+ switch (cmd) {
+ case PFRT_LOG_IOC_SET_INFO:
+ if (copy_from_user(&info, p, sizeof(info)))
+ return -EFAULT;
+
+ if (valid_log_revid(info.log_revid))
+ pfrt_log_dev->info.log_revid = info.log_revid;
+
+ if (valid_log_level(info.log_level)) {
+ ret = set_pfrt_log_level(info.log_level, pfrt_log_dev);
+ if (ret < 0)
+ return ret;
+
+ pfrt_log_dev->info.log_level = info.log_level;
+ }
+
+ if (valid_log_type(info.log_type))
+ pfrt_log_dev->info.log_type = info.log_type;
+
+ return 0;
+
+ case PFRT_LOG_IOC_GET_INFO:
+ info.log_level = get_pfrt_log_level(pfrt_log_dev);
+ if (ret < 0)
+ return ret;
+
+ info.log_type = pfrt_log_dev->info.log_type;
+ info.log_revid = pfrt_log_dev->info.log_revid;
+ if (copy_to_user(p, &info, sizeof(info)))
+ return -EFAULT;
+
+ return 0;
+
+ case PFRT_LOG_IOC_GET_DATA_INFO:
+ ret = get_pfrt_log_data_info(&data_info, pfrt_log_dev);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(p, &data_info, sizeof(struct pfrt_log_data_info)))
+ return -EFAULT;
+
+ return 0;
+
+ default:
+ return -ENOTTY;
+ }
+}
+
+static int
+pfrt_log_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct pfrt_log_device *pfrt_log_dev;
+ struct pfrt_log_data_info info;
+ unsigned long psize, vsize;
+ phys_addr_t base_addr;
+ int ret;
+
+ if (vma->vm_flags & VM_WRITE)
+ return -EROFS;
+
+ /* changing from read to write with mprotect is not allowed */
+ vma->vm_flags &= ~VM_MAYWRITE;
+
+ pfrt_log_dev = to_pfrt_log_dev(file);
+
+ ret = get_pfrt_log_data_info(&info, pfrt_log_dev);
+ if (ret)
+ return ret;
+
+ base_addr = (phys_addr_t)((info.chunk2_addr_hi << 32) | info.chunk2_addr_lo);
+ /* pfrt update has not been launched yet */
+ if (!base_addr)
+ return -ENODEV;
+
+ psize = info.max_data_size;
+ /* base address and total buffer size must be page aligned */
+ if (!PAGE_ALIGNED(base_addr) || !PAGE_ALIGNED(psize))
+ return -ENODEV;
+
+ vsize = vma->vm_end - vma->vm_start;
+ if (vsize > psize)
+ return -EINVAL;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ if (io_remap_pfn_range(vma, vma->vm_start, PFN_DOWN(base_addr),
+ vsize, vma->vm_page_prot))
+ return -EAGAIN;
+
+ return 0;
+}
+
+static const struct file_operations acpi_pfrt_log_fops = {
+ .owner = THIS_MODULE,
+ .mmap = pfrt_log_mmap,
+ .unlocked_ioctl = pfrt_log_ioctl,
+ .llseek = noop_llseek,
+};
+
+static int acpi_pfrt_log_remove(struct platform_device *pdev)
+{
+ struct pfrt_log_device *pfrt_log_dev = platform_get_drvdata(pdev);
+
+ misc_deregister(&pfrt_log_dev->miscdev);
+
+ return 0;
+}
+
+static void pfrt_log_put_idx(void *data)
+{
+ struct pfrt_log_device *pfrt_log_dev = data;
+
+ ida_free(&pfrt_log_ida, pfrt_log_dev->index);
+}
+
+static int acpi_pfrt_log_probe(struct platform_device *pdev)
+{
+ acpi_handle handle = ACPI_HANDLE(&pdev->dev);
+ struct pfrt_log_device *pfrt_log_dev;
+ int ret;
+
+ if (!acpi_has_method(handle, "_DSM")) {
+ dev_dbg(&pdev->dev, "Missing _DSM\n");
+ return -ENODEV;
+ }
+
+ pfrt_log_dev = devm_kzalloc(&pdev->dev, sizeof(*pfrt_log_dev), GFP_KERNEL);
+ if (!pfrt_log_dev)
+ return -ENOMEM;
+
+ ret = ida_alloc(&pfrt_log_ida, GFP_KERNEL);
+ if (ret < 0)
+ return ret;
+
+ pfrt_log_dev->index = ret;
+ ret = devm_add_action_or_reset(&pdev->dev, pfrt_log_put_idx, pfrt_log_dev);
+ if (ret)
+ return ret;
+
+ pfrt_log_dev->info.log_revid = PFRT_DEFAULT_REV_ID;
+ pfrt_log_dev->parent_dev = &pdev->dev;
+
+ pfrt_log_dev->miscdev.minor = MISC_DYNAMIC_MINOR;
+ pfrt_log_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "pfrt%d",
+ pfrt_log_dev->index);
+ if (!pfrt_log_dev->miscdev.name)
+ return -ENOMEM;
+
+ pfrt_log_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "acpi_pfr_telemetry%d",
+ pfrt_log_dev->index);
+ if (!pfrt_log_dev->miscdev.nodename)
+ return -ENOMEM;
+
+ pfrt_log_dev->miscdev.fops = &acpi_pfrt_log_fops;
+ pfrt_log_dev->miscdev.parent = &pdev->dev;
+
+ ret = misc_register(&pfrt_log_dev->miscdev);
+ if (ret)
+ return ret;
+
+ platform_set_drvdata(pdev, pfrt_log_dev);
+
+ return 0;
+}
+
+static const struct acpi_device_id acpi_pfrt_log_ids[] = {
+ {"INTC1081"},
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, acpi_pfrt_log_ids);
+
+static struct platform_driver acpi_pfrt_log_driver = {
+ .driver = {
+ .name = "pfr_telemetry",
+ .acpi_match_table = acpi_pfrt_log_ids,
+ },
+ .probe = acpi_pfrt_log_probe,
+ .remove = acpi_pfrt_log_remove,
+};
+module_platform_driver(acpi_pfrt_log_driver);
+
+MODULE_DESCRIPTION("Platform Firmware Runtime Update Telemetry driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c
new file mode 100644
index 0000000..6bb0b77
--- /dev/null
+++ b/drivers/acpi/pfr_update.c
@@ -0,0 +1,575 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACPI Platform Firmware Runtime Update Device driver
+ *
+ * Copyright (C) 2021 Intel Corporation
+ * Author: Chen Yu <yu.c.chen@intel.com>
+ *
+ * pfr_update driver is used for Platform Firmware Runtime
+ * Update, which includes the code injection and driver update.
+ */
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/efi.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/idr.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/uio.h>
+#include <linux/uuid.h>
+
+#include <uapi/linux/pfrut.h>
+
+#define PFRU_FUNC_STANDARD_QUERY 0
+#define PFRU_FUNC_QUERY_UPDATE_CAP 1
+#define PFRU_FUNC_QUERY_BUF 2
+#define PFRU_FUNC_START 3
+
+#define PFRU_CODE_INJECT_TYPE 1
+#define PFRU_DRIVER_UPDATE_TYPE 2
+
+#define PFRU_REVID_1 1
+#define PFRU_REVID_2 2
+#define PFRU_DEFAULT_REV_ID PFRU_REVID_1
+
+enum cap_index {
+ CAP_STATUS_IDX = 0,
+ CAP_UPDATE_IDX = 1,
+ CAP_CODE_TYPE_IDX = 2,
+ CAP_FW_VER_IDX = 3,
+ CAP_CODE_RT_VER_IDX = 4,
+ CAP_DRV_TYPE_IDX = 5,
+ CAP_DRV_RT_VER_IDX = 6,
+ CAP_DRV_SVN_IDX = 7,
+ CAP_PLAT_ID_IDX = 8,
+ CAP_OEM_ID_IDX = 9,
+ CAP_OEM_INFO_IDX = 10,
+ CAP_NR_IDX
+};
+
+enum buf_index {
+ BUF_STATUS_IDX = 0,
+ BUF_EXT_STATUS_IDX = 1,
+ BUF_ADDR_LOW_IDX = 2,
+ BUF_ADDR_HI_IDX = 3,
+ BUF_SIZE_IDX = 4,
+ BUF_NR_IDX
+};
+
+enum update_index {
+ UPDATE_STATUS_IDX = 0,
+ UPDATE_EXT_STATUS_IDX = 1,
+ UPDATE_AUTH_TIME_LOW_IDX = 2,
+ UPDATE_AUTH_TIME_HI_IDX = 3,
+ UPDATE_EXEC_TIME_LOW_IDX = 4,
+ UPDATE_EXEC_TIME_HI_IDX = 5,
+ UPDATE_NR_IDX
+};
+
+enum pfru_start_action {
+ START_STAGE = 0,
+ START_ACTIVATE = 1,
+ START_STAGE_ACTIVATE = 2,
+};
+
+struct pfru_device {
+ u32 rev_id, index;
+ struct device *parent_dev;
+ struct miscdevice miscdev;
+};
+
+static DEFINE_IDA(pfru_ida);
+
+/*
+ * Manual reference:
+ * https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf
+ *
+ * pfru_guid is the parameter for _DSM method
+ */
+static const guid_t pfru_guid =
+ GUID_INIT(0xECF9533B, 0x4A3C, 0x4E89, 0x93, 0x9E, 0xC7, 0x71,
+ 0x12, 0x60, 0x1C, 0x6D);
+
+/* pfru_code_inj_guid is the UUID to identify code injection EFI capsule file */
+static const guid_t pfru_code_inj_guid =
+ GUID_INIT(0xB2F84B79, 0x7B6E, 0x4E45, 0x88, 0x5F, 0x3F, 0xB9,
+ 0xBB, 0x18, 0x54, 0x02);
+
+/* pfru_drv_update_guid is the UUID to identify driver update EFI capsule file */
+static const guid_t pfru_drv_update_guid =
+ GUID_INIT(0x4569DD8C, 0x75F1, 0x429A, 0xA3, 0xD6, 0x24, 0xDE,
+ 0x80, 0x97, 0xA0, 0xDF);
+
+static inline int pfru_valid_revid(u32 id)
+{
+ return id == PFRU_REVID_1 || id == PFRU_REVID_2;
+}
+
+static inline struct pfru_device *to_pfru_dev(struct file *file)
+{
+ return container_of(file->private_data, struct pfru_device, miscdev);
+}
+
+static int query_capability(struct pfru_update_cap_info *cap_hdr,
+ struct pfru_device *pfru_dev)
+{
+ acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev);
+ union acpi_object *out_obj;
+ int ret = -EINVAL;
+
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid,
+ pfru_dev->rev_id,
+ PFRU_FUNC_QUERY_UPDATE_CAP,
+ NULL, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return ret;
+
+ if (out_obj->package.count < CAP_NR_IDX ||
+ out_obj->package.elements[CAP_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_UPDATE_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_CODE_TYPE_IDX].type != ACPI_TYPE_BUFFER ||
+ out_obj->package.elements[CAP_FW_VER_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_CODE_RT_VER_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_DRV_TYPE_IDX].type != ACPI_TYPE_BUFFER ||
+ out_obj->package.elements[CAP_DRV_RT_VER_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_DRV_SVN_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[CAP_PLAT_ID_IDX].type != ACPI_TYPE_BUFFER ||
+ out_obj->package.elements[CAP_OEM_ID_IDX].type != ACPI_TYPE_BUFFER ||
+ out_obj->package.elements[CAP_OEM_INFO_IDX].type != ACPI_TYPE_BUFFER)
+ goto free_acpi_buffer;
+
+ cap_hdr->status = out_obj->package.elements[CAP_STATUS_IDX].integer.value;
+ if (cap_hdr->status != DSM_SUCCEED) {
+ ret = -EBUSY;
+ dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", cap_hdr->status);
+ goto free_acpi_buffer;
+ }
+
+ cap_hdr->update_cap = out_obj->package.elements[CAP_UPDATE_IDX].integer.value;
+ memcpy(&cap_hdr->code_type,
+ out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.pointer,
+ out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.length);
+ cap_hdr->fw_version =
+ out_obj->package.elements[CAP_FW_VER_IDX].integer.value;
+ cap_hdr->code_rt_version =
+ out_obj->package.elements[CAP_CODE_RT_VER_IDX].integer.value;
+ memcpy(&cap_hdr->drv_type,
+ out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.pointer,
+ out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.length);
+ cap_hdr->drv_rt_version =
+ out_obj->package.elements[CAP_DRV_RT_VER_IDX].integer.value;
+ cap_hdr->drv_svn =
+ out_obj->package.elements[CAP_DRV_SVN_IDX].integer.value;
+ memcpy(&cap_hdr->platform_id,
+ out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.pointer,
+ out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.length);
+ memcpy(&cap_hdr->oem_id,
+ out_obj->package.elements[CAP_OEM_ID_IDX].buffer.pointer,
+ out_obj->package.elements[CAP_OEM_ID_IDX].buffer.length);
+ cap_hdr->oem_info_len =
+ out_obj->package.elements[CAP_OEM_INFO_IDX].buffer.length;
+
+ ret = 0;
+
+free_acpi_buffer:
+ kfree(out_obj);
+
+ return ret;
+}
+
+static int query_buffer(struct pfru_com_buf_info *info,
+ struct pfru_device *pfru_dev)
+{
+ acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev);
+ union acpi_object *out_obj;
+ int ret = -EINVAL;
+
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid,
+ pfru_dev->rev_id, PFRU_FUNC_QUERY_BUF,
+ NULL, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return ret;
+
+ if (out_obj->package.count < BUF_NR_IDX ||
+ out_obj->package.elements[BUF_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[BUF_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[BUF_ADDR_LOW_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[BUF_ADDR_HI_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[BUF_SIZE_IDX].type != ACPI_TYPE_INTEGER)
+ goto free_acpi_buffer;
+
+ info->status = out_obj->package.elements[BUF_STATUS_IDX].integer.value;
+ info->ext_status =
+ out_obj->package.elements[BUF_EXT_STATUS_IDX].integer.value;
+ if (info->status != DSM_SUCCEED) {
+ ret = -EBUSY;
+ dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", info->status);
+ dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", info->ext_status);
+
+ goto free_acpi_buffer;
+ }
+
+ info->addr_lo =
+ out_obj->package.elements[BUF_ADDR_LOW_IDX].integer.value;
+ info->addr_hi =
+ out_obj->package.elements[BUF_ADDR_HI_IDX].integer.value;
+ info->buf_size = out_obj->package.elements[BUF_SIZE_IDX].integer.value;
+
+ ret = 0;
+
+free_acpi_buffer:
+ kfree(out_obj);
+
+ return ret;
+}
+
+static int get_image_type(const struct efi_manage_capsule_image_header *img_hdr,
+ struct pfru_device *pfru_dev)
+{
+ const efi_guid_t *image_type_id = &img_hdr->image_type_id;
+
+ /* check whether this is a code injection or driver update */
+ if (guid_equal(image_type_id, &pfru_code_inj_guid))
+ return PFRU_CODE_INJECT_TYPE;
+
+ if (guid_equal(image_type_id, &pfru_drv_update_guid))
+ return PFRU_DRIVER_UPDATE_TYPE;
+
+ return -EINVAL;
+}
+
+static int adjust_efi_size(const struct efi_manage_capsule_image_header *img_hdr,
+ int size)
+{
+ /*
+ * The (u64 hw_ins) was introduced in UEFI spec version 2,
+ * and (u64 capsule_support) was introduced in version 3.
+ * The size needs to be adjusted accordingly. That is to
+ * say, version 1 should subtract the size of hw_ins+capsule_support,
+ * and version 2 should sbstract the size of capsule_support.
+ */
+ size += sizeof(struct efi_manage_capsule_image_header);
+ switch (img_hdr->ver) {
+ case 1:
+ return size - 2 * sizeof(u64);
+
+ case 2:
+ return size - sizeof(u64);
+
+ default:
+ /* only support version 1 and 2 */
+ return -EINVAL;
+ }
+}
+
+static bool applicable_image(const void *data, struct pfru_update_cap_info *cap,
+ struct pfru_device *pfru_dev)
+{
+ struct pfru_payload_hdr *payload_hdr;
+ const efi_capsule_header_t *cap_hdr = data;
+ const struct efi_manage_capsule_header *m_hdr;
+ const struct efi_manage_capsule_image_header *m_img_hdr;
+ const struct efi_image_auth *auth;
+ int type, size;
+
+ /*
+ * If the code in the capsule is older than the current
+ * firmware code, the update will be rejected by the firmware,
+ * so check the version of it upfront without engaging the
+ * Management Mode update mechanism which may be costly.
+ */
+ size = cap_hdr->headersize;
+ m_hdr = data + size;
+ /*
+ * Current data structure size plus variable array indicated
+ * by number of (emb_drv_cnt + payload_cnt)
+ */
+ size += offsetof(struct efi_manage_capsule_header, offset_list) +
+ (m_hdr->emb_drv_cnt + m_hdr->payload_cnt) * sizeof(u64);
+ m_img_hdr = data + size;
+
+ type = get_image_type(m_img_hdr, pfru_dev);
+ if (type < 0)
+ return false;
+
+ size = adjust_efi_size(m_img_hdr, size);
+ if (size < 0)
+ return false;
+
+ auth = data + size;
+ size += sizeof(u64) + auth->auth_info.hdr.len;
+ payload_hdr = (struct pfru_payload_hdr *)(data + size);
+
+ /* finally compare the version */
+ if (type == PFRU_CODE_INJECT_TYPE)
+ return payload_hdr->rt_ver >= cap->code_rt_version;
+
+ return payload_hdr->rt_ver >= cap->drv_rt_version;
+}
+
+static void print_update_debug_info(struct pfru_updated_result *result,
+ struct pfru_device *pfru_dev)
+{
+ dev_dbg(pfru_dev->parent_dev, "Update result:\n");
+ dev_dbg(pfru_dev->parent_dev, "Authentication Time Low:%lld\n",
+ result->low_auth_time);
+ dev_dbg(pfru_dev->parent_dev, "Authentication Time High:%lld\n",
+ result->high_auth_time);
+ dev_dbg(pfru_dev->parent_dev, "Execution Time Low:%lld\n",
+ result->low_exec_time);
+ dev_dbg(pfru_dev->parent_dev, "Execution Time High:%lld\n",
+ result->high_exec_time);
+}
+
+static int start_update(int action, struct pfru_device *pfru_dev)
+{
+ union acpi_object *out_obj, in_obj, in_buf;
+ struct pfru_updated_result update_result;
+ acpi_handle handle;
+ int ret = -EINVAL;
+
+ memset(&in_obj, 0, sizeof(in_obj));
+ memset(&in_buf, 0, sizeof(in_buf));
+ in_obj.type = ACPI_TYPE_PACKAGE;
+ in_obj.package.count = 1;
+ in_obj.package.elements = &in_buf;
+ in_buf.type = ACPI_TYPE_INTEGER;
+ in_buf.integer.value = action;
+
+ handle = ACPI_HANDLE(pfru_dev->parent_dev);
+ out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid,
+ pfru_dev->rev_id, PFRU_FUNC_START,
+ &in_obj, ACPI_TYPE_PACKAGE);
+ if (!out_obj)
+ return ret;
+
+ if (out_obj->package.count < UPDATE_NR_IDX ||
+ out_obj->package.elements[UPDATE_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[UPDATE_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER ||
+ out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].type != ACPI_TYPE_INTEGER)
+ goto free_acpi_buffer;
+
+ update_result.status =
+ out_obj->package.elements[UPDATE_STATUS_IDX].integer.value;
+ update_result.ext_status =
+ out_obj->package.elements[UPDATE_EXT_STATUS_IDX].integer.value;
+
+ if (update_result.status != DSM_SUCCEED) {
+ ret = -EBUSY;
+ dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", update_result.status);
+ dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n",
+ update_result.ext_status);
+
+ goto free_acpi_buffer;
+ }
+
+ update_result.low_auth_time =
+ out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].integer.value;
+ update_result.high_auth_time =
+ out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].integer.value;
+ update_result.low_exec_time =
+ out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].integer.value;
+ update_result.high_exec_time =
+ out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].integer.value;
+
+ print_update_debug_info(&update_result, pfru_dev);
+ ret = 0;
+
+free_acpi_buffer:
+ kfree(out_obj);
+
+ return ret;
+}
+
+static long pfru_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pfru_update_cap_info cap_hdr;
+ struct pfru_device *pfru_dev = to_pfru_dev(file);
+ void __user *p = (void __user *)arg;
+ u32 rev;
+ int ret;
+
+ switch (cmd) {
+ case PFRU_IOC_QUERY_CAP:
+ ret = query_capability(&cap_hdr, pfru_dev);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(p, &cap_hdr, sizeof(cap_hdr)))
+ return -EFAULT;
+
+ return 0;
+
+ case PFRU_IOC_SET_REV:
+ if (copy_from_user(&rev, p, sizeof(rev)))
+ return -EFAULT;
+
+ if (!pfru_valid_revid(rev))
+ return -EINVAL;
+
+ pfru_dev->rev_id = rev;
+
+ return 0;
+
+ case PFRU_IOC_STAGE:
+ return start_update(START_STAGE, pfru_dev);
+
+ case PFRU_IOC_ACTIVATE:
+ return start_update(START_ACTIVATE, pfru_dev);
+
+ case PFRU_IOC_STAGE_ACTIVATE:
+ return start_update(START_STAGE_ACTIVATE, pfru_dev);
+
+ default:
+ return -ENOTTY;
+ }
+}
+
+static ssize_t pfru_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct pfru_device *pfru_dev = to_pfru_dev(file);
+ struct pfru_update_cap_info cap;
+ struct pfru_com_buf_info buf_info;
+ phys_addr_t phy_addr;
+ struct iov_iter iter;
+ struct iovec iov;
+ char *buf_ptr;
+ int ret;
+
+ ret = query_buffer(&buf_info, pfru_dev);
+ if (ret)
+ return ret;
+
+ if (len > buf_info.buf_size)
+ return -EINVAL;
+
+ iov.iov_base = (void __user *)buf;
+ iov.iov_len = len;
+ iov_iter_init(&iter, WRITE, &iov, 1, len);
+
+ /* map the communication buffer */
+ phy_addr = (phys_addr_t)((buf_info.addr_hi << 32) | buf_info.addr_lo);
+ buf_ptr = memremap(phy_addr, buf_info.buf_size, MEMREMAP_WB);
+ if (!buf_ptr)
+ return -ENOMEM;
+
+ if (!copy_from_iter_full(buf_ptr, len, &iter)) {
+ ret = -EINVAL;
+ goto unmap;
+ }
+
+ /* check if the capsule header has a valid version number */
+ ret = query_capability(&cap, pfru_dev);
+ if (ret)
+ goto unmap;
+
+ if (!applicable_image(buf_ptr, &cap, pfru_dev))
+ ret = -EINVAL;
+
+unmap:
+ memunmap(buf_ptr);
+
+ return ret ?: len;
+}
+
+static const struct file_operations acpi_pfru_fops = {
+ .owner = THIS_MODULE,
+ .write = pfru_write,
+ .unlocked_ioctl = pfru_ioctl,
+ .llseek = noop_llseek,
+};
+
+static int acpi_pfru_remove(struct platform_device *pdev)
+{
+ struct pfru_device *pfru_dev = platform_get_drvdata(pdev);
+
+ misc_deregister(&pfru_dev->miscdev);
+
+ return 0;
+}
+
+static void pfru_put_idx(void *data)
+{
+ struct pfru_device *pfru_dev = data;
+
+ ida_free(&pfru_ida, pfru_dev->index);
+}
+
+static int acpi_pfru_probe(struct platform_device *pdev)
+{
+ acpi_handle handle = ACPI_HANDLE(&pdev->dev);
+ struct pfru_device *pfru_dev;
+ int ret;
+
+ if (!acpi_has_method(handle, "_DSM")) {
+ dev_dbg(&pdev->dev, "Missing _DSM\n");
+ return -ENODEV;
+ }
+
+ pfru_dev = devm_kzalloc(&pdev->dev, sizeof(*pfru_dev), GFP_KERNEL);
+ if (!pfru_dev)
+ return -ENOMEM;
+
+ ret = ida_alloc(&pfru_ida, GFP_KERNEL);
+ if (ret < 0)
+ return ret;
+
+ pfru_dev->index = ret;
+ ret = devm_add_action_or_reset(&pdev->dev, pfru_put_idx, pfru_dev);
+ if (ret)
+ return ret;
+
+ pfru_dev->rev_id = PFRU_DEFAULT_REV_ID;
+ pfru_dev->parent_dev = &pdev->dev;
+
+ pfru_dev->miscdev.minor = MISC_DYNAMIC_MINOR;
+ pfru_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "pfru%d", pfru_dev->index);
+ if (!pfru_dev->miscdev.name)
+ return -ENOMEM;
+
+ pfru_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "acpi_pfr_update%d", pfru_dev->index);
+ if (!pfru_dev->miscdev.nodename)
+ return -ENOMEM;
+
+ pfru_dev->miscdev.fops = &acpi_pfru_fops;
+ pfru_dev->miscdev.parent = &pdev->dev;
+
+ ret = misc_register(&pfru_dev->miscdev);
+ if (ret)
+ return ret;
+
+ platform_set_drvdata(pdev, pfru_dev);
+
+ return 0;
+}
+
+static const struct acpi_device_id acpi_pfru_ids[] = {
+ {"INTC1080"},
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, acpi_pfru_ids);
+
+static struct platform_driver acpi_pfru_driver = {
+ .driver = {
+ .name = "pfr_update",
+ .acpi_match_table = acpi_pfru_ids,
+ },
+ .probe = acpi_pfru_probe,
+ .remove = acpi_pfru_remove,
+};
+module_platform_driver(acpi_pfru_driver);
+
+MODULE_DESCRIPTION("Platform Firmware Runtime Update device driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index c215bc8..1331756 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2502,42 +2502,33 @@ int acpi_bus_register_early_device(int type)
}
EXPORT_SYMBOL_GPL(acpi_bus_register_early_device);
-static int acpi_bus_scan_fixed(void)
+static void acpi_bus_scan_fixed(void)
{
- int result = 0;
-
- /*
- * Enumerate all fixed-feature devices.
- */
if (!(acpi_gbl_FADT.flags & ACPI_FADT_POWER_BUTTON)) {
- struct acpi_device *device = NULL;
+ struct acpi_device *adev = NULL;
- result = acpi_add_single_object(&device, NULL,
- ACPI_BUS_TYPE_POWER_BUTTON, false);
- if (result)
- return result;
-
- device->flags.match_driver = true;
- result = device_attach(&device->dev);
- if (result < 0)
- return result;
-
- device_init_wakeup(&device->dev, true);
+ acpi_add_single_object(&adev, NULL, ACPI_BUS_TYPE_POWER_BUTTON,
+ false);
+ if (adev) {
+ adev->flags.match_driver = true;
+ if (device_attach(&adev->dev) >= 0)
+ device_init_wakeup(&adev->dev, true);
+ else
+ dev_dbg(&adev->dev, "No driver\n");
+ }
}
if (!(acpi_gbl_FADT.flags & ACPI_FADT_SLEEP_BUTTON)) {
- struct acpi_device *device = NULL;
+ struct acpi_device *adev = NULL;
- result = acpi_add_single_object(&device, NULL,
- ACPI_BUS_TYPE_SLEEP_BUTTON, false);
- if (result)
- return result;
-
- device->flags.match_driver = true;
- result = device_attach(&device->dev);
+ acpi_add_single_object(&adev, NULL, ACPI_BUS_TYPE_SLEEP_BUTTON,
+ false);
+ if (adev) {
+ adev->flags.match_driver = true;
+ if (device_attach(&adev->dev) < 0)
+ dev_dbg(&adev->dev, "No driver\n");
+ }
}
-
- return result < 0 ? result : 0;
}
static void __init acpi_get_spcr_uart_addr(void)
@@ -2558,9 +2549,8 @@ static void __init acpi_get_spcr_uart_addr(void)
static bool acpi_scan_initialized;
-int __init acpi_scan_init(void)
+void __init acpi_scan_init(void)
{
- int result;
acpi_status status;
struct acpi_table_stao *stao_ptr;
@@ -2610,33 +2600,23 @@ int __init acpi_scan_init(void)
/*
* Enumerate devices in the ACPI namespace.
*/
- result = acpi_bus_scan(ACPI_ROOT_OBJECT);
- if (result)
- goto out;
+ if (acpi_bus_scan(ACPI_ROOT_OBJECT))
+ goto unlock;
acpi_root = acpi_fetch_acpi_dev(ACPI_ROOT_OBJECT);
if (!acpi_root)
- goto out;
+ goto unlock;
/* Fixed feature devices do not exist on HW-reduced platform */
- if (!acpi_gbl_reduced_hardware) {
- result = acpi_bus_scan_fixed();
- if (result) {
- acpi_detach_data(acpi_root->handle,
- acpi_scan_drop_device);
- acpi_device_del(acpi_root);
- acpi_bus_put_acpi_device(acpi_root);
- goto out;
- }
- }
+ if (!acpi_gbl_reduced_hardware)
+ acpi_bus_scan_fixed();
acpi_turn_off_unused_power_resources();
acpi_scan_initialized = true;
- out:
+unlock:
mutex_unlock(&acpi_scan_lock);
- return result;
}
static struct acpi_probe_entry *ape;
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index 25c2d0b..d589543 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -107,8 +107,13 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console)
pr_info("SPCR table version %d\n", table->header.revision);
if (table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
- switch (ACPI_ACCESS_BIT_WIDTH((
- table->serial_port.access_width))) {
+ u32 bit_width = table->serial_port.access_width;
+
+ if (bit_width > ACPI_ACCESS_BIT_MAX) {
+ pr_err("Unacceptable wide SPCR Access Width. Defaulting to byte size\n");
+ bit_width = ACPI_ACCESS_BIT_DEFAULT;
+ }
+ switch (ACPI_ACCESS_BIT_WIDTH((bit_width))) {
default:
pr_err("Unexpected SPCR Access Width. Defaulting to byte size\n");
fallthrough;
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index a7da8ea..cb54631 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -146,7 +146,7 @@
config AHCI_BRCM
tristate "Broadcom AHCI SATA support"
depends on ARCH_BRCMSTB || BMIPS_GENERIC || ARCH_BCM_NSP || \
- ARCH_BCM_63XX
+ ARCH_BCM_63XX || COMPILE_TEST
select SATA_HOST
help
This option enables support for the AHCI SATA3 controller found on
@@ -156,7 +156,7 @@
config AHCI_DA850
tristate "DaVinci DA850 AHCI SATA support"
- depends on ARCH_DAVINCI_DA850
+ depends on ARCH_DAVINCI_DA850 || COMPILE_TEST
select SATA_HOST
help
This option enables support for the DaVinci DA850 SoC's
@@ -166,7 +166,7 @@
config AHCI_DM816
tristate "DaVinci DM816 AHCI SATA support"
- depends on ARCH_OMAP2PLUS
+ depends on ARCH_OMAP2PLUS || COMPILE_TEST
select SATA_HOST
help
This option enables support for the DaVinci DM816 SoC's
@@ -206,7 +206,7 @@
config AHCI_MTK
tristate "MediaTek AHCI SATA support"
- depends on ARCH_MEDIATEK
+ depends on ARCH_MEDIATEK || COMPILE_TEST
select MFD_SYSCON
select SATA_HOST
help
@@ -217,7 +217,7 @@
config AHCI_MVEBU
tristate "Marvell EBU AHCI SATA support"
- depends on ARCH_MVEBU
+ depends on ARCH_MVEBU || COMPILE_TEST
select SATA_HOST
help
This option enables support for the Marvebu EBU SoC's
@@ -236,7 +236,7 @@
config AHCI_SUNXI
tristate "Allwinner sunxi AHCI SATA support"
- depends on ARCH_SUNXI
+ depends on ARCH_SUNXI || COMPILE_TEST
select SATA_HOST
help
This option enables support for the Allwinner sunxi SoC's
@@ -246,7 +246,7 @@
config AHCI_TEGRA
tristate "NVIDIA Tegra AHCI SATA support"
- depends on ARCH_TEGRA
+ depends on ARCH_TEGRA || COMPILE_TEST
select SATA_HOST
help
This option enables support for the NVIDIA Tegra SoC's
@@ -256,7 +256,7 @@
config AHCI_XGENE
tristate "APM X-Gene 6.0Gbps AHCI SATA host controller support"
- depends on PHY_XGENE
+ depends on PHY_XGENE || COMPILE_TEST
select SATA_HOST
help
This option enables support for APM X-Gene SoC SATA host controller.
@@ -273,7 +273,7 @@
config SATA_FSL
tristate "Freescale 3.0Gbps SATA support"
- depends on FSL_SOC
+ depends on FSL_SOC || COMPILE_TEST
select SATA_HOST
help
This option enables support for Freescale 3.0Gbps SATA controller.
@@ -294,7 +294,7 @@
config SATA_AHCI_SEATTLE
tristate "AMD Seattle 6.0Gbps AHCI SATA host controller support"
- depends on ARCH_SEATTLE
+ depends on ARCH_SEATTLE || COMPILE_TEST
select SATA_HOST
help
This option enables support for AMD Seattle SATA host controller.
@@ -432,18 +432,6 @@
This option enables support for old device trees without the
"dmas" property.
-config SATA_DWC_DEBUG
- bool "Debugging driver version"
- depends on SATA_DWC
- help
- This option enables debugging output in the driver.
-
-config SATA_DWC_VDEBUG
- bool "Verbose debug output"
- depends on SATA_DWC_DEBUG
- help
- This option enables the taskfile dumping and NCQ debugging.
-
config SATA_HIGHBANK
tristate "Calxeda Highbank SATA support"
depends on ARCH_HIGHBANK || COMPILE_TEST
@@ -611,7 +599,7 @@
config PATA_BK3710
tristate "Palmchip BK3710 PATA support"
- depends on ARCH_DAVINCI
+ depends on ARCH_DAVINCI || COMPILE_TEST
select PATA_TIMINGS
help
This option enables support for the integrated IDE controller on
@@ -649,7 +637,7 @@
config PATA_CS5535
tristate "CS5535 PATA support (Experimental)"
- depends on PCI && X86_32
+ depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST))
help
This option enables support for the NatSemi/AMD CS5535
companion chip used with the Geode processor family.
@@ -697,7 +685,7 @@
config PATA_FTIDE010
tristate "Faraday Technology FTIDE010 PATA support"
depends on OF
- depends on ARM
+ depends on ARM || COMPILE_TEST
depends on SATA_GEMINI
help
This option enables support for the Faraday FTIDE010
@@ -760,7 +748,7 @@
config PATA_IMX
tristate "PATA support for Freescale iMX"
- depends on ARCH_MXC
+ depends on ARCH_MXC || COMPILE_TEST
select PATA_TIMINGS
help
This option enables support for the PATA host available on Freescale
@@ -981,7 +969,7 @@
config PATA_PXA
tristate "PXA DMA-capable PATA support"
- depends on ARCH_PXA
+ depends on ARCH_PXA || COMPILE_TEST
help
This option enables support for harddrive attached to PXA CPU's bus.
@@ -1157,7 +1145,7 @@
config PATA_SAMSUNG_CF
tristate "Samsung SoC PATA support"
- depends on SAMSUNG_DEV_IDE
+ depends on SAMSUNG_DEV_IDE || COMPILE_TEST
select PATA_TIMINGS
help
This option enables basic support for Samsung's S3C/S5P board
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 2a04e8a..536d4cb 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -185,8 +185,6 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
struct acard_sg *acard_sg = cmd_tbl + AHCI_CMD_TBL_HDR_SZ;
unsigned int si, last_si = 0;
- VPRINTK("ENTER\n");
-
/*
* Next, the S/G list.
*/
@@ -362,8 +360,6 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id
struct ata_host *host;
int n_ports, i, rc;
- VPRINTK("ENTER\n");
-
WARN_ON((int)ATA_MAX_QUEUE > AHCI_MAX_CMDS);
ata_print_version_once(&pdev->dev, DRV_VERSION);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 1e1167e..ab5811e 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -51,6 +51,7 @@ enum board_ids {
board_ahci,
board_ahci_ign_iferr,
board_ahci_mobile,
+ board_ahci_no_debounce_delay,
board_ahci_nomsi,
board_ahci_noncq,
board_ahci_nosntf,
@@ -141,6 +142,13 @@ static const struct ata_port_info ahci_port_info[] = {
.udma_mask = ATA_UDMA6,
.port_ops = &ahci_ops,
},
+ [board_ahci_no_debounce_delay] = {
+ .flags = AHCI_FLAG_COMMON,
+ .link_flags = ATA_LFLAG_NO_DEBOUNCE_DELAY,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_ops,
+ },
[board_ahci_nomsi] = {
AHCI_HFLAGS (AHCI_HFLAG_NO_MSI),
.flags = AHCI_FLAG_COMMON,
@@ -437,6 +445,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
board_ahci_al },
/* AMD */
{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
+ { PCI_VDEVICE(AMD, 0x7801), board_ahci_no_debounce_delay }, /* AMD Hudson-2 (AHCI mode) */
{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
{ PCI_VDEVICE(AMD, 0x7901), board_ahci_mobile }, /* AMD Green Sardine */
/* AMD is using RAID class only for ahci controllers */
@@ -684,7 +693,7 @@ static void ahci_pci_init_controller(struct ata_host *host)
/* clear port IRQ */
tmp = readl(port_mmio + PORT_IRQ_STAT);
- VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp);
+ dev_dbg(&pdev->dev, "PORT_IRQ_STAT 0x%x\n", tmp);
if (tmp)
writel(tmp, port_mmio + PORT_IRQ_STAT);
}
@@ -700,8 +709,6 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
bool online;
int rc;
- DPRINTK("ENTER\n");
-
hpriv->stop_engine(ap);
rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
@@ -709,8 +716,6 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
hpriv->start_engine(ap);
- DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
-
/* vt8251 doesn't clear BSY on signature FIS reception,
* request follow-up softreset.
*/
@@ -790,8 +795,6 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
bool online;
int rc, i;
- DPRINTK("ENTER\n");
-
hpriv->stop_engine(ap);
for (i = 0; i < 2; i++) {
@@ -829,7 +832,6 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
if (online)
*class = ahci_dev_classify(ap);
- DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
return rc;
}
@@ -1476,7 +1478,6 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance)
u32 irq_stat, irq_masked;
unsigned int handled = 1;
- VPRINTK("ENTER\n");
hpriv = host->private_data;
mmio = hpriv->mmio;
irq_stat = readl(mmio + HOST_IRQ_STAT);
@@ -1493,7 +1494,6 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance)
irq_stat = readl(mmio + HOST_IRQ_STAT);
spin_unlock(&host->lock);
} while (irq_stat);
- VPRINTK("EXIT\n");
return IRQ_RETVAL(handled);
}
@@ -1657,7 +1657,7 @@ static ssize_t remapped_nvme_show(struct device *dev,
struct ata_host *host = dev_get_drvdata(dev);
struct ahci_host_priv *hpriv = host->private_data;
- return sprintf(buf, "%u\n", hpriv->remapped_nvme);
+ return sysfs_emit(buf, "%u\n", hpriv->remapped_nvme);
}
static DEVICE_ATTR_RO(remapped_nvme);
@@ -1673,8 +1673,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
int n_ports, i, rc;
int ahci_pci_bar = AHCI_PCI_BAR_STANDARD;
- VPRINTK("ENTER\n");
-
WARN_ON((int)ATA_MAX_QUEUE > AHCI_MAX_CMDS);
ata_print_version_once(&pdev->dev, DRV_VERSION);
diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c
index 6e9c5ad..64dd8aa3 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -246,7 +246,7 @@ static void brcm_sata_init(struct brcm_ahci_priv *priv)
}
static unsigned int brcm_ahci_read_id(struct ata_device *dev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
struct ata_port *ap = dev->link->ap;
struct ata_host *host = ap->host;
@@ -333,7 +333,7 @@ static struct ata_port_operations ahci_brcm_platform_ops = {
static const struct ata_port_info ahci_brcm_port_info = {
.flags = AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM,
- .link_flags = ATA_LFLAG_NO_DB_DELAY,
+ .link_flags = ATA_LFLAG_NO_DEBOUNCE_DELAY,
.pio_mask = ATA_PIO4,
.udma_mask = ATA_UDMA6,
.port_ops = &ahci_brcm_platform_ops,
diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index e9c7c07..acf59f5 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -92,9 +92,8 @@ struct ceva_ahci_priv {
};
static unsigned int ceva_ahci_read_id(struct ata_device *dev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
- __le16 *__id = (__le16 *)id;
u32 err_mask;
err_mask = ata_do_dev_read_id(dev, tf, id);
@@ -104,7 +103,7 @@ static unsigned int ceva_ahci_read_id(struct ata_device *dev,
* Since CEVA controller does not support device sleep feature, we
* need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data.
*/
- __id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
+ id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
return 0;
}
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 5b46fc9..bf5b388 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -103,8 +103,6 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class,
int rc;
bool ls1021a_workaround = (qoriq_priv->type == AHCI_LS1021A);
- DPRINTK("ENTER\n");
-
hpriv->stop_engine(ap);
/*
@@ -146,8 +144,6 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class,
if (online)
*class = ahci_dev_classify(ap);
-
- DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
return rc;
}
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index dffc432..8e20637 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -193,7 +193,7 @@ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc)
struct xgene_ahci_context *ctx = hpriv->plat_data;
int rc = 0;
u32 port_fbs;
- void *port_mmio = ahci_port_base(ap);
+ void __iomem *port_mmio = ahci_port_base(ap);
/*
* Write the pmp value to PxFBS.DEV
@@ -237,7 +237,7 @@ static bool xgene_ahci_is_memram_inited(struct xgene_ahci_context *ctx)
* does not support DEVSLP.
*/
static unsigned int xgene_ahci_read_id(struct ata_device *dev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
u32 err_mask;
@@ -454,7 +454,7 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class,
int pmp = sata_srst_pmp(link);
struct ata_port *ap = link->ap;
u32 rc;
- void *port_mmio = ahci_port_base(ap);
+ void __iomem *port_mmio = ahci_port_base(ap);
u32 port_fbs;
/*
@@ -499,7 +499,7 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class,
struct ata_port *ap = link->ap;
struct ahci_host_priv *hpriv = ap->host->private_data;
struct xgene_ahci_context *ctx = hpriv->plat_data;
- void *port_mmio = ahci_port_base(ap);
+ void __iomem *port_mmio = ahci_port_base(ap);
u32 port_fbs;
u32 port_fbs_save;
u32 retry = 1;
@@ -588,8 +588,6 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance)
void __iomem *mmio;
u32 irq_stat, irq_masked;
- VPRINTK("ENTER\n");
-
hpriv = host->private_data;
mmio = hpriv->mmio;
@@ -612,8 +610,6 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance)
spin_unlock(&host->lock);
- VPRINTK("EXIT\n");
-
return IRQ_RETVAL(rc);
}
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 0b2fcf0..27b0d90 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -77,6 +77,7 @@
#include <scsi/scsi_host.h>
#include <linux/libata.h>
#include <linux/dmi.h>
+#include <trace/events/libata.h>
#define DRV_NAME "ata_piix"
#define DRV_VERSION "2.13"
@@ -816,10 +817,15 @@ static int piix_sidpr_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
static bool piix_irq_check(struct ata_port *ap)
{
+ unsigned char host_stat;
+
if (unlikely(!ap->ioaddr.bmdma_addr))
return false;
- return ap->ops->bmdma_status(ap) & ATA_DMA_INTR;
+ host_stat = ap->ops->bmdma_status(ap);
+ trace_ata_bmdma_status(ap, host_stat);
+
+ return host_stat & ATA_DMA_INTR;
}
#ifdef CONFIG_PM_SLEEP
@@ -1345,7 +1351,6 @@ static void piix_init_pcs(struct ata_host *host,
new_pcs = pcs | map_db->port_enable;
if (new_pcs != pcs) {
- DPRINTK("updating PCS from 0x%x to 0x%x\n", pcs, new_pcs);
pci_write_config_word(pdev, ICH5_PCS, new_pcs);
msleep(150);
}
@@ -1769,14 +1774,12 @@ static int __init piix_init(void)
{
int rc;
- DPRINTK("pci_register_driver\n");
rc = pci_register_driver(&piix_pci_driver);
if (rc)
return rc;
in_module_init = 0;
- DPRINTK("done\n");
return 0;
}
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index f76b841..0ed484e 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1234,12 +1234,12 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap,
/* clear SError */
tmp = readl(port_mmio + PORT_SCR_ERR);
- VPRINTK("PORT_SCR_ERR 0x%x\n", tmp);
+ dev_dbg(dev, "PORT_SCR_ERR 0x%x\n", tmp);
writel(tmp, port_mmio + PORT_SCR_ERR);
/* clear port IRQ */
tmp = readl(port_mmio + PORT_IRQ_STAT);
- VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp);
+ dev_dbg(dev, "PORT_IRQ_STAT 0x%x\n", tmp);
if (tmp)
writel(tmp, port_mmio + PORT_IRQ_STAT);
@@ -1270,10 +1270,10 @@ void ahci_init_controller(struct ata_host *host)
}
tmp = readl(mmio + HOST_CTL);
- VPRINTK("HOST_CTL 0x%x\n", tmp);
+ dev_dbg(host->dev, "HOST_CTL 0x%x\n", tmp);
writel(tmp | HOST_IRQ_EN, mmio + HOST_CTL);
tmp = readl(mmio + HOST_CTL);
- VPRINTK("HOST_CTL 0x%x\n", tmp);
+ dev_dbg(host->dev, "HOST_CTL 0x%x\n", tmp);
}
EXPORT_SYMBOL_GPL(ahci_init_controller);
@@ -1300,7 +1300,7 @@ unsigned int ahci_dev_classify(struct ata_port *ap)
tf.lbal = (tmp >> 8) & 0xff;
tf.nsect = (tmp) & 0xff;
- return ata_dev_classify(&tf);
+ return ata_port_classify(ap, &tf);
}
EXPORT_SYMBOL_GPL(ahci_dev_classify);
@@ -1415,8 +1415,6 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
bool fbs_disabled = false;
int rc;
- DPRINTK("ENTER\n");
-
/* prepare for SRST (AHCI-1.1 10.4.1) */
rc = ahci_kick_engine(ap);
if (rc && rc != -EOPNOTSUPP)
@@ -1476,7 +1474,6 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
if (fbs_disabled)
ahci_enable_fbs(ap);
- DPRINTK("EXIT, class=%u\n", *class);
return 0;
fail:
@@ -1498,8 +1495,6 @@ static int ahci_softreset(struct ata_link *link, unsigned int *class,
{
int pmp = sata_srst_pmp(link);
- DPRINTK("ENTER\n");
-
return ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
}
EXPORT_SYMBOL_GPL(ahci_do_softreset);
@@ -1529,8 +1524,6 @@ static int ahci_pmp_retry_softreset(struct ata_link *link, unsigned int *class,
int rc;
u32 irq_sts;
- DPRINTK("ENTER\n");
-
rc = ahci_do_softreset(link, class, pmp, deadline,
ahci_bad_pmp_check_ready);
@@ -1564,8 +1557,6 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class,
struct ata_taskfile tf;
int rc;
- DPRINTK("ENTER\n");
-
hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
@@ -1581,7 +1572,6 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class,
if (*online)
*class = ahci_dev_classify(ap);
- DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
return rc;
}
EXPORT_SYMBOL_GPL(ahci_do_hardreset);
@@ -1620,8 +1610,6 @@ static unsigned int ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
struct ahci_sg *ahci_sg = cmd_tbl + AHCI_CMD_TBL_HDR_SZ;
unsigned int si;
- VPRINTK("ENTER\n");
-
/*
* Next, the S/G list.
*/
@@ -1695,7 +1683,6 @@ static void ahci_fbs_dec_intr(struct ata_port *ap)
u32 fbs = readl(port_mmio + PORT_FBS);
int retries = 3;
- DPRINTK("ENTER\n");
BUG_ON(!pp->fbs_enabled);
/* time to wait for DEC is not specified by AHCI spec,
@@ -1924,8 +1911,6 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance)
void __iomem *port_mmio = ahci_port_base(ap);
u32 status;
- VPRINTK("ENTER\n");
-
status = readl(port_mmio + PORT_IRQ_STAT);
writel(status, port_mmio + PORT_IRQ_STAT);
@@ -1933,8 +1918,6 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance)
ahci_handle_port_interrupt(ap, port_mmio, status);
spin_unlock(ap->lock);
- VPRINTK("EXIT\n");
-
return IRQ_HANDLED;
}
@@ -1951,9 +1934,7 @@ u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked)
ap = host->ports[i];
if (ap) {
ahci_port_intr(ap);
- VPRINTK("port %u\n", i);
} else {
- VPRINTK("port %u (no irq)\n", i);
if (ata_ratelimit())
dev_warn(host->dev,
"interrupt on disabled port %u\n", i);
@@ -1974,8 +1955,6 @@ static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance)
void __iomem *mmio;
u32 irq_stat, irq_masked;
- VPRINTK("ENTER\n");
-
hpriv = host->private_data;
mmio = hpriv->mmio;
@@ -2003,8 +1982,6 @@ static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance)
spin_unlock(&host->lock);
- VPRINTK("EXIT\n");
-
return IRQ_RETVAL(rc);
}
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 0910441..1829644 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -579,11 +579,8 @@ int ahci_platform_init_host(struct platform_device *pdev,
int i, irq, n_ports, rc;
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- if (irq != -EPROBE_DEFER)
- dev_err(dev, "no irq\n");
+ if (irq < 0)
return irq;
- }
if (!irq)
return -EINVAL;
@@ -642,13 +639,8 @@ int ahci_platform_init_host(struct platform_device *pdev,
if (hpriv->cap & HOST_CAP_64) {
rc = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
if (rc) {
- rc = dma_coerce_mask_and_coherent(dev,
- DMA_BIT_MASK(32));
- if (rc) {
- dev_err(dev, "Failed to enable 64-bit DMA.\n");
- return rc;
- }
- dev_warn(dev, "Enable 32-bit DMA instead of 64-bit.\n");
+ dev_err(dev, "Failed to enable 64-bit DMA.\n");
+ return rc;
}
}
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 7a7d664..8cfa8c9 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -402,7 +402,6 @@ EXPORT_SYMBOL_GPL(ata_acpi_stm);
*/
static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf)
{
- struct ata_port *ap = dev->link->ap;
acpi_status status;
struct acpi_buffer output;
union acpi_object *out_obj;
@@ -418,10 +417,6 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf)
output.length = ACPI_ALLOCATE_BUFFER;
output.pointer = NULL; /* ACPI-CA sets this; save/free it later */
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: ENTER: port#: %d\n",
- __func__, ap->port_no);
-
/* _GTF has no input parameters */
status = acpi_evaluate_object(ata_dev_acpi_handle(dev), "_GTF", NULL,
&output);
@@ -437,11 +432,9 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf)
}
if (!output.length || !output.pointer) {
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n",
- __func__,
- (unsigned long long)output.length,
- output.pointer);
+ ata_dev_dbg(dev, "Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n",
+ (unsigned long long)output.length,
+ output.pointer);
rc = -EINVAL;
goto out_free;
}
@@ -464,9 +457,8 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf)
rc = out_obj->buffer.length / REGS_PER_GTF;
if (gtf) {
*gtf = (void *)out_obj->buffer.pointer;
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: returning gtf=%p, gtf_count=%d\n",
- __func__, *gtf, rc);
+ ata_dev_dbg(dev, "returning gtf=%p, gtf_count=%d\n",
+ *gtf, rc);
}
return rc;
@@ -650,9 +642,7 @@ static int ata_acpi_run_tf(struct ata_device *dev,
struct ata_taskfile *pptf = NULL;
struct ata_taskfile tf, ptf, rtf;
unsigned int err_mask;
- const char *level;
const char *descr;
- char msg[60];
int rc;
if ((gtf->tf[0] == 0) && (gtf->tf[1] == 0) && (gtf->tf[2] == 0)
@@ -666,6 +656,8 @@ static int ata_acpi_run_tf(struct ata_device *dev,
pptf = &ptf;
}
+ descr = ata_get_cmd_name(tf.command);
+
if (!ata_acpi_filter_tf(dev, &tf, pptf)) {
rtf = tf;
err_mask = ata_exec_internal(dev, &rtf, NULL,
@@ -673,40 +665,42 @@ static int ata_acpi_run_tf(struct ata_device *dev,
switch (err_mask) {
case 0:
- level = KERN_DEBUG;
- snprintf(msg, sizeof(msg), "succeeded");
+ ata_dev_dbg(dev,
+ "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x"
+ "(%s) succeeded\n",
+ tf.command, tf.feature, tf.nsect, tf.lbal,
+ tf.lbam, tf.lbah, tf.device, descr);
rc = 1;
break;
case AC_ERR_DEV:
- level = KERN_INFO;
- snprintf(msg, sizeof(msg),
- "rejected by device (Stat=0x%02x Err=0x%02x)",
- rtf.command, rtf.feature);
+ ata_dev_info(dev,
+ "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x"
+ "(%s) rejected by device (Stat=0x%02x Err=0x%02x)",
+ tf.command, tf.feature, tf.nsect, tf.lbal,
+ tf.lbam, tf.lbah, tf.device, descr,
+ rtf.command, rtf.feature);
rc = 0;
break;
default:
- level = KERN_ERR;
- snprintf(msg, sizeof(msg),
- "failed (Emask=0x%x Stat=0x%02x Err=0x%02x)",
- err_mask, rtf.command, rtf.feature);
+ ata_dev_err(dev,
+ "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x"
+ "(%s) failed (Emask=0x%x Stat=0x%02x Err=0x%02x)",
+ tf.command, tf.feature, tf.nsect, tf.lbal,
+ tf.lbam, tf.lbah, tf.device, descr,
+ err_mask, rtf.command, rtf.feature);
rc = -EIO;
break;
}
} else {
- level = KERN_INFO;
- snprintf(msg, sizeof(msg), "filtered out");
+ ata_dev_info(dev,
+ "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x"
+ "(%s) filtered out\n",
+ tf.command, tf.feature, tf.nsect, tf.lbal,
+ tf.lbam, tf.lbah, tf.device, descr);
rc = 0;
}
- descr = ata_get_cmd_descript(tf.command);
-
- ata_dev_printk(dev, level,
- "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x (%s) %s\n",
- tf.command, tf.feature, tf.nsect, tf.lbal,
- tf.lbam, tf.lbah, tf.device,
- (descr ? descr : "unknown"), msg);
-
return rc;
}
@@ -776,9 +770,8 @@ static int ata_acpi_push_id(struct ata_device *dev)
struct acpi_object_list input;
union acpi_object in_params[1];
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n",
- __func__, dev->devno, ap->port_no);
+ ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n",
+ __func__, dev->devno, ap->port_no);
/* Give the drive Identify data to the drive via the _SDD method */
/* _SDD: set up input parameters */
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index aba0c67..67f8802 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -764,9 +764,6 @@ int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
head = track % dev->heads;
sect = (u32)block % dev->sectors + 1;
- DPRINTK("block %u track %u cyl %u head %u sect %u\n",
- (u32)block, track, cyl, head, sect);
-
/* Check whether the converted CHS can fit.
Cylinder: 0-65535
Head: 0-15
@@ -1010,32 +1007,21 @@ unsigned int ata_dev_classify(const struct ata_taskfile *tf)
* SEMB signature. This is worked around in
* ata_dev_read_id().
*/
- if ((tf->lbam == 0) && (tf->lbah == 0)) {
- DPRINTK("found ATA device by sig\n");
+ if (tf->lbam == 0 && tf->lbah == 0)
return ATA_DEV_ATA;
- }
- if ((tf->lbam == 0x14) && (tf->lbah == 0xeb)) {
- DPRINTK("found ATAPI device by sig\n");
+ if (tf->lbam == 0x14 && tf->lbah == 0xeb)
return ATA_DEV_ATAPI;
- }
- if ((tf->lbam == 0x69) && (tf->lbah == 0x96)) {
- DPRINTK("found PMP device by sig\n");
+ if (tf->lbam == 0x69 && tf->lbah == 0x96)
return ATA_DEV_PMP;
- }
- if ((tf->lbam == 0x3c) && (tf->lbah == 0xc3)) {
- DPRINTK("found SEMB device by sig (could be ATA device)\n");
+ if (tf->lbam == 0x3c && tf->lbah == 0xc3)
return ATA_DEV_SEMB;
- }
- if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) {
- DPRINTK("found ZAC device by sig\n");
+ if (tf->lbam == 0xcd && tf->lbah == 0xab)
return ATA_DEV_ZAC;
- }
- DPRINTK("unknown device\n");
return ATA_DEV_UNKNOWN;
}
EXPORT_SYMBOL_GPL(ata_dev_classify);
@@ -1355,6 +1341,7 @@ static int ata_hpa_resize(struct ata_device *dev)
/**
* ata_dump_id - IDENTIFY DEVICE info debugging output
+ * @dev: device from which the information is fetched
* @id: IDENTIFY DEVICE page to dump
*
* Dump selected 16-bit words from the given IDENTIFY DEVICE
@@ -1364,32 +1351,14 @@ static int ata_hpa_resize(struct ata_device *dev)
* caller.
*/
-static inline void ata_dump_id(const u16 *id)
+static inline void ata_dump_id(struct ata_device *dev, const u16 *id)
{
- DPRINTK("49==0x%04x "
- "53==0x%04x "
- "63==0x%04x "
- "64==0x%04x "
- "75==0x%04x \n",
- id[49],
- id[53],
- id[63],
- id[64],
- id[75]);
- DPRINTK("80==0x%04x "
- "81==0x%04x "
- "82==0x%04x "
- "83==0x%04x "
- "84==0x%04x \n",
- id[80],
- id[81],
- id[82],
- id[83],
- id[84]);
- DPRINTK("88==0x%04x "
- "93==0x%04x\n",
- id[88],
- id[93]);
+ ata_dev_dbg(dev,
+ "49==0x%04x 53==0x%04x 63==0x%04x 64==0x%04x 75==0x%04x\n"
+ "80==0x%04x 81==0x%04x 82==0x%04x 83==0x%04x 84==0x%04x\n"
+ "88==0x%04x 93==0x%04x\n",
+ id[49], id[53], id[63], id[64], id[75], id[80],
+ id[81], id[82], id[83], id[84], id[88], id[93]);
}
/**
@@ -1602,9 +1571,8 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
else
ata_qc_complete(qc);
- if (ata_msg_warn(ap))
- ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n",
- command);
+ ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n",
+ command);
}
spin_unlock_irqrestore(ap->lock, flags);
@@ -1754,7 +1722,7 @@ static u32 ata_pio_mask_no_iordy(const struct ata_device *adev)
* this function is wrapped or replaced by the driver
*/
unsigned int ata_do_dev_read_id(struct ata_device *dev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE,
id, sizeof(id[0]) * ATA_ID_WORDS, 0);
@@ -1794,9 +1762,6 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
int may_fallback = 1, tried_spinup = 0;
int rc;
- if (ata_msg_ctl(ap))
- ata_dev_dbg(dev, "%s: ENTER\n", __func__);
-
retry:
ata_tf_init(dev, &tf);
@@ -1830,9 +1795,9 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
tf.flags |= ATA_TFLAG_POLLING;
if (ap->ops->read_id)
- err_mask = ap->ops->read_id(dev, &tf, id);
+ err_mask = ap->ops->read_id(dev, &tf, (__le16 *)id);
else
- err_mask = ata_do_dev_read_id(dev, &tf, id);
+ err_mask = ata_do_dev_read_id(dev, &tf, (__le16 *)id);
if (err_mask) {
if (err_mask & AC_ERR_NODEV_HINT) {
@@ -1879,10 +1844,10 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
}
if (dev->horkage & ATA_HORKAGE_DUMP_ID) {
- ata_dev_dbg(dev, "dumping IDENTIFY data, "
+ ata_dev_info(dev, "dumping IDENTIFY data, "
"class=%d may_fallback=%d tried_spinup=%d\n",
class, may_fallback, tried_spinup);
- print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET,
+ print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET,
16, 2, id, ATA_ID_WORDS * sizeof(*id), true);
}
@@ -1966,9 +1931,8 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
return 0;
err_out:
- if (ata_msg_warn(ap))
- ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n",
- reason, err_mask);
+ ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n",
+ reason, err_mask);
return rc;
}
@@ -1996,7 +1960,7 @@ unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
unsigned int err_mask;
bool dma = false;
- DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page);
+ ata_dev_dbg(dev, "read log page - log 0x%x, page 0x%x\n", log, page);
/*
* Return error without actually issuing the command on controllers
@@ -2390,7 +2354,6 @@ static void ata_dev_config_trusted(struct ata_device *dev)
static int ata_dev_config_lba(struct ata_device *dev)
{
- struct ata_port *ap = dev->link->ap;
const u16 *id = dev->id;
const char *lba_desc;
char ncq_desc[24];
@@ -2412,7 +2375,7 @@ static int ata_dev_config_lba(struct ata_device *dev)
ret = ata_dev_config_ncq(dev, ncq_desc, sizeof(ncq_desc));
/* print device info to dmesg */
- if (ata_msg_drv(ap) && ata_dev_print_info(dev))
+ if (ata_dev_print_info(dev))
ata_dev_info(dev,
"%llu sectors, multi %u: %s %s\n",
(unsigned long long)dev->n_sectors,
@@ -2423,7 +2386,6 @@ static int ata_dev_config_lba(struct ata_device *dev)
static void ata_dev_config_chs(struct ata_device *dev)
{
- struct ata_port *ap = dev->link->ap;
const u16 *id = dev->id;
if (ata_id_current_chs_valid(id)) {
@@ -2439,7 +2401,7 @@ static void ata_dev_config_chs(struct ata_device *dev)
}
/* print device info to dmesg */
- if (ata_msg_drv(ap) && ata_dev_print_info(dev))
+ if (ata_dev_print_info(dev))
ata_dev_info(dev,
"%llu sectors, multi %u, CHS %u/%u/%u\n",
(unsigned long long)dev->n_sectors,
@@ -2566,14 +2528,11 @@ int ata_dev_configure(struct ata_device *dev)
char modelbuf[ATA_ID_PROD_LEN+1];
int rc;
- if (!ata_dev_enabled(dev) && ata_msg_info(ap)) {
- ata_dev_info(dev, "%s: ENTER/EXIT -- nodev\n", __func__);
+ if (!ata_dev_enabled(dev)) {
+ ata_dev_dbg(dev, "no device\n");
return 0;
}
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: ENTER\n", __func__);
-
/* set horkage */
dev->horkage |= ata_dev_blacklisted(dev);
ata_force_horkage(dev);
@@ -2621,13 +2580,12 @@ int ata_dev_configure(struct ata_device *dev)
return rc;
/* print device capabilities */
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev,
- "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x "
- "85:%04x 86:%04x 87:%04x 88:%04x\n",
- __func__,
- id[49], id[82], id[83], id[84],
- id[85], id[86], id[87], id[88]);
+ ata_dev_dbg(dev,
+ "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x "
+ "85:%04x 86:%04x 87:%04x 88:%04x\n",
+ __func__,
+ id[49], id[82], id[83], id[84],
+ id[85], id[86], id[87], id[88]);
/* initialize to-be-configured parameters */
dev->flags &= ~ATA_DFLAG_CFG_MASK;
@@ -2646,8 +2604,7 @@ int ata_dev_configure(struct ata_device *dev)
/* find max transfer mode; for printk only */
xfer_mask = ata_id_xfermask(id);
- if (ata_msg_probe(ap))
- ata_dump_id(id);
+ ata_dump_id(dev, id);
/* SCSI only uses 4-char revisions, dump full 8 chars from ATA */
ata_id_c_string(dev->id, fwrevbuf, ATA_ID_FW_REV,
@@ -2685,7 +2642,7 @@ int ata_dev_configure(struct ata_device *dev)
}
/* print device info to dmesg */
- if (ata_msg_drv(ap) && print_info)
+ if (print_info)
ata_dev_info(dev, "%s: %s, %s, max %s\n",
revbuf, modelbuf, fwrevbuf,
ata_mode_string(xfer_mask));
@@ -2705,7 +2662,7 @@ int ata_dev_configure(struct ata_device *dev)
ata_dev_config_cpr(dev);
dev->cdb_len = 32;
- if (ata_msg_drv(ap) && print_info)
+ if (print_info)
ata_dev_print_features(dev);
}
@@ -2718,8 +2675,7 @@ int ata_dev_configure(struct ata_device *dev)
rc = atapi_cdb_len(id);
if ((rc < 12) || (rc > ATAPI_CDB_LEN)) {
- if (ata_msg_warn(ap))
- ata_dev_warn(dev, "unsupported CDB len\n");
+ ata_dev_warn(dev, "unsupported CDB len %d\n", rc);
rc = -EINVAL;
goto err_out_nosup;
}
@@ -2763,7 +2719,7 @@ int ata_dev_configure(struct ata_device *dev)
}
/* print device info to dmesg */
- if (ata_msg_drv(ap) && print_info)
+ if (print_info)
ata_dev_info(dev,
"ATAPI: %s, %s, max %s%s%s%s\n",
modelbuf, fwrevbuf,
@@ -2780,7 +2736,7 @@ int ata_dev_configure(struct ata_device *dev)
/* Limit PATA drive on SATA cable bridge transfers to udma5,
200 sectors */
if (ata_dev_knobble(dev)) {
- if (ata_msg_drv(ap) && print_info)
+ if (print_info)
ata_dev_info(dev, "applying bridge limits\n");
dev->udma_mask &= ATA_UDMA5;
dev->max_sectors = ATA_MAX_SECTORS;
@@ -2829,8 +2785,6 @@ int ata_dev_configure(struct ata_device *dev)
return 0;
err_out_nosup:
- if (ata_msg_probe(ap))
- ata_dev_dbg(dev, "%s: EXIT, err\n", __func__);
return rc;
}
@@ -3373,8 +3327,8 @@ static int ata_dev_set_mode(struct ata_device *dev)
dev_err_whine = " (device error ignored)";
}
- DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n",
- dev->xfer_shift, (int)dev->xfer_mode);
+ ata_dev_dbg(dev, "xfer_shift=%u, xfer_mode=0x%x\n",
+ dev->xfer_shift, (int)dev->xfer_mode);
if (!(ehc->i.flags & ATA_EHI_QUIET) ||
ehc->i.flags & ATA_EHI_DID_HARDRESET)
@@ -3688,16 +3642,12 @@ void ata_std_postreset(struct ata_link *link, unsigned int *classes)
{
u32 serror;
- DPRINTK("ENTER\n");
-
/* reset complete, clear SError */
if (!sata_scr_read(link, SCR_ERROR, &serror))
sata_scr_write(link, SCR_ERROR, serror);
/* print link status */
sata_print_link_status(link);
-
- DPRINTK("EXIT\n");
}
EXPORT_SYMBOL_GPL(ata_std_postreset);
@@ -4324,7 +4274,7 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev)
unsigned int err_mask;
/* set up set-features taskfile */
- DPRINTK("set features - xfer mode\n");
+ ata_dev_dbg(dev, "set features - xfer mode\n");
/* Some controllers and ATAPI devices show flaky interrupt
* behavior after setting xfer mode. Use polling instead.
@@ -4346,7 +4296,6 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev)
/* On some disks, this command causes spin-up, so we need longer timeout */
err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000);
- DPRINTK("EXIT, err_mask=%x\n", err_mask);
return err_mask;
}
@@ -4372,7 +4321,7 @@ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature)
unsigned long timeout = 0;
/* set up set-features taskfile */
- DPRINTK("set features - SATA features\n");
+ ata_dev_dbg(dev, "set features - SATA features\n");
ata_tf_init(dev, &tf);
tf.command = ATA_CMD_SET_FEATURES;
@@ -4386,7 +4335,6 @@ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature)
ata_probe_timeout * 1000 : SETFEATURES_SPINUP_TIMEOUT;
err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, timeout);
- DPRINTK("EXIT, err_mask=%x\n", err_mask);
return err_mask;
}
EXPORT_SYMBOL_GPL(ata_dev_set_feature);
@@ -4414,7 +4362,7 @@ static unsigned int ata_dev_init_params(struct ata_device *dev,
return AC_ERR_INVALID;
/* set up init dev params taskfile */
- DPRINTK("init dev params \n");
+ ata_dev_dbg(dev, "init dev params \n");
ata_tf_init(dev, &tf);
tf.command = ATA_CMD_INIT_DEV_PARAMS;
@@ -4430,7 +4378,6 @@ static unsigned int ata_dev_init_params(struct ata_device *dev,
if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED))
err_mask = 0;
- DPRINTK("EXIT, err_mask=%x\n", err_mask);
return err_mask;
}
@@ -4542,8 +4489,6 @@ static void ata_sg_clean(struct ata_queued_cmd *qc)
WARN_ON_ONCE(sg == NULL);
- VPRINTK("unmapping %u sg elements\n", qc->n_elem);
-
if (qc->n_elem)
dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir);
@@ -4569,13 +4514,10 @@ static int ata_sg_setup(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
unsigned int n_elem;
- VPRINTK("ENTER, ata%u\n", ap->print_id);
-
n_elem = dma_map_sg(ap->dev, qc->sg, qc->n_elem, qc->dma_dir);
if (n_elem < 1)
return -1;
- VPRINTK("%d sg elements mapped\n", n_elem);
qc->orig_n_elem = qc->n_elem;
qc->n_elem = n_elem;
qc->flags |= ATA_QCFLAG_DMAMAP;
@@ -4930,6 +4872,7 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
return;
}
+ trace_ata_qc_prep(qc);
qc->err_mask |= ap->ops->qc_prep(qc);
if (unlikely(qc->err_mask))
goto err;
@@ -5375,8 +5318,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host)
{
struct ata_port *ap;
- DPRINTK("ENTER\n");
-
ap = kzalloc(sizeof(*ap), GFP_KERNEL);
if (!ap)
return NULL;
@@ -5388,15 +5329,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host)
ap->host = host;
ap->dev = host->dev;
-#if defined(ATA_VERBOSE_DEBUG)
- /* turn on all debugging levels */
- ap->msg_enable = 0x00FF;
-#elif defined(ATA_DEBUG)
- ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN | ATA_MSG_ERR;
-#else
- ap->msg_enable = ATA_MSG_DRV | ATA_MSG_ERR | ATA_MSG_WARN;
-#endif
-
mutex_init(&ap->scsi_scan_mutex);
INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug);
INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan);
@@ -5493,8 +5425,6 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports)
int i;
void *dr;
- DPRINTK("ENTER\n");
-
/* alloc a container for our list of ATA ports (buses) */
sz = sizeof(struct ata_host) + (max_ports + 1) * sizeof(void *);
host = kzalloc(sz, GFP_KERNEL);
@@ -5784,9 +5714,7 @@ int ata_port_probe(struct ata_port *ap)
__ata_port_probe(ap);
ata_port_wait_eh(ap);
} else {
- DPRINTK("ata%u: bus probe begin\n", ap->print_id);
rc = ata_bus_probe(ap);
- DPRINTK("ata%u: bus probe end\n", ap->print_id);
}
return rc;
}
@@ -6553,69 +6481,14 @@ const struct ata_port_info ata_dummy_port_info = {
};
EXPORT_SYMBOL_GPL(ata_dummy_port_info);
-/*
- * Utility print functions
- */
-void ata_port_printk(const struct ata_port *ap, const char *level,
- const char *fmt, ...)
-{
- struct va_format vaf;
- va_list args;
-
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
-
- printk("%sata%u: %pV", level, ap->print_id, &vaf);
-
- va_end(args);
-}
-EXPORT_SYMBOL(ata_port_printk);
-
-void ata_link_printk(const struct ata_link *link, const char *level,
- const char *fmt, ...)
-{
- struct va_format vaf;
- va_list args;
-
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
-
- if (sata_pmp_attached(link->ap) || link->ap->slave_link)
- printk("%sata%u.%02u: %pV",
- level, link->ap->print_id, link->pmp, &vaf);
- else
- printk("%sata%u: %pV",
- level, link->ap->print_id, &vaf);
-
- va_end(args);
-}
-EXPORT_SYMBOL(ata_link_printk);
-
-void ata_dev_printk(const struct ata_device *dev, const char *level,
- const char *fmt, ...)
-{
- struct va_format vaf;
- va_list args;
-
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
-
- printk("%sata%u.%02u: %pV",
- level, dev->link->ap->print_id, dev->link->pmp + dev->devno,
- &vaf);
-
- va_end(args);
-}
-EXPORT_SYMBOL(ata_dev_printk);
-
void ata_print_version(const struct device *dev, const char *version)
{
dev_printk(KERN_DEBUG, dev, "version %s\n", version);
}
EXPORT_SYMBOL(ata_print_version);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(ata_tf_load);
+EXPORT_TRACEPOINT_SYMBOL_GPL(ata_exec_command);
+EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_setup);
+EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_start);
+EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_status);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 1d4a6f1..7951fd9 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -533,8 +533,6 @@ void ata_scsi_error(struct Scsi_Host *host)
unsigned long flags;
LIST_HEAD(eh_work_q);
- DPRINTK("ENTER\n");
-
spin_lock_irqsave(host->host_lock, flags);
list_splice_init(&host->eh_cmd_q, &eh_work_q);
spin_unlock_irqrestore(host->host_lock, flags);
@@ -548,7 +546,6 @@ void ata_scsi_error(struct Scsi_Host *host)
/* finish or retry handled scmd's and clean up */
WARN_ON(!list_empty(&eh_work_q));
- DPRINTK("EXIT\n");
}
/**
@@ -940,7 +937,7 @@ void ata_std_sched_eh(struct ata_port *ap)
ata_eh_set_pending(ap, 1);
scsi_schedule_eh(ap->scsi_host);
- DPRINTK("port EH scheduled\n");
+ trace_ata_std_sched_eh(ap);
}
EXPORT_SYMBOL_GPL(ata_std_sched_eh);
@@ -1070,7 +1067,7 @@ static void __ata_port_freeze(struct ata_port *ap)
ap->pflags |= ATA_PFLAG_FROZEN;
- DPRINTK("ata%u port frozen\n", ap->print_id);
+ trace_ata_port_freeze(ap);
}
/**
@@ -1147,7 +1144,7 @@ void ata_eh_thaw_port(struct ata_port *ap)
spin_unlock_irqrestore(ap->lock, flags);
- DPRINTK("ata%u port thawed\n", ap->print_id);
+ trace_ata_port_thaw(ap);
}
static void ata_eh_scsidone(struct scsi_cmnd *scmd)
@@ -1217,8 +1214,7 @@ void ata_dev_disable(struct ata_device *dev)
if (!ata_dev_enabled(dev))
return;
- if (ata_msg_drv(dev->link->ap))
- ata_dev_warn(dev, "disabled\n");
+ ata_dev_warn(dev, "disable device\n");
ata_acpi_on_disable(dev);
ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 | ATA_DNXFER_QUIET);
dev->class++;
@@ -1287,6 +1283,8 @@ void ata_eh_about_to_do(struct ata_link *link, struct ata_device *dev,
struct ata_eh_context *ehc = &link->eh_context;
unsigned long flags;
+ trace_ata_eh_about_to_do(link, dev ? dev->devno : 0, action);
+
spin_lock_irqsave(ap->lock, flags);
ata_eh_clear_action(link, dev, ehi, action);
@@ -1317,6 +1315,8 @@ void ata_eh_done(struct ata_link *link, struct ata_device *dev,
{
struct ata_eh_context *ehc = &link->eh_context;
+ trace_ata_eh_done(link, dev ? dev->devno : 0, action);
+
ata_eh_clear_action(link, dev, &ehc->i, action);
}
@@ -1421,8 +1421,6 @@ static void ata_eh_request_sense(struct ata_queued_cmd *qc,
return;
}
- DPRINTK("ATA request sense\n");
-
ata_tf_init(dev, &tf);
tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
tf.flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
@@ -1463,8 +1461,6 @@ unsigned int atapi_eh_request_sense(struct ata_device *dev,
struct ata_port *ap = dev->link->ap;
struct ata_taskfile tf;
- DPRINTK("ATAPI request sense\n");
-
memset(sense_buf, 0, SCSI_SENSE_BUFFERSIZE);
/* initialize sense_buf with the error register,
@@ -1928,8 +1924,6 @@ static void ata_eh_link_autopsy(struct ata_link *link)
u32 serror;
int rc;
- DPRINTK("ENTER\n");
-
if (ehc->i.flags & ATA_EHI_NO_AUTOPSY)
return;
@@ -2036,7 +2030,6 @@ static void ata_eh_link_autopsy(struct ata_link *link)
ehc->i.action |= ata_eh_speed_down(dev, eflags, all_err_mask);
trace_ata_eh_link_autopsy(dev, ehc->i.action, all_err_mask);
}
- DPRINTK("EXIT\n");
}
/**
@@ -2086,16 +2079,15 @@ void ata_eh_autopsy(struct ata_port *ap)
}
/**
- * ata_get_cmd_descript - get description for ATA command
- * @command: ATA command code to get description for
+ * ata_get_cmd_name - get name for ATA command
+ * @command: ATA command code to get name for
*
- * Return a textual description of the given command, or NULL if the
- * command is not known.
+ * Return a textual name of the given command or "unknown"
*
* LOCKING:
* None
*/
-const char *ata_get_cmd_descript(u8 command)
+const char *ata_get_cmd_name(u8 command)
{
#ifdef CONFIG_ATA_VERBOSE_ERROR
static const struct
@@ -2203,9 +2195,9 @@ const char *ata_get_cmd_descript(u8 command)
return cmd_descr[i].text;
#endif
- return NULL;
+ return "unknown";
}
-EXPORT_SYMBOL_GPL(ata_get_cmd_descript);
+EXPORT_SYMBOL_GPL(ata_get_cmd_name);
/**
* ata_eh_link_report - report error handling to user
@@ -2354,12 +2346,9 @@ static void ata_eh_link_report(struct ata_link *link)
}
__scsi_format_command(cdb_buf, sizeof(cdb_buf),
cdb, cdb_len);
- } else {
- const char *descr = ata_get_cmd_descript(cmd->command);
- if (descr)
- ata_dev_err(qc->dev, "failed command: %s\n",
- descr);
- }
+ } else
+ ata_dev_err(qc->dev, "failed command: %s\n",
+ ata_get_cmd_name(cmd->command));
ata_dev_err(qc->dev,
"cmd %02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x "
@@ -2596,12 +2585,19 @@ int ata_eh_reset(struct ata_link *link, int classify,
/* mark that this EH session started with reset */
ehc->last_reset = jiffies;
- if (reset == hardreset)
+ if (reset == hardreset) {
ehc->i.flags |= ATA_EHI_DID_HARDRESET;
- else
+ trace_ata_link_hardreset_begin(link, classes, deadline);
+ } else {
ehc->i.flags |= ATA_EHI_DID_SOFTRESET;
+ trace_ata_link_softreset_begin(link, classes, deadline);
+ }
rc = ata_do_reset(link, reset, classes, deadline, true);
+ if (reset == hardreset)
+ trace_ata_link_hardreset_end(link, classes, rc);
+ else
+ trace_ata_link_softreset_end(link, classes, rc);
if (rc && rc != -EAGAIN) {
failed_link = link;
goto fail;
@@ -2615,8 +2611,11 @@ int ata_eh_reset(struct ata_link *link, int classify,
ata_link_info(slave, "hard resetting link\n");
ata_eh_about_to_do(slave, NULL, ATA_EH_RESET);
+ trace_ata_slave_hardreset_begin(slave, classes,
+ deadline);
tmp = ata_do_reset(slave, reset, classes, deadline,
false);
+ trace_ata_slave_hardreset_end(slave, classes, tmp);
switch (tmp) {
case -EAGAIN:
rc = -EAGAIN;
@@ -2644,7 +2643,9 @@ int ata_eh_reset(struct ata_link *link, int classify,
}
ata_eh_about_to_do(link, NULL, ATA_EH_RESET);
+ trace_ata_link_softreset_begin(link, classes, deadline);
rc = ata_do_reset(link, reset, classes, deadline, true);
+ trace_ata_link_softreset_end(link, classes, rc);
if (rc) {
failed_link = link;
goto fail;
@@ -2698,8 +2699,11 @@ int ata_eh_reset(struct ata_link *link, int classify,
*/
if (postreset) {
postreset(link, classes);
- if (slave)
+ trace_ata_link_postreset(link, classes, rc);
+ if (slave) {
postreset(slave, classes);
+ trace_ata_slave_postreset(slave, classes, rc);
+ }
}
/*
@@ -2921,8 +2925,6 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
unsigned long flags;
int rc = 0;
- DPRINTK("ENTER\n");
-
/* For PATA drive side cable detection to work, IDENTIFY must
* be done backwards such that PDIAG- is released by the slave
* device before the master device is identified.
@@ -3036,7 +3038,6 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
err:
*r_failed_dev = dev;
- DPRINTK("EXIT rc=%d\n", rc);
return rc;
}
@@ -3551,8 +3552,6 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
int rc, nr_fails;
unsigned long flags, deadline;
- DPRINTK("ENTER\n");
-
/* prep for recovery */
ata_for_each_link(link, ap, EDGE) {
struct ata_eh_context *ehc = &link->eh_context;
@@ -3760,7 +3759,6 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
if (rc && r_failed_link)
*r_failed_link = link;
- DPRINTK("EXIT, rc=%d\n", rc);
return rc;
}
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index ba7be3f..e2e9cbd 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -652,8 +652,6 @@ static int sata_pmp_revalidate(struct ata_device *dev, unsigned int new_class)
u32 *gscr = (void *)ap->sector_buf;
int rc;
- DPRINTK("ENTER\n");
-
ata_eh_about_to_do(link, NULL, ATA_EH_REVALIDATE);
if (!ata_dev_enabled(dev)) {
@@ -686,12 +684,10 @@ static int sata_pmp_revalidate(struct ata_device *dev, unsigned int new_class)
ata_eh_done(link, NULL, ATA_EH_REVALIDATE);
- DPRINTK("EXIT, rc=0\n");
return 0;
fail:
ata_dev_err(dev, "PMP revalidation failed (errno=%d)\n", rc);
- DPRINTK("EXIT, rc=%d\n", rc);
return rc;
}
@@ -759,8 +755,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
int detach = 0, rc = 0;
int reval_failed = 0;
- DPRINTK("ENTER\n");
-
if (dev->flags & ATA_DFLAG_DETACH) {
detach = 1;
rc = -ENODEV;
@@ -828,7 +822,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
/* okay, PMP resurrected */
ehc->i.flags = 0;
- DPRINTK("EXIT, rc=0\n");
return 0;
fail:
@@ -838,7 +831,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
else
ata_dev_disable(dev);
- DPRINTK("EXIT, rc=%d\n", rc);
return rc;
}
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index b9c7788..071158c 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -317,7 +317,7 @@ int sata_link_resume(struct ata_link *link, const unsigned long *params,
* immediately after resuming. Delay 200ms before
* debouncing.
*/
- if (!(link->flags & ATA_LFLAG_NO_DB_DELAY))
+ if (!(link->flags & ATA_LFLAG_NO_DEBOUNCE_DELAY))
ata_msleep(link->ap, 200);
/* is SControl restored correctly? */
@@ -533,8 +533,6 @@ int sata_link_hardreset(struct ata_link *link, const unsigned long *timing,
u32 scontrol;
int rc;
- DPRINTK("ENTER\n");
-
if (online)
*online = false;
@@ -610,7 +608,6 @@ int sata_link_hardreset(struct ata_link *link, const unsigned long *timing,
*online = false;
ata_link_err(link, "COMRESET failed (errno=%d)\n", rc);
}
- DPRINTK("EXIT, rc=%d\n", rc);
return rc;
}
EXPORT_SYMBOL_GPL(sata_link_hardreset);
@@ -876,7 +873,7 @@ static ssize_t ata_ncq_prio_enable_show(struct device *device,
ncq_prio_enable = dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE;
spin_unlock_irq(ap->lock);
- return rc ? rc : snprintf(buf, 20, "%u\n", ncq_prio_enable);
+ return rc ? rc : sysfs_emit(buf, "%u\n", ncq_prio_enable);
}
static ssize_t ata_ncq_prio_enable_store(struct device *device,
@@ -972,7 +969,7 @@ ata_scsi_em_message_type_show(struct device *dev, struct device_attribute *attr,
struct Scsi_Host *shost = class_to_shost(dev);
struct ata_port *ap = ata_shost_to_port(shost);
- return snprintf(buf, 23, "%d\n", ap->em_message_type);
+ return sysfs_emit(buf, "%d\n", ap->em_message_type);
}
DEVICE_ATTR(em_message_type, S_IRUGO,
ata_scsi_em_message_type_show, NULL);
@@ -1261,8 +1258,6 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
{
int rc = 0;
- ata_scsi_dump_cdb(ap, cmd);
-
if (likely(ata_dev_enabled(ap->link.device)))
rc = __ata_scsi_queuecmd(cmd, ap->link.device);
else {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 313e947..ed8be58 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -121,7 +121,7 @@ static ssize_t ata_scsi_park_show(struct device *device,
unlock:
spin_unlock_irq(ap->lock);
- return rc ? rc : snprintf(buf, 20, "%u\n", msecs);
+ return rc ? rc : sysfs_emit(buf, "%u\n", msecs);
}
static ssize_t ata_scsi_park_store(struct device *device,
@@ -668,7 +668,7 @@ static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc)
/**
* ata_dump_status - user friendly display of error info
- * @id: id of the port in question
+ * @ap: the port in question
* @tf: ptr to filled out taskfile
*
* Decode and dump the ATA error/status registers for the user so
@@ -678,37 +678,32 @@ static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc)
* LOCKING:
* inherited from caller
*/
-static void ata_dump_status(unsigned id, struct ata_taskfile *tf)
+static void ata_dump_status(struct ata_port *ap, struct ata_taskfile *tf)
{
u8 stat = tf->command, err = tf->feature;
- pr_warn("ata%u: status=0x%02x { ", id, stat);
if (stat & ATA_BUSY) {
- pr_cont("Busy }\n"); /* Data is not valid in this case */
+ ata_port_warn(ap, "status=0x%02x {Busy} ", stat);
} else {
- if (stat & ATA_DRDY) pr_cont("DriveReady ");
- if (stat & ATA_DF) pr_cont("DeviceFault ");
- if (stat & ATA_DSC) pr_cont("SeekComplete ");
- if (stat & ATA_DRQ) pr_cont("DataRequest ");
- if (stat & ATA_CORR) pr_cont("CorrectedError ");
- if (stat & ATA_SENSE) pr_cont("Sense ");
- if (stat & ATA_ERR) pr_cont("Error ");
- pr_cont("}\n");
-
- if (err) {
- pr_warn("ata%u: error=0x%02x { ", id, err);
- if (err & ATA_ABORTED) pr_cont("DriveStatusError ");
- if (err & ATA_ICRC) {
- if (err & ATA_ABORTED)
- pr_cont("BadCRC ");
- else pr_cont("Sector ");
- }
- if (err & ATA_UNC) pr_cont("UncorrectableError ");
- if (err & ATA_IDNF) pr_cont("SectorIdNotFound ");
- if (err & ATA_TRK0NF) pr_cont("TrackZeroNotFound ");
- if (err & ATA_AMNF) pr_cont("AddrMarkNotFound ");
- pr_cont("}\n");
- }
+ ata_port_warn(ap, "status=0x%02x { %s%s%s%s%s%s%s} ", stat,
+ stat & ATA_DRDY ? "DriveReady " : "",
+ stat & ATA_DF ? "DeviceFault " : "",
+ stat & ATA_DSC ? "SeekComplete " : "",
+ stat & ATA_DRQ ? "DataRequest " : "",
+ stat & ATA_CORR ? "CorrectedError " : "",
+ stat & ATA_SENSE ? "Sense " : "",
+ stat & ATA_ERR ? "Error " : "");
+ if (err)
+ ata_port_warn(ap, "error=0x%02x {%s%s%s%s%s%s", err,
+ err & ATA_ABORTED ?
+ "DriveStatusError " : "",
+ err & ATA_ICRC ?
+ (err & ATA_ABORTED ?
+ "BadCRC " : "Sector ") : "",
+ err & ATA_UNC ? "UncorrectableError " : "",
+ err & ATA_IDNF ? "SectorIdNotFound " : "",
+ err & ATA_TRK0NF ? "TrackZeroNotFound " : "",
+ err & ATA_AMNF ? "AddrMarkNotFound " : "");
}
}
@@ -1299,8 +1294,6 @@ static void scsi_6_lba_len(const u8 *cdb, u64 *plba, u32 *plen)
u64 lba = 0;
u32 len;
- VPRINTK("six-byte command\n");
-
lba |= ((u64)(cdb[1] & 0x1f)) << 16;
lba |= ((u64)cdb[2]) << 8;
lba |= ((u64)cdb[3]);
@@ -1326,8 +1319,6 @@ static void scsi_10_lba_len(const u8 *cdb, u64 *plba, u32 *plen)
u64 lba = 0;
u32 len = 0;
- VPRINTK("ten-byte command\n");
-
lba |= ((u64)cdb[2]) << 24;
lba |= ((u64)cdb[3]) << 16;
lba |= ((u64)cdb[4]) << 8;
@@ -1355,8 +1346,6 @@ static void scsi_16_lba_len(const u8 *cdb, u64 *plba, u32 *plen)
u64 lba = 0;
u32 len = 0;
- VPRINTK("sixteen-byte command\n");
-
lba |= ((u64)cdb[2]) << 56;
lba |= ((u64)cdb[3]) << 48;
lba |= ((u64)cdb[4]) << 40;
@@ -1469,9 +1458,6 @@ static unsigned int ata_scsi_verify_xlat(struct ata_queued_cmd *qc)
head = track % dev->heads;
sect = (u32)block % dev->sectors + 1;
- DPRINTK("block %u track %u cyl %u head %u sect %u\n",
- (u32)block, track, cyl, head, sect);
-
/* Check whether the converted CHS can fit.
Cylinder: 0-65535
Head: 0-15
@@ -1594,7 +1580,6 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc)
goto invalid_fld;
break;
default:
- DPRINTK("no-byte command\n");
fp = 0;
goto invalid_fld;
}
@@ -1672,7 +1657,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
cmd->result = SAM_STAT_GOOD;
if (need_sense && !ap->ops->error_handler)
- ata_dump_status(ap->print_id, &qc->result_tf);
+ ata_dump_status(ap, &qc->result_tf);
ata_qc_done(qc);
}
@@ -1710,8 +1695,6 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
struct ata_queued_cmd *qc;
int rc;
- VPRINTK("ENTER\n");
-
qc = ata_scsi_qc_new(dev, cmd);
if (!qc)
goto err_mem;
@@ -1742,13 +1725,11 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
/* select device, send command to hardware */
ata_qc_issue(qc);
- VPRINTK("EXIT\n");
return 0;
early_finish:
ata_qc_free(qc);
scsi_done(cmd);
- DPRINTK("EXIT - early finish (good or error)\n");
return 0;
err_did:
@@ -1756,12 +1737,10 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
cmd->result = (DID_ERROR << 16);
scsi_done(cmd);
err_mem:
- DPRINTK("EXIT - internal\n");
return 0;
defer:
ata_qc_free(qc);
- DPRINTK("EXIT - defer\n");
if (rc == ATA_DEFER_LINK)
return SCSI_MLQUEUE_DEVICE_BUSY;
else
@@ -1858,8 +1837,6 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
2
};
- VPRINTK("ENTER\n");
-
/* set scsi removable (RMB) bit per ata bit, or if the
* AHCI port says it's external (Hotplug-capable, eSATA).
*/
@@ -2294,8 +2271,6 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf)
u8 dpofua, bp = 0xff;
u16 fp;
- VPRINTK("ENTER\n");
-
six_byte = (scsicmd[0] == MODE_SENSE);
ebd = !(scsicmd[1] & 0x8); /* dbd bit inverted == edb */
/*
@@ -2413,8 +2388,6 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
log2_per_phys = ata_id_log2_per_physical_sector(dev->id);
lowest_aligned = ata_id_logical_sector_offset(dev->id, log2_per_phys);
- VPRINTK("ENTER\n");
-
if (args->cmd->cmnd[0] == READ_CAPACITY) {
if (last_lba >= 0xffffffffULL)
last_lba = 0xffffffff;
@@ -2481,7 +2454,6 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
*/
static unsigned int ata_scsiop_report_luns(struct ata_scsi_args *args, u8 *rbuf)
{
- VPRINTK("ENTER\n");
rbuf[3] = 8; /* just one lun, LUN 0, size 8 bytes */
return 0;
@@ -2512,8 +2484,6 @@ static void atapi_request_sense(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
struct scsi_cmnd *cmd = qc->scsicmd;
- DPRINTK("ATAPI request sense\n");
-
memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
#ifdef CONFIG_ATA_SFF
@@ -2552,8 +2522,6 @@ static void atapi_request_sense(struct ata_queued_cmd *qc)
qc->complete_fn = atapi_sense_complete;
ata_qc_issue(qc);
-
- DPRINTK("EXIT\n");
}
/*
@@ -2581,8 +2549,6 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
struct scsi_cmnd *cmd = qc->scsicmd;
unsigned int err_mask = qc->err_mask;
- VPRINTK("ENTER, err_mask 0x%X\n", err_mask);
-
/* handle completion from new EH */
if (unlikely(qc->ap->ops->error_handler &&
(err_mask || qc->flags & ATA_QCFLAG_SENSE_VALID))) {
@@ -2663,7 +2629,6 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
qc->tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
if (scmd->sc_data_direction == DMA_TO_DEVICE) {
qc->tf.flags |= ATA_TFLAG_WRITE;
- DPRINTK("direction: write\n");
}
qc->tf.command = ATA_CMD_PACKET;
@@ -3591,10 +3556,7 @@ static int ata_mselect_caching(struct ata_queued_cmd *qc,
*/
if (len != CACHE_MPAGE_LEN - 2) {
- if (len < CACHE_MPAGE_LEN - 2)
- *fp = len;
- else
- *fp = CACHE_MPAGE_LEN - 2;
+ *fp = min(len, CACHE_MPAGE_LEN - 2);
return -EINVAL;
}
@@ -3647,10 +3609,7 @@ static int ata_mselect_control(struct ata_queued_cmd *qc,
*/
if (len != CONTROL_MPAGE_LEN - 2) {
- if (len < CONTROL_MPAGE_LEN - 2)
- *fp = len;
- else
- *fp = CONTROL_MPAGE_LEN - 2;
+ *fp = min(len, CONTROL_MPAGE_LEN - 2);
return -EINVAL;
}
@@ -3698,8 +3657,6 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
u8 buffer[64];
const u8 *p = buffer;
- VPRINTK("ENTER\n");
-
six_byte = (cdb[0] == MODE_SELECT);
if (six_byte) {
if (scmd->cmd_len < 5) {
@@ -3997,70 +3954,45 @@ static inline ata_xlat_func_t ata_get_xlat_func(struct ata_device *dev, u8 cmd)
return NULL;
}
-/**
- * ata_scsi_dump_cdb - dump SCSI command contents to dmesg
- * @ap: ATA port to which the command was being sent
- * @cmd: SCSI command to dump
- *
- * Prints the contents of a SCSI command via printk().
- */
-
-void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd)
-{
-#ifdef ATA_VERBOSE_DEBUG
- struct scsi_device *scsidev = cmd->device;
-
- VPRINTK("CDB (%u:%d,%d,%lld) %9ph\n",
- ap->print_id,
- scsidev->channel, scsidev->id, scsidev->lun,
- cmd->cmnd);
-#endif
-}
-
int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev)
{
u8 scsi_op = scmd->cmnd[0];
ata_xlat_func_t xlat_func;
- int rc = 0;
+
+ if (unlikely(!scmd->cmd_len))
+ goto bad_cdb_len;
if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) {
- if (unlikely(!scmd->cmd_len || scmd->cmd_len > dev->cdb_len))
+ if (unlikely(scmd->cmd_len > dev->cdb_len))
goto bad_cdb_len;
xlat_func = ata_get_xlat_func(dev, scsi_op);
- } else {
- if (unlikely(!scmd->cmd_len))
+ } else if (likely((scsi_op != ATA_16) || !atapi_passthru16)) {
+ /* relay SCSI command to ATAPI device */
+ int len = COMMAND_SIZE(scsi_op);
+
+ if (unlikely(len > scmd->cmd_len ||
+ len > dev->cdb_len ||
+ scmd->cmd_len > ATAPI_CDB_LEN))
goto bad_cdb_len;
- xlat_func = NULL;
- if (likely((scsi_op != ATA_16) || !atapi_passthru16)) {
- /* relay SCSI command to ATAPI device */
- int len = COMMAND_SIZE(scsi_op);
- if (unlikely(len > scmd->cmd_len ||
- len > dev->cdb_len ||
- scmd->cmd_len > ATAPI_CDB_LEN))
- goto bad_cdb_len;
+ xlat_func = atapi_xlat;
+ } else {
+ /* ATA_16 passthru, treat as an ATA command */
+ if (unlikely(scmd->cmd_len > 16))
+ goto bad_cdb_len;
- xlat_func = atapi_xlat;
- } else {
- /* ATA_16 passthru, treat as an ATA command */
- if (unlikely(scmd->cmd_len > 16))
- goto bad_cdb_len;
-
- xlat_func = ata_get_xlat_func(dev, scsi_op);
- }
+ xlat_func = ata_get_xlat_func(dev, scsi_op);
}
if (xlat_func)
- rc = ata_scsi_translate(dev, scmd, xlat_func);
- else
- ata_scsi_simulate(dev, scmd);
+ return ata_scsi_translate(dev, scmd, xlat_func);
- return rc;
+ ata_scsi_simulate(dev, scmd);
+
+ return 0;
bad_cdb_len:
- DPRINTK("bad CDB len=%u, scsi_op=0x%02x, max=%u\n",
- scmd->cmd_len, scsi_op, dev->cdb_len);
scmd->result = DID_ERROR << 16;
scsi_done(scmd);
return 0;
@@ -4097,8 +4029,6 @@ int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
spin_lock_irqsave(ap->lock, irq_flags);
- ata_scsi_dump_cdb(ap, cmd);
-
dev = ata_scsi_find_dev(ap, scsidev);
if (likely(dev))
rc = __ata_scsi_queuecmd(cmd, dev);
@@ -4531,12 +4461,9 @@ void ata_scsi_hotplug(struct work_struct *work)
container_of(work, struct ata_port, hotplug_task.work);
int i;
- if (ap->pflags & ATA_PFLAG_UNLOADING) {
- DPRINTK("ENTER/EXIT - unloading\n");
+ if (ap->pflags & ATA_PFLAG_UNLOADING)
return;
- }
- DPRINTK("ENTER\n");
mutex_lock(&ap->scsi_scan_mutex);
/* Unplug detached devices. We cannot use link iterator here
@@ -4552,7 +4479,6 @@ void ata_scsi_hotplug(struct work_struct *work)
ata_scsi_scan_host(ap, 0);
mutex_unlock(&ap->scsi_scan_mutex);
- DPRINTK("EXIT\n");
}
/**
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index b71ea4a..7521782 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -18,7 +18,7 @@
#include <linux/module.h>
#include <linux/libata.h>
#include <linux/highmem.h>
-
+#include <trace/events/libata.h>
#include "libata.h"
static struct workqueue_struct *ata_sff_wq;
@@ -330,10 +330,6 @@ EXPORT_SYMBOL_GPL(ata_sff_dev_select);
static void ata_dev_select(struct ata_port *ap, unsigned int device,
unsigned int wait, unsigned int can_sleep)
{
- if (ata_msg_probe(ap))
- ata_port_info(ap, "ata_dev_select: ENTER, device %u, wait %u\n",
- device, wait);
-
if (wait)
ata_wait_idle(ap);
@@ -409,12 +405,6 @@ void ata_sff_tf_load(struct ata_port *ap, const struct ata_taskfile *tf)
iowrite8(tf->hob_lbal, ioaddr->lbal_addr);
iowrite8(tf->hob_lbam, ioaddr->lbam_addr);
iowrite8(tf->hob_lbah, ioaddr->lbah_addr);
- VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->hob_feature,
- tf->hob_nsect,
- tf->hob_lbal,
- tf->hob_lbam,
- tf->hob_lbah);
}
if (is_addr) {
@@ -423,18 +413,10 @@ void ata_sff_tf_load(struct ata_port *ap, const struct ata_taskfile *tf)
iowrite8(tf->lbal, ioaddr->lbal_addr);
iowrite8(tf->lbam, ioaddr->lbam_addr);
iowrite8(tf->lbah, ioaddr->lbah_addr);
- VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n",
- tf->feature,
- tf->nsect,
- tf->lbal,
- tf->lbam,
- tf->lbah);
}
- if (tf->flags & ATA_TFLAG_DEVICE) {
+ if (tf->flags & ATA_TFLAG_DEVICE)
iowrite8(tf->device, ioaddr->device_addr);
- VPRINTK("device 0x%X\n", tf->device);
- }
ata_wait_idle(ap);
}
@@ -494,8 +476,6 @@ EXPORT_SYMBOL_GPL(ata_sff_tf_read);
*/
void ata_sff_exec_command(struct ata_port *ap, const struct ata_taskfile *tf)
{
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
-
iowrite8(tf->command, ap->ioaddr.command_addr);
ata_sff_pause(ap);
}
@@ -505,6 +485,7 @@ EXPORT_SYMBOL_GPL(ata_sff_exec_command);
* ata_tf_to_host - issue ATA taskfile to host controller
* @ap: port to which command is being issued
* @tf: ATA taskfile register set
+ * @tag: tag of the associated command
*
* Issues ATA taskfile register set to ATA host controller,
* with proper synchronization with interrupt handler and
@@ -514,9 +495,12 @@ EXPORT_SYMBOL_GPL(ata_sff_exec_command);
* spin_lock_irqsave(host lock)
*/
static inline void ata_tf_to_host(struct ata_port *ap,
- const struct ata_taskfile *tf)
+ const struct ata_taskfile *tf,
+ unsigned int tag)
{
+ trace_ata_tf_load(ap, tf);
ap->ops->sff_tf_load(ap, tf);
+ trace_ata_exec_command(ap, tf, tag);
ap->ops->sff_exec_command(ap, tf);
}
@@ -680,7 +664,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
page = nth_page(page, (offset >> PAGE_SHIFT));
offset %= PAGE_SIZE;
- DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
+ trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size);
/*
* Split the transfer when it splits a page boundary. Note that the
@@ -750,7 +734,7 @@ static void ata_pio_sectors(struct ata_queued_cmd *qc)
static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc)
{
/* send SCSI cdb */
- DPRINTK("send cdb\n");
+ trace_atapi_send_cdb(qc, 0, qc->dev->cdb_len);
WARN_ON_ONCE(qc->dev->cdb_len < 12);
ap->ops->sff_data_xfer(qc, qc->cdb, qc->dev->cdb_len, 1);
@@ -768,6 +752,7 @@ static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc)
case ATAPI_PROT_DMA:
ap->hsm_task_state = HSM_ST_LAST;
/* initiate bmdma */
+ trace_ata_bmdma_start(ap, &qc->tf, qc->tag);
ap->ops->bmdma_start(qc);
break;
#endif /* CONFIG_ATA_BMDMA */
@@ -820,7 +805,7 @@ static int __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes)
/* don't cross page boundaries */
count = min(count, (unsigned int)PAGE_SIZE - offset);
- DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
+ trace_atapi_pio_transfer_data(qc, offset, count);
/* do the actual data transfer */
buf = kmap_atomic(page);
@@ -888,8 +873,6 @@ static void atapi_pio_bytes(struct ata_queued_cmd *qc)
if (unlikely(!bytes))
goto atapi_check;
- VPRINTK("ata%u: xfering %d bytes\n", ap->print_id, bytes);
-
if (unlikely(__atapi_pio_bytes(qc, bytes)))
goto err_out;
ata_sff_sync(ap); /* flush */
@@ -1002,8 +985,7 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
WARN_ON_ONCE(in_wq != ata_hsm_ok_in_wq(ap, qc));
fsm_start:
- DPRINTK("ata%u: protocol %d task_state %d (dev_stat 0x%X)\n",
- ap->print_id, qc->tf.protocol, ap->hsm_task_state, status);
+ trace_ata_sff_hsm_state(qc, status);
switch (ap->hsm_task_state) {
case HSM_ST_FIRST:
@@ -1204,8 +1186,7 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
}
/* no more data to transfer */
- DPRINTK("ata%u: dev %u command complete, drv_stat 0x%x\n",
- ap->print_id, qc->dev->devno, status);
+ trace_ata_sff_hsm_command_complete(qc, status);
WARN_ON_ONCE(qc->err_mask & (AC_ERR_DEV | AC_ERR_HSM));
@@ -1262,7 +1243,7 @@ EXPORT_SYMBOL_GPL(ata_sff_queue_pio_task);
void ata_sff_flush_pio_task(struct ata_port *ap)
{
- DPRINTK("ENTER\n");
+ trace_ata_sff_flush_pio_task(ap);
cancel_delayed_work_sync(&ap->sff_pio_task);
@@ -1279,9 +1260,6 @@ void ata_sff_flush_pio_task(struct ata_port *ap)
spin_unlock_irq(ap->lock);
ap->sff_pio_task_link = NULL;
-
- if (ata_msg_ctl(ap))
- ata_port_dbg(ap, "%s: EXIT\n", __func__);
}
static void ata_sff_pio_task(struct work_struct *work)
@@ -1376,7 +1354,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc)
if (qc->tf.flags & ATA_TFLAG_POLLING)
ata_qc_set_polling(qc);
- ata_tf_to_host(ap, &qc->tf);
+ ata_tf_to_host(ap, &qc->tf, qc->tag);
ap->hsm_task_state = HSM_ST_LAST;
if (qc->tf.flags & ATA_TFLAG_POLLING)
@@ -1388,7 +1366,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc)
if (qc->tf.flags & ATA_TFLAG_POLLING)
ata_qc_set_polling(qc);
- ata_tf_to_host(ap, &qc->tf);
+ ata_tf_to_host(ap, &qc->tf, qc->tag);
if (qc->tf.flags & ATA_TFLAG_WRITE) {
/* PIO data out protocol */
@@ -1418,7 +1396,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc)
if (qc->tf.flags & ATA_TFLAG_POLLING)
ata_qc_set_polling(qc);
- ata_tf_to_host(ap, &qc->tf);
+ ata_tf_to_host(ap, &qc->tf, qc->tag);
ap->hsm_task_state = HSM_ST_FIRST;
@@ -1478,8 +1456,7 @@ static unsigned int __ata_sff_port_intr(struct ata_port *ap,
{
u8 status;
- VPRINTK("ata%u: protocol %d task_state %d\n",
- ap->print_id, qc->tf.protocol, ap->hsm_task_state);
+ trace_ata_sff_port_intr(qc, hsmv_on_idle);
/* Check whether we are expecting interrupt in this state */
switch (ap->hsm_task_state) {
@@ -1853,7 +1830,7 @@ unsigned int ata_sff_dev_classify(struct ata_device *dev, int present,
return ATA_DEV_NONE;
/* determine if device is ATA or ATAPI */
- class = ata_dev_classify(&tf);
+ class = ata_port_classify(ap, &tf);
if (class == ATA_DEV_UNKNOWN) {
/* If the device failed diagnostic, it's likely to
@@ -1956,8 +1933,6 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask,
{
struct ata_ioports *ioaddr = &ap->ioaddr;
- DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
-
if (ap->ioaddr.ctl_addr) {
/* software reset. causes dev0 to be selected */
iowrite8(ap->ctl, ioaddr->ctl_addr);
@@ -1995,8 +1970,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes,
int rc;
u8 err;
- DPRINTK("ENTER\n");
-
/* determine if device 0/1 are present */
if (ata_devchk(ap, 0))
devmask |= (1 << 0);
@@ -2007,7 +1980,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes,
ap->ops->sff_dev_select(ap, 0);
/* issue bus reset */
- DPRINTK("about to softreset, devmask=%x\n", devmask);
rc = ata_bus_softreset(ap, devmask, deadline);
/* if link is occupied, -ENODEV too is an error */
if (rc && (rc != -ENODEV || sata_scr_valid(link))) {
@@ -2022,7 +1994,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes,
classes[1] = ata_sff_dev_classify(&link->device[1],
devmask & (1 << 1), &err);
- DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]);
return 0;
}
EXPORT_SYMBOL_GPL(ata_sff_softreset);
@@ -2055,7 +2026,6 @@ int sata_sff_hardreset(struct ata_link *link, unsigned int *class,
if (online)
*class = ata_sff_dev_classify(link->device, 1, NULL);
- DPRINTK("EXIT, class=%u\n", *class);
return rc;
}
EXPORT_SYMBOL_GPL(sata_sff_hardreset);
@@ -2085,10 +2055,8 @@ void ata_sff_postreset(struct ata_link *link, unsigned int *classes)
ap->ops->sff_dev_select(ap, 0);
/* bail out if no device is present */
- if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE) {
- DPRINTK("EXIT, no device\n");
+ if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE)
return;
- }
/* set up device control */
if (ap->ops->sff_set_devctl || ap->ioaddr.ctl_addr) {
@@ -2123,7 +2091,6 @@ void ata_sff_drain_fifo(struct ata_queued_cmd *qc)
&& count < 65536; count += 2)
ioread16(ap->ioaddr.data_addr);
- /* Can become DEBUG later */
if (count)
ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count);
@@ -2467,8 +2434,6 @@ static int ata_pci_init_one(struct pci_dev *pdev,
struct ata_host *host = NULL;
int rc;
- DPRINTK("ENTER\n");
-
pi = ata_sff_find_valid_pi(ppi);
if (!pi) {
dev_err(&pdev->dev, "no valid port_info specified\n");
@@ -2614,7 +2579,6 @@ static void ata_bmdma_fill_sg(struct ata_queued_cmd *qc)
prd[pi].addr = cpu_to_le32(addr);
prd[pi].flags_len = cpu_to_le32(len & 0xffff);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", pi, addr, len);
pi++;
sg_len -= len;
@@ -2674,7 +2638,6 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc)
prd[++pi].addr = cpu_to_le32(addr + 0x8000);
}
prd[pi].flags_len = cpu_to_le32(blen);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", pi, addr, len);
pi++;
sg_len -= len;
@@ -2756,8 +2719,11 @@ unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc)
case ATA_PROT_DMA:
WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING);
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */
+ trace_ata_bmdma_setup(ap, &qc->tf, qc->tag);
ap->ops->bmdma_setup(qc); /* set up bmdma */
+ trace_ata_bmdma_start(ap, &qc->tf, qc->tag);
ap->ops->bmdma_start(qc); /* initiate bmdma */
ap->hsm_task_state = HSM_ST_LAST;
break;
@@ -2765,7 +2731,9 @@ unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc)
case ATAPI_PROT_DMA:
WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING);
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */
+ trace_ata_bmdma_setup(ap, &qc->tf, qc->tag);
ap->ops->bmdma_setup(qc); /* set up bmdma */
ap->hsm_task_state = HSM_ST_FIRST;
@@ -2806,13 +2774,14 @@ unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc)
if (ap->hsm_task_state == HSM_ST_LAST && ata_is_dma(qc->tf.protocol)) {
/* check status of DMA engine */
host_stat = ap->ops->bmdma_status(ap);
- VPRINTK("ata%u: host_stat 0x%X\n", ap->print_id, host_stat);
+ trace_ata_bmdma_status(ap, host_stat);
/* if it's not our irq... */
if (!(host_stat & ATA_DMA_INTR))
return ata_sff_idle_irq(ap);
/* before we do anything else, clear DMA-Start bit */
+ trace_ata_bmdma_stop(ap, &qc->tf, qc->tag);
ap->ops->bmdma_stop(qc);
bmdma_stopped = true;
@@ -2881,6 +2850,7 @@ void ata_bmdma_error_handler(struct ata_port *ap)
u8 host_stat;
host_stat = ap->ops->bmdma_status(ap);
+ trace_ata_bmdma_status(ap, host_stat);
/* BMDMA controllers indicate host bus error by
* setting DMA_ERR bit and timing out. As it wasn't
@@ -2892,6 +2862,7 @@ void ata_bmdma_error_handler(struct ata_port *ap)
thaw = true;
}
+ trace_ata_bmdma_stop(ap, &qc->tf, qc->tag);
ap->ops->bmdma_stop(qc);
/* if we're gonna thaw, make sure IRQ is clear */
@@ -2925,6 +2896,7 @@ void ata_bmdma_post_internal_cmd(struct ata_queued_cmd *qc)
if (ata_is_dma(qc->tf.protocol)) {
spin_lock_irqsave(ap->lock, flags);
+ trace_ata_bmdma_stop(ap, &qc->tf, qc->tag);
ap->ops->bmdma_stop(qc);
spin_unlock_irqrestore(ap->lock, flags);
}
diff --git a/drivers/ata/libata-trace.c b/drivers/ata/libata-trace.c
index 08e0013..e0e4d0d 100644
--- a/drivers/ata/libata-trace.c
+++ b/drivers/ata/libata-trace.c
@@ -39,6 +39,24 @@ libata_trace_parse_status(struct trace_seq *p, unsigned char status)
}
const char *
+libata_trace_parse_host_stat(struct trace_seq *p, unsigned char host_stat)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+
+ trace_seq_printf(p, "{ ");
+ if (host_stat & ATA_DMA_INTR)
+ trace_seq_printf(p, "INTR ");
+ if (host_stat & ATA_DMA_ERR)
+ trace_seq_printf(p, "ERR ");
+ if (host_stat & ATA_DMA_ACTIVE)
+ trace_seq_printf(p, "ACTIVE ");
+ trace_seq_putc(p, '}');
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+const char *
libata_trace_parse_eh_action(struct trace_seq *p, unsigned int eh_action)
{
const char *ret = trace_seq_buffer_ptr(p);
@@ -138,6 +156,35 @@ libata_trace_parse_qc_flags(struct trace_seq *p, unsigned int qc_flags)
}
const char *
+libata_trace_parse_tf_flags(struct trace_seq *p, unsigned int tf_flags)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+
+ trace_seq_printf(p, "%x", tf_flags);
+ if (tf_flags) {
+ trace_seq_printf(p, "{ ");
+ if (tf_flags & ATA_TFLAG_LBA48)
+ trace_seq_printf(p, "LBA48 ");
+ if (tf_flags & ATA_TFLAG_ISADDR)
+ trace_seq_printf(p, "ISADDR ");
+ if (tf_flags & ATA_TFLAG_DEVICE)
+ trace_seq_printf(p, "DEV ");
+ if (tf_flags & ATA_TFLAG_WRITE)
+ trace_seq_printf(p, "WRITE ");
+ if (tf_flags & ATA_TFLAG_LBA)
+ trace_seq_printf(p, "LBA ");
+ if (tf_flags & ATA_TFLAG_FUA)
+ trace_seq_printf(p, "FUA ");
+ if (tf_flags & ATA_TFLAG_POLLING)
+ trace_seq_printf(p, "POLL ");
+ trace_seq_putc(p, '}');
+ }
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+const char *
libata_trace_parse_subcmd(struct trace_seq *p, unsigned char cmd,
unsigned char feature, unsigned char hob_nsect)
{
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index 34bb460..ca12985 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -163,7 +163,7 @@ static struct {
{ AC_ERR_INVALID, "InvalidArg" },
{ AC_ERR_OTHER, "Unknown" },
{ AC_ERR_NODEV_HINT, "NoDeviceHint" },
- { AC_ERR_NCQ, "NCQError" }
+ { AC_ERR_NCQ, "NCQError" }
};
ata_bitfield_name_match(err, ata_err_names)
@@ -321,13 +321,43 @@ int ata_tport_add(struct device *parent,
return error;
}
+/**
+ * ata_port_classify - determine device type based on ATA-spec signature
+ * @ap: ATA port device on which the classification should be run
+ * @tf: ATA taskfile register set for device to be identified
+ *
+ * A wrapper around ata_dev_classify() to provide additional logging
+ *
+ * RETURNS:
+ * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP,
+ * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure.
+ */
+unsigned int ata_port_classify(struct ata_port *ap,
+ const struct ata_taskfile *tf)
+{
+ int i;
+ unsigned int class = ata_dev_classify(tf);
+
+ /* Start with index '1' to skip the 'unknown' entry */
+ for (i = 1; i < ARRAY_SIZE(ata_class_names); i++) {
+ if (ata_class_names[i].value == class) {
+ ata_port_dbg(ap, "found %s device by sig\n",
+ ata_class_names[i].name);
+ return class;
+ }
+ }
+
+ ata_port_info(ap, "found unknown device (class %u)\n", class);
+ return class;
+}
+EXPORT_SYMBOL_GPL(ata_port_classify);
/*
* ATA link attributes
*/
static int noop(int x) { return x; }
-#define ata_link_show_linkspeed(field, format) \
+#define ata_link_show_linkspeed(field, format) \
static ssize_t \
show_ata_link_##field(struct device *dev, \
struct device_attribute *attr, char *buf) \
@@ -416,7 +446,7 @@ int ata_tlink_add(struct ata_link *link)
dev->release = ata_tlink_release;
if (ata_is_host_link(link))
dev_set_name(dev, "link%d", ap->print_id);
- else
+ else
dev_set_name(dev, "link%d.%d", ap->print_id, link->pmp);
transport_setup_device(dev);
@@ -472,7 +502,7 @@ ata_dev_attr(xfer, dma_mode);
ata_dev_attr(xfer, xfer_mode);
-#define ata_dev_show_simple(field, format_string, cast) \
+#define ata_dev_show_simple(field, format_string, cast) \
static ssize_t \
show_ata_dev_##field(struct device *dev, \
struct device_attribute *attr, char *buf) \
@@ -482,9 +512,9 @@ show_ata_dev_##field(struct device *dev, \
return scnprintf(buf, 20, format_string, cast ata_dev->field); \
}
-#define ata_dev_simple_attr(field, format_string, type) \
+#define ata_dev_simple_attr(field, format_string, type) \
ata_dev_show_simple(field, format_string, (type)) \
-static DEVICE_ATTR(field, S_IRUGO, \
+ static DEVICE_ATTR(field, S_IRUGO, \
show_ata_dev_##field, NULL)
ata_dev_simple_attr(spdn_cnt, "%d\n", int);
@@ -502,7 +532,7 @@ static int ata_show_ering(struct ata_ering_entry *ent, void *void_arg)
seconds = div_u64_rem(ent->timestamp, HZ, &rem);
arg->written += sprintf(arg->buf + arg->written,
- "[%5llu.%09lu]", seconds,
+ "[%5llu.%09lu]", seconds,
rem * NSEC_PER_SEC / HZ);
arg->written += get_ata_err_names(ent->err_mask,
arg->buf + arg->written);
@@ -667,7 +697,7 @@ static int ata_tdev_add(struct ata_device *ata_dev)
dev->release = ata_tdev_release;
if (ata_is_host_link(link))
dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno);
- else
+ else
dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp);
transport_setup_device(dev);
@@ -689,7 +719,7 @@ static int ata_tdev_add(struct ata_device *ata_dev)
*/
#define SETUP_TEMPLATE(attrb, field, perm, test) \
- i->private_##attrb[count] = dev_attr_##field; \
+ i->private_##attrb[count] = dev_attr_##field; \
i->private_##attrb[count].attr.mode = perm; \
i->attrb[count] = &i->private_##attrb[count]; \
if (test) \
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 68cdd81..51e01ac 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -148,7 +148,6 @@ extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
unsigned int id, u64 lun);
void ata_scsi_sdev_config(struct scsi_device *sdev);
int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev);
-void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd);
int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev);
/* libata-eh.c */
@@ -166,7 +165,7 @@ extern void ata_eh_about_to_do(struct ata_link *link, struct ata_device *dev,
extern void ata_eh_done(struct ata_link *link, struct ata_device *dev,
unsigned int action);
extern void ata_eh_autopsy(struct ata_port *ap);
-const char *ata_get_cmd_descript(u8 command);
+const char *ata_get_cmd_name(u8 command);
extern void ata_eh_report(struct ata_port *ap);
extern int ata_eh_reset(struct ata_link *link, int classify,
ata_prereset_fn_t prereset, ata_reset_fn_t softreset,
@@ -179,7 +178,7 @@ extern int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
extern void ata_eh_finish(struct ata_port *ap);
extern int ata_ering_map(struct ata_ering *ering,
int (*map_fn)(struct ata_ering_entry *, void *),
- void *arg);
+ void *arg);
extern unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key);
extern unsigned int atapi_eh_request_sense(struct ata_device *dev,
u8 *sense_buf, u8 dfl_sense_key);
diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c
index b7ff63e..1b90cda 100644
--- a/drivers/ata/pata_ali.c
+++ b/drivers/ata/pata_ali.c
@@ -37,7 +37,7 @@
#define DRV_NAME "pata_ali"
#define DRV_VERSION "0.7.8"
-static int ali_atapi_dma = 0;
+static int ali_atapi_dma;
module_param_named(atapi_dma, ali_atapi_dma, int, 0644);
MODULE_PARM_DESC(atapi_dma, "Enable ATAPI DMA (0=disable, 1=enable)");
@@ -123,7 +123,7 @@ static unsigned long ali_20_filter(struct ata_device *adev, unsigned long mask)
mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA);
ata_id_c_string(adev->id, model_num, ATA_ID_PROD, sizeof(model_num));
if (strstr(model_num, "WDC"))
- return mask &= ~ATA_MASK_UDMA;
+ mask &= ~ATA_MASK_UDMA;
return mask;
}
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 63f3944..24c3d5e 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -39,6 +39,7 @@
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/workqueue.h>
+#include <trace/events/libata.h>
#define DRIVER_NAME "arasan_cf"
#define TIMEOUT msecs_to_jiffies(3000)
@@ -703,9 +704,11 @@ static unsigned int arasan_cf_qc_issue(struct ata_queued_cmd *qc)
case ATA_PROT_DMA:
WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING);
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf);
acdev->dma_status = 0;
acdev->qc = qc;
+ trace_ata_bmdma_start(ap, &qc->tf, qc->tag);
arasan_cf_dma_start(acdev);
ap->hsm_task_state = HSM_ST_LAST;
break;
diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c
index 2bc5fc8..779d660 100644
--- a/drivers/ata/pata_atp867x.c
+++ b/drivers/ata/pata_atp867x.c
@@ -155,7 +155,7 @@ static int atp867x_get_active_clocks_shifted(struct ata_port *ap,
case 1 ... 6:
break;
default:
- printk(KERN_WARNING "ATP867X: active %dclk is invalid. "
+ ata_port_warn(ap, "ATP867X: active %dclk is invalid. "
"Using 12clk.\n", clk);
fallthrough;
case 9 ... 12:
@@ -171,7 +171,8 @@ static int atp867x_get_active_clocks_shifted(struct ata_port *ap,
return clocks << ATP867X_IO_PIOSPD_ACTIVE_SHIFT;
}
-static int atp867x_get_recover_clocks_shifted(unsigned int clk)
+static int atp867x_get_recover_clocks_shifted(struct ata_port *ap,
+ unsigned int clk)
{
unsigned char clocks = clk;
@@ -188,7 +189,7 @@ static int atp867x_get_recover_clocks_shifted(unsigned int clk)
case 15:
break;
default:
- printk(KERN_WARNING "ATP867X: recover %dclk is invalid. "
+ ata_port_warn(ap, "ATP867X: recover %dclk is invalid. "
"Using default 12clk.\n", clk);
fallthrough;
case 12: /* default 12 clk */
@@ -225,7 +226,7 @@ static void atp867x_set_piomode(struct ata_port *ap, struct ata_device *adev)
iowrite8(b, dp->dma_mode);
b = atp867x_get_active_clocks_shifted(ap, t.active) |
- atp867x_get_recover_clocks_shifted(t.recover);
+ atp867x_get_recover_clocks_shifted(ap, t.recover);
if (adev->devno & 1)
iowrite8(b, dp->slave_piospd);
@@ -233,7 +234,7 @@ static void atp867x_set_piomode(struct ata_port *ap, struct ata_device *adev)
iowrite8(b, dp->mstr_piospd);
b = atp867x_get_active_clocks_shifted(ap, t.act8b) |
- atp867x_get_recover_clocks_shifted(t.rec8b);
+ atp867x_get_recover_clocks_shifted(ap, t.rec8b);
iowrite8(b, dp->eightb_piospd);
}
@@ -270,7 +271,6 @@ static struct ata_port_operations atp867x_ops = {
};
-#ifdef ATP867X_DEBUG
static void atp867x_check_res(struct pci_dev *pdev)
{
int i;
@@ -280,7 +280,7 @@ static void atp867x_check_res(struct pci_dev *pdev)
for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
start = pci_resource_start(pdev, i);
len = pci_resource_len(pdev, i);
- printk(KERN_DEBUG "ATP867X: resource start:len=%lx:%lx\n",
+ dev_dbg(&pdev->dev, "ATP867X: resource start:len=%lx:%lx\n",
start, len);
}
}
@@ -290,49 +290,48 @@ static void atp867x_check_ports(struct ata_port *ap, int port)
struct ata_ioports *ioaddr = &ap->ioaddr;
struct atp867x_priv *dp = ap->private_data;
- printk(KERN_DEBUG "ATP867X: port[%d] addresses\n"
- " cmd_addr =0x%llx, 0x%llx\n"
- " ctl_addr =0x%llx, 0x%llx\n"
- " bmdma_addr =0x%llx, 0x%llx\n"
- " data_addr =0x%llx\n"
- " error_addr =0x%llx\n"
- " feature_addr =0x%llx\n"
- " nsect_addr =0x%llx\n"
- " lbal_addr =0x%llx\n"
- " lbam_addr =0x%llx\n"
- " lbah_addr =0x%llx\n"
- " device_addr =0x%llx\n"
- " status_addr =0x%llx\n"
- " command_addr =0x%llx\n"
- " dp->dma_mode =0x%llx\n"
- " dp->mstr_piospd =0x%llx\n"
- " dp->slave_piospd =0x%llx\n"
- " dp->eightb_piospd =0x%llx\n"
+ ata_port_dbg(ap, "ATP867X: port[%d] addresses\n"
+ " cmd_addr =0x%lx, 0x%lx\n"
+ " ctl_addr =0x%lx, 0x%lx\n"
+ " bmdma_addr =0x%lx, 0x%lx\n"
+ " data_addr =0x%lx\n"
+ " error_addr =0x%lx\n"
+ " feature_addr =0x%lx\n"
+ " nsect_addr =0x%lx\n"
+ " lbal_addr =0x%lx\n"
+ " lbam_addr =0x%lx\n"
+ " lbah_addr =0x%lx\n"
+ " device_addr =0x%lx\n"
+ " status_addr =0x%lx\n"
+ " command_addr =0x%lx\n"
+ " dp->dma_mode =0x%lx\n"
+ " dp->mstr_piospd =0x%lx\n"
+ " dp->slave_piospd =0x%lx\n"
+ " dp->eightb_piospd =0x%lx\n"
" dp->pci66mhz =0x%lx\n",
port,
- (unsigned long long)ioaddr->cmd_addr,
- (unsigned long long)ATP867X_IO_PORTBASE(ap, port),
- (unsigned long long)ioaddr->ctl_addr,
- (unsigned long long)ATP867X_IO_ALTSTATUS(ap, port),
- (unsigned long long)ioaddr->bmdma_addr,
- (unsigned long long)ATP867X_IO_DMABASE(ap, port),
- (unsigned long long)ioaddr->data_addr,
- (unsigned long long)ioaddr->error_addr,
- (unsigned long long)ioaddr->feature_addr,
- (unsigned long long)ioaddr->nsect_addr,
- (unsigned long long)ioaddr->lbal_addr,
- (unsigned long long)ioaddr->lbam_addr,
- (unsigned long long)ioaddr->lbah_addr,
- (unsigned long long)ioaddr->device_addr,
- (unsigned long long)ioaddr->status_addr,
- (unsigned long long)ioaddr->command_addr,
- (unsigned long long)dp->dma_mode,
- (unsigned long long)dp->mstr_piospd,
- (unsigned long long)dp->slave_piospd,
- (unsigned long long)dp->eightb_piospd,
+ (unsigned long)ioaddr->cmd_addr,
+ (unsigned long)ATP867X_IO_PORTBASE(ap, port),
+ (unsigned long)ioaddr->ctl_addr,
+ (unsigned long)ATP867X_IO_ALTSTATUS(ap, port),
+ (unsigned long)ioaddr->bmdma_addr,
+ (unsigned long)ATP867X_IO_DMABASE(ap, port),
+ (unsigned long)ioaddr->data_addr,
+ (unsigned long)ioaddr->error_addr,
+ (unsigned long)ioaddr->feature_addr,
+ (unsigned long)ioaddr->nsect_addr,
+ (unsigned long)ioaddr->lbal_addr,
+ (unsigned long)ioaddr->lbam_addr,
+ (unsigned long)ioaddr->lbah_addr,
+ (unsigned long)ioaddr->device_addr,
+ (unsigned long)ioaddr->status_addr,
+ (unsigned long)ioaddr->command_addr,
+ (unsigned long)dp->dma_mode,
+ (unsigned long)dp->mstr_piospd,
+ (unsigned long)dp->slave_piospd,
+ (unsigned long)dp->eightb_piospd,
(unsigned long)dp->pci66mhz);
}
-#endif
static int atp867x_set_priv(struct ata_port *ap)
{
@@ -370,8 +369,7 @@ static void atp867x_fixup(struct ata_host *host)
if (v < 0x80) {
v = 0x80;
pci_write_config_byte(pdev, PCI_LATENCY_TIMER, v);
- printk(KERN_DEBUG "ATP867X: set latency timer of device %s"
- " to %d\n", pci_name(pdev), v);
+ dev_dbg(&pdev->dev, "ATP867X: set latency timer to %d\n", v);
}
/*
@@ -419,13 +417,11 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host)
return rc;
host->iomap = pcim_iomap_table(pdev);
-#ifdef ATP867X_DEBUG
atp867x_check_res(pdev);
for (i = 0; i < PCI_STD_NUM_BARS; i++)
- printk(KERN_DEBUG "ATP867X: iomap[%d]=0x%llx\n", i,
- (unsigned long long)(host->iomap[i]));
-#endif
+ dev_dbg(gdev, "ATP867X: iomap[%d]=0x%p\n", i,
+ host->iomap[i]);
/*
* request, iomap BARs and init port addresses accordingly
@@ -444,9 +440,8 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host)
if (rc)
return rc;
-#ifdef ATP867X_DEBUG
atp867x_check_ports(ap, i);
-#endif
+
ata_port_desc(ap, "cmd 0x%lx ctl 0x%lx",
(unsigned long)ioaddr->cmd_addr,
(unsigned long)ioaddr->ctl_addr);
@@ -486,7 +481,7 @@ static int atp867x_init_one(struct pci_dev *pdev,
if (rc)
return rc;
- printk(KERN_INFO "ATP867X: ATP867 ATA UDMA133 controller (rev %02X)",
+ dev_info(&pdev->dev, "ATP867X: ATP867 ATA UDMA133 controller (rev %02X)",
pdev->device);
host = ata_host_alloc_pinfo(&pdev->dev, ppi, ATP867X_NUM_PORTS);
diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c
index d0bcabb..1a3372a 100644
--- a/drivers/ata/pata_cmd640.c
+++ b/drivers/ata/pata_cmd640.c
@@ -61,7 +61,7 @@ static void cmd640_set_piomode(struct ata_port *ap, struct ata_device *adev)
struct ata_device *pair = ata_dev_pair(adev);
if (ata_timing_compute(adev, adev->pio_mode, &t, T, 0) < 0) {
- printk(KERN_ERR DRV_NAME ": mode computation failed.\n");
+ ata_dev_err(adev, DRV_NAME ": mode computation failed.\n");
return;
}
diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c
index 1d74d89..5baa4a7 100644
--- a/drivers/ata/pata_cmd64x.c
+++ b/drivers/ata/pata_cmd64x.c
@@ -116,7 +116,7 @@ static void cmd64x_set_timing(struct ata_port *ap, struct ata_device *adev, u8 m
/* ata_timing_compute is smart and will produce timings for MWDMA
that don't violate the drives PIO capabilities. */
if (ata_timing_compute(adev, mode, &t, T, 0) < 0) {
- printk(KERN_ERR DRV_NAME ": mode computation failed.\n");
+ ata_dev_err(adev, DRV_NAME ": mode computation failed.\n");
return;
}
if (ap->port_no) {
@@ -130,7 +130,7 @@ static void cmd64x_set_timing(struct ata_port *ap, struct ata_device *adev, u8 m
}
}
- printk(KERN_DEBUG DRV_NAME ": active %d recovery %d setup %d.\n",
+ ata_dev_dbg(adev, DRV_NAME ": active %d recovery %d setup %d.\n",
t.active, t.recover, t.setup);
if (t.recover > 16) {
t.active += t.recover - 16;
diff --git a/drivers/ata/pata_cs5520.c b/drivers/ata/pata_cs5520.c
index 247c147..24ce866 100644
--- a/drivers/ata/pata_cs5520.c
+++ b/drivers/ata/pata_cs5520.c
@@ -153,12 +153,12 @@ static int cs5520_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
/* Perform set up for DMA */
if (pci_enable_device_io(pdev)) {
- printk(KERN_ERR DRV_NAME ": unable to configure BAR2.\n");
+ dev_err(&pdev->dev, "unable to configure BAR2.\n");
return -ENODEV;
}
if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) {
- printk(KERN_ERR DRV_NAME ": unable to configure DMA mask.\n");
+ dev_err(&pdev->dev, "unable to configure DMA mask.\n");
return -ENODEV;
}
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index 760ac6e..ab47aeb 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -263,12 +263,12 @@ static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id)
ppi[1] = &ata_dummy_port_info;
if (use_msr)
- printk(KERN_ERR DRV_NAME ": Using MSR regs instead of PCI\n");
+ dev_err(&dev->dev, DRV_NAME ": Using MSR regs instead of PCI\n");
cs5536_read(dev, CFG, &cfg);
if ((cfg & IDE_CFG_CHANEN) == 0) {
- printk(KERN_ERR DRV_NAME ": disabled by BIOS\n");
+ dev_err(&dev->dev, DRV_NAME ": disabled by BIOS\n");
return -ENODEV;
}
diff --git a/drivers/ata/pata_cypress.c b/drivers/ata/pata_cypress.c
index 5b3a7a8..3be5d52 100644
--- a/drivers/ata/pata_cypress.c
+++ b/drivers/ata/pata_cypress.c
@@ -62,7 +62,7 @@ static void cy82c693_set_piomode(struct ata_port *ap, struct ata_device *adev)
u32 addr;
if (ata_timing_compute(adev, adev->pio_mode, &t, T, 1) < 0) {
- printk(KERN_ERR DRV_NAME ": mome computation failed.\n");
+ ata_dev_err(adev, DRV_NAME ": mome computation failed.\n");
return;
}
diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c
index 46208ec..b78f71c 100644
--- a/drivers/ata/pata_ep93xx.c
+++ b/drivers/ata/pata_ep93xx.c
@@ -855,7 +855,6 @@ static void ep93xx_pata_drain_fifo(struct ata_queued_cmd *qc)
&& count < 65536; count += 2)
ep93xx_pata_read_reg(drv_data, IDECTRL_ADDR_DATA);
- /* Can become DEBUG later */
if (count)
ata_port_dbg(ap, "drained %d bytes to clear DRQ.\n", count);
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index 06b7c4a..778c893 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -14,9 +14,6 @@
* TODO
* Look into engine reset on timeout errors. Should not be required.
*/
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
@@ -183,7 +180,7 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr,
i = match_string(list, -1, model_num);
if (i >= 0) {
- pr_warn("%s is not supported for %s\n", modestr, list[i]);
+ ata_dev_warn(dev, "%s is not supported for %s\n", modestr, list[i]);
return 1;
}
return 0;
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index f242157..7abc7e0 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -14,9 +14,6 @@
* TODO
* Look into engine reset on timeout errors. Should not be required.
*/
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
@@ -231,7 +228,8 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr,
i = match_string(list, -1, model_num);
if (i >= 0) {
- pr_warn("%s is not supported for %s\n", modestr, list[i]);
+ ata_dev_warn(dev, "%s is not supported for %s\n",
+ modestr, list[i]);
return 1;
}
return 0;
@@ -864,7 +862,8 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
chip_table = &hpt372;
break;
default:
- pr_err("Unknown HPT366 subtype, please report (%d)\n",
+ dev_err(&dev->dev,
+ "Unknown HPT366 subtype, please report (%d)\n",
rev);
return -ENODEV;
}
@@ -905,7 +904,8 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
*ppi = &info_hpt374_fn1;
break;
default:
- pr_err("PCI table is bogus, please report (%d)\n", dev->device);
+ dev_err(&dev->dev, "PCI table is bogus, please report (%d)\n",
+ dev->device);
return -ENODEV;
}
/* Ok so this is a chip we support */
@@ -953,7 +953,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
u8 sr;
u32 total = 0;
- pr_warn("BIOS has not set timing clocks\n");
+ dev_warn(&dev->dev, "BIOS has not set timing clocks\n");
/* This is the process the HPT371 BIOS is reported to use */
for (i = 0; i < 128; i++) {
@@ -1009,7 +1009,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
(f_high << 16) | f_low | 0x100);
}
if (adjust == 8) {
- pr_err("DPLL did not stabilize!\n");
+ dev_err(&dev->dev, "DPLL did not stabilize!\n");
return -ENODEV;
}
if (dpll == 3)
@@ -1017,7 +1017,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
else
private_data = (void *)hpt37x_timings_50;
- pr_info("bus clock %dMHz, using %dMHz DPLL\n",
+ dev_info(&dev->dev, "bus clock %dMHz, using %dMHz DPLL\n",
MHz[clock_slot], MHz[dpll]);
} else {
private_data = (void *)chip_table->clocks[clock_slot];
@@ -1032,7 +1032,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
if (clock_slot < 2 && ppi[0] == &info_hpt370a)
ppi[0] = &info_hpt370a_33;
- pr_info("%s using %dMHz bus clock\n",
+ dev_info(&dev->dev, "%s using %dMHz bus clock\n",
chip_table->name, MHz[clock_slot]);
}
diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c
index 48eef33..1d9d4ee 100644
--- a/drivers/ata/pata_hpt3x2n.c
+++ b/drivers/ata/pata_hpt3x2n.c
@@ -15,9 +15,6 @@
* TODO
* Work out best PLL policy
*/
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
@@ -420,7 +417,7 @@ static int hpt3x2n_pci_clock(struct pci_dev *pdev)
u16 sr;
u32 total = 0;
- pr_warn("BIOS clock data not set\n");
+ dev_warn(&pdev->dev, "BIOS clock data not set\n");
/* This is the process the HPT371 BIOS is reported to use */
for (i = 0; i < 128; i++) {
@@ -530,7 +527,8 @@ static int hpt3x2n_init_one(struct pci_dev *dev, const struct pci_device_id *id)
ppi[0] = &info_hpt372n;
break;
default:
- pr_err("PCI table is bogus, please report (%d)\n", dev->device);
+ dev_err(&dev->dev,"PCI table is bogus, please report (%d)\n",
+ dev->device);
return -ENODEV;
}
@@ -579,11 +577,11 @@ static int hpt3x2n_init_one(struct pci_dev *dev, const struct pci_device_id *id)
pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low);
}
if (adjust == 8) {
- pr_err("DPLL did not stabilize!\n");
+ dev_err(&dev->dev, "DPLL did not stabilize!\n");
return -ENODEV;
}
- pr_info("bus clock %dMHz, using 66MHz DPLL\n", pci_mhz);
+ dev_info(&dev->dev, "bus clock %dMHz, using 66MHz DPLL\n", pci_mhz);
/*
* Set our private data up. We only need a few flags
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index 0e22659..8a5b4e0 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -431,7 +431,8 @@ static unsigned int it821x_smart_qc_issue(struct ata_queued_cmd *qc)
case ATA_CMD_SET_FEATURES:
return ata_bmdma_qc_issue(qc);
}
- printk(KERN_DEBUG "it821x: can't process command 0x%02X\n", qc->tf.command);
+ ata_dev_dbg(qc->dev, "it821x: can't process command 0x%02X\n",
+ qc->tf.command);
return AC_ERR_DEV;
}
@@ -507,12 +508,14 @@ static void it821x_dev_config(struct ata_device *adev)
if (strstr(model_num, "Integrated Technology Express")) {
/* RAID mode */
- ata_dev_info(adev, "%sRAID%d volume",
- adev->id[147] ? "Bootable " : "",
- adev->id[129]);
- if (adev->id[129] != 1)
- pr_cont("(%dK stripe)", adev->id[146]);
- pr_cont("\n");
+ if (adev->id[129] == 1)
+ ata_dev_info(adev, "%sRAID%d volume\n",
+ adev->id[147] ? "Bootable " : "",
+ adev->id[129]);
+ else
+ ata_dev_info(adev, "%sRAID%d volume (%dK stripe)\n",
+ adev->id[147] ? "Bootable " : "",
+ adev->id[129], adev->id[146]);
}
/* This is a controller firmware triggered funny, don't
report the drive faulty! */
@@ -534,7 +537,7 @@ static void it821x_dev_config(struct ata_device *adev)
*/
static unsigned int it821x_read_id(struct ata_device *adev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
unsigned int err_mask;
unsigned char model_num[ATA_ID_PROD_LEN + 1];
@@ -542,21 +545,20 @@ static unsigned int it821x_read_id(struct ata_device *adev,
err_mask = ata_do_dev_read_id(adev, tf, id);
if (err_mask)
return err_mask;
- ata_id_c_string(id, model_num, ATA_ID_PROD, sizeof(model_num));
+ ata_id_c_string((u16 *)id, model_num, ATA_ID_PROD, sizeof(model_num));
- id[83] &= ~(1 << 12); /* Cache flush is firmware handled */
- id[83] &= ~(1 << 13); /* Ditto for LBA48 flushes */
- id[84] &= ~(1 << 6); /* No FUA */
- id[85] &= ~(1 << 10); /* No HPA */
- id[76] = 0; /* No NCQ/AN etc */
+ id[83] &= cpu_to_le16(~(1 << 12)); /* Cache flush is firmware handled */
+ id[84] &= cpu_to_le16(~(1 << 6)); /* No FUA */
+ id[85] &= cpu_to_le16(~(1 << 10)); /* No HPA */
+ id[76] = 0; /* No NCQ/AN etc */
if (strstr(model_num, "Integrated Technology Express")) {
/* Set feature bits the firmware neglects */
- id[49] |= 0x0300; /* LBA, DMA */
- id[83] &= 0x7FFF;
- id[83] |= 0x4400; /* Word 83 is valid and LBA48 */
- id[86] |= 0x0400; /* LBA48 on */
- id[ATA_ID_MAJOR_VER] |= 0x1F;
+ id[49] |= cpu_to_le16(0x0300); /* LBA, DMA */
+ id[83] &= cpu_to_le16(0x7FFF);
+ id[83] |= cpu_to_le16(0x4400); /* Word 83 is valid and LBA48 */
+ id[86] |= cpu_to_le16(0x0400); /* LBA48 on */
+ id[ATA_ID_MAJOR_VER] |= cpu_to_le16(0x1F);
/* Clear the serial number because it's different each boot
which breaks validation on resume */
memset(&id[ATA_ID_SERNO], 0x20, ATA_ID_SERNO_LEN);
@@ -593,6 +595,7 @@ static int it821x_check_atapi_dma(struct ata_queued_cmd *qc)
/**
* it821x_display_disk - display disk setup
+ * @ap: ATA port
* @n: Device number
* @buf: Buffer block from firmware
*
@@ -600,7 +603,7 @@ static int it821x_check_atapi_dma(struct ata_queued_cmd *qc)
* by the firmware.
*/
-static void it821x_display_disk(int n, u8 *buf)
+static void it821x_display_disk(struct ata_port *ap, int n, u8 *buf)
{
unsigned char id[41];
int mode = 0;
@@ -633,13 +636,13 @@ static void it821x_display_disk(int n, u8 *buf)
else
strcpy(mbuf, "PIO");
if (buf[52] == 4)
- printk(KERN_INFO "%d: %-6s %-8s %s %s\n",
+ ata_port_info(ap, "%d: %-6s %-8s %s %s\n",
n, mbuf, types[buf[52]], id, cbl);
else
- printk(KERN_INFO "%d: %-6s %-8s Volume: %1d %s %s\n",
+ ata_port_info(ap, "%d: %-6s %-8s Volume: %1d %s %s\n",
n, mbuf, types[buf[52]], buf[53], id, cbl);
if (buf[125] < 100)
- printk(KERN_INFO "%d: Rebuilding: %d%%\n", n, buf[125]);
+ ata_port_info(ap, "%d: Rebuilding: %d%%\n", n, buf[125]);
}
/**
@@ -676,7 +679,7 @@ static u8 *it821x_firmware_command(struct ata_port *ap, u8 cmd, int len)
status = ioread8(ap->ioaddr.status_addr);
if (status & ATA_ERR) {
kfree(buf);
- printk(KERN_ERR "it821x_firmware_command: rejected\n");
+ ata_port_err(ap, "%s: rejected\n", __func__);
return NULL;
}
if (status & ATA_DRQ) {
@@ -686,7 +689,7 @@ static u8 *it821x_firmware_command(struct ata_port *ap, u8 cmd, int len)
usleep_range(500, 1000);
}
kfree(buf);
- printk(KERN_ERR "it821x_firmware_command: timeout\n");
+ ata_port_err(ap, "%s: timeout\n", __func__);
return NULL;
}
@@ -709,13 +712,13 @@ static void it821x_probe_firmware(struct ata_port *ap)
buf = it821x_firmware_command(ap, 0xFA, 512);
if (buf != NULL) {
- printk(KERN_INFO "pata_it821x: Firmware %02X/%02X/%02X%02X\n",
+ ata_port_info(ap, "pata_it821x: Firmware %02X/%02X/%02X%02X\n",
buf[505],
buf[506],
buf[507],
buf[508]);
for (i = 0; i < 4; i++)
- it821x_display_disk(i, buf + 128 * i);
+ it821x_display_disk(ap, i, buf + 128 * i);
kfree(buf);
}
}
@@ -771,7 +774,8 @@ static int it821x_port_start(struct ata_port *ap)
itdev->timing10 = 1;
/* Need to disable ATAPI DMA for this case */
if (!itdev->smart)
- printk(KERN_WARNING DRV_NAME": Revision 0x10, workarounds activated.\n");
+ dev_warn(&pdev->dev,
+ "Revision 0x10, workarounds activated.\n");
}
return 0;
@@ -919,14 +923,14 @@ static int it821x_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
} else {
/* Force the card into bypass mode if so requested */
if (it8212_noraid) {
- printk(KERN_INFO DRV_NAME ": forcing bypass mode.\n");
+ dev_info(&pdev->dev, "forcing bypass mode.\n");
it821x_disable_raid(pdev);
}
pci_read_config_byte(pdev, 0x50, &conf);
conf &= 1;
- printk(KERN_INFO DRV_NAME": controller in %s mode.\n",
- mode[conf]);
+ dev_info(&pdev->dev, "controller in %s mode.\n", mode[conf]);
+
if (conf == 0)
ppi[0] = &info_passthru;
else
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
index 99c6308..17b557c 100644
--- a/drivers/ata/pata_ixp4xx_cf.c
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -114,7 +114,7 @@ static void ixp4xx_set_piomode(struct ata_port *ap, struct ata_device *adev)
{
struct ixp4xx_pata *ixpp = ap->host->private_data;
- ata_dev_printk(adev, KERN_INFO, "configured for PIO%d 8bit\n",
+ ata_dev_info(adev, "configured for PIO%d 8bit\n",
adev->pio_mode - XFER_PIO_0);
ixp4xx_set_8bit_timing(ixpp, adev->pio_mode);
}
@@ -132,8 +132,8 @@ static unsigned int ixp4xx_mmio_data_xfer(struct ata_queued_cmd *qc,
struct ixp4xx_pata *ixpp = ap->host->private_data;
unsigned long flags;
- ata_dev_printk(adev, KERN_DEBUG, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE",
- buflen);
+ ata_dev_dbg(adev, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE",
+ buflen);
spin_lock_irqsave(ap->lock, flags);
/* set the expansion bus in 16bit mode and restore
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index 361597d..0c5a519 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -32,7 +32,6 @@
static int marvell_pata_active(struct pci_dev *pdev)
{
- int i;
u32 devices;
void __iomem *barp;
@@ -44,11 +43,6 @@ static int marvell_pata_active(struct pci_dev *pdev)
if (barp == NULL)
return -ENOMEM;
- printk("BAR5:");
- for(i = 0; i <= 0x0F; i++)
- printk("%02X:%02X ", i, ioread8(barp + i));
- printk("\n");
-
devices = ioread32(barp + 0x0C);
pci_iounmap(pdev, barp);
@@ -149,7 +143,8 @@ static int marvell_init_one (struct pci_dev *pdev, const struct pci_device_id *i
#if IS_ENABLED(CONFIG_SATA_AHCI)
if (!marvell_pata_active(pdev)) {
- printk(KERN_INFO DRV_NAME ": PATA port not active, deferring to AHCI driver.\n");
+ dev_info(&pdev->dev,
+ "PATA port not active, deferring to AHCI driver.\n");
return -ENODEV;
}
#endif
diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
index a7ecc1a..06929e7 100644
--- a/drivers/ata/pata_netcell.c
+++ b/drivers/ata/pata_netcell.c
@@ -21,12 +21,13 @@
/* No PIO or DMA methods needed for this device */
static unsigned int netcell_read_id(struct ata_device *adev,
- struct ata_taskfile *tf, u16 *id)
+ struct ata_taskfile *tf, __le16 *id)
{
unsigned int err_mask = ata_do_dev_read_id(adev, tf, id);
+
/* Firmware forgets to mark words 85-87 valid */
if (err_mask == 0)
- id[ATA_ID_CSF_DEFAULT] |= 0x4000;
+ id[ATA_ID_CSF_DEFAULT] |= cpu_to_le16(0x4000);
return err_mask;
}
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index b5a3f71..05c2ab3 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -19,7 +19,7 @@
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include <scsi/scsi_host.h>
-
+#include <trace/events/libata.h>
#include <asm/byteorder.h>
#include <asm/octeon/octeon.h>
@@ -73,16 +73,12 @@ MODULE_PARM_DESC(enable_dma,
*/
static unsigned int ns_to_tim_reg(unsigned int tim_mult, unsigned int nsecs)
{
- unsigned int val;
-
/*
* Compute # of eclock periods to get desired duration in
* nanoseconds.
*/
- val = DIV_ROUND_UP(nsecs * (octeon_get_io_clock_rate() / 1000000),
+ return DIV_ROUND_UP(nsecs * (octeon_get_io_clock_rate() / 1000000),
1000 * tim_mult);
-
- return val;
}
static void octeon_cf_set_boot_reg_cfg(int cs, unsigned int multiplier)
@@ -273,9 +269,9 @@ static void octeon_cf_set_dmamode(struct ata_port *ap, struct ata_device *dev)
dma_tim.s.we_n = ns_to_tim_reg(tim_mult, oe_n);
dma_tim.s.we_a = ns_to_tim_reg(tim_mult, oe_a);
- pr_debug("ns to ticks (mult %d) of %d is: %d\n", tim_mult, 60,
+ ata_dev_dbg(dev, "ns to ticks (mult %d) of %d is: %d\n", tim_mult, 60,
ns_to_tim_reg(tim_mult, 60));
- pr_debug("oe_n: %d, oe_a: %d, dmack_s: %d, dmack_h: %d, dmarq: %d, pause: %d\n",
+ ata_dev_dbg(dev, "oe_n: %d, oe_a: %d, dmack_s: %d, dmack_h: %d, dmarq: %d, pause: %d\n",
dma_tim.s.oe_n, dma_tim.s.oe_a, dma_tim.s.dmack_s,
dma_tim.s.dmack_h, dma_tim.s.dmarq, dma_tim.s.pause);
@@ -440,7 +436,6 @@ static int octeon_cf_softreset16(struct ata_link *link, unsigned int *classes,
int rc;
u8 err;
- DPRINTK("about to softreset\n");
__raw_writew(ap->ctl, base + 0xe);
udelay(20);
__raw_writew(ap->ctl | ATA_SRST, base + 0xe);
@@ -455,7 +450,6 @@ static int octeon_cf_softreset16(struct ata_link *link, unsigned int *classes,
/* determine by signature whether we have ATA or ATAPI devices */
classes[0] = ata_sff_dev_classify(&link->device[0], 1, &err);
- DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]);
return 0;
}
@@ -479,23 +473,11 @@ static void octeon_cf_tf_load16(struct ata_port *ap,
__raw_writew(tf->hob_feature << 8, base + 0xc);
__raw_writew(tf->hob_nsect | tf->hob_lbal << 8, base + 2);
__raw_writew(tf->hob_lbam | tf->hob_lbah << 8, base + 4);
- VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->hob_feature,
- tf->hob_nsect,
- tf->hob_lbal,
- tf->hob_lbam,
- tf->hob_lbah);
}
if (is_addr) {
__raw_writew(tf->feature << 8, base + 0xc);
__raw_writew(tf->nsect | tf->lbal << 8, base + 2);
__raw_writew(tf->lbam | tf->lbah << 8, base + 4);
- VPRINTK("feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->feature,
- tf->nsect,
- tf->lbal,
- tf->lbam,
- tf->lbah);
}
ata_wait_idle(ap);
}
@@ -516,20 +498,14 @@ static void octeon_cf_exec_command16(struct ata_port *ap,
{
/* The base of the registers is at ioaddr.data_addr. */
void __iomem *base = ap->ioaddr.data_addr;
- u16 blob;
+ u16 blob = 0;
- if (tf->flags & ATA_TFLAG_DEVICE) {
- VPRINTK("device 0x%X\n", tf->device);
+ if (tf->flags & ATA_TFLAG_DEVICE)
blob = tf->device;
- } else {
- blob = 0;
- }
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
blob |= (tf->command << 8);
__raw_writew(blob, base + 6);
-
ata_wait_idle(ap);
}
@@ -543,12 +519,10 @@ static void octeon_cf_dma_setup(struct ata_queued_cmd *qc)
struct octeon_cf_port *cf_port;
cf_port = ap->private_data;
- DPRINTK("ENTER\n");
/* issue r/w command */
qc->cursg = qc->sg;
cf_port->dma_finished = 0;
ap->ops->sff_exec_command(ap, &qc->tf);
- DPRINTK("EXIT\n");
}
/**
@@ -563,8 +537,6 @@ static void octeon_cf_dma_start(struct ata_queued_cmd *qc)
union cvmx_mio_boot_dma_intx mio_boot_dma_int;
struct scatterlist *sg;
- VPRINTK("%d scatterlists\n", qc->n_elem);
-
/* Get the scatter list entry we need to DMA into */
sg = qc->cursg;
BUG_ON(!sg);
@@ -605,10 +577,6 @@ static void octeon_cf_dma_start(struct ata_queued_cmd *qc)
mio_boot_dma_cfg.s.adr = sg_dma_address(sg);
- VPRINTK("%s %d bytes address=%p\n",
- (mio_boot_dma_cfg.s.rw) ? "write" : "read", sg->length,
- (void *)(unsigned long)mio_boot_dma_cfg.s.adr);
-
cvmx_write_csr(cf_port->dma_base + DMA_CFG, mio_boot_dma_cfg.u64);
}
@@ -627,9 +595,7 @@ static unsigned int octeon_cf_dma_finished(struct ata_port *ap,
union cvmx_mio_boot_dma_intx dma_int;
u8 status;
- VPRINTK("ata%u: protocol %d task_state %d\n",
- ap->print_id, qc->tf.protocol, ap->hsm_task_state);
-
+ trace_ata_bmdma_stop(ap, &qc->tf, qc->tag);
if (ap->hsm_task_state != HSM_ST_LAST)
return 0;
@@ -678,7 +644,6 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance)
spin_lock_irqsave(&host->lock, flags);
- DPRINTK("ENTER\n");
for (i = 0; i < host->n_ports; i++) {
u8 status;
struct ata_port *ap;
@@ -701,6 +666,7 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance)
if (!sg_is_last(qc->cursg)) {
qc->cursg = sg_next(qc->cursg);
handled = 1;
+ trace_ata_bmdma_start(ap, &qc->tf, qc->tag);
octeon_cf_dma_start(qc);
continue;
} else {
@@ -732,7 +698,6 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance)
}
}
spin_unlock_irqrestore(&host->lock, flags);
- DPRINTK("EXIT\n");
return IRQ_RETVAL(handled);
}
@@ -800,8 +765,11 @@ static unsigned int octeon_cf_qc_issue(struct ata_queued_cmd *qc)
case ATA_PROT_DMA:
WARN_ON(qc->tf.flags & ATA_TFLAG_POLLING);
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */
+ trace_ata_bmdma_setup(ap, &qc->tf, qc->tag);
octeon_cf_dma_setup(qc); /* set up dma */
+ trace_ata_bmdma_start(ap, &qc->tf, qc->tag);
octeon_cf_dma_start(qc); /* initiate dma */
ap->hsm_task_state = HSM_ST_LAST;
break;
diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
index 35aa158..c3a40b7 100644
--- a/drivers/ata/pata_of_platform.c
+++ b/drivers/ata/pata_of_platform.c
@@ -25,11 +25,12 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
struct device_node *dn = ofdev->dev.of_node;
struct resource io_res;
struct resource ctl_res;
- struct resource *irq_res;
+ struct resource irq_res;
unsigned int reg_shift = 0;
int pio_mode = 0;
int pio_mask;
bool use16bit;
+ int irq;
ret = of_address_to_resource(dn, 0, &io_res);
if (ret) {
@@ -45,7 +46,15 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
return -EINVAL;
}
- irq_res = platform_get_resource(ofdev, IORESOURCE_IRQ, 0);
+ memset(&irq_res, 0, sizeof(irq_res));
+
+ irq = platform_get_irq_optional(ofdev, 0);
+ if (irq < 0 && irq != -ENXIO)
+ return irq;
+ if (irq > 0) {
+ irq_res.start = irq;
+ irq_res.end = irq;
+ }
of_property_read_u32(dn, "reg-shift", ®_shift);
@@ -63,7 +72,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
pio_mask = 1 << pio_mode;
pio_mask |= (1 << pio_mode) - 1;
- return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq_res,
+ return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq > 0 ? &irq_res : NULL,
reg_shift, pio_mask, &pata_platform_sht,
use16bit);
}
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index effc1a0..4fbb3ee 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -30,13 +30,6 @@
#define DRV_NAME "pata_pdc2027x"
#define DRV_VERSION "1.0"
-#undef PDC_DEBUG
-
-#ifdef PDC_DEBUG
-#define PDPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args)
-#else
-#define PDPRINTK(fmt, args...)
-#endif
enum {
PDC_MMIO_BAR = 5,
@@ -214,11 +207,11 @@ static int pdc2027x_cable_detect(struct ata_port *ap)
if (cgcr & (1 << 26))
goto cbl40;
- PDPRINTK("No cable or 80-conductor cable on port %d\n", ap->port_no);
+ ata_port_dbg(ap, "No cable or 80-conductor cable\n");
return ATA_CBL_PATA80;
cbl40:
- printk(KERN_INFO DRV_NAME ": 40-conductor cable detected on port %d\n", ap->port_no);
+ ata_port_info(ap, DRV_NAME ":40-conductor cable detected\n");
return ATA_CBL_PATA40;
}
@@ -292,17 +285,17 @@ static void pdc2027x_set_piomode(struct ata_port *ap, struct ata_device *adev)
unsigned int pio = adev->pio_mode - XFER_PIO_0;
u32 ctcr0, ctcr1;
- PDPRINTK("adev->pio_mode[%X]\n", adev->pio_mode);
+ ata_port_dbg(ap, "adev->pio_mode[%X]\n", adev->pio_mode);
/* Sanity check */
if (pio > 4) {
- printk(KERN_ERR DRV_NAME ": Unknown pio mode [%d] ignored\n", pio);
+ ata_port_err(ap, "Unknown pio mode [%d] ignored\n", pio);
return;
}
/* Set the PIO timing registers using value table for 133MHz */
- PDPRINTK("Set pio regs... \n");
+ ata_port_dbg(ap, "Set pio regs... \n");
ctcr0 = ioread32(dev_mmio(ap, adev, PDC_CTCR0));
ctcr0 &= 0xffff0000;
@@ -315,9 +308,7 @@ static void pdc2027x_set_piomode(struct ata_port *ap, struct ata_device *adev)
ctcr1 |= (pdc2027x_pio_timing_tbl[pio].value2 << 24);
iowrite32(ctcr1, dev_mmio(ap, adev, PDC_CTCR1));
- PDPRINTK("Set pio regs done\n");
-
- PDPRINTK("Set to pio mode[%u] \n", pio);
+ ata_port_dbg(ap, "Set to pio mode[%u] \n", pio);
}
/**
@@ -350,7 +341,7 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev)
iowrite32(ctcr1 & ~(1 << 7), dev_mmio(ap, adev, PDC_CTCR1));
}
- PDPRINTK("Set udma regs... \n");
+ ata_port_dbg(ap, "Set udma regs... \n");
ctcr1 = ioread32(dev_mmio(ap, adev, PDC_CTCR1));
ctcr1 &= 0xff000000;
@@ -359,16 +350,14 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev)
(pdc2027x_udma_timing_tbl[udma_mode].value2 << 16);
iowrite32(ctcr1, dev_mmio(ap, adev, PDC_CTCR1));
- PDPRINTK("Set udma regs done\n");
-
- PDPRINTK("Set to udma mode[%u] \n", udma_mode);
+ ata_port_dbg(ap, "Set to udma mode[%u] \n", udma_mode);
} else if ((dma_mode >= XFER_MW_DMA_0) &&
(dma_mode <= XFER_MW_DMA_2)) {
/* Set the MDMA timing registers with value table for 133MHz */
unsigned int mdma_mode = dma_mode & 0x07;
- PDPRINTK("Set mdma regs... \n");
+ ata_port_dbg(ap, "Set mdma regs... \n");
ctcr0 = ioread32(dev_mmio(ap, adev, PDC_CTCR0));
ctcr0 &= 0x0000ffff;
@@ -376,11 +365,10 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev)
(pdc2027x_mdma_timing_tbl[mdma_mode].value1 << 24);
iowrite32(ctcr0, dev_mmio(ap, adev, PDC_CTCR0));
- PDPRINTK("Set mdma regs done\n");
- PDPRINTK("Set to mdma mode[%u] \n", mdma_mode);
+ ata_port_dbg(ap, "Set to mdma mode[%u] \n", mdma_mode);
} else {
- printk(KERN_ERR DRV_NAME ": Unknown dma mode [%u] ignored\n", dma_mode);
+ ata_port_err(ap, "Unknown dma mode [%u] ignored\n", dma_mode);
}
}
@@ -414,7 +402,7 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed
ctcr1 |= (1 << 25);
iowrite32(ctcr1, dev_mmio(ap, dev, PDC_CTCR1));
- PDPRINTK("Turn on prefetch\n");
+ ata_dev_dbg(dev, "Turn on prefetch\n");
} else {
pdc2027x_set_dmamode(ap, dev);
}
@@ -485,8 +473,8 @@ static long pdc_read_counter(struct ata_host *host)
counter = (bccrh << 15) | bccrl;
- PDPRINTK("bccrh [%X] bccrl [%X]\n", bccrh, bccrl);
- PDPRINTK("bccrhv[%X] bccrlv[%X]\n", bccrhv, bccrlv);
+ dev_dbg(host->dev, "bccrh [%X] bccrl [%X]\n", bccrh, bccrl);
+ dev_dbg(host->dev, "bccrhv[%X] bccrlv[%X]\n", bccrhv, bccrlv);
/*
* The 30-bit decreasing counter are read by 2 pieces.
@@ -495,7 +483,7 @@ static long pdc_read_counter(struct ata_host *host)
*/
if (retry && !(bccrh == bccrhv && bccrl >= bccrlv)) {
retry--;
- PDPRINTK("rereading counter\n");
+ dev_dbg(host->dev, "rereading counter\n");
goto retry;
}
@@ -520,20 +508,19 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b
/* Sanity check */
if (unlikely(pll_clock_khz < 5000L || pll_clock_khz > 70000L)) {
- printk(KERN_ERR DRV_NAME ": Invalid PLL input clock %ldkHz, give up!\n", pll_clock_khz);
+ dev_err(host->dev, "Invalid PLL input clock %ldkHz, give up!\n",
+ pll_clock_khz);
return;
}
-#ifdef PDC_DEBUG
- PDPRINTK("pout_required is %ld\n", pout_required);
+ dev_dbg(host->dev, "pout_required is %ld\n", pout_required);
/* Show the current clock value of PLL control register
* (maybe already configured by the firmware)
*/
pll_ctl = ioread16(mmio_base + PDC_PLL_CTL);
- PDPRINTK("pll_ctl[%X]\n", pll_ctl);
-#endif
+ dev_dbg(host->dev, "pll_ctl[%X]\n", pll_ctl);
/*
* Calculate the ratio of F, R and OD
@@ -552,7 +539,7 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b
R = 0x00;
} else {
/* Invalid ratio */
- printk(KERN_ERR DRV_NAME ": Invalid ratio %ld, give up!\n", ratio);
+ dev_err(host->dev, "Invalid ratio %ld, give up!\n", ratio);
return;
}
@@ -560,15 +547,15 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b
if (unlikely(F < 0 || F > 127)) {
/* Invalid F */
- printk(KERN_ERR DRV_NAME ": F[%d] invalid!\n", F);
+ dev_err(host->dev, "F[%d] invalid!\n", F);
return;
}
- PDPRINTK("F[%d] R[%d] ratio*1000[%ld]\n", F, R, ratio);
+ dev_dbg(host->dev, "F[%d] R[%d] ratio*1000[%ld]\n", F, R, ratio);
pll_ctl = (R << 8) | F;
- PDPRINTK("Writing pll_ctl[%X]\n", pll_ctl);
+ dev_dbg(host->dev, "Writing pll_ctl[%X]\n", pll_ctl);
iowrite16(pll_ctl, mmio_base + PDC_PLL_CTL);
ioread16(mmio_base + PDC_PLL_CTL); /* flush */
@@ -576,15 +563,13 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b
/* Wait the PLL circuit to be stable */
msleep(30);
-#ifdef PDC_DEBUG
/*
* Show the current clock value of PLL control register
* (maybe configured by the firmware)
*/
pll_ctl = ioread16(mmio_base + PDC_PLL_CTL);
- PDPRINTK("pll_ctl[%X]\n", pll_ctl);
-#endif
+ dev_dbg(host->dev, "pll_ctl[%X]\n", pll_ctl);
return;
}
@@ -605,7 +590,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host)
/* Start the test mode */
scr = ioread32(mmio_base + PDC_SYS_CTL);
- PDPRINTK("scr[%X]\n", scr);
+ dev_dbg(host->dev, "scr[%X]\n", scr);
iowrite32(scr | (0x01 << 14), mmio_base + PDC_SYS_CTL);
ioread32(mmio_base + PDC_SYS_CTL); /* flush */
@@ -622,7 +607,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host)
/* Stop the test mode */
scr = ioread32(mmio_base + PDC_SYS_CTL);
- PDPRINTK("scr[%X]\n", scr);
+ dev_dbg(host->dev, "scr[%X]\n", scr);
iowrite32(scr & ~(0x01 << 14), mmio_base + PDC_SYS_CTL);
ioread32(mmio_base + PDC_SYS_CTL); /* flush */
@@ -632,8 +617,8 @@ static long pdc_detect_pll_input_clock(struct ata_host *host)
pll_clock = ((start_count - end_count) & 0x3fffffff) / 100 *
(100000000 / usec_elapsed);
- PDPRINTK("start[%ld] end[%ld] \n", start_count, end_count);
- PDPRINTK("PLL input clock[%ld]Hz\n", pll_clock);
+ dev_dbg(host->dev, "start[%ld] end[%ld] PLL input clock[%ld]HZ\n",
+ start_count, end_count, pll_clock);
return pll_clock;
}
diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c
index 0c5cbcd..b998490 100644
--- a/drivers/ata/pata_pdc202xx_old.c
+++ b/drivers/ata/pata_pdc202xx_old.c
@@ -38,8 +38,6 @@ static int pdc2026x_cable_detect(struct ata_port *ap)
static void pdc202xx_exec_command(struct ata_port *ap,
const struct ata_taskfile *tf)
{
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
-
iowrite8(tf->command, ap->ioaddr.command_addr);
ndelay(400);
}
diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c
index 3722a67..fb00c3e 100644
--- a/drivers/ata/pata_rz1000.c
+++ b/drivers/ata/pata_rz1000.c
@@ -69,7 +69,7 @@ static int rz1000_fifo_disable(struct pci_dev *pdev)
reg &= 0xDFFF;
if (pci_write_config_word(pdev, 0x40, reg) != 0)
return -1;
- printk(KERN_INFO DRV_NAME ": disabled chipset readahead.\n");
+ dev_info(&pdev->dev, "disabled chipset readahead.\n");
return 0;
}
@@ -97,7 +97,7 @@ static int rz1000_init_one (struct pci_dev *pdev, const struct pci_device_id *en
if (rz1000_fifo_disable(pdev) == 0)
return ata_pci_sff_init_one(pdev, ppi, &rz1000_sht, NULL, 0);
- printk(KERN_ERR DRV_NAME ": failed to disable read-ahead on chipset..\n");
+ dev_err(&pdev->dev, "failed to disable read-ahead on chipset.\n");
/* Not safe to use so skip */
return -ENODEV;
}
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index b602e30..e410fe4 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -286,13 +286,13 @@ static int serverworks_fixup_osb4(struct pci_dev *pdev)
pci_read_config_dword(isa_dev, 0x64, ®);
reg &= ~0x00002000; /* disable 600ns interrupt mask */
if (!(reg & 0x00004000))
- printk(KERN_DEBUG DRV_NAME ": UDMA not BIOS enabled.\n");
+ dev_info(&pdev->dev, "UDMA not BIOS enabled.\n");
reg |= 0x00004000; /* enable UDMA/33 support */
pci_write_config_dword(isa_dev, 0x64, reg);
pci_dev_put(isa_dev);
return 0;
}
- printk(KERN_WARNING DRV_NAME ": Unable to find bridge.\n");
+ dev_warn(&pdev->dev, "Unable to find bridge.\n");
return -ENODEV;
}
diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c
index 43215a6..0da58ce 100644
--- a/drivers/ata/pata_sil680.c
+++ b/drivers/ata/pata_sil680.c
@@ -212,7 +212,6 @@ static void sil680_set_dmamode(struct ata_port *ap, struct ata_device *adev)
static void sil680_sff_exec_command(struct ata_port *ap,
const struct ata_taskfile *tf)
{
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
iowrite8(tf->command, ap->ioaddr.command_addr);
ioread8(ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
}
@@ -309,17 +308,17 @@ static u8 sil680_init_chip(struct pci_dev *pdev, int *try_mmio)
switch (tmpbyte & 0x30) {
case 0x00:
- printk(KERN_INFO "sil680: 100MHz clock.\n");
+ dev_info(&pdev->dev, "sil680: 100MHz clock.\n");
break;
case 0x10:
- printk(KERN_INFO "sil680: 133MHz clock.\n");
+ dev_info(&pdev->dev, "sil680: 133MHz clock.\n");
break;
case 0x20:
- printk(KERN_INFO "sil680: Using PCI clock.\n");
+ dev_info(&pdev->dev, "sil680: Using PCI clock.\n");
break;
/* This last case is _NOT_ ok */
case 0x30:
- printk(KERN_ERR "sil680: Clock disabled ?\n");
+ dev_err(&pdev->dev, "sil680: Clock disabled ?\n");
}
return tmpbyte & 0x30;
}
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 4750320..439ca88 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -414,12 +414,6 @@ static void via_tf_load(struct ata_port *ap, const struct ata_taskfile *tf)
iowrite8(tf->hob_lbal, ioaddr->lbal_addr);
iowrite8(tf->hob_lbam, ioaddr->lbam_addr);
iowrite8(tf->hob_lbah, ioaddr->lbah_addr);
- VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->hob_feature,
- tf->hob_nsect,
- tf->hob_lbal,
- tf->hob_lbam,
- tf->hob_lbah);
}
if (is_addr) {
@@ -428,12 +422,6 @@ static void via_tf_load(struct ata_port *ap, const struct ata_taskfile *tf)
iowrite8(tf->lbal, ioaddr->lbal_addr);
iowrite8(tf->lbam, ioaddr->lbam_addr);
iowrite8(tf->lbah, ioaddr->lbah_addr);
- VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n",
- tf->feature,
- tf->nsect,
- tf->lbal,
- tf->lbam,
- tf->lbah);
}
ata_wait_idle(ap);
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index 5db55e1..35b823a 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -284,9 +284,6 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
*(__le32 *)(buf + i) =
(pFLAGS & pEND) ? 0 : cpu_to_le32(pp->pkt_dma + i + 4);
i += 4;
-
- VPRINTK("PRD[%u] = (0x%lX, 0x%X)\n", i/4,
- (unsigned long)addr, len);
}
if (likely(last_buf))
@@ -302,8 +299,6 @@ static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
u32 pkt_dma = (u32)pp->pkt_dma;
int i = 0;
- VPRINTK("ENTER\n");
-
adma_enter_reg_mode(qc->ap);
if (qc->tf.protocol != ATA_PROT_DMA)
return AC_ERR_OK;
@@ -355,22 +350,6 @@ static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
i = adma_fill_sg(qc);
wmb(); /* flush PRDs and pkt to memory */
-#if 0
- /* dump out CPB + PRDs for debug */
- {
- int j, len = 0;
- static char obuf[2048];
- for (j = 0; j < i; ++j) {
- len += sprintf(obuf+len, "%02x ", buf[j]);
- if ((j & 7) == 7) {
- printk("%s\n", obuf);
- len = 0;
- }
- }
- if (len)
- printk("%s\n", obuf);
- }
-#endif
return AC_ERR_OK;
}
@@ -379,8 +358,6 @@ static inline void adma_packet_start(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
void __iomem *chan = ADMA_PORT_REGS(ap);
- VPRINTK("ENTER, ap %p\n", ap);
-
/* fire up the ADMA engine */
writew(aPIOMD4 | aGO, chan + ADMA_CONTROL);
}
@@ -475,8 +452,6 @@ static inline unsigned int adma_intr_mmio(struct ata_host *host)
u8 status = ata_sff_check_status(ap);
if ((status & ATA_BUSY))
continue;
- DPRINTK("ata%u: protocol %d (dev_stat 0x%X)\n",
- ap->print_id, qc->tf.protocol, status);
/* complete taskfile transaction */
pp->state = adma_state_idle;
@@ -504,14 +479,10 @@ static irqreturn_t adma_intr(int irq, void *dev_instance)
struct ata_host *host = dev_instance;
unsigned int handled = 0;
- VPRINTK("ENTER\n");
-
spin_lock(&host->lock);
handled = adma_intr_pkt(host) | adma_intr_mmio(host);
spin_unlock(&host->lock);
- VPRINTK("EXIT\n");
-
return IRQ_RETVAL(handled);
}
@@ -547,8 +518,8 @@ static int adma_port_start(struct ata_port *ap)
return -ENOMEM;
/* paranoia? */
if ((pp->pkt_dma & 7) != 0) {
- printk(KERN_ERR "bad alignment for pp->pkt_dma: %08x\n",
- (u32)pp->pkt_dma);
+ ata_port_err(ap, "bad alignment for pp->pkt_dma: %08x\n",
+ (u32)pp->pkt_dma);
return -ENOMEM;
}
ap->private_data = pp;
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 338c2e5..bec33d7 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -14,15 +14,6 @@
* COPYRIGHT (C) 2005 SYNOPSYS, INC. ALL RIGHTS RESERVED
*/
-#ifdef CONFIG_SATA_DWC_DEBUG
-#define DEBUG
-#endif
-
-#ifdef CONFIG_SATA_DWC_VDEBUG
-#define VERBOSE_DEBUG
-#define DEBUG_NCQ
-#endif
-
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/device.h>
@@ -34,6 +25,7 @@
#include <linux/phy/phy.h>
#include <linux/libata.h>
#include <linux/slab.h>
+#include <trace/events/libata.h>
#include "libata.h"
@@ -182,10 +174,8 @@ enum {
* Prototypes
*/
static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag);
-static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc,
- u32 check_status);
-static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status);
-static void sata_dwc_port_stop(struct ata_port *ap);
+static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc);
+static void sata_dwc_dma_xfer_complete(struct ata_port *ap);
static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag);
#ifdef CONFIG_SATA_DWC_OLD_DMA
@@ -215,9 +205,10 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp)
{
struct sata_dwc_device *hsdev = hsdevp->hsdev;
struct dw_dma_slave *dws = &sata_dwc_dma_dws;
+ struct device *dev = hsdev->dev;
dma_cap_mask_t mask;
- dws->dma_dev = hsdev->dev;
+ dws->dma_dev = dev;
dma_cap_zero(mask);
dma_cap_set(DMA_SLAVE, mask);
@@ -225,8 +216,7 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp)
/* Acquire DMA channel */
hsdevp->chan = dma_request_channel(mask, sata_dwc_dma_filter, hsdevp);
if (!hsdevp->chan) {
- dev_err(hsdev->dev, "%s: dma channel unavailable\n",
- __func__);
+ dev_err(dev, "%s: dma channel unavailable\n", __func__);
return -EAGAIN;
}
@@ -236,26 +226,25 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp)
static int sata_dwc_dma_init_old(struct platform_device *pdev,
struct sata_dwc_device *hsdev)
{
- struct device_node *np = pdev->dev.of_node;
- struct resource *res;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
- hsdev->dma = devm_kzalloc(&pdev->dev, sizeof(*hsdev->dma), GFP_KERNEL);
+ hsdev->dma = devm_kzalloc(dev, sizeof(*hsdev->dma), GFP_KERNEL);
if (!hsdev->dma)
return -ENOMEM;
- hsdev->dma->dev = &pdev->dev;
+ hsdev->dma->dev = dev;
hsdev->dma->id = pdev->id;
/* Get SATA DMA interrupt number */
hsdev->dma->irq = irq_of_parse_and_map(np, 1);
if (hsdev->dma->irq == NO_IRQ) {
- dev_err(&pdev->dev, "no SATA DMA irq\n");
+ dev_err(dev, "no SATA DMA irq\n");
return -ENODEV;
}
/* Get physical SATA DMA register base address */
- res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- hsdev->dma->regs = devm_ioremap_resource(&pdev->dev, res);
+ hsdev->dma->regs = devm_platform_ioremap_resource(pdev, 1);
if (IS_ERR(hsdev->dma->regs))
return PTR_ERR(hsdev->dma->regs);
@@ -297,35 +286,6 @@ static const char *get_prot_descript(u8 protocol)
}
}
-static const char *get_dma_dir_descript(int dma_dir)
-{
- switch ((enum dma_data_direction)dma_dir) {
- case DMA_BIDIRECTIONAL:
- return "bidirectional";
- case DMA_TO_DEVICE:
- return "to device";
- case DMA_FROM_DEVICE:
- return "from device";
- default:
- return "none";
- }
-}
-
-static void sata_dwc_tf_dump(struct ata_port *ap, struct ata_taskfile *tf)
-{
- dev_vdbg(ap->dev,
- "taskfile cmd: 0x%02x protocol: %s flags: 0x%lx device: %x\n",
- tf->command, get_prot_descript(tf->protocol), tf->flags,
- tf->device);
- dev_vdbg(ap->dev,
- "feature: 0x%02x nsect: 0x%x lbal: 0x%x lbam: 0x%x lbah: 0x%x\n",
- tf->feature, tf->nsect, tf->lbal, tf->lbam, tf->lbah);
- dev_vdbg(ap->dev,
- "hob_feature: 0x%02x hob_nsect: 0x%x hob_lbal: 0x%x hob_lbam: 0x%x hob_lbah: 0x%x\n",
- tf->hob_feature, tf->hob_nsect, tf->hob_lbal, tf->hob_lbam,
- tf->hob_lbah);
-}
-
static void dma_dwc_xfer_done(void *hsdev_instance)
{
unsigned long flags;
@@ -355,7 +315,7 @@ static void dma_dwc_xfer_done(void *hsdev_instance)
}
if ((hsdevp->dma_interrupt_count % 2) == 0)
- sata_dwc_dma_xfer_complete(ap, 1);
+ sata_dwc_dma_xfer_complete(ap);
spin_unlock_irqrestore(&host->lock, flags);
}
@@ -553,6 +513,7 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance)
* active tag. It is the tag that matches the command about to
* be completed.
*/
+ trace_ata_bmdma_start(ap, &qc->tf, tag);
qc->ap->link.active_tag = tag;
sata_dwc_bmdma_start_by_tag(qc, tag);
@@ -586,7 +547,7 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance)
if (status & ATA_ERR) {
dev_dbg(ap->dev, "interrupt ATA_ERR (0x%x)\n", status);
- sata_dwc_qc_complete(ap, qc, 1);
+ sata_dwc_qc_complete(ap, qc);
handled = 1;
goto DONE;
}
@@ -611,13 +572,13 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance)
}
if ((hsdevp->dma_interrupt_count % 2) == 0)
- sata_dwc_dma_xfer_complete(ap, 1);
+ sata_dwc_dma_xfer_complete(ap);
} else if (ata_is_pio(qc->tf.protocol)) {
ata_sff_hsm_move(ap, qc, status, 0);
handled = 1;
goto DONE;
} else {
- if (unlikely(sata_dwc_qc_complete(ap, qc, 1)))
+ if (unlikely(sata_dwc_qc_complete(ap, qc)))
goto DRVSTILLBUSY;
}
@@ -677,7 +638,7 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance)
if (status & ATA_ERR) {
dev_dbg(ap->dev, "%s ATA_ERR (0x%x)\n", __func__,
status);
- sata_dwc_qc_complete(ap, qc, 1);
+ sata_dwc_qc_complete(ap, qc);
handled = 1;
goto DONE;
}
@@ -692,9 +653,9 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance)
dev_warn(ap->dev, "%s: DMA not pending?\n",
__func__);
if ((hsdevp->dma_interrupt_count % 2) == 0)
- sata_dwc_dma_xfer_complete(ap, 1);
+ sata_dwc_dma_xfer_complete(ap);
} else {
- if (unlikely(sata_dwc_qc_complete(ap, qc, 1)))
+ if (unlikely(sata_dwc_qc_complete(ap, qc)))
goto STILLBUSY;
}
continue;
@@ -749,7 +710,7 @@ static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag)
}
}
-static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status)
+static void sata_dwc_dma_xfer_complete(struct ata_port *ap)
{
struct ata_queued_cmd *qc;
struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
@@ -763,17 +724,6 @@ static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status)
return;
}
-#ifdef DEBUG_NCQ
- if (tag > 0) {
- dev_info(ap->dev,
- "%s tag=%u cmd=0x%02x dma dir=%s proto=%s dmacr=0x%08x\n",
- __func__, qc->hw_tag, qc->tf.command,
- get_dma_dir_descript(qc->dma_dir),
- get_prot_descript(qc->tf.protocol),
- sata_dwc_readl(&hsdev->sata_dwc_regs->dmacr));
- }
-#endif
-
if (ata_is_dma(qc->tf.protocol)) {
if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_NONE) {
dev_err(ap->dev,
@@ -783,15 +733,14 @@ static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status)
}
hsdevp->dma_pending[tag] = SATA_DWC_DMA_PENDING_NONE;
- sata_dwc_qc_complete(ap, qc, check_status);
+ sata_dwc_qc_complete(ap, qc);
ap->link.active_tag = ATA_TAG_POISON;
} else {
- sata_dwc_qc_complete(ap, qc, check_status);
+ sata_dwc_qc_complete(ap, qc);
}
}
-static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc,
- u32 check_status)
+static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc)
{
u8 status = 0;
u32 mask = 0x0;
@@ -799,7 +748,6 @@ static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc,
struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap);
struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
hsdev->sactive_queued = 0;
- dev_dbg(ap->dev, "%s checkstatus? %x\n", __func__, check_status);
if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_TX)
dev_err(ap->dev, "TX DMA PENDING\n");
@@ -980,9 +928,6 @@ static void sata_dwc_exec_command_by_tag(struct ata_port *ap,
{
struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
- dev_dbg(ap->dev, "%s cmd(0x%02x): %s tag=%d\n", __func__, tf->command,
- ata_get_cmd_descript(tf->command), tag);
-
hsdevp->cmd_issued[tag] = cmd_issued;
/*
@@ -1005,12 +950,9 @@ static void sata_dwc_bmdma_setup(struct ata_queued_cmd *qc)
{
u8 tag = qc->hw_tag;
- if (ata_is_ncq(qc->tf.protocol)) {
- dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n",
- __func__, qc->ap->link.sactive, tag);
- } else {
+ if (!ata_is_ncq(qc->tf.protocol))
tag = 0;
- }
+
sata_dwc_bmdma_setup_by_tag(qc, tag);
}
@@ -1037,12 +979,6 @@ static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag)
start_dma = 0;
}
- dev_dbg(ap->dev,
- "%s qc=%p tag: %x cmd: 0x%02x dma_dir: %s start_dma? %x\n",
- __func__, qc, tag, qc->tf.command,
- get_dma_dir_descript(qc->dma_dir), start_dma);
- sata_dwc_tf_dump(ap, &qc->tf);
-
if (start_dma) {
sata_dwc_scr_read(&ap->link, SCR_ERROR, ®);
if (reg & SATA_DWC_SERROR_ERR_BITS) {
@@ -1067,13 +1003,9 @@ static void sata_dwc_bmdma_start(struct ata_queued_cmd *qc)
{
u8 tag = qc->hw_tag;
- if (ata_is_ncq(qc->tf.protocol)) {
- dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n",
- __func__, qc->ap->link.sactive, tag);
- } else {
+ if (!ata_is_ncq(qc->tf.protocol))
tag = 0;
- }
- dev_dbg(qc->ap->dev, "%s\n", __func__);
+
sata_dwc_bmdma_start_by_tag(qc, tag);
}
@@ -1084,16 +1016,6 @@ static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
-#ifdef DEBUG_NCQ
- if (qc->hw_tag > 0 || ap->link.sactive > 1)
- dev_info(ap->dev,
- "%s ap id=%d cmd(0x%02x)=%s qc tag=%d prot=%s ap active_tag=0x%08x ap sactive=0x%08x\n",
- __func__, ap->print_id, qc->tf.command,
- ata_get_cmd_descript(qc->tf.command),
- qc->hw_tag, get_prot_descript(qc->tf.protocol),
- ap->link.active_tag, ap->link.sactive);
-#endif
-
if (!ata_is_ncq(qc->tf.protocol))
tag = 0;
@@ -1110,11 +1032,9 @@ static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc)
sactive |= (0x00000001 << tag);
sata_dwc_scr_write(&ap->link, SCR_ACTIVE, sactive);
- dev_dbg(qc->ap->dev,
- "%s: tag=%d ap->link.sactive = 0x%08x sactive=0x%08x\n",
- __func__, tag, qc->ap->link.sactive, sactive);
-
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf);
+ trace_ata_exec_command(ap, &qc->tf, tag);
sata_dwc_exec_command_by_tag(ap, &qc->tf, tag,
SATA_DWC_CMD_ISSUED_PEND);
} else {
@@ -1207,6 +1127,8 @@ static const struct ata_port_info sata_dwc_port_info[] = {
static int sata_dwc_probe(struct platform_device *ofdev)
{
+ struct device *dev = &ofdev->dev;
+ struct device_node *np = dev->of_node;
struct sata_dwc_device *hsdev;
u32 idr, versionr;
char *ver = (char *)&versionr;
@@ -1216,23 +1138,21 @@ static int sata_dwc_probe(struct platform_device *ofdev)
struct ata_host *host;
struct ata_port_info pi = sata_dwc_port_info[0];
const struct ata_port_info *ppi[] = { &pi, NULL };
- struct device_node *np = ofdev->dev.of_node;
struct resource *res;
/* Allocate DWC SATA device */
- host = ata_host_alloc_pinfo(&ofdev->dev, ppi, SATA_DWC_MAX_PORTS);
- hsdev = devm_kzalloc(&ofdev->dev, sizeof(*hsdev), GFP_KERNEL);
+ host = ata_host_alloc_pinfo(dev, ppi, SATA_DWC_MAX_PORTS);
+ hsdev = devm_kzalloc(dev, sizeof(*hsdev), GFP_KERNEL);
if (!host || !hsdev)
return -ENOMEM;
host->private_data = hsdev;
/* Ioremap SATA registers */
- res = platform_get_resource(ofdev, IORESOURCE_MEM, 0);
- base = devm_ioremap_resource(&ofdev->dev, res);
+ base = devm_platform_get_and_ioremap_resource(ofdev, 0, &res);
if (IS_ERR(base))
return PTR_ERR(base);
- dev_dbg(&ofdev->dev, "ioremap done for SATA register address\n");
+ dev_dbg(dev, "ioremap done for SATA register address\n");
/* Synopsys DWC SATA specific Registers */
hsdev->sata_dwc_regs = base + SATA_DWC_REG_OFFSET;
@@ -1246,11 +1166,10 @@ static int sata_dwc_probe(struct platform_device *ofdev)
/* Read the ID and Version Registers */
idr = sata_dwc_readl(&hsdev->sata_dwc_regs->idr);
versionr = sata_dwc_readl(&hsdev->sata_dwc_regs->versionr);
- dev_notice(&ofdev->dev, "id %d, controller version %c.%c%c\n",
- idr, ver[0], ver[1], ver[2]);
+ dev_notice(dev, "id %d, controller version %c.%c%c\n", idr, ver[0], ver[1], ver[2]);
/* Save dev for later use in dev_xxx() routines */
- hsdev->dev = &ofdev->dev;
+ hsdev->dev = dev;
/* Enable SATA Interrupts */
sata_dwc_enable_interrupts(hsdev);
@@ -1258,7 +1177,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
/* Get SATA interrupt number */
irq = irq_of_parse_and_map(np, 0);
if (irq == NO_IRQ) {
- dev_err(&ofdev->dev, "no SATA DMA irq\n");
+ dev_err(dev, "no SATA DMA irq\n");
return -ENODEV;
}
@@ -1270,7 +1189,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
}
#endif
- hsdev->phy = devm_phy_optional_get(hsdev->dev, "sata-phy");
+ hsdev->phy = devm_phy_optional_get(dev, "sata-phy");
if (IS_ERR(hsdev->phy))
return PTR_ERR(hsdev->phy);
@@ -1285,7 +1204,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
*/
err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
if (err)
- dev_err(&ofdev->dev, "failed to activate host");
+ dev_err(dev, "failed to activate host");
return 0;
@@ -1309,7 +1228,7 @@ static int sata_dwc_remove(struct platform_device *ofdev)
sata_dwc_dma_exit_old(hsdev);
#endif
- dev_dbg(&ofdev->dev, "done\n");
+ dev_dbg(dev, "done\n");
return 0;
}
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 3b31a4f..da01521 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -221,10 +221,10 @@ enum {
* 4 Dwords per command slot, command header size == 64 Dwords.
*/
struct cmdhdr_tbl_entry {
- u32 cda;
- u32 prde_fis_len;
- u32 ttl;
- u32 desc_info;
+ __le32 cda;
+ __le32 prde_fis_len;
+ __le32 ttl;
+ __le32 desc_info;
};
/*
@@ -246,8 +246,10 @@ enum {
struct command_desc {
u8 cfis[8 * 4];
u8 sfis[8 * 4];
- u8 acmd[4 * 4];
- u8 fill[4 * 4];
+ struct_group(cdb,
+ u8 acmd[4 * 4];
+ u8 fill[4 * 4];
+ );
u32 prdt[SATA_FSL_MAX_PRD_DIRECT * 4];
u32 prdt_indirect[(SATA_FSL_MAX_PRD - SATA_FSL_MAX_PRD_DIRECT) * 4];
};
@@ -257,9 +259,9 @@ struct command_desc {
*/
struct prde {
- u32 dba;
+ __le32 dba;
u8 fill[2 * 4];
- u32 ddc_and_ext;
+ __le32 ddc_and_ext;
};
/*
@@ -311,16 +313,16 @@ static void fsl_sata_set_irq_coalescing(struct ata_host *host,
intr_coalescing_ticks = ticks;
spin_unlock_irqrestore(&host->lock, flags);
- DPRINTK("interrupt coalescing, count = 0x%x, ticks = %x\n",
- intr_coalescing_count, intr_coalescing_ticks);
- DPRINTK("ICC register status: (hcr base: %p) = 0x%x\n",
- hcr_base, ioread32(hcr_base + ICC));
+ dev_dbg(host->dev, "interrupt coalescing, count = 0x%x, ticks = %x\n",
+ intr_coalescing_count, intr_coalescing_ticks);
+ dev_dbg(host->dev, "ICC register status: (hcr base: 0x%p) = 0x%x\n",
+ hcr_base, ioread32(hcr_base + ICC));
}
static ssize_t fsl_sata_intr_coalescing_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return sprintf(buf, "%d %d\n",
+ return sysfs_emit(buf, "%d %d\n",
intr_coalescing_count, intr_coalescing_ticks);
}
@@ -355,9 +357,9 @@ static ssize_t fsl_sata_rx_watermark_show(struct device *dev,
spin_lock_irqsave(&host->lock, flags);
rx_watermark = ioread32(csr_base + TRANSCFG);
rx_watermark &= 0x1f;
-
spin_unlock_irqrestore(&host->lock, flags);
- return sprintf(buf, "%d\n", rx_watermark);
+
+ return sysfs_emit(buf, "%d\n", rx_watermark);
}
static ssize_t fsl_sata_rx_watermark_store(struct device *dev,
@@ -385,25 +387,27 @@ static ssize_t fsl_sata_rx_watermark_store(struct device *dev,
return strlen(buf);
}
-static inline unsigned int sata_fsl_tag(unsigned int tag,
+static inline unsigned int sata_fsl_tag(struct ata_port *ap,
+ unsigned int tag,
void __iomem *hcr_base)
{
/* We let libATA core do actual (queue) tag allocation */
if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) {
- DPRINTK("tag %d invalid : out of range\n", tag);
+ ata_port_dbg(ap, "tag %d invalid : out of range\n", tag);
return 0;
}
if (unlikely((ioread32(hcr_base + CQ)) & (1 << tag))) {
- DPRINTK("tag %d invalid : in use!!\n", tag);
+ ata_port_dbg(ap, "tag %d invalid : in use!!\n", tag);
return 0;
}
return tag;
}
-static void sata_fsl_setup_cmd_hdr_entry(struct sata_fsl_port_priv *pp,
+static void sata_fsl_setup_cmd_hdr_entry(struct ata_port *ap,
+ struct sata_fsl_port_priv *pp,
unsigned int tag, u32 desc_info,
u32 data_xfer_len, u8 num_prde,
u8 fis_len)
@@ -421,11 +425,11 @@ static void sata_fsl_setup_cmd_hdr_entry(struct sata_fsl_port_priv *pp,
pp->cmdslot[tag].ttl = cpu_to_le32(data_xfer_len & ~0x03);
pp->cmdslot[tag].desc_info = cpu_to_le32(desc_info | (tag & 0x1F));
- VPRINTK("cda=0x%x, prde_fis_len=0x%x, ttl=0x%x, di=0x%x\n",
- pp->cmdslot[tag].cda,
- pp->cmdslot[tag].prde_fis_len,
- pp->cmdslot[tag].ttl, pp->cmdslot[tag].desc_info);
-
+ ata_port_dbg(ap, "cda=0x%x, prde_fis_len=0x%x, ttl=0x%x, di=0x%x\n",
+ le32_to_cpu(pp->cmdslot[tag].cda),
+ le32_to_cpu(pp->cmdslot[tag].prde_fis_len),
+ le32_to_cpu(pp->cmdslot[tag].ttl),
+ le32_to_cpu(pp->cmdslot[tag].desc_info));
}
static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
@@ -447,8 +451,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
dma_addr_t indirect_ext_segment_paddr;
unsigned int si;
- VPRINTK("SATA FSL : cd = 0x%p, prd = 0x%p\n", cmd_desc, prd);
-
indirect_ext_segment_paddr = cmd_desc_paddr +
SATA_FSL_CMD_DESC_OFFSET_TO_PRDT + SATA_FSL_MAX_PRD_DIRECT * 16;
@@ -456,9 +458,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
dma_addr_t sg_addr = sg_dma_address(sg);
u32 sg_len = sg_dma_len(sg);
- VPRINTK("SATA FSL : fill_sg, sg_addr = 0x%llx, sg_len = %d\n",
- (unsigned long long)sg_addr, sg_len);
-
/* warn if each s/g element is not dword aligned */
if (unlikely(sg_addr & 0x03))
ata_port_err(qc->ap, "s/g addr unaligned : 0x%llx\n",
@@ -469,7 +468,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
if (num_prde == (SATA_FSL_MAX_PRD_DIRECT - 1) &&
sg_next(sg) != NULL) {
- VPRINTK("setting indirect prde\n");
prd_ptr_to_indirect_ext = prd;
prd->dba = cpu_to_le32(indirect_ext_segment_paddr);
indirect_ext_segment_sz = 0;
@@ -481,9 +479,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
prd->dba = cpu_to_le32(sg_addr);
prd->ddc_and_ext = cpu_to_le32(data_snoop | (sg_len & ~0x03));
- VPRINTK("sg_fill, ttl=%d, dba=0x%x, ddc=0x%x\n",
- ttl_dwords, prd->dba, prd->ddc_and_ext);
-
++num_prde;
++prd;
if (prd_ptr_to_indirect_ext)
@@ -508,7 +503,7 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
struct sata_fsl_port_priv *pp = ap->private_data;
struct sata_fsl_host_priv *host_priv = ap->host->private_data;
void __iomem *hcr_base = host_priv->hcr_base;
- unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
+ unsigned int tag = sata_fsl_tag(ap, qc->hw_tag, hcr_base);
struct command_desc *cd;
u32 desc_info = CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE;
u32 num_prde = 0;
@@ -520,19 +515,11 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, (u8 *) &cd->cfis);
- VPRINTK("Dumping cfis : 0x%x, 0x%x, 0x%x\n",
- cd->cfis[0], cd->cfis[1], cd->cfis[2]);
-
- if (qc->tf.protocol == ATA_PROT_NCQ) {
- VPRINTK("FPDMA xfer,Sctor cnt[0:7],[8:15] = %d,%d\n",
- cd->cfis[3], cd->cfis[11]);
- }
-
/* setup "ACMD - atapi command" in cmd. desc. if this is ATAPI cmd */
if (ata_is_atapi(qc->tf.protocol)) {
desc_info |= ATAPI_CMD;
- memset((void *)&cd->acmd, 0, 32);
- memcpy((void *)&cd->acmd, qc->cdb, qc->dev->cdb_len);
+ memset(&cd->cdb, 0, sizeof(cd->cdb));
+ memcpy(&cd->cdb, qc->cdb, qc->dev->cdb_len);
}
if (qc->flags & ATA_QCFLAG_DMAMAP)
@@ -543,10 +530,10 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
if (qc->tf.protocol == ATA_PROT_NCQ)
desc_info |= FPDMA_QUEUED_CMD;
- sata_fsl_setup_cmd_hdr_entry(pp, tag, desc_info, ttl_dwords,
+ sata_fsl_setup_cmd_hdr_entry(ap, pp, tag, desc_info, ttl_dwords,
num_prde, 5);
- VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n",
+ ata_port_dbg(ap, "SATA FSL : di = 0x%x, ttl = %d, num_prde = %d\n",
desc_info, ttl_dwords, num_prde);
return AC_ERR_OK;
@@ -557,9 +544,9 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
struct sata_fsl_host_priv *host_priv = ap->host->private_data;
void __iomem *hcr_base = host_priv->hcr_base;
- unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
+ unsigned int tag = sata_fsl_tag(ap, qc->hw_tag, hcr_base);
- VPRINTK("xx_qc_issue called,CQ=0x%x,CA=0x%x,CE=0x%x,CC=0x%x\n",
+ ata_port_dbg(ap, "CQ=0x%x,CA=0x%x,CE=0x%x,CC=0x%x\n",
ioread32(CQ + hcr_base),
ioread32(CA + hcr_base),
ioread32(CE + hcr_base), ioread32(CC + hcr_base));
@@ -569,10 +556,10 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
/* Simply queue command to the controller/device */
iowrite32(1 << tag, CQ + hcr_base);
- VPRINTK("xx_qc_issue called, tag=%d, CQ=0x%x, CA=0x%x\n",
+ ata_port_dbg(ap, "tag=%d, CQ=0x%x, CA=0x%x\n",
tag, ioread32(CQ + hcr_base), ioread32(CA + hcr_base));
- VPRINTK("CE=0x%x, DE=0x%x, CC=0x%x, CmdStat = 0x%x\n",
+ ata_port_dbg(ap, "CE=0x%x, DE=0x%x, CC=0x%x, CmdStat = 0x%x\n",
ioread32(CE + hcr_base),
ioread32(DE + hcr_base),
ioread32(CC + hcr_base),
@@ -586,7 +573,7 @@ static bool sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc)
struct sata_fsl_port_priv *pp = qc->ap->private_data;
struct sata_fsl_host_priv *host_priv = qc->ap->host->private_data;
void __iomem *hcr_base = host_priv->hcr_base;
- unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
+ unsigned int tag = sata_fsl_tag(qc->ap, qc->hw_tag, hcr_base);
struct command_desc *cd;
cd = pp->cmdentry + tag;
@@ -613,7 +600,7 @@ static int sata_fsl_scr_write(struct ata_link *link,
return -EINVAL;
}
- VPRINTK("xx_scr_write, reg_in = %d\n", sc_reg);
+ ata_link_dbg(link, "reg_in = %d\n", sc_reg);
iowrite32(val, ssr_base + (sc_reg * 4));
return 0;
@@ -637,7 +624,7 @@ static int sata_fsl_scr_read(struct ata_link *link,
return -EINVAL;
}
- VPRINTK("xx_scr_read, reg_in = %d\n", sc_reg);
+ ata_link_dbg(link, "reg_in = %d\n", sc_reg);
*val = ioread32(ssr_base + (sc_reg * 4));
return 0;
@@ -649,18 +636,18 @@ static void sata_fsl_freeze(struct ata_port *ap)
void __iomem *hcr_base = host_priv->hcr_base;
u32 temp;
- VPRINTK("xx_freeze, CQ=0x%x, CA=0x%x, CE=0x%x, DE=0x%x\n",
+ ata_port_dbg(ap, "CQ=0x%x, CA=0x%x, CE=0x%x, DE=0x%x\n",
ioread32(CQ + hcr_base),
ioread32(CA + hcr_base),
ioread32(CE + hcr_base), ioread32(DE + hcr_base));
- VPRINTK("CmdStat = 0x%x\n",
+ ata_port_dbg(ap, "CmdStat = 0x%x\n",
ioread32(host_priv->csr_base + COMMANDSTAT));
/* disable interrupts on the controller/port */
temp = ioread32(hcr_base + HCONTROL);
iowrite32((temp & ~0x3F), hcr_base + HCONTROL);
- VPRINTK("in xx_freeze : HControl = 0x%x, HStatus = 0x%x\n",
+ ata_port_dbg(ap, "HControl = 0x%x, HStatus = 0x%x\n",
ioread32(hcr_base + HCONTROL), ioread32(hcr_base + HSTATUS));
}
@@ -673,7 +660,7 @@ static void sata_fsl_thaw(struct ata_port *ap)
/* ack. any pending IRQs for this controller/port */
temp = ioread32(hcr_base + HSTATUS);
- VPRINTK("xx_thaw, pending IRQs = 0x%x\n", (temp & 0x3F));
+ ata_port_dbg(ap, "pending IRQs = 0x%x\n", (temp & 0x3F));
if (temp & 0x3F)
iowrite32((temp & 0x3F), hcr_base + HSTATUS);
@@ -682,7 +669,7 @@ static void sata_fsl_thaw(struct ata_port *ap)
temp = ioread32(hcr_base + HCONTROL);
iowrite32((temp | DEFAULT_PORT_IRQ_ENABLE_MASK), hcr_base + HCONTROL);
- VPRINTK("xx_thaw : HControl = 0x%x, HStatus = 0x%x\n",
+ ata_port_dbg(ap, "HControl = 0x%x, HStatus = 0x%x\n",
ioread32(hcr_base + HCONTROL), ioread32(hcr_base + HSTATUS));
}
@@ -744,8 +731,9 @@ static int sata_fsl_port_start(struct ata_port *ap)
ap->private_data = pp;
- VPRINTK("CHBA = 0x%x, cmdentry_phys = 0x%x\n",
- pp->cmdslot_paddr, pp->cmdentry_paddr);
+ ata_port_dbg(ap, "CHBA = 0x%lx, cmdentry_phys = 0x%lx\n",
+ (unsigned long)pp->cmdslot_paddr,
+ (unsigned long)pp->cmdentry_paddr);
/* Now, update the CHBA register in host controller cmd register set */
iowrite32(pp->cmdslot_paddr & 0xffffffff, hcr_base + CHBA);
@@ -761,9 +749,9 @@ static int sata_fsl_port_start(struct ata_port *ap)
temp = ioread32(hcr_base + HCONTROL);
iowrite32((temp | HCONTROL_ONLINE_PHY_RST), hcr_base + HCONTROL);
- VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
- VPRINTK("CHBA = 0x%x\n", ioread32(hcr_base + CHBA));
+ ata_port_dbg(ap, "HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
+ ata_port_dbg(ap, "HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
+ ata_port_dbg(ap, "CHBA = 0x%x\n", ioread32(hcr_base + CHBA));
return 0;
}
@@ -803,16 +791,15 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap)
temp = ioread32(hcr_base + SIGNATURE);
- VPRINTK("raw sig = 0x%x\n", temp);
- VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
+ ata_port_dbg(ap, "HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
+ ata_port_dbg(ap, "HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
tf.lbah = (temp >> 24) & 0xff;
tf.lbam = (temp >> 16) & 0xff;
tf.lbal = (temp >> 8) & 0xff;
tf.nsect = temp & 0xff;
- return ata_dev_classify(&tf);
+ return ata_port_classify(ap, &tf);
}
static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class,
@@ -825,8 +812,6 @@ static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class,
int i = 0;
unsigned long start_jiffies;
- DPRINTK("in xx_hardreset\n");
-
try_offline_again:
/*
* Force host controller to go off-line, aborting current operations
@@ -852,9 +837,10 @@ static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class,
goto try_offline_again;
}
- DPRINTK("hardreset, controller off-lined\n");
- VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
+ ata_port_dbg(ap, "hardreset, controller off-lined\n"
+ "HStatus = 0x%x HControl = 0x%x\n",
+ ioread32(hcr_base + HSTATUS),
+ ioread32(hcr_base + HCONTROL));
/*
* PHY reset should remain asserted for atleast 1ms
@@ -882,9 +868,10 @@ static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class,
goto err;
}
- DPRINTK("hardreset, controller off-lined & on-lined\n");
- VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
+ ata_port_dbg(ap, "controller off-lined & on-lined\n"
+ "HStatus = 0x%x HControl = 0x%x\n",
+ ioread32(hcr_base + HSTATUS),
+ ioread32(hcr_base + HCONTROL));
/*
* First, wait for the PHYRDY change to occur before waiting for
@@ -941,10 +928,7 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
u8 *cfis;
u32 Serror;
- DPRINTK("in xx_softreset\n");
-
if (ata_link_offline(link)) {
- DPRINTK("PHY reports no device\n");
*class = ATA_DEV_NONE;
return 0;
}
@@ -957,19 +941,17 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
* reached here, we can send a command to the target device
*/
- DPRINTK("Sending SRST/device reset\n");
-
ata_tf_init(link->device, &tf);
cfis = (u8 *) &pp->cmdentry->cfis;
/* device reset/SRST is a control register update FIS, uses tag0 */
- sata_fsl_setup_cmd_hdr_entry(pp, 0,
+ sata_fsl_setup_cmd_hdr_entry(ap, pp, 0,
SRST_CMD | CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE, 0, 0, 5);
tf.ctl |= ATA_SRST; /* setup SRST bit in taskfile control reg */
ata_tf_to_fis(&tf, pmp, 0, cfis);
- DPRINTK("Dumping cfis : 0x%x, 0x%x, 0x%x, 0x%x\n",
+ ata_port_dbg(ap, "Dumping cfis : 0x%x, 0x%x, 0x%x, 0x%x\n",
cfis[0], cfis[1], cfis[2], cfis[3]);
/*
@@ -977,7 +959,7 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
* other commands are active on the controller/device
*/
- DPRINTK("@Softreset, CQ = 0x%x, CA = 0x%x, CC = 0x%x\n",
+ ata_port_dbg(ap, "CQ = 0x%x, CA = 0x%x, CC = 0x%x\n",
ioread32(CQ + hcr_base),
ioread32(CA + hcr_base), ioread32(CC + hcr_base));
@@ -990,15 +972,16 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
if (temp & 0x1) {
ata_port_warn(ap, "ATA_SRST issue failed\n");
- DPRINTK("Softreset@5000,CQ=0x%x,CA=0x%x,CC=0x%x\n",
+ ata_port_dbg(ap, "Softreset@5000,CQ=0x%x,CA=0x%x,CC=0x%x\n",
ioread32(CQ + hcr_base),
ioread32(CA + hcr_base), ioread32(CC + hcr_base));
sata_fsl_scr_read(&ap->link, SCR_ERROR, &Serror);
- DPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- DPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
- DPRINTK("Serror = 0x%x\n", Serror);
+ ata_port_dbg(ap, "HStatus = 0x%x HControl = 0x%x Serror = 0x%x\n",
+ ioread32(hcr_base + HSTATUS),
+ ioread32(hcr_base + HCONTROL),
+ Serror);
goto err;
}
@@ -1012,8 +995,9 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
* using ATA signature D2H register FIS to the host controller.
*/
- sata_fsl_setup_cmd_hdr_entry(pp, 0, CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE,
- 0, 0, 5);
+ sata_fsl_setup_cmd_hdr_entry(ap, pp, 0,
+ CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE,
+ 0, 0, 5);
tf.ctl &= ~ATA_SRST; /* 2nd H2D Ctl. register FIS */
ata_tf_to_fis(&tf, pmp, 0, cfis);
@@ -1030,8 +1014,6 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
*/
iowrite32(0x01, CC + hcr_base); /* We know it will be cmd#0 always */
- DPRINTK("SATA FSL : Now checking device signature\n");
-
*class = ATA_DEV_NONE;
/* Verify if SStatus indicates device presence */
@@ -1045,9 +1027,8 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
*class = sata_fsl_dev_classify(ap);
- DPRINTK("class = %d\n", *class);
- VPRINTK("ccreg = 0x%x\n", ioread32(hcr_base + CC));
- VPRINTK("cereg = 0x%x\n", ioread32(hcr_base + CE));
+ ata_port_dbg(ap, "ccreg = 0x%x\n", ioread32(hcr_base + CC));
+ ata_port_dbg(ap, "cereg = 0x%x\n", ioread32(hcr_base + CE));
}
return 0;
@@ -1058,10 +1039,7 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class,
static void sata_fsl_error_handler(struct ata_port *ap)
{
-
- DPRINTK("in xx_error_handler\n");
sata_pmp_error_handler(ap);
-
}
static void sata_fsl_post_internal_cmd(struct ata_queued_cmd *qc)
@@ -1102,7 +1080,7 @@ static void sata_fsl_error_intr(struct ata_port *ap)
if (unlikely(SError & 0xFFFF0000))
sata_fsl_scr_write(&ap->link, SCR_ERROR, SError);
- DPRINTK("error_intr,hStat=0x%x,CE=0x%x,DE =0x%x,SErr=0x%x\n",
+ ata_port_dbg(ap, "hStat=0x%x,CE=0x%x,DE =0x%x,SErr=0x%x\n",
hstatus, cereg, ioread32(hcr_base + DE), SError);
/* handle fatal errors */
@@ -1119,7 +1097,7 @@ static void sata_fsl_error_intr(struct ata_port *ap)
/* Handle PHYRDY change notification */
if (hstatus & INT_ON_PHYRDY_CHG) {
- DPRINTK("SATA FSL: PHYRDY change indication\n");
+ ata_port_dbg(ap, "PHYRDY change indication\n");
/* Setup a soft-reset EH action */
ata_ehi_hotplugged(ehi);
@@ -1140,7 +1118,7 @@ static void sata_fsl_error_intr(struct ata_port *ap)
*/
abort = 1;
- DPRINTK("single device error, CE=0x%x, DE=0x%x\n",
+ ata_port_dbg(ap, "single device error, CE=0x%x, DE=0x%x\n",
ioread32(hcr_base + CE), ioread32(hcr_base + DE));
/* find out the offending link and qc */
@@ -1245,18 +1223,18 @@ static void sata_fsl_host_intr(struct ata_port *ap)
}
if (unlikely(SError & 0xFFFF0000)) {
- DPRINTK("serror @host_intr : 0x%x\n", SError);
+ ata_port_dbg(ap, "serror @host_intr : 0x%x\n", SError);
sata_fsl_error_intr(ap);
}
if (unlikely(hstatus & status_mask)) {
- DPRINTK("error interrupt!!\n");
+ ata_port_dbg(ap, "error interrupt!!\n");
sata_fsl_error_intr(ap);
return;
}
- VPRINTK("Status of all queues :\n");
- VPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%llx\n",
+ ata_port_dbg(ap, "Status of all queues :\n");
+ ata_port_dbg(ap, "done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%llx\n",
done_mask,
ioread32(hcr_base + CA),
ioread32(hcr_base + CE),
@@ -1268,15 +1246,13 @@ static void sata_fsl_host_intr(struct ata_port *ap)
/* clear CC bit, this will also complete the interrupt */
iowrite32(done_mask, hcr_base + CC);
- DPRINTK("Status of all queues :\n");
- DPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x\n",
+ ata_port_dbg(ap, "Status of all queues: done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x\n",
done_mask, ioread32(hcr_base + CA),
ioread32(hcr_base + CE));
for (i = 0; i < SATA_FSL_QUEUE_DEPTH; i++) {
if (done_mask & (1 << i))
- DPRINTK
- ("completing ncq cmd,tag=%d,CC=0x%x,CA=0x%x\n",
+ ata_port_dbg(ap, "completing ncq cmd,tag=%d,CC=0x%x,CA=0x%x\n",
i, ioread32(hcr_base + CC),
ioread32(hcr_base + CA));
}
@@ -1287,7 +1263,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
iowrite32(1, hcr_base + CC);
qc = ata_qc_from_tag(ap, ATA_TAG_INTERNAL);
- DPRINTK("completing non-ncq cmd, CC=0x%x\n",
+ ata_port_dbg(ap, "completing non-ncq cmd, CC=0x%x\n",
ioread32(hcr_base + CC));
if (qc) {
@@ -1295,7 +1271,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
}
} else {
/* Spurious Interrupt!! */
- DPRINTK("spurious interrupt!!, CC = 0x%x\n",
+ ata_port_dbg(ap, "spurious interrupt!!, CC = 0x%x\n",
ioread32(hcr_base + CC));
iowrite32(done_mask, hcr_base + CC);
return;
@@ -1315,8 +1291,6 @@ static irqreturn_t sata_fsl_interrupt(int irq, void *dev_instance)
interrupt_enables = ioread32(hcr_base + HSTATUS);
interrupt_enables &= 0x3F;
- DPRINTK("interrupt status 0x%x\n", interrupt_enables);
-
if (!interrupt_enables)
return IRQ_NONE;
@@ -1369,7 +1343,7 @@ static int sata_fsl_init_controller(struct ata_host *host)
iowrite32((temp & ~0x3F), hcr_base + HCONTROL);
/* Disable interrupt coalescing control(icc), for the moment */
- DPRINTK("icc = 0x%x\n", ioread32(hcr_base + ICC));
+ dev_dbg(host->dev, "icc = 0x%x\n", ioread32(hcr_base + ICC));
iowrite32(0x01000000, hcr_base + ICC);
/* clear error registers, SError is cleared by libATA */
@@ -1388,8 +1362,8 @@ static int sata_fsl_init_controller(struct ata_host *host)
* callback, that should also initiate the OOB, COMINIT sequence
*/
- DPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS));
- DPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
+ dev_dbg(host->dev, "HStatus = 0x%x HControl = 0x%x\n",
+ ioread32(hcr_base + HSTATUS), ioread32(hcr_base + HCONTROL));
return 0;
}
@@ -1406,8 +1380,7 @@ static void sata_fsl_host_stop(struct ata_host *host)
* scsi mid-layer and libata interface structures
*/
static struct scsi_host_template sata_fsl_sht = {
- ATA_NCQ_SHT("sata_fsl"),
- .can_queue = SATA_FSL_QUEUE_DEPTH,
+ ATA_NCQ_SHT_QD("sata_fsl", SATA_FSL_QUEUE_DEPTH),
.sg_tablesize = SATA_FSL_MAX_PRD_USABLE,
.dma_boundary = ATA_DMA_BOUNDARY,
};
@@ -1478,9 +1451,8 @@ static int sata_fsl_probe(struct platform_device *ofdev)
iowrite32(temp | TRANSCFG_RX_WATER_MARK, csr_base + TRANSCFG);
}
- DPRINTK("@reset i/o = 0x%x\n", ioread32(csr_base + TRANSCFG));
- DPRINTK("sizeof(cmd_desc) = %d\n", sizeof(struct command_desc));
- DPRINTK("sizeof(#define cmd_desc) = %d\n", SATA_FSL_CMD_DESC_SIZE);
+ dev_dbg(&ofdev->dev, "@reset i/o = 0x%x\n",
+ ioread32(csr_base + TRANSCFG));
host_priv = kzalloc(sizeof(struct sata_fsl_host_priv), GFP_KERNEL);
if (!host_priv)
diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c
index f793564..440a63d 100644
--- a/drivers/ata/sata_gemini.c
+++ b/drivers/ata/sata_gemini.c
@@ -253,12 +253,12 @@ static int gemini_sata_bridge_init(struct sata_gemini *sg)
ret = clk_prepare_enable(sg->sata0_pclk);
if (ret) {
- pr_err("failed to enable SATA0 PCLK\n");
+ dev_err(dev, "failed to enable SATA0 PCLK\n");
return ret;
}
ret = clk_prepare_enable(sg->sata1_pclk);
if (ret) {
- pr_err("failed to enable SATA1 PCLK\n");
+ dev_err(dev, "failed to enable SATA1 PCLK\n");
clk_disable_unprepare(sg->sata0_pclk);
return ret;
}
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index e517bd8..78190115 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -488,8 +488,6 @@ static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc)
bool is_data = ata_is_data(qc->tf.protocol);
unsigned int cdb_len = 0;
- VPRINTK("ENTER\n");
-
if (is_atapi)
cdb_len = qc->dev->cdb_len;
@@ -657,7 +655,7 @@ static int inic_hardreset(struct ata_link *link, unsigned int *class,
}
inic_tf_read(ap, &tf);
- *class = ata_dev_classify(&tf);
+ *class = ata_port_classify(ap, &tf);
}
return 0;
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index cae4c1e..53446b9 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -579,7 +579,7 @@ struct mv_hw_ops {
void (*enable_leds)(struct mv_host_priv *hpriv, void __iomem *mmio);
void (*read_preamp)(struct mv_host_priv *hpriv, int idx,
void __iomem *mmio);
- int (*reset_hc)(struct mv_host_priv *hpriv, void __iomem *mmio,
+ int (*reset_hc)(struct ata_host *host, void __iomem *mmio,
unsigned int n_hc);
void (*reset_flash)(struct mv_host_priv *hpriv, void __iomem *mmio);
void (*reset_bus)(struct ata_host *host, void __iomem *mmio);
@@ -606,7 +606,7 @@ static void mv5_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio,
static void mv5_enable_leds(struct mv_host_priv *hpriv, void __iomem *mmio);
static void mv5_read_preamp(struct mv_host_priv *hpriv, int idx,
void __iomem *mmio);
-static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
+static int mv5_reset_hc(struct ata_host *host, void __iomem *mmio,
unsigned int n_hc);
static void mv5_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio);
static void mv5_reset_bus(struct ata_host *host, void __iomem *mmio);
@@ -616,14 +616,14 @@ static void mv6_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio,
static void mv6_enable_leds(struct mv_host_priv *hpriv, void __iomem *mmio);
static void mv6_read_preamp(struct mv_host_priv *hpriv, int idx,
void __iomem *mmio);
-static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
+static int mv6_reset_hc(struct ata_host *host, void __iomem *mmio,
unsigned int n_hc);
static void mv6_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio);
static void mv_soc_enable_leds(struct mv_host_priv *hpriv,
void __iomem *mmio);
static void mv_soc_read_preamp(struct mv_host_priv *hpriv, int idx,
void __iomem *mmio);
-static int mv_soc_reset_hc(struct mv_host_priv *hpriv,
+static int mv_soc_reset_hc(struct ata_host *host,
void __iomem *mmio, unsigned int n_hc);
static void mv_soc_reset_flash(struct mv_host_priv *hpriv,
void __iomem *mmio);
@@ -1248,81 +1248,74 @@ static int mv_stop_edma(struct ata_port *ap)
return err;
}
-#ifdef ATA_DEBUG
-static void mv_dump_mem(void __iomem *start, unsigned bytes)
+static void mv_dump_mem(struct device *dev, void __iomem *start, unsigned bytes)
{
- int b, w;
+ int b, w, o;
+ unsigned char linebuf[38];
+
for (b = 0; b < bytes; ) {
- DPRINTK("%p: ", start + b);
- for (w = 0; b < bytes && w < 4; w++) {
- printk("%08x ", readl(start + b));
+ for (w = 0, o = 0; b < bytes && w < 4; w++) {
+ o += snprintf(linebuf + o, sizeof(linebuf) - o,
+ "%08x ", readl(start + b));
b += sizeof(u32);
}
- printk("\n");
+ dev_dbg(dev, "%s: %p: %s\n",
+ __func__, start + b, linebuf);
}
}
-#endif
-#if defined(ATA_DEBUG) || defined(CONFIG_PCI)
+
static void mv_dump_pci_cfg(struct pci_dev *pdev, unsigned bytes)
{
-#ifdef ATA_DEBUG
- int b, w;
- u32 dw;
+ int b, w, o;
+ u32 dw = 0;
+ unsigned char linebuf[38];
+
for (b = 0; b < bytes; ) {
- DPRINTK("%02x: ", b);
- for (w = 0; b < bytes && w < 4; w++) {
+ for (w = 0, o = 0; b < bytes && w < 4; w++) {
(void) pci_read_config_dword(pdev, b, &dw);
- printk("%08x ", dw);
+ o += snprintf(linebuf + o, sizeof(linebuf) - o,
+ "%08x ", dw);
b += sizeof(u32);
}
- printk("\n");
+ dev_dbg(&pdev->dev, "%s: %02x: %s\n",
+ __func__, b, linebuf);
}
-#endif
}
-#endif
-static void mv_dump_all_regs(void __iomem *mmio_base, int port,
+
+static void mv_dump_all_regs(void __iomem *mmio_base,
struct pci_dev *pdev)
{
-#ifdef ATA_DEBUG
- void __iomem *hc_base = mv_hc_base(mmio_base,
- port >> MV_PORT_HC_SHIFT);
+ void __iomem *hc_base;
void __iomem *port_base;
int start_port, num_ports, p, start_hc, num_hcs, hc;
- if (0 > port) {
- start_hc = start_port = 0;
- num_ports = 8; /* shld be benign for 4 port devs */
- num_hcs = 2;
- } else {
- start_hc = port >> MV_PORT_HC_SHIFT;
- start_port = port;
- num_ports = num_hcs = 1;
- }
- DPRINTK("All registers for port(s) %u-%u:\n", start_port,
- num_ports > 1 ? num_ports - 1 : start_port);
+ start_hc = start_port = 0;
+ num_ports = 8; /* should be benign for 4 port devs */
+ num_hcs = 2;
+ dev_dbg(&pdev->dev,
+ "%s: All registers for port(s) %u-%u:\n", __func__,
+ start_port, num_ports > 1 ? num_ports - 1 : start_port);
- if (NULL != pdev) {
- DPRINTK("PCI config space regs:\n");
- mv_dump_pci_cfg(pdev, 0x68);
- }
- DPRINTK("PCI regs:\n");
- mv_dump_mem(mmio_base+0xc00, 0x3c);
- mv_dump_mem(mmio_base+0xd00, 0x34);
- mv_dump_mem(mmio_base+0xf00, 0x4);
- mv_dump_mem(mmio_base+0x1d00, 0x6c);
+ dev_dbg(&pdev->dev, "%s: PCI config space regs:\n", __func__);
+ mv_dump_pci_cfg(pdev, 0x68);
+
+ dev_dbg(&pdev->dev, "%s: PCI regs:\n", __func__);
+ mv_dump_mem(&pdev->dev, mmio_base+0xc00, 0x3c);
+ mv_dump_mem(&pdev->dev, mmio_base+0xd00, 0x34);
+ mv_dump_mem(&pdev->dev, mmio_base+0xf00, 0x4);
+ mv_dump_mem(&pdev->dev, mmio_base+0x1d00, 0x6c);
for (hc = start_hc; hc < start_hc + num_hcs; hc++) {
hc_base = mv_hc_base(mmio_base, hc);
- DPRINTK("HC regs (HC %i):\n", hc);
- mv_dump_mem(hc_base, 0x1c);
+ dev_dbg(&pdev->dev, "%s: HC regs (HC %i):\n", __func__, hc);
+ mv_dump_mem(&pdev->dev, hc_base, 0x1c);
}
for (p = start_port; p < start_port + num_ports; p++) {
port_base = mv_port_base(mmio_base, p);
- DPRINTK("EDMA regs (port %i):\n", p);
- mv_dump_mem(port_base, 0x54);
- DPRINTK("SATA regs (port %i):\n", p);
- mv_dump_mem(port_base+0x300, 0x60);
+ dev_dbg(&pdev->dev, "%s: EDMA regs (port %i):\n", __func__, p);
+ mv_dump_mem(&pdev->dev, port_base, 0x54);
+ dev_dbg(&pdev->dev, "%s: SATA regs (port %i):\n", __func__, p);
+ mv_dump_mem(&pdev->dev, port_base+0x300, 0x60);
}
-#endif
}
static unsigned int mv_scr_offset(unsigned int sc_reg_in)
@@ -2962,8 +2955,8 @@ static int mv_pci_error(struct ata_host *host, void __iomem *mmio)
dev_err(host->dev, "PCI ERROR; PCI IRQ cause=0x%08x\n", err_cause);
- DPRINTK("All regs @ PCI error\n");
- mv_dump_all_regs(mmio, -1, to_pci_dev(host->dev));
+ dev_dbg(host->dev, "%s: All regs @ PCI error\n", __func__);
+ mv_dump_all_regs(mmio, to_pci_dev(host->dev));
writelfl(0, mmio + hpriv->irq_cause_offset);
@@ -3201,9 +3194,10 @@ static void mv5_reset_one_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
}
#undef ZERO
-static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
+static int mv5_reset_hc(struct ata_host *host, void __iomem *mmio,
unsigned int n_hc)
{
+ struct mv_host_priv *hpriv = host->private_data;
unsigned int hc, port;
for (hc = 0; hc < n_hc; hc++) {
@@ -3262,7 +3256,7 @@ static void mv6_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio)
* LOCKING:
* Inherited from caller.
*/
-static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
+static int mv6_reset_hc(struct ata_host *host, void __iomem *mmio,
unsigned int n_hc)
{
void __iomem *reg = mmio + PCI_MAIN_CMD_STS;
@@ -3282,7 +3276,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
break;
}
if (!(PCI_MASTER_EMPTY & t)) {
- printk(KERN_ERR DRV_NAME ": PCI master won't flush\n");
+ dev_err(host->dev, "PCI master won't flush\n");
rc = 1;
goto done;
}
@@ -3296,7 +3290,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
} while (!(GLOB_SFT_RST & t) && (i-- > 0));
if (!(GLOB_SFT_RST & t)) {
- printk(KERN_ERR DRV_NAME ": can't set global reset\n");
+ dev_err(host->dev, "can't set global reset\n");
rc = 1;
goto done;
}
@@ -3310,7 +3304,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio,
} while ((GLOB_SFT_RST & t) && (i-- > 0));
if (GLOB_SFT_RST & t) {
- printk(KERN_ERR DRV_NAME ": can't clear global reset\n");
+ dev_err(host->dev, "can't clear global reset\n");
rc = 1;
}
done:
@@ -3479,9 +3473,10 @@ static void mv_soc_reset_one_hc(struct mv_host_priv *hpriv,
#undef ZERO
-static int mv_soc_reset_hc(struct mv_host_priv *hpriv,
+static int mv_soc_reset_hc(struct ata_host *host,
void __iomem *mmio, unsigned int n_hc)
{
+ struct mv_host_priv *hpriv = host->private_data;
unsigned int port;
for (port = 0; port < hpriv->n_ports; port++)
@@ -3723,11 +3718,6 @@ static void mv_port_init(struct ata_ioports *port, void __iomem *port_mmio)
/* unmask all non-transient EDMA error interrupts */
writelfl(~EDMA_ERR_IRQ_TRANSIENT, port_mmio + EDMA_ERR_IRQ_MASK);
-
- VPRINTK("EDMA cfg=0x%08x EDMA IRQ err cause/mask=0x%08x/0x%08x\n",
- readl(port_mmio + EDMA_CFG),
- readl(port_mmio + EDMA_ERR_IRQ_CAUSE),
- readl(port_mmio + EDMA_ERR_IRQ_MASK));
}
static unsigned int mv_in_pcix_mode(struct ata_host *host)
@@ -3859,11 +3849,11 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx)
*
* Warn the user, lest they think we're just buggy.
*/
- printk(KERN_WARNING DRV_NAME ": Highpoint RocketRAID"
+ dev_warn(&pdev->dev, "Highpoint RocketRAID"
" BIOS CORRUPTS DATA on all attached drives,"
" regardless of if/how they are configured."
" BEWARE!\n");
- printk(KERN_WARNING DRV_NAME ": For data safety, do not"
+ dev_warn(&pdev->dev, "For data safety, do not"
" use sectors 8-9 on \"Legacy\" drives,"
" and avoid the final two gigabytes on"
" all RocketRAID BIOS initialized drives.\n");
@@ -3954,7 +3944,7 @@ static int mv_init_host(struct ata_host *host)
if (hpriv->ops->read_preamp)
hpriv->ops->read_preamp(hpriv, port, mmio);
- rc = hpriv->ops->reset_hc(hpriv, mmio, n_hc);
+ rc = hpriv->ops->reset_hc(host, mmio, n_hc);
if (rc)
goto done;
@@ -3972,7 +3962,7 @@ static int mv_init_host(struct ata_host *host)
for (hc = 0; hc < n_hc; hc++) {
void __iomem *hc_mmio = mv_hc_base(mmio, hc);
- VPRINTK("HC%i: HC config=0x%08x HC IRQ cause "
+ dev_dbg(host->dev, "HC%i: HC config=0x%08x HC IRQ cause "
"(before clear)=0x%08x\n", hc,
readl(hc_mmio + HC_CFG),
readl(hc_mmio + HC_IRQ_CAUSE));
@@ -4270,7 +4260,7 @@ static int mv_platform_resume(struct platform_device *pdev)
/* initialize adapter */
ret = mv_init_host(host);
if (ret) {
- printk(KERN_ERR DRV_NAME ": Error during HW init\n");
+ dev_err(&pdev->dev, "Error during HW init\n");
return ret;
}
ata_host_resume(host);
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 16272c1..7f14d0d 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -31,6 +31,7 @@
#include <scsi/scsi_host.h>
#include <scsi/scsi_device.h>
#include <linux/libata.h>
+#include <trace/events/libata.h>
#define DRV_NAME "sata_nv"
#define DRV_VERSION "3.5"
@@ -808,7 +809,7 @@ static int nv_adma_check_cpb(struct ata_port *ap, int cpb_num, int force_err)
struct nv_adma_port_priv *pp = ap->private_data;
u8 flags = pp->cpb[cpb_num].resp_flags;
- VPRINTK("CPB %d, flags=0x%x\n", cpb_num, flags);
+ ata_port_dbg(ap, "CPB %d, flags=0x%x\n", cpb_num, flags);
if (unlikely((force_err ||
flags & (NV_CPB_RESP_ATA_ERR |
@@ -1100,8 +1101,6 @@ static int nv_adma_port_start(struct ata_port *ap)
struct pci_dev *pdev = to_pci_dev(dev);
u16 tmp;
- VPRINTK("ENTER\n");
-
/*
* Ensure DMA mask is set to 32-bit before allocating legacy PRD and
* pad buffers.
@@ -1190,7 +1189,6 @@ static void nv_adma_port_stop(struct ata_port *ap)
struct nv_adma_port_priv *pp = ap->private_data;
void __iomem *mmio = pp->ctl_block;
- VPRINTK("ENTER\n");
writew(0, mmio + NV_ADMA_CTL);
}
@@ -1252,8 +1250,6 @@ static void nv_adma_setup_port(struct ata_port *ap)
void __iomem *mmio = ap->host->iomap[NV_MMIO_BAR];
struct ata_ioports *ioport = &ap->ioaddr;
- VPRINTK("ENTER\n");
-
mmio += NV_ADMA_PORT + ap->port_no * NV_ADMA_PORT_SIZE;
ioport->cmd_addr = mmio;
@@ -1277,8 +1273,6 @@ static int nv_adma_host_init(struct ata_host *host)
unsigned int i;
u32 tmp32;
- VPRINTK("ENTER\n");
-
/* enable ADMA on the ports */
pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &tmp32);
tmp32 |= NV_MCP_SATA_CFG_20_PORT0_EN |
@@ -1320,8 +1314,6 @@ static void nv_adma_fill_sg(struct ata_queued_cmd *qc, struct nv_adma_cpb *cpb)
struct scatterlist *sg;
unsigned int si;
- VPRINTK("ENTER\n");
-
for_each_sg(qc->sg, sg, qc->n_elem, si) {
aprd = (si < 5) ? &cpb->aprd[si] :
&pp->aprd[NV_ADMA_SGTBL_LEN * qc->hw_tag + (si-5)];
@@ -1378,8 +1370,6 @@ static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc)
if (qc->tf.protocol == ATA_PROT_NCQ)
ctl_flags |= NV_CPB_CTL_QUEUE | NV_CPB_CTL_FPDMA;
- VPRINTK("qc->flags = 0x%lx\n", qc->flags);
-
nv_adma_tf_to_cpb(&qc->tf, cpb->tf);
if (qc->flags & ATA_QCFLAG_DMAMAP) {
@@ -1404,8 +1394,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
void __iomem *mmio = pp->ctl_block;
int curr_ncq = (qc->tf.protocol == ATA_PROT_NCQ);
- VPRINTK("ENTER\n");
-
/* We can't handle result taskfile with NCQ commands, since
retrieving the taskfile switches us out of ADMA mode and would abort
existing commands. */
@@ -1417,7 +1405,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
if (nv_adma_use_reg_mode(qc)) {
/* use ATA register mode */
- VPRINTK("using ATA register mode: 0x%lx\n", qc->flags);
BUG_ON(!(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) &&
(qc->flags & ATA_QCFLAG_DMAMAP));
nv_adma_register_mode(qc->ap);
@@ -1438,8 +1425,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
writew(qc->hw_tag, mmio + NV_ADMA_APPEND);
- DPRINTK("Issued tag %u\n", qc->hw_tag);
-
return 0;
}
@@ -1871,12 +1856,12 @@ static void nv_swncq_host_init(struct ata_host *host)
/* enable swncq */
tmp = readl(mmio + NV_CTL_MCP55);
- VPRINTK("HOST_CTL:0x%X\n", tmp);
+ dev_dbg(&pdev->dev, "HOST_CTL:0x%X\n", tmp);
writel(tmp | NV_CTL_PRI_SWNCQ | NV_CTL_SEC_SWNCQ, mmio + NV_CTL_MCP55);
/* enable irq intr */
tmp = readl(mmio + NV_INT_ENABLE_MCP55);
- VPRINTK("HOST_ENABLE:0x%X\n", tmp);
+ dev_dbg(&pdev->dev, "HOST_ENABLE:0x%X\n", tmp);
writel(tmp | 0x00fd00fd, mmio + NV_INT_ENABLE_MCP55);
/* clear port irq */
@@ -2017,19 +2002,17 @@ static unsigned int nv_swncq_issue_atacmd(struct ata_port *ap,
if (qc == NULL)
return 0;
- DPRINTK("Enter\n");
-
writel((1 << qc->hw_tag), pp->sactive_block);
pp->last_issue_tag = qc->hw_tag;
pp->dhfis_bits &= ~(1 << qc->hw_tag);
pp->dmafis_bits &= ~(1 << qc->hw_tag);
pp->qc_active |= (0x1 << qc->hw_tag);
+ trace_ata_tf_load(ap, &qc->tf);
ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */
+ trace_ata_exec_command(ap, &qc->tf, qc->hw_tag);
ap->ops->sff_exec_command(ap, &qc->tf);
- DPRINTK("Issued tag %u\n", qc->hw_tag);
-
return 0;
}
@@ -2041,8 +2024,6 @@ static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc)
if (qc->tf.protocol != ATA_PROT_NCQ)
return ata_bmdma_qc_issue(qc);
- DPRINTK("Enter\n");
-
if (!pp->qc_active)
nv_swncq_issue_atacmd(ap, qc);
else
@@ -2087,6 +2068,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap)
u8 lack_dhfis = 0;
host_stat = ap->ops->bmdma_status(ap);
+ trace_ata_bmdma_status(ap, host_stat);
if (unlikely(host_stat & ATA_DMA_ERR)) {
/* error when transferring data to/from memory */
ata_ehi_clear_desc(ehi);
@@ -2109,7 +2091,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap)
ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
if (!ap->qc_active) {
- DPRINTK("over\n");
+ ata_port_dbg(ap, "over\n");
nv_swncq_pp_reinit(ap);
return 0;
}
@@ -2124,12 +2106,12 @@ static int nv_swncq_sdbfis(struct ata_port *ap)
*/
lack_dhfis = 1;
- DPRINTK("id 0x%x QC: qc_active 0x%llx,"
- "SWNCQ:qc_active 0x%X defer_bits %X "
- "dhfis 0x%X dmafis 0x%X last_issue_tag %x\n",
- ap->print_id, ap->qc_active, pp->qc_active,
- pp->defer_queue.defer_bits, pp->dhfis_bits,
- pp->dmafis_bits, pp->last_issue_tag);
+ ata_port_dbg(ap, "QC: qc_active 0x%llx,"
+ "SWNCQ:qc_active 0x%X defer_bits %X "
+ "dhfis 0x%X dmafis 0x%X last_issue_tag %x\n",
+ ap->qc_active, pp->qc_active,
+ pp->defer_queue.defer_bits, pp->dhfis_bits,
+ pp->dmafis_bits, pp->last_issue_tag);
nv_swncq_fis_reinit(ap);
@@ -2169,7 +2151,7 @@ static void nv_swncq_dmafis(struct ata_port *ap)
__ata_bmdma_stop(ap);
tag = nv_swncq_tag(ap);
- DPRINTK("dma setup tag 0x%x\n", tag);
+ ata_port_dbg(ap, "dma setup tag 0x%x\n", tag);
qc = ata_qc_from_tag(ap, tag);
if (unlikely(!qc))
@@ -2237,9 +2219,9 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis)
if (fis & NV_SWNCQ_IRQ_SDBFIS) {
pp->ncq_flags |= ncq_saw_sdb;
- DPRINTK("id 0x%x SWNCQ: qc_active 0x%X "
+ ata_port_dbg(ap, "SWNCQ: qc_active 0x%X "
"dhfis 0x%X dmafis 0x%X sactive 0x%X\n",
- ap->print_id, pp->qc_active, pp->dhfis_bits,
+ pp->qc_active, pp->dhfis_bits,
pp->dmafis_bits, readl(pp->sactive_block));
if (nv_swncq_sdbfis(ap) < 0)
goto irq_error;
@@ -2265,7 +2247,7 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis)
goto irq_exit;
if (pp->defer_queue.defer_bits) {
- DPRINTK("send next command\n");
+ ata_port_dbg(ap, "send next command\n");
qc = nv_swncq_qc_from_dq(ap);
nv_swncq_issue_atacmd(ap, qc);
}
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 7815da8..b8465fe 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -596,7 +596,8 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc)
prd[idx].addr = cpu_to_le32(addr);
prd[idx].flags_len = cpu_to_le32(len & 0xffff);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len);
+ ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n",
+ idx, addr, len);
idx++;
sg_len -= len;
@@ -609,17 +610,16 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc)
if (len > SG_COUNT_ASIC_BUG) {
u32 addr;
- VPRINTK("Splitting last PRD.\n");
-
addr = le32_to_cpu(prd[idx - 1].addr);
prd[idx - 1].flags_len = cpu_to_le32(len - SG_COUNT_ASIC_BUG);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx - 1, addr, SG_COUNT_ASIC_BUG);
+ ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n",
+ idx - 1, addr, SG_COUNT_ASIC_BUG);
addr = addr + len - SG_COUNT_ASIC_BUG;
len = SG_COUNT_ASIC_BUG;
prd[idx].addr = cpu_to_le32(addr);
prd[idx].flags_len = cpu_to_le32(len);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len);
+ ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len);
idx++;
}
@@ -632,8 +632,6 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
struct pdc_port_priv *pp = qc->ap->private_data;
unsigned int i;
- VPRINTK("ENTER\n");
-
switch (qc->tf.protocol) {
case ATA_PROT_DMA:
pdc_fill_sg(qc);
@@ -922,12 +920,8 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance)
u32 hotplug_status;
int is_sataii_tx4;
- VPRINTK("ENTER\n");
-
- if (!host || !host->iomap[PDC_MMIO_BAR]) {
- VPRINTK("QUICK EXIT\n");
+ if (!host || !host->iomap[PDC_MMIO_BAR])
return IRQ_NONE;
- }
host_mmio = host->iomap[PDC_MMIO_BAR];
@@ -946,23 +940,18 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance)
/* reading should also clear interrupts */
mask = readl(host_mmio + PDC_INT_SEQMASK);
- if (mask == 0xffffffff && hotplug_status == 0) {
- VPRINTK("QUICK EXIT 2\n");
+ if (mask == 0xffffffff && hotplug_status == 0)
goto done_irq;
- }
mask &= 0xffff; /* only 16 SEQIDs possible */
- if (mask == 0 && hotplug_status == 0) {
- VPRINTK("QUICK EXIT 3\n");
+ if (mask == 0 && hotplug_status == 0)
goto done_irq;
- }
writel(mask, host_mmio + PDC_INT_SEQMASK);
is_sataii_tx4 = pdc_is_sataii_tx4(host->ports[0]->flags);
for (i = 0; i < host->n_ports; i++) {
- VPRINTK("port %u\n", i);
ap = host->ports[i];
/* check for a plug or unplug event */
@@ -989,8 +978,6 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance)
}
}
- VPRINTK("EXIT\n");
-
done_irq:
spin_unlock(&host->lock);
return IRQ_RETVAL(handled);
@@ -1005,8 +992,6 @@ static void pdc_packet_start(struct ata_queued_cmd *qc)
unsigned int port_no = ap->port_no;
u8 seq = (u8) (port_no + 1);
- VPRINTK("ENTER, ap %p\n", ap);
-
writel(0x00000001, host_mmio + (seq * 4));
readl(host_mmio + (seq * 4)); /* flush */
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index ef00ab6..8ca0810 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -252,9 +252,6 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc)
len = sg_dma_len(sg);
*(__le32 *)prd = cpu_to_le32(len);
prd += sizeof(u64);
-
- VPRINTK("PRD[%u] = (0x%llX, 0x%X)\n", si,
- (unsigned long long)addr, len);
}
return si;
@@ -268,8 +265,6 @@ static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc)
u64 addr;
unsigned int nelem;
- VPRINTK("ENTER\n");
-
qs_enter_reg_mode(qc->ap);
if (qc->tf.protocol != ATA_PROT_DMA)
return AC_ERR_OK;
@@ -304,8 +299,6 @@ static inline void qs_packet_start(struct ata_queued_cmd *qc)
struct ata_port *ap = qc->ap;
u8 __iomem *chan = qs_mmio_base(ap->host) + (ap->port_no * 0x4000);
- VPRINTK("ENTER, ap %p\n", ap);
-
writeb(QS_CTR0_CLER, chan + QS_CCT_CTR0);
wmb(); /* flush PRDs and pkt to memory */
writel(QS_CCF_RUN_PKT, chan + QS_CCT_CFF);
@@ -374,8 +367,8 @@ static inline unsigned int qs_intr_pkt(struct ata_host *host)
struct qs_port_priv *pp = ap->private_data;
struct ata_queued_cmd *qc;
- DPRINTK("SFF=%08x%08x: sCHAN=%u sHST=%d sDST=%02x\n",
- sff1, sff0, port_no, sHST, sDST);
+ dev_dbg(host->dev, "SFF=%08x%08x: sHST=%d sDST=%02x\n",
+ sff1, sff0, sHST, sDST);
handled = 1;
if (!pp || pp->state != qs_state_pkt)
continue;
@@ -435,14 +428,10 @@ static irqreturn_t qs_intr(int irq, void *dev_instance)
unsigned int handled = 0;
unsigned long flags;
- VPRINTK("ENTER\n");
-
spin_lock_irqsave(&host->lock, flags);
handled = qs_intr_pkt(host) | qs_intr_mmio(host);
spin_unlock_irqrestore(&host->lock, flags);
- VPRINTK("EXIT\n");
-
return IRQ_RETVAL(handled);
}
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 44b0ed8..3d96b6f 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -323,8 +323,6 @@ static int sata_rcar_bus_softreset(struct ata_port *ap, unsigned long deadline)
{
struct ata_ioports *ioaddr = &ap->ioaddr;
- DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
-
/* software reset. causes dev0 to be selected */
iowrite32(ap->ctl, ioaddr->ctl_addr);
udelay(20);
@@ -350,7 +348,6 @@ static int sata_rcar_softreset(struct ata_link *link, unsigned int *classes,
devmask |= 1 << 0;
/* issue bus reset */
- DPRINTK("about to softreset, devmask=%x\n", devmask);
rc = sata_rcar_bus_softreset(ap, deadline);
/* if link is occupied, -ENODEV too is an error */
if (rc && (rc != -ENODEV || sata_scr_valid(link))) {
@@ -361,7 +358,6 @@ static int sata_rcar_softreset(struct ata_link *link, unsigned int *classes,
/* determine by signature whether we have ATA or ATAPI devices */
classes[0] = ata_sff_dev_classify(&link->device[0], devmask, &err);
- DPRINTK("classes[0]=%u\n", classes[0]);
return 0;
}
@@ -383,12 +379,6 @@ static void sata_rcar_tf_load(struct ata_port *ap,
iowrite32(tf->hob_lbal, ioaddr->lbal_addr);
iowrite32(tf->hob_lbam, ioaddr->lbam_addr);
iowrite32(tf->hob_lbah, ioaddr->lbah_addr);
- VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->hob_feature,
- tf->hob_nsect,
- tf->hob_lbal,
- tf->hob_lbam,
- tf->hob_lbah);
}
if (is_addr) {
@@ -397,18 +387,10 @@ static void sata_rcar_tf_load(struct ata_port *ap,
iowrite32(tf->lbal, ioaddr->lbal_addr);
iowrite32(tf->lbam, ioaddr->lbam_addr);
iowrite32(tf->lbah, ioaddr->lbah_addr);
- VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n",
- tf->feature,
- tf->nsect,
- tf->lbal,
- tf->lbam,
- tf->lbah);
}
- if (tf->flags & ATA_TFLAG_DEVICE) {
+ if (tf->flags & ATA_TFLAG_DEVICE)
iowrite32(tf->device, ioaddr->device_addr);
- VPRINTK("device 0x%X\n", tf->device);
- }
ata_wait_idle(ap);
}
@@ -440,8 +422,6 @@ static void sata_rcar_tf_read(struct ata_port *ap, struct ata_taskfile *tf)
static void sata_rcar_exec_command(struct ata_port *ap,
const struct ata_taskfile *tf)
{
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
-
iowrite32(tf->command, ap->ioaddr.command_addr);
ata_sff_pause(ap);
}
@@ -499,7 +479,6 @@ static void sata_rcar_drain_fifo(struct ata_queued_cmd *qc)
count < 65536; count += 2)
ioread32(ap->ioaddr.data_addr);
- /* Can become DEBUG later */
if (count)
ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count);
}
@@ -543,7 +522,6 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc)
prd[si].addr = cpu_to_le32(addr);
prd[si].flags_len = cpu_to_le32(sg_len);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", si, addr, sg_len);
}
/* end-of-table flag */
@@ -685,7 +663,7 @@ static void sata_rcar_serr_interrupt(struct ata_port *ap)
if (!serror)
return;
- DPRINTK("SError @host_intr: 0x%x\n", serror);
+ ata_port_dbg(ap, "SError @host_intr: 0x%x\n", serror);
/* first, analyze and record host port events */
ata_ehi_clear_desc(ehi);
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 75321f1..3b989a5 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -307,7 +307,6 @@ static void sil_fill_sg(struct ata_queued_cmd *qc)
prd->addr = cpu_to_le32(addr);
prd->flags_len = cpu_to_le32(sg_len);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", si, addr, sg_len);
last_prd = prd;
prd++;
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index f99ec6f..2fef6ce 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -656,8 +656,6 @@ static int sil24_softreset(struct ata_link *link, unsigned int *class,
const char *reason;
int rc;
- DPRINTK("ENTER\n");
-
/* put the port into known state */
if (sil24_init_port(ap)) {
reason = "port not ready";
@@ -680,9 +678,8 @@ static int sil24_softreset(struct ata_link *link, unsigned int *class,
}
sil24_read_tf(ap, 0, &tf);
- *class = ata_dev_classify(&tf);
+ *class = ata_port_classify(ap, &tf);
- DPRINTK("EXIT, class=%u\n", *class);
return 0;
err:
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 4c01190..6ceec59 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -78,6 +78,9 @@
#define DRV_NAME "sata_sx4"
#define DRV_VERSION "0.12"
+static int dimm_test;
+module_param(dimm_test, int, 0644);
+MODULE_PARM_DESC(dimm_test, "Enable DIMM test during startup (1 = enabled)");
enum {
PDC_MMIO_BAR = 3,
@@ -211,10 +214,8 @@ static unsigned int pdc20621_i2c_read(struct ata_host *host,
u32 device, u32 subaddr, u32 *pdata);
static int pdc20621_prog_dimm0(struct ata_host *host);
static unsigned int pdc20621_prog_dimm_global(struct ata_host *host);
-#ifdef ATA_VERBOSE_DEBUG
static void pdc20621_get_from_dimm(struct ata_host *host,
void *psource, u32 offset, u32 size);
-#endif
static void pdc20621_put_to_dimm(struct ata_host *host,
void *psource, u32 offset, u32 size);
static void pdc20621_irq_clear(struct ata_port *ap);
@@ -308,15 +309,9 @@ static inline void pdc20621_ata_sg(u8 *buf, unsigned int portno,
/* output ATA packet S/G table */
addr = PDC_20621_DIMM_BASE + PDC_20621_DIMM_DATA +
(PDC_DIMM_DATA_STEP * portno);
- VPRINTK("ATA sg addr 0x%x, %d\n", addr, addr);
+
buf32[dw] = cpu_to_le32(addr);
buf32[dw + 1] = cpu_to_le32(total_len | ATA_PRD_EOT);
-
- VPRINTK("ATA PSG @ %x == (0x%x, 0x%x)\n",
- PDC_20621_DIMM_BASE +
- (PDC_DIMM_WINDOW_STEP * portno) +
- PDC_DIMM_APKT_PRD,
- buf32[dw], buf32[dw + 1]);
}
static inline void pdc20621_host_sg(u8 *buf, unsigned int portno,
@@ -332,12 +327,6 @@ static inline void pdc20621_host_sg(u8 *buf, unsigned int portno,
buf32[dw] = cpu_to_le32(addr);
buf32[dw + 1] = cpu_to_le32(total_len | ATA_PRD_EOT);
-
- VPRINTK("HOST PSG @ %x == (0x%x, 0x%x)\n",
- PDC_20621_DIMM_BASE +
- (PDC_DIMM_WINDOW_STEP * portno) +
- PDC_DIMM_HPKT_PRD,
- buf32[dw], buf32[dw + 1]);
}
static inline unsigned int pdc20621_ata_pkt(struct ata_taskfile *tf,
@@ -351,7 +340,6 @@ static inline unsigned int pdc20621_ata_pkt(struct ata_taskfile *tf,
unsigned int dimm_sg = PDC_20621_DIMM_BASE +
(PDC_DIMM_WINDOW_STEP * portno) +
PDC_DIMM_APKT_PRD;
- VPRINTK("ENTER, dimm_sg == 0x%x, %d\n", dimm_sg, dimm_sg);
i = PDC_DIMM_ATA_PKT;
@@ -406,8 +394,6 @@ static inline void pdc20621_host_pkt(struct ata_taskfile *tf, u8 *buf,
unsigned int dimm_sg = PDC_20621_DIMM_BASE +
(PDC_DIMM_WINDOW_STEP * portno) +
PDC_DIMM_HPKT_PRD;
- VPRINTK("ENTER, dimm_sg == 0x%x, %d\n", dimm_sg, dimm_sg);
- VPRINTK("host_sg == 0x%x, %d\n", host_sg, host_sg);
dw = PDC_DIMM_HOST_PKT >> 2;
@@ -424,14 +410,6 @@ static inline void pdc20621_host_pkt(struct ata_taskfile *tf, u8 *buf,
buf32[dw + 1] = cpu_to_le32(host_sg);
buf32[dw + 2] = cpu_to_le32(dimm_sg);
buf32[dw + 3] = 0;
-
- VPRINTK("HOST PKT @ %x == (0x%x 0x%x 0x%x 0x%x)\n",
- PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * portno) +
- PDC_DIMM_HOST_PKT,
- buf32[dw + 0],
- buf32[dw + 1],
- buf32[dw + 2],
- buf32[dw + 3]);
}
static void pdc20621_dma_prep(struct ata_queued_cmd *qc)
@@ -447,8 +425,6 @@ static void pdc20621_dma_prep(struct ata_queued_cmd *qc)
WARN_ON(!(qc->flags & ATA_QCFLAG_DMAMAP));
- VPRINTK("ata%u: ENTER\n", ap->print_id);
-
/* hard-code chip #0 */
mmio += PDC_CHIP0_OFS;
@@ -492,7 +468,8 @@ static void pdc20621_dma_prep(struct ata_queued_cmd *qc)
readl(dimm_mmio); /* MMIO PCI posting flush */
- VPRINTK("ata pkt buf ofs %u, prd size %u, mmio copied\n", i, sgt_len);
+ ata_port_dbg(ap, "ata pkt buf ofs %u, prd size %u, mmio copied\n",
+ i, sgt_len);
}
static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
@@ -504,8 +481,6 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
unsigned int portno = ap->port_no;
unsigned int i;
- VPRINTK("ata%u: ENTER\n", ap->print_id);
-
/* hard-code chip #0 */
mmio += PDC_CHIP0_OFS;
@@ -527,7 +502,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
readl(dimm_mmio); /* MMIO PCI posting flush */
- VPRINTK("ata pkt buf ofs %u, mmio copied\n", i);
+ ata_port_dbg(ap, "ata pkt buf ofs %u, mmio copied\n", i);
}
static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc)
@@ -601,7 +576,6 @@ static void pdc20621_pop_hdma(struct ata_queued_cmd *qc)
pp->hdma_cons++;
}
-#ifdef ATA_VERBOSE_DEBUG
static void pdc20621_dump_hdma(struct ata_queued_cmd *qc)
{
struct ata_port *ap = qc->ap;
@@ -611,14 +585,10 @@ static void pdc20621_dump_hdma(struct ata_queued_cmd *qc)
dimm_mmio += (port_no * PDC_DIMM_WINDOW_STEP);
dimm_mmio += PDC_DIMM_HOST_PKT;
- printk(KERN_ERR "HDMA[0] == 0x%08X\n", readl(dimm_mmio));
- printk(KERN_ERR "HDMA[1] == 0x%08X\n", readl(dimm_mmio + 4));
- printk(KERN_ERR "HDMA[2] == 0x%08X\n", readl(dimm_mmio + 8));
- printk(KERN_ERR "HDMA[3] == 0x%08X\n", readl(dimm_mmio + 12));
+ ata_port_dbg(ap, "HDMA 0x%08X 0x%08X 0x%08X 0x%08X\n",
+ readl(dimm_mmio), readl(dimm_mmio + 4),
+ readl(dimm_mmio + 8), readl(dimm_mmio + 12));
}
-#else
-static inline void pdc20621_dump_hdma(struct ata_queued_cmd *qc) { }
-#endif /* ATA_VERBOSE_DEBUG */
static void pdc20621_packet_start(struct ata_queued_cmd *qc)
{
@@ -633,8 +603,6 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc)
/* hard-code chip #0 */
mmio += PDC_CHIP0_OFS;
- VPRINTK("ata%u: ENTER\n", ap->print_id);
-
wmb(); /* flush PRD, pkt writes */
port_ofs = PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * port_no);
@@ -645,7 +613,7 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc)
pdc20621_dump_hdma(qc);
pdc20621_push_hdma(qc, seq, port_ofs + PDC_DIMM_HOST_PKT);
- VPRINTK("queued ofs 0x%x (%u), seq %u\n",
+ ata_port_dbg(ap, "queued ofs 0x%x (%u), seq %u\n",
port_ofs + PDC_DIMM_HOST_PKT,
port_ofs + PDC_DIMM_HOST_PKT,
seq);
@@ -656,7 +624,7 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc)
writel(port_ofs + PDC_DIMM_ATA_PKT,
ap->ioaddr.cmd_addr + PDC_PKT_SUBMIT);
readl(ap->ioaddr.cmd_addr + PDC_PKT_SUBMIT);
- VPRINTK("submitted ofs 0x%x (%u), seq %u\n",
+ ata_port_dbg(ap, "submitted ofs 0x%x (%u), seq %u\n",
port_ofs + PDC_DIMM_ATA_PKT,
port_ofs + PDC_DIMM_ATA_PKT,
seq);
@@ -696,14 +664,12 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap,
u8 status;
unsigned int handled = 0;
- VPRINTK("ENTER\n");
-
if ((qc->tf.protocol == ATA_PROT_DMA) && /* read */
(!(qc->tf.flags & ATA_TFLAG_WRITE))) {
/* step two - DMA from DIMM to host */
if (doing_hdma) {
- VPRINTK("ata%u: read hdma, 0x%x 0x%x\n", ap->print_id,
+ ata_port_dbg(ap, "read hdma, 0x%x 0x%x\n",
readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT));
/* get drive status; clear intr; complete txn */
qc->err_mask |= ac_err_mask(ata_wait_idle(ap));
@@ -714,7 +680,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap,
/* step one - exec ATA command */
else {
u8 seq = (u8) (port_no + 1 + 4);
- VPRINTK("ata%u: read ata, 0x%x 0x%x\n", ap->print_id,
+ ata_port_dbg(ap, "read ata, 0x%x 0x%x\n",
readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT));
/* submit hdma pkt */
@@ -729,7 +695,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap,
/* step one - DMA from host to DIMM */
if (doing_hdma) {
u8 seq = (u8) (port_no + 1);
- VPRINTK("ata%u: write hdma, 0x%x 0x%x\n", ap->print_id,
+ ata_port_dbg(ap, "write hdma, 0x%x 0x%x\n",
readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT));
/* submit ata pkt */
@@ -742,7 +708,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap,
/* step two - execute ATA command */
else {
- VPRINTK("ata%u: write ata, 0x%x 0x%x\n", ap->print_id,
+ ata_port_dbg(ap, "write ata, 0x%x 0x%x\n",
readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT));
/* get drive status; clear intr; complete txn */
qc->err_mask |= ac_err_mask(ata_wait_idle(ap));
@@ -755,7 +721,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap,
} else if (qc->tf.protocol == ATA_PROT_NODATA) {
status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000);
- DPRINTK("BUS_NODATA (drv_stat 0x%X)\n", status);
+ ata_port_dbg(ap, "BUS_NODATA (drv_stat 0x%X)\n", status);
qc->err_mask |= ac_err_mask(status);
ata_qc_complete(qc);
handled = 1;
@@ -781,29 +747,21 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance)
unsigned int handled = 0;
void __iomem *mmio_base;
- VPRINTK("ENTER\n");
-
- if (!host || !host->iomap[PDC_MMIO_BAR]) {
- VPRINTK("QUICK EXIT\n");
+ if (!host || !host->iomap[PDC_MMIO_BAR])
return IRQ_NONE;
- }
mmio_base = host->iomap[PDC_MMIO_BAR];
/* reading should also clear interrupts */
mmio_base += PDC_CHIP0_OFS;
mask = readl(mmio_base + PDC_20621_SEQMASK);
- VPRINTK("mask == 0x%x\n", mask);
- if (mask == 0xffffffff) {
- VPRINTK("QUICK EXIT 2\n");
+ if (mask == 0xffffffff)
return IRQ_NONE;
- }
+
mask &= 0xffff; /* only 16 tags possible */
- if (!mask) {
- VPRINTK("QUICK EXIT 3\n");
+ if (!mask)
return IRQ_NONE;
- }
spin_lock(&host->lock);
@@ -816,7 +774,8 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance)
else
ap = host->ports[port_no];
tmp = mask & (1 << i);
- VPRINTK("seq %u, port_no %u, ap %p, tmp %x\n", i, port_no, ap, tmp);
+ if (ap)
+ ata_port_dbg(ap, "seq %u, tmp %x\n", i, tmp);
if (tmp && ap) {
struct ata_queued_cmd *qc;
@@ -829,10 +788,6 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance)
spin_unlock(&host->lock);
- VPRINTK("mask == 0x%x\n", mask);
-
- VPRINTK("EXIT\n");
-
return IRQ_RETVAL(handled);
}
@@ -979,7 +934,6 @@ static void pdc_sata_setup_port(struct ata_ioports *port, void __iomem *base)
}
-#ifdef ATA_VERBOSE_DEBUG
static void pdc20621_get_from_dimm(struct ata_host *host, void *psource,
u32 offset, u32 size)
{
@@ -1029,7 +983,6 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource,
memcpy_fromio(psource, dimm_mmio, size / 4);
}
}
-#endif
static void pdc20621_put_to_dimm(struct ata_host *host, void *psource,
@@ -1226,15 +1179,16 @@ static unsigned int pdc20621_prog_dimm_global(struct ata_host *host)
/* Turn on for ECC */
if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
PDC_DIMM_SPD_TYPE, &spd0)) {
- pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
- PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
+ dev_err(host->dev,
+ "Failed in i2c read: device=%#x, subaddr=%#x\n",
+ PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
return 1;
}
if (spd0 == 0x02) {
data |= (0x01 << 16);
writel(data, mmio + PDC_SDRAM_CONTROL);
readl(mmio + PDC_SDRAM_CONTROL);
- printk(KERN_ERR "Local DIMM ECC Enabled\n");
+ dev_err(host->dev, "Local DIMM ECC Enabled\n");
}
/* DIMM Initialization Select/Enable (bit 18/19) */
@@ -1274,7 +1228,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
/* Initialize Time Period Register */
writel(0xffffffff, mmio + PDC_TIME_PERIOD);
time_period = readl(mmio + PDC_TIME_PERIOD);
- VPRINTK("Time Period Register (0x40): 0x%x\n", time_period);
+ dev_dbg(host->dev, "Time Period Register (0x40): 0x%x\n", time_period);
/* Enable timer */
writel(PDC_TIMER_DEFAULT, mmio + PDC_TIME_CONTROL);
@@ -1289,7 +1243,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
*/
tcount = readl(mmio + PDC_TIME_COUNTER);
- VPRINTK("Time Counter Register (0x44): 0x%x\n", tcount);
+ dev_dbg(host->dev, "Time Counter Register (0x44): 0x%x\n", tcount);
/*
If SX4 is on PCI-X bus, after 3 seconds, the timer counter
@@ -1297,17 +1251,19 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
*/
if (tcount >= PCI_X_TCOUNT) {
ticks = (time_period - tcount);
- VPRINTK("Num counters 0x%x (%d)\n", ticks, ticks);
+ dev_dbg(host->dev, "Num counters 0x%x (%d)\n", ticks, ticks);
clock = (ticks / 300000);
- VPRINTK("10 * Internal clk = 0x%x (%d)\n", clock, clock);
+ dev_dbg(host->dev, "10 * Internal clk = 0x%x (%d)\n",
+ clock, clock);
clock = (clock * 33);
- VPRINTK("10 * Internal clk * 33 = 0x%x (%d)\n", clock, clock);
+ dev_dbg(host->dev, "10 * Internal clk * 33 = 0x%x (%d)\n",
+ clock, clock);
/* PLL F Param (bit 22:16) */
fparam = (1400000 / clock) - 2;
- VPRINTK("PLL F Param: 0x%x (%d)\n", fparam, fparam);
+ dev_dbg(host->dev, "PLL F Param: 0x%x (%d)\n", fparam, fparam);
/* OD param = 0x2 (bit 31:30), R param = 0x5 (bit 29:25) */
pci_status = (0x8a001824 | (fparam << 16));
@@ -1315,7 +1271,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
pci_status = PCI_PLL_INIT;
/* Initialize PLL. */
- VPRINTK("pci_status: 0x%x\n", pci_status);
+ dev_dbg(host->dev, "pci_status: 0x%x\n", pci_status);
writel(pci_status, mmio + PDC_CTL_STATUS);
readl(mmio + PDC_CTL_STATUS);
@@ -1324,23 +1280,23 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
and program the DIMM Module Controller.
*/
if (!(speed = pdc20621_detect_dimm(host))) {
- printk(KERN_ERR "Detect Local DIMM Fail\n");
+ dev_err(host->dev, "Detect Local DIMM Fail\n");
return 1; /* DIMM error */
}
- VPRINTK("Local DIMM Speed = %d\n", speed);
+ dev_dbg(host->dev, "Local DIMM Speed = %d\n", speed);
/* Programming DIMM0 Module Control Register (index_CID0:80h) */
size = pdc20621_prog_dimm0(host);
- VPRINTK("Local DIMM Size = %dMB\n", size);
+ dev_dbg(host->dev, "Local DIMM Size = %dMB\n", size);
/* Programming DIMM Module Global Control Register (index_CID0:88h) */
if (pdc20621_prog_dimm_global(host)) {
- printk(KERN_ERR "Programming DIMM Module Global Control Register Fail\n");
+ dev_err(host->dev,
+ "Programming DIMM Module Global Control Register Fail\n");
return 1;
}
-#ifdef ATA_VERBOSE_DEBUG
- {
+ if (dimm_test) {
u8 test_parttern1[40] =
{0x55,0xAA,'P','r','o','m','i','s','e',' ',
'N','o','t',' ','Y','e','t',' ',
@@ -1354,31 +1310,33 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
pdc20621_put_to_dimm(host, test_parttern1, 0x10040, 40);
pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40);
- printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0],
+ dev_info(host->dev, "DIMM test pattern 1: %x, %x, %s\n", test_parttern2[0],
test_parttern2[1], &(test_parttern2[2]));
pdc20621_get_from_dimm(host, test_parttern2, 0x10040,
40);
- printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0],
- test_parttern2[1], &(test_parttern2[2]));
+ dev_info(host->dev, "DIMM test pattern 2: %x, %x, %s\n",
+ test_parttern2[0],
+ test_parttern2[1], &(test_parttern2[2]));
pdc20621_put_to_dimm(host, test_parttern1, 0x40, 40);
pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40);
- printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0],
- test_parttern2[1], &(test_parttern2[2]));
+ dev_info(host->dev, "DIMM test pattern 3: %x, %x, %s\n",
+ test_parttern2[0],
+ test_parttern2[1], &(test_parttern2[2]));
}
-#endif
/* ECC initiliazation. */
if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
PDC_DIMM_SPD_TYPE, &spd0)) {
- pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
+ dev_err(host->dev,
+ "Failed in i2c read: device=%#x, subaddr=%#x\n",
PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
return 1;
}
if (spd0 == 0x02) {
void *buf;
- VPRINTK("Start ECC initialization\n");
+ dev_dbg(host->dev, "Start ECC initialization\n");
addr = 0;
length = size * 1024 * 1024;
buf = kzalloc(ECC_ERASE_BUF_SZ, GFP_KERNEL);
@@ -1390,7 +1348,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
addr += ECC_ERASE_BUF_SZ;
}
kfree(buf);
- VPRINTK("Finish ECC initialization\n");
+ dev_dbg(host->dev, "Finish ECC initialization\n");
}
return 0;
}
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index bc8e8d9..3e726ee 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -178,7 +178,6 @@ static void ia_hack_tcq(IADEV *dev) {
static u16 get_desc (IADEV *dev, struct ia_vcc *iavcc) {
u_short desc_num, i;
- struct sk_buff *skb;
struct ia_vcc *iavcc_r = NULL;
unsigned long delta;
static unsigned long timer = 0;
@@ -202,8 +201,7 @@ static u16 get_desc (IADEV *dev, struct ia_vcc *iavcc) {
else
dev->ffL.tcq_rd -= 2;
*(u_short *)(dev->seg_ram + dev->ffL.tcq_rd) = i+1;
- if (!(skb = dev->desc_tbl[i].txskb) ||
- !(iavcc_r = dev->desc_tbl[i].iavcc))
+ if (!dev->desc_tbl[i].txskb || !(iavcc_r = dev->desc_tbl[i].iavcc))
printk("Fatal err, desc table vcc or skb is NULL\n");
else
iavcc_r->vc_desc_cnt--;
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index bc18769..eaa31e5 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -14,7 +14,6 @@
#include <linux/of.h>
#include <asm/sections.h>
-#include <asm/pgalloc.h>
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@@ -155,66 +154,6 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
}
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
- size_t align)
-{
- int nid = early_cpu_to_node(cpu);
-
- return memblock_alloc_try_nid(size, align,
- __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
-}
-
-static void __init pcpu_fc_free(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
-static void __init pcpu_populate_pte(unsigned long addr)
-{
- pgd_t *pgd = pgd_offset_k(addr);
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
-
- p4d = p4d_offset(pgd, addr);
- if (p4d_none(*p4d)) {
- pud_t *new;
-
- new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- p4d_populate(&init_mm, p4d, new);
- }
-
- pud = pud_offset(p4d, addr);
- if (pud_none(*pud)) {
- pmd_t *new;
-
- new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- pud_populate(&init_mm, pud, new);
- }
-
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd)) {
- pte_t *new;
-
- new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- if (!new)
- goto err_alloc;
- pmd_populate_kernel(&init_mm, pmd, new);
- }
-
- return;
-
-err_alloc:
- panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
- __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
-}
-#endif
-
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
@@ -229,7 +168,7 @@ void __init setup_per_cpu_areas(void)
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
pcpu_cpu_distance,
- pcpu_fc_alloc, pcpu_fc_free);
+ early_cpu_to_node);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
if (rc < 0)
pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n",
@@ -239,10 +178,7 @@ void __init setup_per_cpu_areas(void)
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
if (rc < 0)
- rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
- pcpu_fc_alloc,
- pcpu_fc_free,
- pcpu_populate_pte);
+ rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, early_cpu_to_node);
#endif
if (rc < 0)
panic("Failed to initialize percpu areas (err=%d).", rc);
diff --git a/drivers/base/firmware_loader/builtin/Makefile b/drivers/base/firmware_loader/builtin/Makefile
index eb4be45..6c067de 100644
--- a/drivers/base/firmware_loader/builtin/Makefile
+++ b/drivers/base/firmware_loader/builtin/Makefile
@@ -3,10 +3,10 @@
# Create $(fwdir) from $(CONFIG_EXTRA_FIRMWARE_DIR) -- if it doesn't have a
# leading /, it's relative to $(srctree).
-fwdir := $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE_DIR))
+fwdir := $(CONFIG_EXTRA_FIRMWARE_DIR)
fwdir := $(addprefix $(srctree)/,$(filter-out /%,$(fwdir)))$(filter /%,$(fwdir))
-firmware := $(addsuffix .gen.o, $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE)))
+firmware := $(addsuffix .gen.o, $(CONFIG_EXTRA_FIRMWARE))
obj-y += $(firmware)
FWNAME = $(patsubst $(obj)/%.gen.S,%,$@)
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 9466503..72b7a92 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -120,7 +120,11 @@ static unsigned int read_magic_time(void)
struct rtc_time time;
unsigned int val;
- mc146818_get_time(&time);
+ if (mc146818_get_time(&time) < 0) {
+ pr_err("Unable to read current time from RTC\n");
+ return 0;
+ }
+
pr_info("RTC time: %ptRt, date: %ptRd\n", &time, &time);
val = time.tm_year; /* 100 years */
if (val > 100)
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 588889b..6af111f 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -122,7 +122,7 @@ newtag(struct aoedev *d)
register ulong n;
n = jiffies & 0xffff;
- return n |= (++d->lasttag & 0x7fff) << 16;
+ return n | (++d->lasttag & 0x7fff) << 16;
}
static u32
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 8fe2e42..6e3f2f0 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -362,7 +362,6 @@ __setup("ramdisk_size=", ramdisk_size);
* (should share code eventually).
*/
static LIST_HEAD(brd_devices);
-static DEFINE_MUTEX(brd_devices_mutex);
static struct dentry *brd_debugfs_dir;
static int brd_alloc(int i)
@@ -372,21 +371,14 @@ static int brd_alloc(int i)
char buf[DISK_NAME_LEN];
int err = -ENOMEM;
- mutex_lock(&brd_devices_mutex);
- list_for_each_entry(brd, &brd_devices, brd_list) {
- if (brd->brd_number == i) {
- mutex_unlock(&brd_devices_mutex);
+ list_for_each_entry(brd, &brd_devices, brd_list)
+ if (brd->brd_number == i)
return -EEXIST;
- }
- }
brd = kzalloc(sizeof(*brd), GFP_KERNEL);
- if (!brd) {
- mutex_unlock(&brd_devices_mutex);
+ if (!brd)
return -ENOMEM;
- }
brd->brd_number = i;
list_add_tail(&brd->brd_list, &brd_devices);
- mutex_unlock(&brd_devices_mutex);
spin_lock_init(&brd->brd_lock);
INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
@@ -429,9 +421,7 @@ static int brd_alloc(int i)
out_cleanup_disk:
blk_cleanup_disk(disk);
out_free_dev:
- mutex_lock(&brd_devices_mutex);
list_del(&brd->brd_list);
- mutex_unlock(&brd_devices_mutex);
kfree(brd);
return err;
}
@@ -441,15 +431,19 @@ static void brd_probe(dev_t dev)
brd_alloc(MINOR(dev) / max_part);
}
-static void brd_del_one(struct brd_device *brd)
+static void brd_cleanup(void)
{
- del_gendisk(brd->brd_disk);
- blk_cleanup_disk(brd->brd_disk);
- brd_free_pages(brd);
- mutex_lock(&brd_devices_mutex);
- list_del(&brd->brd_list);
- mutex_unlock(&brd_devices_mutex);
- kfree(brd);
+ struct brd_device *brd, *next;
+
+ debugfs_remove_recursive(brd_debugfs_dir);
+
+ list_for_each_entry_safe(brd, next, &brd_devices, brd_list) {
+ del_gendisk(brd->brd_disk);
+ blk_cleanup_disk(brd->brd_disk);
+ brd_free_pages(brd);
+ list_del(&brd->brd_list);
+ kfree(brd);
+ }
}
static inline void brd_check_and_reset_par(void)
@@ -473,9 +467,18 @@ static inline void brd_check_and_reset_par(void)
static int __init brd_init(void)
{
- struct brd_device *brd, *next;
int err, i;
+ brd_check_and_reset_par();
+
+ brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
+
+ for (i = 0; i < rd_nr; i++) {
+ err = brd_alloc(i);
+ if (err)
+ goto out_free;
+ }
+
/*
* brd module now has a feature to instantiate underlying device
* structure on-demand, provided that there is an access dev node.
@@ -491,28 +494,16 @@ static int __init brd_init(void)
* dynamically.
*/
- if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe))
- return -EIO;
-
- brd_check_and_reset_par();
-
- brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
-
- for (i = 0; i < rd_nr; i++) {
- err = brd_alloc(i);
- if (err)
- goto out_free;
+ if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) {
+ err = -EIO;
+ goto out_free;
}
pr_info("brd: module loaded\n");
return 0;
out_free:
- unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
- debugfs_remove_recursive(brd_debugfs_dir);
-
- list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
- brd_del_one(brd);
+ brd_cleanup();
pr_info("brd: module NOT loaded !!!\n");
return err;
@@ -520,13 +511,9 @@ static int __init brd_init(void)
static void __exit brd_exit(void)
{
- struct brd_device *brd, *next;
unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
- debugfs_remove_recursive(brd_debugfs_dir);
-
- list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
- brd_del_one(brd);
+ brd_cleanup();
pr_info("brd: module unloaded\n");
}
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index b1b05c4..01cbbfc 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -820,7 +820,7 @@ static inline int queue_on_root_worker(struct cgroup_subsys_state *css)
static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd)
{
- struct rb_node **node = &(lo->worker_tree.rb_node), *parent = NULL;
+ struct rb_node **node, *parent = NULL;
struct loop_worker *cur_worker, *worker = NULL;
struct work_struct *work;
struct list_head *cmd_list;
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 8f140da..4203cda 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -6189,7 +6189,7 @@ static inline size_t next_token(const char **buf)
* These are the characters that produce nonzero for
* isspace() in the "C" and "POSIX" locales.
*/
- const char *spaces = " \f\n\r\t\v";
+ static const char spaces[] = " \f\n\r\t\v";
*buf += strspn(*buf, spaces); /* Find start of token */
@@ -6495,7 +6495,8 @@ static int rbd_add_parse_args(const char *buf,
pctx.opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
pctx.opts->trim = RBD_TRIM_DEFAULT;
- ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL);
+ ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL,
+ ',');
if (ret)
goto out_err;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c3dc3cd..c443cd6 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -976,7 +976,7 @@ static void virtblk_remove(struct virtio_device *vdev)
mutex_lock(&vblk->vdev_mutex);
/* Stop all the virtqueues. */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
/* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
vblk->vdev = NULL;
@@ -995,7 +995,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
struct virtio_blk *vblk = vdev->priv;
/* Ensure we don't receive any more interrupts */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
/* Make sure no work handler is accessing the device. */
flush_work(&vblk->config_work);
diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c
index 076e494..67c2126 100644
--- a/drivers/bluetooth/virtio_bt.c
+++ b/drivers/bluetooth/virtio_bt.c
@@ -367,7 +367,7 @@ static void virtbt_remove(struct virtio_device *vdev)
struct hci_dev *hdev = vbt->hdev;
hci_unregister_dev(hdev);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
hci_free_dev(hdev);
vbt->hdev = NULL;
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 0a7dde1..e856df7 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -179,9 +179,9 @@ static void remove_common(struct virtio_device *vdev)
vi->data_avail = 0;
vi->data_idx = 0;
complete(&vi->have_data);
- vdev->config->reset(vdev);
if (vi->hwrng_register_done)
hwrng_unregister(&vi->hwrng);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
ida_simple_remove(&rng_index_ida, vi->index);
kfree(vi);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 227fb78..b411182 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -101,7 +101,7 @@
* ===============================
*
* There are four exported interfaces; two for use within the kernel,
- * and two or use from userspace.
+ * and two for use from userspace.
*
* Exported interfaces ---- userspace output
* -----------------------------------------
@@ -124,7 +124,7 @@
*
* The primary kernel interface is
*
- * void get_random_bytes(void *buf, int nbytes);
+ * void get_random_bytes(void *buf, int nbytes);
*
* This interface will return the requested number of random bytes,
* and place it in the requested buffer. This is equivalent to a
@@ -132,10 +132,10 @@
*
* For less critical applications, there are the functions:
*
- * u32 get_random_u32()
- * u64 get_random_u64()
- * unsigned int get_random_int()
- * unsigned long get_random_long()
+ * u32 get_random_u32()
+ * u64 get_random_u64()
+ * unsigned int get_random_int()
+ * unsigned long get_random_long()
*
* These are produced by a cryptographic RNG seeded from get_random_bytes,
* and so do not deplete the entropy pool as much. These are recommended
@@ -197,10 +197,10 @@
* from the devices are:
*
* void add_device_randomness(const void *buf, unsigned int size);
- * void add_input_randomness(unsigned int type, unsigned int code,
+ * void add_input_randomness(unsigned int type, unsigned int code,
* unsigned int value);
* void add_interrupt_randomness(int irq);
- * void add_disk_randomness(struct gendisk *disk);
+ * void add_disk_randomness(struct gendisk *disk);
* void add_hwgenerator_randomness(const char *buffer, size_t count,
* size_t entropy);
* void add_bootloader_randomness(const void *buf, unsigned int size);
@@ -296,8 +296,8 @@
* /dev/random and /dev/urandom created already, they can be created
* by using the commands:
*
- * mknod /dev/random c 1 8
- * mknod /dev/urandom c 1 9
+ * mknod /dev/random c 1 8
+ * mknod /dev/urandom c 1 9
*
* Acknowledgements:
* =================
@@ -337,7 +337,6 @@
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/percpu.h>
-#include <linux/fips.h>
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
@@ -360,30 +359,11 @@
/* #define ADD_INTERRUPT_BENCH */
/*
- * Configuration information
- */
-#define INPUT_POOL_SHIFT 12
-#define INPUT_POOL_WORDS (1 << (INPUT_POOL_SHIFT-5))
-#define OUTPUT_POOL_SHIFT 10
-#define OUTPUT_POOL_WORDS (1 << (OUTPUT_POOL_SHIFT-5))
-#define EXTRACT_SIZE (BLAKE2S_HASH_SIZE / 2)
-
-/*
- * To allow fractional bits to be tracked, the entropy_count field is
- * denominated in units of 1/8th bits.
- *
- * 2*(ENTROPY_SHIFT + poolbitshift) must <= 31, or the multiply in
- * credit_entropy_bits() needs to be 64 bits wide.
- */
-#define ENTROPY_SHIFT 3
-#define ENTROPY_BITS(r) ((r)->entropy_count >> ENTROPY_SHIFT)
-
-/*
* If the entropy count falls under this number of bits, then we
* should wake up processes which are selecting or polling on write
* access to /dev/random.
*/
-static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
+static int random_write_wakeup_bits = 28 * (1 << 5);
/*
* Originally, we used a primitive polynomial of degree .poolwords
@@ -430,14 +410,27 @@ static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
* polynomial which improves the resulting TGFSR polynomial to be
* irreducible, which we have made here.
*/
-static const struct poolinfo {
- int poolbitshift, poolwords, poolbytes, poolfracbits;
-#define S(x) ilog2(x)+5, (x), (x)*4, (x) << (ENTROPY_SHIFT+5)
- int tap1, tap2, tap3, tap4, tap5;
-} poolinfo_table[] = {
- /* was: x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 */
+enum poolinfo {
+ POOL_WORDS = 128,
+ POOL_WORDMASK = POOL_WORDS - 1,
+ POOL_BYTES = POOL_WORDS * sizeof(u32),
+ POOL_BITS = POOL_BYTES * 8,
+ POOL_BITSHIFT = ilog2(POOL_BITS),
+
+ /* To allow fractional bits to be tracked, the entropy_count field is
+ * denominated in units of 1/8th bits. */
+ POOL_ENTROPY_SHIFT = 3,
+#define POOL_ENTROPY_BITS() (input_pool.entropy_count >> POOL_ENTROPY_SHIFT)
+ POOL_FRACBITS = POOL_BITS << POOL_ENTROPY_SHIFT,
+
/* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */
- { S(128), 104, 76, 51, 25, 1 },
+ POOL_TAP1 = 104,
+ POOL_TAP2 = 76,
+ POOL_TAP3 = 51,
+ POOL_TAP4 = 25,
+ POOL_TAP5 = 1,
+
+ EXTRACT_SIZE = BLAKE2S_HASH_SIZE / 2
};
/*
@@ -450,9 +443,9 @@ static DEFINE_SPINLOCK(random_ready_list_lock);
static LIST_HEAD(random_ready_list);
struct crng_state {
- __u32 state[16];
- unsigned long init_time;
- spinlock_t lock;
+ u32 state[16];
+ unsigned long init_time;
+ spinlock_t lock;
};
static struct crng_state primary_crng = {
@@ -476,10 +469,10 @@ static bool crng_need_final_init = false;
#define crng_ready() (likely(crng_init > 1))
static int crng_init_cnt = 0;
static unsigned long crng_global_init_time = 0;
-#define CRNG_INIT_CNT_THRESH (2*CHACHA_KEY_SIZE)
-static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]);
+#define CRNG_INIT_CNT_THRESH (2 * CHACHA_KEY_SIZE)
+static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE]);
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA_BLOCK_SIZE], int used);
+ u8 tmp[CHACHA_BLOCK_SIZE], int used);
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);
@@ -500,38 +493,23 @@ MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
*
**********************************************************************/
-struct entropy_store;
-struct entropy_store {
- /* read-only data: */
- const struct poolinfo *poolinfo;
- __u32 *pool;
- const char *name;
+static u32 input_pool_data[POOL_WORDS] __latent_entropy;
- /* read-write data: */
+static struct {
spinlock_t lock;
- unsigned short add_ptr;
- unsigned short input_rotate;
+ u16 add_ptr;
+ u16 input_rotate;
int entropy_count;
- unsigned int last_data_init:1;
- __u8 last_data[EXTRACT_SIZE];
-};
-
-static ssize_t extract_entropy(struct entropy_store *r, void *buf,
- size_t nbytes, int min, int rsvd);
-static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
- size_t nbytes, int fips);
-
-static void crng_reseed(struct crng_state *crng, struct entropy_store *r);
-static __u32 input_pool_data[INPUT_POOL_WORDS] __latent_entropy;
-
-static struct entropy_store input_pool = {
- .poolinfo = &poolinfo_table[0],
- .name = "input",
+} input_pool = {
.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
- .pool = input_pool_data
};
-static __u32 const twist_table[8] = {
+static ssize_t extract_entropy(void *buf, size_t nbytes, int min);
+static ssize_t _extract_entropy(void *buf, size_t nbytes);
+
+static void crng_reseed(struct crng_state *crng, bool use_input_pool);
+
+static const u32 twist_table[8] = {
0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
@@ -545,39 +523,31 @@ static __u32 const twist_table[8] = {
* it's cheap to do so and helps slightly in the expected case where
* the entropy is concentrated in the low-order bits.
*/
-static void _mix_pool_bytes(struct entropy_store *r, const void *in,
- int nbytes)
+static void _mix_pool_bytes(const void *in, int nbytes)
{
- unsigned long i, tap1, tap2, tap3, tap4, tap5;
+ unsigned long i;
int input_rotate;
- int wordmask = r->poolinfo->poolwords - 1;
- const unsigned char *bytes = in;
- __u32 w;
+ const u8 *bytes = in;
+ u32 w;
- tap1 = r->poolinfo->tap1;
- tap2 = r->poolinfo->tap2;
- tap3 = r->poolinfo->tap3;
- tap4 = r->poolinfo->tap4;
- tap5 = r->poolinfo->tap5;
-
- input_rotate = r->input_rotate;
- i = r->add_ptr;
+ input_rotate = input_pool.input_rotate;
+ i = input_pool.add_ptr;
/* mix one byte at a time to simplify size handling and churn faster */
while (nbytes--) {
w = rol32(*bytes++, input_rotate);
- i = (i - 1) & wordmask;
+ i = (i - 1) & POOL_WORDMASK;
/* XOR in the various taps */
- w ^= r->pool[i];
- w ^= r->pool[(i + tap1) & wordmask];
- w ^= r->pool[(i + tap2) & wordmask];
- w ^= r->pool[(i + tap3) & wordmask];
- w ^= r->pool[(i + tap4) & wordmask];
- w ^= r->pool[(i + tap5) & wordmask];
+ w ^= input_pool_data[i];
+ w ^= input_pool_data[(i + POOL_TAP1) & POOL_WORDMASK];
+ w ^= input_pool_data[(i + POOL_TAP2) & POOL_WORDMASK];
+ w ^= input_pool_data[(i + POOL_TAP3) & POOL_WORDMASK];
+ w ^= input_pool_data[(i + POOL_TAP4) & POOL_WORDMASK];
+ w ^= input_pool_data[(i + POOL_TAP5) & POOL_WORDMASK];
/* Mix the result back in with a twist */
- r->pool[i] = (w >> 3) ^ twist_table[w & 7];
+ input_pool_data[i] = (w >> 3) ^ twist_table[w & 7];
/*
* Normally, we add 7 bits of rotation to the pool.
@@ -588,33 +558,31 @@ static void _mix_pool_bytes(struct entropy_store *r, const void *in,
input_rotate = (input_rotate + (i ? 7 : 14)) & 31;
}
- r->input_rotate = input_rotate;
- r->add_ptr = i;
+ input_pool.input_rotate = input_rotate;
+ input_pool.add_ptr = i;
}
-static void __mix_pool_bytes(struct entropy_store *r, const void *in,
- int nbytes)
+static void __mix_pool_bytes(const void *in, int nbytes)
{
- trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
- _mix_pool_bytes(r, in, nbytes);
+ trace_mix_pool_bytes_nolock(nbytes, _RET_IP_);
+ _mix_pool_bytes(in, nbytes);
}
-static void mix_pool_bytes(struct entropy_store *r, const void *in,
- int nbytes)
+static void mix_pool_bytes(const void *in, int nbytes)
{
unsigned long flags;
- trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
- spin_lock_irqsave(&r->lock, flags);
- _mix_pool_bytes(r, in, nbytes);
- spin_unlock_irqrestore(&r->lock, flags);
+ trace_mix_pool_bytes(nbytes, _RET_IP_);
+ spin_lock_irqsave(&input_pool.lock, flags);
+ _mix_pool_bytes(in, nbytes);
+ spin_unlock_irqrestore(&input_pool.lock, flags);
}
struct fast_pool {
- __u32 pool[4];
- unsigned long last;
- unsigned short reg_idx;
- unsigned char count;
+ u32 pool[4];
+ unsigned long last;
+ u16 reg_idx;
+ u8 count;
};
/*
@@ -624,8 +592,8 @@ struct fast_pool {
*/
static void fast_mix(struct fast_pool *f)
{
- __u32 a = f->pool[0], b = f->pool[1];
- __u32 c = f->pool[2], d = f->pool[3];
+ u32 a = f->pool[0], b = f->pool[1];
+ u32 c = f->pool[2], d = f->pool[3];
a += b; c += d;
b = rol32(b, 6); d = rol32(d, 27);
@@ -669,17 +637,19 @@ static void process_random_ready_list(void)
* Use credit_entropy_bits_safe() if the value comes from userspace
* or otherwise should be checked for extreme values.
*/
-static void credit_entropy_bits(struct entropy_store *r, int nbits)
+static void credit_entropy_bits(int nbits)
{
- int entropy_count, orig;
- const int pool_size = r->poolinfo->poolfracbits;
- int nfrac = nbits << ENTROPY_SHIFT;
+ int entropy_count, entropy_bits, orig;
+ int nfrac = nbits << POOL_ENTROPY_SHIFT;
+
+ /* Ensure that the multiplication can avoid being 64 bits wide. */
+ BUILD_BUG_ON(2 * (POOL_ENTROPY_SHIFT + POOL_BITSHIFT) > 31);
if (!nbits)
return;
retry:
- entropy_count = orig = READ_ONCE(r->entropy_count);
+ entropy_count = orig = READ_ONCE(input_pool.entropy_count);
if (nfrac < 0) {
/* Debit */
entropy_count += nfrac;
@@ -706,50 +676,43 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
* turns no matter how large nbits is.
*/
int pnfrac = nfrac;
- const int s = r->poolinfo->poolbitshift + ENTROPY_SHIFT + 2;
+ const int s = POOL_BITSHIFT + POOL_ENTROPY_SHIFT + 2;
/* The +2 corresponds to the /4 in the denominator */
do {
- unsigned int anfrac = min(pnfrac, pool_size/2);
+ unsigned int anfrac = min(pnfrac, POOL_FRACBITS / 2);
unsigned int add =
- ((pool_size - entropy_count)*anfrac*3) >> s;
+ ((POOL_FRACBITS - entropy_count) * anfrac * 3) >> s;
entropy_count += add;
pnfrac -= anfrac;
- } while (unlikely(entropy_count < pool_size-2 && pnfrac));
+ } while (unlikely(entropy_count < POOL_FRACBITS - 2 && pnfrac));
}
if (WARN_ON(entropy_count < 0)) {
- pr_warn("negative entropy/overflow: pool %s count %d\n",
- r->name, entropy_count);
+ pr_warn("negative entropy/overflow: count %d\n", entropy_count);
entropy_count = 0;
- } else if (entropy_count > pool_size)
- entropy_count = pool_size;
- if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+ } else if (entropy_count > POOL_FRACBITS)
+ entropy_count = POOL_FRACBITS;
+ if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig)
goto retry;
- trace_credit_entropy_bits(r->name, nbits,
- entropy_count >> ENTROPY_SHIFT, _RET_IP_);
+ trace_credit_entropy_bits(nbits, entropy_count >> POOL_ENTROPY_SHIFT, _RET_IP_);
- if (r == &input_pool) {
- int entropy_bits = entropy_count >> ENTROPY_SHIFT;
-
- if (crng_init < 2 && entropy_bits >= 128)
- crng_reseed(&primary_crng, r);
- }
+ entropy_bits = entropy_count >> POOL_ENTROPY_SHIFT;
+ if (crng_init < 2 && entropy_bits >= 128)
+ crng_reseed(&primary_crng, true);
}
-static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
+static int credit_entropy_bits_safe(int nbits)
{
- const int nbits_max = r->poolinfo->poolwords * 32;
-
if (nbits < 0)
return -EINVAL;
/* Cap the value to avoid overflows */
- nbits = min(nbits, nbits_max);
+ nbits = min(nbits, POOL_BITS);
- credit_entropy_bits(r, nbits);
+ credit_entropy_bits(nbits);
return 0;
}
@@ -759,7 +722,7 @@ static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
*
*********************************************************************/
-#define CRNG_RESEED_INTERVAL (300*HZ)
+#define CRNG_RESEED_INTERVAL (300 * HZ)
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
@@ -783,9 +746,9 @@ early_param("random.trust_cpu", parse_trust_cpu);
static bool crng_init_try_arch(struct crng_state *crng)
{
- int i;
- bool arch_init = true;
- unsigned long rv;
+ int i;
+ bool arch_init = true;
+ unsigned long rv;
for (i = 4; i < 16; i++) {
if (!arch_get_random_seed_long(&rv) &&
@@ -801,9 +764,9 @@ static bool crng_init_try_arch(struct crng_state *crng)
static bool __init crng_init_try_arch_early(struct crng_state *crng)
{
- int i;
- bool arch_init = true;
- unsigned long rv;
+ int i;
+ bool arch_init = true;
+ unsigned long rv;
for (i = 4; i < 16; i++) {
if (!arch_get_random_seed_long_early(&rv) &&
@@ -820,14 +783,14 @@ static bool __init crng_init_try_arch_early(struct crng_state *crng)
static void crng_initialize_secondary(struct crng_state *crng)
{
chacha_init_consts(crng->state);
- _get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
+ _get_random_bytes(&crng->state[4], sizeof(u32) * 12);
crng_init_try_arch(crng);
crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
}
static void __init crng_initialize_primary(struct crng_state *crng)
{
- _extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0);
+ _extract_entropy(&crng->state[4], sizeof(u32) * 12);
if (crng_init_try_arch_early(crng) && trust_cpu && crng_init < 2) {
invalidate_batched_entropy();
numa_crng_init();
@@ -873,7 +836,7 @@ static void do_numa_crng_init(struct work_struct *work)
struct crng_state *crng;
struct crng_state **pool;
- pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
+ pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL | __GFP_NOFAIL);
for_each_online_node(i) {
crng = kmalloc_node(sizeof(struct crng_state),
GFP_KERNEL | __GFP_NOFAIL, i);
@@ -917,10 +880,10 @@ static struct crng_state *select_crng(void)
* path. So we can't afford to dilly-dally. Returns the number of
* bytes processed from cp.
*/
-static size_t crng_fast_load(const char *cp, size_t len)
+static size_t crng_fast_load(const u8 *cp, size_t len)
{
unsigned long flags;
- char *p;
+ u8 *p;
size_t ret = 0;
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
@@ -929,7 +892,7 @@ static size_t crng_fast_load(const char *cp, size_t len)
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 0;
}
- p = (unsigned char *) &primary_crng.state[4];
+ p = (u8 *)&primary_crng.state[4];
while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp;
cp++; crng_init_cnt++; len--; ret++;
@@ -957,14 +920,14 @@ static size_t crng_fast_load(const char *cp, size_t len)
* like a fixed DMI table (for example), which might very well be
* unique to the machine, but is otherwise unvarying.
*/
-static int crng_slow_load(const char *cp, size_t len)
+static int crng_slow_load(const u8 *cp, size_t len)
{
- unsigned long flags;
- static unsigned char lfsr = 1;
- unsigned char tmp;
- unsigned i, max = CHACHA_KEY_SIZE;
- const char * src_buf = cp;
- char * dest_buf = (char *) &primary_crng.state[4];
+ unsigned long flags;
+ static u8 lfsr = 1;
+ u8 tmp;
+ unsigned int i, max = CHACHA_KEY_SIZE;
+ const u8 *src_buf = cp;
+ u8 *dest_buf = (u8 *)&primary_crng.state[4];
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
return 0;
@@ -975,7 +938,7 @@ static int crng_slow_load(const char *cp, size_t len)
if (len > max)
max = len;
- for (i = 0; i < max ; i++) {
+ for (i = 0; i < max; i++) {
tmp = lfsr;
lfsr >>= 1;
if (tmp & 1)
@@ -988,17 +951,17 @@ static int crng_slow_load(const char *cp, size_t len)
return 1;
}
-static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
+static void crng_reseed(struct crng_state *crng, bool use_input_pool)
{
- unsigned long flags;
- int i, num;
+ unsigned long flags;
+ int i, num;
union {
- __u8 block[CHACHA_BLOCK_SIZE];
- __u32 key[8];
+ u8 block[CHACHA_BLOCK_SIZE];
+ u32 key[8];
} buf;
- if (r) {
- num = extract_entropy(r, &buf, 32, 16, 0);
+ if (use_input_pool) {
+ num = extract_entropy(&buf, 32, 16);
if (num == 0)
return;
} else {
@@ -1008,11 +971,11 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
}
spin_lock_irqsave(&crng->lock, flags);
for (i = 0; i < 8; i++) {
- unsigned long rv;
+ unsigned long rv;
if (!arch_get_random_seed_long(&rv) &&
!arch_get_random_long(&rv))
rv = random_get_entropy();
- crng->state[i+4] ^= buf.key[i] ^ rv;
+ crng->state[i + 4] ^= buf.key[i] ^ rv;
}
memzero_explicit(&buf, sizeof(buf));
WRITE_ONCE(crng->init_time, jiffies);
@@ -1020,8 +983,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
crng_finalize_init(crng);
}
-static void _extract_crng(struct crng_state *crng,
- __u8 out[CHACHA_BLOCK_SIZE])
+static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE])
{
unsigned long flags, init_time;
@@ -1029,8 +991,7 @@ static void _extract_crng(struct crng_state *crng,
init_time = READ_ONCE(crng->init_time);
if (time_after(READ_ONCE(crng_global_init_time), init_time) ||
time_after(jiffies, init_time + CRNG_RESEED_INTERVAL))
- crng_reseed(crng, crng == &primary_crng ?
- &input_pool : NULL);
+ crng_reseed(crng, crng == &primary_crng);
}
spin_lock_irqsave(&crng->lock, flags);
chacha20_block(&crng->state[0], out);
@@ -1039,7 +1000,7 @@ static void _extract_crng(struct crng_state *crng,
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE])
+static void extract_crng(u8 out[CHACHA_BLOCK_SIZE])
{
_extract_crng(select_crng(), out);
}
@@ -1049,26 +1010,26 @@ static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE])
* enough) to mutate the CRNG key to provide backtracking protection.
*/
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA_BLOCK_SIZE], int used)
+ u8 tmp[CHACHA_BLOCK_SIZE], int used)
{
- unsigned long flags;
- __u32 *s, *d;
- int i;
+ unsigned long flags;
+ u32 *s, *d;
+ int i;
- used = round_up(used, sizeof(__u32));
+ used = round_up(used, sizeof(u32));
if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) {
extract_crng(tmp);
used = 0;
}
spin_lock_irqsave(&crng->lock, flags);
- s = (__u32 *) &tmp[used];
+ s = (u32 *)&tmp[used];
d = &crng->state[4];
- for (i=0; i < 8; i++)
+ for (i = 0; i < 8; i++)
*d++ ^= *s++;
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used)
+static void crng_backtrack_protect(u8 tmp[CHACHA_BLOCK_SIZE], int used)
{
_crng_backtrack_protect(select_crng(), tmp, used);
}
@@ -1076,7 +1037,7 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used)
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
ssize_t ret = 0, i = CHACHA_BLOCK_SIZE;
- __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
+ u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
int large_request = (nbytes > 256);
while (nbytes) {
@@ -1108,7 +1069,6 @@ static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
return ret;
}
-
/*********************************************************************
*
* Entropy input management
@@ -1141,8 +1101,8 @@ void add_device_randomness(const void *buf, unsigned int size)
trace_add_device_randomness(size, _RET_IP_);
spin_lock_irqsave(&input_pool.lock, flags);
- _mix_pool_bytes(&input_pool, buf, size);
- _mix_pool_bytes(&input_pool, &time, sizeof(time));
+ _mix_pool_bytes(buf, size);
+ _mix_pool_bytes(&time, sizeof(time));
spin_unlock_irqrestore(&input_pool.lock, flags);
}
EXPORT_SYMBOL(add_device_randomness);
@@ -1161,19 +1121,17 @@ static struct timer_rand_state input_timer_state = INIT_TIMER_RAND_STATE;
*/
static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
{
- struct entropy_store *r;
struct {
long jiffies;
- unsigned cycles;
- unsigned num;
+ unsigned int cycles;
+ unsigned int num;
} sample;
long delta, delta2, delta3;
sample.jiffies = jiffies;
sample.cycles = random_get_entropy();
sample.num = num;
- r = &input_pool;
- mix_pool_bytes(r, &sample, sizeof(sample));
+ mix_pool_bytes(&sample, sizeof(sample));
/*
* Calculate number of bits of randomness we probably added.
@@ -1205,11 +1163,11 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
* Round down by 1 bit on general principles,
* and limit entropy estimate to 12 bits.
*/
- credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
+ credit_entropy_bits(min_t(int, fls(delta >> 1), 11));
}
void add_input_randomness(unsigned int type, unsigned int code,
- unsigned int value)
+ unsigned int value)
{
static unsigned char last_value;
@@ -1220,7 +1178,7 @@ void add_input_randomness(unsigned int type, unsigned int code,
last_value = value;
add_timer_randomness(&input_timer_state,
(type << 4) ^ code ^ (code >> 4) ^ value);
- trace_add_input_randomness(ENTROPY_BITS(&input_pool));
+ trace_add_input_randomness(POOL_ENTROPY_BITS());
}
EXPORT_SYMBOL_GPL(add_input_randomness);
@@ -1229,33 +1187,33 @@ static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
#ifdef ADD_INTERRUPT_BENCH
static unsigned long avg_cycles, avg_deviation;
-#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */
-#define FIXED_1_2 (1 << (AVG_SHIFT-1))
+#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */
+#define FIXED_1_2 (1 << (AVG_SHIFT - 1))
static void add_interrupt_bench(cycles_t start)
{
- long delta = random_get_entropy() - start;
+ long delta = random_get_entropy() - start;
- /* Use a weighted moving average */
- delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT);
- avg_cycles += delta;
- /* And average deviation */
- delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT);
- avg_deviation += delta;
+ /* Use a weighted moving average */
+ delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT);
+ avg_cycles += delta;
+ /* And average deviation */
+ delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT);
+ avg_deviation += delta;
}
#else
#define add_interrupt_bench(x)
#endif
-static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
+static u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
{
- __u32 *ptr = (__u32 *) regs;
+ u32 *ptr = (u32 *)regs;
unsigned int idx;
if (regs == NULL)
return 0;
idx = READ_ONCE(f->reg_idx);
- if (idx >= sizeof(struct pt_regs) / sizeof(__u32))
+ if (idx >= sizeof(struct pt_regs) / sizeof(u32))
idx = 0;
ptr += idx++;
WRITE_ONCE(f->reg_idx, idx);
@@ -1264,13 +1222,12 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
void add_interrupt_randomness(int irq)
{
- struct entropy_store *r;
- struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
- struct pt_regs *regs = get_irq_regs();
- unsigned long now = jiffies;
- cycles_t cycles = random_get_entropy();
- __u32 c_high, j_high;
- __u64 ip;
+ struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
+ struct pt_regs *regs = get_irq_regs();
+ unsigned long now = jiffies;
+ cycles_t cycles = random_get_entropy();
+ u32 c_high, j_high;
+ u64 ip;
if (cycles == 0)
cycles = get_reg(fast_pool, regs);
@@ -1280,38 +1237,35 @@ void add_interrupt_randomness(int irq)
fast_pool->pool[1] ^= now ^ c_high;
ip = regs ? instruction_pointer(regs) : _RET_IP_;
fast_pool->pool[2] ^= ip;
- fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
- get_reg(fast_pool, regs);
+ fast_pool->pool[3] ^=
+ (sizeof(ip) > 4) ? ip >> 32 : get_reg(fast_pool, regs);
fast_mix(fast_pool);
add_interrupt_bench(cycles);
if (unlikely(crng_init == 0)) {
if ((fast_pool->count >= 64) &&
- crng_fast_load((char *) fast_pool->pool,
- sizeof(fast_pool->pool)) > 0) {
+ crng_fast_load((u8 *)fast_pool->pool, sizeof(fast_pool->pool)) > 0) {
fast_pool->count = 0;
fast_pool->last = now;
}
return;
}
- if ((fast_pool->count < 64) &&
- !time_after(now, fast_pool->last + HZ))
+ if ((fast_pool->count < 64) && !time_after(now, fast_pool->last + HZ))
return;
- r = &input_pool;
- if (!spin_trylock(&r->lock))
+ if (!spin_trylock(&input_pool.lock))
return;
fast_pool->last = now;
- __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
- spin_unlock(&r->lock);
+ __mix_pool_bytes(&fast_pool->pool, sizeof(fast_pool->pool));
+ spin_unlock(&input_pool.lock);
fast_pool->count = 0;
/* award one bit for the contents of the fast pool */
- credit_entropy_bits(r, 1);
+ credit_entropy_bits(1);
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);
@@ -1322,7 +1276,7 @@ void add_disk_randomness(struct gendisk *disk)
return;
/* first major is 1, so we get >= 0x200 here */
add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
- trace_add_disk_randomness(disk_devt(disk), ENTROPY_BITS(&input_pool));
+ trace_add_disk_randomness(disk_devt(disk), POOL_ENTROPY_BITS());
}
EXPORT_SYMBOL_GPL(add_disk_randomness);
#endif
@@ -1337,43 +1291,36 @@ EXPORT_SYMBOL_GPL(add_disk_randomness);
* This function decides how many bytes to actually take from the
* given pool, and also debits the entropy count accordingly.
*/
-static size_t account(struct entropy_store *r, size_t nbytes, int min,
- int reserved)
+static size_t account(size_t nbytes, int min)
{
- int entropy_count, orig, have_bytes;
+ int entropy_count, orig;
size_t ibytes, nfrac;
- BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
+ BUG_ON(input_pool.entropy_count > POOL_FRACBITS);
/* Can we pull enough? */
retry:
- entropy_count = orig = READ_ONCE(r->entropy_count);
- ibytes = nbytes;
- /* never pull more than available */
- have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
-
- if ((have_bytes -= reserved) < 0)
- have_bytes = 0;
- ibytes = min_t(size_t, ibytes, have_bytes);
- if (ibytes < min)
- ibytes = 0;
-
+ entropy_count = orig = READ_ONCE(input_pool.entropy_count);
if (WARN_ON(entropy_count < 0)) {
- pr_warn("negative entropy count: pool %s count %d\n",
- r->name, entropy_count);
+ pr_warn("negative entropy count: count %d\n", entropy_count);
entropy_count = 0;
}
- nfrac = ibytes << (ENTROPY_SHIFT + 3);
- if ((size_t) entropy_count > nfrac)
+
+ /* never pull more than available */
+ ibytes = min_t(size_t, nbytes, entropy_count >> (POOL_ENTROPY_SHIFT + 3));
+ if (ibytes < min)
+ ibytes = 0;
+ nfrac = ibytes << (POOL_ENTROPY_SHIFT + 3);
+ if ((size_t)entropy_count > nfrac)
entropy_count -= nfrac;
else
entropy_count = 0;
- if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+ if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig)
goto retry;
- trace_debit_entropy(r->name, 8 * ibytes);
- if (ibytes && ENTROPY_BITS(r) < random_write_wakeup_bits) {
+ trace_debit_entropy(8 * ibytes);
+ if (ibytes && POOL_ENTROPY_BITS() < random_write_wakeup_bits) {
wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
@@ -1386,7 +1333,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
*
* Note: we assume that .poolwords is a multiple of 16 words.
*/
-static void extract_buf(struct entropy_store *r, __u8 *out)
+static void extract_buf(u8 *out)
{
struct blake2s_state state __aligned(__alignof__(unsigned long));
u8 hash[BLAKE2S_HASH_SIZE];
@@ -1408,9 +1355,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
}
/* Generate a hash across the pool */
- spin_lock_irqsave(&r->lock, flags);
- blake2s_update(&state, (const u8 *)r->pool,
- r->poolinfo->poolwords * sizeof(*r->pool));
+ spin_lock_irqsave(&input_pool.lock, flags);
+ blake2s_update(&state, (const u8 *)input_pool_data, POOL_BYTES);
blake2s_final(&state, hash); /* final zeros out state */
/*
@@ -1422,8 +1368,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
* brute-forcing the feedback as hard as brute-forcing the
* hash.
*/
- __mix_pool_bytes(r, hash, sizeof(hash));
- spin_unlock_irqrestore(&r->lock, flags);
+ __mix_pool_bytes(hash, sizeof(hash));
+ spin_unlock_irqrestore(&input_pool.lock, flags);
/* Note that EXTRACT_SIZE is half of hash size here, because above
* we've dumped the full length back into mixer. By reducing the
@@ -1433,23 +1379,13 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
memzero_explicit(hash, sizeof(hash));
}
-static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
- size_t nbytes, int fips)
+static ssize_t _extract_entropy(void *buf, size_t nbytes)
{
ssize_t ret = 0, i;
- __u8 tmp[EXTRACT_SIZE];
- unsigned long flags;
+ u8 tmp[EXTRACT_SIZE];
while (nbytes) {
- extract_buf(r, tmp);
-
- if (fips) {
- spin_lock_irqsave(&r->lock, flags);
- if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
- panic("Hardware RNG duplicated output!\n");
- memcpy(r->last_data, tmp, EXTRACT_SIZE);
- spin_unlock_irqrestore(&r->lock, flags);
- }
+ extract_buf(tmp);
i = min_t(int, nbytes, EXTRACT_SIZE);
memcpy(buf, tmp, i);
nbytes -= i;
@@ -1468,42 +1404,19 @@ static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
* returns it in a buffer.
*
* The min parameter specifies the minimum amount we can pull before
- * failing to avoid races that defeat catastrophic reseeding while the
- * reserved parameter indicates how much entropy we must leave in the
- * pool after each pull to avoid starving other readers.
+ * failing to avoid races that defeat catastrophic reseeding.
*/
-static ssize_t extract_entropy(struct entropy_store *r, void *buf,
- size_t nbytes, int min, int reserved)
+static ssize_t extract_entropy(void *buf, size_t nbytes, int min)
{
- __u8 tmp[EXTRACT_SIZE];
- unsigned long flags;
-
- /* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */
- if (fips_enabled) {
- spin_lock_irqsave(&r->lock, flags);
- if (!r->last_data_init) {
- r->last_data_init = 1;
- spin_unlock_irqrestore(&r->lock, flags);
- trace_extract_entropy(r->name, EXTRACT_SIZE,
- ENTROPY_BITS(r), _RET_IP_);
- extract_buf(r, tmp);
- spin_lock_irqsave(&r->lock, flags);
- memcpy(r->last_data, tmp, EXTRACT_SIZE);
- }
- spin_unlock_irqrestore(&r->lock, flags);
- }
-
- trace_extract_entropy(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
- nbytes = account(r, nbytes, min, reserved);
-
- return _extract_entropy(r, buf, nbytes, fips_enabled);
+ trace_extract_entropy(nbytes, POOL_ENTROPY_BITS(), _RET_IP_);
+ nbytes = account(nbytes, min);
+ return _extract_entropy(buf, nbytes);
}
#define warn_unseeded_randomness(previous) \
- _warn_unseeded_randomness(__func__, (void *) _RET_IP_, (previous))
+ _warn_unseeded_randomness(__func__, (void *)_RET_IP_, (previous))
-static void _warn_unseeded_randomness(const char *func_name, void *caller,
- void **previous)
+static void _warn_unseeded_randomness(const char *func_name, void *caller, void **previous)
{
#ifdef CONFIG_WARN_ALL_UNSEEDED_RANDOM
const bool print_once = false;
@@ -1511,8 +1424,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
static bool print_once __read_mostly;
#endif
- if (print_once ||
- crng_ready() ||
+ if (print_once || crng_ready() ||
(previous && (caller == READ_ONCE(*previous))))
return;
WRITE_ONCE(*previous, caller);
@@ -1520,9 +1432,8 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
print_once = true;
#endif
if (__ratelimit(&unseeded_warning))
- printk_deferred(KERN_NOTICE "random: %s called from %pS "
- "with crng_init=%d\n", func_name, caller,
- crng_init);
+ printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n",
+ func_name, caller, crng_init);
}
/*
@@ -1537,7 +1448,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
*/
static void _get_random_bytes(void *buf, int nbytes)
{
- __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
+ u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
trace_get_random_bytes(nbytes, _RET_IP_);
@@ -1565,7 +1476,6 @@ void get_random_bytes(void *buf, int nbytes)
}
EXPORT_SYMBOL(get_random_bytes);
-
/*
* Each time the timer fires, we expect that we got an unpredictable
* jump in the cycle counter. Even if the timer is running on another
@@ -1581,7 +1491,7 @@ EXPORT_SYMBOL(get_random_bytes);
*/
static void entropy_timer(struct timer_list *t)
{
- credit_entropy_bits(&input_pool, 1);
+ credit_entropy_bits(1);
}
/*
@@ -1604,15 +1514,15 @@ static void try_to_generate_entropy(void)
timer_setup_on_stack(&stack.timer, entropy_timer, 0);
while (!crng_ready()) {
if (!timer_pending(&stack.timer))
- mod_timer(&stack.timer, jiffies+1);
- mix_pool_bytes(&input_pool, &stack.now, sizeof(stack.now));
+ mod_timer(&stack.timer, jiffies + 1);
+ mix_pool_bytes(&stack.now, sizeof(stack.now));
schedule();
stack.now = random_get_entropy();
}
del_timer_sync(&stack.timer);
destroy_timer_on_stack(&stack.timer);
- mix_pool_bytes(&input_pool, &stack.now, sizeof(stack.now));
+ mix_pool_bytes(&stack.now, sizeof(stack.now));
}
/*
@@ -1731,7 +1641,7 @@ EXPORT_SYMBOL(del_random_ready_callback);
int __must_check get_random_bytes_arch(void *buf, int nbytes)
{
int left = nbytes;
- char *p = buf;
+ u8 *p = buf;
trace_get_random_bytes_arch(left, _RET_IP_);
while (left) {
@@ -1753,26 +1663,24 @@ EXPORT_SYMBOL(get_random_bytes_arch);
/*
* init_std_data - initialize pool with system data
*
- * @r: pool to initialize
- *
* This function clears the pool's entropy count and mixes some system
* data into the pool to prepare it for use. The pool is not cleared
* as that can only decrease the entropy in the pool.
*/
-static void __init init_std_data(struct entropy_store *r)
+static void __init init_std_data(void)
{
int i;
ktime_t now = ktime_get_real();
unsigned long rv;
- mix_pool_bytes(r, &now, sizeof(now));
- for (i = r->poolinfo->poolbytes; i > 0; i -= sizeof(rv)) {
+ mix_pool_bytes(&now, sizeof(now));
+ for (i = POOL_BYTES; i > 0; i -= sizeof(rv)) {
if (!arch_get_random_seed_long(&rv) &&
!arch_get_random_long(&rv))
rv = random_get_entropy();
- mix_pool_bytes(r, &rv, sizeof(rv));
+ mix_pool_bytes(&rv, sizeof(rv));
}
- mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
+ mix_pool_bytes(utsname(), sizeof(*(utsname())));
}
/*
@@ -1787,7 +1695,7 @@ static void __init init_std_data(struct entropy_store *r)
*/
int __init rand_initialize(void)
{
- init_std_data(&input_pool);
+ init_std_data();
if (crng_need_final_init)
crng_finalize_init(&primary_crng);
crng_initialize_primary(&primary_crng);
@@ -1816,20 +1724,19 @@ void rand_initialize_disk(struct gendisk *disk)
}
#endif
-static ssize_t
-urandom_read_nowarn(struct file *file, char __user *buf, size_t nbytes,
- loff_t *ppos)
+static ssize_t urandom_read_nowarn(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *ppos)
{
int ret;
- nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
+ nbytes = min_t(size_t, nbytes, INT_MAX >> (POOL_ENTROPY_SHIFT + 3));
ret = extract_crng_user(buf, nbytes);
- trace_urandom_read(8 * nbytes, 0, ENTROPY_BITS(&input_pool));
+ trace_urandom_read(8 * nbytes, 0, POOL_ENTROPY_BITS());
return ret;
}
-static ssize_t
-urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
+ loff_t *ppos)
{
static int maxwarn = 10;
@@ -1843,8 +1750,8 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
return urandom_read_nowarn(file, buf, nbytes, ppos);
}
-static ssize_t
-random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+static ssize_t random_read(struct file *file, char __user *buf, size_t nbytes,
+ loff_t *ppos)
{
int ret;
@@ -1854,8 +1761,7 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
return urandom_read_nowarn(file, buf, nbytes, ppos);
}
-static __poll_t
-random_poll(struct file *file, poll_table * wait)
+static __poll_t random_poll(struct file *file, poll_table *wait)
{
__poll_t mask;
@@ -1864,16 +1770,15 @@ random_poll(struct file *file, poll_table * wait)
mask = 0;
if (crng_ready())
mask |= EPOLLIN | EPOLLRDNORM;
- if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
+ if (POOL_ENTROPY_BITS() < random_write_wakeup_bits)
mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
-static int
-write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
+static int write_pool(const char __user *buffer, size_t count)
{
size_t bytes;
- __u32 t, buf[16];
+ u32 t, buf[16];
const char __user *p = buffer;
while (count > 0) {
@@ -1883,7 +1788,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
if (copy_from_user(&buf, p, bytes))
return -EFAULT;
- for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) {
+ for (b = bytes; b > 0; b -= sizeof(u32), i++) {
if (!arch_get_random_int(&t))
break;
buf[i] ^= t;
@@ -1892,7 +1797,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
count -= bytes;
p += bytes;
- mix_pool_bytes(r, buf, bytes);
+ mix_pool_bytes(buf, bytes);
cond_resched();
}
@@ -1904,7 +1809,7 @@ static ssize_t random_write(struct file *file, const char __user *buffer,
{
size_t ret;
- ret = write_pool(&input_pool, buffer, count);
+ ret = write_pool(buffer, count);
if (ret)
return ret;
@@ -1920,7 +1825,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
switch (cmd) {
case RNDGETENTCNT:
/* inherently racy, no point locking */
- ent_count = ENTROPY_BITS(&input_pool);
+ ent_count = POOL_ENTROPY_BITS();
if (put_user(ent_count, p))
return -EFAULT;
return 0;
@@ -1929,7 +1834,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
- return credit_entropy_bits_safe(&input_pool, ent_count);
+ return credit_entropy_bits_safe(ent_count);
case RNDADDENTROPY:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1939,11 +1844,10 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
return -EINVAL;
if (get_user(size, p++))
return -EFAULT;
- retval = write_pool(&input_pool, (const char __user *)p,
- size);
+ retval = write_pool((const char __user *)p, size);
if (retval < 0)
return retval;
- return credit_entropy_bits_safe(&input_pool, ent_count);
+ return credit_entropy_bits_safe(ent_count);
case RNDZAPENTCNT:
case RNDCLEARPOOL:
/*
@@ -1959,7 +1863,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
return -EPERM;
if (crng_init < 2)
return -ENODATA;
- crng_reseed(&primary_crng, &input_pool);
+ crng_reseed(&primary_crng, true);
WRITE_ONCE(crng_global_init_time, jiffies - 1);
return 0;
default:
@@ -1973,9 +1877,9 @@ static int random_fasync(int fd, struct file *filp, int on)
}
const struct file_operations random_fops = {
- .read = random_read,
+ .read = random_read,
.write = random_write,
- .poll = random_poll,
+ .poll = random_poll,
.unlocked_ioctl = random_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.fasync = random_fasync,
@@ -1983,7 +1887,7 @@ const struct file_operations random_fops = {
};
const struct file_operations urandom_fops = {
- .read = urandom_read,
+ .read = urandom_read,
.write = random_write,
.unlocked_ioctl = random_ioctl,
.compat_ioctl = compat_ptr_ioctl,
@@ -1991,19 +1895,19 @@ const struct file_operations urandom_fops = {
.llseek = noop_llseek,
};
-SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
- unsigned int, flags)
+SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
+ flags)
{
int ret;
- if (flags & ~(GRND_NONBLOCK|GRND_RANDOM|GRND_INSECURE))
+ if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
return -EINVAL;
/*
* Requesting insecure and blocking randomness at the same time makes
* no sense.
*/
- if ((flags & (GRND_INSECURE|GRND_RANDOM)) == (GRND_INSECURE|GRND_RANDOM))
+ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
return -EINVAL;
if (count > INT_MAX)
@@ -2030,7 +1934,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
#include <linux/sysctl.h>
static int min_write_thresh;
-static int max_write_thresh = INPUT_POOL_WORDS * 32;
+static int max_write_thresh = POOL_BITS;
static int random_min_urandom_seed = 60;
static char sysctl_bootid[16];
@@ -2043,8 +1947,8 @@ static char sysctl_bootid[16];
* returned as an ASCII string in the standard UUID format; if via the
* sysctl system call, as 16 bytes of binary data.
*/
-static int proc_do_uuid(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+static int proc_do_uuid(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
struct ctl_table fake_table;
unsigned char buf[64], tmp_uuid[16], *uuid;
@@ -2073,13 +1977,13 @@ static int proc_do_uuid(struct ctl_table *table, int write,
/*
* Return entropy available scaled to integral bits
*/
-static int proc_do_entropy(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+static int proc_do_entropy(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
struct ctl_table fake_table;
int entropy_count;
- entropy_count = *(int *)table->data >> ENTROPY_SHIFT;
+ entropy_count = *(int *)table->data >> POOL_ENTROPY_SHIFT;
fake_table.data = &entropy_count;
fake_table.maxlen = sizeof(entropy_count);
@@ -2087,7 +1991,7 @@ static int proc_do_entropy(struct ctl_table *table, int write,
return proc_dointvec(&fake_table, write, buffer, lenp, ppos);
}
-static int sysctl_poolsize = INPUT_POOL_WORDS * 32;
+static int sysctl_poolsize = POOL_BITS;
extern struct ctl_table random_table[];
struct ctl_table random_table[] = {
{
@@ -2151,7 +2055,7 @@ struct ctl_table random_table[] = {
#endif
{ }
};
-#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_SYSCTL */
struct batched_entropy {
union {
@@ -2171,7 +2075,7 @@ struct batched_entropy {
* point prior.
*/
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
- .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock),
+ .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock),
};
u64 get_random_u64(void)
@@ -2196,7 +2100,7 @@ u64 get_random_u64(void)
EXPORT_SYMBOL(get_random_u64);
static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
- .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock),
+ .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock),
};
u32 get_random_u32(void)
{
@@ -2228,7 +2132,7 @@ static void invalidate_batched_entropy(void)
int cpu;
unsigned long flags;
- for_each_possible_cpu (cpu) {
+ for_each_possible_cpu(cpu) {
struct batched_entropy *batched_entropy;
batched_entropy = per_cpu_ptr(&batched_entropy_u32, cpu);
@@ -2257,8 +2161,7 @@ static void invalidate_batched_entropy(void)
* Return: A page aligned address within [start, start + range). On error,
* @start is returned.
*/
-unsigned long
-randomize_page(unsigned long start, unsigned long range)
+unsigned long randomize_page(unsigned long start, unsigned long range)
{
if (!PAGE_ALIGNED(start)) {
range -= PAGE_ALIGN(start) - start;
@@ -2283,11 +2186,9 @@ randomize_page(unsigned long start, unsigned long range)
void add_hwgenerator_randomness(const char *buffer, size_t count,
size_t entropy)
{
- struct entropy_store *poolp = &input_pool;
-
if (unlikely(crng_init == 0)) {
size_t ret = crng_fast_load(buffer, count);
- mix_pool_bytes(poolp, buffer, ret);
+ mix_pool_bytes(buffer, ret);
count -= ret;
buffer += ret;
if (!count || crng_init == 0)
@@ -2300,9 +2201,9 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
*/
wait_event_interruptible(random_write_wait,
!system_wq || kthread_should_stop() ||
- ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
- mix_pool_bytes(poolp, buffer, count);
- credit_entropy_bits(poolp, entropy);
+ POOL_ENTROPY_BITS() <= random_write_wakeup_bits);
+ mix_pool_bytes(buffer, count);
+ credit_entropy_bits(entropy);
}
EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 660c5c3..2359889 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1958,7 +1958,7 @@ static void virtcons_remove(struct virtio_device *vdev)
spin_unlock_irq(&pdrvdata_lock);
/* Disable interrupts for vqs */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
/* Finish up work that's lined up */
if (use_multiport(portdev))
cancel_work_sync(&portdev->control_work);
@@ -2148,7 +2148,7 @@ static int virtcons_freeze(struct virtio_device *vdev)
portdev = vdev->priv;
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
if (use_multiport(portdev))
virtqueue_disable_cb(portdev->c_ivq);
diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c
index 57ae183..f7b4136 100644
--- a/drivers/clk/clk-si5341.c
+++ b/drivers/clk/clk-si5341.c
@@ -1740,7 +1740,7 @@ static int si5341_probe(struct i2c_client *client,
clk_prepare(data->clk[i].hw.clk);
}
- err = of_clk_add_hw_provider(client->dev.of_node, of_clk_si5341_get,
+ err = devm_of_clk_add_hw_provider(&client->dev, of_clk_si5341_get,
data);
if (err) {
dev_err(&client->dev, "unable to add clk provider\n");
diff --git a/drivers/clk/mediatek/clk-mt7986-apmixed.c b/drivers/clk/mediatek/clk-mt7986-apmixed.c
index 76c8ebd..98ec388 100644
--- a/drivers/clk/mediatek/clk-mt7986-apmixed.c
+++ b/drivers/clk/mediatek/clk-mt7986-apmixed.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-1.0
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2021 MediaTek Inc.
* Author: Sam Shih <sam.shih@mediatek.com>
diff --git a/drivers/clk/mediatek/clk-mt7986-infracfg.c b/drivers/clk/mediatek/clk-mt7986-infracfg.c
index 3be168c..f209c55 100644
--- a/drivers/clk/mediatek/clk-mt7986-infracfg.c
+++ b/drivers/clk/mediatek/clk-mt7986-infracfg.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-1.0
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2021 MediaTek Inc.
* Author: Sam Shih <sam.shih@mediatek.com>
diff --git a/drivers/clk/mediatek/clk-mt7986-topckgen.c b/drivers/clk/mediatek/clk-mt7986-topckgen.c
index 8550e2b..8f6f79b 100644
--- a/drivers/clk/mediatek/clk-mt7986-topckgen.c
+++ b/drivers/clk/mediatek/clk-mt7986-topckgen.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-1.0
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2021 MediaTek Inc.
* Author: Sam Shih <sam.shih@mediatek.com>
diff --git a/drivers/clk/visconti/pll.c b/drivers/clk/visconti/pll.c
index a2398bc6..a484cb9 100644
--- a/drivers/clk/visconti/pll.c
+++ b/drivers/clk/visconti/pll.c
@@ -246,7 +246,6 @@ static struct clk_hw *visconti_register_pll(struct visconti_pll_provider *ctx,
{
struct clk_init_data init;
struct visconti_pll *pll;
- struct clk *pll_clk;
struct clk_hw *pll_hw_clk;
size_t len;
int ret;
@@ -277,7 +276,7 @@ static struct clk_hw *visconti_register_pll(struct visconti_pll_provider *ctx,
pll_hw_clk = &pll->hw;
ret = clk_hw_register(NULL, &pll->hw);
if (ret) {
- pr_err("failed to register pll clock %s : %ld\n", name, PTR_ERR(pll_clk));
+ pr_err("failed to register pll clock %s : %d\n", name, ret);
kfree(pll);
pll_hw_clk = ERR_PTR(ret);
}
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index e2375d9..8e977b7 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -404,7 +404,7 @@ static int virtcrypto_probe(struct virtio_device *vdev)
free_engines:
virtcrypto_clear_crypto_engines(vcrypto);
free_vqs:
- vcrypto->vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtcrypto_del_vqs(vcrypto);
free_dev:
virtcrypto_devmgr_rm_dev(vcrypto);
@@ -436,7 +436,7 @@ static void virtcrypto_remove(struct virtio_device *vdev)
if (virtcrypto_dev_started(vcrypto))
virtcrypto_dev_stop(vcrypto);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtcrypto_free_unused_reqs(vcrypto);
virtcrypto_clear_crypto_engines(vcrypto);
virtcrypto_del_vqs(vcrypto);
@@ -456,7 +456,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev)
{
struct virtio_crypto *vcrypto = vdev->priv;
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtcrypto_free_unused_reqs(vcrypto);
if (virtcrypto_dev_started(vcrypto))
virtcrypto_dev_stop(vcrypto);
@@ -492,7 +492,7 @@ static int virtcrypto_restore(struct virtio_device *vdev)
free_engines:
virtcrypto_clear_crypto_engines(vcrypto);
free_vqs:
- vcrypto->vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtcrypto_del_vqs(vcrypto);
return err;
}
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 275a76f..a1da2b4 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -99,6 +99,7 @@
#define AT_XDMAC_CNDC_NDE (0x1 << 0) /* Channel x Next Descriptor Enable */
#define AT_XDMAC_CNDC_NDSUP (0x1 << 1) /* Channel x Next Descriptor Source Update */
#define AT_XDMAC_CNDC_NDDUP (0x1 << 2) /* Channel x Next Descriptor Destination Update */
+#define AT_XDMAC_CNDC_NDVIEW_MASK GENMASK(28, 27)
#define AT_XDMAC_CNDC_NDVIEW_NDV0 (0x0 << 3) /* Channel x Next Descriptor View 0 */
#define AT_XDMAC_CNDC_NDVIEW_NDV1 (0x1 << 3) /* Channel x Next Descriptor View 1 */
#define AT_XDMAC_CNDC_NDVIEW_NDV2 (0x2 << 3) /* Channel x Next Descriptor View 2 */
@@ -252,15 +253,15 @@ struct at_xdmac {
/* Linked List Descriptor */
struct at_xdmac_lld {
- dma_addr_t mbr_nda; /* Next Descriptor Member */
- u32 mbr_ubc; /* Microblock Control Member */
- dma_addr_t mbr_sa; /* Source Address Member */
- dma_addr_t mbr_da; /* Destination Address Member */
- u32 mbr_cfg; /* Configuration Register */
- u32 mbr_bc; /* Block Control Register */
- u32 mbr_ds; /* Data Stride Register */
- u32 mbr_sus; /* Source Microblock Stride Register */
- u32 mbr_dus; /* Destination Microblock Stride Register */
+ u32 mbr_nda; /* Next Descriptor Member */
+ u32 mbr_ubc; /* Microblock Control Member */
+ u32 mbr_sa; /* Source Address Member */
+ u32 mbr_da; /* Destination Address Member */
+ u32 mbr_cfg; /* Configuration Register */
+ u32 mbr_bc; /* Block Control Register */
+ u32 mbr_ds; /* Data Stride Register */
+ u32 mbr_sus; /* Source Microblock Stride Register */
+ u32 mbr_dus; /* Destination Microblock Stride Register */
};
/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
@@ -385,9 +386,6 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, first);
- if (at_xdmac_chan_is_enabled(atchan))
- return;
-
/* Set transfer as active to not try to start it again. */
first->active_xfer = true;
@@ -405,7 +403,8 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
*/
if (at_xdmac_chan_is_cyclic(atchan))
reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
- else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3)
+ else if ((first->lld.mbr_ubc &
+ AT_XDMAC_CNDC_NDVIEW_MASK) == AT_XDMAC_MBR_UBC_NDV3)
reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
else
reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
@@ -476,13 +475,12 @@ static dma_cookie_t at_xdmac_tx_submit(struct dma_async_tx_descriptor *tx)
spin_lock_irqsave(&atchan->lock, irqflags);
cookie = dma_cookie_assign(tx);
+ list_add_tail(&desc->xfer_node, &atchan->xfers_list);
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
+
dev_vdbg(chan2dev(tx->chan), "%s: atchan 0x%p, add desc 0x%p to xfers_list\n",
__func__, atchan, desc);
- list_add_tail(&desc->xfer_node, &atchan->xfers_list);
- if (list_is_singular(&atchan->xfers_list))
- at_xdmac_start_xfer(atchan, desc);
- spin_unlock_irqrestore(&atchan->lock, irqflags);
return cookie;
}
@@ -733,7 +731,8 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
if (!desc) {
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
- list_splice_init(&first->descs_list, &atchan->free_descs_list);
+ list_splice_tail_init(&first->descs_list,
+ &atchan->free_descs_list);
goto spin_unlock;
}
@@ -821,7 +820,8 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
if (!desc) {
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
- list_splice_init(&first->descs_list, &atchan->free_descs_list);
+ list_splice_tail_init(&first->descs_list,
+ &atchan->free_descs_list);
spin_unlock_irqrestore(&atchan->lock, irqflags);
return NULL;
}
@@ -1055,8 +1055,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan,
src_addr, dst_addr,
xt, chunk);
if (!desc) {
- list_splice_init(&first->descs_list,
- &atchan->free_descs_list);
+ list_splice_tail_init(&first->descs_list,
+ &atchan->free_descs_list);
return NULL;
}
@@ -1136,7 +1136,8 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
if (!desc) {
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
- list_splice_init(&first->descs_list, &atchan->free_descs_list);
+ list_splice_tail_init(&first->descs_list,
+ &atchan->free_descs_list);
return NULL;
}
@@ -1312,8 +1313,8 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl,
sg_dma_len(sg),
value);
if (!desc && first)
- list_splice_init(&first->descs_list,
- &atchan->free_descs_list);
+ list_splice_tail_init(&first->descs_list,
+ &atchan->free_descs_list);
if (!first)
first = desc;
@@ -1586,20 +1587,6 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
return ret;
}
-/* Call must be protected by lock. */
-static void at_xdmac_remove_xfer(struct at_xdmac_chan *atchan,
- struct at_xdmac_desc *desc)
-{
- dev_dbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
-
- /*
- * Remove the transfer from the transfer list then move the transfer
- * descriptors into the free descriptors list.
- */
- list_del(&desc->xfer_node);
- list_splice_init(&desc->descs_list, &atchan->free_descs_list);
-}
-
static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
{
struct at_xdmac_desc *desc;
@@ -1608,14 +1595,14 @@ static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
* If channel is enabled, do nothing, advance_work will be triggered
* after the interruption.
*/
- if (!at_xdmac_chan_is_enabled(atchan) && !list_empty(&atchan->xfers_list)) {
- desc = list_first_entry(&atchan->xfers_list,
- struct at_xdmac_desc,
- xfer_node);
- dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
- if (!desc->active_xfer)
- at_xdmac_start_xfer(atchan, desc);
- }
+ if (at_xdmac_chan_is_enabled(atchan) || list_empty(&atchan->xfers_list))
+ return;
+
+ desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc,
+ xfer_node);
+ dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
+ if (!desc->active_xfer)
+ at_xdmac_start_xfer(atchan, desc);
}
static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
@@ -1623,16 +1610,22 @@ static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
struct at_xdmac_desc *desc;
struct dma_async_tx_descriptor *txd;
- if (!list_empty(&atchan->xfers_list)) {
- desc = list_first_entry(&atchan->xfers_list,
- struct at_xdmac_desc, xfer_node);
- txd = &desc->tx_dma_desc;
-
- if (txd->flags & DMA_PREP_INTERRUPT)
- dmaengine_desc_get_callback_invoke(txd, NULL);
+ spin_lock_irq(&atchan->lock);
+ dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n",
+ __func__, atchan->irq_status);
+ if (list_empty(&atchan->xfers_list)) {
+ spin_unlock_irq(&atchan->lock);
+ return;
}
+ desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc,
+ xfer_node);
+ spin_unlock_irq(&atchan->lock);
+ txd = &desc->tx_dma_desc;
+ if (txd->flags & DMA_PREP_INTERRUPT)
+ dmaengine_desc_get_callback_invoke(txd, NULL);
}
+/* Called with atchan->lock held. */
static void at_xdmac_handle_error(struct at_xdmac_chan *atchan)
{
struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device);
@@ -1651,8 +1644,6 @@ static void at_xdmac_handle_error(struct at_xdmac_chan *atchan)
if (atchan->irq_status & AT_XDMAC_CIS_ROIS)
dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
- spin_lock_irq(&atchan->lock);
-
/* Channel must be disabled first as it's not done automatically */
at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask)
@@ -1662,8 +1653,6 @@ static void at_xdmac_handle_error(struct at_xdmac_chan *atchan)
struct at_xdmac_desc,
xfer_node);
- spin_unlock_irq(&atchan->lock);
-
/* Print bad descriptor's details if needed */
dev_dbg(chan2dev(&atchan->chan),
"%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
@@ -1677,50 +1666,52 @@ static void at_xdmac_tasklet(struct tasklet_struct *t)
{
struct at_xdmac_chan *atchan = from_tasklet(atchan, t, tasklet);
struct at_xdmac_desc *desc;
+ struct dma_async_tx_descriptor *txd;
u32 error_mask;
+ if (at_xdmac_chan_is_cyclic(atchan))
+ return at_xdmac_handle_cyclic(atchan);
+
+ error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS |
+ AT_XDMAC_CIS_ROIS;
+
+ spin_lock_irq(&atchan->lock);
+
dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n",
__func__, atchan->irq_status);
- error_mask = AT_XDMAC_CIS_RBEIS
- | AT_XDMAC_CIS_WBEIS
- | AT_XDMAC_CIS_ROIS;
+ if (!(atchan->irq_status & AT_XDMAC_CIS_LIS) &&
+ !(atchan->irq_status & error_mask))
+ return;
- if (at_xdmac_chan_is_cyclic(atchan)) {
- at_xdmac_handle_cyclic(atchan);
- } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS)
- || (atchan->irq_status & error_mask)) {
- struct dma_async_tx_descriptor *txd;
+ if (atchan->irq_status & error_mask)
+ at_xdmac_handle_error(atchan);
- if (atchan->irq_status & error_mask)
- at_xdmac_handle_error(atchan);
-
- spin_lock_irq(&atchan->lock);
- desc = list_first_entry(&atchan->xfers_list,
- struct at_xdmac_desc,
- xfer_node);
- dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
- if (!desc->active_xfer) {
- dev_err(chan2dev(&atchan->chan), "Xfer not active: exiting");
- spin_unlock_irq(&atchan->lock);
- return;
- }
-
- txd = &desc->tx_dma_desc;
-
- at_xdmac_remove_xfer(atchan, desc);
+ desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc,
+ xfer_node);
+ dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
+ if (!desc->active_xfer) {
+ dev_err(chan2dev(&atchan->chan), "Xfer not active: exiting");
spin_unlock_irq(&atchan->lock);
-
- dma_cookie_complete(txd);
- if (txd->flags & DMA_PREP_INTERRUPT)
- dmaengine_desc_get_callback_invoke(txd, NULL);
-
- dma_run_dependencies(txd);
-
- spin_lock_irq(&atchan->lock);
- at_xdmac_advance_work(atchan);
- spin_unlock_irq(&atchan->lock);
+ return;
}
+
+ txd = &desc->tx_dma_desc;
+ dma_cookie_complete(txd);
+ /* Remove the transfer from the transfer list. */
+ list_del(&desc->xfer_node);
+ spin_unlock_irq(&atchan->lock);
+
+ if (txd->flags & DMA_PREP_INTERRUPT)
+ dmaengine_desc_get_callback_invoke(txd, NULL);
+
+ dma_run_dependencies(txd);
+
+ spin_lock_irq(&atchan->lock);
+ /* Move the xfer descriptors into the free descriptors list. */
+ list_splice_tail_init(&desc->descs_list, &atchan->free_descs_list);
+ at_xdmac_advance_work(atchan);
+ spin_unlock_irq(&atchan->lock);
}
static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
@@ -1784,11 +1775,9 @@ static void at_xdmac_issue_pending(struct dma_chan *chan)
dev_dbg(chan2dev(&atchan->chan), "%s\n", __func__);
- if (!at_xdmac_chan_is_cyclic(atchan)) {
- spin_lock_irqsave(&atchan->lock, flags);
- at_xdmac_advance_work(atchan);
- spin_unlock_irqrestore(&atchan->lock, flags);
- }
+ spin_lock_irqsave(&atchan->lock, flags);
+ at_xdmac_advance_work(atchan);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return;
}
@@ -1866,8 +1855,11 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan)
cpu_relax();
/* Cancel all pending transfers. */
- list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node)
- at_xdmac_remove_xfer(atchan, desc);
+ list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) {
+ list_del(&desc->xfer_node);
+ list_splice_tail_init(&desc->descs_list,
+ &atchan->free_descs_list);
+ }
clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status);
@@ -2031,7 +2023,7 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev)
static int at_xdmac_probe(struct platform_device *pdev)
{
struct at_xdmac *atxdmac;
- int irq, size, nr_channels, i, ret;
+ int irq, nr_channels, i, ret;
void __iomem *base;
u32 reg;
@@ -2056,9 +2048,9 @@ static int at_xdmac_probe(struct platform_device *pdev)
return -EINVAL;
}
- size = sizeof(*atxdmac);
- size += nr_channels * sizeof(struct at_xdmac_chan);
- atxdmac = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+ atxdmac = devm_kzalloc(&pdev->dev,
+ struct_size(atxdmac, chan, nr_channels),
+ GFP_KERNEL);
if (!atxdmac) {
dev_err(&pdev->dev, "can't allocate at_xdmac structure\n");
return -ENOMEM;
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 96701de..fc513eb 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -104,10 +104,10 @@
* descriptor base address in the upper 8 bits.
*/
struct jz4780_dma_hwdesc {
- uint32_t dcm;
- uint32_t dsa;
- uint32_t dta;
- uint32_t dtc;
+ u32 dcm;
+ u32 dsa;
+ u32 dta;
+ u32 dtc;
};
/* Size of allocations for hardware descriptor blocks. */
@@ -122,7 +122,8 @@ struct jz4780_dma_desc {
dma_addr_t desc_phys;
unsigned int count;
enum dma_transaction_type type;
- uint32_t status;
+ u32 transfer_type;
+ u32 status;
};
struct jz4780_dma_chan {
@@ -130,8 +131,8 @@ struct jz4780_dma_chan {
unsigned int id;
struct dma_pool *desc_pool;
- uint32_t transfer_type;
- uint32_t transfer_shift;
+ u32 transfer_type_tx, transfer_type_rx;
+ u32 transfer_shift;
struct dma_slave_config config;
struct jz4780_dma_desc *desc;
@@ -152,12 +153,12 @@ struct jz4780_dma_dev {
unsigned int irq;
const struct jz4780_dma_soc_data *soc_data;
- uint32_t chan_reserved;
+ u32 chan_reserved;
struct jz4780_dma_chan chan[];
};
struct jz4780_dma_filter_data {
- uint32_t transfer_type;
+ u32 transfer_type_tx, transfer_type_rx;
int channel;
};
@@ -179,26 +180,26 @@ static inline struct jz4780_dma_dev *jz4780_dma_chan_parent(
dma_device);
}
-static inline uint32_t jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma,
+static inline u32 jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma,
unsigned int chn, unsigned int reg)
{
return readl(jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
}
static inline void jz4780_dma_chn_writel(struct jz4780_dma_dev *jzdma,
- unsigned int chn, unsigned int reg, uint32_t val)
+ unsigned int chn, unsigned int reg, u32 val)
{
writel(val, jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
}
-static inline uint32_t jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma,
+static inline u32 jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma,
unsigned int reg)
{
return readl(jzdma->ctrl_base + reg);
}
static inline void jz4780_dma_ctrl_writel(struct jz4780_dma_dev *jzdma,
- unsigned int reg, uint32_t val)
+ unsigned int reg, u32 val)
{
writel(val, jzdma->ctrl_base + reg);
}
@@ -226,9 +227,10 @@ static inline void jz4780_dma_chan_disable(struct jz4780_dma_dev *jzdma,
jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DCKEC, BIT(chn));
}
-static struct jz4780_dma_desc *jz4780_dma_desc_alloc(
- struct jz4780_dma_chan *jzchan, unsigned int count,
- enum dma_transaction_type type)
+static struct jz4780_dma_desc *
+jz4780_dma_desc_alloc(struct jz4780_dma_chan *jzchan, unsigned int count,
+ enum dma_transaction_type type,
+ enum dma_transfer_direction direction)
{
struct jz4780_dma_desc *desc;
@@ -248,6 +250,12 @@ static struct jz4780_dma_desc *jz4780_dma_desc_alloc(
desc->count = count;
desc->type = type;
+
+ if (direction == DMA_DEV_TO_MEM)
+ desc->transfer_type = jzchan->transfer_type_rx;
+ else
+ desc->transfer_type = jzchan->transfer_type_tx;
+
return desc;
}
@@ -260,8 +268,8 @@ static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc)
kfree(desc);
}
-static uint32_t jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan,
- unsigned long val, uint32_t *shift)
+static u32 jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan,
+ unsigned long val, u32 *shift)
{
struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
int ord = ffs(val) - 1;
@@ -303,7 +311,7 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
enum dma_transfer_direction direction)
{
struct dma_slave_config *config = &jzchan->config;
- uint32_t width, maxburst, tsz;
+ u32 width, maxburst, tsz;
if (direction == DMA_MEM_TO_DEV) {
desc->dcm = JZ_DMA_DCM_SAI;
@@ -361,7 +369,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
unsigned int i;
int err;
- desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE);
+ desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE, direction);
if (!desc)
return NULL;
@@ -410,7 +418,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic(
periods = buf_len / period_len;
- desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC);
+ desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC, direction);
if (!desc)
return NULL;
@@ -453,16 +461,16 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
{
struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
struct jz4780_dma_desc *desc;
- uint32_t tsz;
+ u32 tsz;
- desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY);
+ desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY, 0);
if (!desc)
return NULL;
tsz = jz4780_dma_transfer_size(jzchan, dest | src | len,
&jzchan->transfer_shift);
- jzchan->transfer_type = JZ_DMA_DRT_AUTO;
+ desc->transfer_type = JZ_DMA_DRT_AUTO;
desc->desc[0].dsa = src;
desc->desc[0].dta = dest;
@@ -528,7 +536,7 @@ static void jz4780_dma_begin(struct jz4780_dma_chan *jzchan)
/* Set transfer type. */
jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DRT,
- jzchan->transfer_type);
+ jzchan->desc->transfer_type);
/*
* Set the transfer count. This is redundant for a descriptor-driven
@@ -670,7 +678,7 @@ static bool jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma,
{
const unsigned int soc_flags = jzdma->soc_data->flags;
struct jz4780_dma_desc *desc = jzchan->desc;
- uint32_t dcs;
+ u32 dcs;
bool ack = true;
spin_lock(&jzchan->vchan.lock);
@@ -727,7 +735,7 @@ static irqreturn_t jz4780_dma_irq_handler(int irq, void *data)
struct jz4780_dma_dev *jzdma = data;
unsigned int nb_channels = jzdma->soc_data->nb_channels;
unsigned long pending;
- uint32_t dmac;
+ u32 dmac;
int i;
pending = jz4780_dma_ctrl_readl(jzdma, JZ_DMA_REG_DIRQP);
@@ -788,7 +796,8 @@ static bool jz4780_dma_filter_fn(struct dma_chan *chan, void *param)
return false;
}
- jzchan->transfer_type = data->transfer_type;
+ jzchan->transfer_type_tx = data->transfer_type_tx;
+ jzchan->transfer_type_rx = data->transfer_type_rx;
return true;
}
@@ -800,11 +809,17 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
dma_cap_mask_t mask = jzdma->dma_device.cap_mask;
struct jz4780_dma_filter_data data;
- if (dma_spec->args_count != 2)
+ if (dma_spec->args_count == 2) {
+ data.transfer_type_tx = dma_spec->args[0];
+ data.transfer_type_rx = dma_spec->args[0];
+ data.channel = dma_spec->args[1];
+ } else if (dma_spec->args_count == 3) {
+ data.transfer_type_tx = dma_spec->args[0];
+ data.transfer_type_rx = dma_spec->args[1];
+ data.channel = dma_spec->args[2];
+ } else {
return NULL;
-
- data.transfer_type = dma_spec->args[0];
- data.channel = dma_spec->args[1];
+ }
if (data.channel > -1) {
if (data.channel >= jzdma->soc_data->nb_channels) {
@@ -822,7 +837,8 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
return NULL;
}
- jzdma->chan[data.channel].transfer_type = data.transfer_type;
+ jzdma->chan[data.channel].transfer_type_tx = data.transfer_type_tx;
+ jzdma->chan[data.channel].transfer_type_rx = data.transfer_type_rx;
return dma_get_slave_channel(
&jzdma->chan[data.channel].vchan.chan);
@@ -938,6 +954,14 @@ static int jz4780_dma_probe(struct platform_device *pdev)
jzchan->vchan.desc_free = jz4780_dma_desc_free;
}
+ /*
+ * On JZ4760, chan0 won't enable properly the first time.
+ * Enabling then disabling chan1 will magically make chan0 work
+ * correctly.
+ */
+ jz4780_dma_chan_enable(jzdma, 1);
+ jz4780_dma_chan_disable(jzdma, 1);
+
ret = platform_get_irq(pdev, 0);
if (ret < 0)
goto err_disable_clk;
@@ -1011,12 +1035,36 @@ static const struct jz4780_dma_soc_data jz4760_dma_soc_data = {
.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
};
+static const struct jz4780_dma_soc_data jz4760_mdma_soc_data = {
+ .nb_channels = 2,
+ .transfer_ord_max = 6,
+ .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
+static const struct jz4780_dma_soc_data jz4760_bdma_soc_data = {
+ .nb_channels = 3,
+ .transfer_ord_max = 6,
+ .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
static const struct jz4780_dma_soc_data jz4760b_dma_soc_data = {
.nb_channels = 5,
.transfer_ord_max = 6,
.flags = JZ_SOC_DATA_PER_CHAN_PM,
};
+static const struct jz4780_dma_soc_data jz4760b_mdma_soc_data = {
+ .nb_channels = 2,
+ .transfer_ord_max = 6,
+ .flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
+static const struct jz4780_dma_soc_data jz4760b_bdma_soc_data = {
+ .nb_channels = 3,
+ .transfer_ord_max = 6,
+ .flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
.nb_channels = 6,
.transfer_ord_max = 6,
@@ -1045,7 +1093,11 @@ static const struct of_device_id jz4780_dma_dt_match[] = {
{ .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data },
{ .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data },
{ .compatible = "ingenic,jz4760-dma", .data = &jz4760_dma_soc_data },
+ { .compatible = "ingenic,jz4760-mdma", .data = &jz4760_mdma_soc_data },
+ { .compatible = "ingenic,jz4760-bdma", .data = &jz4760_bdma_soc_data },
{ .compatible = "ingenic,jz4760b-dma", .data = &jz4760b_dma_soc_data },
+ { .compatible = "ingenic,jz4760b-mdma", .data = &jz4760b_mdma_soc_data },
+ { .compatible = "ingenic,jz4760b-bdma", .data = &jz4760b_bdma_soc_data },
{ .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data },
{ .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data },
{ .compatible = "ingenic,x1000-dma", .data = &x1000_dma_soc_data },
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index d9f7c09..2cfa845 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1159,6 +1159,13 @@ int dma_async_device_register(struct dma_device *device)
return -EIO;
}
+ if (dma_has_cap(DMA_MEMCPY_SG, device->cap_mask) && !device->device_prep_dma_memcpy_sg) {
+ dev_err(device->dev,
+ "Device claims capability %s, but op is not defined\n",
+ "DMA_MEMCPY_SG");
+ return -EIO;
+ }
+
if (dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor) {
dev_err(device->dev,
"Device claims capability %s, but op is not defined\n",
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index fab4123..573ad8b 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -19,30 +19,6 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd);
static void idxd_wq_disable_cleanup(struct idxd_wq *wq);
/* Interrupt control bits */
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
- struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
-
- pci_msi_mask_irq(data);
-}
-
-void idxd_mask_msix_vectors(struct idxd_device *idxd)
-{
- struct pci_dev *pdev = idxd->pdev;
- int msixcnt = pci_msix_vec_count(pdev);
- int i;
-
- for (i = 0; i < msixcnt; i++)
- idxd_mask_msix_vector(idxd, i);
-}
-
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
- struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
-
- pci_msi_unmask_irq(data);
-}
-
void idxd_unmask_error_interrupts(struct idxd_device *idxd)
{
union genctrl_reg genctrl;
@@ -382,14 +358,24 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
lockdep_assert_held(&wq->wq_lock);
memset(wq->wqcfg, 0, idxd->wqcfg_size);
wq->type = IDXD_WQT_NONE;
- wq->size = 0;
- wq->group = NULL;
wq->threshold = 0;
wq->priority = 0;
wq->ats_dis = 0;
+ wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
memset(wq->name, 0, WQ_NAME_SIZE);
+ wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
+ wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+}
+
+static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq)
+{
+ lockdep_assert_held(&wq->wq_lock);
+
+ idxd_wq_disable_cleanup(wq);
+ wq->size = 0;
+ wq->group = NULL;
}
static void idxd_wq_ref_release(struct percpu_ref *ref)
@@ -404,17 +390,29 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
int rc;
memset(&wq->wq_active, 0, sizeof(wq->wq_active));
- rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release, 0, GFP_KERNEL);
+ rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release,
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
if (rc < 0)
return rc;
reinit_completion(&wq->wq_dead);
+ reinit_completion(&wq->wq_resurrect);
return 0;
}
+void __idxd_wq_quiesce(struct idxd_wq *wq)
+{
+ lockdep_assert_held(&wq->wq_lock);
+ reinit_completion(&wq->wq_resurrect);
+ percpu_ref_kill(&wq->wq_active);
+ complete_all(&wq->wq_resurrect);
+ wait_for_completion(&wq->wq_dead);
+}
+
void idxd_wq_quiesce(struct idxd_wq *wq)
{
- percpu_ref_kill(&wq->wq_active);
- wait_for_completion(&wq->wq_dead);
+ mutex_lock(&wq->wq_lock);
+ __idxd_wq_quiesce(wq);
+ mutex_unlock(&wq->wq_lock);
}
/* Device control bits */
@@ -572,7 +570,6 @@ void idxd_device_reset(struct idxd_device *idxd)
idxd_device_clear_state(idxd);
idxd->state = IDXD_DEV_DISABLED;
idxd_unmask_error_interrupts(idxd);
- idxd_msix_perm_setup(idxd);
spin_unlock(&idxd->dev_lock);
}
@@ -681,9 +678,9 @@ static void idxd_groups_clear_state(struct idxd_device *idxd)
memset(&group->grpcfg, 0, sizeof(group->grpcfg));
group->num_engines = 0;
group->num_wqs = 0;
- group->use_token_limit = false;
- group->tokens_allowed = 0;
- group->tokens_reserved = 0;
+ group->use_rdbuf_limit = false;
+ group->rdbufs_allowed = 0;
+ group->rdbufs_reserved = 0;
group->tc_a = -1;
group->tc_b = -1;
}
@@ -699,6 +696,7 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
if (wq->state == IDXD_WQ_ENABLED) {
idxd_wq_disable_cleanup(wq);
+ idxd_wq_device_reset_cleanup(wq);
wq->state = IDXD_WQ_DISABLED;
}
}
@@ -711,36 +709,6 @@ void idxd_device_clear_state(struct idxd_device *idxd)
idxd_device_wqs_clear_state(idxd);
}
-void idxd_msix_perm_setup(struct idxd_device *idxd)
-{
- union msix_perm mperm;
- int i, msixcnt;
-
- msixcnt = pci_msix_vec_count(idxd->pdev);
- if (msixcnt < 0)
- return;
-
- mperm.bits = 0;
- mperm.pasid = idxd->pasid;
- mperm.pasid_en = device_pasid_enabled(idxd);
- for (i = 1; i < msixcnt; i++)
- iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
-void idxd_msix_perm_clear(struct idxd_device *idxd)
-{
- union msix_perm mperm;
- int i, msixcnt;
-
- msixcnt = pci_msix_vec_count(idxd->pdev);
- if (msixcnt < 0)
- return;
-
- mperm.bits = 0;
- for (i = 1; i < msixcnt; i++)
- iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
static void idxd_group_config_write(struct idxd_group *group)
{
struct idxd_device *idxd = group->idxd;
@@ -780,10 +748,10 @@ static int idxd_groups_config_write(struct idxd_device *idxd)
int i;
struct device *dev = &idxd->pdev->dev;
- /* Setup bandwidth token limit */
- if (idxd->hw.gen_cap.config_en && idxd->token_limit) {
+ /* Setup bandwidth rdbuf limit */
+ if (idxd->hw.gen_cap.config_en && idxd->rdbuf_limit) {
reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
- reg.token_limit = idxd->token_limit;
+ reg.rdbuf_limit = idxd->rdbuf_limit;
iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
}
@@ -827,15 +795,12 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
}
+ if (wq->size == 0 && wq->type != IDXD_WQT_NONE)
+ wq->size = WQ_DEFAULT_QUEUE_DEPTH;
+
/* byte 0-3 */
wq->wqcfg->wq_size = wq->size;
- if (wq->size == 0) {
- idxd->cmd_status = IDXD_SCMD_WQ_NO_SIZE;
- dev_warn(dev, "Incorrect work queue size: 0\n");
- return -EINVAL;
- }
-
/* bytes 4-7 */
wq->wqcfg->wq_thresh = wq->threshold;
@@ -924,13 +889,12 @@ static void idxd_group_flags_setup(struct idxd_device *idxd)
group->tc_b = group->grpcfg.flags.tc_b = 1;
else
group->grpcfg.flags.tc_b = group->tc_b;
- group->grpcfg.flags.use_token_limit = group->use_token_limit;
- group->grpcfg.flags.tokens_reserved = group->tokens_reserved;
- if (group->tokens_allowed)
- group->grpcfg.flags.tokens_allowed =
- group->tokens_allowed;
+ group->grpcfg.flags.use_rdbuf_limit = group->use_rdbuf_limit;
+ group->grpcfg.flags.rdbufs_reserved = group->rdbufs_reserved;
+ if (group->rdbufs_allowed)
+ group->grpcfg.flags.rdbufs_allowed = group->rdbufs_allowed;
else
- group->grpcfg.flags.tokens_allowed = idxd->max_tokens;
+ group->grpcfg.flags.rdbufs_allowed = idxd->max_rdbufs;
}
}
@@ -981,8 +945,6 @@ static int idxd_wqs_setup(struct idxd_device *idxd)
if (!wq->group)
continue;
- if (!wq->size)
- continue;
if (wq_shared(wq) && !device_swq_supported(idxd)) {
idxd->cmd_status = IDXD_SCMD_WQ_NO_SWQ_SUPPORT;
@@ -1123,7 +1085,7 @@ int idxd_device_load_config(struct idxd_device *idxd)
int i, rc;
reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
- idxd->token_limit = reg.token_limit;
+ idxd->rdbuf_limit = reg.rdbuf_limit;
for (i = 0; i < idxd->max_groups; i++) {
struct idxd_group *group = idxd->groups[i];
@@ -1142,6 +1104,106 @@ int idxd_device_load_config(struct idxd_device *idxd)
return 0;
}
+static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
+{
+ struct idxd_desc *desc, *itr;
+ struct llist_node *head;
+ LIST_HEAD(flist);
+ enum idxd_complete_type ctype;
+
+ spin_lock(&ie->list_lock);
+ head = llist_del_all(&ie->pending_llist);
+ if (head) {
+ llist_for_each_entry_safe(desc, itr, head, llnode)
+ list_add_tail(&desc->list, &ie->work_list);
+ }
+
+ list_for_each_entry_safe(desc, itr, &ie->work_list, list)
+ list_move_tail(&desc->list, &flist);
+ spin_unlock(&ie->list_lock);
+
+ list_for_each_entry_safe(desc, itr, &flist, list) {
+ list_del(&desc->list);
+ ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
+ idxd_dma_complete_txd(desc, ctype, true);
+ }
+}
+
+static void idxd_device_set_perm_entry(struct idxd_device *idxd,
+ struct idxd_irq_entry *ie)
+{
+ union msix_perm mperm;
+
+ if (ie->pasid == INVALID_IOASID)
+ return;
+
+ mperm.bits = 0;
+ mperm.pasid = ie->pasid;
+ mperm.pasid_en = 1;
+ iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+static void idxd_device_clear_perm_entry(struct idxd_device *idxd,
+ struct idxd_irq_entry *ie)
+{
+ iowrite32(0, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+void idxd_wq_free_irq(struct idxd_wq *wq)
+{
+ struct idxd_device *idxd = wq->idxd;
+ struct idxd_irq_entry *ie = &wq->ie;
+
+ synchronize_irq(ie->vector);
+ free_irq(ie->vector, ie);
+ idxd_flush_pending_descs(ie);
+ if (idxd->request_int_handles)
+ idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+ idxd_device_clear_perm_entry(idxd, ie);
+ ie->vector = -1;
+ ie->int_handle = INVALID_INT_HANDLE;
+ ie->pasid = INVALID_IOASID;
+}
+
+int idxd_wq_request_irq(struct idxd_wq *wq)
+{
+ struct idxd_device *idxd = wq->idxd;
+ struct pci_dev *pdev = idxd->pdev;
+ struct device *dev = &pdev->dev;
+ struct idxd_irq_entry *ie;
+ int rc;
+
+ ie = &wq->ie;
+ ie->vector = pci_irq_vector(pdev, ie->id);
+ ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID;
+ idxd_device_set_perm_entry(idxd, ie);
+
+ rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie);
+ if (rc < 0) {
+ dev_err(dev, "Failed to request irq %d.\n", ie->vector);
+ goto err_irq;
+ }
+
+ if (idxd->request_int_handles) {
+ rc = idxd_device_request_int_handle(idxd, ie->id, &ie->int_handle,
+ IDXD_IRQ_MSIX);
+ if (rc < 0)
+ goto err_int_handle;
+ } else {
+ ie->int_handle = ie->id;
+ }
+
+ return 0;
+
+err_int_handle:
+ ie->int_handle = INVALID_INT_HANDLE;
+ free_irq(ie->vector, ie);
+err_irq:
+ idxd_device_clear_perm_entry(idxd, ie);
+ ie->pasid = INVALID_IOASID;
+ return rc;
+}
+
int __drv_enable_wq(struct idxd_wq *wq)
{
struct idxd_device *idxd = wq->idxd;
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index c39e948..bfff596 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -21,20 +21,27 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
}
void idxd_dma_complete_txd(struct idxd_desc *desc,
- enum idxd_complete_type comp_type)
+ enum idxd_complete_type comp_type,
+ bool free_desc)
{
+ struct idxd_device *idxd = desc->wq->idxd;
struct dma_async_tx_descriptor *tx;
struct dmaengine_result res;
int complete = 1;
- if (desc->completion->status == DSA_COMP_SUCCESS)
+ if (desc->completion->status == DSA_COMP_SUCCESS) {
res.result = DMA_TRANS_NOERROR;
- else if (desc->completion->status)
+ } else if (desc->completion->status) {
+ if (idxd->request_int_handles && comp_type != IDXD_COMPLETE_ABORT &&
+ desc->completion->status == DSA_COMP_INT_HANDLE_INVAL &&
+ idxd_queue_int_handle_resubmit(desc))
+ return;
res.result = DMA_TRANS_WRITE_FAILED;
- else if (comp_type == IDXD_COMPLETE_ABORT)
+ } else if (comp_type == IDXD_COMPLETE_ABORT) {
res.result = DMA_TRANS_ABORTED;
- else
+ } else {
complete = 0;
+ }
tx = &desc->txd;
if (complete && tx->cookie) {
@@ -44,6 +51,9 @@ void idxd_dma_complete_txd(struct idxd_desc *desc,
tx->callback = NULL;
tx->callback_result = NULL;
}
+
+ if (free_desc)
+ idxd_free_desc(desc->wq, desc);
}
static void op_flag_setup(unsigned long flags, u32 *desc_flags)
@@ -153,8 +163,10 @@ static dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
cookie = dma_cookie_assign(tx);
rc = idxd_submit_desc(wq, desc);
- if (rc < 0)
+ if (rc < 0) {
+ idxd_free_desc(wq, desc);
return rc;
+ }
return cookie;
}
@@ -277,6 +289,14 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
mutex_lock(&wq->wq_lock);
wq->type = IDXD_WQT_KERNEL;
+
+ rc = idxd_wq_request_irq(wq);
+ if (rc < 0) {
+ idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR;
+ dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc);
+ goto err_irq;
+ }
+
rc = __drv_enable_wq(wq);
if (rc < 0) {
dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
@@ -310,13 +330,15 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
return 0;
err_dma:
- idxd_wq_quiesce(wq);
+ __idxd_wq_quiesce(wq);
percpu_ref_exit(&wq->wq_active);
err_ref:
idxd_wq_free_resources(wq);
err_res_alloc:
__drv_disable_wq(wq);
err:
+ idxd_wq_free_irq(wq);
+err_irq:
wq->type = IDXD_WQT_NONE;
mutex_unlock(&wq->wq_lock);
return rc;
@@ -327,11 +349,13 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
mutex_lock(&wq->wq_lock);
- idxd_wq_quiesce(wq);
+ __idxd_wq_quiesce(wq);
idxd_unregister_dma_channel(wq);
idxd_wq_free_resources(wq);
__drv_disable_wq(wq);
percpu_ref_exit(&wq->wq_active);
+ idxd_wq_free_irq(wq);
+ wq->type = IDXD_WQT_NONE;
mutex_unlock(&wq->wq_lock);
}
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 0cf8d31..da72eb1 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -10,6 +10,7 @@
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/pci.h>
+#include <linux/ioasid.h>
#include <linux/perf_event.h>
#include <uapi/linux/idxd.h>
#include "registers.h"
@@ -51,6 +52,9 @@ enum idxd_type {
#define IDXD_NAME_SIZE 128
#define IDXD_PMU_EVENT_MAX 64
+#define IDXD_ENQCMDS_RETRIES 32
+#define IDXD_ENQCMDS_MAX_RETRIES 64
+
struct idxd_device_driver {
const char *name;
enum idxd_dev_type *type;
@@ -64,8 +68,8 @@ extern struct idxd_device_driver idxd_drv;
extern struct idxd_device_driver idxd_dmaengine_drv;
extern struct idxd_device_driver idxd_user_drv;
+#define INVALID_INT_HANDLE -1
struct idxd_irq_entry {
- struct idxd_device *idxd;
int id;
int vector;
struct llist_head pending_llist;
@@ -75,6 +79,8 @@ struct idxd_irq_entry {
* and irq thread processing error descriptor.
*/
spinlock_t list_lock;
+ int int_handle;
+ ioasid_t pasid;
};
struct idxd_group {
@@ -84,9 +90,9 @@ struct idxd_group {
int id;
int num_engines;
int num_wqs;
- bool use_token_limit;
- u8 tokens_allowed;
- u8 tokens_reserved;
+ bool use_rdbuf_limit;
+ u8 rdbufs_allowed;
+ u8 rdbufs_reserved;
int tc_a;
int tc_b;
};
@@ -145,6 +151,10 @@ struct idxd_cdev {
#define WQ_NAME_SIZE 1024
#define WQ_TYPE_SIZE 10
+#define WQ_DEFAULT_QUEUE_DEPTH 16
+#define WQ_DEFAULT_MAX_XFER SZ_2M
+#define WQ_DEFAULT_MAX_BATCH 32
+
enum idxd_op_type {
IDXD_OP_BLOCK = 0,
IDXD_OP_NONBLOCK = 1,
@@ -164,13 +174,16 @@ struct idxd_dma_chan {
struct idxd_wq {
void __iomem *portal;
u32 portal_offset;
+ unsigned int enqcmds_retries;
struct percpu_ref wq_active;
struct completion wq_dead;
+ struct completion wq_resurrect;
struct idxd_dev idxd_dev;
struct idxd_cdev *idxd_cdev;
struct wait_queue_head err_queue;
struct idxd_device *idxd;
int id;
+ struct idxd_irq_entry ie;
enum idxd_wq_type type;
struct idxd_group *group;
int client_count;
@@ -251,6 +264,7 @@ struct idxd_device {
int id;
int major;
u32 cmd_status;
+ struct idxd_irq_entry ie; /* misc irq, msix 0 */
struct pci_dev *pdev;
void __iomem *reg_base;
@@ -266,6 +280,8 @@ struct idxd_device {
unsigned int pasid;
int num_groups;
+ int irq_cnt;
+ bool request_int_handles;
u32 msix_perm_offset;
u32 wqcfg_offset;
@@ -276,24 +292,20 @@ struct idxd_device {
u32 max_batch_size;
int max_groups;
int max_engines;
- int max_tokens;
+ int max_rdbufs;
int max_wqs;
int max_wq_size;
- int token_limit;
- int nr_tokens; /* non-reserved tokens */
+ int rdbuf_limit;
+ int nr_rdbufs; /* non-reserved read buffers */
unsigned int wqcfg_size;
union sw_err_reg sw_err;
wait_queue_head_t cmd_waitq;
- int num_wq_irqs;
- struct idxd_irq_entry *irq_entries;
struct idxd_dma_dev *idxd_dma;
struct workqueue_struct *wq;
struct work_struct work;
- int *int_handles;
-
struct idxd_pmu *idxd_pmu;
};
@@ -380,6 +392,21 @@ static inline void idxd_dev_set_type(struct idxd_dev *idev, int type)
idev->type = type;
}
+static inline struct idxd_irq_entry *idxd_get_ie(struct idxd_device *idxd, int idx)
+{
+ return (idx == 0) ? &idxd->ie : &idxd->wqs[idx - 1]->ie;
+}
+
+static inline struct idxd_wq *ie_to_wq(struct idxd_irq_entry *ie)
+{
+ return container_of(ie, struct idxd_wq, ie);
+}
+
+static inline struct idxd_device *ie_to_idxd(struct idxd_irq_entry *ie)
+{
+ return container_of(ie, struct idxd_device, ie);
+}
+
extern struct bus_type dsa_bus_type;
extern bool support_enqcmd;
@@ -518,17 +545,13 @@ void idxd_unregister_devices(struct idxd_device *idxd);
int idxd_register_driver(void);
void idxd_unregister_driver(void);
void idxd_wqs_quiesce(struct idxd_device *idxd);
+bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
/* device interrupt control */
-void idxd_msix_perm_setup(struct idxd_device *idxd);
-void idxd_msix_perm_clear(struct idxd_device *idxd);
irqreturn_t idxd_misc_thread(int vec, void *data);
irqreturn_t idxd_wq_thread(int irq, void *data);
void idxd_mask_error_interrupts(struct idxd_device *idxd);
void idxd_unmask_error_interrupts(struct idxd_device *idxd);
-void idxd_mask_msix_vectors(struct idxd_device *idxd);
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id);
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id);
/* device control */
int idxd_register_idxd_drv(void);
@@ -564,13 +587,17 @@ int idxd_wq_map_portal(struct idxd_wq *wq);
void idxd_wq_unmap_portal(struct idxd_wq *wq);
int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid);
int idxd_wq_disable_pasid(struct idxd_wq *wq);
+void __idxd_wq_quiesce(struct idxd_wq *wq);
void idxd_wq_quiesce(struct idxd_wq *wq);
int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
+void idxd_wq_free_irq(struct idxd_wq *wq);
+int idxd_wq_request_irq(struct idxd_wq *wq);
/* submission */
int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
/* dmaengine */
int idxd_register_dma_device(struct idxd_device *idxd);
@@ -579,7 +606,7 @@ int idxd_register_dma_channel(struct idxd_wq *wq);
void idxd_unregister_dma_channel(struct idxd_wq *wq);
void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
void idxd_dma_complete_txd(struct idxd_desc *desc,
- enum idxd_complete_type comp_type);
+ enum idxd_complete_type comp_type, bool free_desc);
/* cdev */
int idxd_cdev_register(void);
@@ -603,10 +630,4 @@ static inline void perfmon_init(void) {}
static inline void perfmon_exit(void) {}
#endif
-static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
-{
- idxd_dma_complete_txd(desc, reason);
- idxd_free_desc(desc->wq, desc);
-}
-
#endif
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 7bf03f3..08a5f43 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -72,7 +72,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
{
struct pci_dev *pdev = idxd->pdev;
struct device *dev = &pdev->dev;
- struct idxd_irq_entry *irq_entry;
+ struct idxd_irq_entry *ie;
int i, msixcnt;
int rc = 0;
@@ -81,6 +81,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
dev_err(dev, "Not MSI-X interrupt capable.\n");
return -ENOSPC;
}
+ idxd->irq_cnt = msixcnt;
rc = pci_alloc_irq_vectors(pdev, msixcnt, msixcnt, PCI_IRQ_MSIX);
if (rc != msixcnt) {
@@ -89,87 +90,34 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
}
dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
- /*
- * We implement 1 completion list per MSI-X entry except for
- * entry 0, which is for errors and others.
- */
- idxd->irq_entries = kcalloc_node(msixcnt, sizeof(struct idxd_irq_entry),
- GFP_KERNEL, dev_to_node(dev));
- if (!idxd->irq_entries) {
- rc = -ENOMEM;
- goto err_irq_entries;
- }
- for (i = 0; i < msixcnt; i++) {
- idxd->irq_entries[i].id = i;
- idxd->irq_entries[i].idxd = idxd;
- idxd->irq_entries[i].vector = pci_irq_vector(pdev, i);
- spin_lock_init(&idxd->irq_entries[i].list_lock);
- }
-
- idxd_msix_perm_setup(idxd);
-
- irq_entry = &idxd->irq_entries[0];
- rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread,
- 0, "idxd-misc", irq_entry);
+ ie = idxd_get_ie(idxd, 0);
+ ie->vector = pci_irq_vector(pdev, 0);
+ rc = request_threaded_irq(ie->vector, NULL, idxd_misc_thread, 0, "idxd-misc", ie);
if (rc < 0) {
dev_err(dev, "Failed to allocate misc interrupt.\n");
goto err_misc_irq;
}
+ dev_dbg(dev, "Requested idxd-misc handler on msix vector %d\n", ie->vector);
- dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", irq_entry->vector);
+ for (i = 0; i < idxd->max_wqs; i++) {
+ int msix_idx = i + 1;
- /* first MSI-X entry is not for wq interrupts */
- idxd->num_wq_irqs = msixcnt - 1;
+ ie = idxd_get_ie(idxd, msix_idx);
+ ie->id = msix_idx;
+ ie->int_handle = INVALID_INT_HANDLE;
+ ie->pasid = INVALID_IOASID;
- for (i = 1; i < msixcnt; i++) {
- irq_entry = &idxd->irq_entries[i];
-
- init_llist_head(&idxd->irq_entries[i].pending_llist);
- INIT_LIST_HEAD(&idxd->irq_entries[i].work_list);
- rc = request_threaded_irq(irq_entry->vector, NULL,
- idxd_wq_thread, 0, "idxd-portal", irq_entry);
- if (rc < 0) {
- dev_err(dev, "Failed to allocate irq %d.\n", irq_entry->vector);
- goto err_wq_irqs;
- }
-
- dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, irq_entry->vector);
- if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
- /*
- * The MSIX vector enumeration starts at 1 with vector 0 being the
- * misc interrupt that handles non I/O completion events. The
- * interrupt handles are for IMS enumeration on guest. The misc
- * interrupt vector does not require a handle and therefore we start
- * the int_handles at index 0. Since 'i' starts at 1, the first
- * int_handles index will be 0.
- */
- rc = idxd_device_request_int_handle(idxd, i, &idxd->int_handles[i - 1],
- IDXD_IRQ_MSIX);
- if (rc < 0) {
- free_irq(irq_entry->vector, irq_entry);
- goto err_wq_irqs;
- }
- dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i - 1]);
- }
+ spin_lock_init(&ie->list_lock);
+ init_llist_head(&ie->pending_llist);
+ INIT_LIST_HEAD(&ie->work_list);
}
idxd_unmask_error_interrupts(idxd);
return 0;
- err_wq_irqs:
- while (--i >= 0) {
- irq_entry = &idxd->irq_entries[i];
- free_irq(irq_entry->vector, irq_entry);
- if (i != 0)
- idxd_device_release_int_handle(idxd,
- idxd->int_handles[i], IDXD_IRQ_MSIX);
- }
err_misc_irq:
- /* Disable error interrupt generation */
idxd_mask_error_interrupts(idxd);
- idxd_msix_perm_clear(idxd);
- err_irq_entries:
pci_free_irq_vectors(pdev);
dev_err(dev, "No usable interrupts\n");
return rc;
@@ -178,26 +126,16 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
static void idxd_cleanup_interrupts(struct idxd_device *idxd)
{
struct pci_dev *pdev = idxd->pdev;
- struct idxd_irq_entry *irq_entry;
- int i, msixcnt;
+ struct idxd_irq_entry *ie;
+ int msixcnt;
msixcnt = pci_msix_vec_count(pdev);
if (msixcnt <= 0)
return;
- irq_entry = &idxd->irq_entries[0];
- free_irq(irq_entry->vector, irq_entry);
-
- for (i = 1; i < msixcnt; i++) {
-
- irq_entry = &idxd->irq_entries[i];
- if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE))
- idxd_device_release_int_handle(idxd, idxd->int_handles[i],
- IDXD_IRQ_MSIX);
- free_irq(irq_entry->vector, irq_entry);
- }
-
+ ie = idxd_get_ie(idxd, 0);
idxd_mask_error_interrupts(idxd);
+ free_irq(ie->vector, ie);
pci_free_irq_vectors(pdev);
}
@@ -237,8 +175,10 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
mutex_init(&wq->wq_lock);
init_waitqueue_head(&wq->err_queue);
init_completion(&wq->wq_dead);
- wq->max_xfer_bytes = idxd->max_xfer_bytes;
- wq->max_batch_size = idxd->max_batch_size;
+ init_completion(&wq->wq_resurrect);
+ wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
+ wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+ wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
if (!wq->wqcfg) {
put_device(conf_dev);
@@ -379,13 +319,6 @@ static int idxd_setup_internals(struct idxd_device *idxd)
init_waitqueue_head(&idxd->cmd_waitq);
- if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
- idxd->int_handles = kcalloc_node(idxd->max_wqs, sizeof(int), GFP_KERNEL,
- dev_to_node(dev));
- if (!idxd->int_handles)
- return -ENOMEM;
- }
-
rc = idxd_setup_wqs(idxd);
if (rc < 0)
goto err_wqs;
@@ -416,7 +349,6 @@ static int idxd_setup_internals(struct idxd_device *idxd)
for (i = 0; i < idxd->max_wqs; i++)
put_device(wq_confdev(idxd->wqs[i]));
err_wqs:
- kfree(idxd->int_handles);
return rc;
}
@@ -451,6 +383,10 @@ static void idxd_read_caps(struct idxd_device *idxd)
dev_dbg(dev, "cmd_cap: %#x\n", idxd->hw.cmd_cap);
}
+ /* reading command capabilities */
+ if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE))
+ idxd->request_int_handles = true;
+
idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift;
dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes);
idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift;
@@ -464,9 +400,9 @@ static void idxd_read_caps(struct idxd_device *idxd)
dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits);
idxd->max_groups = idxd->hw.group_cap.num_groups;
dev_dbg(dev, "max groups: %u\n", idxd->max_groups);
- idxd->max_tokens = idxd->hw.group_cap.total_tokens;
- dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens);
- idxd->nr_tokens = idxd->max_tokens;
+ idxd->max_rdbufs = idxd->hw.group_cap.total_rdbufs;
+ dev_dbg(dev, "max read buffers: %u\n", idxd->max_rdbufs);
+ idxd->nr_rdbufs = idxd->max_rdbufs;
/* read engine capabilities */
idxd->hw.engine_cap.bits =
@@ -611,8 +547,6 @@ static int idxd_probe(struct idxd_device *idxd)
if (rc)
goto err_config;
- dev_dbg(dev, "IDXD interrupt setup complete.\n");
-
idxd->major = idxd_cdev_get_major(idxd);
rc = perfmon_pmu_init(idxd);
@@ -708,32 +642,6 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return rc;
}
-static void idxd_flush_pending_llist(struct idxd_irq_entry *ie)
-{
- struct idxd_desc *desc, *itr;
- struct llist_node *head;
-
- head = llist_del_all(&ie->pending_llist);
- if (!head)
- return;
-
- llist_for_each_entry_safe(desc, itr, head, llnode) {
- idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
- idxd_free_desc(desc->wq, desc);
- }
-}
-
-static void idxd_flush_work_list(struct idxd_irq_entry *ie)
-{
- struct idxd_desc *desc, *iter;
-
- list_for_each_entry_safe(desc, iter, &ie->work_list, list) {
- list_del(&desc->list);
- idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
- idxd_free_desc(desc->wq, desc);
- }
-}
-
void idxd_wqs_quiesce(struct idxd_device *idxd)
{
struct idxd_wq *wq;
@@ -746,47 +654,19 @@ void idxd_wqs_quiesce(struct idxd_device *idxd)
}
}
-static void idxd_release_int_handles(struct idxd_device *idxd)
-{
- struct device *dev = &idxd->pdev->dev;
- int i, rc;
-
- for (i = 0; i < idxd->num_wq_irqs; i++) {
- if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) {
- rc = idxd_device_release_int_handle(idxd, idxd->int_handles[i],
- IDXD_IRQ_MSIX);
- if (rc < 0)
- dev_warn(dev, "irq handle %d release failed\n",
- idxd->int_handles[i]);
- else
- dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i]);
- }
- }
-}
-
static void idxd_shutdown(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
- int rc, i;
struct idxd_irq_entry *irq_entry;
- int msixcnt = pci_msix_vec_count(pdev);
+ int rc;
rc = idxd_device_disable(idxd);
if (rc)
dev_err(&pdev->dev, "Disabling device failed\n");
- dev_dbg(&pdev->dev, "%s called\n", __func__);
- idxd_mask_msix_vectors(idxd);
+ irq_entry = &idxd->ie;
+ synchronize_irq(irq_entry->vector);
idxd_mask_error_interrupts(idxd);
-
- for (i = 0; i < msixcnt; i++) {
- irq_entry = &idxd->irq_entries[i];
- synchronize_irq(irq_entry->vector);
- if (i == 0)
- continue;
- idxd_flush_pending_llist(irq_entry);
- idxd_flush_work_list(irq_entry);
- }
flush_workqueue(idxd->wq);
}
@@ -794,8 +674,6 @@ static void idxd_remove(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
struct idxd_irq_entry *irq_entry;
- int msixcnt = pci_msix_vec_count(pdev);
- int i;
idxd_unregister_devices(idxd);
/*
@@ -811,12 +689,8 @@ static void idxd_remove(struct pci_dev *pdev)
if (device_pasid_enabled(idxd))
idxd_disable_system_pasid(idxd);
- for (i = 0; i < msixcnt; i++) {
- irq_entry = &idxd->irq_entries[i];
- free_irq(irq_entry->vector, irq_entry);
- }
- idxd_msix_perm_clear(idxd);
- idxd_release_int_handles(idxd);
+ irq_entry = idxd_get_ie(idxd, 0);
+ free_irq(irq_entry->vector, irq_entry);
pci_free_irq_vectors(pdev);
pci_iounmap(pdev, idxd->reg_base);
iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index cf2c8bc..743ead5 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -6,6 +6,7 @@
#include <linux/pci.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/dmaengine.h>
+#include <linux/delay.h>
#include <uapi/linux/idxd.h>
#include "../dmaengine.h"
#include "idxd.h"
@@ -22,6 +23,16 @@ struct idxd_fault {
struct idxd_device *idxd;
};
+struct idxd_resubmit {
+ struct work_struct work;
+ struct idxd_desc *desc;
+};
+
+struct idxd_int_handle_revoke {
+ struct work_struct work;
+ struct idxd_device *idxd;
+};
+
static void idxd_device_reinit(struct work_struct *work)
{
struct idxd_device *idxd = container_of(work, struct idxd_device, work);
@@ -55,6 +66,162 @@ static void idxd_device_reinit(struct work_struct *work)
idxd_device_clear_state(idxd);
}
+/*
+ * The function sends a drain descriptor for the interrupt handle. The drain ensures
+ * all descriptors with this interrupt handle is flushed and the interrupt
+ * will allow the cleanup of the outstanding descriptors.
+ */
+static void idxd_int_handle_revoke_drain(struct idxd_irq_entry *ie)
+{
+ struct idxd_wq *wq = ie_to_wq(ie);
+ struct idxd_device *idxd = wq->idxd;
+ struct device *dev = &idxd->pdev->dev;
+ struct dsa_hw_desc desc = {};
+ void __iomem *portal;
+ int rc;
+
+ /* Issue a simple drain operation with interrupt but no completion record */
+ desc.flags = IDXD_OP_FLAG_RCI;
+ desc.opcode = DSA_OPCODE_DRAIN;
+ desc.priv = 1;
+
+ if (ie->pasid != INVALID_IOASID)
+ desc.pasid = ie->pasid;
+ desc.int_handle = ie->int_handle;
+ portal = idxd_wq_portal_addr(wq);
+
+ /*
+ * The wmb() makes sure that the descriptor is all there before we
+ * issue.
+ */
+ wmb();
+ if (wq_dedicated(wq)) {
+ iosubmit_cmds512(portal, &desc, 1);
+ } else {
+ rc = idxd_enqcmds(wq, portal, &desc);
+ /* This should not fail unless hardware failed. */
+ if (rc < 0)
+ dev_warn(dev, "Failed to submit drain desc on wq %d\n", wq->id);
+ }
+}
+
+static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie)
+{
+ LIST_HEAD(flist);
+ struct idxd_desc *d, *t;
+ struct llist_node *head;
+
+ spin_lock(&ie->list_lock);
+ head = llist_del_all(&ie->pending_llist);
+ if (head) {
+ llist_for_each_entry_safe(d, t, head, llnode)
+ list_add_tail(&d->list, &ie->work_list);
+ }
+
+ list_for_each_entry_safe(d, t, &ie->work_list, list) {
+ if (d->completion->status == DSA_COMP_INT_HANDLE_INVAL)
+ list_move_tail(&d->list, &flist);
+ }
+ spin_unlock(&ie->list_lock);
+
+ list_for_each_entry_safe(d, t, &flist, list) {
+ list_del(&d->list);
+ idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true);
+ }
+}
+
+static void idxd_int_handle_revoke(struct work_struct *work)
+{
+ struct idxd_int_handle_revoke *revoke =
+ container_of(work, struct idxd_int_handle_revoke, work);
+ struct idxd_device *idxd = revoke->idxd;
+ struct pci_dev *pdev = idxd->pdev;
+ struct device *dev = &pdev->dev;
+ int i, new_handle, rc;
+
+ if (!idxd->request_int_handles) {
+ kfree(revoke);
+ dev_warn(dev, "Unexpected int handle refresh interrupt.\n");
+ return;
+ }
+
+ /*
+ * The loop attempts to acquire new interrupt handle for all interrupt
+ * vectors that supports a handle. If a new interrupt handle is acquired and the
+ * wq is kernel type, the driver will kill the percpu_ref to pause all
+ * ongoing descriptor submissions. The interrupt handle is then changed.
+ * After change, the percpu_ref is revived and all the pending submissions
+ * are woken to try again. A drain is sent to for the interrupt handle
+ * at the end to make sure all invalid int handle descriptors are processed.
+ */
+ for (i = 1; i < idxd->irq_cnt; i++) {
+ struct idxd_irq_entry *ie = idxd_get_ie(idxd, i);
+ struct idxd_wq *wq = ie_to_wq(ie);
+
+ if (ie->int_handle == INVALID_INT_HANDLE)
+ continue;
+
+ rc = idxd_device_request_int_handle(idxd, i, &new_handle, IDXD_IRQ_MSIX);
+ if (rc < 0) {
+ dev_warn(dev, "get int handle %d failed: %d\n", i, rc);
+ /*
+ * Failed to acquire new interrupt handle. Kill the WQ
+ * and release all the pending submitters. The submitters will
+ * get error return code and handle appropriately.
+ */
+ ie->int_handle = INVALID_INT_HANDLE;
+ idxd_wq_quiesce(wq);
+ idxd_abort_invalid_int_handle_descs(ie);
+ continue;
+ }
+
+ /* No change in interrupt handle, nothing needs to be done */
+ if (ie->int_handle == new_handle)
+ continue;
+
+ if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL) {
+ /*
+ * All the MSIX interrupts are allocated at once during probe.
+ * Therefore we need to update all interrupts even if the WQ
+ * isn't supporting interrupt operations.
+ */
+ ie->int_handle = new_handle;
+ continue;
+ }
+
+ mutex_lock(&wq->wq_lock);
+ reinit_completion(&wq->wq_resurrect);
+
+ /* Kill percpu_ref to pause additional descriptor submissions */
+ percpu_ref_kill(&wq->wq_active);
+
+ /* Wait for all submitters quiesce before we change interrupt handle */
+ wait_for_completion(&wq->wq_dead);
+
+ ie->int_handle = new_handle;
+
+ /* Revive percpu ref and wake up all the waiting submitters */
+ percpu_ref_reinit(&wq->wq_active);
+ complete_all(&wq->wq_resurrect);
+ mutex_unlock(&wq->wq_lock);
+
+ /*
+ * The delay here is to wait for all possible MOVDIR64B that
+ * are issued before percpu_ref_kill() has happened to have
+ * reached the PCIe domain before the drain is issued. The driver
+ * needs to ensure that the drain descriptor issued does not pass
+ * all the other issued descriptors that contain the invalid
+ * interrupt handle in order to ensure that the drain descriptor
+ * interrupt will allow the cleanup of all the descriptors with
+ * invalid interrupt handle.
+ */
+ if (wq_dedicated(wq))
+ udelay(100);
+ idxd_int_handle_revoke_drain(ie);
+ }
+ kfree(revoke);
+}
+
static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
{
struct device *dev = &idxd->pdev->dev;
@@ -101,6 +268,23 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
err = true;
}
+ if (cause & IDXD_INTC_INT_HANDLE_REVOKED) {
+ struct idxd_int_handle_revoke *revoke;
+
+ val |= IDXD_INTC_INT_HANDLE_REVOKED;
+
+ revoke = kzalloc(sizeof(*revoke), GFP_ATOMIC);
+ if (revoke) {
+ revoke->idxd = idxd;
+ INIT_WORK(&revoke->work, idxd_int_handle_revoke);
+ queue_work(idxd->wq, &revoke->work);
+
+ } else {
+ dev_err(dev, "Failed to allocate work for int handle revoke\n");
+ idxd_wqs_quiesce(idxd);
+ }
+ }
+
if (cause & IDXD_INTC_CMD) {
val |= IDXD_INTC_CMD;
complete(idxd->cmd_done);
@@ -157,7 +341,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
irqreturn_t idxd_misc_thread(int vec, void *data)
{
struct idxd_irq_entry *irq_entry = data;
- struct idxd_device *idxd = irq_entry->idxd;
+ struct idxd_device *idxd = ie_to_idxd(irq_entry);
int rc;
u32 cause;
@@ -177,6 +361,51 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
return IRQ_HANDLED;
}
+static void idxd_int_handle_resubmit_work(struct work_struct *work)
+{
+ struct idxd_resubmit *irw = container_of(work, struct idxd_resubmit, work);
+ struct idxd_desc *desc = irw->desc;
+ struct idxd_wq *wq = desc->wq;
+ int rc;
+
+ desc->completion->status = 0;
+ rc = idxd_submit_desc(wq, desc);
+ if (rc < 0) {
+ dev_dbg(&wq->idxd->pdev->dev, "Failed to resubmit desc %d to wq %d.\n",
+ desc->id, wq->id);
+ /*
+ * If the error is not -EAGAIN, it means the submission failed due to wq
+ * has been killed instead of ENQCMDS failure. Here the driver needs to
+ * notify the submitter of the failure by reporting abort status.
+ *
+ * -EAGAIN comes from ENQCMDS failure. idxd_submit_desc() will handle the
+ * abort.
+ */
+ if (rc != -EAGAIN) {
+ desc->completion->status = IDXD_COMP_DESC_ABORT;
+ idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false);
+ }
+ idxd_free_desc(wq, desc);
+ }
+ kfree(irw);
+}
+
+bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc)
+{
+ struct idxd_wq *wq = desc->wq;
+ struct idxd_device *idxd = wq->idxd;
+ struct idxd_resubmit *irw;
+
+ irw = kzalloc(sizeof(*irw), GFP_KERNEL);
+ if (!irw)
+ return false;
+
+ irw->desc = desc;
+ INIT_WORK(&irw->work, idxd_int_handle_resubmit_work);
+ queue_work(idxd->wq, &irw->work);
+ return true;
+}
+
static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
{
struct idxd_desc *desc, *t;
@@ -195,11 +424,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
* and 0xff, which DSA_COMP_STATUS_MASK can mask out.
*/
if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
- complete_desc(desc, IDXD_COMPLETE_ABORT);
+ idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
continue;
}
- complete_desc(desc, IDXD_COMPLETE_NORMAL);
+ idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
} else {
spin_lock(&irq_entry->list_lock);
list_add_tail(&desc->list,
@@ -238,11 +467,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
* and 0xff, which DSA_COMP_STATUS_MASK can mask out.
*/
if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
- complete_desc(desc, IDXD_COMPLETE_ABORT);
+ idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
continue;
}
- complete_desc(desc, IDXD_COMPLETE_NORMAL);
+ idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
}
}
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 262c822..aa642ae 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -64,9 +64,9 @@ union wq_cap_reg {
union group_cap_reg {
struct {
u64 num_groups:8;
- u64 total_tokens:8;
- u64 token_en:1;
- u64 token_limit:1;
+ u64 total_rdbufs:8; /* formerly total_tokens */
+ u64 rdbuf_ctrl:1; /* formerly token_en */
+ u64 rdbuf_limit:1; /* formerly token_limit */
u64 rsvd:46;
};
u64 bits;
@@ -110,7 +110,7 @@ union offsets_reg {
#define IDXD_GENCFG_OFFSET 0x80
union gencfg_reg {
struct {
- u32 token_limit:8;
+ u32 rdbuf_limit:8;
u32 rsvd:4;
u32 user_int_en:1;
u32 rsvd2:19;
@@ -158,6 +158,7 @@ enum idxd_device_reset_type {
#define IDXD_INTC_OCCUPY 0x04
#define IDXD_INTC_PERFMON_OVFL 0x08
#define IDXD_INTC_HALT_STATE 0x10
+#define IDXD_INTC_INT_HANDLE_REVOKED 0x80000000
#define IDXD_CMD_OFFSET 0xa0
union idxd_command_reg {
@@ -287,10 +288,10 @@ union group_flags {
u32 tc_a:3;
u32 tc_b:3;
u32 rsvd:1;
- u32 use_token_limit:1;
- u32 tokens_reserved:8;
+ u32 use_rdbuf_limit:1;
+ u32 rdbufs_reserved:8;
u32 rsvd2:4;
- u32 tokens_allowed:8;
+ u32 rdbufs_allowed:8;
u32 rsvd3:4;
};
u32 bits;
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index 83452fb..e289fd4 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -21,15 +21,6 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu)
if (device_pasid_enabled(idxd))
desc->hw->pasid = idxd->pasid;
- /*
- * On host, MSIX vecotr 0 is used for misc interrupt. Therefore when we match
- * vector 1:1 to the WQ id, we need to add 1
- */
- if (!idxd->int_handles)
- desc->hw->int_handle = wq->id + 1;
- else
- desc->hw->int_handle = idxd->int_handles[wq->id];
-
return desc;
}
@@ -134,35 +125,58 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
spin_unlock(&ie->list_lock);
if (found)
- complete_desc(found, IDXD_COMPLETE_ABORT);
+ idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false);
/*
- * complete_desc() will return desc to allocator and the desc can be
- * acquired by a different process and the desc->list can be modified.
- * Delete desc from list so the list trasversing does not get corrupted
- * by the other process.
+ * completing the descriptor will return desc to allocator and
+ * the desc can be acquired by a different process and the
+ * desc->list can be modified. Delete desc from list so the
+ * list trasversing does not get corrupted by the other process.
*/
list_for_each_entry_safe(d, t, &flist, list) {
list_del_init(&d->list);
- complete_desc(d, IDXD_COMPLETE_NORMAL);
+ idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true);
}
}
+/*
+ * ENQCMDS typically fail when the WQ is inactive or busy. On host submission, the driver
+ * has better control of number of descriptors being submitted to a shared wq by limiting
+ * the number of driver allocated descriptors to the wq size. However, when the swq is
+ * exported to a guest kernel, it may be shared with multiple guest kernels. This means
+ * the likelihood of getting busy returned on the swq when submitting goes significantly up.
+ * Having a tunable retry mechanism allows the driver to keep trying for a bit before giving
+ * up. The sysfs knob can be tuned by the system administrator.
+ */
+int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc)
+{
+ int rc, retries = 0;
+
+ do {
+ rc = enqcmds(portal, desc);
+ if (rc == 0)
+ break;
+ cpu_relax();
+ } while (retries++ < wq->enqcmds_retries);
+
+ return rc;
+}
+
int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
{
struct idxd_device *idxd = wq->idxd;
struct idxd_irq_entry *ie = NULL;
+ u32 desc_flags = desc->hw->flags;
void __iomem *portal;
int rc;
- if (idxd->state != IDXD_DEV_ENABLED) {
- idxd_free_desc(wq, desc);
+ if (idxd->state != IDXD_DEV_ENABLED)
return -EIO;
- }
if (!percpu_ref_tryget_live(&wq->wq_active)) {
- idxd_free_desc(wq, desc);
- return -ENXIO;
+ wait_for_completion(&wq->wq_resurrect);
+ if (!percpu_ref_tryget_live(&wq->wq_active))
+ return -ENXIO;
}
portal = idxd_wq_portal_addr(wq);
@@ -178,28 +192,21 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
* Pending the descriptor to the lockless list for the irq_entry
* that we designated the descriptor to.
*/
- if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
- ie = &idxd->irq_entries[wq->id + 1];
+ if (desc_flags & IDXD_OP_FLAG_RCI) {
+ ie = &wq->ie;
+ desc->hw->int_handle = ie->int_handle;
llist_add(&desc->llnode, &ie->pending_llist);
}
if (wq_dedicated(wq)) {
iosubmit_cmds512(portal, desc->hw, 1);
} else {
- /*
- * It's not likely that we would receive queue full rejection
- * since the descriptor allocation gates at wq size. If we
- * receive a -EAGAIN, that means something went wrong such as the
- * device is not accepting descriptor at all.
- */
- rc = enqcmds(portal, desc->hw);
+ rc = idxd_enqcmds(wq, portal, desc->hw);
if (rc < 0) {
percpu_ref_put(&wq->wq_active);
/* abort operation frees the descriptor */
if (ie)
llist_abort_desc(wq, ie, desc);
- else
- idxd_free_desc(wq, desc);
return rc;
}
}
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index a9025be..7e19ab9 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -99,31 +99,39 @@ struct device_type idxd_engine_device_type = {
/* Group attributes */
-static void idxd_set_free_tokens(struct idxd_device *idxd)
+static void idxd_set_free_rdbufs(struct idxd_device *idxd)
{
- int i, tokens;
+ int i, rdbufs;
- for (i = 0, tokens = 0; i < idxd->max_groups; i++) {
+ for (i = 0, rdbufs = 0; i < idxd->max_groups; i++) {
struct idxd_group *g = idxd->groups[i];
- tokens += g->tokens_reserved;
+ rdbufs += g->rdbufs_reserved;
}
- idxd->nr_tokens = idxd->max_tokens - tokens;
+ idxd->nr_rdbufs = idxd->max_rdbufs - rdbufs;
+}
+
+static ssize_t group_read_buffers_reserved_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+
+ return sysfs_emit(buf, "%u\n", group->rdbufs_reserved);
}
static ssize_t group_tokens_reserved_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- struct idxd_group *group = confdev_to_group(dev);
-
- return sysfs_emit(buf, "%u\n", group->tokens_reserved);
+ dev_warn_once(dev, "attribute deprecated, see read_buffers_reserved.\n");
+ return group_read_buffers_reserved_show(dev, attr, buf);
}
-static ssize_t group_tokens_reserved_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t group_read_buffers_reserved_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct idxd_group *group = confdev_to_group(dev);
struct idxd_device *idxd = group->idxd;
@@ -143,33 +151,53 @@ static ssize_t group_tokens_reserved_store(struct device *dev,
if (idxd->state == IDXD_DEV_ENABLED)
return -EPERM;
- if (val > idxd->max_tokens)
+ if (val > idxd->max_rdbufs)
return -EINVAL;
- if (val > idxd->nr_tokens + group->tokens_reserved)
+ if (val > idxd->nr_rdbufs + group->rdbufs_reserved)
return -EINVAL;
- group->tokens_reserved = val;
- idxd_set_free_tokens(idxd);
+ group->rdbufs_reserved = val;
+ idxd_set_free_rdbufs(idxd);
return count;
}
+static ssize_t group_tokens_reserved_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ dev_warn_once(dev, "attribute deprecated, see read_buffers_reserved.\n");
+ return group_read_buffers_reserved_store(dev, attr, buf, count);
+}
+
static struct device_attribute dev_attr_group_tokens_reserved =
__ATTR(tokens_reserved, 0644, group_tokens_reserved_show,
group_tokens_reserved_store);
+static struct device_attribute dev_attr_group_read_buffers_reserved =
+ __ATTR(read_buffers_reserved, 0644, group_read_buffers_reserved_show,
+ group_read_buffers_reserved_store);
+
+static ssize_t group_read_buffers_allowed_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+
+ return sysfs_emit(buf, "%u\n", group->rdbufs_allowed);
+}
+
static ssize_t group_tokens_allowed_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- struct idxd_group *group = confdev_to_group(dev);
-
- return sysfs_emit(buf, "%u\n", group->tokens_allowed);
+ dev_warn_once(dev, "attribute deprecated, see read_buffers_allowed.\n");
+ return group_read_buffers_allowed_show(dev, attr, buf);
}
-static ssize_t group_tokens_allowed_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t group_read_buffers_allowed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct idxd_group *group = confdev_to_group(dev);
struct idxd_device *idxd = group->idxd;
@@ -190,29 +218,49 @@ static ssize_t group_tokens_allowed_store(struct device *dev,
return -EPERM;
if (val < 4 * group->num_engines ||
- val > group->tokens_reserved + idxd->nr_tokens)
+ val > group->rdbufs_reserved + idxd->nr_rdbufs)
return -EINVAL;
- group->tokens_allowed = val;
+ group->rdbufs_allowed = val;
return count;
}
+static ssize_t group_tokens_allowed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ dev_warn_once(dev, "attribute deprecated, see read_buffers_allowed.\n");
+ return group_read_buffers_allowed_store(dev, attr, buf, count);
+}
+
static struct device_attribute dev_attr_group_tokens_allowed =
__ATTR(tokens_allowed, 0644, group_tokens_allowed_show,
group_tokens_allowed_store);
+static struct device_attribute dev_attr_group_read_buffers_allowed =
+ __ATTR(read_buffers_allowed, 0644, group_read_buffers_allowed_show,
+ group_read_buffers_allowed_store);
+
+static ssize_t group_use_read_buffer_limit_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+
+ return sysfs_emit(buf, "%u\n", group->use_rdbuf_limit);
+}
+
static ssize_t group_use_token_limit_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- struct idxd_group *group = confdev_to_group(dev);
-
- return sysfs_emit(buf, "%u\n", group->use_token_limit);
+ dev_warn_once(dev, "attribute deprecated, see use_read_buffer_limit.\n");
+ return group_use_read_buffer_limit_show(dev, attr, buf);
}
-static ssize_t group_use_token_limit_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t group_use_read_buffer_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct idxd_group *group = confdev_to_group(dev);
struct idxd_device *idxd = group->idxd;
@@ -232,17 +280,29 @@ static ssize_t group_use_token_limit_store(struct device *dev,
if (idxd->state == IDXD_DEV_ENABLED)
return -EPERM;
- if (idxd->token_limit == 0)
+ if (idxd->rdbuf_limit == 0)
return -EPERM;
- group->use_token_limit = !!val;
+ group->use_rdbuf_limit = !!val;
return count;
}
+static ssize_t group_use_token_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ dev_warn_once(dev, "attribute deprecated, see use_read_buffer_limit.\n");
+ return group_use_read_buffer_limit_store(dev, attr, buf, count);
+}
+
static struct device_attribute dev_attr_group_use_token_limit =
__ATTR(use_token_limit, 0644, group_use_token_limit_show,
group_use_token_limit_store);
+static struct device_attribute dev_attr_group_use_read_buffer_limit =
+ __ATTR(use_read_buffer_limit, 0644, group_use_read_buffer_limit_show,
+ group_use_read_buffer_limit_store);
+
static ssize_t group_engines_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -387,8 +447,11 @@ static struct attribute *idxd_group_attributes[] = {
&dev_attr_group_work_queues.attr,
&dev_attr_group_engines.attr,
&dev_attr_group_use_token_limit.attr,
+ &dev_attr_group_use_read_buffer_limit.attr,
&dev_attr_group_tokens_allowed.attr,
+ &dev_attr_group_read_buffers_allowed.attr,
&dev_attr_group_tokens_reserved.attr,
+ &dev_attr_group_read_buffers_reserved.attr,
&dev_attr_group_traffic_class_a.attr,
&dev_attr_group_traffic_class_b.attr,
NULL,
@@ -945,6 +1008,41 @@ static ssize_t wq_occupancy_show(struct device *dev, struct device_attribute *at
static struct device_attribute dev_attr_wq_occupancy =
__ATTR(occupancy, 0444, wq_occupancy_show, NULL);
+static ssize_t wq_enqcmds_retries_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct idxd_wq *wq = confdev_to_wq(dev);
+
+ if (wq_dedicated(wq))
+ return -EOPNOTSUPP;
+
+ return sysfs_emit(buf, "%u\n", wq->enqcmds_retries);
+}
+
+static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct idxd_wq *wq = confdev_to_wq(dev);
+ int rc;
+ unsigned int retries;
+
+ if (wq_dedicated(wq))
+ return -EOPNOTSUPP;
+
+ rc = kstrtouint(buf, 10, &retries);
+ if (rc < 0)
+ return rc;
+
+ if (retries > IDXD_ENQCMDS_MAX_RETRIES)
+ retries = IDXD_ENQCMDS_MAX_RETRIES;
+
+ wq->enqcmds_retries = retries;
+ return count;
+}
+
+static struct device_attribute dev_attr_wq_enqcmds_retries =
+ __ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store);
+
static struct attribute *idxd_wq_attributes[] = {
&dev_attr_wq_clients.attr,
&dev_attr_wq_state.attr,
@@ -961,6 +1059,7 @@ static struct attribute *idxd_wq_attributes[] = {
&dev_attr_wq_max_batch_size.attr,
&dev_attr_wq_ats_disable.attr,
&dev_attr_wq_occupancy.attr,
+ &dev_attr_wq_enqcmds_retries.attr,
NULL,
};
@@ -1156,26 +1255,42 @@ static ssize_t errors_show(struct device *dev,
}
static DEVICE_ATTR_RO(errors);
-static ssize_t max_tokens_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t max_read_buffers_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct idxd_device *idxd = confdev_to_idxd(dev);
- return sysfs_emit(buf, "%u\n", idxd->max_tokens);
+ return sysfs_emit(buf, "%u\n", idxd->max_rdbufs);
}
-static DEVICE_ATTR_RO(max_tokens);
+
+static ssize_t max_tokens_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ dev_warn_once(dev, "attribute deprecated, see max_read_buffers.\n");
+ return max_read_buffers_show(dev, attr, buf);
+}
+
+static DEVICE_ATTR_RO(max_tokens); /* deprecated */
+static DEVICE_ATTR_RO(max_read_buffers);
+
+static ssize_t read_buffer_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct idxd_device *idxd = confdev_to_idxd(dev);
+
+ return sysfs_emit(buf, "%u\n", idxd->rdbuf_limit);
+}
static ssize_t token_limit_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct idxd_device *idxd = confdev_to_idxd(dev);
-
- return sysfs_emit(buf, "%u\n", idxd->token_limit);
+ dev_warn_once(dev, "attribute deprecated, see read_buffer_limit.\n");
+ return read_buffer_limit_show(dev, attr, buf);
}
-static ssize_t token_limit_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t read_buffer_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct idxd_device *idxd = confdev_to_idxd(dev);
unsigned long val;
@@ -1191,16 +1306,26 @@ static ssize_t token_limit_store(struct device *dev,
if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
return -EPERM;
- if (!idxd->hw.group_cap.token_limit)
+ if (!idxd->hw.group_cap.rdbuf_limit)
return -EPERM;
- if (val > idxd->hw.group_cap.total_tokens)
+ if (val > idxd->hw.group_cap.total_rdbufs)
return -EINVAL;
- idxd->token_limit = val;
+ idxd->rdbuf_limit = val;
return count;
}
-static DEVICE_ATTR_RW(token_limit);
+
+static ssize_t token_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ dev_warn_once(dev, "attribute deprecated, see read_buffer_limit\n");
+ return read_buffer_limit_store(dev, attr, buf, count);
+}
+
+static DEVICE_ATTR_RW(token_limit); /* deprecated */
+static DEVICE_ATTR_RW(read_buffer_limit);
static ssize_t cdev_major_show(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -1246,7 +1371,9 @@ static struct attribute *idxd_device_attributes[] = {
&dev_attr_state.attr,
&dev_attr_errors.attr,
&dev_attr_max_tokens.attr,
+ &dev_attr_max_read_buffers.attr,
&dev_attr_token_limit.attr,
+ &dev_attr_read_buffer_limit.attr,
&dev_attr_cdev_major.attr,
&dev_attr_cmd_status.attr,
NULL,
@@ -1268,8 +1395,6 @@ static void idxd_conf_device_release(struct device *dev)
kfree(idxd->groups);
kfree(idxd->wqs);
kfree(idxd->engines);
- kfree(idxd->irq_entries);
- kfree(idxd->int_handles);
ida_free(&idxd_ida, idxd->id);
kfree(idxd);
}
diff --git a/drivers/dma/ioat/sysfs.c b/drivers/dma/ioat/sysfs.c
index aa44bcd..168adf2 100644
--- a/drivers/dma/ioat/sysfs.c
+++ b/drivers/dma/ioat/sysfs.c
@@ -158,8 +158,9 @@ static struct attribute *ioat_attrs[] = {
&intr_coalesce_attr.attr,
NULL,
};
+ATTRIBUTE_GROUPS(ioat);
struct kobj_type ioat_ktype = {
.sysfs_ops = &ioat_sysfs_ops,
- .default_attrs = ioat_attrs,
+ .default_groups = ioat_groups,
};
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 1da0411..c359dec 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -835,7 +835,7 @@ static int pch_dma_probe(struct pci_dev *pdev,
goto err_disable_pdev;
}
- err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
if (err) {
dev_err(&pdev->dev, "Cannot set proper DMA config\n");
goto err_free_res;
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index e2b5129..5e46e34 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -3240,7 +3240,6 @@ static int ppc440spe_adma_dma2rxor_prep_src(
struct ppc440spe_rxor *cursor, int index,
int src_cnt, u32 addr)
{
- int rval = 0;
u32 sign;
struct ppc440spe_adma_desc_slot *desc = hdesc;
int i;
@@ -3348,7 +3347,7 @@ static int ppc440spe_adma_dma2rxor_prep_src(
break;
}
- return rval;
+ return 0;
}
/**
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 1a1b7d8..94f3648 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -2206,10 +2206,8 @@ static int gpi_probe(struct platform_device *pdev)
/* set up irq */
ret = platform_get_irq(pdev, i);
- if (ret < 0) {
- dev_err(gpi_dev->dev, "platform_get_irq failed for %d:%d\n", i, ret);
+ if (ret < 0)
return ret;
- }
gpii->irq = ret;
/* set up channel specific register info */
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 5c7716f..481f45c 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -236,7 +236,7 @@ struct rcar_dmac_of_data {
#define RCAR_DMAOR_PRI_ROUND_ROBIN (3 << 8)
#define RCAR_DMAOR_AE (1 << 2)
#define RCAR_DMAOR_DME (1 << 0)
-#define RCAR_DMACHCLR 0x0080 /* Not on R-Car V3U */
+#define RCAR_DMACHCLR 0x0080 /* Not on R-Car Gen4 */
#define RCAR_DMADPSEC 0x00a0
#define RCAR_DMASAR 0x0000
@@ -299,8 +299,8 @@ struct rcar_dmac_of_data {
#define RCAR_DMAFIXDAR 0x0014
#define RCAR_DMAFIXDPBASE 0x0060
-/* For R-Car V3U */
-#define RCAR_V3U_DMACHCLR 0x0100
+/* For R-Car Gen4 */
+#define RCAR_GEN4_DMACHCLR 0x0100
/* Hardcode the MEMCPY transfer size to 4 bytes. */
#define RCAR_DMAC_MEMCPY_XFER_SIZE 4
@@ -345,7 +345,7 @@ static void rcar_dmac_chan_clear(struct rcar_dmac *dmac,
struct rcar_dmac_chan *chan)
{
if (dmac->chan_base)
- rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+ rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1);
else
rcar_dmac_write(dmac, RCAR_DMACHCLR, BIT(chan->index));
}
@@ -357,7 +357,7 @@ static void rcar_dmac_chan_clear_all(struct rcar_dmac *dmac)
if (dmac->chan_base) {
for_each_rcar_dmac_chan(i, dmac, chan)
- rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+ rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1);
} else {
rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
}
@@ -2009,7 +2009,7 @@ static const struct rcar_dmac_of_data rcar_dmac_data = {
.chan_offset_stride = 0x80,
};
-static const struct rcar_dmac_of_data rcar_v3u_dmac_data = {
+static const struct rcar_dmac_of_data rcar_gen4_dmac_data = {
.chan_offset_base = 0x0,
.chan_offset_stride = 0x1000,
};
@@ -2019,8 +2019,11 @@ static const struct of_device_id rcar_dmac_of_ids[] = {
.compatible = "renesas,rcar-dmac",
.data = &rcar_dmac_data,
}, {
+ .compatible = "renesas,rcar-gen4-dmac",
+ .data = &rcar_gen4_dmac_data,
+ }, {
.compatible = "renesas,dmac-r8a779a0",
- .data = &rcar_v3u_dmac_data,
+ .data = &rcar_gen4_dmac_data,
},
{ /* Sentinel */ }
};
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 41c6bc6..158e5e7 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -1034,9 +1034,7 @@ EXPORT_SYMBOL(shdma_cleanup);
static int __init shdma_enter(void)
{
- shdma_slave_used = kcalloc(DIV_ROUND_UP(slave_num, BITS_PER_LONG),
- sizeof(long),
- GFP_KERNEL);
+ shdma_slave_used = bitmap_zalloc(slave_num, GFP_KERNEL);
if (!shdma_slave_used)
return -ENOMEM;
return 0;
@@ -1045,7 +1043,7 @@ module_init(shdma_enter);
static void __exit shdma_exit(void)
{
- kfree(shdma_slave_used);
+ bitmap_free(shdma_slave_used);
}
module_exit(shdma_exit);
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index d30a4a2..6f57ff0 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -10,6 +10,7 @@
* Inspired by stm32-dma.c and dma-jz4780.c
*/
+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
@@ -32,13 +33,6 @@
#include "virt-dma.h"
-/* MDMA Generic getter/setter */
-#define STM32_MDMA_SHIFT(n) (ffs(n) - 1)
-#define STM32_MDMA_SET(n, mask) (((n) << STM32_MDMA_SHIFT(mask)) & \
- (mask))
-#define STM32_MDMA_GET(n, mask) (((n) & (mask)) >> \
- STM32_MDMA_SHIFT(mask))
-
#define STM32_MDMA_GISR0 0x0000 /* MDMA Int Status Reg 1 */
#define STM32_MDMA_GISR1 0x0004 /* MDMA Int Status Reg 2 */
@@ -80,8 +74,7 @@
#define STM32_MDMA_CCR_HEX BIT(13)
#define STM32_MDMA_CCR_BEX BIT(12)
#define STM32_MDMA_CCR_PL_MASK GENMASK(7, 6)
-#define STM32_MDMA_CCR_PL(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CCR_PL_MASK)
+#define STM32_MDMA_CCR_PL(n) FIELD_PREP(STM32_MDMA_CCR_PL_MASK, (n))
#define STM32_MDMA_CCR_TCIE BIT(5)
#define STM32_MDMA_CCR_BTIE BIT(4)
#define STM32_MDMA_CCR_BRTIE BIT(3)
@@ -99,48 +92,33 @@
#define STM32_MDMA_CTCR_BWM BIT(31)
#define STM32_MDMA_CTCR_SWRM BIT(30)
#define STM32_MDMA_CTCR_TRGM_MSK GENMASK(29, 28)
-#define STM32_MDMA_CTCR_TRGM(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_TRGM_MSK)
-#define STM32_MDMA_CTCR_TRGM_GET(n) STM32_MDMA_GET((n), \
- STM32_MDMA_CTCR_TRGM_MSK)
+#define STM32_MDMA_CTCR_TRGM(n) FIELD_PREP(STM32_MDMA_CTCR_TRGM_MSK, (n))
+#define STM32_MDMA_CTCR_TRGM_GET(n) FIELD_GET(STM32_MDMA_CTCR_TRGM_MSK, (n))
#define STM32_MDMA_CTCR_PAM_MASK GENMASK(27, 26)
-#define STM32_MDMA_CTCR_PAM(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTCR_PAM_MASK)
+#define STM32_MDMA_CTCR_PAM(n) FIELD_PREP(STM32_MDMA_CTCR_PAM_MASK, (n))
#define STM32_MDMA_CTCR_PKE BIT(25)
#define STM32_MDMA_CTCR_TLEN_MSK GENMASK(24, 18)
-#define STM32_MDMA_CTCR_TLEN(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_TLEN_MSK)
-#define STM32_MDMA_CTCR_TLEN_GET(n) STM32_MDMA_GET((n), \
- STM32_MDMA_CTCR_TLEN_MSK)
+#define STM32_MDMA_CTCR_TLEN(n) FIELD_PREP(STM32_MDMA_CTCR_TLEN_MSK, (n))
+#define STM32_MDMA_CTCR_TLEN_GET(n) FIELD_GET(STM32_MDMA_CTCR_TLEN_MSK, (n))
#define STM32_MDMA_CTCR_LEN2_MSK GENMASK(25, 18)
-#define STM32_MDMA_CTCR_LEN2(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_LEN2_MSK)
-#define STM32_MDMA_CTCR_LEN2_GET(n) STM32_MDMA_GET((n), \
- STM32_MDMA_CTCR_LEN2_MSK)
+#define STM32_MDMA_CTCR_LEN2(n) FIELD_PREP(STM32_MDMA_CTCR_LEN2_MSK, (n))
+#define STM32_MDMA_CTCR_LEN2_GET(n) FIELD_GET(STM32_MDMA_CTCR_LEN2_MSK, (n))
#define STM32_MDMA_CTCR_DBURST_MASK GENMASK(17, 15)
-#define STM32_MDMA_CTCR_DBURST(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTCR_DBURST_MASK)
+#define STM32_MDMA_CTCR_DBURST(n) FIELD_PREP(STM32_MDMA_CTCR_DBURST_MASK, (n))
#define STM32_MDMA_CTCR_SBURST_MASK GENMASK(14, 12)
-#define STM32_MDMA_CTCR_SBURST(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTCR_SBURST_MASK)
+#define STM32_MDMA_CTCR_SBURST(n) FIELD_PREP(STM32_MDMA_CTCR_SBURST_MASK, (n))
#define STM32_MDMA_CTCR_DINCOS_MASK GENMASK(11, 10)
-#define STM32_MDMA_CTCR_DINCOS(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_DINCOS_MASK)
+#define STM32_MDMA_CTCR_DINCOS(n) FIELD_PREP(STM32_MDMA_CTCR_DINCOS_MASK, (n))
#define STM32_MDMA_CTCR_SINCOS_MASK GENMASK(9, 8)
-#define STM32_MDMA_CTCR_SINCOS(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_SINCOS_MASK)
+#define STM32_MDMA_CTCR_SINCOS(n) FIELD_PREP(STM32_MDMA_CTCR_SINCOS_MASK, (n))
#define STM32_MDMA_CTCR_DSIZE_MASK GENMASK(7, 6)
-#define STM32_MDMA_CTCR_DSIZE(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTCR_DSIZE_MASK)
+#define STM32_MDMA_CTCR_DSIZE(n) FIELD_PREP(STM32_MDMA_CTCR_DSIZE_MASK, (n))
#define STM32_MDMA_CTCR_SSIZE_MASK GENMASK(5, 4)
-#define STM32_MDMA_CTCR_SSIZE(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTCR_SSIZE_MASK)
+#define STM32_MDMA_CTCR_SSIZE(n) FIELD_PREP(STM32_MDMA_CTCR_SSIZE_MASK, (n))
#define STM32_MDMA_CTCR_DINC_MASK GENMASK(3, 2)
-#define STM32_MDMA_CTCR_DINC(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_DINC_MASK)
+#define STM32_MDMA_CTCR_DINC(n) FIELD_PREP(STM32_MDMA_CTCR_DINC_MASK, (n))
#define STM32_MDMA_CTCR_SINC_MASK GENMASK(1, 0)
-#define STM32_MDMA_CTCR_SINC(n) STM32_MDMA_SET((n), \
- STM32_MDMA_CTCR_SINC_MASK)
+#define STM32_MDMA_CTCR_SINC(n) FIELD_PREP(STM32_MDMA_CTCR_SINC_MASK, (n))
#define STM32_MDMA_CTCR_CFG_MASK (STM32_MDMA_CTCR_SINC_MASK \
| STM32_MDMA_CTCR_DINC_MASK \
| STM32_MDMA_CTCR_SINCOS_MASK \
@@ -151,16 +129,13 @@
/* MDMA Channel x block number of data register */
#define STM32_MDMA_CBNDTR(x) (0x54 + 0x40 * (x))
#define STM32_MDMA_CBNDTR_BRC_MK GENMASK(31, 20)
-#define STM32_MDMA_CBNDTR_BRC(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CBNDTR_BRC_MK)
-#define STM32_MDMA_CBNDTR_BRC_GET(n) STM32_MDMA_GET((n), \
- STM32_MDMA_CBNDTR_BRC_MK)
+#define STM32_MDMA_CBNDTR_BRC(n) FIELD_PREP(STM32_MDMA_CBNDTR_BRC_MK, (n))
+#define STM32_MDMA_CBNDTR_BRC_GET(n) FIELD_GET(STM32_MDMA_CBNDTR_BRC_MK, (n))
#define STM32_MDMA_CBNDTR_BRDUM BIT(19)
#define STM32_MDMA_CBNDTR_BRSUM BIT(18)
#define STM32_MDMA_CBNDTR_BNDT_MASK GENMASK(16, 0)
-#define STM32_MDMA_CBNDTR_BNDT(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CBNDTR_BNDT_MASK)
+#define STM32_MDMA_CBNDTR_BNDT(n) FIELD_PREP(STM32_MDMA_CBNDTR_BNDT_MASK, (n))
/* MDMA Channel x source address register */
#define STM32_MDMA_CSAR(x) (0x58 + 0x40 * (x))
@@ -171,11 +146,9 @@
/* MDMA Channel x block repeat address update register */
#define STM32_MDMA_CBRUR(x) (0x60 + 0x40 * (x))
#define STM32_MDMA_CBRUR_DUV_MASK GENMASK(31, 16)
-#define STM32_MDMA_CBRUR_DUV(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CBRUR_DUV_MASK)
+#define STM32_MDMA_CBRUR_DUV(n) FIELD_PREP(STM32_MDMA_CBRUR_DUV_MASK, (n))
#define STM32_MDMA_CBRUR_SUV_MASK GENMASK(15, 0)
-#define STM32_MDMA_CBRUR_SUV(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CBRUR_SUV_MASK)
+#define STM32_MDMA_CBRUR_SUV(n) FIELD_PREP(STM32_MDMA_CBRUR_SUV_MASK, (n))
/* MDMA Channel x link address register */
#define STM32_MDMA_CLAR(x) (0x64 + 0x40 * (x))
@@ -184,9 +157,8 @@
#define STM32_MDMA_CTBR(x) (0x68 + 0x40 * (x))
#define STM32_MDMA_CTBR_DBUS BIT(17)
#define STM32_MDMA_CTBR_SBUS BIT(16)
-#define STM32_MDMA_CTBR_TSEL_MASK GENMASK(7, 0)
-#define STM32_MDMA_CTBR_TSEL(n) STM32_MDMA_SET(n, \
- STM32_MDMA_CTBR_TSEL_MASK)
+#define STM32_MDMA_CTBR_TSEL_MASK GENMASK(5, 0)
+#define STM32_MDMA_CTBR_TSEL(n) FIELD_PREP(STM32_MDMA_CTBR_TSEL_MASK, (n))
/* MDMA Channel x mask address register */
#define STM32_MDMA_CMAR(x) (0x70 + 0x40 * (x))
@@ -1279,7 +1251,7 @@ static size_t stm32_mdma_desc_residue(struct stm32_mdma_chan *chan,
u32 curr_hwdesc)
{
struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
- struct stm32_mdma_hwdesc *hwdesc = desc->node[0].hwdesc;
+ struct stm32_mdma_hwdesc *hwdesc;
u32 cbndtr, residue, modulo, burst_size;
int i;
diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index bd496ef..1d4081a 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -8,5 +8,6 @@
k3-psil-am654.o \
k3-psil-j721e.o \
k3-psil-j7200.o \
- k3-psil-am64.o
+ k3-psil-am64.o \
+ k3-psil-j721s2.o
obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 35d81bd..08e47f4 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -1681,8 +1681,7 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data)
dev_dbg(ecc->dev, "EMR%d 0x%08x\n", j, val);
emr = val;
- for (i = find_next_bit(&emr, 32, 0); i < 32;
- i = find_next_bit(&emr, 32, i + 1)) {
+ for_each_set_bit(i, &emr, 32) {
int k = (j << 5) + i;
/* Clear the corresponding EMR bits */
diff --git a/drivers/dma/ti/k3-psil-j721s2.c b/drivers/dma/ti/k3-psil-j721s2.c
new file mode 100644
index 0000000..4c4172a
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-j721s2.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ }, \
+ }
+
+#define PSIL_PDMA_XY_PKT(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ .pkt_mode = 1, \
+ }, \
+ }
+
+#define PSIL_PDMA_MCASP(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_PDMA_XY, \
+ .pdma_acc32 = 1, \
+ .pdma_burst = 1, \
+ }, \
+ }
+
+#define PSIL_ETHERNET(x) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_NATIVE, \
+ .pkt_mode = 1, \
+ .needs_epib = 1, \
+ .psd_size = 16, \
+ }, \
+ }
+
+#define PSIL_SA2UL(x, tx) \
+ { \
+ .thread_id = x, \
+ .ep_config = { \
+ .ep_type = PSIL_EP_NATIVE, \
+ .pkt_mode = 1, \
+ .needs_epib = 1, \
+ .psd_size = 64, \
+ .notdpkt = tx, \
+ }, \
+ }
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep j721s2_src_ep_map[] = {
+ /* PDMA_MCASP - McASP0-4 */
+ PSIL_PDMA_MCASP(0x4400),
+ PSIL_PDMA_MCASP(0x4401),
+ PSIL_PDMA_MCASP(0x4402),
+ PSIL_PDMA_MCASP(0x4403),
+ PSIL_PDMA_MCASP(0x4404),
+ /* PDMA_SPI_G0 - SPI0-3 */
+ PSIL_PDMA_XY_PKT(0x4600),
+ PSIL_PDMA_XY_PKT(0x4601),
+ PSIL_PDMA_XY_PKT(0x4602),
+ PSIL_PDMA_XY_PKT(0x4603),
+ PSIL_PDMA_XY_PKT(0x4604),
+ PSIL_PDMA_XY_PKT(0x4605),
+ PSIL_PDMA_XY_PKT(0x4606),
+ PSIL_PDMA_XY_PKT(0x4607),
+ PSIL_PDMA_XY_PKT(0x4608),
+ PSIL_PDMA_XY_PKT(0x4609),
+ PSIL_PDMA_XY_PKT(0x460a),
+ PSIL_PDMA_XY_PKT(0x460b),
+ PSIL_PDMA_XY_PKT(0x460c),
+ PSIL_PDMA_XY_PKT(0x460d),
+ PSIL_PDMA_XY_PKT(0x460e),
+ PSIL_PDMA_XY_PKT(0x460f),
+ /* PDMA_SPI_G1 - SPI4-7 */
+ PSIL_PDMA_XY_PKT(0x4610),
+ PSIL_PDMA_XY_PKT(0x4611),
+ PSIL_PDMA_XY_PKT(0x4612),
+ PSIL_PDMA_XY_PKT(0x4613),
+ PSIL_PDMA_XY_PKT(0x4614),
+ PSIL_PDMA_XY_PKT(0x4615),
+ PSIL_PDMA_XY_PKT(0x4616),
+ PSIL_PDMA_XY_PKT(0x4617),
+ PSIL_PDMA_XY_PKT(0x4618),
+ PSIL_PDMA_XY_PKT(0x4619),
+ PSIL_PDMA_XY_PKT(0x461a),
+ PSIL_PDMA_XY_PKT(0x461b),
+ PSIL_PDMA_XY_PKT(0x461c),
+ PSIL_PDMA_XY_PKT(0x461d),
+ PSIL_PDMA_XY_PKT(0x461e),
+ PSIL_PDMA_XY_PKT(0x461f),
+ /* PDMA_USART_G0 - UART0-1 */
+ PSIL_PDMA_XY_PKT(0x4700),
+ PSIL_PDMA_XY_PKT(0x4701),
+ /* PDMA_USART_G1 - UART2-3 */
+ PSIL_PDMA_XY_PKT(0x4702),
+ PSIL_PDMA_XY_PKT(0x4703),
+ /* PDMA_USART_G2 - UART4-9 */
+ PSIL_PDMA_XY_PKT(0x4704),
+ PSIL_PDMA_XY_PKT(0x4705),
+ PSIL_PDMA_XY_PKT(0x4706),
+ PSIL_PDMA_XY_PKT(0x4707),
+ PSIL_PDMA_XY_PKT(0x4708),
+ PSIL_PDMA_XY_PKT(0x4709),
+ /* CPSW0 */
+ PSIL_ETHERNET(0x7000),
+ /* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */
+ PSIL_PDMA_XY_PKT(0x7100),
+ PSIL_PDMA_XY_PKT(0x7101),
+ PSIL_PDMA_XY_PKT(0x7102),
+ PSIL_PDMA_XY_PKT(0x7103),
+ /* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */
+ PSIL_PDMA_XY_PKT(0x7200),
+ PSIL_PDMA_XY_PKT(0x7201),
+ PSIL_PDMA_XY_PKT(0x7202),
+ PSIL_PDMA_XY_PKT(0x7203),
+ PSIL_PDMA_XY_PKT(0x7204),
+ PSIL_PDMA_XY_PKT(0x7205),
+ PSIL_PDMA_XY_PKT(0x7206),
+ PSIL_PDMA_XY_PKT(0x7207),
+ /* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */
+ PSIL_PDMA_XY_PKT(0x7300),
+ /* MCU_PDMA_ADC - ADC0-1 */
+ PSIL_PDMA_XY_TR(0x7400),
+ PSIL_PDMA_XY_TR(0x7401),
+ PSIL_PDMA_XY_TR(0x7402),
+ PSIL_PDMA_XY_TR(0x7403),
+ /* SA2UL */
+ PSIL_SA2UL(0x7500, 0),
+ PSIL_SA2UL(0x7501, 0),
+ PSIL_SA2UL(0x7502, 0),
+ PSIL_SA2UL(0x7503, 0),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep j721s2_dst_ep_map[] = {
+ /* CPSW0 */
+ PSIL_ETHERNET(0xf000),
+ PSIL_ETHERNET(0xf001),
+ PSIL_ETHERNET(0xf002),
+ PSIL_ETHERNET(0xf003),
+ PSIL_ETHERNET(0xf004),
+ PSIL_ETHERNET(0xf005),
+ PSIL_ETHERNET(0xf006),
+ PSIL_ETHERNET(0xf007),
+ /* SA2UL */
+ PSIL_SA2UL(0xf500, 1),
+ PSIL_SA2UL(0xf501, 1),
+};
+
+struct psil_ep_map j721s2_ep_map = {
+ .name = "j721s2",
+ .src = j721s2_src_ep_map,
+ .src_count = ARRAY_SIZE(j721s2_src_ep_map),
+ .dst = j721s2_dst_ep_map,
+ .dst_count = ARRAY_SIZE(j721s2_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index b74e192..e51e179 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -41,5 +41,6 @@ extern struct psil_ep_map am654_ep_map;
extern struct psil_ep_map j721e_ep_map;
extern struct psil_ep_map j7200_ep_map;
extern struct psil_ep_map am64_ep_map;
+extern struct psil_ep_map j721s2_ep_map;
#endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index 13ce736..8867b4b 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -21,6 +21,7 @@ static const struct soc_device_attribute k3_soc_devices[] = {
{ .family = "J721E", .data = &j721e_ep_map },
{ .family = "J7200", .data = &j7200_ep_map },
{ .family = "AM64X", .data = &am64_ep_map },
+ { .family = "J721S2", .data = &j721s2_ep_map },
{ /* sentinel */ }
};
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index c542ba5..d2d4cbe 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4374,6 +4374,7 @@ static const struct soc_device_attribute k3_soc_devices[] = {
{ .family = "J721E", .data = &j721e_soc_data },
{ .family = "J7200", .data = &j7200_soc_data },
{ .family = "AM64X", .data = &am64_soc_data },
+ { .family = "J721S2", .data = &j721e_soc_data},
{ /* sentinel */ }
};
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index d6b8a20..290836b 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -131,8 +131,9 @@ uniphier_xdmac_next_desc(struct uniphier_xdmac_chan *xc)
static void uniphier_xdmac_chan_start(struct uniphier_xdmac_chan *xc,
struct uniphier_xdmac_desc *xd)
{
- u32 src_mode, src_addr, src_width;
- u32 dst_mode, dst_addr, dst_width;
+ u32 src_mode, src_width;
+ u32 dst_mode, dst_width;
+ dma_addr_t src_addr, dst_addr;
u32 val, its, tnum;
enum dma_slave_buswidth buswidth;
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 4677ce0..cd62bbb 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2128,6 +2128,126 @@ xilinx_cdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst,
}
/**
+ * xilinx_cdma_prep_memcpy_sg - prepare descriptors for a memcpy_sg transaction
+ * @dchan: DMA channel
+ * @dst_sg: Destination scatter list
+ * @dst_sg_len: Number of entries in destination scatter list
+ * @src_sg: Source scatter list
+ * @src_sg_len: Number of entries in source scatter list
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *xilinx_cdma_prep_memcpy_sg(
+ struct dma_chan *dchan, struct scatterlist *dst_sg,
+ unsigned int dst_sg_len, struct scatterlist *src_sg,
+ unsigned int src_sg_len, unsigned long flags)
+{
+ struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+ struct xilinx_dma_tx_descriptor *desc;
+ struct xilinx_cdma_tx_segment *segment, *prev = NULL;
+ struct xilinx_cdma_desc_hw *hw;
+ size_t len, dst_avail, src_avail;
+ dma_addr_t dma_dst, dma_src;
+
+ if (unlikely(dst_sg_len == 0 || src_sg_len == 0))
+ return NULL;
+
+ if (unlikely(!dst_sg || !src_sg))
+ return NULL;
+
+ desc = xilinx_dma_alloc_tx_descriptor(chan);
+ if (!desc)
+ return NULL;
+
+ dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+ desc->async_tx.tx_submit = xilinx_dma_tx_submit;
+
+ dst_avail = sg_dma_len(dst_sg);
+ src_avail = sg_dma_len(src_sg);
+ /*
+ * loop until there is either no more source or no more destination
+ * scatterlist entry
+ */
+ while (true) {
+ len = min_t(size_t, src_avail, dst_avail);
+ len = min_t(size_t, len, chan->xdev->max_buffer_len);
+ if (len == 0)
+ goto fetch;
+
+ /* Allocate the link descriptor from DMA pool */
+ segment = xilinx_cdma_alloc_tx_segment(chan);
+ if (!segment)
+ goto error;
+
+ dma_dst = sg_dma_address(dst_sg) + sg_dma_len(dst_sg) -
+ dst_avail;
+ dma_src = sg_dma_address(src_sg) + sg_dma_len(src_sg) -
+ src_avail;
+ hw = &segment->hw;
+ hw->control = len;
+ hw->src_addr = dma_src;
+ hw->dest_addr = dma_dst;
+ if (chan->ext_addr) {
+ hw->src_addr_msb = upper_32_bits(dma_src);
+ hw->dest_addr_msb = upper_32_bits(dma_dst);
+ }
+
+ if (prev) {
+ prev->hw.next_desc = segment->phys;
+ if (chan->ext_addr)
+ prev->hw.next_desc_msb =
+ upper_32_bits(segment->phys);
+ }
+
+ prev = segment;
+ dst_avail -= len;
+ src_avail -= len;
+ list_add_tail(&segment->node, &desc->segments);
+
+fetch:
+ /* Fetch the next dst scatterlist entry */
+ if (dst_avail == 0) {
+ if (dst_sg_len == 0)
+ break;
+ dst_sg = sg_next(dst_sg);
+ if (dst_sg == NULL)
+ break;
+ dst_sg_len--;
+ dst_avail = sg_dma_len(dst_sg);
+ }
+ /* Fetch the next src scatterlist entry */
+ if (src_avail == 0) {
+ if (src_sg_len == 0)
+ break;
+ src_sg = sg_next(src_sg);
+ if (src_sg == NULL)
+ break;
+ src_sg_len--;
+ src_avail = sg_dma_len(src_sg);
+ }
+ }
+
+ if (list_empty(&desc->segments)) {
+ dev_err(chan->xdev->dev,
+ "%s: Zero-size SG transfer requested\n", __func__);
+ goto error;
+ }
+
+ /* Link the last hardware descriptor with the first. */
+ segment = list_first_entry(&desc->segments,
+ struct xilinx_cdma_tx_segment, node);
+ desc->async_tx.phys = segment->phys;
+ prev->hw.next_desc = segment->phys;
+
+ return &desc->async_tx;
+
+error:
+ xilinx_dma_free_tx_descriptor(chan, desc);
+ return NULL;
+}
+
+/**
* xilinx_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
* @dchan: DMA channel
* @sgl: scatterlist to transfer to/from
@@ -2860,7 +2980,9 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
}
/* Request the interrupt */
- chan->irq = irq_of_parse_and_map(node, chan->tdest);
+ chan->irq = of_irq_get(node, chan->tdest);
+ if (chan->irq < 0)
+ return dev_err_probe(xdev->dev, chan->irq, "failed to get irq\n");
err = request_irq(chan->irq, xdev->dma_config->irq_handler,
IRQF_SHARED, "xilinx-dma-controller", chan);
if (err) {
@@ -2934,8 +3056,11 @@ static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0)
dev_warn(xdev->dev, "missing dma-channels property\n");
- for (i = 0; i < nr_channels; i++)
- xilinx_dma_chan_probe(xdev, node);
+ for (i = 0; i < nr_channels; i++) {
+ ret = xilinx_dma_chan_probe(xdev, node);
+ if (ret)
+ return ret;
+ }
return 0;
}
@@ -3115,7 +3240,9 @@ static int xilinx_dma_probe(struct platform_device *pdev)
DMA_RESIDUE_GRANULARITY_SEGMENT;
} else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
dma_cap_set(DMA_MEMCPY, xdev->common.cap_mask);
+ dma_cap_set(DMA_MEMCPY_SG, xdev->common.cap_mask);
xdev->common.device_prep_dma_memcpy = xilinx_cdma_prep_memcpy;
+ xdev->common.device_prep_dma_memcpy_sg = xilinx_cdma_prep_memcpy_sg;
/* Residue calculation is supported by only AXI DMA and CDMA */
xdev->common.residue_granularity =
DMA_RESIDUE_GRANULARITY_SEGMENT;
diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c
index 87039c5..eefcc41 100644
--- a/drivers/firmware/arm_scmi/virtio.c
+++ b/drivers/firmware/arm_scmi/virtio.c
@@ -452,7 +452,7 @@ static void scmi_vio_remove(struct virtio_device *vdev)
* outstanding message on any vqueue to be ignored by complete_cb: now
* we can just stop processing buffers and destroy the vqueues.
*/
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
/* Ensure scmi_vdev is visible as NULL */
smp_store_mb(scmi_vdev, NULL);
diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index e87e7f1..da93864 100644
--- a/drivers/firmware/efi/libstub/efi-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -40,6 +40,8 @@
#ifdef CONFIG_ARM64
# define EFI_RT_VIRTUAL_LIMIT DEFAULT_MAP_WINDOW_64
+#elif defined(CONFIG_RISCV)
+# define EFI_RT_VIRTUAL_LIMIT TASK_SIZE_MIN
#else
# define EFI_RT_VIRTUAL_LIMIT TASK_SIZE
#endif
diff --git a/drivers/gpio/gpio-idt3243x.c b/drivers/gpio/gpio-idt3243x.c
index 50003ad..52b8b72 100644
--- a/drivers/gpio/gpio-idt3243x.c
+++ b/drivers/gpio/gpio-idt3243x.c
@@ -132,7 +132,7 @@ static int idt_gpio_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct gpio_irq_chip *girq;
struct idt_gpio_ctrl *ctrl;
- unsigned int parent_irq;
+ int parent_irq;
int ngpios;
int ret;
@@ -164,8 +164,8 @@ static int idt_gpio_probe(struct platform_device *pdev)
return PTR_ERR(ctrl->pic);
parent_irq = platform_get_irq(pdev, 0);
- if (!parent_irq)
- return -EINVAL;
+ if (parent_irq < 0)
+ return parent_irq;
girq = &ctrl->gc.irq;
girq->chip = &idt_gpio_irqchip;
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 70d6ae2..a964e25 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -47,7 +47,7 @@ struct mpc8xxx_gpio_chip {
unsigned offset, int value);
struct irq_domain *irq;
- unsigned int irqn;
+ int irqn;
};
/*
@@ -388,8 +388,8 @@ static int mpc8xxx_probe(struct platform_device *pdev)
}
mpc8xxx_gc->irqn = platform_get_irq(pdev, 0);
- if (!mpc8xxx_gc->irqn)
- return 0;
+ if (mpc8xxx_gc->irqn < 0)
+ return mpc8xxx_gc->irqn;
mpc8xxx_gc->irq = irq_domain_create_linear(fwnode,
MPC8XXX_GPIO_PINS,
diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c
index 9f4941b..fcc5e8c 100644
--- a/drivers/gpio/gpio-virtio.c
+++ b/drivers/gpio/gpio-virtio.c
@@ -450,7 +450,7 @@ static void virtio_gpio_request_vq(struct virtqueue *vq)
static void virtio_gpio_free_vqs(struct virtio_device *vdev)
{
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index cf7fad8..ed077de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2354,7 +2354,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
}
if (amdgpu_sriov_vf(adev))
- amdgpu_virt_exchange_data(adev);
+ amdgpu_virt_init_data_exchange(adev);
r = amdgpu_ib_pool_init(adev);
if (r) {
@@ -4450,33 +4450,24 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
if (amdgpu_gpu_recovery == -1) {
switch (adev->asic_type) {
- case CHIP_BONAIRE:
- case CHIP_HAWAII:
- case CHIP_TOPAZ:
- case CHIP_TONGA:
- case CHIP_FIJI:
- case CHIP_POLARIS10:
- case CHIP_POLARIS11:
- case CHIP_POLARIS12:
- case CHIP_VEGAM:
- case CHIP_VEGA20:
- case CHIP_VEGA10:
- case CHIP_VEGA12:
- case CHIP_RAVEN:
- case CHIP_ARCTURUS:
- case CHIP_RENOIR:
- case CHIP_NAVI10:
- case CHIP_NAVI14:
- case CHIP_NAVI12:
- case CHIP_SIENNA_CICHLID:
- case CHIP_NAVY_FLOUNDER:
- case CHIP_DIMGREY_CAVEFISH:
- case CHIP_BEIGE_GOBY:
- case CHIP_VANGOGH:
- case CHIP_ALDEBARAN:
- break;
- default:
+#ifdef CONFIG_DRM_AMDGPU_SI
+ case CHIP_VERDE:
+ case CHIP_TAHITI:
+ case CHIP_PITCAIRN:
+ case CHIP_OLAND:
+ case CHIP_HAINAN:
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+ case CHIP_KAVERI:
+ case CHIP_KABINI:
+ case CHIP_MULLINS:
+#endif
+ case CHIP_CARRIZO:
+ case CHIP_STONEY:
+ case CHIP_CYAN_SKILLFISH:
goto disabled;
+ default:
+ break;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index be45650..81bfee9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -243,6 +243,30 @@ static inline bool amdgpu_discovery_verify_binary_signature(uint8_t *binary)
return (le32_to_cpu(bhdr->binary_signature) == BINARY_SIGNATURE);
}
+static void amdgpu_discovery_harvest_config_quirk(struct amdgpu_device *adev)
+{
+ /*
+ * So far, apply this quirk only on those Navy Flounder boards which
+ * have a bad harvest table of VCN config.
+ */
+ if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) &&
+ (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2))) {
+ switch (adev->pdev->revision) {
+ case 0xC1:
+ case 0xC2:
+ case 0xC3:
+ case 0xC5:
+ case 0xC7:
+ case 0xCF:
+ case 0xDF:
+ adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1;
+ break;
+ default:
+ break;
+ }
+ }
+}
+
static int amdgpu_discovery_init(struct amdgpu_device *adev)
{
struct table_info *info;
@@ -548,11 +572,9 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
break;
}
}
- /* some IP discovery tables on Navy Flounder don't have this set correctly */
- if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) &&
- (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2)) &&
- (adev->pdev->revision != 0xFF))
- adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1;
+
+ amdgpu_discovery_harvest_config_quirk(adev);
+
if (vcn_harvest_count == adev->vcn.num_vcn_inst) {
adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index c610e27..b21bcdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1930,11 +1930,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
return -ENODEV;
}
- if (flags == 0) {
- DRM_INFO("Unsupported asic. Remove me when IP discovery init is in place.\n");
- return -ENODEV;
- }
-
if (amdgpu_virtual_display ||
amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
supports_atomic = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 894444a..07bc0f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -625,20 +625,20 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
adev->virt.fw_reserve.p_vf2pf = NULL;
adev->virt.vf2pf_update_interval_ms = 0;
- if (adev->bios != NULL) {
- adev->virt.vf2pf_update_interval_ms = 2000;
+ if (adev->mman.fw_vram_usage_va != NULL) {
+ /* go through this logic in ip_init and reset to init workqueue*/
+ amdgpu_virt_exchange_data(adev);
+ INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
+ schedule_delayed_work(&(adev->virt.vf2pf_work), msecs_to_jiffies(adev->virt.vf2pf_update_interval_ms));
+ } else if (adev->bios != NULL) {
+ /* got through this logic in early init stage to get necessary flags, e.g. rlcg_acc related*/
adev->virt.fw_reserve.p_pf2vf =
(struct amd_sriov_msg_pf2vf_info_header *)
(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
amdgpu_virt_read_pf2vf_data(adev);
}
-
- if (adev->virt.vf2pf_update_interval_ms != 0) {
- INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
- schedule_delayed_work(&(adev->virt.vf2pf_work), msecs_to_jiffies(adev->virt.vf2pf_update_interval_ms));
- }
}
@@ -674,12 +674,6 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
if (adev->virt.ras_init_done)
amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size);
}
- } else if (adev->bios != NULL) {
- adev->virt.fw_reserve.p_pf2vf =
- (struct amd_sriov_msg_pf2vf_info_header *)
- (adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
-
- amdgpu_virt_read_pf2vf_data(adev);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 54f28c0..f10ce74 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1428,6 +1428,10 @@ static int cik_asic_reset(struct amdgpu_device *adev)
{
int r;
+ /* APUs don't have full asic reset */
+ if (adev->flags & AMD_IS_APU)
+ return 0;
+
if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
dev_info(adev->dev, "BACO reset\n");
r = amdgpu_dpm_baco_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index fe9a7cc..6645ebb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -956,6 +956,10 @@ static int vi_asic_reset(struct amdgpu_device *adev)
{
int r;
+ /* APUs don't have full asic reset */
+ if (adev->flags & AMD_IS_APU)
+ return 0;
+
if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
dev_info(adev->dev, "BACO reset\n");
r = amdgpu_dpm_baco_reset(adev);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 9f35f2e..cac80ba 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -38,7 +38,6 @@
#include "clk/clk_11_0_0_offset.h"
#include "clk/clk_11_0_0_sh_mask.h"
-#include "irq/dcn20/irq_service_dcn20.h"
#undef FN
#define FN(reg_name, field_name) \
@@ -223,8 +222,6 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
bool force_reset = false;
bool p_state_change_support;
int total_plane_count;
- int irq_src;
- uint32_t hpd_state;
if (dc->work_arounds.skip_clock_update)
return;
@@ -242,13 +239,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
if (dc->res_pool->pp_smu)
pp_smu = &dc->res_pool->pp_smu->nv_funcs;
- for (irq_src = DC_IRQ_SOURCE_HPD1; irq_src <= DC_IRQ_SOURCE_HPD6; irq_src++) {
- hpd_state = dc_get_hpd_state_dcn20(dc->res_pool->irqs, irq_src);
- if (hpd_state)
- break;
- }
-
- if (display_count == 0 && !hpd_state)
+ if (display_count == 0)
enter_display_off = true;
if (enter_display_off == safe_to_lower) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index fbda423..f4dee0e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -42,7 +42,6 @@
#include "clk/clk_10_0_2_sh_mask.h"
#include "renoir_ip_offset.h"
-#include "irq/dcn21/irq_service_dcn21.h"
/* Constants */
@@ -129,11 +128,9 @@ static void rn_update_clocks(struct clk_mgr *clk_mgr_base,
struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
struct dc *dc = clk_mgr_base->ctx->dc;
int display_count;
- int irq_src;
bool update_dppclk = false;
bool update_dispclk = false;
bool dpp_clock_lowered = false;
- uint32_t hpd_state;
struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
@@ -150,14 +147,8 @@ static void rn_update_clocks(struct clk_mgr *clk_mgr_base,
display_count = rn_get_active_display_cnt_wa(dc, context);
- for (irq_src = DC_IRQ_SOURCE_HPD1; irq_src <= DC_IRQ_SOURCE_HPD5; irq_src++) {
- hpd_state = dc_get_hpd_state_dcn21(dc->res_pool->irqs, irq_src);
- if (hpd_state)
- break;
- }
-
/* if we can go lower, go lower */
- if (display_count == 0 && !hpd_state) {
+ if (display_count == 0) {
rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER);
/* update power state */
clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER;
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 9ccafe0..c4b067d 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -132,31 +132,6 @@ enum dc_irq_source to_dal_irq_source_dcn20(
}
}
-uint32_t dc_get_hpd_state_dcn20(struct irq_service *irq_service, enum dc_irq_source source)
-{
- const struct irq_source_info *info;
- uint32_t addr;
- uint32_t value;
- uint32_t current_status;
-
- info = find_irq_source_info(irq_service, source);
- if (!info)
- return 0;
-
- addr = info->status_reg;
- if (!addr)
- return 0;
-
- value = dm_read_reg(irq_service->ctx, addr);
- current_status =
- get_reg_field_value(
- value,
- HPD0_DC_HPD_INT_STATUS,
- DC_HPD_SENSE);
-
- return current_status;
-}
-
static bool hpd_ack(
struct irq_service *irq_service,
const struct irq_source_info *info)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
index 4d69ab2..aee4b37 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
@@ -31,6 +31,4 @@
struct irq_service *dal_irq_service_dcn20_create(
struct irq_service_init_data *init_data);
-uint32_t dc_get_hpd_state_dcn20(struct irq_service *irq_service, enum dc_irq_source source);
-
#endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index 23529453..0f15bca 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -134,31 +134,6 @@ static enum dc_irq_source to_dal_irq_source_dcn21(struct irq_service *irq_servic
return DC_IRQ_SOURCE_INVALID;
}
-uint32_t dc_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source)
-{
- const struct irq_source_info *info;
- uint32_t addr;
- uint32_t value;
- uint32_t current_status;
-
- info = find_irq_source_info(irq_service, source);
- if (!info)
- return 0;
-
- addr = info->status_reg;
- if (!addr)
- return 0;
-
- value = dm_read_reg(irq_service->ctx, addr);
- current_status =
- get_reg_field_value(
- value,
- HPD0_DC_HPD_INT_STATUS,
- DC_HPD_SENSE);
-
- return current_status;
-}
-
static bool hpd_ack(
struct irq_service *irq_service,
const struct irq_source_info *info)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
index 616470e..da2bd0e 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
@@ -31,6 +31,4 @@
struct irq_service *dal_irq_service_dcn21_create(
struct irq_service_init_data *init_data);
-uint32_t dc_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source);
-
#endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 4db1133..a2a4fbe 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -79,7 +79,7 @@ void dal_irq_service_destroy(struct irq_service **irq_service)
*irq_service = NULL;
}
-const struct irq_source_info *find_irq_source_info(
+static const struct irq_source_info *find_irq_source_info(
struct irq_service *irq_service,
enum dc_irq_source source)
{
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
index e60b824..dbfcb09 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
@@ -69,10 +69,6 @@ struct irq_service {
const struct irq_service_funcs *funcs;
};
-const struct irq_source_info *find_irq_source_info(
- struct irq_service *irq_service,
- enum dc_irq_source source);
-
void dal_irq_service_construct(
struct irq_service *irq_service,
struct irq_service_init_data *init_data);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 9c9d574..cab5052 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1298,6 +1298,28 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder,
intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
DKL_TX_DP20BITMODE, 0);
+
+ if (IS_ALDERLAKE_P(dev_priv)) {
+ u32 val;
+
+ if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+ if (ln == 0) {
+ val = DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(0);
+ val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(2);
+ } else {
+ val = DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(3);
+ val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(3);
+ }
+ } else {
+ val = DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(0);
+ val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(0);
+ }
+
+ intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
+ DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK |
+ DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK,
+ val);
+ }
}
}
diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
index 1e689d5..e2dfb93 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c
@@ -477,14 +477,14 @@ static const struct intel_ddi_buf_trans icl_combo_phy_trans_hdmi = {
static const union intel_ddi_buf_trans_entry _ehl_combo_phy_trans_dp[] = {
/* NT mV Trans mV db */
{ .icl = { 0xA, 0x33, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */
- { .icl = { 0xA, 0x47, 0x36, 0x00, 0x09 } }, /* 350 500 3.1 */
- { .icl = { 0xC, 0x64, 0x34, 0x00, 0x0B } }, /* 350 700 6.0 */
- { .icl = { 0x6, 0x7F, 0x30, 0x00, 0x0F } }, /* 350 900 8.2 */
+ { .icl = { 0xA, 0x47, 0x38, 0x00, 0x07 } }, /* 350 500 3.1 */
+ { .icl = { 0xC, 0x64, 0x33, 0x00, 0x0C } }, /* 350 700 6.0 */
+ { .icl = { 0x6, 0x7F, 0x2F, 0x00, 0x10 } }, /* 350 900 8.2 */
{ .icl = { 0xA, 0x46, 0x3F, 0x00, 0x00 } }, /* 500 500 0.0 */
- { .icl = { 0xC, 0x64, 0x38, 0x00, 0x07 } }, /* 500 700 2.9 */
+ { .icl = { 0xC, 0x64, 0x37, 0x00, 0x08 } }, /* 500 700 2.9 */
{ .icl = { 0x6, 0x7F, 0x32, 0x00, 0x0D } }, /* 500 900 5.1 */
{ .icl = { 0xC, 0x61, 0x3F, 0x00, 0x00 } }, /* 650 700 0.6 */
- { .icl = { 0x6, 0x7F, 0x38, 0x00, 0x07 } }, /* 600 900 3.5 */
+ { .icl = { 0x6, 0x7F, 0x37, 0x00, 0x08 } }, /* 600 900 3.5 */
{ .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */
};
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4c28dad..971d601 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11166,8 +11166,12 @@ enum skl_power_gate {
_DKL_PHY2_BASE) + \
_DKL_TX_DPCNTL1)
-#define _DKL_TX_DPCNTL2 0x2C8
-#define DKL_TX_DP20BITMODE (1 << 2)
+#define _DKL_TX_DPCNTL2 0x2C8
+#define DKL_TX_DP20BITMODE REG_BIT(2)
+#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK REG_GENMASK(4, 3)
+#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK, (val))
+#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK REG_GENMASK(6, 5)
+#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, (val))
#define DKL_TX_DPCNTL2(tc_port) _MMIO(_PORT(tc_port, \
_DKL_PHY1_BASE, \
_DKL_PHY2_BASE) + \
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index e248855..11ad210 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -666,18 +666,18 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
if (unlikely(!fpriv)) {
r = -ENOMEM;
- goto out_suspend;
+ goto err_suspend;
}
if (rdev->accel_working) {
vm = &fpriv->vm;
r = radeon_vm_init(rdev, vm);
if (r)
- goto out_fpriv;
+ goto err_fpriv;
r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
if (r)
- goto out_vm_fini;
+ goto err_vm_fini;
/* map the ib pool buffer read only into
* virtual address space */
@@ -685,7 +685,7 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
rdev->ring_tmp_bo.bo);
if (!vm->ib_bo_va) {
r = -ENOMEM;
- goto out_vm_fini;
+ goto err_vm_fini;
}
r = radeon_vm_bo_set_addr(rdev, vm->ib_bo_va,
@@ -693,19 +693,21 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
RADEON_VM_PAGE_READABLE |
RADEON_VM_PAGE_SNOOPED);
if (r)
- goto out_vm_fini;
+ goto err_vm_fini;
}
file_priv->driver_priv = fpriv;
}
- if (!r)
- goto out_suspend;
+ pm_runtime_mark_last_busy(dev->dev);
+ pm_runtime_put_autosuspend(dev->dev);
+ return 0;
-out_vm_fini:
+err_vm_fini:
radeon_vm_fini(rdev, vm);
-out_fpriv:
+err_fpriv:
kfree(fpriv);
-out_suspend:
+
+err_suspend:
pm_runtime_mark_last_busy(dev->dev);
pm_runtime_put_autosuspend(dev->dev);
return r;
diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c
index 21f4109..3313b92 100644
--- a/drivers/gpu/drm/virtio/virtgpu_kms.c
+++ b/drivers/gpu/drm/virtio/virtgpu_kms.c
@@ -279,7 +279,7 @@ void virtio_gpu_deinit(struct drm_device *dev)
flush_work(&vgdev->ctrlq.dequeue_work);
flush_work(&vgdev->cursorq.dequeue_work);
flush_work(&vgdev->config_changed_work);
- vgdev->vdev->config->reset(vgdev->vdev);
+ virtio_reset_device(vgdev->vdev);
vgdev->vdev->config->del_vqs(vgdev->vdev);
}
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 26cee45..8597503 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -400,6 +400,7 @@
#define USB_DEVICE_ID_HP_X2 0x074d
#define USB_DEVICE_ID_HP_X2_10_COVER 0x0755
#define I2C_DEVICE_ID_HP_ENVY_X360_15 0x2d05
+#define I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100 0x29CF
#define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817
#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544
#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 1ce75e8..112901d 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -330,6 +330,8 @@ static const struct hid_device_id hid_battery_quirks[] = {
HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100),
+ HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15),
HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN),
diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c
index 72957a9..efa6140 100644
--- a/drivers/hid/hid-vivaldi.c
+++ b/drivers/hid/hid-vivaldi.c
@@ -6,16 +6,17 @@
* Author: Sean O'Brien <seobrien@chromium.org>
*/
+#include <linux/device.h>
#include <linux/hid.h>
+#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/sysfs.h>
#define MIN_FN_ROW_KEY 1
#define MAX_FN_ROW_KEY 24
#define HID_VD_FN_ROW_PHYSMAP 0x00000001
#define HID_USAGE_FN_ROW_PHYSMAP (HID_UP_GOOGLEVENDOR | HID_VD_FN_ROW_PHYSMAP)
-static struct hid_driver hid_vivaldi;
-
struct vivaldi_data {
u32 function_row_physmap[MAX_FN_ROW_KEY - MIN_FN_ROW_KEY + 1];
int max_function_row_key;
@@ -40,7 +41,7 @@ static ssize_t function_row_physmap_show(struct device *dev,
return size;
}
-DEVICE_ATTR_RO(function_row_physmap);
+static DEVICE_ATTR_RO(function_row_physmap);
static struct attribute *sysfs_attrs[] = {
&dev_attr_function_row_physmap.attr,
NULL
@@ -74,10 +75,11 @@ static void vivaldi_feature_mapping(struct hid_device *hdev,
struct hid_usage *usage)
{
struct vivaldi_data *drvdata = hid_get_drvdata(hdev);
+ struct hid_report *report = field->report;
int fn_key;
int ret;
u32 report_len;
- u8 *buf;
+ u8 *report_data, *buf;
if (field->logical != HID_USAGE_FN_ROW_PHYSMAP ||
(usage->hid & HID_USAGE_PAGE) != HID_UP_ORDINAL)
@@ -89,12 +91,24 @@ static void vivaldi_feature_mapping(struct hid_device *hdev,
if (fn_key > drvdata->max_function_row_key)
drvdata->max_function_row_key = fn_key;
- buf = hid_alloc_report_buf(field->report, GFP_KERNEL);
- if (!buf)
+ report_data = buf = hid_alloc_report_buf(report, GFP_KERNEL);
+ if (!report_data)
return;
- report_len = hid_report_len(field->report);
- ret = hid_hw_raw_request(hdev, field->report->id, buf,
+ report_len = hid_report_len(report);
+ if (!report->id) {
+ /*
+ * hid_hw_raw_request() will stuff report ID (which will be 0)
+ * into the first byte of the buffer even for unnumbered
+ * reports, so we need to account for this to avoid getting
+ * -EOVERFLOW in return.
+ * Note that hid_alloc_report_buf() adds 7 bytes to the size
+ * so we can safely say that we have space for an extra byte.
+ */
+ report_len++;
+ }
+
+ ret = hid_hw_raw_request(hdev, report->id, report_data,
report_len, HID_FEATURE_REPORT,
HID_REQ_GET_REPORT);
if (ret < 0) {
@@ -103,7 +117,16 @@ static void vivaldi_feature_mapping(struct hid_device *hdev,
goto out;
}
- ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf,
+ if (!report->id) {
+ /*
+ * Undo the damage from hid_hw_raw_request() for unnumbered
+ * reports.
+ */
+ report_data++;
+ report_len--;
+ }
+
+ ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data,
report_len, 0);
if (ret) {
dev_warn(&hdev->dev, "failed to report feature %d\n",
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 8fe3efc..614adb5 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -28,11 +28,22 @@
struct uhid_device {
struct mutex devlock;
+
+ /* This flag tracks whether the HID device is usable for commands from
+ * userspace. The flag is already set before hid_add_device(), which
+ * runs in workqueue context, to allow hid_add_device() to communicate
+ * with userspace.
+ * However, if hid_add_device() fails, the flag is cleared without
+ * holding devlock.
+ * We guarantee that if @running changes from true to false while you're
+ * holding @devlock, it's still fine to access @hid.
+ */
bool running;
__u8 *rd_data;
uint rd_size;
+ /* When this is NULL, userspace may use UHID_CREATE/UHID_CREATE2. */
struct hid_device *hid;
struct uhid_event input_buf;
@@ -63,9 +74,18 @@ static void uhid_device_add_worker(struct work_struct *work)
if (ret) {
hid_err(uhid->hid, "Cannot register HID device: error %d\n", ret);
- hid_destroy_device(uhid->hid);
- uhid->hid = NULL;
- uhid->running = false;
+ /* We used to call hid_destroy_device() here, but that's really
+ * messy to get right because we have to coordinate with
+ * concurrent writes from userspace that might be in the middle
+ * of using uhid->hid.
+ * Just leave uhid->hid as-is for now, and clean it up when
+ * userspace tries to close or reinitialize the uhid instance.
+ *
+ * However, we do have to clear the ->running flag and do a
+ * wakeup to make sure userspace knows that the device is gone.
+ */
+ WRITE_ONCE(uhid->running, false);
+ wake_up_interruptible(&uhid->report_wait);
}
}
@@ -174,9 +194,9 @@ static int __uhid_report_queue_and_wait(struct uhid_device *uhid,
spin_unlock_irqrestore(&uhid->qlock, flags);
ret = wait_event_interruptible_timeout(uhid->report_wait,
- !uhid->report_running || !uhid->running,
+ !uhid->report_running || !READ_ONCE(uhid->running),
5 * HZ);
- if (!ret || !uhid->running || uhid->report_running)
+ if (!ret || !READ_ONCE(uhid->running) || uhid->report_running)
ret = -EIO;
else if (ret < 0)
ret = -ERESTARTSYS;
@@ -217,7 +237,7 @@ static int uhid_hid_get_report(struct hid_device *hid, unsigned char rnum,
struct uhid_event *ev;
int ret;
- if (!uhid->running)
+ if (!READ_ONCE(uhid->running))
return -EIO;
ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -259,7 +279,7 @@ static int uhid_hid_set_report(struct hid_device *hid, unsigned char rnum,
struct uhid_event *ev;
int ret;
- if (!uhid->running || count > UHID_DATA_MAX)
+ if (!READ_ONCE(uhid->running) || count > UHID_DATA_MAX)
return -EIO;
ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -474,7 +494,7 @@ static int uhid_dev_create2(struct uhid_device *uhid,
void *rd_data;
int ret;
- if (uhid->running)
+ if (uhid->hid)
return -EALREADY;
rd_size = ev->u.create2.rd_size;
@@ -556,15 +576,16 @@ static int uhid_dev_create(struct uhid_device *uhid,
static int uhid_dev_destroy(struct uhid_device *uhid)
{
- if (!uhid->running)
+ if (!uhid->hid)
return -EINVAL;
- uhid->running = false;
+ WRITE_ONCE(uhid->running, false);
wake_up_interruptible(&uhid->report_wait);
cancel_work_sync(&uhid->worker);
hid_destroy_device(uhid->hid);
+ uhid->hid = NULL;
kfree(uhid->rd_data);
return 0;
@@ -572,7 +593,7 @@ static int uhid_dev_destroy(struct uhid_device *uhid)
static int uhid_dev_input(struct uhid_device *uhid, struct uhid_event *ev)
{
- if (!uhid->running)
+ if (!READ_ONCE(uhid->running))
return -EINVAL;
hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input.data,
@@ -583,7 +604,7 @@ static int uhid_dev_input(struct uhid_device *uhid, struct uhid_event *ev)
static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev)
{
- if (!uhid->running)
+ if (!READ_ONCE(uhid->running))
return -EINVAL;
hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input2.data,
@@ -595,7 +616,7 @@ static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev)
static int uhid_dev_get_report_reply(struct uhid_device *uhid,
struct uhid_event *ev)
{
- if (!uhid->running)
+ if (!READ_ONCE(uhid->running))
return -EINVAL;
uhid_report_wake_up(uhid, ev->u.get_report_reply.id, ev);
@@ -605,7 +626,7 @@ static int uhid_dev_get_report_reply(struct uhid_device *uhid,
static int uhid_dev_set_report_reply(struct uhid_device *uhid,
struct uhid_event *ev)
{
- if (!uhid->running)
+ if (!READ_ONCE(uhid->running))
return -EINVAL;
uhid_report_wake_up(uhid, ev->u.set_report_reply.id, ev);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 2a4cc39..a7176fc 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2588,6 +2588,24 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac,
}
}
+static bool wacom_wac_slot_is_active(struct input_dev *dev, int key)
+{
+ struct input_mt *mt = dev->mt;
+ struct input_mt_slot *s;
+
+ if (!mt)
+ return false;
+
+ for (s = mt->slots; s != mt->slots + mt->num_slots; s++) {
+ if (s->key == key &&
+ input_mt_get_value(s, ABS_MT_TRACKING_ID) >= 0) {
+ return true;
+ }
+ }
+
+ return false;
+}
+
static void wacom_wac_finger_event(struct hid_device *hdev,
struct hid_field *field, struct hid_usage *usage, __s32 value)
{
@@ -2638,9 +2656,14 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
}
if (usage->usage_index + 1 == field->report_count) {
- if (equivalent_usage == wacom_wac->hid_data.last_slot_field &&
- wacom_wac->hid_data.confidence)
- wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
+ if (equivalent_usage == wacom_wac->hid_data.last_slot_field) {
+ bool touch_removed = wacom_wac_slot_is_active(wacom_wac->touch_input,
+ wacom_wac->hid_data.id) && !wacom_wac->hid_data.tipswitch;
+
+ if (wacom_wac->hid_data.confidence || touch_removed) {
+ wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
+ }
+ }
}
}
@@ -2659,6 +2682,10 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
hid_data->confidence = true;
+ hid_data->cc_report = 0;
+ hid_data->cc_index = -1;
+ hid_data->cc_value_index = -1;
+
for (i = 0; i < report->maxfield; i++) {
struct hid_field *field = report->field[i];
int j;
@@ -2692,11 +2719,14 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
hid_data->cc_index >= 0) {
struct hid_field *field = report->field[hid_data->cc_index];
int value = field->value[hid_data->cc_value_index];
- if (value)
+ if (value) {
hid_data->num_expected = value;
+ hid_data->num_received = 0;
+ }
}
else {
hid_data->num_expected = wacom_wac->features.touch_max;
+ hid_data->num_received = 0;
}
}
@@ -2724,6 +2754,7 @@ static void wacom_wac_finger_report(struct hid_device *hdev,
input_sync(input);
wacom_wac->hid_data.num_received = 0;
+ wacom_wac->hid_data.num_expected = 0;
/* keep touch state for pen event */
wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac);
diff --git a/drivers/hwspinlock/stm32_hwspinlock.c b/drivers/hwspinlock/stm32_hwspinlock.c
index 3ad0ce0..5bd11a7 100644
--- a/drivers/hwspinlock/stm32_hwspinlock.c
+++ b/drivers/hwspinlock/stm32_hwspinlock.c
@@ -54,8 +54,23 @@ static const struct hwspinlock_ops stm32_hwspinlock_ops = {
.relax = stm32_hwspinlock_relax,
};
+static void stm32_hwspinlock_disable_clk(void *data)
+{
+ struct platform_device *pdev = data;
+ struct stm32_hwspinlock *hw = platform_get_drvdata(pdev);
+ struct device *dev = &pdev->dev;
+
+ pm_runtime_get_sync(dev);
+ pm_runtime_disable(dev);
+ pm_runtime_set_suspended(dev);
+ pm_runtime_put_noidle(dev);
+
+ clk_disable_unprepare(hw->clk);
+}
+
static int stm32_hwspinlock_probe(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
struct stm32_hwspinlock *hw;
void __iomem *io_base;
size_t array_size;
@@ -66,43 +81,45 @@ static int stm32_hwspinlock_probe(struct platform_device *pdev)
return PTR_ERR(io_base);
array_size = STM32_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock);
- hw = devm_kzalloc(&pdev->dev, sizeof(*hw) + array_size, GFP_KERNEL);
+ hw = devm_kzalloc(dev, sizeof(*hw) + array_size, GFP_KERNEL);
if (!hw)
return -ENOMEM;
- hw->clk = devm_clk_get(&pdev->dev, "hsem");
+ hw->clk = devm_clk_get(dev, "hsem");
if (IS_ERR(hw->clk))
return PTR_ERR(hw->clk);
+ ret = clk_prepare_enable(hw->clk);
+ if (ret) {
+ dev_err(dev, "Failed to prepare_enable clock\n");
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, hw);
+
+ pm_runtime_get_noresume(dev);
+ pm_runtime_set_active(dev);
+ pm_runtime_enable(dev);
+ pm_runtime_put(dev);
+
+ ret = devm_add_action_or_reset(dev, stm32_hwspinlock_disable_clk, pdev);
+ if (ret) {
+ dev_err(dev, "Failed to register action\n");
+ return ret;
+ }
+
for (i = 0; i < STM32_MUTEX_NUM_LOCKS; i++)
hw->bank.lock[i].priv = io_base + i * sizeof(u32);
- platform_set_drvdata(pdev, hw);
- pm_runtime_enable(&pdev->dev);
-
- ret = hwspin_lock_register(&hw->bank, &pdev->dev, &stm32_hwspinlock_ops,
- 0, STM32_MUTEX_NUM_LOCKS);
+ ret = devm_hwspin_lock_register(dev, &hw->bank, &stm32_hwspinlock_ops,
+ 0, STM32_MUTEX_NUM_LOCKS);
if (ret)
- pm_runtime_disable(&pdev->dev);
+ dev_err(dev, "Failed to register hwspinlock\n");
return ret;
}
-static int stm32_hwspinlock_remove(struct platform_device *pdev)
-{
- struct stm32_hwspinlock *hw = platform_get_drvdata(pdev);
- int ret;
-
- ret = hwspin_lock_unregister(&hw->bank);
- if (ret)
- dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
-
- pm_runtime_disable(&pdev->dev);
-
- return 0;
-}
-
static int __maybe_unused stm32_hwspinlock_runtime_suspend(struct device *dev)
{
struct stm32_hwspinlock *hw = dev_get_drvdata(dev);
@@ -135,7 +152,6 @@ MODULE_DEVICE_TABLE(of, stm32_hwpinlock_ids);
static struct platform_driver stm32_hwspinlock_driver = {
.probe = stm32_hwspinlock_probe,
- .remove = stm32_hwspinlock_remove,
.driver = {
.name = "stm32_hwspinlock",
.of_match_table = stm32_hwpinlock_ids,
diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c
index 41eb0dc..4b9536f 100644
--- a/drivers/i2c/busses/i2c-virtio.c
+++ b/drivers/i2c/busses/i2c-virtio.c
@@ -165,7 +165,7 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
static void virtio_i2c_del_vqs(struct virtio_device *vdev)
{
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
}
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 6b7da40..bf8167f 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -1138,7 +1138,6 @@ int bmp280_common_probe(struct device *dev,
}
EXPORT_SYMBOL(bmp280_common_probe);
-#ifdef CONFIG_PM
static int bmp280_runtime_suspend(struct device *dev)
{
struct iio_dev *indio_dev = dev_get_drvdata(dev);
@@ -1159,15 +1158,9 @@ static int bmp280_runtime_resume(struct device *dev)
usleep_range(data->start_up_time, data->start_up_time + 100);
return data->chip_info->chip_config(data);
}
-#endif /* CONFIG_PM */
-const struct dev_pm_ops bmp280_dev_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
- SET_RUNTIME_PM_OPS(bmp280_runtime_suspend,
- bmp280_runtime_resume, NULL)
-};
-EXPORT_SYMBOL(bmp280_dev_pm_ops);
+EXPORT_RUNTIME_DEV_PM_OPS(bmp280_dev_pm_ops, bmp280_runtime_suspend,
+ bmp280_runtime_resume, NULL);
MODULE_AUTHOR("Vlad Dogaru <vlad.dogaru@intel.com>");
MODULE_DESCRIPTION("Driver for Bosch Sensortec BMP180/BMP280 pressure and temperature sensor");
diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c
index 8b03ea1..35045bd 100644
--- a/drivers/iio/pressure/bmp280-i2c.c
+++ b/drivers/iio/pressure/bmp280-i2c.c
@@ -58,7 +58,7 @@ static struct i2c_driver bmp280_i2c_driver = {
.driver = {
.name = "bmp280",
.of_match_table = bmp280_of_i2c_match,
- .pm = &bmp280_dev_pm_ops,
+ .pm = pm_ptr(&bmp280_dev_pm_ops),
},
.probe = bmp280_i2c_probe,
.id_table = bmp280_i2c_id,
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 625b868..41f6cc5 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -109,7 +109,7 @@ static struct spi_driver bmp280_spi_driver = {
.driver = {
.name = "bmp280",
.of_match_table = bmp280_of_spi_match,
- .pm = &bmp280_dev_pm_ops,
+ .pm = pm_ptr(&bmp280_dev_pm_ops),
},
.id_table = bmp280_spi_id,
.probe = bmp280_spi_probe,
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index 9363bccf..a8e1c30 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -196,7 +196,7 @@ struct qib_ctxtdata {
pid_t pid;
pid_t subpid[QLOGIC_IB_MAX_SUBCTXT];
/* same size as task_struct .comm[], command that opened context */
- char comm[16];
+ char comm[TASK_COMM_LEN];
/* pkeys set by this use of this ctxt */
u16 pkeys[4];
/* so file ops can get at unit */
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 63854f4..aa29092 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1321,7 +1321,7 @@ static int setup_ctxt(struct qib_pportdata *ppd, int ctxt,
rcd->tid_pg_list = ptmp;
rcd->pid = current->pid;
init_waitqueue_head(&dd->rcd[ctxt]->wait);
- strlcpy(rcd->comm, current->comm, sizeof(rcd->comm));
+ get_task_comm(rcd->comm, current);
ctxt_fp(fp) = rcd;
qib_stats.sps_ctxts++;
dd->freectxts--;
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index afe11f47..5018b93 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -217,8 +217,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
* the port number must be in the Dynamic Ports range
* (0xc000 - 0xffff).
*/
- qp->src_port = RXE_ROCE_V2_SPORT +
- (hash_32_generic(qp_num(qp), 14) & 0x3fff);
+ qp->src_port = RXE_ROCE_V2_SPORT + (hash_32(qp_num(qp), 14) & 0x3fff);
qp->sq.max_wr = init->cap.max_send_wr;
/* These caps are limited by rxe_qp_chk_cap() done by the caller */
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 1f79321..f2aa34f 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -1189,7 +1189,7 @@ static void viommu_remove(struct virtio_device *vdev)
iommu_device_unregister(&viommu->iommu);
/* Stop all virtqueues */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
dev_info(&vdev->dev, "device removed\n");
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 24a4532..e90adfa 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -300,8 +300,8 @@ mpt_is_discovery_complete(MPT_ADAPTER *ioc)
if (!hdr.ExtPageLength)
goto out;
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer)
goto out;
@@ -316,8 +316,8 @@ mpt_is_discovery_complete(MPT_ADAPTER *ioc)
rc = 1;
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return rc;
}
@@ -1661,16 +1661,14 @@ mpt_mapresources(MPT_ADAPTER *ioc)
const uint64_t required_mask = dma_get_required_mask
(&pdev->dev);
if (required_mask > DMA_BIT_MASK(32)
- && !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))
- && !pci_set_consistent_dma_mask(pdev,
- DMA_BIT_MASK(64))) {
+ && !dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))
+ && !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
ioc->dma_mask = DMA_BIT_MASK(64);
dinitprintk(ioc, printk(MYIOC_s_INFO_FMT
": 64 BIT PCI BUS DMA ADDRESSING SUPPORTED\n",
ioc->name));
- } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))
- && !pci_set_consistent_dma_mask(pdev,
- DMA_BIT_MASK(32))) {
+ } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))
+ && !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32))) {
ioc->dma_mask = DMA_BIT_MASK(32);
dinitprintk(ioc, printk(MYIOC_s_INFO_FMT
": 32 BIT PCI BUS DMA ADDRESSING SUPPORTED\n",
@@ -1681,9 +1679,8 @@ mpt_mapresources(MPT_ADAPTER *ioc)
goto out_pci_release_region;
}
} else {
- if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))
- && !pci_set_consistent_dma_mask(pdev,
- DMA_BIT_MASK(32))) {
+ if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))
+ && !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32))) {
ioc->dma_mask = DMA_BIT_MASK(32);
dinitprintk(ioc, printk(MYIOC_s_INFO_FMT
": 32 BIT PCI BUS DMA ADDRESSING SUPPORTED\n",
@@ -2769,9 +2766,9 @@ mpt_adapter_disable(MPT_ADAPTER *ioc)
if (ioc->spi_data.pIocPg4 != NULL) {
sz = ioc->spi_data.IocPg4Sz;
- pci_free_consistent(ioc->pcidev, sz,
- ioc->spi_data.pIocPg4,
- ioc->spi_data.IocPg4_dma);
+ dma_free_coherent(&ioc->pcidev->dev, sz,
+ ioc->spi_data.pIocPg4,
+ ioc->spi_data.IocPg4_dma);
ioc->spi_data.pIocPg4 = NULL;
ioc->alloc_total -= sz;
}
@@ -3515,7 +3512,8 @@ mpt_alloc_fw_memory(MPT_ADAPTER *ioc, int size)
rc = 0;
goto out;
}
- ioc->cached_fw = pci_alloc_consistent(ioc->pcidev, size, &ioc->cached_fw_dma);
+ ioc->cached_fw = dma_alloc_coherent(&ioc->pcidev->dev, size,
+ &ioc->cached_fw_dma, GFP_ATOMIC);
if (!ioc->cached_fw) {
printk(MYIOC_s_ERR_FMT "Unable to allocate memory for the cached firmware image!\n",
ioc->name);
@@ -3548,7 +3546,8 @@ mpt_free_fw_memory(MPT_ADAPTER *ioc)
sz = ioc->facts.FWImageSize;
dinitprintk(ioc, printk(MYIOC_s_DEBUG_FMT "free_fw_memory: FW Image @ %p[%p], sz=%d[%x] bytes\n",
ioc->name, ioc->cached_fw, (void *)(ulong)ioc->cached_fw_dma, sz, sz));
- pci_free_consistent(ioc->pcidev, sz, ioc->cached_fw, ioc->cached_fw_dma);
+ dma_free_coherent(&ioc->pcidev->dev, sz, ioc->cached_fw,
+ ioc->cached_fw_dma);
ioc->alloc_total -= sz;
ioc->cached_fw = NULL;
}
@@ -4447,9 +4446,8 @@ PrimeIocFifos(MPT_ADAPTER *ioc)
*/
if (ioc->pcidev->device == MPI_MANUFACTPAGE_DEVID_SAS1078 &&
ioc->dma_mask > DMA_BIT_MASK(35)) {
- if (!pci_set_dma_mask(ioc->pcidev, DMA_BIT_MASK(32))
- && !pci_set_consistent_dma_mask(ioc->pcidev,
- DMA_BIT_MASK(32))) {
+ if (!dma_set_mask(&ioc->pcidev->dev, DMA_BIT_MASK(32))
+ && !dma_set_coherent_mask(&ioc->pcidev->dev, DMA_BIT_MASK(32))) {
dma_mask = DMA_BIT_MASK(35);
d36memprintk(ioc, printk(MYIOC_s_DEBUG_FMT
"setting 35 bit addressing for "
@@ -4457,10 +4455,10 @@ PrimeIocFifos(MPT_ADAPTER *ioc)
ioc->name));
} else {
/*Reseting DMA mask to 64 bit*/
- pci_set_dma_mask(ioc->pcidev,
- DMA_BIT_MASK(64));
- pci_set_consistent_dma_mask(ioc->pcidev,
- DMA_BIT_MASK(64));
+ dma_set_mask(&ioc->pcidev->dev,
+ DMA_BIT_MASK(64));
+ dma_set_coherent_mask(&ioc->pcidev->dev,
+ DMA_BIT_MASK(64));
printk(MYIOC_s_ERR_FMT
"failed setting 35 bit addressing for "
@@ -4595,8 +4593,8 @@ PrimeIocFifos(MPT_ADAPTER *ioc)
alloc_dma += ioc->reply_sz;
}
- if (dma_mask == DMA_BIT_MASK(35) && !pci_set_dma_mask(ioc->pcidev,
- ioc->dma_mask) && !pci_set_consistent_dma_mask(ioc->pcidev,
+ if (dma_mask == DMA_BIT_MASK(35) && !dma_set_mask(&ioc->pcidev->dev,
+ ioc->dma_mask) && !dma_set_coherent_mask(&ioc->pcidev->dev,
ioc->dma_mask))
d36memprintk(ioc, printk(MYIOC_s_DEBUG_FMT
"restoring 64 bit addressing\n", ioc->name));
@@ -4620,8 +4618,8 @@ PrimeIocFifos(MPT_ADAPTER *ioc)
ioc->sense_buf_pool = NULL;
}
- if (dma_mask == DMA_BIT_MASK(35) && !pci_set_dma_mask(ioc->pcidev,
- DMA_BIT_MASK(64)) && !pci_set_consistent_dma_mask(ioc->pcidev,
+ if (dma_mask == DMA_BIT_MASK(35) && !dma_set_mask(&ioc->pcidev->dev,
+ DMA_BIT_MASK(64)) && !dma_set_coherent_mask(&ioc->pcidev->dev,
DMA_BIT_MASK(64)))
d36memprintk(ioc, printk(MYIOC_s_DEBUG_FMT
"restoring 64 bit addressing\n", ioc->name));
@@ -4968,7 +4966,8 @@ GetLanConfigPages(MPT_ADAPTER *ioc)
if (hdr.PageLength > 0) {
data_sz = hdr.PageLength * 4;
- ppage0_alloc = pci_alloc_consistent(ioc->pcidev, data_sz, &page0_dma);
+ ppage0_alloc = dma_alloc_coherent(&ioc->pcidev->dev, data_sz,
+ &page0_dma, GFP_KERNEL);
rc = -ENOMEM;
if (ppage0_alloc) {
memset((u8 *)ppage0_alloc, 0, data_sz);
@@ -4982,7 +4981,8 @@ GetLanConfigPages(MPT_ADAPTER *ioc)
}
- pci_free_consistent(ioc->pcidev, data_sz, (u8 *) ppage0_alloc, page0_dma);
+ dma_free_coherent(&ioc->pcidev->dev, data_sz,
+ (u8 *)ppage0_alloc, page0_dma);
/* FIXME!
* Normalize endianness of structure data,
@@ -5014,7 +5014,8 @@ GetLanConfigPages(MPT_ADAPTER *ioc)
data_sz = hdr.PageLength * 4;
rc = -ENOMEM;
- ppage1_alloc = pci_alloc_consistent(ioc->pcidev, data_sz, &page1_dma);
+ ppage1_alloc = dma_alloc_coherent(&ioc->pcidev->dev, data_sz,
+ &page1_dma, GFP_KERNEL);
if (ppage1_alloc) {
memset((u8 *)ppage1_alloc, 0, data_sz);
cfg.physAddr = page1_dma;
@@ -5026,7 +5027,8 @@ GetLanConfigPages(MPT_ADAPTER *ioc)
memcpy(&ioc->lan_cnfg_page1, ppage1_alloc, copy_sz);
}
- pci_free_consistent(ioc->pcidev, data_sz, (u8 *) ppage1_alloc, page1_dma);
+ dma_free_coherent(&ioc->pcidev->dev, data_sz,
+ (u8 *)ppage1_alloc, page1_dma);
/* FIXME!
* Normalize endianness of structure data,
@@ -5315,7 +5317,8 @@ GetIoUnitPage2(MPT_ADAPTER *ioc)
/* Read the config page */
data_sz = hdr.PageLength * 4;
rc = -ENOMEM;
- ppage_alloc = pci_alloc_consistent(ioc->pcidev, data_sz, &page_dma);
+ ppage_alloc = dma_alloc_coherent(&ioc->pcidev->dev, data_sz,
+ &page_dma, GFP_KERNEL);
if (ppage_alloc) {
memset((u8 *)ppage_alloc, 0, data_sz);
cfg.physAddr = page_dma;
@@ -5325,7 +5328,8 @@ GetIoUnitPage2(MPT_ADAPTER *ioc)
if ((rc = mpt_config(ioc, &cfg)) == 0)
ioc->biosVersion = le32_to_cpu(ppage_alloc->BiosVersion);
- pci_free_consistent(ioc->pcidev, data_sz, (u8 *) ppage_alloc, page_dma);
+ dma_free_coherent(&ioc->pcidev->dev, data_sz,
+ (u8 *)ppage_alloc, page_dma);
}
return rc;
@@ -5400,7 +5404,9 @@ mpt_GetScsiPortSettings(MPT_ADAPTER *ioc, int portnum)
return -EFAULT;
if (header.PageLength > 0) {
- pbuf = pci_alloc_consistent(ioc->pcidev, header.PageLength * 4, &buf_dma);
+ pbuf = dma_alloc_coherent(&ioc->pcidev->dev,
+ header.PageLength * 4, &buf_dma,
+ GFP_KERNEL);
if (pbuf) {
cfg.action = MPI_CONFIG_ACTION_PAGE_READ_CURRENT;
cfg.physAddr = buf_dma;
@@ -5456,7 +5462,9 @@ mpt_GetScsiPortSettings(MPT_ADAPTER *ioc, int portnum)
}
}
if (pbuf) {
- pci_free_consistent(ioc->pcidev, header.PageLength * 4, pbuf, buf_dma);
+ dma_free_coherent(&ioc->pcidev->dev,
+ header.PageLength * 4, pbuf,
+ buf_dma);
}
}
}
@@ -5478,7 +5486,9 @@ mpt_GetScsiPortSettings(MPT_ADAPTER *ioc, int portnum)
if (header.PageLength > 0) {
/* Allocate memory and read SCSI Port Page 2
*/
- pbuf = pci_alloc_consistent(ioc->pcidev, header.PageLength * 4, &buf_dma);
+ pbuf = dma_alloc_coherent(&ioc->pcidev->dev,
+ header.PageLength * 4, &buf_dma,
+ GFP_KERNEL);
if (pbuf) {
cfg.action = MPI_CONFIG_ACTION_PAGE_READ_NVRAM;
cfg.physAddr = buf_dma;
@@ -5543,7 +5553,9 @@ mpt_GetScsiPortSettings(MPT_ADAPTER *ioc, int portnum)
}
}
- pci_free_consistent(ioc->pcidev, header.PageLength * 4, pbuf, buf_dma);
+ dma_free_coherent(&ioc->pcidev->dev,
+ header.PageLength * 4, pbuf,
+ buf_dma);
}
}
@@ -5659,8 +5671,8 @@ mpt_inactive_raid_volumes(MPT_ADAPTER *ioc, u8 channel, u8 id)
if (!hdr.PageLength)
goto out;
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer)
goto out;
@@ -5707,8 +5719,8 @@ mpt_inactive_raid_volumes(MPT_ADAPTER *ioc, u8 channel, u8 id)
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
}
/**
@@ -5752,8 +5764,8 @@ mpt_raid_phys_disk_pg0(MPT_ADAPTER *ioc, u8 phys_disk_num,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
rc = -ENOMEM;
@@ -5776,8 +5788,8 @@ mpt_raid_phys_disk_pg0(MPT_ADAPTER *ioc, u8 phys_disk_num,
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
return rc;
}
@@ -5819,8 +5831,8 @@ mpt_raid_phys_disk_get_num_paths(MPT_ADAPTER *ioc, u8 phys_disk_num)
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
rc = 0;
@@ -5840,8 +5852,8 @@ mpt_raid_phys_disk_get_num_paths(MPT_ADAPTER *ioc, u8 phys_disk_num)
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
return rc;
}
@@ -5891,8 +5903,8 @@ mpt_raid_phys_disk_pg1(MPT_ADAPTER *ioc, u8 phys_disk_num,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
rc = -ENOMEM;
@@ -5929,8 +5941,8 @@ mpt_raid_phys_disk_pg1(MPT_ADAPTER *ioc, u8 phys_disk_num,
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
return rc;
}
@@ -5986,7 +5998,8 @@ mpt_findImVolumes(MPT_ADAPTER *ioc)
return -EFAULT;
iocpage2sz = header.PageLength * 4;
- pIoc2 = pci_alloc_consistent(ioc->pcidev, iocpage2sz, &ioc2_dma);
+ pIoc2 = dma_alloc_coherent(&ioc->pcidev->dev, iocpage2sz, &ioc2_dma,
+ GFP_KERNEL);
if (!pIoc2)
return -ENOMEM;
@@ -6011,7 +6024,7 @@ mpt_findImVolumes(MPT_ADAPTER *ioc)
pIoc2->RaidVolume[i].VolumeID);
out:
- pci_free_consistent(ioc->pcidev, iocpage2sz, pIoc2, ioc2_dma);
+ dma_free_coherent(&ioc->pcidev->dev, iocpage2sz, pIoc2, ioc2_dma);
return rc;
}
@@ -6053,7 +6066,8 @@ mpt_read_ioc_pg_3(MPT_ADAPTER *ioc)
/* Read Header good, alloc memory
*/
iocpage3sz = header.PageLength * 4;
- pIoc3 = pci_alloc_consistent(ioc->pcidev, iocpage3sz, &ioc3_dma);
+ pIoc3 = dma_alloc_coherent(&ioc->pcidev->dev, iocpage3sz, &ioc3_dma,
+ GFP_KERNEL);
if (!pIoc3)
return 0;
@@ -6070,7 +6084,7 @@ mpt_read_ioc_pg_3(MPT_ADAPTER *ioc)
}
}
- pci_free_consistent(ioc->pcidev, iocpage3sz, pIoc3, ioc3_dma);
+ dma_free_coherent(&ioc->pcidev->dev, iocpage3sz, pIoc3, ioc3_dma);
return 0;
}
@@ -6104,7 +6118,8 @@ mpt_read_ioc_pg_4(MPT_ADAPTER *ioc)
if ( (pIoc4 = ioc->spi_data.pIocPg4) == NULL ) {
iocpage4sz = (header.PageLength + 4) * 4; /* Allow 4 additional SEP's */
- pIoc4 = pci_alloc_consistent(ioc->pcidev, iocpage4sz, &ioc4_dma);
+ pIoc4 = dma_alloc_coherent(&ioc->pcidev->dev, iocpage4sz,
+ &ioc4_dma, GFP_KERNEL);
if (!pIoc4)
return;
ioc->alloc_total += iocpage4sz;
@@ -6122,7 +6137,8 @@ mpt_read_ioc_pg_4(MPT_ADAPTER *ioc)
ioc->spi_data.IocPg4_dma = ioc4_dma;
ioc->spi_data.IocPg4Sz = iocpage4sz;
} else {
- pci_free_consistent(ioc->pcidev, iocpage4sz, pIoc4, ioc4_dma);
+ dma_free_coherent(&ioc->pcidev->dev, iocpage4sz, pIoc4,
+ ioc4_dma);
ioc->spi_data.pIocPg4 = NULL;
ioc->alloc_total -= iocpage4sz;
}
@@ -6159,7 +6175,8 @@ mpt_read_ioc_pg_1(MPT_ADAPTER *ioc)
/* Read Header good, alloc memory
*/
iocpage1sz = header.PageLength * 4;
- pIoc1 = pci_alloc_consistent(ioc->pcidev, iocpage1sz, &ioc1_dma);
+ pIoc1 = dma_alloc_coherent(&ioc->pcidev->dev, iocpage1sz, &ioc1_dma,
+ GFP_KERNEL);
if (!pIoc1)
return;
@@ -6210,7 +6227,7 @@ mpt_read_ioc_pg_1(MPT_ADAPTER *ioc)
}
}
- pci_free_consistent(ioc->pcidev, iocpage1sz, pIoc1, ioc1_dma);
+ dma_free_coherent(&ioc->pcidev->dev, iocpage1sz, pIoc1, ioc1_dma);
return;
}
@@ -6239,7 +6256,8 @@ mpt_get_manufacturing_pg_0(MPT_ADAPTER *ioc)
goto out;
cfg.action = MPI_CONFIG_ACTION_PAGE_READ_CURRENT;
- pbuf = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4, &buf_dma);
+ pbuf = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &buf_dma, GFP_KERNEL);
if (!pbuf)
goto out;
@@ -6255,7 +6273,8 @@ mpt_get_manufacturing_pg_0(MPT_ADAPTER *ioc)
out:
if (pbuf)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, pbuf, buf_dma);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4, pbuf,
+ buf_dma);
}
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index ae433c1..03c8fb1 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -1041,14 +1041,15 @@ kbuf_alloc_2_sgl(int bytes, u32 sgdir, int sge_offset, int *frags,
* copying the data in this array into the correct place in the
* request and chain buffers.
*/
- sglbuf = pci_alloc_consistent(ioc->pcidev, MAX_SGL_BYTES, sglbuf_dma);
+ sglbuf = dma_alloc_coherent(&ioc->pcidev->dev, MAX_SGL_BYTES,
+ sglbuf_dma, GFP_KERNEL);
if (sglbuf == NULL)
goto free_and_fail;
if (sgdir & 0x04000000)
- dir = PCI_DMA_TODEVICE;
+ dir = DMA_TO_DEVICE;
else
- dir = PCI_DMA_FROMDEVICE;
+ dir = DMA_FROM_DEVICE;
/* At start:
* sgl = sglbuf = point to beginning of sg buffer
@@ -1062,9 +1063,9 @@ kbuf_alloc_2_sgl(int bytes, u32 sgdir, int sge_offset, int *frags,
while (bytes_allocd < bytes) {
this_alloc = min(alloc_sz, bytes-bytes_allocd);
buflist[buflist_ent].len = this_alloc;
- buflist[buflist_ent].kptr = pci_alloc_consistent(ioc->pcidev,
- this_alloc,
- &pa);
+ buflist[buflist_ent].kptr = dma_alloc_coherent(&ioc->pcidev->dev,
+ this_alloc,
+ &pa, GFP_KERNEL);
if (buflist[buflist_ent].kptr == NULL) {
alloc_sz = alloc_sz / 2;
if (alloc_sz == 0) {
@@ -1080,8 +1081,9 @@ kbuf_alloc_2_sgl(int bytes, u32 sgdir, int sge_offset, int *frags,
bytes_allocd += this_alloc;
sgl->FlagsLength = (0x10000000|sgdir|this_alloc);
- dma_addr = pci_map_single(ioc->pcidev,
- buflist[buflist_ent].kptr, this_alloc, dir);
+ dma_addr = dma_map_single(&ioc->pcidev->dev,
+ buflist[buflist_ent].kptr,
+ this_alloc, dir);
sgl->Address = dma_addr;
fragcnt++;
@@ -1140,9 +1142,11 @@ kbuf_alloc_2_sgl(int bytes, u32 sgdir, int sge_offset, int *frags,
kptr = buflist[i].kptr;
len = buflist[i].len;
- pci_free_consistent(ioc->pcidev, len, kptr, dma_addr);
+ dma_free_coherent(&ioc->pcidev->dev, len, kptr,
+ dma_addr);
}
- pci_free_consistent(ioc->pcidev, MAX_SGL_BYTES, sglbuf, *sglbuf_dma);
+ dma_free_coherent(&ioc->pcidev->dev, MAX_SGL_BYTES, sglbuf,
+ *sglbuf_dma);
}
kfree(buflist);
return NULL;
@@ -1162,9 +1166,9 @@ kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma, struct buflist *buflist, MPT_ADAPTE
int n = 0;
if (sg->FlagsLength & 0x04000000)
- dir = PCI_DMA_TODEVICE;
+ dir = DMA_TO_DEVICE;
else
- dir = PCI_DMA_FROMDEVICE;
+ dir = DMA_FROM_DEVICE;
nib = (sg->FlagsLength & 0xF0000000) >> 28;
while (! (nib & 0x4)) { /* eob */
@@ -1179,8 +1183,10 @@ kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma, struct buflist *buflist, MPT_ADAPTE
dma_addr = sg->Address;
kptr = bl->kptr;
len = bl->len;
- pci_unmap_single(ioc->pcidev, dma_addr, len, dir);
- pci_free_consistent(ioc->pcidev, len, kptr, dma_addr);
+ dma_unmap_single(&ioc->pcidev->dev, dma_addr, len,
+ dir);
+ dma_free_coherent(&ioc->pcidev->dev, len, kptr,
+ dma_addr);
n++;
}
sg++;
@@ -1197,12 +1203,12 @@ kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma, struct buflist *buflist, MPT_ADAPTE
dma_addr = sg->Address;
kptr = bl->kptr;
len = bl->len;
- pci_unmap_single(ioc->pcidev, dma_addr, len, dir);
- pci_free_consistent(ioc->pcidev, len, kptr, dma_addr);
+ dma_unmap_single(&ioc->pcidev->dev, dma_addr, len, dir);
+ dma_free_coherent(&ioc->pcidev->dev, len, kptr, dma_addr);
n++;
}
- pci_free_consistent(ioc->pcidev, MAX_SGL_BYTES, sgl, sgl_dma);
+ dma_free_coherent(&ioc->pcidev->dev, MAX_SGL_BYTES, sgl, sgl_dma);
kfree(buflist);
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "-SG: Free'd 1 SGL buf + %d kbufs!\n",
ioc->name, n));
@@ -2100,8 +2106,9 @@ mptctl_do_mpt_command (MPT_ADAPTER *ioc, struct mpt_ioctl_command karg, void __u
}
flagsLength |= karg.dataOutSize;
bufOut.len = karg.dataOutSize;
- bufOut.kptr = pci_alloc_consistent(
- ioc->pcidev, bufOut.len, &dma_addr_out);
+ bufOut.kptr = dma_alloc_coherent(&ioc->pcidev->dev,
+ bufOut.len,
+ &dma_addr_out, GFP_KERNEL);
if (bufOut.kptr == NULL) {
rc = -ENOMEM;
@@ -2134,8 +2141,9 @@ mptctl_do_mpt_command (MPT_ADAPTER *ioc, struct mpt_ioctl_command karg, void __u
flagsLength |= karg.dataInSize;
bufIn.len = karg.dataInSize;
- bufIn.kptr = pci_alloc_consistent(ioc->pcidev,
- bufIn.len, &dma_addr_in);
+ bufIn.kptr = dma_alloc_coherent(&ioc->pcidev->dev,
+ bufIn.len,
+ &dma_addr_in, GFP_KERNEL);
if (bufIn.kptr == NULL) {
rc = -ENOMEM;
@@ -2283,13 +2291,13 @@ mptctl_do_mpt_command (MPT_ADAPTER *ioc, struct mpt_ioctl_command karg, void __u
/* Free the allocated memory.
*/
if (bufOut.kptr != NULL) {
- pci_free_consistent(ioc->pcidev,
- bufOut.len, (void *) bufOut.kptr, dma_addr_out);
+ dma_free_coherent(&ioc->pcidev->dev, bufOut.len,
+ (void *)bufOut.kptr, dma_addr_out);
}
if (bufIn.kptr != NULL) {
- pci_free_consistent(ioc->pcidev,
- bufIn.len, (void *) bufIn.kptr, dma_addr_in);
+ dma_free_coherent(&ioc->pcidev->dev, bufIn.len,
+ (void *)bufIn.kptr, dma_addr_in);
}
/* mf is null if command issued successfully
@@ -2395,7 +2403,9 @@ mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
/* Issue the second config page request */
cfg.action = MPI_CONFIG_ACTION_PAGE_READ_CURRENT;
- pbuf = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4, &buf_dma);
+ pbuf = dma_alloc_coherent(&ioc->pcidev->dev,
+ hdr.PageLength * 4,
+ &buf_dma, GFP_KERNEL);
if (pbuf) {
cfg.physAddr = buf_dma;
if (mpt_config(ioc, &cfg) == 0) {
@@ -2405,7 +2415,9 @@ mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
pdata->BoardTracerNumber, 24);
}
}
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, pbuf, buf_dma);
+ dma_free_coherent(&ioc->pcidev->dev,
+ hdr.PageLength * 4, pbuf,
+ buf_dma);
pbuf = NULL;
}
}
@@ -2470,7 +2482,7 @@ mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
else
IstwiRWRequest->DeviceAddr = 0xB0;
- pbuf = pci_alloc_consistent(ioc->pcidev, 4, &buf_dma);
+ pbuf = dma_alloc_coherent(&ioc->pcidev->dev, 4, &buf_dma, GFP_KERNEL);
if (!pbuf)
goto out;
ioc->add_sge((char *)&IstwiRWRequest->SGL,
@@ -2519,7 +2531,7 @@ mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
SET_MGMT_MSG_CONTEXT(ioc->ioctl_cmds.msg_context, 0);
if (pbuf)
- pci_free_consistent(ioc->pcidev, 4, pbuf, buf_dma);
+ dma_free_coherent(&ioc->pcidev->dev, 4, pbuf, buf_dma);
/* Copy the data from kernel memory to user memory
*/
@@ -2585,7 +2597,8 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
/* Get the data transfer speeds
*/
data_sz = ioc->spi_data.sdp0length * 4;
- pg0_alloc = pci_alloc_consistent(ioc->pcidev, data_sz, &page_dma);
+ pg0_alloc = dma_alloc_coherent(&ioc->pcidev->dev, data_sz, &page_dma,
+ GFP_KERNEL);
if (pg0_alloc) {
hdr.PageVersion = ioc->spi_data.sdp0version;
hdr.PageLength = data_sz;
@@ -2623,7 +2636,8 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
karg.negotiated_speed = HP_DEV_SPEED_ASYNC;
}
- pci_free_consistent(ioc->pcidev, data_sz, (u8 *) pg0_alloc, page_dma);
+ dma_free_coherent(&ioc->pcidev->dev, data_sz, (u8 *)pg0_alloc,
+ page_dma);
}
/* Set defaults
@@ -2649,7 +2663,8 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
/* Issue the second config page request */
cfg.action = MPI_CONFIG_ACTION_PAGE_READ_CURRENT;
data_sz = (int) cfg.cfghdr.hdr->PageLength * 4;
- pg3_alloc = pci_alloc_consistent(ioc->pcidev, data_sz, &page_dma);
+ pg3_alloc = dma_alloc_coherent(&ioc->pcidev->dev, data_sz,
+ &page_dma, GFP_KERNEL);
if (pg3_alloc) {
cfg.physAddr = page_dma;
cfg.pageAddr = (karg.hdr.channel << 8) | karg.hdr.id;
@@ -2658,7 +2673,8 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
karg.phase_errors = (u32) le16_to_cpu(pg3_alloc->PhaseErrorCount);
karg.parity_errors = (u32) le16_to_cpu(pg3_alloc->ParityErrorCount);
}
- pci_free_consistent(ioc->pcidev, data_sz, (u8 *) pg3_alloc, page_dma);
+ dma_free_coherent(&ioc->pcidev->dev, data_sz,
+ (u8 *)pg3_alloc, page_dma);
}
}
hd = shost_priv(ioc->sh);
diff --git a/drivers/message/fusion/mptlan.c b/drivers/message/fusion/mptlan.c
index 117fa4e..142eb5d 100644
--- a/drivers/message/fusion/mptlan.c
+++ b/drivers/message/fusion/mptlan.c
@@ -516,9 +516,9 @@ mpt_lan_close(struct net_device *dev)
if (priv->RcvCtl[i].skb != NULL) {
/**/ dlprintk((KERN_INFO MYNAM "/lan_close: bucket %05x "
/**/ "is still out\n", i));
- pci_unmap_single(mpt_dev->pcidev, priv->RcvCtl[i].dma,
- priv->RcvCtl[i].len,
- PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[i].dma,
+ priv->RcvCtl[i].len, DMA_FROM_DEVICE);
dev_kfree_skb(priv->RcvCtl[i].skb);
}
}
@@ -528,9 +528,9 @@ mpt_lan_close(struct net_device *dev)
for (i = 0; i < priv->tx_max_out; i++) {
if (priv->SendCtl[i].skb != NULL) {
- pci_unmap_single(mpt_dev->pcidev, priv->SendCtl[i].dma,
- priv->SendCtl[i].len,
- PCI_DMA_TODEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev,
+ priv->SendCtl[i].dma,
+ priv->SendCtl[i].len, DMA_TO_DEVICE);
dev_kfree_skb(priv->SendCtl[i].skb);
}
}
@@ -582,8 +582,8 @@ mpt_lan_send_turbo(struct net_device *dev, u32 tmsg)
__func__, sent));
priv->SendCtl[ctx].skb = NULL;
- pci_unmap_single(mpt_dev->pcidev, priv->SendCtl[ctx].dma,
- priv->SendCtl[ctx].len, PCI_DMA_TODEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev, priv->SendCtl[ctx].dma,
+ priv->SendCtl[ctx].len, DMA_TO_DEVICE);
dev_kfree_skb_irq(sent);
spin_lock_irqsave(&priv->txfidx_lock, flags);
@@ -648,8 +648,9 @@ mpt_lan_send_reply(struct net_device *dev, LANSendReply_t *pSendRep)
__func__, sent));
priv->SendCtl[ctx].skb = NULL;
- pci_unmap_single(mpt_dev->pcidev, priv->SendCtl[ctx].dma,
- priv->SendCtl[ctx].len, PCI_DMA_TODEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev,
+ priv->SendCtl[ctx].dma,
+ priv->SendCtl[ctx].len, DMA_TO_DEVICE);
dev_kfree_skb_irq(sent);
priv->mpt_txfidx[++priv->mpt_txfidx_tail] = ctx;
@@ -720,8 +721,8 @@ mpt_lan_sdu_send (struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
skb_pull(skb, 12);
- dma = pci_map_single(mpt_dev->pcidev, skb->data, skb->len,
- PCI_DMA_TODEVICE);
+ dma = dma_map_single(&mpt_dev->pcidev->dev, skb->data, skb->len,
+ DMA_TO_DEVICE);
priv->SendCtl[ctx].skb = skb;
priv->SendCtl[ctx].dma = dma;
@@ -868,13 +869,17 @@ mpt_lan_receive_post_turbo(struct net_device *dev, u32 tmsg)
return -ENOMEM;
}
- pci_dma_sync_single_for_cpu(mpt_dev->pcidev, priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_cpu(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
skb_copy_from_linear_data(old_skb, skb_put(skb, len), len);
- pci_dma_sync_single_for_device(mpt_dev->pcidev, priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_device(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
goto out;
}
@@ -882,8 +887,8 @@ mpt_lan_receive_post_turbo(struct net_device *dev, u32 tmsg)
priv->RcvCtl[ctx].skb = NULL;
- pci_unmap_single(mpt_dev->pcidev, priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev, priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len, DMA_FROM_DEVICE);
out:
spin_lock_irqsave(&priv->rxfidx_lock, flags);
@@ -927,8 +932,8 @@ mpt_lan_receive_post_free(struct net_device *dev,
// dlprintk((KERN_INFO MYNAM "@rpr[2] TC + 3\n"));
priv->RcvCtl[ctx].skb = NULL;
- pci_unmap_single(mpt_dev->pcidev, priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev, priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len, DMA_FROM_DEVICE);
dev_kfree_skb_any(skb);
priv->mpt_rxfidx[++priv->mpt_rxfidx_tail] = ctx;
@@ -1028,16 +1033,16 @@ mpt_lan_receive_post_reply(struct net_device *dev,
// IOC_AND_NETDEV_NAMES_s_s(dev),
// i, l));
- pci_dma_sync_single_for_cpu(mpt_dev->pcidev,
- priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len,
- PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_cpu(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
skb_copy_from_linear_data(old_skb, skb_put(skb, l), l);
- pci_dma_sync_single_for_device(mpt_dev->pcidev,
- priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len,
- PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_device(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
priv->mpt_rxfidx[++priv->mpt_rxfidx_tail] = ctx;
szrem -= l;
@@ -1056,17 +1061,17 @@ mpt_lan_receive_post_reply(struct net_device *dev,
return -ENOMEM;
}
- pci_dma_sync_single_for_cpu(mpt_dev->pcidev,
- priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len,
- PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_cpu(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
skb_copy_from_linear_data(old_skb, skb_put(skb, len), len);
- pci_dma_sync_single_for_device(mpt_dev->pcidev,
- priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len,
- PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_device(&mpt_dev->pcidev->dev,
+ priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len,
+ DMA_FROM_DEVICE);
spin_lock_irqsave(&priv->rxfidx_lock, flags);
priv->mpt_rxfidx[++priv->mpt_rxfidx_tail] = ctx;
@@ -1077,8 +1082,8 @@ mpt_lan_receive_post_reply(struct net_device *dev,
priv->RcvCtl[ctx].skb = NULL;
- pci_unmap_single(mpt_dev->pcidev, priv->RcvCtl[ctx].dma,
- priv->RcvCtl[ctx].len, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&mpt_dev->pcidev->dev, priv->RcvCtl[ctx].dma,
+ priv->RcvCtl[ctx].len, DMA_FROM_DEVICE);
priv->RcvCtl[ctx].dma = 0;
priv->mpt_rxfidx[++priv->mpt_rxfidx_tail] = ctx;
@@ -1199,10 +1204,10 @@ mpt_lan_post_receive_buckets(struct mpt_lan_priv *priv)
skb = priv->RcvCtl[ctx].skb;
if (skb && (priv->RcvCtl[ctx].len != len)) {
- pci_unmap_single(mpt_dev->pcidev,
+ dma_unmap_single(&mpt_dev->pcidev->dev,
priv->RcvCtl[ctx].dma,
priv->RcvCtl[ctx].len,
- PCI_DMA_FROMDEVICE);
+ DMA_FROM_DEVICE);
dev_kfree_skb(priv->RcvCtl[ctx].skb);
skb = priv->RcvCtl[ctx].skb = NULL;
}
@@ -1218,8 +1223,9 @@ mpt_lan_post_receive_buckets(struct mpt_lan_priv *priv)
break;
}
- dma = pci_map_single(mpt_dev->pcidev, skb->data,
- len, PCI_DMA_FROMDEVICE);
+ dma = dma_map_single(&mpt_dev->pcidev->dev,
+ skb->data, len,
+ DMA_FROM_DEVICE);
priv->RcvCtl[ctx].skb = skb;
priv->RcvCtl[ctx].dma = dma;
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 091b450..4acd8f9 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -702,8 +702,8 @@ mptsas_add_device_component_starget_ir(MPT_ADAPTER *ioc,
if (!hdr.PageLength)
goto out;
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer)
goto out;
@@ -769,8 +769,8 @@ mptsas_add_device_component_starget_ir(MPT_ADAPTER *ioc,
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
}
/**
@@ -1399,8 +1399,8 @@ mptsas_sas_enclosure_pg0(MPT_ADAPTER *ioc, struct mptsas_enclosure *enclosure,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -1426,8 +1426,8 @@ mptsas_sas_enclosure_pg0(MPT_ADAPTER *ioc, struct mptsas_enclosure *enclosure,
enclosure->sep_channel = buffer->SEPBus;
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2058,8 +2058,8 @@ static int mptsas_get_linkerrors(struct sas_phy *phy)
if (!hdr.ExtPageLength)
return -ENXIO;
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer)
return -ENOMEM;
@@ -2081,8 +2081,8 @@ static int mptsas_get_linkerrors(struct sas_phy *phy)
le32_to_cpu(buffer->PhyResetProblemCount);
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
return error;
}
@@ -2301,7 +2301,7 @@ static void mptsas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
<< MPI_SGE_FLAGS_SHIFT;
if (!dma_map_sg(&ioc->pcidev->dev, job->request_payload.sg_list,
- 1, PCI_DMA_BIDIRECTIONAL))
+ 1, DMA_BIDIRECTIONAL))
goto put_mf;
flagsLength |= (sg_dma_len(job->request_payload.sg_list) - 4);
@@ -2318,7 +2318,7 @@ static void mptsas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
flagsLength = flagsLength << MPI_SGE_FLAGS_SHIFT;
if (!dma_map_sg(&ioc->pcidev->dev, job->reply_payload.sg_list,
- 1, PCI_DMA_BIDIRECTIONAL))
+ 1, DMA_BIDIRECTIONAL))
goto unmap_out;
flagsLength |= sg_dma_len(job->reply_payload.sg_list) + 4;
ioc->add_sge(psge, flagsLength,
@@ -2356,10 +2356,10 @@ static void mptsas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
unmap_in:
dma_unmap_sg(&ioc->pcidev->dev, job->reply_payload.sg_list, 1,
- PCI_DMA_BIDIRECTIONAL);
+ DMA_BIDIRECTIONAL);
unmap_out:
dma_unmap_sg(&ioc->pcidev->dev, job->request_payload.sg_list, 1,
- PCI_DMA_BIDIRECTIONAL);
+ DMA_BIDIRECTIONAL);
put_mf:
if (mf)
mpt_free_msg_frame(ioc, mf);
@@ -2412,8 +2412,8 @@ mptsas_sas_io_unit_pg0(MPT_ADAPTER *ioc, struct mptsas_portinfo *port_info)
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2452,8 +2452,8 @@ mptsas_sas_io_unit_pg0(MPT_ADAPTER *ioc, struct mptsas_portinfo *port_info)
}
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2487,8 +2487,8 @@ mptsas_sas_io_unit_pg1(MPT_ADAPTER *ioc)
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2509,8 +2509,8 @@ mptsas_sas_io_unit_pg1(MPT_ADAPTER *ioc)
device_missing_delay & MPI_SAS_IOUNIT1_REPORT_MISSING_TIMEOUT_MASK;
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2551,8 +2551,8 @@ mptsas_sas_phy_pg0(MPT_ADAPTER *ioc, struct mptsas_phyinfo *phy_info,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2573,8 +2573,8 @@ mptsas_sas_phy_pg0(MPT_ADAPTER *ioc, struct mptsas_phyinfo *phy_info,
phy_info->attached.handle = le16_to_cpu(buffer->AttachedDevHandle);
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2614,8 +2614,8 @@ mptsas_sas_device_pg0(MPT_ADAPTER *ioc, struct mptsas_devinfo *device_info,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2654,8 +2654,8 @@ mptsas_sas_device_pg0(MPT_ADAPTER *ioc, struct mptsas_devinfo *device_info,
device_info->flags = le16_to_cpu(buffer->Flags);
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2697,8 +2697,8 @@ mptsas_sas_expander_pg0(MPT_ADAPTER *ioc, struct mptsas_portinfo *port_info,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2737,8 +2737,8 @@ mptsas_sas_expander_pg0(MPT_ADAPTER *ioc, struct mptsas_portinfo *port_info,
}
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2777,8 +2777,8 @@ mptsas_sas_expander_pg1(MPT_ADAPTER *ioc, struct mptsas_phyinfo *phy_info,
goto out;
}
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto out;
@@ -2810,8 +2810,8 @@ mptsas_sas_expander_pg1(MPT_ADAPTER *ioc, struct mptsas_phyinfo *phy_info,
phy_info->attached.handle = le16_to_cpu(buffer->AttachedDevHandle);
out_free_consistent:
- pci_free_consistent(ioc->pcidev, hdr.ExtPageLength * 4,
- buffer, dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.ExtPageLength * 4, buffer,
+ dma_handle);
out:
return error;
}
@@ -2896,7 +2896,8 @@ mptsas_exp_repmanufacture_info(MPT_ADAPTER *ioc,
sz = sizeof(struct rep_manu_request) + sizeof(struct rep_manu_reply);
- data_out = pci_alloc_consistent(ioc->pcidev, sz, &data_out_dma);
+ data_out = dma_alloc_coherent(&ioc->pcidev->dev, sz, &data_out_dma,
+ GFP_KERNEL);
if (!data_out) {
printk(KERN_ERR "Memory allocation failure at %s:%d/%s()!\n",
__FILE__, __LINE__, __func__);
@@ -2987,7 +2988,8 @@ mptsas_exp_repmanufacture_info(MPT_ADAPTER *ioc,
}
out_free:
if (data_out_dma)
- pci_free_consistent(ioc->pcidev, sz, data_out, data_out_dma);
+ dma_free_coherent(&ioc->pcidev->dev, sz, data_out,
+ data_out_dma);
put_mf:
if (mf)
mpt_free_msg_frame(ioc, mf);
@@ -4271,8 +4273,8 @@ mptsas_adding_inactive_raid_components(MPT_ADAPTER *ioc, u8 channel, u8 id)
if (!hdr.PageLength)
goto out;
- buffer = pci_alloc_consistent(ioc->pcidev, hdr.PageLength * 4,
- &dma_handle);
+ buffer = dma_alloc_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ &dma_handle, GFP_KERNEL);
if (!buffer)
goto out;
@@ -4318,8 +4320,8 @@ mptsas_adding_inactive_raid_components(MPT_ADAPTER *ioc, u8 channel, u8 id)
out:
if (buffer)
- pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, buffer,
- dma_handle);
+ dma_free_coherent(&ioc->pcidev->dev, hdr.PageLength * 4,
+ buffer, dma_handle);
}
/*
* Work queue thread to handle SAS hotplug events
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index 7693236..7ab1b38 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -1128,8 +1128,8 @@ static int jz4740_mmc_resume(struct device *dev)
return pinctrl_select_default_state(dev);
}
-DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend,
- jz4740_mmc_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend,
+ jz4740_mmc_resume);
static struct platform_driver jz4740_mmc_driver = {
.probe = jz4740_mmc_probe,
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 98c218b..40b6878 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -1210,7 +1210,7 @@ static int mxcmci_resume(struct device *dev)
return ret;
}
-DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
static struct platform_driver mxcmci_driver = {
.probe = mxcmci_probe,
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 07fc603..ec498ce 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3874,8 +3874,8 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
skb->l4_hash)
return skb->hash;
- return __bond_xmit_hash(bond, skb, skb->head, skb->protocol,
- skb->mac_header, skb->network_header,
+ return __bond_xmit_hash(bond, skb, skb->data, skb->protocol,
+ skb_mac_offset(skb), skb_network_offset(skb),
skb_headlen(skb));
}
@@ -4884,25 +4884,39 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave = NULL;
struct list_head *iter;
+ bool xmit_suc = false;
+ bool skb_used = false;
bond_for_each_slave_rcu(bond, slave, iter) {
- if (bond_is_last_slave(bond, slave))
- break;
- if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
- struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *skb2;
+ if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
+ continue;
+
+ if (bond_is_last_slave(bond, slave)) {
+ skb2 = skb;
+ skb_used = true;
+ } else {
+ skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2) {
net_err_ratelimited("%s: Error: %s: skb_clone() failed\n",
bond_dev->name, __func__);
continue;
}
- bond_dev_queue_xmit(bond, skb2, slave->dev);
}
- }
- if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)
- return bond_dev_queue_xmit(bond, skb, slave->dev);
- return bond_tx_drop(bond_dev, skb);
+ if (bond_dev_queue_xmit(bond, skb2, slave->dev) == NETDEV_TX_OK)
+ xmit_suc = true;
+ }
+
+ if (!skb_used)
+ dev_kfree_skb_any(skb);
+
+ if (xmit_suc)
+ return NETDEV_TX_OK;
+
+ atomic_long_inc(&bond_dev->tx_dropped);
+ return NET_XMIT_DROP;
}
/*------------------------- Device initialization ---------------------------*/
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 9123089..444ef6a 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -754,7 +754,7 @@ static void cfv_remove(struct virtio_device *vdev)
debugfs_remove_recursive(cfv->debugfs);
vringh_kiov_cleanup(&cfv->ctx.riov);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->vringh_config->del_vrhs(cfv->vdev);
cfv->vr_rx = NULL;
vdev->config->del_vqs(cfv->vdev);
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 849de45..621ce74 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -106,9 +106,9 @@ static void emac_update_speed(struct net_device *dev)
/* set EMAC SPEED, depend on PHY */
reg_val = readl(db->membase + EMAC_MAC_SUPP_REG);
- reg_val &= ~(0x1 << 8);
+ reg_val &= ~EMAC_MAC_SUPP_100M;
if (db->speed == SPEED_100)
- reg_val |= 1 << 8;
+ reg_val |= EMAC_MAC_SUPP_100M;
writel(reg_val, db->membase + EMAC_MAC_SUPP_REG);
}
@@ -264,7 +264,7 @@ static void emac_dma_done_callback(void *arg)
/* re enable interrupt */
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0x01 << 8);
+ reg_val |= EMAC_INT_CTL_RX_EN;
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
db->emacrx_completed_flag = 1;
@@ -429,7 +429,7 @@ static unsigned int emac_powerup(struct net_device *ndev)
/* initial EMAC */
/* flush RX FIFO */
reg_val = readl(db->membase + EMAC_RX_CTL_REG);
- reg_val |= 0x8;
+ reg_val |= EMAC_RX_CTL_FLUSH_FIFO;
writel(reg_val, db->membase + EMAC_RX_CTL_REG);
udelay(1);
@@ -441,8 +441,8 @@ static unsigned int emac_powerup(struct net_device *ndev)
/* set MII clock */
reg_val = readl(db->membase + EMAC_MAC_MCFG_REG);
- reg_val &= (~(0xf << 2));
- reg_val |= (0xD << 2);
+ reg_val &= ~EMAC_MAC_MCFG_MII_CLKD_MASK;
+ reg_val |= EMAC_MAC_MCFG_MII_CLKD_72;
writel(reg_val, db->membase + EMAC_MAC_MCFG_REG);
/* clear RX counter */
@@ -506,7 +506,7 @@ static void emac_init_device(struct net_device *dev)
/* enable RX/TX0/RX Hlevel interrup */
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0xf << 0) | (0x01 << 8);
+ reg_val |= (EMAC_INT_CTL_TX_EN | EMAC_INT_CTL_TX_ABRT_EN | EMAC_INT_CTL_RX_EN);
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
spin_unlock_irqrestore(&db->lock, flags);
@@ -637,7 +637,9 @@ static void emac_rx(struct net_device *dev)
if (!rxcount) {
db->emacrx_completed_flag = 1;
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0xf << 0) | (0x01 << 8);
+ reg_val |= (EMAC_INT_CTL_TX_EN |
+ EMAC_INT_CTL_TX_ABRT_EN |
+ EMAC_INT_CTL_RX_EN);
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
/* had one stuck? */
@@ -669,7 +671,9 @@ static void emac_rx(struct net_device *dev)
writel(reg_val | EMAC_CTL_RX_EN,
db->membase + EMAC_CTL_REG);
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0xf << 0) | (0x01 << 8);
+ reg_val |= (EMAC_INT_CTL_TX_EN |
+ EMAC_INT_CTL_TX_ABRT_EN |
+ EMAC_INT_CTL_RX_EN);
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
db->emacrx_completed_flag = 1;
@@ -783,20 +787,20 @@ static irqreturn_t emac_interrupt(int irq, void *dev_id)
}
/* Transmit Interrupt check */
- if (int_status & (0x01 | 0x02))
+ if (int_status & EMAC_INT_STA_TX_COMPLETE)
emac_tx_done(dev, db, int_status);
- if (int_status & (0x04 | 0x08))
+ if (int_status & EMAC_INT_STA_TX_ABRT)
netdev_info(dev, " ab : %x\n", int_status);
/* Re-enable interrupt mask */
if (db->emacrx_completed_flag == 1) {
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0xf << 0) | (0x01 << 8);
+ reg_val |= (EMAC_INT_CTL_TX_EN | EMAC_INT_CTL_TX_ABRT_EN | EMAC_INT_CTL_RX_EN);
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
} else {
reg_val = readl(db->membase + EMAC_INT_CTL_REG);
- reg_val |= (0xf << 0);
+ reg_val |= (EMAC_INT_CTL_TX_EN | EMAC_INT_CTL_TX_ABRT_EN);
writel(reg_val, db->membase + EMAC_INT_CTL_REG);
}
@@ -1068,6 +1072,7 @@ static int emac_probe(struct platform_device *pdev)
clk_disable_unprepare(db->clk);
out_dispose_mapping:
irq_dispose_mapping(ndev->irq);
+ dma_release_channel(db->rx_chan);
out_iounmap:
iounmap(db->membase);
out:
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.h b/drivers/net/ethernet/allwinner/sun4i-emac.h
index 38c72d9..90bd9ad 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.h
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.h
@@ -38,6 +38,7 @@
#define EMAC_RX_CTL_REG (0x3c)
#define EMAC_RX_CTL_AUTO_DRQ_EN (1 << 1)
#define EMAC_RX_CTL_DMA_EN (1 << 2)
+#define EMAC_RX_CTL_FLUSH_FIFO (1 << 3)
#define EMAC_RX_CTL_PASS_ALL_EN (1 << 4)
#define EMAC_RX_CTL_PASS_CTL_EN (1 << 5)
#define EMAC_RX_CTL_PASS_CRC_ERR_EN (1 << 6)
@@ -61,7 +62,21 @@
#define EMAC_RX_IO_DATA_STATUS_OK (1 << 7)
#define EMAC_RX_FBC_REG (0x50)
#define EMAC_INT_CTL_REG (0x54)
+#define EMAC_INT_CTL_RX_EN (1 << 8)
+#define EMAC_INT_CTL_TX0_EN (1)
+#define EMAC_INT_CTL_TX1_EN (1 << 1)
+#define EMAC_INT_CTL_TX_EN (EMAC_INT_CTL_TX0_EN | EMAC_INT_CTL_TX1_EN)
+#define EMAC_INT_CTL_TX0_ABRT_EN (0x1 << 2)
+#define EMAC_INT_CTL_TX1_ABRT_EN (0x1 << 3)
+#define EMAC_INT_CTL_TX_ABRT_EN (EMAC_INT_CTL_TX0_ABRT_EN | EMAC_INT_CTL_TX1_ABRT_EN)
#define EMAC_INT_STA_REG (0x58)
+#define EMAC_INT_STA_TX0_COMPLETE (0x1)
+#define EMAC_INT_STA_TX1_COMPLETE (0x1 << 1)
+#define EMAC_INT_STA_TX_COMPLETE (EMAC_INT_STA_TX0_COMPLETE | EMAC_INT_STA_TX1_COMPLETE)
+#define EMAC_INT_STA_TX0_ABRT (0x1 << 2)
+#define EMAC_INT_STA_TX1_ABRT (0x1 << 3)
+#define EMAC_INT_STA_TX_ABRT (EMAC_INT_STA_TX0_ABRT | EMAC_INT_STA_TX1_ABRT)
+#define EMAC_INT_STA_RX_COMPLETE (0x1 << 8)
#define EMAC_MAC_CTL0_REG (0x5c)
#define EMAC_MAC_CTL0_RX_FLOW_CTL_EN (1 << 2)
#define EMAC_MAC_CTL0_TX_FLOW_CTL_EN (1 << 3)
@@ -87,8 +102,11 @@
#define EMAC_MAC_CLRT_RM (0x0f)
#define EMAC_MAC_MAXF_REG (0x70)
#define EMAC_MAC_SUPP_REG (0x74)
+#define EMAC_MAC_SUPP_100M (0x1 << 8)
#define EMAC_MAC_TEST_REG (0x78)
#define EMAC_MAC_MCFG_REG (0x7c)
+#define EMAC_MAC_MCFG_MII_CLKD_MASK (0xff << 2)
+#define EMAC_MAC_MCFG_MII_CLKD_72 (0x0d << 2)
#define EMAC_MAC_A0_REG (0x98)
#define EMAC_MAC_A1_REG (0x9c)
#define EMAC_MAC_A2_REG (0xa0)
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 9a650d1..4d2ba30 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1237,6 +1237,7 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match)
struct bmac_data *bp;
const unsigned char *prop_addr;
unsigned char addr[6];
+ u8 macaddr[6];
struct net_device *dev;
int is_bmac_plus = ((int)match->data) != 0;
@@ -1284,7 +1285,9 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match)
rev = addr[0] == 0 && addr[1] == 0xA0;
for (j = 0; j < 6; ++j)
- dev->dev_addr[j] = rev ? bitrev8(addr[j]): addr[j];
+ macaddr[j] = rev ? bitrev8(addr[j]): addr[j];
+
+ eth_hw_addr_set(dev, macaddr);
/* Enable chip without interrupts for now */
bmac_enable_and_reset_chip(dev);
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index 4b80e3a..6f8c91e 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -90,7 +90,7 @@ static void mace_set_timeout(struct net_device *dev);
static void mace_tx_timeout(struct timer_list *t);
static inline void dbdma_reset(volatile struct dbdma_regs __iomem *dma);
static inline void mace_clean_rings(struct mace_data *mp);
-static void __mace_set_address(struct net_device *dev, void *addr);
+static void __mace_set_address(struct net_device *dev, const void *addr);
/*
* If we can't get a skbuff when we need it, we use this area for DMA.
@@ -112,6 +112,7 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match)
struct net_device *dev;
struct mace_data *mp;
const unsigned char *addr;
+ u8 macaddr[ETH_ALEN];
int j, rev, rc = -EBUSY;
if (macio_resource_count(mdev) != 3 || macio_irq_count(mdev) != 3) {
@@ -167,8 +168,9 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match)
rev = addr[0] == 0 && addr[1] == 0xA0;
for (j = 0; j < 6; ++j) {
- dev->dev_addr[j] = rev ? bitrev8(addr[j]): addr[j];
+ macaddr[j] = rev ? bitrev8(addr[j]): addr[j];
}
+ eth_hw_addr_set(dev, macaddr);
mp->chipid = (in_8(&mp->mace->chipid_hi) << 8) |
in_8(&mp->mace->chipid_lo);
@@ -369,11 +371,12 @@ static void mace_reset(struct net_device *dev)
out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO);
}
-static void __mace_set_address(struct net_device *dev, void *addr)
+static void __mace_set_address(struct net_device *dev, const void *addr)
{
struct mace_data *mp = netdev_priv(dev);
volatile struct mace __iomem *mb = mp->mace;
- unsigned char *p = addr;
+ const unsigned char *p = addr;
+ u8 macaddr[ETH_ALEN];
int i;
/* load up the hardware address */
@@ -385,7 +388,10 @@ static void __mace_set_address(struct net_device *dev, void *addr)
;
}
for (i = 0; i < 6; ++i)
- out_8(&mb->padr, dev->dev_addr[i] = p[i]);
+ out_8(&mb->padr, macaddr[i] = p[i]);
+
+ eth_hw_addr_set(dev, macaddr);
+
if (mp->chipid != BROKEN_ADDRCHG_REV)
out_8(&mb->iac, 0);
}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 226f440..87f1056 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -4020,10 +4020,12 @@ static int bcmgenet_probe(struct platform_device *pdev)
/* Request the WOL interrupt and advertise suspend if available */
priv->wol_irq_disabled = true;
- err = devm_request_irq(&pdev->dev, priv->wol_irq, bcmgenet_wol_isr, 0,
- dev->name, priv);
- if (!err)
- device_set_wakeup_capable(&pdev->dev, 1);
+ if (priv->wol_irq > 0) {
+ err = devm_request_irq(&pdev->dev, priv->wol_irq,
+ bcmgenet_wol_isr, 0, dev->name, priv);
+ if (!err)
+ device_set_wakeup_capable(&pdev->dev, 1);
+ }
/* Set the needed headroom to account for any possible
* features enabling/disabling at runtime
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
index d04a6c1..da8d104 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.c
@@ -32,6 +32,7 @@
#include <linux/tcp.h>
#include <linux/ipv6.h>
+#include <net/inet_ecn.h>
#include <net/route.h>
#include <net/ip6_route.h>
@@ -99,7 +100,7 @@ cxgb_find_route(struct cxgb4_lld_info *lldi,
rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip, local_ip,
peer_port, local_port, IPPROTO_TCP,
- tos, 0);
+ tos & ~INET_ECN_MASK, 0);
if (IS_ERR(rt))
return NULL;
n = dst_neigh_lookup(&rt->dst, &peer_ip);
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index 5b8b9bc..266e562 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -51,6 +51,7 @@ struct tgec_mdio_controller {
struct mdio_fsl_priv {
struct tgec_mdio_controller __iomem *mdio_base;
bool is_little_endian;
+ bool has_a009885;
bool has_a011043;
};
@@ -186,10 +187,10 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
{
struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv;
struct tgec_mdio_controller __iomem *regs = priv->mdio_base;
+ unsigned long flags;
uint16_t dev_addr;
uint32_t mdio_stat;
uint32_t mdio_ctl;
- uint16_t value;
int ret;
bool endian = priv->is_little_endian;
@@ -221,12 +222,18 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
return ret;
}
+ if (priv->has_a009885)
+ /* Once the operation completes, i.e. MDIO_STAT_BSY clears, we
+ * must read back the data register within 16 MDC cycles.
+ */
+ local_irq_save(flags);
+
/* Initiate the read */
xgmac_write32(mdio_ctl | MDIO_CTL_READ, ®s->mdio_ctl, endian);
ret = xgmac_wait_until_done(&bus->dev, regs, endian);
if (ret)
- return ret;
+ goto irq_restore;
/* Return all Fs if nothing was there */
if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) &&
@@ -234,13 +241,17 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
dev_dbg(&bus->dev,
"Error while reading PHY%d reg at %d.%hhu\n",
phy_id, dev_addr, regnum);
- return 0xffff;
+ ret = 0xffff;
+ } else {
+ ret = xgmac_read32(®s->mdio_data, endian) & 0xffff;
+ dev_dbg(&bus->dev, "read %04x\n", ret);
}
- value = xgmac_read32(®s->mdio_data, endian) & 0xffff;
- dev_dbg(&bus->dev, "read %04x\n", value);
+irq_restore:
+ if (priv->has_a009885)
+ local_irq_restore(flags);
- return value;
+ return ret;
}
static int xgmac_mdio_probe(struct platform_device *pdev)
@@ -287,6 +298,8 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
priv->is_little_endian = device_property_read_bool(&pdev->dev,
"little-endian");
+ priv->has_a009885 = device_property_read_bool(&pdev->dev,
+ "fsl,erratum-a009885");
priv->has_a011043 = device_property_read_bool(&pdev->dev,
"fsl,erratum-a011043");
@@ -318,9 +331,10 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
static int xgmac_mdio_remove(struct platform_device *pdev)
{
struct mii_bus *bus = platform_get_drvdata(pdev);
+ struct mdio_fsl_priv *priv = bus->priv;
mdiobus_unregister(bus);
- iounmap(bus->priv);
+ iounmap(priv->mdio_base);
mdiobus_free(bus);
return 0;
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index 27937c5..daec9ce 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -117,9 +117,10 @@ static int sni_82596_probe(struct platform_device *dev)
netdevice->dev_addr[5] = readb(eth_addr + 0x06);
iounmap(eth_addr);
- if (!netdevice->irq) {
+ if (netdevice->irq < 0) {
printk(KERN_ERR "%s: IRQ not found for i82596 at 0x%lx\n",
__FILE__, netdevice->base_addr);
+ retval = netdevice->irq;
goto probe_failed;
}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera.h b/drivers/net/ethernet/marvell/prestera/prestera.h
index a0a5a8e..2fd9ef2 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera.h
@@ -283,7 +283,6 @@ struct prestera_router {
struct list_head rif_entry_list;
struct notifier_block inetaddr_nb;
struct notifier_block inetaddr_valid_nb;
- bool aborted;
};
struct prestera_rxtx_params {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
index 51fc841..e6bfadc 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
@@ -1831,8 +1831,8 @@ static int prestera_iface_to_msg(struct prestera_iface *iface,
int prestera_hw_rif_create(struct prestera_switch *sw,
struct prestera_iface *iif, u8 *mac, u16 *rif_id)
{
- struct prestera_msg_rif_req req;
struct prestera_msg_rif_resp resp;
+ struct prestera_msg_rif_req req;
int err;
memcpy(req.mac, mac, ETH_ALEN);
@@ -1868,9 +1868,9 @@ int prestera_hw_rif_delete(struct prestera_switch *sw, u16 rif_id,
int prestera_hw_vr_create(struct prestera_switch *sw, u16 *vr_id)
{
- int err;
struct prestera_msg_vr_resp resp;
struct prestera_msg_vr_req req;
+ int err;
err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ROUTER_VR_CREATE,
&req.cmd, sizeof(req), &resp.ret, sizeof(resp));
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 08fdd1e..cad93f7 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -982,6 +982,7 @@ static void prestera_switch_fini(struct prestera_switch *sw)
prestera_event_handlers_unregister(sw);
prestera_rxtx_switch_fini(sw);
prestera_switchdev_fini(sw);
+ prestera_router_fini(sw);
prestera_netdev_event_handler_unregister(sw);
prestera_hw_switch_fini(sw);
}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c
index 8a3b7b6..6ef4d32 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_router.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c
@@ -25,10 +25,10 @@ static int __prestera_inetaddr_port_event(struct net_device *port_dev,
struct netlink_ext_ack *extack)
{
struct prestera_port *port = netdev_priv(port_dev);
- int err;
- struct prestera_rif_entry *re;
struct prestera_rif_entry_key re_key = {};
+ struct prestera_rif_entry *re;
u32 kern_tb_id;
+ int err;
err = prestera_is_valid_mac_addr(port, port_dev->dev_addr);
if (err) {
@@ -45,21 +45,21 @@ static int __prestera_inetaddr_port_event(struct net_device *port_dev,
switch (event) {
case NETDEV_UP:
if (re) {
- NL_SET_ERR_MSG_MOD(extack, "rif_entry already exist");
+ NL_SET_ERR_MSG_MOD(extack, "RIF already exist");
return -EEXIST;
}
re = prestera_rif_entry_create(port->sw, &re_key,
prestera_fix_tb_id(kern_tb_id),
port_dev->dev_addr);
if (!re) {
- NL_SET_ERR_MSG_MOD(extack, "Can't create rif_entry");
+ NL_SET_ERR_MSG_MOD(extack, "Can't create RIF");
return -EINVAL;
}
dev_hold(port_dev);
break;
case NETDEV_DOWN:
if (!re) {
- NL_SET_ERR_MSG_MOD(extack, "rif_entry not exist");
+ NL_SET_ERR_MSG_MOD(extack, "Can't find RIF");
return -EEXIST;
}
prestera_rif_entry_destroy(port->sw, re);
@@ -75,11 +75,11 @@ static int __prestera_inetaddr_event(struct prestera_switch *sw,
unsigned long event,
struct netlink_ext_ack *extack)
{
- if (prestera_netdev_check(dev) && !netif_is_bridge_port(dev) &&
- !netif_is_lag_port(dev) && !netif_is_ovs_port(dev))
- return __prestera_inetaddr_port_event(dev, event, extack);
+ if (!prestera_netdev_check(dev) || netif_is_bridge_port(dev) ||
+ netif_is_lag_port(dev) || netif_is_ovs_port(dev))
+ return 0;
- return 0;
+ return __prestera_inetaddr_port_event(dev, event, extack);
}
static int __prestera_inetaddr_cb(struct notifier_block *nb,
@@ -126,6 +126,8 @@ static int __prestera_inetaddr_valid_cb(struct notifier_block *nb,
goto out;
if (ipv4_is_multicast(ivi->ivi_addr)) {
+ NL_SET_ERR_MSG_MOD(ivi->extack,
+ "Multicast addr on RIF is not supported");
err = -EINVAL;
goto out;
}
@@ -166,7 +168,7 @@ int prestera_router_init(struct prestera_switch *sw)
err_register_inetaddr_notifier:
unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb);
err_register_inetaddr_validator_notifier:
- /* prestera_router_hw_fini */
+ prestera_router_hw_fini(sw);
err_router_lib_init:
kfree(sw->router);
return err;
@@ -176,7 +178,7 @@ void prestera_router_fini(struct prestera_switch *sw)
{
unregister_inetaddr_notifier(&sw->router->inetaddr_nb);
unregister_inetaddr_validator_notifier(&sw->router->inetaddr_valid_nb);
- /* router_hw_fini */
+ prestera_router_hw_fini(sw);
kfree(sw->router);
sw->router = NULL;
}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c
index 5866a4b..e5592b6 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c
@@ -29,6 +29,12 @@ int prestera_router_hw_init(struct prestera_switch *sw)
return 0;
}
+void prestera_router_hw_fini(struct prestera_switch *sw)
+{
+ WARN_ON(!list_empty(&sw->router->vr_list));
+ WARN_ON(!list_empty(&sw->router->rif_entry_list));
+}
+
static struct prestera_vr *__prestera_vr_find(struct prestera_switch *sw,
u32 tb_id)
{
@@ -47,13 +53,8 @@ static struct prestera_vr *__prestera_vr_create(struct prestera_switch *sw,
struct netlink_ext_ack *extack)
{
struct prestera_vr *vr;
- u16 hw_vr_id;
int err;
- err = prestera_hw_vr_create(sw, &hw_vr_id);
- if (err)
- return ERR_PTR(-ENOMEM);
-
vr = kzalloc(sizeof(*vr), GFP_KERNEL);
if (!vr) {
err = -ENOMEM;
@@ -61,23 +62,26 @@ static struct prestera_vr *__prestera_vr_create(struct prestera_switch *sw,
}
vr->tb_id = tb_id;
- vr->hw_vr_id = hw_vr_id;
+
+ err = prestera_hw_vr_create(sw, &vr->hw_vr_id);
+ if (err)
+ goto err_hw_create;
list_add(&vr->router_node, &sw->router->vr_list);
return vr;
-err_alloc_vr:
- prestera_hw_vr_delete(sw, hw_vr_id);
+err_hw_create:
kfree(vr);
+err_alloc_vr:
return ERR_PTR(err);
}
static void __prestera_vr_destroy(struct prestera_switch *sw,
struct prestera_vr *vr)
{
- prestera_hw_vr_delete(sw, vr->hw_vr_id);
list_del(&vr->router_node);
+ prestera_hw_vr_delete(sw, vr->hw_vr_id);
kfree(vr);
}
@@ -87,17 +91,22 @@ static struct prestera_vr *prestera_vr_get(struct prestera_switch *sw, u32 tb_id
struct prestera_vr *vr;
vr = __prestera_vr_find(sw, tb_id);
- if (!vr)
+ if (vr) {
+ refcount_inc(&vr->refcount);
+ } else {
vr = __prestera_vr_create(sw, tb_id, extack);
- if (IS_ERR(vr))
- return ERR_CAST(vr);
+ if (IS_ERR(vr))
+ return ERR_CAST(vr);
+
+ refcount_set(&vr->refcount, 1);
+ }
return vr;
}
static void prestera_vr_put(struct prestera_switch *sw, struct prestera_vr *vr)
{
- if (!vr->ref_cnt)
+ if (refcount_dec_and_test(&vr->refcount))
__prestera_vr_destroy(sw, vr);
}
@@ -120,7 +129,7 @@ __prestera_rif_entry_key_copy(const struct prestera_rif_entry_key *in,
out->iface.vlan_id = in->iface.vlan_id;
break;
default:
- pr_err("Unsupported iface type");
+ WARN(1, "Unsupported iface type");
return -EINVAL;
}
@@ -158,7 +167,6 @@ void prestera_rif_entry_destroy(struct prestera_switch *sw,
iface.vr_id = e->vr->hw_vr_id;
prestera_hw_rif_delete(sw, e->hw_id, &iface);
- e->vr->ref_cnt--;
prestera_vr_put(sw, e->vr);
kfree(e);
}
@@ -183,7 +191,6 @@ prestera_rif_entry_create(struct prestera_switch *sw,
if (IS_ERR(e->vr))
goto err_vr_get;
- e->vr->ref_cnt++;
memcpy(&e->addr, addr, sizeof(e->addr));
/* HW */
@@ -198,7 +205,6 @@ prestera_rif_entry_create(struct prestera_switch *sw,
return e;
err_hw_create:
- e->vr->ref_cnt--;
prestera_vr_put(sw, e->vr);
err_vr_get:
err_key_copy:
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.h b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.h
index fed5359..b6b0285 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.h
@@ -6,7 +6,7 @@
struct prestera_vr {
struct list_head router_node;
- unsigned int ref_cnt;
+ refcount_t refcount;
u32 tb_id; /* key (kernel fib table id) */
u16 hw_vr_id; /* virtual router ID */
u8 __pad[2];
@@ -32,5 +32,6 @@ prestera_rif_entry_create(struct prestera_switch *sw,
struct prestera_rif_entry_key *k,
u32 tb_id, const unsigned char *addr);
int prestera_router_hw_init(struct prestera_switch *sw);
+void prestera_router_hw_fini(struct prestera_switch *sw);
#endif /* _PRESTERA_ROUTER_HW_H_ */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index b67b432..f02d07e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -267,7 +267,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
phylink_config);
struct mtk_eth *eth = mac->hw;
u32 mcr_cur, mcr_new, sid, i;
- int val, ge_mode, err;
+ int val, ge_mode, err = 0;
/* MT76x8 has no hardware settings between for the MAC */
if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628) &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 3381524..378fc8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/* Copyright (c) 2018 Mellanox Technologies. */
+#include <net/inet_ecn.h>
#include <net/vxlan.h>
#include <net/gre.h>
#include <net/geneve.h>
@@ -235,7 +236,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
int err;
/* add the IP fields */
- attr.fl.fl4.flowi4_tos = tun_key->tos;
+ attr.fl.fl4.flowi4_tos = tun_key->tos & ~INET_ECN_MASK;
attr.fl.fl4.daddr = tun_key->u.ipv4.dst;
attr.fl.fl4.saddr = tun_key->u.ipv4.src;
attr.ttl = tun_key->ttl;
@@ -350,7 +351,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
int err;
/* add the IP fields */
- attr.fl.fl4.flowi4_tos = tun_key->tos;
+ attr.fl.fl4.flowi4_tos = tun_key->tos & ~INET_ECN_MASK;
attr.fl.fl4.daddr = tun_key->u.ipv4.dst;
attr.fl.fl4.saddr = tun_key->u.ipv4.src;
attr.ttl = tun_key->ttl;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index b1311b6..455293a 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -771,7 +771,10 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port,
ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
- ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, tx_pause);
+ /* Don't attempt to send PAUSE frames on the NPI port, it's broken */
+ if (port != ocelot->npi)
+ ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA,
+ tx_pause);
/* Undo the effects of ocelot_phylink_mac_link_down:
* enable MAC module
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index beb9379..9498588 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -559,13 +559,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
return -EOPNOTSUPP;
}
- if (filter->block_id == VCAP_IS1 &&
- !is_zero_ether_addr(match.mask->dst)) {
- NL_SET_ERR_MSG_MOD(extack,
- "Key type S1_NORMAL cannot match on destination MAC");
- return -EOPNOTSUPP;
- }
-
/* The hw support mac matches only for MAC_ETYPE key,
* therefore if other matches(port, tcp flags, etc) are added
* then just bail out
@@ -580,6 +573,14 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
return -EOPNOTSUPP;
flow_rule_match_eth_addrs(rule, &match);
+
+ if (filter->block_id == VCAP_IS1 &&
+ !is_zero_ether_addr(match.mask->dst)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Key type S1_NORMAL cannot match on destination MAC");
+ return -EOPNOTSUPP;
+ }
+
filter->key_type = OCELOT_VCAP_KEY_ETYPE;
ether_addr_copy(filter->key.etype.dmac.value,
match.key->dst);
@@ -805,13 +806,34 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port,
struct netlink_ext_ack *extack = f->common.extack;
struct ocelot_vcap_filter *filter;
int chain = f->common.chain_index;
- int ret;
+ int block_id, ret;
if (chain && !ocelot_find_vcap_filter_that_points_at(ocelot, chain)) {
NL_SET_ERR_MSG_MOD(extack, "No default GOTO action points to this chain");
return -EOPNOTSUPP;
}
+ block_id = ocelot_chain_to_block(chain, ingress);
+ if (block_id < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot offload to this chain");
+ return -EOPNOTSUPP;
+ }
+
+ filter = ocelot_vcap_block_find_filter_by_id(&ocelot->block[block_id],
+ f->cookie, true);
+ if (filter) {
+ /* Filter already exists on other ports */
+ if (!ingress) {
+ NL_SET_ERR_MSG_MOD(extack, "VCAP ES0 does not support shared filters");
+ return -EOPNOTSUPP;
+ }
+
+ filter->ingress_port_mask |= BIT(port);
+
+ return ocelot_vcap_filter_replace(ocelot, filter);
+ }
+
+ /* Filter didn't exist, create it now */
filter = ocelot_vcap_filter_create(ocelot, port, ingress, f);
if (!filter)
return -ENOMEM;
@@ -874,6 +896,12 @@ int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port,
if (filter->type == OCELOT_VCAP_FILTER_DUMMY)
return ocelot_vcap_dummy_filter_del(ocelot, filter);
+ if (ingress) {
+ filter->ingress_port_mask &= ~BIT(port);
+ if (filter->ingress_port_mask)
+ return ocelot_vcap_filter_replace(ocelot, filter);
+ }
+
return ocelot_vcap_filter_del(ocelot, filter);
}
EXPORT_SYMBOL_GPL(ocelot_cls_flower_destroy);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 8115c3d..e271b62 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -1187,7 +1187,7 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
ocelot_port_bridge_join(ocelot, port, bridge);
err = switchdev_bridge_port_offload(brport_dev, dev, priv,
- &ocelot_netdevice_nb,
+ &ocelot_switchdev_nb,
&ocelot_switchdev_blocking_nb,
false, extack);
if (err)
@@ -1201,7 +1201,7 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
err_switchdev_sync:
switchdev_bridge_port_unoffload(brport_dev, priv,
- &ocelot_netdevice_nb,
+ &ocelot_switchdev_nb,
&ocelot_switchdev_blocking_nb);
err_switchdev_offload:
ocelot_port_bridge_leave(ocelot, port, bridge);
@@ -1214,7 +1214,7 @@ static void ocelot_netdevice_pre_bridge_leave(struct net_device *dev,
struct ocelot_port_private *priv = netdev_priv(dev);
switchdev_bridge_port_unoffload(brport_dev, priv,
- &ocelot_netdevice_nb,
+ &ocelot_switchdev_nb,
&ocelot_switchdev_blocking_nb);
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
index adfeb8d..62a69a9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
@@ -12,6 +12,7 @@
#include <linux/io.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/mfd/syscon.h>
@@ -48,16 +49,75 @@
#define DWMAC_RX_VARDELAY(d) ((d) << DWMAC_RX_VARDELAY_SHIFT)
#define DWMAC_RXN_VARDELAY(d) ((d) << DWMAC_RXN_VARDELAY_SHIFT)
+struct oxnas_dwmac;
+
+struct oxnas_dwmac_data {
+ int (*setup)(struct oxnas_dwmac *dwmac);
+};
+
struct oxnas_dwmac {
struct device *dev;
struct clk *clk;
struct regmap *regmap;
+ const struct oxnas_dwmac_data *data;
};
+static int oxnas_dwmac_setup_ox810se(struct oxnas_dwmac *dwmac)
+{
+ unsigned int value;
+ int ret;
+
+ ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
+ if (ret < 0)
+ return ret;
+
+ /* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
+ value |= BIT(DWMAC_CKEN_GTX) |
+ /* Use simple mux for 25/125 Mhz clock switching */
+ BIT(DWMAC_SIMPLE_MUX);
+
+ regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
+
+ return 0;
+}
+
+static int oxnas_dwmac_setup_ox820(struct oxnas_dwmac *dwmac)
+{
+ unsigned int value;
+ int ret;
+
+ ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
+ if (ret < 0)
+ return ret;
+
+ /* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
+ value |= BIT(DWMAC_CKEN_GTX) |
+ /* Use simple mux for 25/125 Mhz clock switching */
+ BIT(DWMAC_SIMPLE_MUX) |
+ /* set auto switch tx clock source */
+ BIT(DWMAC_AUTO_TX_SOURCE) |
+ /* enable tx & rx vardelay */
+ BIT(DWMAC_CKEN_TX_OUT) |
+ BIT(DWMAC_CKEN_TXN_OUT) |
+ BIT(DWMAC_CKEN_TX_IN) |
+ BIT(DWMAC_CKEN_RX_OUT) |
+ BIT(DWMAC_CKEN_RXN_OUT) |
+ BIT(DWMAC_CKEN_RX_IN);
+ regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
+
+ /* set tx & rx vardelay */
+ value = DWMAC_TX_VARDELAY(4) |
+ DWMAC_TXN_VARDELAY(2) |
+ DWMAC_RX_VARDELAY(10) |
+ DWMAC_RXN_VARDELAY(8);
+ regmap_write(dwmac->regmap, OXNAS_DWMAC_DELAY_REGOFFSET, value);
+
+ return 0;
+}
+
static int oxnas_dwmac_init(struct platform_device *pdev, void *priv)
{
struct oxnas_dwmac *dwmac = priv;
- unsigned int value;
int ret;
/* Reset HW here before changing the glue configuration */
@@ -69,35 +129,11 @@ static int oxnas_dwmac_init(struct platform_device *pdev, void *priv)
if (ret)
return ret;
- ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
- if (ret < 0) {
+ ret = dwmac->data->setup(dwmac);
+ if (ret)
clk_disable_unprepare(dwmac->clk);
- return ret;
- }
- /* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
- value |= BIT(DWMAC_CKEN_GTX) |
- /* Use simple mux for 25/125 Mhz clock switching */
- BIT(DWMAC_SIMPLE_MUX) |
- /* set auto switch tx clock source */
- BIT(DWMAC_AUTO_TX_SOURCE) |
- /* enable tx & rx vardelay */
- BIT(DWMAC_CKEN_TX_OUT) |
- BIT(DWMAC_CKEN_TXN_OUT) |
- BIT(DWMAC_CKEN_TX_IN) |
- BIT(DWMAC_CKEN_RX_OUT) |
- BIT(DWMAC_CKEN_RXN_OUT) |
- BIT(DWMAC_CKEN_RX_IN);
- regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
-
- /* set tx & rx vardelay */
- value = DWMAC_TX_VARDELAY(4) |
- DWMAC_TXN_VARDELAY(2) |
- DWMAC_RX_VARDELAY(10) |
- DWMAC_RXN_VARDELAY(8);
- regmap_write(dwmac->regmap, OXNAS_DWMAC_DELAY_REGOFFSET, value);
-
- return 0;
+ return ret;
}
static void oxnas_dwmac_exit(struct platform_device *pdev, void *priv)
@@ -128,6 +164,12 @@ static int oxnas_dwmac_probe(struct platform_device *pdev)
goto err_remove_config_dt;
}
+ dwmac->data = (const struct oxnas_dwmac_data *)of_device_get_match_data(&pdev->dev);
+ if (!dwmac->data) {
+ ret = -EINVAL;
+ goto err_remove_config_dt;
+ }
+
dwmac->dev = &pdev->dev;
plat_dat->bsp_priv = dwmac;
plat_dat->init = oxnas_dwmac_init;
@@ -166,8 +208,23 @@ static int oxnas_dwmac_probe(struct platform_device *pdev)
return ret;
}
+static const struct oxnas_dwmac_data ox810se_dwmac_data = {
+ .setup = oxnas_dwmac_setup_ox810se,
+};
+
+static const struct oxnas_dwmac_data ox820_dwmac_data = {
+ .setup = oxnas_dwmac_setup_ox820,
+};
+
static const struct of_device_id oxnas_dwmac_match[] = {
- { .compatible = "oxsemi,ox820-dwmac" },
+ {
+ .compatible = "oxsemi,ox810se-dwmac",
+ .data = &ox810se_dwmac_data,
+ },
+ {
+ .compatible = "oxsemi,ox820-dwmac",
+ .data = &ox820_dwmac_data,
+ },
{ }
};
MODULE_DEVICE_TABLE(of, oxnas_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 63ff2da..6708ca2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7159,7 +7159,8 @@ int stmmac_dvr_probe(struct device *device,
pm_runtime_get_noresume(device);
pm_runtime_set_active(device);
- pm_runtime_enable(device);
+ if (!pm_runtime_enabled(device))
+ pm_runtime_enable(device);
if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 33142d5..03575c0 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -349,7 +349,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
struct cpsw_common *cpsw = ndev_to_cpsw(xmeta->ndev);
int pkt_size = cpsw->rx_packet_max;
int ret = 0, port, ch = xmeta->ch;
- int headroom = CPSW_HEADROOM;
+ int headroom = CPSW_HEADROOM_NA;
struct net_device *ndev = xmeta->ndev;
struct cpsw_priv *priv;
struct page_pool *pool;
@@ -392,7 +392,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
}
if (priv->xdp_prog) {
- int headroom = CPSW_HEADROOM, size = len;
+ int size = len;
xdp_init_buff(&xdp, PAGE_SIZE, &priv->xdp_rxq[ch]);
if (status & CPDMA_RX_VLAN_ENCAP) {
@@ -442,7 +442,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
xmeta->ndev = ndev;
xmeta->ch = ch;
- dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+ dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM_NA;
ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
pkt_size, 0);
if (ret < 0) {
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 279e261..bd4b152 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -283,7 +283,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
{
struct page *new_page, *page = token;
void *pa = page_address(page);
- int headroom = CPSW_HEADROOM;
+ int headroom = CPSW_HEADROOM_NA;
struct cpsw_meta_xdp *xmeta;
struct cpsw_common *cpsw;
struct net_device *ndev;
@@ -336,7 +336,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
}
if (priv->xdp_prog) {
- int headroom = CPSW_HEADROOM, size = len;
+ int size = len;
xdp_init_buff(&xdp, PAGE_SIZE, &priv->xdp_rxq[ch]);
if (status & CPDMA_RX_VLAN_ENCAP) {
@@ -386,7 +386,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
xmeta->ndev = ndev;
xmeta->ch = ch;
- dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+ dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM_NA;
ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
pkt_size, 0);
if (ret < 0) {
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 3537502..ba22059 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1122,7 +1122,7 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv)
xmeta->ndev = priv->ndev;
xmeta->ch = ch;
- dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+ dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM_NA;
ret = cpdma_chan_idle_submit_mapped(cpsw->rxv[ch].ch,
page, dma,
cpsw->rx_packet_max,
diff --git a/drivers/net/ethernet/vertexcom/Kconfig b/drivers/net/ethernet/vertexcom/Kconfig
index 6e2cf06..4184a63 100644
--- a/drivers/net/ethernet/vertexcom/Kconfig
+++ b/drivers/net/ethernet/vertexcom/Kconfig
@@ -5,7 +5,7 @@
config NET_VENDOR_VERTEXCOM
bool "Vertexcom devices"
- default n
+ default y
help
If you have a network (Ethernet) card belonging to this class, say Y.
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 23ac353..377c94e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -41,8 +41,9 @@
#include "xilinx_axienet.h"
/* Descriptors defines for Tx and Rx DMA */
-#define TX_BD_NUM_DEFAULT 64
+#define TX_BD_NUM_DEFAULT 128
#define RX_BD_NUM_DEFAULT 1024
+#define TX_BD_NUM_MIN (MAX_SKB_FRAGS + 1)
#define TX_BD_NUM_MAX 4096
#define RX_BD_NUM_MAX 4096
@@ -496,7 +497,8 @@ static void axienet_setoptions(struct net_device *ndev, u32 options)
static int __axienet_device_reset(struct axienet_local *lp)
{
- u32 timeout;
+ u32 value;
+ int ret;
/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
* process of Axi DMA takes a while to complete as all pending
@@ -506,15 +508,23 @@ static int __axienet_device_reset(struct axienet_local *lp)
* they both reset the entire DMA core, so only one needs to be used.
*/
axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, XAXIDMA_CR_RESET_MASK);
- timeout = DELAY_OF_ONE_MILLISEC;
- while (axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET) &
- XAXIDMA_CR_RESET_MASK) {
- udelay(1);
- if (--timeout == 0) {
- netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
- __func__);
- return -ETIMEDOUT;
- }
+ ret = read_poll_timeout(axienet_dma_in32, value,
+ !(value & XAXIDMA_CR_RESET_MASK),
+ DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+ XAXIDMA_TX_CR_OFFSET);
+ if (ret) {
+ dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__);
+ return ret;
+ }
+
+ /* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */
+ ret = read_poll_timeout(axienet_ior, value,
+ value & XAE_INT_PHYRSTCMPLT_MASK,
+ DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+ XAE_IS_OFFSET);
+ if (ret) {
+ dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__);
+ return ret;
}
return 0;
@@ -623,6 +633,8 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
if (nr_bds == -1 && !(status & XAXIDMA_BD_STS_COMPLETE_MASK))
break;
+ /* Ensure we see complete descriptor update */
+ dma_rmb();
phys = desc_get_phys_addr(lp, cur_p);
dma_unmap_single(ndev->dev.parent, phys,
(cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
@@ -631,13 +643,15 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
dev_consume_skb_irq(cur_p->skb);
- cur_p->cntrl = 0;
cur_p->app0 = 0;
cur_p->app1 = 0;
cur_p->app2 = 0;
cur_p->app4 = 0;
- cur_p->status = 0;
cur_p->skb = NULL;
+ /* ensure our transmit path and device don't prematurely see status cleared */
+ wmb();
+ cur_p->cntrl = 0;
+ cur_p->status = 0;
if (sizep)
*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
@@ -647,6 +661,32 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
}
/**
+ * axienet_check_tx_bd_space - Checks if a BD/group of BDs are currently busy
+ * @lp: Pointer to the axienet_local structure
+ * @num_frag: The number of BDs to check for
+ *
+ * Return: 0, on success
+ * NETDEV_TX_BUSY, if any of the descriptors are not free
+ *
+ * This function is invoked before BDs are allocated and transmission starts.
+ * This function returns 0 if a BD or group of BDs can be allocated for
+ * transmission. If the BD or any of the BDs are not free the function
+ * returns a busy status. This is invoked from axienet_start_xmit.
+ */
+static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
+ int num_frag)
+{
+ struct axidma_bd *cur_p;
+
+ /* Ensure we see all descriptor updates from device or TX IRQ path */
+ rmb();
+ cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
+ if (cur_p->cntrl)
+ return NETDEV_TX_BUSY;
+ return 0;
+}
+
+/**
* axienet_start_xmit_done - Invoked once a transmit is completed by the
* Axi DMA Tx channel.
* @ndev: Pointer to the net_device structure
@@ -675,30 +715,8 @@ static void axienet_start_xmit_done(struct net_device *ndev)
/* Matches barrier in axienet_start_xmit */
smp_mb();
- netif_wake_queue(ndev);
-}
-
-/**
- * axienet_check_tx_bd_space - Checks if a BD/group of BDs are currently busy
- * @lp: Pointer to the axienet_local structure
- * @num_frag: The number of BDs to check for
- *
- * Return: 0, on success
- * NETDEV_TX_BUSY, if any of the descriptors are not free
- *
- * This function is invoked before BDs are allocated and transmission starts.
- * This function returns 0 if a BD or group of BDs can be allocated for
- * transmission. If the BD or any of the BDs are not free the function
- * returns a busy status. This is invoked from axienet_start_xmit.
- */
-static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
- int num_frag)
-{
- struct axidma_bd *cur_p;
- cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
- if (cur_p->status & XAXIDMA_BD_STS_ALL_MASK)
- return NETDEV_TX_BUSY;
- return 0;
+ if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+ netif_wake_queue(ndev);
}
/**
@@ -730,20 +748,15 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
num_frag = skb_shinfo(skb)->nr_frags;
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
- if (axienet_check_tx_bd_space(lp, num_frag)) {
- if (netif_queue_stopped(ndev))
- return NETDEV_TX_BUSY;
-
+ if (axienet_check_tx_bd_space(lp, num_frag + 1)) {
+ /* Should not happen as last start_xmit call should have
+ * checked for sufficient space and queue should only be
+ * woken when sufficient space is available.
+ */
netif_stop_queue(ndev);
-
- /* Matches barrier in axienet_start_xmit_done */
- smp_mb();
-
- /* Space might have just been freed - check again */
- if (axienet_check_tx_bd_space(lp, num_frag))
- return NETDEV_TX_BUSY;
-
- netif_wake_queue(ndev);
+ if (net_ratelimit())
+ netdev_warn(ndev, "TX ring unexpectedly full\n");
+ return NETDEV_TX_BUSY;
}
if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -804,6 +817,18 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
if (++lp->tx_bd_tail >= lp->tx_bd_num)
lp->tx_bd_tail = 0;
+ /* Stop queue if next transmit may not have space */
+ if (axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
+ netif_stop_queue(ndev);
+
+ /* Matches barrier in axienet_start_xmit_done */
+ smp_mb();
+
+ /* Space might have just been freed - check again */
+ if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+ netif_wake_queue(ndev);
+ }
+
return NETDEV_TX_OK;
}
@@ -834,6 +859,8 @@ static void axienet_recv(struct net_device *ndev)
tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
+ /* Ensure we see complete descriptor update */
+ dma_rmb();
phys = desc_get_phys_addr(lp, cur_p);
dma_unmap_single(ndev->dev.parent, phys, lp->max_frm_size,
DMA_FROM_DEVICE);
@@ -1352,7 +1379,8 @@ axienet_ethtools_set_ringparam(struct net_device *ndev,
if (ering->rx_pending > RX_BD_NUM_MAX ||
ering->rx_mini_pending ||
ering->rx_jumbo_pending ||
- ering->rx_pending > TX_BD_NUM_MAX)
+ ering->tx_pending < TX_BD_NUM_MIN ||
+ ering->tx_pending > TX_BD_NUM_MAX)
return -EINVAL;
if (netif_running(ndev))
@@ -2027,6 +2055,11 @@ static int axienet_probe(struct platform_device *pdev)
lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
+ /* Reset core now that clocks are enabled, prior to accessing MDIO */
+ ret = __axienet_device_reset(lp);
+ if (ret)
+ goto cleanup_clk;
+
lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
if (lp->phy_node) {
ret = axienet_mdio_setup(lp);
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 49d9a07..68291a3 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -1080,27 +1080,38 @@ static void ipa_endpoint_replenish(struct ipa_endpoint *endpoint, bool add_one)
{
struct gsi *gsi;
u32 backlog;
+ int delta;
- if (!endpoint->replenish_enabled) {
+ if (!test_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags)) {
if (add_one)
atomic_inc(&endpoint->replenish_saved);
return;
}
+ /* If already active, just update the backlog */
+ if (test_and_set_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags)) {
+ if (add_one)
+ atomic_inc(&endpoint->replenish_backlog);
+ return;
+ }
+
while (atomic_dec_not_zero(&endpoint->replenish_backlog))
if (ipa_endpoint_replenish_one(endpoint))
goto try_again_later;
+
+ clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags);
+
if (add_one)
atomic_inc(&endpoint->replenish_backlog);
return;
try_again_later:
- /* The last one didn't succeed, so fix the backlog */
- backlog = atomic_inc_return(&endpoint->replenish_backlog);
+ clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags);
- if (add_one)
- atomic_inc(&endpoint->replenish_backlog);
+ /* The last one didn't succeed, so fix the backlog */
+ delta = add_one ? 2 : 1;
+ backlog = atomic_add_return(delta, &endpoint->replenish_backlog);
/* Whenever a receive buffer transaction completes we'll try to
* replenish again. It's unlikely, but if we fail to supply even
@@ -1120,7 +1131,7 @@ static void ipa_endpoint_replenish_enable(struct ipa_endpoint *endpoint)
u32 max_backlog;
u32 saved;
- endpoint->replenish_enabled = true;
+ set_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags);
while ((saved = atomic_xchg(&endpoint->replenish_saved, 0)))
atomic_add(saved, &endpoint->replenish_backlog);
@@ -1134,7 +1145,7 @@ static void ipa_endpoint_replenish_disable(struct ipa_endpoint *endpoint)
{
u32 backlog;
- endpoint->replenish_enabled = false;
+ clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags);
while ((backlog = atomic_xchg(&endpoint->replenish_backlog, 0)))
atomic_add(backlog, &endpoint->replenish_saved);
}
@@ -1691,7 +1702,8 @@ static void ipa_endpoint_setup_one(struct ipa_endpoint *endpoint)
/* RX transactions require a single TRE, so the maximum
* backlog is the same as the maximum outstanding TREs.
*/
- endpoint->replenish_enabled = false;
+ clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags);
+ clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags);
atomic_set(&endpoint->replenish_saved,
gsi_channel_tre_max(gsi, endpoint->channel_id));
atomic_set(&endpoint->replenish_backlog, 0);
diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h
index 0a859d1..0313cdc 100644
--- a/drivers/net/ipa/ipa_endpoint.h
+++ b/drivers/net/ipa/ipa_endpoint.h
@@ -41,6 +41,19 @@ enum ipa_endpoint_name {
#define IPA_ENDPOINT_MAX 32 /* Max supported by driver */
/**
+ * enum ipa_replenish_flag: RX buffer replenish flags
+ *
+ * @IPA_REPLENISH_ENABLED: Whether receive buffer replenishing is enabled
+ * @IPA_REPLENISH_ACTIVE: Whether replenishing is underway
+ * @IPA_REPLENISH_COUNT: Number of defined replenish flags
+ */
+enum ipa_replenish_flag {
+ IPA_REPLENISH_ENABLED,
+ IPA_REPLENISH_ACTIVE,
+ IPA_REPLENISH_COUNT, /* Number of flags (must be last) */
+};
+
+/**
* struct ipa_endpoint - IPA endpoint information
* @ipa: IPA pointer
* @ee_id: Execution environmnent endpoint is associated with
@@ -51,7 +64,7 @@ enum ipa_endpoint_name {
* @trans_tre_max: Maximum number of TRE descriptors per transaction
* @evt_ring_id: GSI event ring used by the endpoint
* @netdev: Network device pointer, if endpoint uses one
- * @replenish_enabled: Whether receive buffer replenishing is enabled
+ * @replenish_flags: Replenishing state flags
* @replenish_ready: Number of replenish transactions without doorbell
* @replenish_saved: Replenish requests held while disabled
* @replenish_backlog: Number of buffers needed to fill hardware queue
@@ -72,7 +85,7 @@ struct ipa_endpoint {
struct net_device *netdev;
/* Receive buffer replenishing for RX endpoints */
- bool replenish_enabled;
+ DECLARE_BITMAP(replenish_flags, IPA_REPLENISH_COUNT);
u32 replenish_ready;
atomic_t replenish_saved;
atomic_t replenish_backlog;
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index dae95d9..5b6c0d1 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -421,7 +421,7 @@ static int at803x_set_wol(struct phy_device *phydev,
const u8 *mac;
int ret, irq_enabled;
unsigned int i;
- const unsigned int offsets[] = {
+ static const unsigned int offsets[] = {
AT803X_LOC_MAC_ADDR_32_47_OFFSET,
AT803X_LOC_MAC_ADDR_16_31_OFFSET,
AT803X_LOC_MAC_ADDR_0_15_OFFSET,
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 739859c..fa71fb7 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -189,6 +189,8 @@
#define MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_SGMII 0x4
#define MII_88E1510_GEN_CTRL_REG_1_RESET 0x8000 /* Soft reset */
+#define MII_88E1510_MSCR_2 0x15
+
#define MII_VCT5_TX_RX_MDI0_COUPLING 0x10
#define MII_VCT5_TX_RX_MDI1_COUPLING 0x11
#define MII_VCT5_TX_RX_MDI2_COUPLING 0x12
@@ -1932,6 +1934,58 @@ static void marvell_get_stats(struct phy_device *phydev,
data[i] = marvell_get_stat(phydev, i);
}
+static int m88e1510_loopback(struct phy_device *phydev, bool enable)
+{
+ int err;
+
+ if (enable) {
+ u16 bmcr_ctl = 0, mscr2_ctl = 0;
+
+ if (phydev->speed == SPEED_1000)
+ bmcr_ctl = BMCR_SPEED1000;
+ else if (phydev->speed == SPEED_100)
+ bmcr_ctl = BMCR_SPEED100;
+
+ if (phydev->duplex == DUPLEX_FULL)
+ bmcr_ctl |= BMCR_FULLDPLX;
+
+ err = phy_write(phydev, MII_BMCR, bmcr_ctl);
+ if (err < 0)
+ return err;
+
+ if (phydev->speed == SPEED_1000)
+ mscr2_ctl = BMCR_SPEED1000;
+ else if (phydev->speed == SPEED_100)
+ mscr2_ctl = BMCR_SPEED100;
+
+ err = phy_modify_paged(phydev, MII_MARVELL_MSCR_PAGE,
+ MII_88E1510_MSCR_2, BMCR_SPEED1000 |
+ BMCR_SPEED100, mscr2_ctl);
+ if (err < 0)
+ return err;
+
+ /* Need soft reset to have speed configuration takes effect */
+ err = genphy_soft_reset(phydev);
+ if (err < 0)
+ return err;
+
+ /* FIXME: Based on trial and error test, it seem 1G need to have
+ * delay between soft reset and loopback enablement.
+ */
+ if (phydev->speed == SPEED_1000)
+ msleep(1000);
+
+ return phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK,
+ BMCR_LOOPBACK);
+ } else {
+ err = phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK, 0);
+ if (err < 0)
+ return err;
+
+ return phy_config_aneg(phydev);
+ }
+}
+
static int marvell_vct5_wait_complete(struct phy_device *phydev)
{
int i;
@@ -3078,7 +3132,7 @@ static struct phy_driver marvell_drivers[] = {
.get_sset_count = marvell_get_sset_count,
.get_strings = marvell_get_strings,
.get_stats = marvell_get_stats,
- .set_loopback = genphy_loopback,
+ .set_loopback = m88e1510_loopback,
.get_tunable = m88e1011_get_tunable,
.set_tunable = m88e1011_set_tunable,
.cable_test_start = marvell_vct7_cable_test_start,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 4570cb9..a7ebcda 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1726,8 +1726,8 @@ static struct phy_driver ksphy_driver[] = {
.config_init = kszphy_config_init,
.config_intr = kszphy_config_intr,
.handle_interrupt = kszphy_handle_interrupt,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8021,
.phy_id_mask = 0x00ffffff,
@@ -1741,8 +1741,8 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8031,
.phy_id_mask = 0x00ffffff,
@@ -1756,8 +1756,8 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8041,
.phy_id_mask = MICREL_PHY_ID_MASK,
@@ -1788,8 +1788,8 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.name = "Micrel KSZ8051",
/* PHY_BASIC_FEATURES */
@@ -1802,8 +1802,8 @@ static struct phy_driver ksphy_driver[] = {
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.match_phy_device = ksz8051_match_phy_device,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8001,
.name = "Micrel KSZ8001 or KS8721",
@@ -1817,8 +1817,8 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8081,
.name = "Micrel KSZ8081 or KSZ8091",
@@ -1848,8 +1848,8 @@ static struct phy_driver ksphy_driver[] = {
.config_init = ksz8061_config_init,
.config_intr = kszphy_config_intr,
.handle_interrupt = kszphy_handle_interrupt,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ9021,
.phy_id_mask = 0x000ffffe,
@@ -1864,8 +1864,8 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
- .resume = genphy_resume,
+ .suspend = kszphy_suspend,
+ .resume = kszphy_resume,
.read_mmd = genphy_read_mmd_unsupported,
.write_mmd = genphy_write_mmd_unsupported,
}, {
@@ -1883,7 +1883,7 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
+ .suspend = kszphy_suspend,
.resume = kszphy_resume,
}, {
.phy_id = PHY_ID_LAN8814,
@@ -1928,7 +1928,7 @@ static struct phy_driver ksphy_driver[] = {
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
+ .suspend = kszphy_suspend,
.resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8873MLL,
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index ab77a9f..4720b24 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1641,17 +1641,20 @@ static int sfp_sm_probe_for_phy(struct sfp *sfp)
static int sfp_module_parse_power(struct sfp *sfp)
{
u32 power_mW = 1000;
+ bool supports_a2;
if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_POWER_DECL))
power_mW = 1500;
if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_HIGH_POWER_LEVEL))
power_mW = 2000;
+ supports_a2 = sfp->id.ext.sff8472_compliance !=
+ SFP_SFF8472_COMPLIANCE_NONE ||
+ sfp->id.ext.diagmon & SFP_DIAGMON_DDM;
+
if (power_mW > sfp->max_power_mW) {
/* Module power specification exceeds the allowed maximum. */
- if (sfp->id.ext.sff8472_compliance ==
- SFP_SFF8472_COMPLIANCE_NONE &&
- !(sfp->id.ext.diagmon & SFP_DIAGMON_DDM)) {
+ if (!supports_a2) {
/* The module appears not to implement bus address
* 0xa2, so assume that the module powers up in the
* indicated mode.
@@ -1668,11 +1671,25 @@ static int sfp_module_parse_power(struct sfp *sfp)
}
}
+ if (power_mW <= 1000) {
+ /* Modules below 1W do not require a power change sequence */
+ sfp->module_power_mW = power_mW;
+ return 0;
+ }
+
+ if (!supports_a2) {
+ /* The module power level is below the host maximum and the
+ * module appears not to implement bus address 0xa2, so assume
+ * that the module powers up in the indicated mode.
+ */
+ return 0;
+ }
+
/* If the module requires a higher power mode, but also requires
* an address change sequence, warn the user that the module may
* not be functional.
*/
- if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE && power_mW > 1000) {
+ if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE) {
dev_warn(sfp->dev,
"Address Change Sequence not supported but module requires %u.%uW, module may not be functional\n",
power_mW / 1000, (power_mW / 100) % 10);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f510e82..37e5f34 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1316,6 +1316,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */
{QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */
{QMI_FIXED_INTF(0x19d2, 0x1432, 3)}, /* ZTE ME3620 */
+ {QMI_FIXED_INTF(0x19d2, 0x1485, 5)}, /* ZTE MF286D */
{QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */
{QMI_FIXED_INTF(0x2001, 0x7e16, 3)}, /* D-Link DWM-221 */
{QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */
@@ -1401,6 +1402,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/
{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */
+ {QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index abe0149..bc1e3dd 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1962,7 +1962,8 @@ static const struct driver_info smsc95xx_info = {
.bind = smsc95xx_bind,
.unbind = smsc95xx_unbind,
.link_reset = smsc95xx_link_reset,
- .reset = smsc95xx_start_phy,
+ .reset = smsc95xx_reset,
+ .check_connect = smsc95xx_start_phy,
.stop = smsc95xx_stop,
.rx_fixup = smsc95xx_rx_fixup,
.tx_fixup = smsc95xx_tx_fixup,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 569eecf..3d97f15 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3312,7 +3312,7 @@ static int virtnet_probe(struct virtio_device *vdev)
return 0;
free_unregister_netdev:
- vi->vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
unregister_netdev(dev);
free_failover:
@@ -3328,7 +3328,7 @@ static int virtnet_probe(struct virtio_device *vdev)
static void remove_vq_common(struct virtnet_info *vi)
{
- vi->vdev->config->reset(vi->vdev);
+ virtio_reset_device(vi->vdev);
/* Free unused buffers in both send and recv, if any. */
free_unused_bufs(vi);
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index c0cfd9b..720952b 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -302,6 +302,41 @@ void wg_noise_set_static_identity_private_key(
static_identity->static_public, private_key);
}
+static void hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, const size_t keylen)
+{
+ struct blake2s_state state;
+ u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 };
+ u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32));
+ int i;
+
+ if (keylen > BLAKE2S_BLOCK_SIZE) {
+ blake2s_init(&state, BLAKE2S_HASH_SIZE);
+ blake2s_update(&state, key, keylen);
+ blake2s_final(&state, x_key);
+ } else
+ memcpy(x_key, key, keylen);
+
+ for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
+ x_key[i] ^= 0x36;
+
+ blake2s_init(&state, BLAKE2S_HASH_SIZE);
+ blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
+ blake2s_update(&state, in, inlen);
+ blake2s_final(&state, i_hash);
+
+ for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
+ x_key[i] ^= 0x5c ^ 0x36;
+
+ blake2s_init(&state, BLAKE2S_HASH_SIZE);
+ blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
+ blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE);
+ blake2s_final(&state, i_hash);
+
+ memcpy(out, i_hash, BLAKE2S_HASH_SIZE);
+ memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE);
+ memzero_explicit(i_hash, BLAKE2S_HASH_SIZE);
+}
+
/* This is Hugo Krawczyk's HKDF:
* - https://eprint.iacr.org/2010/264.pdf
* - https://tools.ietf.org/html/rfc5869
@@ -322,14 +357,14 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
((third_len || third_dst) && (!second_len || !second_dst))));
/* Extract entropy from data into secret */
- blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN);
+ hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN);
if (!first_dst || !first_len)
goto out;
/* Expand first key: key = secret, data = 0x1 */
output[0] = 1;
- blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE);
+ hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE);
memcpy(first_dst, output, first_len);
if (!second_dst || !second_len)
@@ -337,8 +372,7 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
/* Expand second key: key = secret, data = first-key || 0x2 */
output[BLAKE2S_HASH_SIZE] = 2;
- blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
- BLAKE2S_HASH_SIZE);
+ hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE);
memcpy(second_dst, output, second_len);
if (!third_dst || !third_len)
@@ -346,8 +380,7 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
/* Expand third key: key = secret, data = second-key || 0x3 */
output[BLAKE2S_HASH_SIZE] = 3;
- blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
- BLAKE2S_HASH_SIZE);
+ hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE);
memcpy(third_dst, output, third_len);
out:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c
index 2f3c451..2f89080 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c
@@ -4,6 +4,8 @@
*/
#include <asm/unaligned.h>
+
+#include <linux/math.h>
#include <linux/string.h>
#include <linux/bug.h>
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 0307a66..8d54f9f 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -4498,7 +4498,7 @@ static void remove_vqs(struct virtio_device *vdev)
{
int i;
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) {
struct virtqueue *vq = hwsim_vqs[i];
diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c
index 71bf9b4..6872782 100644
--- a/drivers/net/wwan/mhi_wwan_mbim.c
+++ b/drivers/net/wwan/mhi_wwan_mbim.c
@@ -385,13 +385,13 @@ static void mhi_net_rx_refill_work(struct work_struct *work)
int err;
while (!mhi_queue_is_full(mdev, DMA_FROM_DEVICE)) {
- struct sk_buff *skb = alloc_skb(MHI_DEFAULT_MRU, GFP_KERNEL);
+ struct sk_buff *skb = alloc_skb(mbim->mru, GFP_KERNEL);
if (unlikely(!skb))
break;
err = mhi_queue_skb(mdev, DMA_FROM_DEVICE, skb,
- MHI_DEFAULT_MRU, MHI_EOT);
+ mbim->mru, MHI_EOT);
if (unlikely(err)) {
kfree_skb(skb);
break;
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 37d26f0..62a0f1a 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -188,7 +188,7 @@ do { \
static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
{
int polarity, retry, ret;
- char rset_cmd[] = { 0x05, 0xF9, 0x04, 0x00, 0xC3, 0xE5 };
+ static const char rset_cmd[] = { 0x05, 0xF9, 0x04, 0x00, 0xC3, 0xE5 };
int count = sizeof(rset_cmd);
nfc_info(&phy->i2c_dev->dev, "Detecting nfc_en polarity\n");
diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c
index a43fc41..c922f10 100644
--- a/drivers/nfc/st21nfca/se.c
+++ b/drivers/nfc/st21nfca/se.c
@@ -316,6 +316,11 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
return -ENOMEM;
transaction->aid_len = skb->data[1];
+
+ /* Checking if the length of the AID is valid */
+ if (transaction->aid_len > sizeof(transaction->aid))
+ return -EINVAL;
+
memcpy(transaction->aid, &skb->data[2],
transaction->aid_len);
@@ -325,6 +330,11 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
return -EPROTO;
transaction->params_len = skb->data[transaction->aid_len + 3];
+
+ /* Total size is allocated (skb->len - 2) minus fixed array members */
+ if (transaction->params_len > ((skb->len - 2) - sizeof(struct nfc_evt_transaction)))
+ return -EINVAL;
+
memcpy(transaction->params, skb->data +
transaction->aid_len + 4, transaction->params_len);
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index 726c735..995b6cd 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -105,7 +105,7 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
nvdimm_bus_unregister(nvdimm_bus);
vdev->config->del_vqs(vdev);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
}
static struct virtio_driver virtio_pmem_driver = {
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 8a24d37..e7d92b6 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1420,15 +1420,18 @@ int of_phandle_iterator_args(struct of_phandle_iterator *it,
return count;
}
-static int __of_parse_phandle_with_args(const struct device_node *np,
- const char *list_name,
- const char *cells_name,
- int cell_count, int index,
- struct of_phandle_args *out_args)
+int __of_parse_phandle_with_args(const struct device_node *np,
+ const char *list_name,
+ const char *cells_name,
+ int cell_count, int index,
+ struct of_phandle_args *out_args)
{
struct of_phandle_iterator it;
int rc, cur_index = 0;
+ if (index < 0)
+ return -EINVAL;
+
/* Loop over the phandles until all the requested entry is found */
of_for_each_phandle(&it, rc, np, list_name, cells_name, cell_count) {
/*
@@ -1471,82 +1474,7 @@ static int __of_parse_phandle_with_args(const struct device_node *np,
of_node_put(it.node);
return rc;
}
-
-/**
- * of_parse_phandle - Resolve a phandle property to a device_node pointer
- * @np: Pointer to device node holding phandle property
- * @phandle_name: Name of property holding a phandle value
- * @index: For properties holding a table of phandles, this is the index into
- * the table
- *
- * Return: The device_node pointer with refcount incremented. Use
- * of_node_put() on it when done.
- */
-struct device_node *of_parse_phandle(const struct device_node *np,
- const char *phandle_name, int index)
-{
- struct of_phandle_args args;
-
- if (index < 0)
- return NULL;
-
- if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0,
- index, &args))
- return NULL;
-
- return args.np;
-}
-EXPORT_SYMBOL(of_parse_phandle);
-
-/**
- * of_parse_phandle_with_args() - Find a node pointed by phandle in a list
- * @np: pointer to a device tree node containing a list
- * @list_name: property name that contains a list
- * @cells_name: property name that specifies phandles' arguments count
- * @index: index of a phandle to parse out
- * @out_args: optional pointer to output arguments structure (will be filled)
- *
- * This function is useful to parse lists of phandles and their arguments.
- * Returns 0 on success and fills out_args, on error returns appropriate
- * errno value.
- *
- * Caller is responsible to call of_node_put() on the returned out_args->np
- * pointer.
- *
- * Example::
- *
- * phandle1: node1 {
- * #list-cells = <2>;
- * };
- *
- * phandle2: node2 {
- * #list-cells = <1>;
- * };
- *
- * node3 {
- * list = <&phandle1 1 2 &phandle2 3>;
- * };
- *
- * To get a device_node of the ``node2`` node you may call this:
- * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args);
- */
-int of_parse_phandle_with_args(const struct device_node *np, const char *list_name,
- const char *cells_name, int index,
- struct of_phandle_args *out_args)
-{
- int cell_count = -1;
-
- if (index < 0)
- return -EINVAL;
-
- /* If cells_name is NULL we assume a cell count of 0 */
- if (!cells_name)
- cell_count = 0;
-
- return __of_parse_phandle_with_args(np, list_name, cells_name,
- cell_count, index, out_args);
-}
-EXPORT_SYMBOL(of_parse_phandle_with_args);
+EXPORT_SYMBOL(__of_parse_phandle_with_args);
/**
* of_parse_phandle_with_args_map() - Find a node pointed by phandle in a list and remap it
@@ -1733,47 +1661,6 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
EXPORT_SYMBOL(of_parse_phandle_with_args_map);
/**
- * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list
- * @np: pointer to a device tree node containing a list
- * @list_name: property name that contains a list
- * @cell_count: number of argument cells following the phandle
- * @index: index of a phandle to parse out
- * @out_args: optional pointer to output arguments structure (will be filled)
- *
- * This function is useful to parse lists of phandles and their arguments.
- * Returns 0 on success and fills out_args, on error returns appropriate
- * errno value.
- *
- * Caller is responsible to call of_node_put() on the returned out_args->np
- * pointer.
- *
- * Example::
- *
- * phandle1: node1 {
- * };
- *
- * phandle2: node2 {
- * };
- *
- * node3 {
- * list = <&phandle1 0 2 &phandle2 2 3>;
- * };
- *
- * To get a device_node of the ``node2`` node you may call this:
- * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args);
- */
-int of_parse_phandle_with_fixed_args(const struct device_node *np,
- const char *list_name, int cell_count,
- int index, struct of_phandle_args *out_args)
-{
- if (index < 0)
- return -EINVAL;
- return __of_parse_phandle_with_args(np, list_name, NULL, cell_count,
- index, out_args);
-}
-EXPORT_SYMBOL(of_parse_phandle_with_fixed_args);
-
-/**
* of_count_phandle_with_args() - Find the number of phandles references in a property
* @np: pointer to a device tree node containing a list
* @list_name: property name that contains a list
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b0800c2..874f031 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -28,7 +28,7 @@
const struct of_device_id *of_match_device(const struct of_device_id *matches,
const struct device *dev)
{
- if ((!matches) || (!dev->of_node))
+ if (!matches || !dev->of_node || dev->of_node_reused)
return NULL;
return of_match_node(matches, dev->of_node);
}
diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c
index 9513c39..d9e5103 100644
--- a/drivers/parisc/pdc_stable.c
+++ b/drivers/parisc/pdc_stable.c
@@ -980,8 +980,10 @@ pdcs_register_pathentries(void)
entry->kobj.kset = paths_kset;
err = kobject_init_and_add(&entry->kobj, &ktype_pdcspath, NULL,
"%s", entry->name);
- if (err)
+ if (err) {
+ kobject_put(&entry->kobj);
return err;
+ }
/* kobject is now registered */
write_lock(&entry->rw_lock);
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 93772ab..c7552df 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -548,6 +548,73 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
}
}
+static int pwm_apply_legacy(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ int err;
+ struct pwm_state initial_state = pwm->state;
+
+ if (state->polarity != pwm->state.polarity) {
+ if (!chip->ops->set_polarity)
+ return -EINVAL;
+
+ /*
+ * Changing the polarity of a running PWM is only allowed when
+ * the PWM driver implements ->apply().
+ */
+ if (pwm->state.enabled) {
+ chip->ops->disable(chip, pwm);
+
+ /*
+ * Update pwm->state already here in case
+ * .set_polarity() or another callback depend on that.
+ */
+ pwm->state.enabled = false;
+ }
+
+ err = chip->ops->set_polarity(chip, pwm, state->polarity);
+ if (err)
+ goto rollback;
+
+ pwm->state.polarity = state->polarity;
+ }
+
+ if (!state->enabled) {
+ if (pwm->state.enabled)
+ chip->ops->disable(chip, pwm);
+
+ return 0;
+ }
+
+ /*
+ * We cannot skip calling ->config even if state->period ==
+ * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
+ * because we might have exited early in the last call to
+ * pwm_apply_state because of !state->enabled and so the two values in
+ * pwm->state might not be configured in hardware.
+ */
+ err = chip->ops->config(pwm->chip, pwm,
+ state->duty_cycle,
+ state->period);
+ if (err)
+ goto rollback;
+
+ pwm->state.period = state->period;
+ pwm->state.duty_cycle = state->duty_cycle;
+
+ if (!pwm->state.enabled) {
+ err = chip->ops->enable(chip, pwm);
+ if (err)
+ goto rollback;
+ }
+
+ return 0;
+
+rollback:
+ pwm->state = initial_state;
+ return err;
+}
+
/**
* pwm_apply_state() - atomically apply a new state to a PWM device
* @pwm: PWM device
@@ -580,70 +647,22 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
state->usage_power == pwm->state.usage_power)
return 0;
- if (chip->ops->apply) {
+ if (chip->ops->apply)
err = chip->ops->apply(chip, pwm, state);
- if (err)
- return err;
+ else
+ err = pwm_apply_legacy(chip, pwm, state);
+ if (err)
+ return err;
- trace_pwm_apply(pwm, state);
+ trace_pwm_apply(pwm, state);
- pwm->state = *state;
+ pwm->state = *state;
- /*
- * only do this after pwm->state was applied as some
- * implementations of .get_state depend on this
- */
- pwm_apply_state_debug(pwm, state);
- } else {
- /*
- * FIXME: restore the initial state in case of error.
- */
- if (state->polarity != pwm->state.polarity) {
- if (!chip->ops->set_polarity)
- return -EINVAL;
-
- /*
- * Changing the polarity of a running PWM is
- * only allowed when the PWM driver implements
- * ->apply().
- */
- if (pwm->state.enabled) {
- chip->ops->disable(chip, pwm);
- pwm->state.enabled = false;
- }
-
- err = chip->ops->set_polarity(chip, pwm,
- state->polarity);
- if (err)
- return err;
-
- pwm->state.polarity = state->polarity;
- }
-
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- err = chip->ops->config(pwm->chip, pwm,
- state->duty_cycle,
- state->period);
- if (err)
- return err;
-
- pwm->state.duty_cycle = state->duty_cycle;
- pwm->state.period = state->period;
- }
-
- if (state->enabled != pwm->state.enabled) {
- if (state->enabled) {
- err = chip->ops->enable(chip, pwm);
- if (err)
- return err;
- } else {
- chip->ops->disable(chip, pwm);
- }
-
- pwm->state.enabled = state->enabled;
- }
- }
+ /*
+ * only do this after pwm->state was applied as some
+ * implementations of .get_state depend on this
+ */
+ pwm_apply_state_debug(pwm, state);
return 0;
}
diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c
index f97f825..5996049 100644
--- a/drivers/pwm/pwm-img.c
+++ b/drivers/pwm/pwm-img.c
@@ -128,11 +128,9 @@ static int img_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
duty = DIV_ROUND_UP(timebase * duty_ns, period_ns);
- ret = pm_runtime_get_sync(chip->dev);
- if (ret < 0) {
- pm_runtime_put_autosuspend(chip->dev);
+ ret = pm_runtime_resume_and_get(chip->dev);
+ if (ret < 0)
return ret;
- }
val = img_pwm_readl(pwm_chip, PWM_CTRL_CFG);
val &= ~(PWM_CTRL_CFG_DIV_MASK << PWM_CTRL_CFG_DIV_SHIFT(pwm->hwpwm));
@@ -184,10 +182,33 @@ static void img_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
pm_runtime_put_autosuspend(chip->dev);
}
+static int img_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ int err;
+
+ if (state->polarity != PWM_POLARITY_NORMAL)
+ return -EINVAL;
+
+ if (!state->enabled) {
+ if (pwm->state.enabled)
+ img_pwm_disable(chip, pwm);
+
+ return 0;
+ }
+
+ err = img_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
+
+ if (!pwm->state.enabled)
+ err = img_pwm_enable(chip, pwm);
+
+ return err;
+}
+
static const struct pwm_ops img_pwm_ops = {
- .config = img_pwm_config,
- .enable = img_pwm_enable,
- .disable = img_pwm_disable,
+ .apply = img_pwm_apply,
.owner = THIS_MODULE,
};
diff --git a/drivers/pwm/pwm-twl.c b/drivers/pwm/pwm-twl.c
index 203194f..86567ad 100644
--- a/drivers/pwm/pwm-twl.c
+++ b/drivers/pwm/pwm-twl.c
@@ -58,9 +58,9 @@ static inline struct twl_pwm_chip *to_twl(struct pwm_chip *chip)
}
static int twl_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
- int duty_ns, int period_ns)
+ u64 duty_ns, u64 period_ns)
{
- int duty_cycle = DIV_ROUND_UP(duty_ns * TWL_PWM_MAX, period_ns) + 1;
+ int duty_cycle = DIV64_U64_ROUND_UP(duty_ns * TWL_PWM_MAX, period_ns) + 1;
u8 pwm_config[2] = { 1, 0 };
int base, ret;
@@ -279,19 +279,65 @@ static void twl6030_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
mutex_unlock(&twl->mutex);
}
+static int twl4030_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ int err;
+
+ if (state->polarity != PWM_POLARITY_NORMAL)
+ return -EINVAL;
+
+ if (!state->enabled) {
+ if (pwm->state.enabled)
+ twl4030_pwm_disable(chip, pwm);
+
+ return 0;
+ }
+
+ err = twl_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
+
+ if (!pwm->state.enabled)
+ err = twl4030_pwm_enable(chip, pwm);
+
+ return err;
+}
+
+static int twl6030_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ int err;
+
+ if (state->polarity != PWM_POLARITY_NORMAL)
+ return -EINVAL;
+
+ if (!state->enabled) {
+ if (pwm->state.enabled)
+ twl6030_pwm_disable(chip, pwm);
+
+ return 0;
+ }
+
+ err = twl_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
+
+ if (!pwm->state.enabled)
+ err = twl6030_pwm_enable(chip, pwm);
+
+ return err;
+}
+
static const struct pwm_ops twl4030_pwm_ops = {
- .config = twl_pwm_config,
- .enable = twl4030_pwm_enable,
- .disable = twl4030_pwm_disable,
+ .apply = twl4030_pwm_apply,
.request = twl4030_pwm_request,
.free = twl4030_pwm_free,
.owner = THIS_MODULE,
};
static const struct pwm_ops twl6030_pwm_ops = {
- .config = twl_pwm_config,
- .enable = twl6030_pwm_enable,
- .disable = twl6030_pwm_disable,
+ .apply = twl6030_pwm_apply,
.owner = THIS_MODULE,
};
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index 480bfc2..7170a315 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -70,7 +70,7 @@ static inline void vt8500_pwm_busy_wait(struct vt8500_chip *vt8500, int nr, u8 b
}
static int vt8500_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
- int duty_ns, int period_ns)
+ u64 duty_ns, u64 period_ns)
{
struct vt8500_chip *vt8500 = to_vt8500_chip(chip);
unsigned long long c;
@@ -102,8 +102,8 @@ static int vt8500_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
}
c = (unsigned long long)pv * duty_ns;
- do_div(c, period_ns);
- dc = c;
+
+ dc = div64_u64(c, period_ns);
writel(prescale, vt8500->base + REG_SCALAR(pwm->hwpwm));
vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_SCALAR_UPDATE);
@@ -176,11 +176,54 @@ static int vt8500_pwm_set_polarity(struct pwm_chip *chip,
return 0;
}
+static int vt8500_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ int err;
+ bool enabled = pwm->state.enabled;
+
+ if (state->polarity != pwm->state.polarity) {
+ /*
+ * Changing the polarity of a running PWM is only allowed when
+ * the PWM driver implements ->apply().
+ */
+ if (enabled) {
+ vt8500_pwm_disable(chip, pwm);
+
+ enabled = false;
+ }
+
+ err = vt8500_pwm_set_polarity(chip, pwm, state->polarity);
+ if (err)
+ return err;
+ }
+
+ if (!state->enabled) {
+ if (enabled)
+ vt8500_pwm_disable(chip, pwm);
+
+ return 0;
+ }
+
+ /*
+ * We cannot skip calling ->config even if state->period ==
+ * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
+ * because we might have exited early in the last call to
+ * pwm_apply_state because of !state->enabled and so the two values in
+ * pwm->state might not be configured in hardware.
+ */
+ err = vt8500_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
+
+ if (!enabled)
+ err = vt8500_pwm_enable(chip, pwm);
+
+ return err;
+}
+
static const struct pwm_ops vt8500_pwm_ops = {
- .enable = vt8500_pwm_enable,
- .disable = vt8500_pwm_disable,
- .config = vt8500_pwm_config,
- .set_polarity = vt8500_pwm_set_polarity,
+ .apply = vt8500_pwm_apply,
.owner = THIS_MODULE,
};
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index f2e961f..3ddd426 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -283,6 +283,17 @@
verified and booted with the help of the Peripheral Authentication
System (PAS) in TrustZone.
+config RCAR_REMOTEPROC
+ tristate "Renesas R-Car Gen3 remoteproc support"
+ depends on ARCH_RENESAS || COMPILE_TEST
+ help
+ Say y here to support R-Car realtime processor via the
+ remote processor framework. An ELF firmware can be loaded
+ thanks to sysfs remoteproc entries. The remote processor
+ can be started and stopped.
+ This can be either built-in or a loadable module.
+ If compiled as module (M), the module name is rcar_rproc.
+
config ST_REMOTEPROC
tristate "ST remoteproc support"
depends on ARCH_STI
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 0ac256b..5478c7c 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -32,6 +32,7 @@
obj-$(CONFIG_QCOM_WCNSS_PIL) += qcom_wcnss_pil.o
qcom_wcnss_pil-y += qcom_wcnss.o
qcom_wcnss_pil-y += qcom_wcnss_iris.o
+obj-$(CONFIG_RCAR_REMOTEPROC) += rcar_rproc.o
obj-$(CONFIG_ST_REMOTEPROC) += st_remoteproc.o
obj-$(CONFIG_ST_SLIM_REMOTEPROC) += st_slim_rproc.o
obj-$(CONFIG_STM32_RPROC) += stm32_rproc.o
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index ff8170d..7a096f1 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -34,7 +34,8 @@
#define IMX7D_M4_START (IMX7D_ENABLE_M4 | IMX7D_SW_M4P_RST \
| IMX7D_SW_M4C_RST)
-#define IMX7D_M4_STOP IMX7D_SW_M4C_NON_SCLR_RST
+#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_RST | \
+ IMX7D_SW_M4C_NON_SCLR_RST)
/* Address: 0x020D8000 */
#define IMX6SX_SRC_SCR 0x00
@@ -45,7 +46,8 @@
#define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \
| IMX6SX_SW_M4C_RST)
-#define IMX6SX_M4_STOP IMX6SX_SW_M4C_NON_SCLR_RST
+#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_RST | \
+ IMX6SX_SW_M4C_NON_SCLR_RST)
#define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \
| IMX6SX_SW_M4C_NON_SCLR_RST \
| IMX6SX_SW_M4C_RST)
@@ -684,7 +686,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv)
return ret;
}
- if (!(val & dcfg->src_stop))
+ if ((val & dcfg->src_mask) != dcfg->src_stop)
priv->rproc->state = RPROC_DETACHED;
return 0;
@@ -804,6 +806,7 @@ static int imx_rproc_remove(struct platform_device *pdev)
clk_disable_unprepare(priv->clk);
rproc_del(rproc);
imx_rproc_free_mbox(rproc);
+ destroy_workqueue(priv->workqueue);
rproc_free(rproc);
return 0;
diff --git a/drivers/remoteproc/ingenic_rproc.c b/drivers/remoteproc/ingenic_rproc.c
index a356738..9902cce 100644
--- a/drivers/remoteproc/ingenic_rproc.c
+++ b/drivers/remoteproc/ingenic_rproc.c
@@ -218,14 +218,13 @@ static int ingenic_rproc_probe(struct platform_device *pdev)
if (vpu->irq < 0)
return vpu->irq;
- ret = devm_request_irq(dev, vpu->irq, vpu_interrupt, 0, "VPU", rproc);
+ ret = devm_request_irq(dev, vpu->irq, vpu_interrupt, IRQF_NO_AUTOEN,
+ "VPU", rproc);
if (ret < 0) {
dev_err(dev, "Failed to request IRQ\n");
return ret;
}
- disable_irq(vpu->irq);
-
ret = devm_rproc_add(dev, rproc);
if (ret) {
dev_err(dev, "Failed to register remote processor\n");
diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c
index 6dc955e..00f041e 100644
--- a/drivers/remoteproc/mtk_scp_ipi.c
+++ b/drivers/remoteproc/mtk_scp_ipi.c
@@ -23,7 +23,7 @@
*
* Register an ipi function to receive ipi interrupt from SCP.
*
- * Returns 0 if ipi registers successfully, -error on error.
+ * Return: 0 if ipi registers successfully, -error on error.
*/
int scp_ipi_register(struct mtk_scp *scp,
u32 id,
@@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(scp_ipi_unlock);
* When the processing completes, IPI handler registered
* by scp_ipi_register will be called in interrupt context.
*
- * Returns 0 if sending data successfully, -error on error.
+ * Return: 0 if sending data successfully, -error on error.
**/
int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
unsigned int wait)
diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c
index 7c007dd..aca2156 100644
--- a/drivers/remoteproc/qcom_pil_info.c
+++ b/drivers/remoteproc/qcom_pil_info.c
@@ -104,7 +104,7 @@ int qcom_pil_info_store(const char *image, phys_addr_t base, size_t size)
return -ENOMEM;
found_unused:
- memcpy_toio(entry, image, PIL_RELOC_NAME_LEN);
+ memcpy_toio(entry, image, strnlen(image, PIL_RELOC_NAME_LEN));
found_existing:
/* Use two writel() as base is only aligned to 4 bytes on odd entries */
writel(base, entry + PIL_RELOC_NAME_LEN);
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 03857dc..184bb7c 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -524,6 +524,23 @@ static const struct adsp_data sdm845_adsp_resource_init = {
.ssctl_id = 0x14,
};
+static const struct adsp_data sm6350_adsp_resource = {
+ .crash_reason_smem = 423,
+ .firmware_name = "adsp.mdt",
+ .pas_id = 1,
+ .has_aggre2_clk = false,
+ .auto_boot = true,
+ .proxy_pd_names = (char*[]){
+ "lcx",
+ "lmx",
+ NULL
+ },
+ .load_state = "adsp",
+ .ssr_name = "lpass",
+ .sysmon_name = "adsp",
+ .ssctl_id = 0x14,
+};
+
static const struct adsp_data sm8150_adsp_resource = {
.crash_reason_smem = 423,
.firmware_name = "adsp.mdt",
@@ -612,6 +629,23 @@ static const struct adsp_data sdm845_cdsp_resource_init = {
.ssctl_id = 0x17,
};
+static const struct adsp_data sm6350_cdsp_resource = {
+ .crash_reason_smem = 601,
+ .firmware_name = "cdsp.mdt",
+ .pas_id = 18,
+ .has_aggre2_clk = false,
+ .auto_boot = true,
+ .proxy_pd_names = (char*[]){
+ "cx",
+ "mx",
+ NULL
+ },
+ .load_state = "cdsp",
+ .ssr_name = "cdsp",
+ .sysmon_name = "cdsp",
+ .ssctl_id = 0x17,
+};
+
static const struct adsp_data sm8150_cdsp_resource = {
.crash_reason_smem = 601,
.firmware_name = "cdsp.mdt",
@@ -652,6 +686,7 @@ static const struct adsp_data sm8350_cdsp_resource = {
.auto_boot = true,
.proxy_pd_names = (char*[]){
"cx",
+ "mxc",
NULL
},
.load_state = "cdsp",
@@ -804,6 +839,9 @@ static const struct of_device_id adsp_of_match[] = {
{ .compatible = "qcom,sdm845-adsp-pas", .data = &sdm845_adsp_resource_init},
{ .compatible = "qcom,sdm845-cdsp-pas", .data = &sdm845_cdsp_resource_init},
{ .compatible = "qcom,sdx55-mpss-pas", .data = &sdx55_mpss_resource},
+ { .compatible = "qcom,sm6350-adsp-pas", .data = &sm6350_adsp_resource},
+ { .compatible = "qcom,sm6350-cdsp-pas", .data = &sm6350_cdsp_resource},
+ { .compatible = "qcom,sm6350-mpss-pas", .data = &mpss_resource_init},
{ .compatible = "qcom,sm8150-adsp-pas", .data = &sm8150_adsp_resource},
{ .compatible = "qcom,sm8150-cdsp-pas", .data = &sm8150_cdsp_resource},
{ .compatible = "qcom,sm8150-mpss-pas", .data = &mpss_resource_init},
diff --git a/drivers/remoteproc/rcar_rproc.c b/drivers/remoteproc/rcar_rproc.c
new file mode 100644
index 0000000..aa86154
--- /dev/null
+++ b/drivers/remoteproc/rcar_rproc.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) IoT.bzh 2021
+ */
+
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/pm_runtime.h>
+#include <linux/remoteproc.h>
+#include <linux/reset.h>
+#include <linux/soc/renesas/rcar-rst.h>
+
+#include "remoteproc_internal.h"
+
+struct rcar_rproc {
+ struct reset_control *rst;
+};
+
+static int rcar_rproc_mem_alloc(struct rproc *rproc,
+ struct rproc_mem_entry *mem)
+{
+ struct device *dev = &rproc->dev;
+ void *va;
+
+ dev_dbg(dev, "map memory: %pa+%zx\n", &mem->dma, mem->len);
+ va = ioremap_wc(mem->dma, mem->len);
+ if (!va) {
+ dev_err(dev, "Unable to map memory region: %pa+%zx\n",
+ &mem->dma, mem->len);
+ return -ENOMEM;
+ }
+
+ /* Update memory entry va */
+ mem->va = va;
+
+ return 0;
+}
+
+static int rcar_rproc_mem_release(struct rproc *rproc,
+ struct rproc_mem_entry *mem)
+{
+ dev_dbg(&rproc->dev, "unmap memory: %pa\n", &mem->dma);
+ iounmap(mem->va);
+
+ return 0;
+}
+
+static int rcar_rproc_prepare(struct rproc *rproc)
+{
+ struct device *dev = rproc->dev.parent;
+ struct device_node *np = dev->of_node;
+ struct of_phandle_iterator it;
+ struct rproc_mem_entry *mem;
+ struct reserved_mem *rmem;
+ u32 da;
+
+ /* Register associated reserved memory regions */
+ of_phandle_iterator_init(&it, np, "memory-region", NULL, 0);
+ while (of_phandle_iterator_next(&it) == 0) {
+
+ rmem = of_reserved_mem_lookup(it.node);
+ if (!rmem) {
+ dev_err(&rproc->dev,
+ "unable to acquire memory-region\n");
+ return -EINVAL;
+ }
+
+ if (rmem->base > U32_MAX)
+ return -EINVAL;
+
+ /* No need to translate pa to da, R-Car use same map */
+ da = rmem->base;
+ mem = rproc_mem_entry_init(dev, NULL,
+ rmem->base,
+ rmem->size, da,
+ rcar_rproc_mem_alloc,
+ rcar_rproc_mem_release,
+ it.node->name);
+
+ if (!mem)
+ return -ENOMEM;
+
+ rproc_add_carveout(rproc, mem);
+ }
+
+ return 0;
+}
+
+static int rcar_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw)
+{
+ int ret;
+
+ ret = rproc_elf_load_rsc_table(rproc, fw);
+ if (ret)
+ dev_info(&rproc->dev, "No resource table in elf\n");
+
+ return 0;
+}
+
+static int rcar_rproc_start(struct rproc *rproc)
+{
+ struct rcar_rproc *priv = rproc->priv;
+ int err;
+
+ if (!rproc->bootaddr)
+ return -EINVAL;
+
+ err = rcar_rst_set_rproc_boot_addr(rproc->bootaddr);
+ if (err) {
+ dev_err(&rproc->dev, "failed to set rproc boot addr\n");
+ return err;
+ }
+
+ err = reset_control_deassert(priv->rst);
+ if (err)
+ dev_err(&rproc->dev, "failed to deassert reset\n");
+
+ return err;
+}
+
+static int rcar_rproc_stop(struct rproc *rproc)
+{
+ struct rcar_rproc *priv = rproc->priv;
+ int err;
+
+ err = reset_control_assert(priv->rst);
+ if (err)
+ dev_err(&rproc->dev, "failed to assert reset\n");
+
+ return err;
+}
+
+static struct rproc_ops rcar_rproc_ops = {
+ .prepare = rcar_rproc_prepare,
+ .start = rcar_rproc_start,
+ .stop = rcar_rproc_stop,
+ .load = rproc_elf_load_segments,
+ .parse_fw = rcar_rproc_parse_fw,
+ .find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table,
+ .sanity_check = rproc_elf_sanity_check,
+ .get_boot_addr = rproc_elf_get_boot_addr,
+
+};
+
+static int rcar_rproc_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct rcar_rproc *priv;
+ struct rproc *rproc;
+ int ret;
+
+ rproc = devm_rproc_alloc(dev, np->name, &rcar_rproc_ops,
+ NULL, sizeof(*priv));
+ if (!rproc)
+ return -ENOMEM;
+
+ priv = rproc->priv;
+
+ priv->rst = devm_reset_control_get_exclusive(dev, NULL);
+ if (IS_ERR(priv->rst)) {
+ ret = PTR_ERR(priv->rst);
+ dev_err_probe(dev, ret, "fail to acquire rproc reset\n");
+ return ret;
+ }
+
+ pm_runtime_enable(dev);
+ ret = pm_runtime_resume_and_get(dev);
+ if (ret) {
+ dev_err(dev, "failed to power up\n");
+ return ret;
+ }
+
+ dev_set_drvdata(dev, rproc);
+
+ /* Manually start the rproc */
+ rproc->auto_boot = false;
+
+ ret = devm_rproc_add(dev, rproc);
+ if (ret) {
+ dev_err(dev, "rproc_add failed\n");
+ goto pm_disable;
+ }
+
+ return 0;
+
+pm_disable:
+ pm_runtime_disable(dev);
+
+ return ret;
+}
+
+static int rcar_rproc_remove(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+
+ pm_runtime_disable(dev);
+
+ return 0;
+}
+
+static const struct of_device_id rcar_rproc_of_match[] = {
+ { .compatible = "renesas,rcar-cr7" },
+ {},
+};
+
+MODULE_DEVICE_TABLE(of, rcar_rproc_of_match);
+
+static struct platform_driver rcar_rproc_driver = {
+ .probe = rcar_rproc_probe,
+ .remove = rcar_rproc_remove,
+ .driver = {
+ .name = "rcar-rproc",
+ .of_match_table = rcar_rproc_of_match,
+ },
+};
+
+module_platform_driver(rcar_rproc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Renesas R-Car Gen3 remote processor control driver");
+MODULE_AUTHOR("Julien Massot <julien.massot@iot.bzh>");
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 775df16..69f51ac 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -577,8 +577,8 @@ static int rproc_handle_vdev(struct rproc *rproc, void *ptr,
dma_get_mask(rproc->dev.parent));
if (ret) {
dev_warn(dev,
- "Failed to set DMA mask %llx. Trying to continue... %x\n",
- dma_get_mask(rproc->dev.parent), ret);
+ "Failed to set DMA mask %llx. Trying to continue... (%pe)\n",
+ dma_get_mask(rproc->dev.parent), ERR_PTR(ret));
}
/* parse the vrings */
diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index c892f43..4b09342 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -166,7 +166,7 @@ static void rproc_copy_segment(struct rproc *rproc, void *dest,
memset(dest, 0xff, size);
} else {
if (is_iomem)
- memcpy_fromio(dest, ptr, size);
+ memcpy_fromio(dest, (void const __iomem *)ptr, size);
else
memcpy(dest, ptr, size);
}
diff --git a/drivers/remoteproc/st_slim_rproc.c b/drivers/remoteproc/st_slim_rproc.c
index 22096ad..4ed9467 100644
--- a/drivers/remoteproc/st_slim_rproc.c
+++ b/drivers/remoteproc/st_slim_rproc.c
@@ -216,7 +216,7 @@ static const struct rproc_ops slim_rproc_ops = {
* obtains and enables any clocks required by the SLIM core and also
* ioremaps the various IO.
*
- * Returns st_slim_rproc pointer or PTR_ERR() on error.
+ * Return: st_slim_rproc pointer or PTR_ERR() on error.
*/
struct st_slim_rproc *st_slim_rproc_alloc(struct platform_device *pdev,
diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c
index b643efc..7d782ed 100644
--- a/drivers/remoteproc/stm32_rproc.c
+++ b/drivers/remoteproc/stm32_rproc.c
@@ -494,7 +494,7 @@ static int stm32_rproc_stop(struct rproc *rproc)
int err, idx;
/* request shutdown of the remote processor */
- if (rproc->state != RPROC_OFFLINE) {
+ if (rproc->state != RPROC_OFFLINE && rproc->state != RPROC_CRASHED) {
idx = stm32_rproc_mbox_idx(rproc, STM32_MBX_SHUTDOWN);
if (idx >= 0 && ddata->mb[idx].chan) {
err = mbox_send_message(ddata->mb[idx].chan, "detach");
diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index c352fa2..939c5d9 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -767,6 +767,7 @@ static const struct k3_dsp_dev_data c71_data = {
static const struct of_device_id k3_dsp_of_match[] = {
{ .compatible = "ti,j721e-c66-dsp", .data = &c66_data, },
{ .compatible = "ti,j721e-c71-dsp", .data = &c71_data, },
+ { .compatible = "ti,j721s2-c71-dsp", .data = &c71_data, },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, k3_dsp_of_match);
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 6499302..969531c 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -1535,7 +1535,7 @@ static const struct k3_r5_soc_data am65_j721e_soc_data = {
.single_cpu_mode = false,
};
-static const struct k3_r5_soc_data j7200_soc_data = {
+static const struct k3_r5_soc_data j7200_j721s2_soc_data = {
.tcm_is_double = true,
.tcm_ecc_autoinit = true,
.single_cpu_mode = false,
@@ -1550,8 +1550,9 @@ static const struct k3_r5_soc_data am64_soc_data = {
static const struct of_device_id k3_r5_of_match[] = {
{ .compatible = "ti,am654-r5fss", .data = &am65_j721e_soc_data, },
{ .compatible = "ti,j721e-r5fss", .data = &am65_j721e_soc_data, },
- { .compatible = "ti,j7200-r5fss", .data = &j7200_soc_data, },
+ { .compatible = "ti,j7200-r5fss", .data = &j7200_j721s2_soc_data, },
{ .compatible = "ti,am64-r5fss", .data = &am64_soc_data, },
+ { .compatible = "ti,j721s2-r5fss", .data = &j7200_j721s2_soc_data, },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, k3_r5_of_match);
diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c
index 3f377a7..1030cfa 100644
--- a/drivers/rpmsg/qcom_glink_native.c
+++ b/drivers/rpmsg/qcom_glink_native.c
@@ -427,7 +427,7 @@ static void qcom_glink_handle_intent_req_ack(struct qcom_glink *glink,
* Allocates a local channel id and sends a RPM_CMD_OPEN message to the remote.
* Will return with refcount held, regardless of outcome.
*
- * Returns 0 on success, negative errno otherwise.
+ * Return: 0 on success, negative errno otherwise.
*/
static int qcom_glink_send_open_req(struct qcom_glink *glink,
struct glink_channel *channel)
diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c
index 8da1b5c..540e027 100644
--- a/drivers/rpmsg/qcom_smd.c
+++ b/drivers/rpmsg/qcom_smd.c
@@ -1467,7 +1467,7 @@ ATTRIBUTE_GROUPS(qcom_smd_edge);
* @parent: parent device for the edge
* @node: device_node describing the edge
*
- * Returns an edge reference, or negative ERR_PTR() on failure.
+ * Return: an edge reference, or negative ERR_PTR() on failure.
*/
struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
struct device_node *node)
diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c
index b5907b8..d6214cb6 100644
--- a/drivers/rpmsg/rpmsg_char.c
+++ b/drivers/rpmsg/rpmsg_char.c
@@ -9,6 +9,9 @@
* Based on rpmsg performance statistics driver by Michal Simek, which in turn
* was based on TI & Google OMX rpmsg driver.
*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/cdev.h>
#include <linux/device.h>
#include <linux/fs.h>
@@ -550,7 +553,7 @@ static int rpmsg_chrdev_init(void)
ret = alloc_chrdev_region(&rpmsg_major, 0, RPMSG_DEV_MAX, "rpmsg");
if (ret < 0) {
- pr_err("rpmsg: failed to allocate char dev region\n");
+ pr_err("failed to allocate char dev region\n");
return ret;
}
@@ -563,7 +566,7 @@ static int rpmsg_chrdev_init(void)
ret = register_rpmsg_driver(&rpmsg_chrdev_driver);
if (ret < 0) {
- pr_err("rpmsgchr: failed to register rpmsg driver\n");
+ pr_err("failed to register rpmsg driver\n");
class_destroy(rpmsg_class);
unregister_chrdev_region(rpmsg_major, RPMSG_DEV_MAX);
}
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index d3eb600..d9e612f 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -26,7 +26,7 @@
* @rpdev: rpmsg device
* @chinfo: channel_info to bind
*
- * Returns a pointer to the new rpmsg device on success, or NULL on error.
+ * Return: a pointer to the new rpmsg device on success, or NULL on error.
*/
struct rpmsg_device *rpmsg_create_channel(struct rpmsg_device *rpdev,
struct rpmsg_channel_info *chinfo)
@@ -48,7 +48,7 @@ EXPORT_SYMBOL(rpmsg_create_channel);
* @rpdev: rpmsg device
* @chinfo: channel_info to bind
*
- * Returns 0 on success or an appropriate error value.
+ * Return: 0 on success or an appropriate error value.
*/
int rpmsg_release_channel(struct rpmsg_device *rpdev,
struct rpmsg_channel_info *chinfo)
@@ -102,7 +102,7 @@ EXPORT_SYMBOL(rpmsg_release_channel);
* dynamically assign them an available rpmsg address (drivers should have
* a very good reason why not to always use RPMSG_ADDR_ANY here).
*
- * Returns a pointer to the endpoint on success, or NULL on error.
+ * Return: a pointer to the endpoint on success, or NULL on error.
*/
struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev,
rpmsg_rx_cb_t cb, void *priv,
@@ -146,7 +146,7 @@ EXPORT_SYMBOL(rpmsg_destroy_ept);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len)
{
@@ -175,7 +175,7 @@ EXPORT_SYMBOL(rpmsg_send);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst)
{
@@ -206,7 +206,7 @@ EXPORT_SYMBOL(rpmsg_sendto);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
void *data, int len)
@@ -235,7 +235,7 @@ EXPORT_SYMBOL(rpmsg_send_offchannel);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len)
{
@@ -263,7 +263,7 @@ EXPORT_SYMBOL(rpmsg_trysend);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst)
{
@@ -282,7 +282,7 @@ EXPORT_SYMBOL(rpmsg_trysendto);
* @filp: file for poll_wait()
* @wait: poll_table for poll_wait()
*
- * Returns mask representing the current state of the endpoint's send buffers
+ * Return: mask representing the current state of the endpoint's send buffers
*/
__poll_t rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp,
poll_table *wait)
@@ -313,7 +313,7 @@ EXPORT_SYMBOL(rpmsg_poll);
*
* Can only be called from process context (for now).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
void *data, int len)
@@ -540,13 +540,25 @@ static int rpmsg_dev_probe(struct device *dev)
err = rpdrv->probe(rpdev);
if (err) {
dev_err(dev, "%s: failed: %d\n", __func__, err);
- if (ept)
- rpmsg_destroy_ept(ept);
- goto out;
+ goto destroy_ept;
}
- if (ept && rpdev->ops->announce_create)
+ if (ept && rpdev->ops->announce_create) {
err = rpdev->ops->announce_create(rpdev);
+ if (err) {
+ dev_err(dev, "failed to announce creation\n");
+ goto remove_rpdev;
+ }
+ }
+
+ return 0;
+
+remove_rpdev:
+ if (rpdrv->remove)
+ rpdrv->remove(rpdev);
+destroy_ept:
+ if (ept)
+ rpmsg_destroy_ept(ept);
out:
return err;
}
@@ -623,7 +635,7 @@ EXPORT_SYMBOL(rpmsg_unregister_device);
* @rpdrv: pointer to a struct rpmsg_driver
* @owner: owning module/driver
*
- * Returns 0 on success, and an appropriate error value on failure.
+ * Return: 0 on success, and an appropriate error value on failure.
*/
int __register_rpmsg_driver(struct rpmsg_driver *rpdrv, struct module *owner)
{
@@ -637,7 +649,7 @@ EXPORT_SYMBOL(__register_rpmsg_driver);
* unregister_rpmsg_driver() - unregister an rpmsg driver from the rpmsg bus
* @rpdrv: pointer to a struct rpmsg_driver
*
- * Returns 0 on success, and an appropriate error value on failure.
+ * Return: 0 on success, and an appropriate error value on failure.
*/
void unregister_rpmsg_driver(struct rpmsg_driver *rpdrv)
{
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 9c112aa..ac764e0 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -547,7 +547,7 @@ static void rpmsg_downref_sleepers(struct virtproc_info *vrp)
* should use the appropriate rpmsg_{try}send{to, _offchannel} API
* (see include/linux/rpmsg.h).
*
- * Returns 0 on success and an appropriate error value on failure.
+ * Return: 0 on success and an appropriate error value on failure.
*/
static int rpmsg_send_offchannel_raw(struct rpmsg_device *rpdev,
u32 src, u32 dst,
@@ -1024,7 +1024,7 @@ static void rpmsg_remove(struct virtio_device *vdev)
size_t total_buf_space = vrp->num_bufs * vrp->buf_size;
int ret;
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
ret = device_for_each_child(&vdev->dev, NULL, rpmsg_remove_device);
if (ret)
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 058e56a1..d85a3c3 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1216,6 +1216,17 @@
This driver can also be built as a module. If so, the module
will be called rtc-v3020.
+config RTC_DRV_GAMECUBE
+ tristate "Nintendo GameCube, Wii and Wii U RTC"
+ depends on GAMECUBE || WII || COMPILE_TEST
+ select REGMAP
+ help
+ If you say yes here you will get support for the RTC subsystem
+ of the Nintendo GameCube, Wii and Wii U.
+
+ This driver can also be built as a module. If so, the module
+ will be called "rtc-gamecube".
+
config RTC_DRV_WM831X
tristate "Wolfson Microelectronics WM831x RTC"
depends on MFD_WM831X
@@ -1444,6 +1455,19 @@
To compile this driver as a module, choose M here: the
module will be called rtc-sh.
+config RTC_DRV_SUNPLUS
+ tristate "Sunplus SP7021 RTC"
+ depends on SOC_SP7021
+ help
+ Say 'yes' to get support for the real-time clock present in
+ Sunplus SP7021 - a SoC for industrial applications. It provides
+ RTC status check, timer/alarm functionalities, user data
+ reservation with the battery over 2.5V, RTC power status check
+ and battery charge.
+
+ This driver can also be built as a module. If so, the module
+ will be called rtc-sunplus.
+
config RTC_DRV_VR41XX
tristate "NEC VR41XX"
depends on CPU_VR41XX || COMPILE_TEST
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 678a8ef..e92f3e9 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -111,6 +111,7 @@
obj-$(CONFIG_RTC_DRV_MV) += rtc-mv.o
obj-$(CONFIG_RTC_DRV_MXC) += rtc-mxc.o
obj-$(CONFIG_RTC_DRV_MXC_V2) += rtc-mxc_v2.o
+obj-$(CONFIG_RTC_DRV_GAMECUBE) += rtc-gamecube.o
obj-$(CONFIG_RTC_DRV_NTXEC) += rtc-ntxec.o
obj-$(CONFIG_RTC_DRV_OMAP) += rtc-omap.o
obj-$(CONFIG_RTC_DRV_OPAL) += rtc-opal.o
@@ -165,6 +166,7 @@
obj-$(CONFIG_RTC_DRV_STMP) += rtc-stmp3xxx.o
obj-$(CONFIG_RTC_DRV_SUN4V) += rtc-sun4v.o
obj-$(CONFIG_RTC_DRV_SUN6I) += rtc-sun6i.o
+obj-$(CONFIG_RTC_DRV_SUNPLUS) += rtc-sunplus.o
obj-$(CONFIG_RTC_DRV_SUNXI) += rtc-sunxi.o
obj-$(CONFIG_RTC_DRV_TEGRA) += rtc-tegra.o
obj-$(CONFIG_RTC_DRV_TEST) += rtc-test.o
diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c
index e104972..69325ae 100644
--- a/drivers/rtc/dev.c
+++ b/drivers/rtc/dev.c
@@ -391,14 +391,14 @@ static long rtc_dev_ioctl(struct file *file,
}
switch(param.param) {
- long offset;
case RTC_PARAM_FEATURES:
if (param.index != 0)
err = -EINVAL;
param.uvalue = rtc->features[0];
break;
- case RTC_PARAM_CORRECTION:
+ case RTC_PARAM_CORRECTION: {
+ long offset;
mutex_unlock(&rtc->ops_lock);
if (param.index != 0)
return -EINVAL;
@@ -407,7 +407,7 @@ static long rtc_dev_ioctl(struct file *file,
if (err == 0)
param.svalue = offset;
break;
-
+ }
default:
if (rtc->ops->param_get)
err = rtc->ops->param_get(rtc->dev.parent, ¶m);
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 4eb5341..7c006c2 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -222,6 +222,8 @@ static inline void cmos_write_bank2(unsigned char val, unsigned char addr)
static int cmos_read_time(struct device *dev, struct rtc_time *t)
{
+ int ret;
+
/*
* If pm_trace abused the RTC for storage, set the timespec to 0,
* which tells the caller that this RTC value is unusable.
@@ -229,7 +231,12 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t)
if (!pm_trace_rtc_valid())
return -EIO;
- mc146818_get_time(t);
+ ret = mc146818_get_time(t);
+ if (ret < 0) {
+ dev_err_ratelimited(dev, "unable to read current time\n");
+ return ret;
+ }
+
return 0;
}
@@ -242,10 +249,46 @@ static int cmos_set_time(struct device *dev, struct rtc_time *t)
return mc146818_set_time(t);
}
+struct cmos_read_alarm_callback_param {
+ struct cmos_rtc *cmos;
+ struct rtc_time *time;
+ unsigned char rtc_control;
+};
+
+static void cmos_read_alarm_callback(unsigned char __always_unused seconds,
+ void *param_in)
+{
+ struct cmos_read_alarm_callback_param *p =
+ (struct cmos_read_alarm_callback_param *)param_in;
+ struct rtc_time *time = p->time;
+
+ time->tm_sec = CMOS_READ(RTC_SECONDS_ALARM);
+ time->tm_min = CMOS_READ(RTC_MINUTES_ALARM);
+ time->tm_hour = CMOS_READ(RTC_HOURS_ALARM);
+
+ if (p->cmos->day_alrm) {
+ /* ignore upper bits on readback per ACPI spec */
+ time->tm_mday = CMOS_READ(p->cmos->day_alrm) & 0x3f;
+ if (!time->tm_mday)
+ time->tm_mday = -1;
+
+ if (p->cmos->mon_alrm) {
+ time->tm_mon = CMOS_READ(p->cmos->mon_alrm);
+ if (!time->tm_mon)
+ time->tm_mon = -1;
+ }
+ }
+
+ p->rtc_control = CMOS_READ(RTC_CONTROL);
+}
+
static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
- unsigned char rtc_control;
+ struct cmos_read_alarm_callback_param p = {
+ .cmos = cmos,
+ .time = &t->time,
+ };
/* This not only a rtc_op, but also called directly */
if (!is_valid_irq(cmos->irq))
@@ -256,28 +299,18 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
* the future.
*/
- spin_lock_irq(&rtc_lock);
- t->time.tm_sec = CMOS_READ(RTC_SECONDS_ALARM);
- t->time.tm_min = CMOS_READ(RTC_MINUTES_ALARM);
- t->time.tm_hour = CMOS_READ(RTC_HOURS_ALARM);
+ /* Some Intel chipsets disconnect the alarm registers when the clock
+ * update is in progress - during this time reads return bogus values
+ * and writes may fail silently. See for example "7th Generation Intel®
+ * Processor Family I/O for U/Y Platforms [...] Datasheet", section
+ * 27.7.1
+ *
+ * Use the mc146818_avoid_UIP() function to avoid this.
+ */
+ if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p))
+ return -EIO;
- if (cmos->day_alrm) {
- /* ignore upper bits on readback per ACPI spec */
- t->time.tm_mday = CMOS_READ(cmos->day_alrm) & 0x3f;
- if (!t->time.tm_mday)
- t->time.tm_mday = -1;
-
- if (cmos->mon_alrm) {
- t->time.tm_mon = CMOS_READ(cmos->mon_alrm);
- if (!t->time.tm_mon)
- t->time.tm_mon = -1;
- }
- }
-
- rtc_control = CMOS_READ(RTC_CONTROL);
- spin_unlock_irq(&rtc_lock);
-
- if (!(rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+ if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
if (((unsigned)t->time.tm_sec) < 0x60)
t->time.tm_sec = bcd2bin(t->time.tm_sec);
else
@@ -306,7 +339,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
}
}
- t->enabled = !!(rtc_control & RTC_AIE);
+ t->enabled = !!(p.rtc_control & RTC_AIE);
t->pending = 0;
return 0;
@@ -437,10 +470,57 @@ static int cmos_validate_alarm(struct device *dev, struct rtc_wkalrm *t)
return 0;
}
+struct cmos_set_alarm_callback_param {
+ struct cmos_rtc *cmos;
+ unsigned char mon, mday, hrs, min, sec;
+ struct rtc_wkalrm *t;
+};
+
+/* Note: this function may be executed by mc146818_avoid_UIP() more then
+ * once
+ */
+static void cmos_set_alarm_callback(unsigned char __always_unused seconds,
+ void *param_in)
+{
+ struct cmos_set_alarm_callback_param *p =
+ (struct cmos_set_alarm_callback_param *)param_in;
+
+ /* next rtc irq must not be from previous alarm setting */
+ cmos_irq_disable(p->cmos, RTC_AIE);
+
+ /* update alarm */
+ CMOS_WRITE(p->hrs, RTC_HOURS_ALARM);
+ CMOS_WRITE(p->min, RTC_MINUTES_ALARM);
+ CMOS_WRITE(p->sec, RTC_SECONDS_ALARM);
+
+ /* the system may support an "enhanced" alarm */
+ if (p->cmos->day_alrm) {
+ CMOS_WRITE(p->mday, p->cmos->day_alrm);
+ if (p->cmos->mon_alrm)
+ CMOS_WRITE(p->mon, p->cmos->mon_alrm);
+ }
+
+ if (use_hpet_alarm()) {
+ /*
+ * FIXME the HPET alarm glue currently ignores day_alrm
+ * and mon_alrm ...
+ */
+ hpet_set_alarm_time(p->t->time.tm_hour, p->t->time.tm_min,
+ p->t->time.tm_sec);
+ }
+
+ if (p->t->enabled)
+ cmos_irq_enable(p->cmos, RTC_AIE);
+}
+
static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
- unsigned char mon, mday, hrs, min, sec, rtc_control;
+ struct cmos_set_alarm_callback_param p = {
+ .cmos = cmos,
+ .t = t
+ };
+ unsigned char rtc_control;
int ret;
/* This not only a rtc_op, but also called directly */
@@ -451,53 +531,34 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
if (ret < 0)
return ret;
- mon = t->time.tm_mon + 1;
- mday = t->time.tm_mday;
- hrs = t->time.tm_hour;
- min = t->time.tm_min;
- sec = t->time.tm_sec;
-
- rtc_control = CMOS_READ(RTC_CONTROL);
- if (!(rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
- /* Writing 0xff means "don't care" or "match all". */
- mon = (mon <= 12) ? bin2bcd(mon) : 0xff;
- mday = (mday >= 1 && mday <= 31) ? bin2bcd(mday) : 0xff;
- hrs = (hrs < 24) ? bin2bcd(hrs) : 0xff;
- min = (min < 60) ? bin2bcd(min) : 0xff;
- sec = (sec < 60) ? bin2bcd(sec) : 0xff;
- }
+ p.mon = t->time.tm_mon + 1;
+ p.mday = t->time.tm_mday;
+ p.hrs = t->time.tm_hour;
+ p.min = t->time.tm_min;
+ p.sec = t->time.tm_sec;
spin_lock_irq(&rtc_lock);
-
- /* next rtc irq must not be from previous alarm setting */
- cmos_irq_disable(cmos, RTC_AIE);
-
- /* update alarm */
- CMOS_WRITE(hrs, RTC_HOURS_ALARM);
- CMOS_WRITE(min, RTC_MINUTES_ALARM);
- CMOS_WRITE(sec, RTC_SECONDS_ALARM);
-
- /* the system may support an "enhanced" alarm */
- if (cmos->day_alrm) {
- CMOS_WRITE(mday, cmos->day_alrm);
- if (cmos->mon_alrm)
- CMOS_WRITE(mon, cmos->mon_alrm);
- }
-
- if (use_hpet_alarm()) {
- /*
- * FIXME the HPET alarm glue currently ignores day_alrm
- * and mon_alrm ...
- */
- hpet_set_alarm_time(t->time.tm_hour, t->time.tm_min,
- t->time.tm_sec);
- }
-
- if (t->enabled)
- cmos_irq_enable(cmos, RTC_AIE);
-
+ rtc_control = CMOS_READ(RTC_CONTROL);
spin_unlock_irq(&rtc_lock);
+ if (!(rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+ /* Writing 0xff means "don't care" or "match all". */
+ p.mon = (p.mon <= 12) ? bin2bcd(p.mon) : 0xff;
+ p.mday = (p.mday >= 1 && p.mday <= 31) ? bin2bcd(p.mday) : 0xff;
+ p.hrs = (p.hrs < 24) ? bin2bcd(p.hrs) : 0xff;
+ p.min = (p.min < 60) ? bin2bcd(p.min) : 0xff;
+ p.sec = (p.sec < 60) ? bin2bcd(p.sec) : 0xff;
+ }
+
+ /*
+ * Some Intel chipsets disconnect the alarm registers when the clock
+ * update is in progress - during this time writes fail silently.
+ *
+ * Use mc146818_avoid_UIP() to avoid this.
+ */
+ if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p))
+ return -EIO;
+
cmos->alarm_expires = rtc_tm_to_time64(&t->time);
return 0;
@@ -790,16 +851,14 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
rename_region(ports, dev_name(&cmos_rtc.rtc->dev));
- spin_lock_irq(&rtc_lock);
-
- /* Ensure that the RTC is accessible. Bit 6 must be 0! */
- if ((CMOS_READ(RTC_VALID) & 0x40) != 0) {
- spin_unlock_irq(&rtc_lock);
- dev_warn(dev, "not accessible\n");
+ if (!mc146818_does_rtc_work()) {
+ dev_warn(dev, "broken or not accessible\n");
retval = -ENXIO;
goto cleanup1;
}
+ spin_lock_irq(&rtc_lock);
+
if (!(flags & CMOS_RTC_FLAGS_NOFREQ)) {
/* force periodic irq to CMOS reset default of 1024Hz;
*
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index d4b72a9..ee2efb4 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -475,12 +475,14 @@ static int da9063_rtc_probe(struct platform_device *pdev)
da9063_data_to_tm(data, &rtc->alarm_time, rtc);
rtc->rtc_sync = false;
- /*
- * TODO: some models have alarms on a minute boundary but still support
- * real hardware interrupts. Add this once the core supports it.
- */
- if (config->rtc_data_start != RTC_SEC)
- rtc->rtc_dev->uie_unsupported = 1;
+ if (config->rtc_data_start != RTC_SEC) {
+ set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->rtc_dev->features);
+ /*
+ * TODO: some models have alarms on a minute boundary but still
+ * support real hardware interrupts.
+ */
+ clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
+ }
irq_alarm = platform_get_irq_byname(pdev, "ALARM");
if (irq_alarm < 0)
@@ -494,6 +496,8 @@ static int da9063_rtc_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
irq_alarm, ret);
+ device_init_wakeup(&pdev->dev, true);
+
return devm_rtc_register_device(rtc->rtc_dev);
}
diff --git a/drivers/rtc/rtc-ftrtc010.c b/drivers/rtc/rtc-ftrtc010.c
index ad3add5..53bb08f 100644
--- a/drivers/rtc/rtc-ftrtc010.c
+++ b/drivers/rtc/rtc-ftrtc010.c
@@ -141,11 +141,9 @@ static int ftrtc010_rtc_probe(struct platform_device *pdev)
}
}
- res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (!res)
- return -ENODEV;
-
- rtc->rtc_irq = res->start;
+ rtc->rtc_irq = platform_get_irq(pdev, 0);
+ if (rtc->rtc_irq < 0)
+ return rtc->rtc_irq;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res)
diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c
new file mode 100644
index 0000000..f717b36
--- /dev/null
+++ b/drivers/rtc/rtc-gamecube.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Nintendo GameCube, Wii and Wii U RTC driver
+ *
+ * This driver is for the MX23L4005, more specifically its real-time clock and
+ * SRAM storage. The value returned by the RTC counter must be added with the
+ * offset stored in a bias register in SRAM (on the GameCube and Wii) or in
+ * /config/rtc.xml (on the Wii U). The latter being very impractical to access
+ * from Linux, this driver assumes the bootloader has read it and stored it in
+ * SRAM like for the other two consoles.
+ *
+ * This device sits on a bus named EXI (which is similar to SPI), channel 0,
+ * device 1. This driver assumes no other user of the EXI bus, which is
+ * currently the case but would have to be reworked to add support for other
+ * GameCube hardware exposed on this bus.
+ *
+ * References:
+ * - https://wiiubrew.org/wiki/Hardware/RTC
+ * - https://wiibrew.org/wiki/MX23L4005
+ *
+ * Copyright (C) 2018 rw-r-r-0644
+ * Copyright (C) 2021 Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>
+ *
+ * Based on rtc-gcn.c
+ * Copyright (C) 2004-2009 The GameCube Linux Team
+ * Copyright (C) 2005,2008,2009 Albert Herranz
+ * Based on gamecube_time.c from Torben Nielsen.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/time.h>
+
+/* EXI registers */
+#define EXICSR 0
+#define EXICR 12
+#define EXIDATA 16
+
+/* EXI register values */
+#define EXICSR_DEV 0x380
+ #define EXICSR_DEV1 0x100
+#define EXICSR_CLK 0x070
+ #define EXICSR_CLK_1MHZ 0x000
+ #define EXICSR_CLK_2MHZ 0x010
+ #define EXICSR_CLK_4MHZ 0x020
+ #define EXICSR_CLK_8MHZ 0x030
+ #define EXICSR_CLK_16MHZ 0x040
+ #define EXICSR_CLK_32MHZ 0x050
+#define EXICSR_INT 0x008
+ #define EXICSR_INTSET 0x008
+
+#define EXICR_TSTART 0x001
+#define EXICR_TRSMODE 0x002
+ #define EXICR_TRSMODE_IMM 0x000
+#define EXICR_TRSTYPE 0x00C
+ #define EXICR_TRSTYPE_R 0x000
+ #define EXICR_TRSTYPE_W 0x004
+#define EXICR_TLEN 0x030
+ #define EXICR_TLEN32 0x030
+
+/* EXI registers values to access the RTC */
+#define RTC_EXICSR (EXICSR_DEV1 | EXICSR_CLK_8MHZ | EXICSR_INTSET)
+#define RTC_EXICR_W (EXICR_TSTART | EXICR_TRSMODE_IMM | EXICR_TRSTYPE_W | EXICR_TLEN32)
+#define RTC_EXICR_R (EXICR_TSTART | EXICR_TRSMODE_IMM | EXICR_TRSTYPE_R | EXICR_TLEN32)
+#define RTC_EXIDATA_W 0x80000000
+
+/* RTC registers */
+#define RTC_COUNTER 0x200000
+#define RTC_SRAM 0x200001
+#define RTC_SRAM_BIAS 0x200004
+#define RTC_SNAPSHOT 0x204000
+#define RTC_ONTMR 0x210000
+#define RTC_OFFTMR 0x210001
+#define RTC_TEST0 0x210004
+#define RTC_TEST1 0x210005
+#define RTC_TEST2 0x210006
+#define RTC_TEST3 0x210007
+#define RTC_CONTROL0 0x21000c
+#define RTC_CONTROL1 0x21000d
+
+/* RTC flags */
+#define RTC_CONTROL0_UNSTABLE_POWER 0x00000800
+#define RTC_CONTROL0_LOW_BATTERY 0x00000200
+
+struct priv {
+ struct regmap *regmap;
+ void __iomem *iob;
+ u32 rtc_bias;
+};
+
+static int exi_read(void *context, u32 reg, u32 *data)
+{
+ struct priv *d = (struct priv *)context;
+ void __iomem *iob = d->iob;
+
+ /* The spin loops here loop about 15~16 times each, so there is no need
+ * to use a more expensive sleep method.
+ */
+
+ /* Write register offset */
+ iowrite32be(RTC_EXICSR, iob + EXICSR);
+ iowrite32be(reg << 8, iob + EXIDATA);
+ iowrite32be(RTC_EXICR_W, iob + EXICR);
+ while (!(ioread32be(iob + EXICSR) & EXICSR_INTSET))
+ cpu_relax();
+
+ /* Read data */
+ iowrite32be(RTC_EXICSR, iob + EXICSR);
+ iowrite32be(RTC_EXICR_R, iob + EXICR);
+ while (!(ioread32be(iob + EXICSR) & EXICSR_INTSET))
+ cpu_relax();
+ *data = ioread32be(iob + EXIDATA);
+
+ /* Clear channel parameters */
+ iowrite32be(0, iob + EXICSR);
+
+ return 0;
+}
+
+static int exi_write(void *context, u32 reg, u32 data)
+{
+ struct priv *d = (struct priv *)context;
+ void __iomem *iob = d->iob;
+
+ /* The spin loops here loop about 15~16 times each, so there is no need
+ * to use a more expensive sleep method.
+ */
+
+ /* Write register offset */
+ iowrite32be(RTC_EXICSR, iob + EXICSR);
+ iowrite32be(RTC_EXIDATA_W | (reg << 8), iob + EXIDATA);
+ iowrite32be(RTC_EXICR_W, iob + EXICR);
+ while (!(ioread32be(iob + EXICSR) & EXICSR_INTSET))
+ cpu_relax();
+
+ /* Write data */
+ iowrite32be(RTC_EXICSR, iob + EXICSR);
+ iowrite32be(data, iob + EXIDATA);
+ iowrite32be(RTC_EXICR_W, iob + EXICR);
+ while (!(ioread32be(iob + EXICSR) & EXICSR_INTSET))
+ cpu_relax();
+
+ /* Clear channel parameters */
+ iowrite32be(0, iob + EXICSR);
+
+ return 0;
+}
+
+static const struct regmap_bus exi_bus = {
+ /* TODO: is that true? Not that it matters here, but still. */
+ .fast_io = true,
+ .reg_read = exi_read,
+ .reg_write = exi_write,
+};
+
+static int gamecube_rtc_read_time(struct device *dev, struct rtc_time *t)
+{
+ struct priv *d = dev_get_drvdata(dev);
+ int ret;
+ u32 counter;
+ time64_t timestamp;
+
+ ret = regmap_read(d->regmap, RTC_COUNTER, &counter);
+ if (ret)
+ return ret;
+
+ /* Add the counter and the bias to obtain the timestamp */
+ timestamp = (time64_t)d->rtc_bias + counter;
+ rtc_time64_to_tm(timestamp, t);
+
+ return 0;
+}
+
+static int gamecube_rtc_set_time(struct device *dev, struct rtc_time *t)
+{
+ struct priv *d = dev_get_drvdata(dev);
+ time64_t timestamp;
+
+ /* Subtract the timestamp and the bias to obtain the counter value */
+ timestamp = rtc_tm_to_time64(t);
+ return regmap_write(d->regmap, RTC_COUNTER, timestamp - d->rtc_bias);
+}
+
+static int gamecube_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+ struct priv *d = dev_get_drvdata(dev);
+ int value;
+ int control0;
+ int ret;
+
+ switch (cmd) {
+ case RTC_VL_READ:
+ ret = regmap_read(d->regmap, RTC_CONTROL0, &control0);
+ if (ret)
+ return ret;
+
+ value = 0;
+ if (control0 & RTC_CONTROL0_UNSTABLE_POWER)
+ value |= RTC_VL_DATA_INVALID;
+ if (control0 & RTC_CONTROL0_LOW_BATTERY)
+ value |= RTC_VL_BACKUP_LOW;
+ return put_user(value, (unsigned int __user *)arg);
+
+ default:
+ return -ENOIOCTLCMD;
+ }
+}
+
+static const struct rtc_class_ops gamecube_rtc_ops = {
+ .read_time = gamecube_rtc_read_time,
+ .set_time = gamecube_rtc_set_time,
+ .ioctl = gamecube_rtc_ioctl,
+};
+
+static int gamecube_rtc_read_offset_from_sram(struct priv *d)
+{
+ struct device_node *np;
+ int ret;
+ struct resource res;
+ void __iomem *hw_srnprot;
+ u32 old;
+
+ np = of_find_compatible_node(NULL, NULL, "nintendo,latte-srnprot");
+ if (!np)
+ np = of_find_compatible_node(NULL, NULL,
+ "nintendo,hollywood-srnprot");
+ if (!np) {
+ pr_info("HW_SRNPROT not found, assuming a GameCube\n");
+ return regmap_read(d->regmap, RTC_SRAM_BIAS, &d->rtc_bias);
+ }
+
+ ret = of_address_to_resource(np, 0, &res);
+ if (ret) {
+ pr_err("no io memory range found\n");
+ return -1;
+ }
+
+ hw_srnprot = ioremap(res.start, resource_size(&res));
+ old = ioread32be(hw_srnprot);
+
+ /* TODO: figure out why we use this magic constant. I obtained it by
+ * reading the leftover value after boot, after IOSU already ran.
+ *
+ * On my Wii U, setting this register to 1 prevents the console from
+ * rebooting properly, so wiiubrew.org must be missing something.
+ *
+ * See https://wiiubrew.org/wiki/Hardware/Latte_registers
+ */
+ if (old != 0x7bf)
+ iowrite32be(0x7bf, hw_srnprot);
+
+ /* Get the offset from RTC SRAM.
+ *
+ * Its default location on the GameCube and on the Wii is in the SRAM,
+ * while on the Wii U the bootloader needs to fill it with the contents
+ * of /config/rtc.xml on the SLC (the eMMC). We don’t do that from
+ * Linux since it requires implementing a proprietary filesystem and do
+ * file decryption, instead we require the bootloader to fill the same
+ * SRAM address as on previous consoles.
+ */
+ ret = regmap_read(d->regmap, RTC_SRAM_BIAS, &d->rtc_bias);
+ if (ret) {
+ pr_err("failed to get the RTC bias\n");
+ return -1;
+ }
+
+ /* Reset SRAM access to how it was before, our job here is done. */
+ if (old != 0x7bf)
+ iowrite32be(old, hw_srnprot);
+ iounmap(hw_srnprot);
+
+ return 0;
+}
+
+static const struct regmap_range rtc_rd_ranges[] = {
+ regmap_reg_range(0x200000, 0x200010),
+ regmap_reg_range(0x204000, 0x204000),
+ regmap_reg_range(0x210000, 0x210001),
+ regmap_reg_range(0x210004, 0x210007),
+ regmap_reg_range(0x21000c, 0x21000d),
+};
+
+static const struct regmap_access_table rtc_rd_regs = {
+ .yes_ranges = rtc_rd_ranges,
+ .n_yes_ranges = ARRAY_SIZE(rtc_rd_ranges),
+};
+
+static const struct regmap_range rtc_wr_ranges[] = {
+ regmap_reg_range(0x200000, 0x200010),
+ regmap_reg_range(0x204000, 0x204000),
+ regmap_reg_range(0x210000, 0x210001),
+ regmap_reg_range(0x21000d, 0x21000d),
+};
+
+static const struct regmap_access_table rtc_wr_regs = {
+ .yes_ranges = rtc_wr_ranges,
+ .n_yes_ranges = ARRAY_SIZE(rtc_wr_ranges),
+};
+
+static const struct regmap_config gamecube_rtc_regmap_config = {
+ .reg_bits = 24,
+ .val_bits = 32,
+ .rd_table = &rtc_rd_regs,
+ .wr_table = &rtc_wr_regs,
+ .max_register = 0x21000d,
+ .name = "gamecube-rtc",
+};
+
+static int gamecube_rtc_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct rtc_device *rtc;
+ struct priv *d;
+ int ret;
+
+ d = devm_kzalloc(dev, sizeof(struct priv), GFP_KERNEL);
+ if (!d)
+ return -ENOMEM;
+
+ d->iob = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(d->iob))
+ return PTR_ERR(d->iob);
+
+ d->regmap = devm_regmap_init(dev, &exi_bus, d,
+ &gamecube_rtc_regmap_config);
+ if (IS_ERR(d->regmap))
+ return PTR_ERR(d->regmap);
+
+ ret = gamecube_rtc_read_offset_from_sram(d);
+ if (ret)
+ return ret;
+ dev_dbg(dev, "SRAM bias: 0x%x", d->rtc_bias);
+
+ dev_set_drvdata(dev, d);
+
+ rtc = devm_rtc_allocate_device(dev);
+ if (IS_ERR(rtc))
+ return PTR_ERR(rtc);
+
+ /* We can represent further than that, but it depends on the stored
+ * bias and we can’t modify it persistently on all supported consoles,
+ * so here we pretend to be limited to 2106.
+ */
+ rtc->range_min = 0;
+ rtc->range_max = U32_MAX;
+ rtc->ops = &gamecube_rtc_ops;
+
+ devm_rtc_register_device(rtc);
+
+ return 0;
+}
+
+static const struct of_device_id gamecube_rtc_of_match[] = {
+ {.compatible = "nintendo,latte-exi" },
+ {.compatible = "nintendo,hollywood-exi" },
+ {.compatible = "nintendo,flipper-exi" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, gamecube_rtc_of_match);
+
+static struct platform_driver gamecube_rtc_driver = {
+ .probe = gamecube_rtc_probe,
+ .driver = {
+ .name = "rtc-gamecube",
+ .of_match_table = gamecube_rtc_of_match,
+ },
+};
+module_platform_driver(gamecube_rtc_driver);
+
+MODULE_AUTHOR("Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>");
+MODULE_DESCRIPTION("Nintendo GameCube, Wii and Wii U RTC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index dcfaf09..ae9f131 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -8,48 +8,100 @@
#include <linux/acpi.h>
#endif
-unsigned int mc146818_get_time(struct rtc_time *time)
+/*
+ * Execute a function while the UIP (Update-in-progress) bit of the RTC is
+ * unset.
+ *
+ * Warning: callback may be executed more then once.
+ */
+bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+ void *param)
{
- unsigned char ctrl;
+ int i;
unsigned long flags;
- unsigned char century = 0;
- bool retry;
+ unsigned char seconds;
+ for (i = 0; i < 10; i++) {
+ spin_lock_irqsave(&rtc_lock, flags);
+
+ /*
+ * Check whether there is an update in progress during which the
+ * readout is unspecified. The maximum update time is ~2ms. Poll
+ * every msec for completion.
+ *
+ * Store the second value before checking UIP so a long lasting
+ * NMI which happens to hit after the UIP check cannot make
+ * an update cycle invisible.
+ */
+ seconds = CMOS_READ(RTC_SECONDS);
+
+ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
+ spin_unlock_irqrestore(&rtc_lock, flags);
+ mdelay(1);
+ continue;
+ }
+
+ /* Revalidate the above readout */
+ if (seconds != CMOS_READ(RTC_SECONDS)) {
+ spin_unlock_irqrestore(&rtc_lock, flags);
+ continue;
+ }
+
+ if (callback)
+ callback(seconds, param);
+
+ /*
+ * Check for the UIP bit again. If it is set now then
+ * the above values may contain garbage.
+ */
+ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
+ spin_unlock_irqrestore(&rtc_lock, flags);
+ mdelay(1);
+ continue;
+ }
+
+ /*
+ * A NMI might have interrupted the above sequence so check
+ * whether the seconds value has changed which indicates that
+ * the NMI took longer than the UIP bit was set. Unlikely, but
+ * possible and there is also virt...
+ */
+ if (seconds != CMOS_READ(RTC_SECONDS)) {
+ spin_unlock_irqrestore(&rtc_lock, flags);
+ continue;
+ }
+ spin_unlock_irqrestore(&rtc_lock, flags);
+
+ return true;
+ }
+ return false;
+}
+EXPORT_SYMBOL_GPL(mc146818_avoid_UIP);
+
+/*
+ * If the UIP (Update-in-progress) bit of the RTC is set for more then
+ * 10ms, the RTC is apparently broken or not present.
+ */
+bool mc146818_does_rtc_work(void)
+{
+ return mc146818_avoid_UIP(NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
+
+struct mc146818_get_time_callback_param {
+ struct rtc_time *time;
+ unsigned char ctrl;
+#ifdef CONFIG_ACPI
+ unsigned char century;
+#endif
#ifdef CONFIG_MACH_DECSTATION
unsigned int real_year;
#endif
+};
-again:
- spin_lock_irqsave(&rtc_lock, flags);
- /* Ensure that the RTC is accessible. Bit 6 must be 0! */
- if (WARN_ON_ONCE((CMOS_READ(RTC_VALID) & 0x40) != 0)) {
- spin_unlock_irqrestore(&rtc_lock, flags);
- memset(time, 0xff, sizeof(*time));
- return 0;
- }
-
- /*
- * Check whether there is an update in progress during which the
- * readout is unspecified. The maximum update time is ~2ms. Poll
- * every msec for completion.
- *
- * Store the second value before checking UIP so a long lasting NMI
- * which happens to hit after the UIP check cannot make an update
- * cycle invisible.
- */
- time->tm_sec = CMOS_READ(RTC_SECONDS);
-
- if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
- spin_unlock_irqrestore(&rtc_lock, flags);
- mdelay(1);
- goto again;
- }
-
- /* Revalidate the above readout */
- if (time->tm_sec != CMOS_READ(RTC_SECONDS)) {
- spin_unlock_irqrestore(&rtc_lock, flags);
- goto again;
- }
+static void mc146818_get_time_callback(unsigned char seconds, void *param_in)
+{
+ struct mc146818_get_time_callback_param *p = param_in;
/*
* Only the values that we read from the RTC are set. We leave
@@ -57,39 +109,39 @@ unsigned int mc146818_get_time(struct rtc_time *time)
* RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated
* by the RTC when initially set to a non-zero value.
*/
- time->tm_min = CMOS_READ(RTC_MINUTES);
- time->tm_hour = CMOS_READ(RTC_HOURS);
- time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH);
- time->tm_mon = CMOS_READ(RTC_MONTH);
- time->tm_year = CMOS_READ(RTC_YEAR);
+ p->time->tm_sec = seconds;
+ p->time->tm_min = CMOS_READ(RTC_MINUTES);
+ p->time->tm_hour = CMOS_READ(RTC_HOURS);
+ p->time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH);
+ p->time->tm_mon = CMOS_READ(RTC_MONTH);
+ p->time->tm_year = CMOS_READ(RTC_YEAR);
#ifdef CONFIG_MACH_DECSTATION
- real_year = CMOS_READ(RTC_DEC_YEAR);
+ p->real_year = CMOS_READ(RTC_DEC_YEAR);
#endif
#ifdef CONFIG_ACPI
if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
- acpi_gbl_FADT.century)
- century = CMOS_READ(acpi_gbl_FADT.century);
+ acpi_gbl_FADT.century) {
+ p->century = CMOS_READ(acpi_gbl_FADT.century);
+ } else {
+ p->century = 0;
+ }
#endif
- ctrl = CMOS_READ(RTC_CONTROL);
- /*
- * Check for the UIP bit again. If it is set now then
- * the above values may contain garbage.
- */
- retry = CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP;
- /*
- * A NMI might have interrupted the above sequence so check whether
- * the seconds value has changed which indicates that the NMI took
- * longer than the UIP bit was set. Unlikely, but possible and
- * there is also virt...
- */
- retry |= time->tm_sec != CMOS_READ(RTC_SECONDS);
- spin_unlock_irqrestore(&rtc_lock, flags);
+ p->ctrl = CMOS_READ(RTC_CONTROL);
+}
- if (retry)
- goto again;
+int mc146818_get_time(struct rtc_time *time)
+{
+ struct mc146818_get_time_callback_param p = {
+ .time = time
+ };
- if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+ if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) {
+ memset(time, 0, sizeof(*time));
+ return -EIO;
+ }
+
+ if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
{
time->tm_sec = bcd2bin(time->tm_sec);
time->tm_min = bcd2bin(time->tm_min);
@@ -97,15 +149,19 @@ unsigned int mc146818_get_time(struct rtc_time *time)
time->tm_mday = bcd2bin(time->tm_mday);
time->tm_mon = bcd2bin(time->tm_mon);
time->tm_year = bcd2bin(time->tm_year);
- century = bcd2bin(century);
+#ifdef CONFIG_ACPI
+ p.century = bcd2bin(p.century);
+#endif
}
#ifdef CONFIG_MACH_DECSTATION
- time->tm_year += real_year - 72;
+ time->tm_year += p.real_year - 72;
#endif
- if (century > 20)
- time->tm_year += (century - 19) * 100;
+#ifdef CONFIG_ACPI
+ if (p.century > 19)
+ time->tm_year += (p.century - 19) * 100;
+#endif
/*
* Account for differences between how the RTC uses the values
@@ -116,7 +172,7 @@ unsigned int mc146818_get_time(struct rtc_time *time)
time->tm_mon--;
- return RTC_24H;
+ return 0;
}
EXPORT_SYMBOL_GPL(mc146818_get_time);
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 56c58b0..81a5b1f 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -748,7 +748,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
/*
* Enable timestamp function and store timestamp of first trigger
- * event until TSF1 and TFS2 interrupt flags are cleared.
+ * event until TSF1 and TSF2 interrupt flags are cleared.
*/
ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_TS_CTRL,
PCF2127_BIT_TS_CTRL_TSOFF |
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index 15e50bb..df2b072 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -514,21 +514,56 @@ static struct clk *pcf85063_clkout_register_clk(struct pcf85063 *pcf85063)
}
#endif
-static const struct pcf85063_config pcf85063tp_config = {
- .regmap = {
- .reg_bits = 8,
- .val_bits = 8,
- .max_register = 0x0a,
+enum pcf85063_type {
+ PCF85063,
+ PCF85063TP,
+ PCF85063A,
+ RV8263,
+ PCF85063_LAST_ID
+};
+
+static struct pcf85063_config pcf85063_cfg[] = {
+ [PCF85063] = {
+ .regmap = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .max_register = 0x0a,
+ },
+ },
+ [PCF85063TP] = {
+ .regmap = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .max_register = 0x0a,
+ },
+ },
+ [PCF85063A] = {
+ .regmap = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .max_register = 0x11,
+ },
+ .has_alarms = 1,
+ },
+ [RV8263] = {
+ .regmap = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .max_register = 0x11,
+ },
+ .has_alarms = 1,
+ .force_cap_7000 = 1,
},
};
+static const struct i2c_device_id pcf85063_ids[];
+
static int pcf85063_probe(struct i2c_client *client)
{
struct pcf85063 *pcf85063;
unsigned int tmp;
int err;
- const struct pcf85063_config *config = &pcf85063tp_config;
- const void *data = of_device_get_match_data(&client->dev);
+ const struct pcf85063_config *config;
struct nvmem_config nvmem_cfg = {
.name = "pcf85063_nvram",
.reg_read = pcf85063_nvmem_read,
@@ -544,8 +579,17 @@ static int pcf85063_probe(struct i2c_client *client)
if (!pcf85063)
return -ENOMEM;
- if (data)
- config = data;
+ if (client->dev.of_node) {
+ config = of_device_get_match_data(&client->dev);
+ if (!config)
+ return -ENODEV;
+ } else {
+ enum pcf85063_type type =
+ i2c_match_id(pcf85063_ids, client)->driver_data;
+ if (type >= PCF85063_LAST_ID)
+ return -ENODEV;
+ config = &pcf85063_cfg[type];
+ }
pcf85063->regmap = devm_regmap_init_i2c(client, &config->regmap);
if (IS_ERR(pcf85063->regmap))
@@ -604,31 +648,21 @@ static int pcf85063_probe(struct i2c_client *client)
return devm_rtc_register_device(pcf85063->rtc);
}
+static const struct i2c_device_id pcf85063_ids[] = {
+ { "pcf85063", PCF85063 },
+ { "pcf85063tp", PCF85063TP },
+ { "pcf85063a", PCF85063A },
+ { "rv8263", RV8263 },
+ {}
+};
+MODULE_DEVICE_TABLE(i2c, pcf85063_ids);
+
#ifdef CONFIG_OF
-static const struct pcf85063_config pcf85063a_config = {
- .regmap = {
- .reg_bits = 8,
- .val_bits = 8,
- .max_register = 0x11,
- },
- .has_alarms = 1,
-};
-
-static const struct pcf85063_config rv8263_config = {
- .regmap = {
- .reg_bits = 8,
- .val_bits = 8,
- .max_register = 0x11,
- },
- .has_alarms = 1,
- .force_cap_7000 = 1,
-};
-
static const struct of_device_id pcf85063_of_match[] = {
- { .compatible = "nxp,pcf85063", .data = &pcf85063tp_config },
- { .compatible = "nxp,pcf85063tp", .data = &pcf85063tp_config },
- { .compatible = "nxp,pcf85063a", .data = &pcf85063a_config },
- { .compatible = "microcrystal,rv8263", .data = &rv8263_config },
+ { .compatible = "nxp,pcf85063", .data = &pcf85063_cfg[PCF85063] },
+ { .compatible = "nxp,pcf85063tp", .data = &pcf85063_cfg[PCF85063TP] },
+ { .compatible = "nxp,pcf85063a", .data = &pcf85063_cfg[PCF85063A] },
+ { .compatible = "microcrystal,rv8263", .data = &pcf85063_cfg[RV8263] },
{}
};
MODULE_DEVICE_TABLE(of, pcf85063_of_match);
@@ -640,6 +674,7 @@ static struct i2c_driver pcf85063_driver = {
.of_match_table = of_match_ptr(pcf85063_of_match),
},
.probe_new = pcf85063_probe,
+ .id_table = pcf85063_ids,
};
module_i2c_driver(pcf85063_driver);
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index d2f1d8f..cf8119b 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -330,6 +330,10 @@ static int __init pxa_rtc_probe(struct platform_device *pdev)
if (sa1100_rtc->irq_alarm < 0)
return -ENXIO;
+ sa1100_rtc->rtc = devm_rtc_allocate_device(&pdev->dev);
+ if (IS_ERR(sa1100_rtc->rtc))
+ return PTR_ERR(sa1100_rtc->rtc);
+
pxa_rtc->base = devm_ioremap(dev, pxa_rtc->ress->start,
resource_size(pxa_rtc->ress));
if (!pxa_rtc->base) {
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index 8098041..cb15983 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -28,8 +28,10 @@
#define RS5C372_REG_MONTH 5
#define RS5C372_REG_YEAR 6
#define RS5C372_REG_TRIM 7
-# define RS5C372_TRIM_XSL 0x80
+# define RS5C372_TRIM_XSL 0x80 /* only if RS5C372[a|b] */
# define RS5C372_TRIM_MASK 0x7F
+# define R2221TL_TRIM_DEV (1 << 7) /* only if R2221TL */
+# define RS5C372_TRIM_DECR (1 << 6)
#define RS5C_REG_ALARM_A_MIN 8 /* or ALARM_W */
#define RS5C_REG_ALARM_A_HOURS 9
@@ -324,8 +326,12 @@ static int rs5c372_get_trim(struct i2c_client *client, int *osc, int *trim)
struct rs5c372 *rs5c372 = i2c_get_clientdata(client);
u8 tmp = rs5c372->regs[RS5C372_REG_TRIM];
- if (osc)
- *osc = (tmp & RS5C372_TRIM_XSL) ? 32000 : 32768;
+ if (osc) {
+ if (rs5c372->type == rtc_rs5c372a || rs5c372->type == rtc_rs5c372b)
+ *osc = (tmp & RS5C372_TRIM_XSL) ? 32000 : 32768;
+ else
+ *osc = 32768;
+ }
if (trim) {
dev_dbg(&client->dev, "%s: raw trim=%x\n", __func__, tmp);
@@ -485,6 +491,176 @@ static int rs5c372_rtc_proc(struct device *dev, struct seq_file *seq)
#define rs5c372_rtc_proc NULL
#endif
+#ifdef CONFIG_RTC_INTF_DEV
+static int rs5c372_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+ struct rs5c372 *rs5c = i2c_get_clientdata(to_i2c_client(dev));
+ unsigned char ctrl2;
+ int addr;
+ unsigned int flags;
+
+ dev_dbg(dev, "%s: cmd=%x\n", __func__, cmd);
+
+ addr = RS5C_ADDR(RS5C_REG_CTRL2);
+ ctrl2 = i2c_smbus_read_byte_data(rs5c->client, addr);
+
+ switch (cmd) {
+ case RTC_VL_READ:
+ flags = 0;
+
+ switch (rs5c->type) {
+ case rtc_r2025sd:
+ case rtc_r2221tl:
+ if ((rs5c->type == rtc_r2025sd && !(ctrl2 & R2x2x_CTRL2_XSTP)) ||
+ (rs5c->type == rtc_r2221tl && (ctrl2 & R2x2x_CTRL2_XSTP))) {
+ flags |= RTC_VL_DATA_INVALID;
+ }
+ if (ctrl2 & R2x2x_CTRL2_VDET)
+ flags |= RTC_VL_BACKUP_LOW;
+ break;
+ default:
+ if (ctrl2 & RS5C_CTRL2_XSTP)
+ flags |= RTC_VL_DATA_INVALID;
+ break;
+ }
+
+ return put_user(flags, (unsigned int __user *)arg);
+ case RTC_VL_CLR:
+ /* clear VDET bit */
+ if (rs5c->type == rtc_r2025sd || rs5c->type == rtc_r2221tl) {
+ ctrl2 &= ~R2x2x_CTRL2_VDET;
+ if (i2c_smbus_write_byte_data(rs5c->client, addr, ctrl2) < 0) {
+ dev_dbg(&rs5c->client->dev, "%s: write error in line %i\n",
+ __func__, __LINE__);
+ return -EIO;
+ }
+ }
+ return 0;
+ default:
+ return -ENOIOCTLCMD;
+ }
+ return 0;
+}
+#else
+#define rs5c372_ioctl NULL
+#endif
+
+static int rs5c372_read_offset(struct device *dev, long *offset)
+{
+ struct rs5c372 *rs5c = i2c_get_clientdata(to_i2c_client(dev));
+ u8 val = rs5c->regs[RS5C372_REG_TRIM];
+ long ppb_per_step = 0;
+ bool decr = val & RS5C372_TRIM_DECR;
+
+ switch (rs5c->type) {
+ case rtc_r2221tl:
+ ppb_per_step = val & R2221TL_TRIM_DEV ? 1017 : 3051;
+ break;
+ case rtc_rs5c372a:
+ case rtc_rs5c372b:
+ ppb_per_step = val & RS5C372_TRIM_XSL ? 3125 : 3051;
+ break;
+ default:
+ ppb_per_step = 3051;
+ break;
+ }
+
+ /* Only bits[0:5] repsents the time counts */
+ val &= 0x3F;
+
+ /* If bits[1:5] are all 0, it means no increment or decrement */
+ if (!(val & 0x3E)) {
+ *offset = 0;
+ } else {
+ if (decr)
+ *offset = -(((~val) & 0x3F) + 1) * ppb_per_step;
+ else
+ *offset = (val - 1) * ppb_per_step;
+ }
+
+ return 0;
+}
+
+static int rs5c372_set_offset(struct device *dev, long offset)
+{
+ struct rs5c372 *rs5c = i2c_get_clientdata(to_i2c_client(dev));
+ int addr = RS5C_ADDR(RS5C372_REG_TRIM);
+ u8 val = 0;
+ u8 tmp = 0;
+ long ppb_per_step = 3051;
+ long steps = LONG_MIN;
+
+ switch (rs5c->type) {
+ case rtc_rs5c372a:
+ case rtc_rs5c372b:
+ tmp = rs5c->regs[RS5C372_REG_TRIM];
+ if (tmp & RS5C372_TRIM_XSL) {
+ ppb_per_step = 3125;
+ val |= RS5C372_TRIM_XSL;
+ }
+ break;
+ case rtc_r2221tl:
+ /*
+ * Check if it is possible to use high resolution mode (DEV=1).
+ * In this mode, the minimum resolution is 2 / (32768 * 20 * 3),
+ * which is about 1017 ppb.
+ */
+ steps = DIV_ROUND_CLOSEST(offset, 1017);
+ if (steps >= -0x3E && steps <= 0x3E) {
+ ppb_per_step = 1017;
+ val |= R2221TL_TRIM_DEV;
+ } else {
+ /*
+ * offset is out of the range of high resolution mode.
+ * Try to use low resolution mode (DEV=0). In this mode,
+ * the minimum resolution is 2 / (32768 * 20), which is
+ * about 3051 ppb.
+ */
+ steps = LONG_MIN;
+ }
+ break;
+ default:
+ break;
+ }
+
+ if (steps == LONG_MIN) {
+ steps = DIV_ROUND_CLOSEST(offset, ppb_per_step);
+ if (steps > 0x3E || steps < -0x3E)
+ return -ERANGE;
+ }
+
+ if (steps > 0) {
+ val |= steps + 1;
+ } else {
+ val |= RS5C372_TRIM_DECR;
+ val |= (~(-steps - 1)) & 0x3F;
+ }
+
+ if (!steps || !(val & 0x3E)) {
+ /*
+ * if offset is too small, set oscillation adjustment register
+ * or time trimming register with its default value whic means
+ * no increment or decrement. But for rs5c372[a|b], the XSL bit
+ * should be kept unchanged.
+ */
+ if (rs5c->type == rtc_rs5c372a || rs5c->type == rtc_rs5c372b)
+ val &= RS5C372_TRIM_XSL;
+ else
+ val = 0;
+ }
+
+ dev_dbg(&rs5c->client->dev, "write 0x%x for offset %ld\n", val, offset);
+
+ if (i2c_smbus_write_byte_data(rs5c->client, addr, val) < 0) {
+ dev_err(&rs5c->client->dev, "failed to write 0x%x to reg %d\n", val, addr);
+ return -EIO;
+ }
+
+ rs5c->regs[RS5C372_REG_TRIM] = val;
+
+ return 0;
+}
+
static const struct rtc_class_ops rs5c372_rtc_ops = {
.proc = rs5c372_rtc_proc,
.read_time = rs5c372_rtc_read_time,
@@ -492,6 +668,9 @@ static const struct rtc_class_ops rs5c372_rtc_ops = {
.read_alarm = rs5c_read_alarm,
.set_alarm = rs5c_set_alarm,
.alarm_irq_enable = rs5c_rtc_alarm_irq_enable,
+ .ioctl = rs5c372_ioctl,
+ .read_offset = rs5c372_read_offset,
+ .set_offset = rs5c372_set_offset,
};
#if IS_ENABLED(CONFIG_RTC_INTF_SYSFS)
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 0d5ed38..f69e0b1 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -55,6 +55,7 @@
enum rv8803_type {
rv_8803,
+ rx_8804,
rx_8900
};
@@ -601,6 +602,7 @@ static int rv8803_probe(struct i2c_client *client,
static const struct i2c_device_id rv8803_id[] = {
{ "rv8803", rv_8803 },
+ { "rv8804", rx_8804 },
{ "rx8803", rv_8803 },
{ "rx8900", rx_8900 },
{ }
@@ -617,6 +619,10 @@ static const __maybe_unused struct of_device_id rv8803_of_match[] = {
.data = (void *)rv_8803
},
{
+ .compatible = "epson,rx8804",
+ .data = (void *)rx_8804
+ },
+ {
.compatible = "epson,rx8900",
.data = (void *)rx_8900
},
diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c
new file mode 100644
index 0000000..e8e2ab1
--- /dev/null
+++ b/drivers/rtc/rtc-sunplus.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * The RTC driver for Sunplus SP7021
+ *
+ * Copyright (C) 2019 Sunplus Technology Inc., All rights reseerved.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/rtc.h>
+
+#define RTC_REG_NAME "rtc"
+
+#define RTC_CTRL 0x40
+#define TIMER_FREEZE_MASK_BIT BIT(5 + 16)
+#define TIMER_FREEZE BIT(5)
+#define DIS_SYS_RST_RTC_MASK_BIT BIT(4 + 16)
+#define DIS_SYS_RST_RTC BIT(4)
+#define RTC32K_MODE_RESET_MASK_BIT BIT(3 + 16)
+#define RTC32K_MODE_RESET BIT(3)
+#define ALARM_EN_OVERDUE_MASK_BIT BIT(2 + 16)
+#define ALARM_EN_OVERDUE BIT(2)
+#define ALARM_EN_PMC_MASK_BIT BIT(1 + 16)
+#define ALARM_EN_PMC BIT(1)
+#define ALARM_EN_MASK_BIT BIT(0 + 16)
+#define ALARM_EN BIT(0)
+#define RTC_TIMER_OUT 0x44
+#define RTC_DIVIDER 0x48
+#define RTC_TIMER_SET 0x4c
+#define RTC_ALARM_SET 0x50
+#define RTC_USER_DATA 0x54
+#define RTC_RESET_RECORD 0x58
+#define RTC_BATT_CHARGE_CTRL 0x5c
+#define BAT_CHARGE_RSEL_MASK_BIT GENMASK(3 + 16, 2 + 16)
+#define BAT_CHARGE_RSEL_MASK GENMASK(3, 2)
+#define BAT_CHARGE_RSEL_2K_OHM FIELD_PREP(BAT_CHARGE_RSEL_MASK, 0)
+#define BAT_CHARGE_RSEL_250_OHM FIELD_PREP(BAT_CHARGE_RSEL_MASK, 1)
+#define BAT_CHARGE_RSEL_50_OHM FIELD_PREP(BAT_CHARGE_RSEL_MASK, 2)
+#define BAT_CHARGE_RSEL_0_OHM FIELD_PREP(BAT_CHARGE_RSEL_MASK, 3)
+#define BAT_CHARGE_DSEL_MASK_BIT BIT(1 + 16)
+#define BAT_CHARGE_DSEL_MASK GENMASK(1, 1)
+#define BAT_CHARGE_DSEL_ON FIELD_PREP(BAT_CHARGE_DSEL_MASK, 0)
+#define BAT_CHARGE_DSEL_OFF FIELD_PREP(BAT_CHARGE_DSEL_MASK, 1)
+#define BAT_CHARGE_EN_MASK_BIT BIT(0 + 16)
+#define BAT_CHARGE_EN BIT(0)
+#define RTC_TRIM_CTRL 0x60
+
+struct sunplus_rtc {
+ struct rtc_device *rtc;
+ struct resource *res;
+ struct clk *rtcclk;
+ struct reset_control *rstc;
+ void __iomem *reg_base;
+ int irq;
+};
+
+static void sp_get_seconds(struct device *dev, unsigned long *secs)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+
+ *secs = (unsigned long)readl(sp_rtc->reg_base + RTC_TIMER_OUT);
+}
+
+static void sp_set_seconds(struct device *dev, unsigned long secs)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+
+ writel((u32)secs, sp_rtc->reg_base + RTC_TIMER_SET);
+}
+
+static int sp_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+ unsigned long secs;
+
+ sp_get_seconds(dev, &secs);
+ rtc_time64_to_tm(secs, tm);
+
+ return 0;
+}
+
+static int sp_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+ unsigned long secs;
+
+ secs = rtc_tm_to_time64(tm);
+ dev_dbg(dev, "%s, secs = %lu\n", __func__, secs);
+ sp_set_seconds(dev, secs);
+
+ return 0;
+}
+
+static int sp_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+ unsigned long alarm_time;
+
+ alarm_time = rtc_tm_to_time64(&alrm->time);
+ dev_dbg(dev, "%s, alarm_time: %u\n", __func__, (u32)(alarm_time));
+ writel((u32)alarm_time, sp_rtc->reg_base + RTC_ALARM_SET);
+
+ return 0;
+}
+
+static int sp_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+ unsigned int alarm_time;
+
+ alarm_time = readl(sp_rtc->reg_base + RTC_ALARM_SET);
+ dev_dbg(dev, "%s, alarm_time: %u\n", __func__, alarm_time);
+
+ if (alarm_time == 0)
+ alrm->enabled = 0;
+ else
+ alrm->enabled = 1;
+
+ rtc_time64_to_tm((unsigned long)(alarm_time), &alrm->time);
+
+ return 0;
+}
+
+static int sp_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+
+ if (enabled)
+ writel((TIMER_FREEZE_MASK_BIT | DIS_SYS_RST_RTC_MASK_BIT |
+ RTC32K_MODE_RESET_MASK_BIT | ALARM_EN_OVERDUE_MASK_BIT |
+ ALARM_EN_PMC_MASK_BIT | ALARM_EN_MASK_BIT) |
+ (DIS_SYS_RST_RTC | ALARM_EN_OVERDUE | ALARM_EN_PMC | ALARM_EN),
+ sp_rtc->reg_base + RTC_CTRL);
+ else
+ writel((ALARM_EN_OVERDUE_MASK_BIT | ALARM_EN_PMC_MASK_BIT | ALARM_EN_MASK_BIT) |
+ 0x0, sp_rtc->reg_base + RTC_CTRL);
+
+ return 0;
+}
+
+static const struct rtc_class_ops sp_rtc_ops = {
+ .read_time = sp_rtc_read_time,
+ .set_time = sp_rtc_set_time,
+ .set_alarm = sp_rtc_set_alarm,
+ .read_alarm = sp_rtc_read_alarm,
+ .alarm_irq_enable = sp_rtc_alarm_irq_enable,
+};
+
+static irqreturn_t sp_rtc_irq_handler(int irq, void *dev_id)
+{
+ struct platform_device *plat_dev = dev_id;
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev);
+
+ rtc_update_irq(sp_rtc->rtc, 1, RTC_IRQF | RTC_AF);
+ dev_dbg(&plat_dev->dev, "[RTC] ALARM INT\n");
+
+ return IRQ_HANDLED;
+}
+
+/*
+ * -------------------------------------------------------------------------------------
+ * bat_charge_rsel bat_charge_dsel bat_charge_en Remarks
+ * x x 0 Disable
+ * 0 0 1 0.86mA (2K Ohm with diode)
+ * 1 0 1 1.81mA (250 Ohm with diode)
+ * 2 0 1 2.07mA (50 Ohm with diode)
+ * 3 0 1 16.0mA (0 Ohm with diode)
+ * 0 1 1 1.36mA (2K Ohm without diode)
+ * 1 1 1 3.99mA (250 Ohm without diode)
+ * 2 1 1 4.41mA (50 Ohm without diode)
+ * 3 1 1 16.0mA (0 Ohm without diode)
+ * -------------------------------------------------------------------------------------
+ */
+static void sp_rtc_set_trickle_charger(struct device dev)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(&dev);
+ u32 ohms, rsel;
+ u32 chargeable;
+
+ if (of_property_read_u32(dev.of_node, "trickle-resistor-ohms", &ohms) ||
+ of_property_read_u32(dev.of_node, "aux-voltage-chargeable", &chargeable)) {
+ dev_warn(&dev, "battery charger disabled\n");
+ return;
+ }
+
+ switch (ohms) {
+ case 2000:
+ rsel = BAT_CHARGE_RSEL_2K_OHM;
+ break;
+ case 250:
+ rsel = BAT_CHARGE_RSEL_250_OHM;
+ break;
+ case 50:
+ rsel = BAT_CHARGE_RSEL_50_OHM;
+ break;
+ case 0:
+ rsel = BAT_CHARGE_RSEL_0_OHM;
+ break;
+ default:
+ dev_err(&dev, "invalid charger resistor value (%d)\n", ohms);
+ return;
+ }
+
+ writel(BAT_CHARGE_RSEL_MASK_BIT | rsel, sp_rtc->reg_base + RTC_BATT_CHARGE_CTRL);
+
+ switch (chargeable) {
+ case 0:
+ writel(BAT_CHARGE_DSEL_MASK_BIT | BAT_CHARGE_DSEL_OFF,
+ sp_rtc->reg_base + RTC_BATT_CHARGE_CTRL);
+ break;
+ case 1:
+ writel(BAT_CHARGE_DSEL_MASK_BIT | BAT_CHARGE_DSEL_ON,
+ sp_rtc->reg_base + RTC_BATT_CHARGE_CTRL);
+ break;
+ default:
+ dev_err(&dev, "invalid aux-voltage-chargeable value (%d)\n", chargeable);
+ return;
+ }
+
+ writel(BAT_CHARGE_EN_MASK_BIT | BAT_CHARGE_EN, sp_rtc->reg_base + RTC_BATT_CHARGE_CTRL);
+}
+
+static int sp_rtc_probe(struct platform_device *plat_dev)
+{
+ struct sunplus_rtc *sp_rtc;
+ int ret;
+
+ sp_rtc = devm_kzalloc(&plat_dev->dev, sizeof(*sp_rtc), GFP_KERNEL);
+ if (!sp_rtc)
+ return -ENOMEM;
+
+ sp_rtc->res = platform_get_resource_byname(plat_dev, IORESOURCE_MEM, RTC_REG_NAME);
+ sp_rtc->reg_base = devm_ioremap_resource(&plat_dev->dev, sp_rtc->res);
+ if (IS_ERR(sp_rtc->reg_base))
+ return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base),
+ "%s devm_ioremap_resource fail\n", RTC_REG_NAME);
+ dev_dbg(&plat_dev->dev, "res = 0x%x, reg_base = 0x%lx\n",
+ sp_rtc->res->start, (unsigned long)sp_rtc->reg_base);
+
+ sp_rtc->irq = platform_get_irq(plat_dev, 0);
+ if (sp_rtc->irq < 0)
+ return dev_err_probe(&plat_dev->dev, sp_rtc->irq, "platform_get_irq failed\n");
+
+ ret = devm_request_irq(&plat_dev->dev, sp_rtc->irq, sp_rtc_irq_handler,
+ IRQF_TRIGGER_RISING, "rtc irq", plat_dev);
+ if (ret)
+ return dev_err_probe(&plat_dev->dev, ret, "devm_request_irq failed:\n");
+
+ sp_rtc->rtcclk = devm_clk_get(&plat_dev->dev, NULL);
+ if (IS_ERR(sp_rtc->rtcclk))
+ return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->rtcclk),
+ "devm_clk_get fail\n");
+
+ sp_rtc->rstc = devm_reset_control_get_exclusive(&plat_dev->dev, NULL);
+ if (IS_ERR(sp_rtc->rstc))
+ return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->rstc),
+ "failed to retrieve reset controller\n");
+
+ ret = clk_prepare_enable(sp_rtc->rtcclk);
+ if (ret)
+ goto free_clk;
+
+ ret = reset_control_deassert(sp_rtc->rstc);
+ if (ret)
+ goto free_reset_assert;
+
+ device_init_wakeup(&plat_dev->dev, 1);
+ dev_set_drvdata(&plat_dev->dev, sp_rtc);
+
+ sp_rtc->rtc = devm_rtc_allocate_device(&plat_dev->dev);
+ if (IS_ERR(sp_rtc->rtc)) {
+ ret = PTR_ERR(sp_rtc->rtc);
+ goto free_reset_assert;
+ }
+
+ sp_rtc->rtc->range_max = U32_MAX;
+ sp_rtc->rtc->range_min = 0;
+ sp_rtc->rtc->ops = &sp_rtc_ops;
+
+ ret = devm_rtc_register_device(sp_rtc->rtc);
+ if (ret)
+ goto free_reset_assert;
+
+ /* Setup trickle charger */
+ if (plat_dev->dev.of_node)
+ sp_rtc_set_trickle_charger(plat_dev->dev);
+
+ /* Keep RTC from system reset */
+ writel(DIS_SYS_RST_RTC_MASK_BIT | DIS_SYS_RST_RTC, sp_rtc->reg_base + RTC_CTRL);
+
+ return 0;
+
+free_reset_assert:
+ reset_control_assert(sp_rtc->rstc);
+free_clk:
+ clk_disable_unprepare(sp_rtc->rtcclk);
+
+ return ret;
+}
+
+static int sp_rtc_remove(struct platform_device *plat_dev)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev);
+
+ device_init_wakeup(&plat_dev->dev, 0);
+ reset_control_assert(sp_rtc->rstc);
+ clk_disable_unprepare(sp_rtc->rtcclk);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int sp_rtc_suspend(struct device *dev)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+
+ if (device_may_wakeup(dev))
+ enable_irq_wake(sp_rtc->irq);
+
+ return 0;
+}
+
+static int sp_rtc_resume(struct device *dev)
+{
+ struct sunplus_rtc *sp_rtc = dev_get_drvdata(dev);
+
+ if (device_may_wakeup(dev))
+ disable_irq_wake(sp_rtc->irq);
+
+ return 0;
+}
+#endif
+
+static const struct of_device_id sp_rtc_of_match[] = {
+ { .compatible = "sunplus,sp7021-rtc" },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sp_rtc_of_match);
+
+static SIMPLE_DEV_PM_OPS(sp_rtc_pm_ops, sp_rtc_suspend, sp_rtc_resume);
+
+static struct platform_driver sp_rtc_driver = {
+ .probe = sp_rtc_probe,
+ .remove = sp_rtc_remove,
+ .driver = {
+ .name = "sp7021-rtc",
+ .of_match_table = sp_rtc_of_match,
+ .pm = &sp_rtc_pm_ops,
+ },
+};
+module_platform_driver(sp_rtc_driver);
+
+MODULE_AUTHOR("Vincent Shih <vincent.sunplus@gmail.com>");
+MODULE_DESCRIPTION("Sunplus RTC driver");
+MODULE_LICENSE("GPL v2");
+
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 59f6b7b..b04d039 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -271,7 +271,7 @@ MODULE_PARM_DESC(msi, "IRQ handling."
" 0=PIC(default), 1=MSI, 2=MSI-X)");
module_param(startup_timeout, int, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(startup_timeout, "The duration of time in seconds to wait for"
- " adapter to have it's kernel up and\n"
+ " adapter to have its kernel up and\n"
"running. This is typically adjusted for large systems that do not"
" have a BIOS.");
module_param(aif_timeout, int, S_IRUGO|S_IWUSR);
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 5d566d2..9280991 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -755,11 +755,7 @@ ahd_linux_biosparam(struct scsi_device *sdev, struct block_device *bdev,
static int
ahd_linux_abort(struct scsi_cmnd *cmd)
{
- int error;
-
- error = ahd_linux_queue_abort_cmd(cmd);
-
- return error;
+ return ahd_linux_queue_abort_cmd(cmd);
}
/*
diff --git a/drivers/scsi/elx/efct/efct_driver.c b/drivers/scsi/elx/efct/efct_driver.c
index ae62fc3..b08fc88 100644
--- a/drivers/scsi/elx/efct/efct_driver.c
+++ b/drivers/scsi/elx/efct/efct_driver.c
@@ -541,13 +541,10 @@ efct_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_set_drvdata(pdev, efct);
- if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) != 0) {
- dev_warn(&pdev->dev, "trying DMA_BIT_MASK(32)\n");
- if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)) != 0) {
- dev_err(&pdev->dev, "setting DMA_BIT_MASK failed\n");
- rc = -1;
- goto dma_mask_out;
- }
+ rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (rc) {
+ dev_err(&pdev->dev, "setting DMA_BIT_MASK failed\n");
+ goto dma_mask_out;
}
num_interrupts = efct_device_interrupts_required(efct);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index f46f679..a05ec7a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1525,16 +1525,11 @@ static void hisi_sas_send_ata_reset_each_phy(struct hisi_hba *hisi_hba,
struct device *dev = hisi_hba->dev;
int s = sizeof(struct host_to_dev_fis);
int rc = TMF_RESP_FUNC_FAILED;
- struct asd_sas_phy *sas_phy;
struct ata_link *link;
u8 fis[20] = {0};
- u32 state;
int i;
- state = hisi_hba->hw->get_phys_state(hisi_hba);
for (i = 0; i < hisi_hba->n_phy; i++) {
- if (!(state & BIT(sas_phy->id)))
- continue;
if (!(sas_port->phy_mask & BIT(i)))
continue;
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 0d31d7a..bf987f3 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -192,23 +192,21 @@ mega_query_adapter(adapter_t *adapter)
{
dma_addr_t prod_info_dma_handle;
mega_inquiry3 *inquiry3;
- u8 raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ u8 *raw_mbox = (u8 *)&mbox;
int retval;
/* Initialize adapter inquiry mailbox */
- mbox = (mbox_t *)raw_mbox;
-
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
/*
* Try to issue Inquiry3 command
* if not succeeded, then issue MEGA_MBOXCMD_ADAPTERINQ command and
* update enquiry3 structure
*/
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
inquiry3 = (mega_inquiry3 *)adapter->mega_buffer;
@@ -232,10 +230,10 @@ mega_query_adapter(adapter_t *adapter)
inq = &ext_inq->raid_inq;
- mbox->m_out.xferaddr = (u32)dma_handle;
+ mbox.xferaddr = (u32)dma_handle;
/*issue old 0x04 command to adapter */
- mbox->m_out.cmd = MEGA_MBOXCMD_ADPEXTINQ;
+ mbox.cmd = MEGA_MBOXCMD_ADPEXTINQ;
issue_scb_block(adapter, raw_mbox);
@@ -262,7 +260,7 @@ mega_query_adapter(adapter_t *adapter)
sizeof(mega_product_info),
DMA_FROM_DEVICE);
- mbox->m_out.xferaddr = prod_info_dma_handle;
+ mbox.xferaddr = prod_info_dma_handle;
raw_mbox[0] = FC_NEW_CONFIG; /* i.e. mbox->cmd=0xA1 */
raw_mbox[2] = NC_SUBOP_PRODUCT_INFO; /* i.e. 0x0E */
@@ -3569,16 +3567,14 @@ mega_n_to_m(void __user *arg, megacmd_t *mc)
static int
mega_is_bios_enabled(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
- mbox = (mbox_t *)raw_mbox;
-
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
raw_mbox[0] = IS_BIOS_ENABLED;
raw_mbox[2] = GET_BIOS;
@@ -3600,13 +3596,11 @@ mega_is_bios_enabled(adapter_t *adapter)
static void
mega_enum_raid_scsi(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
int i;
- mbox = (mbox_t *)raw_mbox;
-
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
/*
* issue command to find out what channels are raid/scsi
@@ -3616,7 +3610,7 @@ mega_enum_raid_scsi(adapter_t *adapter)
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
/*
* Non-ROMB firmware fail this command, so all channels
@@ -3655,23 +3649,21 @@ static void
mega_get_boot_drv(adapter_t *adapter)
{
struct private_bios_data *prv_bios_data;
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
u16 cksum = 0;
u8 *cksum_p;
u8 boot_pdrv;
int i;
- mbox = (mbox_t *)raw_mbox;
-
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
raw_mbox[0] = BIOS_PVT_DATA;
raw_mbox[2] = GET_BIOS_PVT_DATA;
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
adapter->boot_ldrv_enabled = 0;
adapter->boot_ldrv = 0;
@@ -3721,13 +3713,11 @@ mega_get_boot_drv(adapter_t *adapter)
static int
mega_support_random_del(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
int rval;
- mbox = (mbox_t *)raw_mbox;
-
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
/*
* issue command
@@ -3750,13 +3740,11 @@ mega_support_random_del(adapter_t *adapter)
static int
mega_support_ext_cdb(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
int rval;
- mbox = (mbox_t *)raw_mbox;
-
- memset(&mbox->m_out, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
/*
* issue command to find out if controller supports extended CDBs.
*/
@@ -3865,16 +3853,14 @@ mega_do_del_logdrv(adapter_t *adapter, int logdrv)
static void
mega_get_max_sgl(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
- mbox = (mbox_t *)raw_mbox;
-
- memset(mbox, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
raw_mbox[0] = MAIN_MISC_OPCODE;
raw_mbox[2] = GET_MAX_SG_SUPPORT;
@@ -3888,7 +3874,7 @@ mega_get_max_sgl(adapter_t *adapter)
}
else {
adapter->sglen = *((char *)adapter->mega_buffer);
-
+
/*
* Make sure this is not more than the resources we are
* planning to allocate
@@ -3910,16 +3896,14 @@ mega_get_max_sgl(adapter_t *adapter)
static int
mega_support_cluster(adapter_t *adapter)
{
- unsigned char raw_mbox[sizeof(struct mbox_out)];
- mbox_t *mbox;
+ struct mbox_out mbox;
+ unsigned char *raw_mbox = (u8 *)&mbox;
- mbox = (mbox_t *)raw_mbox;
-
- memset(mbox, 0, sizeof(raw_mbox));
+ memset(&mbox, 0, sizeof(mbox));
memset((void *)adapter->mega_buffer, 0, MEGA_BUFFER_SIZE);
- mbox->m_out.xferaddr = (u32)adapter->buf_dma_handle;
+ mbox.xferaddr = (u32)adapter->buf_dma_handle;
/*
* Try to get the initiator id. This command will succeed iff the
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index c39dd49..15bdc21 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -901,7 +901,7 @@ static const struct {
},
{ MPI3MR_RESET_FROM_SYSFS, "sysfs invocation" },
{ MPI3MR_RESET_FROM_SYSFS_TIMEOUT, "sysfs TM timeout" },
- { MPI3MR_RESET_FROM_FIRMWARE, "firmware asynchronus reset" },
+ { MPI3MR_RESET_FROM_FIRMWARE, "firmware asynchronous reset" },
};
/**
@@ -1242,7 +1242,7 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc)
ioc_state = mpi3mr_get_iocstate(mrioc);
if (ioc_state == MRIOC_STATE_READY) {
ioc_info(mrioc,
- "successfully transistioned to %s state\n",
+ "successfully transitioned to %s state\n",
mpi3mr_iocstate_name(ioc_state));
return 0;
}
@@ -2174,7 +2174,7 @@ int mpi3mr_op_request_post(struct mpi3mr_ioc *mrioc,
* mpi3mr_check_rh_fault_ioc - check reset history and fault
* controller
* @mrioc: Adapter instance reference
- * @reason_code, reason code for the fault.
+ * @reason_code: reason code for the fault.
*
* This routine will save snapdump and fault the controller with
* the given reason code if it is not already in the fault or
@@ -3633,7 +3633,6 @@ static int mpi3mr_enable_events(struct mpi3mr_ioc *mrioc)
/**
* mpi3mr_init_ioc - Initialize the controller
* @mrioc: Adapter instance reference
- * @init_type: Flag to indicate is the init_type
*
* This the controller initialization routine, executed either
* after soft reset or from pci probe callback.
@@ -3844,7 +3843,7 @@ int mpi3mr_reinit_ioc(struct mpi3mr_ioc *mrioc, u8 is_resume)
if (mrioc->shost->nr_hw_queues > mrioc->num_op_reply_q) {
ioc_err(mrioc,
- "cannot create minimum number of operatioanl queues expected:%d created:%d\n",
+ "cannot create minimum number of operational queues expected:%d created:%d\n",
mrioc->shost->nr_hw_queues, mrioc->num_op_reply_q);
goto out_failed_noretry;
}
@@ -4174,7 +4173,7 @@ static void mpi3mr_issue_ioc_shutdown(struct mpi3mr_ioc *mrioc)
/**
* mpi3mr_cleanup_ioc - Cleanup controller
* @mrioc: Adapter instance reference
-
+ *
* controller cleanup handler, Message unit reset or soft reset
* and shutdown notification is issued to the controller.
*
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index a0af986..949e98d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -77,8 +77,8 @@
#define MPT3SAS_DRIVER_NAME "mpt3sas"
#define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
#define MPT3SAS_DESCRIPTION "LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION "39.100.00.00"
-#define MPT3SAS_MAJOR_VERSION 39
+#define MPT3SAS_DRIVER_VERSION "40.100.00.00"
+#define MPT3SAS_MAJOR_VERSION 40
#define MPT3SAS_MINOR_VERSION 100
#define MPT3SAS_BUILD_VERSION 0
#define MPT3SAS_RELEASE_VERSION 00
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 05b6c6a..d92ca14 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -3533,11 +3533,31 @@ diag_trigger_master_store(struct device *cdev,
{
struct Scsi_Host *shost = class_to_shost(cdev);
struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
+ struct SL_WH_MASTER_TRIGGER_T *master_tg;
unsigned long flags;
ssize_t rc;
+ bool set = 1;
+
+ rc = min(sizeof(struct SL_WH_MASTER_TRIGGER_T), count);
+
+ if (ioc->supports_trigger_pages) {
+ master_tg = kzalloc(sizeof(struct SL_WH_MASTER_TRIGGER_T),
+ GFP_KERNEL);
+ if (!master_tg)
+ return -ENOMEM;
+
+ memcpy(master_tg, buf, rc);
+ if (!master_tg->MasterData)
+ set = 0;
+ if (mpt3sas_config_update_driver_trigger_pg1(ioc, master_tg,
+ set)) {
+ kfree(master_tg);
+ return -EFAULT;
+ }
+ kfree(master_tg);
+ }
spin_lock_irqsave(&ioc->diag_trigger_lock, flags);
- rc = min(sizeof(struct SL_WH_MASTER_TRIGGER_T), count);
memset(&ioc->diag_trigger_master, 0,
sizeof(struct SL_WH_MASTER_TRIGGER_T));
memcpy(&ioc->diag_trigger_master, buf, rc);
@@ -3589,11 +3609,31 @@ diag_trigger_event_store(struct device *cdev,
{
struct Scsi_Host *shost = class_to_shost(cdev);
struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
+ struct SL_WH_EVENT_TRIGGERS_T *event_tg;
unsigned long flags;
ssize_t sz;
+ bool set = 1;
+
+ sz = min(sizeof(struct SL_WH_EVENT_TRIGGERS_T), count);
+ if (ioc->supports_trigger_pages) {
+ event_tg = kzalloc(sizeof(struct SL_WH_EVENT_TRIGGERS_T),
+ GFP_KERNEL);
+ if (!event_tg)
+ return -ENOMEM;
+
+ memcpy(event_tg, buf, sz);
+ if (!event_tg->ValidEntries)
+ set = 0;
+ if (mpt3sas_config_update_driver_trigger_pg2(ioc, event_tg,
+ set)) {
+ kfree(event_tg);
+ return -EFAULT;
+ }
+ kfree(event_tg);
+ }
spin_lock_irqsave(&ioc->diag_trigger_lock, flags);
- sz = min(sizeof(struct SL_WH_EVENT_TRIGGERS_T), count);
+
memset(&ioc->diag_trigger_event, 0,
sizeof(struct SL_WH_EVENT_TRIGGERS_T));
memcpy(&ioc->diag_trigger_event, buf, sz);
@@ -3644,11 +3684,31 @@ diag_trigger_scsi_store(struct device *cdev,
{
struct Scsi_Host *shost = class_to_shost(cdev);
struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
+ struct SL_WH_SCSI_TRIGGERS_T *scsi_tg;
unsigned long flags;
ssize_t sz;
+ bool set = 1;
+
+ sz = min(sizeof(struct SL_WH_SCSI_TRIGGERS_T), count);
+ if (ioc->supports_trigger_pages) {
+ scsi_tg = kzalloc(sizeof(struct SL_WH_SCSI_TRIGGERS_T),
+ GFP_KERNEL);
+ if (!scsi_tg)
+ return -ENOMEM;
+
+ memcpy(scsi_tg, buf, sz);
+ if (!scsi_tg->ValidEntries)
+ set = 0;
+ if (mpt3sas_config_update_driver_trigger_pg3(ioc, scsi_tg,
+ set)) {
+ kfree(scsi_tg);
+ return -EFAULT;
+ }
+ kfree(scsi_tg);
+ }
spin_lock_irqsave(&ioc->diag_trigger_lock, flags);
- sz = min(sizeof(ioc->diag_trigger_scsi), count);
+
memset(&ioc->diag_trigger_scsi, 0, sizeof(ioc->diag_trigger_scsi));
memcpy(&ioc->diag_trigger_scsi, buf, sz);
if (ioc->diag_trigger_scsi.ValidEntries > NUM_VALID_ENTRIES)
@@ -3698,11 +3758,30 @@ diag_trigger_mpi_store(struct device *cdev,
{
struct Scsi_Host *shost = class_to_shost(cdev);
struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
+ struct SL_WH_MPI_TRIGGERS_T *mpi_tg;
unsigned long flags;
ssize_t sz;
+ bool set = 1;
+
+ sz = min(sizeof(struct SL_WH_MPI_TRIGGERS_T), count);
+ if (ioc->supports_trigger_pages) {
+ mpi_tg = kzalloc(sizeof(struct SL_WH_MPI_TRIGGERS_T),
+ GFP_KERNEL);
+ if (!mpi_tg)
+ return -ENOMEM;
+
+ memcpy(mpi_tg, buf, sz);
+ if (!mpi_tg->ValidEntries)
+ set = 0;
+ if (mpt3sas_config_update_driver_trigger_pg4(ioc, mpi_tg,
+ set)) {
+ kfree(mpi_tg);
+ return -EFAULT;
+ }
+ kfree(mpi_tg);
+ }
spin_lock_irqsave(&ioc->diag_trigger_lock, flags);
- sz = min(sizeof(struct SL_WH_MPI_TRIGGERS_T), count);
memset(&ioc->diag_trigger_mpi, 0,
sizeof(ioc->diag_trigger_mpi));
memcpy(&ioc->diag_trigger_mpi, buf, sz);
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index 8b9e889..92c818a 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -1557,6 +1557,9 @@ static int nsp_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
data->MmioAddress = (unsigned long)
ioremap(p_dev->resource[2]->start,
resource_size(p_dev->resource[2]));
+ if (!data->MmioAddress)
+ goto next_entry;
+
data->MmioLength = resource_size(p_dev->resource[2]);
}
/* If we got this far, we're cool! */
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index c9a16ee..160ee8b2 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -1199,7 +1199,7 @@ int pm8001_abort_task(struct sas_task *task)
struct pm8001_device *pm8001_dev;
struct pm8001_tmf_task tmf_task;
int rc = TMF_RESP_FUNC_FAILED, ret;
- u32 phy_id;
+ u32 phy_id, port_id;
struct sas_task_slow slow_task;
if (unlikely(!task || !task->lldd_task || !task->dev))
@@ -1246,6 +1246,7 @@ int pm8001_abort_task(struct sas_task *task)
DECLARE_COMPLETION_ONSTACK(completion_reset);
DECLARE_COMPLETION_ONSTACK(completion);
struct pm8001_phy *phy = pm8001_ha->phy + phy_id;
+ port_id = phy->port->port_id;
/* 1. Set Device state as Recovery */
pm8001_dev->setds_completion = &completion;
@@ -1297,6 +1298,10 @@ int pm8001_abort_task(struct sas_task *task)
PORT_RESET_TMO);
if (phy->port_reset_status == PORT_RESET_TMO) {
pm8001_dev_gone_notify(dev);
+ PM8001_CHIP_DISP->hw_event_ack_req(
+ pm8001_ha, 0,
+ 0x07, /*HW_EVENT_PHY_DOWN ack*/
+ port_id, phy_id, 0, 0);
goto out;
}
}
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index 83eec16..a17da1c 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -216,6 +216,9 @@ struct pm8001_dispatch {
u32 state);
int (*sas_re_init_req)(struct pm8001_hba_info *pm8001_ha);
int (*fatal_errors)(struct pm8001_hba_info *pm8001_ha);
+ void (*hw_event_ack_req)(struct pm8001_hba_info *pm8001_ha,
+ u32 Qnum, u32 SEA, u32 port_id, u32 phyId, u32 param0,
+ u32 param1);
};
struct pm8001_chip_info {
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index ad3c6da..bbf538f 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -3712,8 +3712,10 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb)
break;
case HW_EVENT_PORT_RESET_TIMER_TMO:
pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_RESET_TIMER_TMO\n");
- pm80xx_hw_event_ack_req(pm8001_ha, 0, HW_EVENT_PHY_DOWN,
- port_id, phy_id, 0, 0);
+ if (!pm8001_ha->phy[phy_id].reset_completion) {
+ pm80xx_hw_event_ack_req(pm8001_ha, 0, HW_EVENT_PHY_DOWN,
+ port_id, phy_id, 0, 0);
+ }
sas_phy_disconnected(sas_phy);
phy->phy_attached = 0;
sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR,
@@ -5055,4 +5057,5 @@ const struct pm8001_dispatch pm8001_80xx_dispatch = {
.fw_flash_update_req = pm8001_chip_fw_flash_update_req,
.set_dev_state_req = pm8001_chip_set_dev_state_req,
.fatal_errors = pm80xx_fatal_errors,
+ .hw_event_ack_req = pm80xx_hw_event_ack_req,
};
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 1bf7a22..cdc66e2 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -1415,6 +1415,8 @@ static void qedf_upload_connection(struct qedf_ctx *qedf,
*/
term_params = dma_alloc_coherent(&qedf->pdev->dev, QEDF_TERM_BUFF_SIZE,
&term_params_dma, GFP_KERNEL);
+ if (!term_params)
+ return;
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "Uploading connection "
"port_id=%06x.\n", fcport->rdata->ids.port_id);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 35e381f..0a70aa7 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2067,7 +2067,6 @@ void scsi_exit_queue(void)
* @sdev: SCSI device to be queried
* @pf: Page format bit (1 == standard, 0 == vendor specific)
* @sp: Save page bit (0 == don't save, 1 == save)
- * @modepage: mode page being requested
* @buffer: request buffer (may not be smaller than eight bytes)
* @len: length of request buffer.
* @timeout: command timeout
@@ -2080,10 +2079,9 @@ void scsi_exit_queue(void)
* status on error
*
*/
-int
-scsi_mode_select(struct scsi_device *sdev, int pf, int sp, int modepage,
- unsigned char *buffer, int len, int timeout, int retries,
- struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
+int scsi_mode_select(struct scsi_device *sdev, int pf, int sp,
+ unsigned char *buffer, int len, int timeout, int retries,
+ struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
{
unsigned char cmd[10];
unsigned char *real_buffer;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 0e73c3f..62eb992 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -209,7 +209,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
*/
data.device_specific = 0;
- if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
+ if (scsi_mode_select(sdp, 1, sp, buffer_data, len, SD_TIMEOUT,
sdkp->max_retries, &data, &sshdr)) {
if (scsi_sense_valid(&sshdr))
sd_print_sense_hdr(sdkp, &sshdr);
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 5393b5c..86a9380 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -557,7 +557,7 @@ static void ufs_mtk_init_va09_pwr_ctrl(struct ufs_hba *hba)
struct ufs_mtk_host *host = ufshcd_get_variant(hba);
host->reg_va09 = regulator_get(hba->dev, "va09");
- if (!host->reg_va09)
+ if (IS_ERR(host->reg_va09))
dev_info(hba->dev, "failed to get va09");
else
host->caps |= UFS_MTK_CAP_VA09_PWR_CTRL;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 1049e41..460d2b4 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -7815,7 +7815,7 @@ static int ufshcd_quirk_tune_host_pa_tactivate(struct ufs_hba *hba)
peer_pa_tactivate_us = peer_pa_tactivate *
gran_to_us_table[peer_granularity - 1];
- if (pa_tactivate_us > peer_pa_tactivate_us) {
+ if (pa_tactivate_us >= peer_pa_tactivate_us) {
u32 new_peer_pa_tactivate;
new_peer_pa_tactivate = pa_tactivate_us /
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 65c642b..0e6110d 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -778,7 +778,7 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
static void virtscsi_remove_vqs(struct virtio_device *vdev)
{
/* Stop all the virtqueues. */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
}
diff --git a/drivers/soc/canaan/Kconfig b/drivers/soc/canaan/Kconfig
index 853096b..2527cf5 100644
--- a/drivers/soc/canaan/Kconfig
+++ b/drivers/soc/canaan/Kconfig
@@ -5,7 +5,6 @@
depends on RISCV && SOC_CANAAN && OF
default SOC_CANAAN
select PM
- select SYSCON
select MFD_SYSCON
help
Canaan Kendryte K210 SoC system controller driver.
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 8502b7d..72acb1f 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -596,6 +596,7 @@ static const struct acpi_device_id int3400_thermal_match[] = {
{"INT3400", 0},
{"INTC1040", 0},
{"INTC1041", 0},
+ {"INTC10A0", 0},
{}
};
diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
index c3c4c4d..07e2532 100644
--- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
@@ -285,6 +285,7 @@ static const struct acpi_device_id int3403_device_ids[] = {
{"INT3403", 0},
{"INTC1043", 0},
{"INTC1046", 0},
+ {"INTC10A1", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, int3403_device_ids);
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h
index 9b2a64e..49932a6 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h
@@ -24,6 +24,7 @@
#define PCI_DEVICE_ID_INTEL_HSB_THERMAL 0x0A03
#define PCI_DEVICE_ID_INTEL_ICL_THERMAL 0x8a03
#define PCI_DEVICE_ID_INTEL_JSL_THERMAL 0x4E03
+#define PCI_DEVICE_ID_INTEL_RPL_THERMAL 0xA71D
#define PCI_DEVICE_ID_INTEL_SKL_THERMAL 0x1903
#define PCI_DEVICE_ID_INTEL_TGL_THERMAL 0x9A03
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
index b4bcd3f..ca40b09 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
@@ -358,6 +358,7 @@ static SIMPLE_DEV_PM_OPS(proc_thermal_pci_pm, proc_thermal_pci_suspend,
static const struct pci_device_id proc_thermal_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MBOX) },
+ { PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MBOX) },
{ },
};
diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
index 3f78879..f480d54 100644
--- a/drivers/vdpa/alibaba/eni_vdpa.c
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -58,7 +58,7 @@ static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa)
return &eni_vdpa->ldev;
}
-static u64 eni_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 eni_vdpa_get_device_features(struct vdpa_device *vdpa)
{
struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
u64 features = vp_legacy_get_features(ldev);
@@ -69,7 +69,7 @@ static u64 eni_vdpa_get_features(struct vdpa_device *vdpa)
return features;
}
-static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int eni_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
{
struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
@@ -84,6 +84,13 @@ static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
return 0;
}
+static u64 eni_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return vp_legacy_get_driver_features(ldev);
+}
+
static u8 eni_vdpa_get_status(struct vdpa_device *vdpa)
{
struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
@@ -401,8 +408,9 @@ static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa,
}
static const struct vdpa_config_ops eni_vdpa_ops = {
- .get_features = eni_vdpa_get_features,
- .set_features = eni_vdpa_set_features,
+ .get_device_features = eni_vdpa_get_device_features,
+ .set_driver_features = eni_vdpa_set_driver_features,
+ .get_driver_features = eni_vdpa_get_driver_features,
.get_status = eni_vdpa_get_status,
.set_status = eni_vdpa_set_status,
.reset = eni_vdpa_reset,
@@ -450,11 +458,6 @@ static u16 eni_vdpa_get_num_queues(struct eni_vdpa *eni_vdpa)
return num;
}
-static void eni_vdpa_free_irq_vectors(void *data)
-{
- pci_free_irq_vectors(data);
-}
-
static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct device *dev = &pdev->dev;
@@ -488,13 +491,6 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
eni_vdpa->vdpa.dma_dev = &pdev->dev;
eni_vdpa->queues = eni_vdpa_get_num_queues(eni_vdpa);
- ret = devm_add_action_or_reset(dev, eni_vdpa_free_irq_vectors, pdev);
- if (ret) {
- ENI_ERR(pdev,
- "failed for adding devres for freeing irq vectors\n");
- goto err;
- }
-
eni_vdpa->vring = devm_kcalloc(&pdev->dev, eni_vdpa->queues,
sizeof(*eni_vdpa->vring),
GFP_KERNEL);
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index 2808f1b..7d41dfe 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -143,8 +143,8 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
IFCVF_DBG(pdev, "hw->isr = %p\n", hw->isr);
break;
case VIRTIO_PCI_CAP_DEVICE_CFG:
- hw->net_cfg = get_cap_addr(hw, &cap);
- IFCVF_DBG(pdev, "hw->net_cfg = %p\n", hw->net_cfg);
+ hw->dev_cfg = get_cap_addr(hw, &cap);
+ IFCVF_DBG(pdev, "hw->dev_cfg = %p\n", hw->dev_cfg);
break;
}
@@ -153,7 +153,7 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
}
if (hw->common_cfg == NULL || hw->notify_base == NULL ||
- hw->isr == NULL || hw->net_cfg == NULL) {
+ hw->isr == NULL || hw->dev_cfg == NULL) {
IFCVF_ERR(pdev, "Incomplete PCI capabilities\n");
return -EIO;
}
@@ -174,7 +174,7 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
IFCVF_DBG(pdev,
"PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n",
hw->common_cfg, hw->notify_base, hw->isr,
- hw->net_cfg, hw->notify_off_multiplier);
+ hw->dev_cfg, hw->notify_off_multiplier);
return 0;
}
@@ -242,33 +242,54 @@ int ifcvf_verify_min_features(struct ifcvf_hw *hw, u64 features)
return 0;
}
-void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+u32 ifcvf_get_config_size(struct ifcvf_hw *hw)
+{
+ struct ifcvf_adapter *adapter;
+ u32 config_size;
+
+ adapter = vf_to_adapter(hw);
+ switch (hw->dev_type) {
+ case VIRTIO_ID_NET:
+ config_size = sizeof(struct virtio_net_config);
+ break;
+ case VIRTIO_ID_BLOCK:
+ config_size = sizeof(struct virtio_blk_config);
+ break;
+ default:
+ config_size = 0;
+ IFCVF_ERR(adapter->pdev, "VIRTIO ID %u not supported\n", hw->dev_type);
+ }
+
+ return config_size;
+}
+
+void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset,
void *dst, int length)
{
u8 old_gen, new_gen, *p;
int i;
- WARN_ON(offset + length > sizeof(struct virtio_net_config));
+ WARN_ON(offset + length > hw->config_size);
do {
old_gen = ifc_ioread8(&hw->common_cfg->config_generation);
p = dst;
for (i = 0; i < length; i++)
- *p++ = ifc_ioread8(hw->net_cfg + offset + i);
+ *p++ = ifc_ioread8(hw->dev_cfg + offset + i);
new_gen = ifc_ioread8(&hw->common_cfg->config_generation);
} while (old_gen != new_gen);
}
-void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset,
const void *src, int length)
{
const u8 *p;
int i;
p = src;
- WARN_ON(offset + length > sizeof(struct virtio_net_config));
+ WARN_ON(offset + length > hw->config_size);
for (i = 0; i < length; i++)
- ifc_iowrite8(*p++, hw->net_cfg + offset + i);
+ ifc_iowrite8(*p++, hw->dev_cfg + offset + i);
}
static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index 09918af..c486873 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -71,12 +71,14 @@ struct ifcvf_hw {
u64 hw_features;
u32 dev_type;
struct virtio_pci_common_cfg __iomem *common_cfg;
- void __iomem *net_cfg;
+ void __iomem *dev_cfg;
struct vring_info vring[IFCVF_MAX_QUEUES];
void __iomem * const *base;
char config_msix_name[256];
struct vdpa_callback config_cb;
unsigned int config_irq;
+ /* virtio-net or virtio-blk device config size */
+ u32 config_size;
};
struct ifcvf_adapter {
@@ -105,9 +107,9 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
int ifcvf_start_hw(struct ifcvf_hw *hw);
void ifcvf_stop_hw(struct ifcvf_hw *hw);
void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid);
-void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset,
void *dst, int length);
-void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset,
const void *src, int length);
u8 ifcvf_get_status(struct ifcvf_hw *hw);
void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
@@ -120,4 +122,5 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num);
struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
int ifcvf_probed_virtio_net(struct ifcvf_hw *hw);
+u32 ifcvf_get_config_size(struct ifcvf_hw *hw);
#endif /* _IFCVF_H_ */
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 6dc75ca..d1a6b5a 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -169,7 +169,7 @@ static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev)
return &adapter->vf;
}
-static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev)
+static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev)
{
struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
@@ -187,7 +187,7 @@ static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev)
return features;
}
-static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features)
+static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features)
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
int ret;
@@ -201,6 +201,13 @@ static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features)
return 0;
}
+static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev)
+{
+ struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+ return vf->req_features;
+}
+
static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
@@ -366,24 +373,9 @@ static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)
{
- struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
- struct pci_dev *pdev = adapter->pdev;
- size_t size;
- switch (vf->dev_type) {
- case VIRTIO_ID_NET:
- size = sizeof(struct virtio_net_config);
- break;
- case VIRTIO_ID_BLOCK:
- size = sizeof(struct virtio_blk_config);
- break;
- default:
- size = 0;
- IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type);
- }
-
- return size;
+ return vf->config_size;
}
static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
@@ -392,8 +384,7 @@ static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
- WARN_ON(offset + len > sizeof(struct virtio_net_config));
- ifcvf_read_net_config(vf, offset, buf, len);
+ ifcvf_read_dev_config(vf, offset, buf, len);
}
static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
@@ -402,8 +393,7 @@ static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
- WARN_ON(offset + len > sizeof(struct virtio_net_config));
- ifcvf_write_net_config(vf, offset, buf, len);
+ ifcvf_write_dev_config(vf, offset, buf, len);
}
static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
@@ -443,8 +433,9 @@ static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_devic
* implemented set_map()/dma_map()/dma_unmap()
*/
static const struct vdpa_config_ops ifc_vdpa_ops = {
- .get_features = ifcvf_vdpa_get_features,
- .set_features = ifcvf_vdpa_set_features,
+ .get_device_features = ifcvf_vdpa_get_device_features,
+ .set_driver_features = ifcvf_vdpa_set_driver_features,
+ .get_driver_features = ifcvf_vdpa_get_driver_features,
.get_status = ifcvf_vdpa_get_status,
.set_status = ifcvf_vdpa_set_status,
.reset = ifcvf_vdpa_reset,
@@ -542,6 +533,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
vf->vring[i].irq = -EINVAL;
vf->hw_features = ifcvf_get_hw_features(vf);
+ vf->config_size = ifcvf_get_config_size(vf);
adapter->vdpa.mdev = &ifcvf_mgmt_dev->mdev;
ret = _vdpa_register_device(&adapter->vdpa, vf->nr_vring);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index cf59f7e..f648f1c5 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -131,25 +131,24 @@ struct mlx5_vdpa_virtqueue {
struct mlx5_vq_restore_info ri;
};
-/* We will remove this limitation once mlx5_vdpa_alloc_resources()
- * provides for driver space allocation
- */
-#define MLX5_MAX_SUPPORTED_VQS 16
-
static bool is_index_valid(struct mlx5_vdpa_dev *mvdev, u16 idx)
{
- if (unlikely(idx > mvdev->max_idx))
- return false;
+ if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) {
+ if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)))
+ return idx < 2;
+ else
+ return idx < 3;
+ }
- return true;
+ return idx <= mvdev->max_idx;
}
struct mlx5_vdpa_net {
struct mlx5_vdpa_dev mvdev;
struct mlx5_vdpa_net_resources res;
struct virtio_net_config config;
- struct mlx5_vdpa_virtqueue vqs[MLX5_MAX_SUPPORTED_VQS];
- struct vdpa_callback event_cbs[MLX5_MAX_SUPPORTED_VQS + 1];
+ struct mlx5_vdpa_virtqueue *vqs;
+ struct vdpa_callback *event_cbs;
/* Serialize vq resources creation and destruction. This is required
* since memory map might change and we need to destroy and create
@@ -876,8 +875,6 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
MLX5_SET(virtio_q, vq_ctx, umem_3_id, mvq->umem3.id);
MLX5_SET(virtio_q, vq_ctx, umem_3_size, mvq->umem3.size);
MLX5_SET(virtio_q, vq_ctx, pd, ndev->mvdev.res.pdn);
- if (MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, eth_frame_offload_type))
- MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, 1);
err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
if (err)
@@ -1218,7 +1215,7 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev)
{
int i;
- for (i = 0; i < MLX5_MAX_SUPPORTED_VQS; i++)
+ for (i = 0; i < ndev->mvdev.max_vqs; i++)
suspend_vq(ndev, &ndev->vqs[i]);
}
@@ -1244,8 +1241,14 @@ static int create_rqt(struct mlx5_vdpa_net *ndev)
void *in;
int i, j;
int err;
+ int num;
- max_rqt = min_t(int, MLX5_MAX_SUPPORTED_VQS / 2,
+ if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ)))
+ num = 1;
+ else
+ num = ndev->cur_num_vqs / 2;
+
+ max_rqt = min_t(int, roundup_pow_of_two(num),
1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
if (max_rqt < 1)
return -EOPNOTSUPP;
@@ -1261,17 +1264,10 @@ static int create_rqt(struct mlx5_vdpa_net *ndev)
MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
MLX5_SET(rqtc, rqtc, rqt_max_size, max_rqt);
list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
- for (i = 0, j = 0; j < max_rqt; j++) {
- if (!ndev->vqs[j].initialized)
- continue;
+ for (i = 0, j = 0; i < max_rqt; i++, j += 2)
+ list[i] = cpu_to_be32(ndev->vqs[j % (2 * num)].virtq_id);
- if (!vq_is_tx(ndev->vqs[j].index)) {
- list[i] = cpu_to_be32(ndev->vqs[j].virtq_id);
- i++;
- }
- }
- MLX5_SET(rqtc, rqtc, rqt_actual_size, i);
-
+ MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt);
err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn);
kfree(in);
if (err)
@@ -1292,7 +1288,7 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
int i, j;
int err;
- max_rqt = min_t(int, ndev->cur_num_vqs / 2,
+ max_rqt = min_t(int, roundup_pow_of_two(ndev->cur_num_vqs / 2),
1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
if (max_rqt < 1)
return -EOPNOTSUPP;
@@ -1308,16 +1304,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
- for (i = 0, j = 0; j < num; j++) {
- if (!ndev->vqs[j].initialized)
- continue;
+ for (i = 0, j = 0; i < max_rqt; i++, j += 2)
+ list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id);
- if (!vq_is_tx(ndev->vqs[j].index)) {
- list[i] = cpu_to_be32(ndev->vqs[j].virtq_id);
- i++;
- }
- }
- MLX5_SET(rqtc, rqtc, rqt_actual_size, i);
+ MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt);
err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn);
kfree(in);
if (err)
@@ -1554,9 +1544,11 @@ static int change_num_qps(struct mlx5_vdpa_dev *mvdev, int newqps)
return 0;
clean_added:
- for (--i; i >= cur_qps; --i)
+ for (--i; i >= 2 * cur_qps; --i)
teardown_vq(ndev, &ndev->vqs[i]);
+ ndev->cur_num_vqs = 2 * cur_qps;
+
return err;
}
@@ -1581,9 +1573,6 @@ static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd)
break;
}
- if (newqps & (newqps - 1))
- break;
-
if (!change_num_qps(mvdev, newqps))
status = VIRTIO_NET_OK;
@@ -1880,21 +1869,29 @@ static u64 mlx_to_vritio_features(u16 dev_features)
return result;
}
-static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
+static u64 get_supported_features(struct mlx5_core_dev *mdev)
+{
+ u64 mlx_vdpa_features = 0;
+ u16 dev_features;
+
+ dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mdev, device_features_bits_mask);
+ mlx_vdpa_features |= mlx_to_vritio_features(dev_features);
+ if (MLX5_CAP_DEV_VDPA_EMULATION(mdev, virtio_version_1_0))
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_F_VERSION_1);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_MQ);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_STATUS);
+ mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_MTU);
+
+ return mlx_vdpa_features;
+}
+
+static u64 mlx5_vdpa_get_device_features(struct vdpa_device *vdev)
{
struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
- u16 dev_features;
-
- dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
- ndev->mvdev.mlx_features |= mlx_to_vritio_features(dev_features);
- if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1);
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ);
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR);
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MQ);
- ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_STATUS);
print_features(mvdev, ndev->mvdev.mlx_features, false);
return ndev->mvdev.mlx_features;
@@ -1972,7 +1969,7 @@ static void update_cvq_info(struct mlx5_vdpa_dev *mvdev)
}
}
-static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
+static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features)
{
struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
@@ -1985,6 +1982,11 @@ static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
return err;
ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features;
+ if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ))
+ ndev->cur_num_vqs = 2 * mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs);
+ else
+ ndev->cur_num_vqs = 2;
+
update_cvq_info(mvdev);
return err;
}
@@ -2235,7 +2237,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
clear_vqs_ready(ndev);
mlx5_vdpa_destroy_mr(&ndev->mvdev);
ndev->mvdev.status = 0;
- memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs));
+ ndev->cur_num_vqs = 0;
+ memset(ndev->event_cbs, 0, sizeof(*ndev->event_cbs) * (mvdev->max_vqs + 1));
ndev->mvdev.actual_features = 0;
++mvdev->generation;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
@@ -2308,6 +2311,8 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev)
}
mlx5_vdpa_free_resources(&ndev->mvdev);
mutex_destroy(&ndev->reslock);
+ kfree(ndev->event_cbs);
+ kfree(ndev->vqs);
}
static struct vdpa_notification_area mlx5_get_vq_notification(struct vdpa_device *vdev, u16 idx)
@@ -2339,6 +2344,13 @@ static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx)
return -EOPNOTSUPP;
}
+static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+
+ return mvdev->actual_features;
+}
+
static const struct vdpa_config_ops mlx5_vdpa_ops = {
.set_vq_address = mlx5_vdpa_set_vq_address,
.set_vq_num = mlx5_vdpa_set_vq_num,
@@ -2351,8 +2363,9 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
.get_vq_notification = mlx5_get_vq_notification,
.get_vq_irq = mlx5_get_vq_irq,
.get_vq_align = mlx5_vdpa_get_vq_align,
- .get_features = mlx5_vdpa_get_features,
- .set_features = mlx5_vdpa_set_features,
+ .get_device_features = mlx5_vdpa_get_device_features,
+ .set_driver_features = mlx5_vdpa_set_driver_features,
+ .get_driver_features = mlx5_vdpa_get_driver_features,
.set_config_cb = mlx5_vdpa_set_config_cb,
.get_vq_num_max = mlx5_vdpa_get_vq_num_max,
.get_device_id = mlx5_vdpa_get_device_id,
@@ -2545,18 +2558,39 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
return -EOPNOTSUPP;
}
- /* we save one virtqueue for control virtqueue should we require it */
max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues);
- max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
+ if (max_vqs < 2) {
+ dev_warn(mdev->device,
+ "%d virtqueues are supported. At least 2 are required\n",
+ max_vqs);
+ return -EAGAIN;
+ }
+
+ if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP)) {
+ if (add_config->net.max_vq_pairs > max_vqs / 2)
+ return -EINVAL;
+ max_vqs = min_t(u32, max_vqs, 2 * add_config->net.max_vq_pairs);
+ } else {
+ max_vqs = 2;
+ }
ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
name, false);
if (IS_ERR(ndev))
return PTR_ERR(ndev);
+ ndev->mvdev.mlx_features = mgtdev->mgtdev.supported_features;
ndev->mvdev.max_vqs = max_vqs;
mvdev = &ndev->mvdev;
mvdev->mdev = mdev;
+
+ ndev->vqs = kcalloc(max_vqs, sizeof(*ndev->vqs), GFP_KERNEL);
+ ndev->event_cbs = kcalloc(max_vqs + 1, sizeof(*ndev->event_cbs), GFP_KERNEL);
+ if (!ndev->vqs || !ndev->event_cbs) {
+ err = -ENOMEM;
+ goto err_alloc;
+ }
+
init_mvqs(ndev);
mutex_init(&ndev->reslock);
config = &ndev->config;
@@ -2612,9 +2646,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
ndev->nb.notifier_call = event_handler;
mlx5_notifier_register(mdev, &ndev->nb);
- ndev->cur_num_vqs = 2 * mlx5_vdpa_max_qps(max_vqs);
mvdev->vdev.mdev = &mgtdev->mgtdev;
- err = _vdpa_register_device(&mvdev->vdev, ndev->cur_num_vqs + 1);
+ err = _vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs) + 1);
if (err)
goto err_reg;
@@ -2634,6 +2667,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
mlx5_mpfs_del_mac(pfmdev, config->mac);
err_mtu:
mutex_destroy(&ndev->reslock);
+err_alloc:
put_device(&mvdev->vdev.dev);
return err;
}
@@ -2676,7 +2710,11 @@ static int mlx5v_probe(struct auxiliary_device *adev,
mgtdev->mgtdev.ops = &mdev_ops;
mgtdev->mgtdev.device = mdev->device;
mgtdev->mgtdev.id_table = id_table;
- mgtdev->mgtdev.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
+ mgtdev->mgtdev.config_attr_mask = BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) |
+ BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
+ mgtdev->mgtdev.max_supported_vqs =
+ MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues) + 1;
+ mgtdev->mgtdev.supported_features = get_supported_features(mdev);
mgtdev->madev = madev;
err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 09bbe53..9846c9d 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -21,6 +21,14 @@ static LIST_HEAD(mdev_head);
static DEFINE_MUTEX(vdpa_dev_mutex);
static DEFINE_IDA(vdpa_index_ida);
+void vdpa_set_status(struct vdpa_device *vdev, u8 status)
+{
+ mutex_lock(&vdev->cf_mutex);
+ vdev->config->set_status(vdev, status);
+ mutex_unlock(&vdev->cf_mutex);
+}
+EXPORT_SYMBOL(vdpa_set_status);
+
static struct genl_family vdpa_nl_family;
static int vdpa_dev_probe(struct device *d)
@@ -52,8 +60,81 @@ static void vdpa_dev_remove(struct device *d)
drv->remove(vdev);
}
+static int vdpa_dev_match(struct device *dev, struct device_driver *drv)
+{
+ struct vdpa_device *vdev = dev_to_vdpa(dev);
+
+ /* Check override first, and if set, only use the named driver */
+ if (vdev->driver_override)
+ return strcmp(vdev->driver_override, drv->name) == 0;
+
+ /* Currently devices must be supported by all vDPA bus drivers */
+ return 1;
+}
+
+static ssize_t driver_override_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct vdpa_device *vdev = dev_to_vdpa(dev);
+ const char *driver_override, *old;
+ char *cp;
+
+ /* We need to keep extra room for a newline */
+ if (count >= (PAGE_SIZE - 1))
+ return -EINVAL;
+
+ driver_override = kstrndup(buf, count, GFP_KERNEL);
+ if (!driver_override)
+ return -ENOMEM;
+
+ cp = strchr(driver_override, '\n');
+ if (cp)
+ *cp = '\0';
+
+ device_lock(dev);
+ old = vdev->driver_override;
+ if (strlen(driver_override)) {
+ vdev->driver_override = driver_override;
+ } else {
+ kfree(driver_override);
+ vdev->driver_override = NULL;
+ }
+ device_unlock(dev);
+
+ kfree(old);
+
+ return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct vdpa_device *vdev = dev_to_vdpa(dev);
+ ssize_t len;
+
+ device_lock(dev);
+ len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override);
+ device_unlock(dev);
+
+ return len;
+}
+static DEVICE_ATTR_RW(driver_override);
+
+static struct attribute *vdpa_dev_attrs[] = {
+ &dev_attr_driver_override.attr,
+ NULL,
+};
+
+static const struct attribute_group vdpa_dev_group = {
+ .attrs = vdpa_dev_attrs,
+};
+__ATTRIBUTE_GROUPS(vdpa_dev);
+
static struct bus_type vdpa_bus = {
.name = "vdpa",
+ .dev_groups = vdpa_dev_groups,
+ .match = vdpa_dev_match,
.probe = vdpa_dev_probe,
.remove = vdpa_dev_remove,
};
@@ -68,6 +149,7 @@ static void vdpa_release_dev(struct device *d)
ida_simple_remove(&vdpa_index_ida, vdev->index);
mutex_destroy(&vdev->cf_mutex);
+ kfree(vdev->driver_override);
kfree(vdev);
}
@@ -300,6 +382,21 @@ void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev)
}
EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);
+static void vdpa_get_config_unlocked(struct vdpa_device *vdev,
+ unsigned int offset,
+ void *buf, unsigned int len)
+{
+ const struct vdpa_config_ops *ops = vdev->config;
+
+ /*
+ * Config accesses aren't supposed to trigger before features are set.
+ * If it does happen we assume a legacy guest.
+ */
+ if (!vdev->features_valid)
+ vdpa_set_features(vdev, 0, true);
+ ops->get_config(vdev, offset, buf, len);
+}
+
/**
* vdpa_get_config - Get one or more device configuration fields.
* @vdev: vdpa device to operate on
@@ -310,16 +407,8 @@ EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);
void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
void *buf, unsigned int len)
{
- const struct vdpa_config_ops *ops = vdev->config;
-
mutex_lock(&vdev->cf_mutex);
- /*
- * Config accesses aren't supposed to trigger before features are set.
- * If it does happen we assume a legacy guest.
- */
- if (!vdev->features_valid)
- vdpa_set_features(vdev, 0);
- ops->get_config(vdev, offset, buf, len);
+ vdpa_get_config_unlocked(vdev, offset, buf, len);
mutex_unlock(&vdev->cf_mutex);
}
EXPORT_SYMBOL_GPL(vdpa_get_config);
@@ -414,6 +503,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m
err = -EMSGSIZE;
goto msg_err;
}
+ if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,
+ mdev->max_supported_vqs)) {
+ err = -EMSGSIZE;
+ goto msg_err;
+ }
+ if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES,
+ mdev->supported_features, VDPA_ATTR_PAD)) {
+ err = -EMSGSIZE;
+ goto msg_err;
+ }
genlmsg_end(msg, hdr);
return 0;
@@ -480,8 +579,9 @@ vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
return msg->len;
}
-#define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
- (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
+#define VDPA_DEV_NET_ATTRS_MASK (BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
+ BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU) | \
+ BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP))
static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info)
{
@@ -500,12 +600,22 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) {
macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]);
memcpy(config.net.mac, macaddr, sizeof(config.net.mac));
- config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
+ config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR);
}
if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) {
config.net.mtu =
nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]);
- config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU);
+ config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU);
+ }
+ if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) {
+ config.net.max_vq_pairs =
+ nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]);
+ if (!config.net.max_vq_pairs) {
+ NL_SET_ERR_MSG_MOD(info->extack,
+ "At least one pair of VQs is required");
+ return -EINVAL;
+ }
+ config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
}
/* Skip checking capability if user didn't prefer to configure any
@@ -707,7 +817,7 @@ static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
{
u16 val_u16;
- if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0)
+ if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0)
return 0;
val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
@@ -720,7 +830,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
u64 features;
u16 val_u16;
- vdpa_get_config(vdev, 0, &config, sizeof(config));
+ vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
config.mac))
@@ -734,7 +844,10 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
return -EMSGSIZE;
- features = vdev->config->get_features(vdev);
+ features = vdev->config->get_driver_features(vdev);
+ if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
+ VDPA_ATTR_PAD))
+ return -EMSGSIZE;
return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
}
@@ -745,12 +858,23 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
{
u32 device_id;
void *hdr;
+ u8 status;
int err;
+ mutex_lock(&vdev->cf_mutex);
+ status = vdev->config->get_status(vdev);
+ if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+ NL_SET_ERR_MSG_MOD(extack, "Features negotiation not completed");
+ err = -EAGAIN;
+ goto out;
+ }
+
hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
VDPA_CMD_DEV_CONFIG_GET);
- if (!hdr)
- return -EMSGSIZE;
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto out;
+ }
if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
err = -EMSGSIZE;
@@ -774,11 +898,14 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
if (err)
goto msg_err;
+ mutex_unlock(&vdev->cf_mutex);
genlmsg_end(msg, hdr);
return 0;
msg_err:
genlmsg_cancel(msg, hdr);
+out:
+ mutex_unlock(&vdev->cf_mutex);
return err;
}
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 41b0cd1..ddbe142 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -399,14 +399,14 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
return VDPASIM_QUEUE_ALIGN;
}
-static u64 vdpasim_get_features(struct vdpa_device *vdpa)
+static u64 vdpasim_get_device_features(struct vdpa_device *vdpa)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
return vdpasim->dev_attr.supported_features;
}
-static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
+static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -419,6 +419,13 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
return 0;
}
+static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa)
+{
+ struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+ return vdpasim->features;
+}
+
static void vdpasim_set_config_cb(struct vdpa_device *vdpa,
struct vdpa_callback *cb)
{
@@ -613,8 +620,9 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
.set_vq_state = vdpasim_set_vq_state,
.get_vq_state = vdpasim_get_vq_state,
.get_vq_align = vdpasim_get_vq_align,
- .get_features = vdpasim_get_features,
- .set_features = vdpasim_set_features,
+ .get_device_features = vdpasim_get_device_features,
+ .set_driver_features = vdpasim_set_driver_features,
+ .get_driver_features = vdpasim_get_driver_features,
.set_config_cb = vdpasim_set_config_cb,
.get_vq_num_max = vdpasim_get_vq_num_max,
.get_device_id = vdpasim_get_device_id,
@@ -642,8 +650,9 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
.set_vq_state = vdpasim_set_vq_state,
.get_vq_state = vdpasim_get_vq_state,
.get_vq_align = vdpasim_get_vq_align,
- .get_features = vdpasim_get_features,
- .set_features = vdpasim_set_features,
+ .get_device_features = vdpasim_get_device_features,
+ .set_driver_features = vdpasim_set_driver_features,
+ .get_driver_features = vdpasim_get_driver_features,
.set_config_cb = vdpasim_set_config_cb,
.get_vq_num_max = vdpasim_get_vq_num_max,
.get_device_id = vdpasim_get_device_id,
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index 76dd24a..d5324f6 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -191,6 +191,8 @@ static struct vdpa_mgmt_dev mgmt_dev = {
.ops = &vdpasim_net_mgmtdev_ops,
.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
1 << VDPA_ATTR_DEV_NET_CFG_MTU),
+ .max_supported_vqs = VDPASIM_NET_VQ_NUM,
+ .supported_features = VDPASIM_NET_FEATURES,
};
static int __init vdpasim_net_init(void)
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index eddcb64..f85d1a0 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -573,14 +573,14 @@ static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa)
return dev->vq_align;
}
-static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 vduse_vdpa_get_device_features(struct vdpa_device *vdpa)
{
struct vduse_dev *dev = vdpa_to_vduse(vdpa);
return dev->device_features;
}
-static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int vduse_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
{
struct vduse_dev *dev = vdpa_to_vduse(vdpa);
@@ -588,6 +588,13 @@ static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
return 0;
}
+static u64 vduse_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return dev->driver_features;
+}
+
static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa,
struct vdpa_callback *cb)
{
@@ -721,8 +728,9 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
.set_vq_state = vduse_vdpa_set_vq_state,
.get_vq_state = vduse_vdpa_get_vq_state,
.get_vq_align = vduse_vdpa_get_vq_align,
- .get_features = vduse_vdpa_get_features,
- .set_features = vduse_vdpa_set_features,
+ .get_device_features = vduse_vdpa_get_device_features,
+ .set_driver_features = vduse_vdpa_set_driver_features,
+ .get_driver_features = vduse_vdpa_get_driver_features,
.set_config_cb = vduse_vdpa_set_config_cb,
.get_vq_num_max = vduse_vdpa_get_vq_num_max,
.get_device_id = vduse_vdpa_get_device_id,
@@ -1357,7 +1365,6 @@ static int vduse_create_dev(struct vduse_dev_config *config,
err_str:
vduse_dev_destroy(dev);
err:
- kvfree(config_buf);
return ret;
}
@@ -1408,6 +1415,8 @@ static long vduse_ioctl(struct file *file, unsigned int cmd,
}
config.name[VDUSE_NAME_MAX - 1] = '\0';
ret = vduse_create_dev(&config, buf, control->api_version);
+ if (ret)
+ kvfree(buf);
break;
}
case VDUSE_DESTROY_DEV: {
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index e3ff787..a57e381 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -53,14 +53,14 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa)
return &vp_vdpa->mdev;
}
-static u64 vp_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa)
{
struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
return vp_modern_get_features(mdev);
}
-static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
{
struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
@@ -69,6 +69,13 @@ static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
return 0;
}
+static u64 vp_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+ return vp_modern_get_driver_features(mdev);
+}
+
static u8 vp_vdpa_get_status(struct vdpa_device *vdpa)
{
struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
@@ -415,8 +422,9 @@ vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid)
}
static const struct vdpa_config_ops vp_vdpa_ops = {
- .get_features = vp_vdpa_get_features,
- .set_features = vp_vdpa_set_features,
+ .get_device_features = vp_vdpa_get_device_features,
+ .set_driver_features = vp_vdpa_set_driver_features,
+ .get_driver_features = vp_vdpa_get_driver_features,
.get_status = vp_vdpa_get_status,
.set_status = vp_vdpa_set_status,
.reset = vp_vdpa_reset,
diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c
index 362f91e..352c725 100644
--- a/drivers/vfio/pci/vfio_pci_igd.c
+++ b/drivers/vfio/pci/vfio_pci_igd.c
@@ -309,13 +309,14 @@ static ssize_t vfio_pci_igd_cfg_rw(struct vfio_pci_core_device *vdev,
if ((pos & 3) && size > 2) {
u16 val;
+ __le16 lval;
ret = pci_user_read_config_word(pdev, pos, &val);
if (ret)
return ret;
- val = cpu_to_le16(val);
- if (copy_to_user(buf + count - size, &val, 2))
+ lval = cpu_to_le16(val);
+ if (copy_to_user(buf + count - size, &lval, 2))
return -EFAULT;
pos += 2;
@@ -324,13 +325,14 @@ static ssize_t vfio_pci_igd_cfg_rw(struct vfio_pci_core_device *vdev,
while (size > 3) {
u32 val;
+ __le32 lval;
ret = pci_user_read_config_dword(pdev, pos, &val);
if (ret)
return ret;
- val = cpu_to_le32(val);
- if (copy_to_user(buf + count - size, &val, 4))
+ lval = cpu_to_le32(val);
+ if (copy_to_user(buf + count - size, &lval, 4))
return -EFAULT;
pos += 4;
@@ -339,13 +341,14 @@ static ssize_t vfio_pci_igd_cfg_rw(struct vfio_pci_core_device *vdev,
while (size >= 2) {
u16 val;
+ __le16 lval;
ret = pci_user_read_config_word(pdev, pos, &val);
if (ret)
return ret;
- val = cpu_to_le16(val);
- if (copy_to_user(buf + count - size, &val, 2))
+ lval = cpu_to_le16(val);
+ if (copy_to_user(buf + count - size, &lval, 2))
return -EFAULT;
pos += 2;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index f17490a..9394aa9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -256,7 +256,7 @@ static int vfio_dma_bitmap_alloc(struct vfio_dma *dma, size_t pgsize)
static void vfio_dma_bitmap_free(struct vfio_dma *dma)
{
- kfree(dma->bitmap);
+ kvfree(dma->bitmap);
dma->bitmap = NULL;
}
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index a09dedc..05740cb 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -166,6 +166,7 @@ static int vhost_test_release(struct inode *inode, struct file *f)
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_test_flush(n);
+ kfree(n->dev.vqs);
kfree(n);
return 0;
}
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index e3c4f05..8515398 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -170,7 +170,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
* Userspace shouldn't remove status bits unless reset the
* status to 0.
*/
- if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
+ if (status != 0 && (status_old & ~status) != 0)
return -EINVAL;
if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -178,11 +178,11 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
vhost_vdpa_unsetup_vq_irq(v, i);
if (status == 0) {
- ret = ops->reset(vdpa);
+ ret = vdpa_reset(vdpa);
if (ret)
return ret;
} else
- ops->set_status(vdpa, status);
+ vdpa_set_status(vdpa, status);
if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
for (i = 0; i < nvqs; i++)
@@ -195,7 +195,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
struct vhost_vdpa_config *c)
{
struct vdpa_device *vdpa = v->vdpa;
- long size = vdpa->config->get_config_size(vdpa);
+ size_t size = vdpa->config->get_config_size(vdpa);
if (c->len == 0 || c->off > size)
return -EINVAL;
@@ -262,7 +262,7 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
const struct vdpa_config_ops *ops = vdpa->config;
u64 features;
- features = ops->get_features(vdpa);
+ features = ops->get_device_features(vdpa);
if (copy_to_user(featurep, &features, sizeof(features)))
return -EFAULT;
@@ -286,7 +286,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
if (copy_from_user(&features, featurep, sizeof(features)))
return -EFAULT;
- if (vdpa_set_features(vdpa, features))
+ if (vdpa_set_features(vdpa, features, false))
return -EINVAL;
return 0;
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 236081a..00ac9db 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -204,6 +204,12 @@ int virtio_finalize_features(struct virtio_device *dev)
}
EXPORT_SYMBOL_GPL(virtio_finalize_features);
+void virtio_reset_device(struct virtio_device *dev)
+{
+ dev->config->reset(dev);
+}
+EXPORT_SYMBOL_GPL(virtio_reset_device);
+
static int virtio_dev_probe(struct device *_d)
{
int err, i;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index c22ff01..f4c34a2 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1056,7 +1056,7 @@ static void remove_common(struct virtio_balloon *vb)
return_free_pages_to_mm(vb, ULONG_MAX);
/* Now we reset the device so we can clean up the queues. */
- vb->vdev->config->reset(vb->vdev);
+ virtio_reset_device(vb->vdev);
vb->vdev->config->del_vqs(vb->vdev);
}
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index ce51ae16..3aa4670 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -347,7 +347,7 @@ static void virtinput_remove(struct virtio_device *vdev)
spin_unlock_irqrestore(&vi->lock, flags);
input_unregister_device(vi->idev);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
kfree(buf);
vdev->config->del_vqs(vdev);
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 96e5a87..38becd8 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -20,6 +20,7 @@
#include <linux/mutex.h>
#include <linux/bitmap.h>
#include <linux/lockdep.h>
+#include <linux/log2.h>
#include <acpi/acpi_numa.h>
@@ -592,7 +593,7 @@ static int virtio_mem_sbm_sb_states_prepare_next_mb(struct virtio_mem *vm)
return -ENOMEM;
mutex_lock(&vm->hotplug_mutex);
- if (new_bitmap)
+ if (vm->sbm.sb_states)
memcpy(new_bitmap, vm->sbm.sb_states, old_pages * PAGE_SIZE);
old_bitmap = vm->sbm.sb_states;
@@ -1120,15 +1121,18 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
*/
static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
{
- const unsigned long max_nr_pages = MAX_ORDER_NR_PAGES;
+ unsigned long order = MAX_ORDER - 1;
unsigned long i;
/*
- * We are always called at least with MAX_ORDER_NR_PAGES
- * granularity/alignment (e.g., the way subblocks work). All pages
- * inside such a block are alike.
+ * We might get called for ranges that don't cover properly aligned
+ * MAX_ORDER - 1 pages; however, we can only online properly aligned
+ * pages with an order of MAX_ORDER - 1 at maximum.
*/
- for (i = 0; i < nr_pages; i += max_nr_pages) {
+ while (!IS_ALIGNED(pfn | nr_pages, 1 << order))
+ order--;
+
+ for (i = 0; i < nr_pages; i += 1 << order) {
struct page *page = pfn_to_page(pfn + i);
/*
@@ -1138,14 +1142,12 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
* alike.
*/
if (PageDirty(page)) {
- virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
- false);
- generic_online_page(page, MAX_ORDER - 1);
+ virtio_mem_clear_fake_offline(pfn + i, 1 << order, false);
+ generic_online_page(page, order);
} else {
- virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
- true);
- free_contig_range(pfn + i, max_nr_pages);
- adjust_managed_page_count(page, max_nr_pages);
+ virtio_mem_clear_fake_offline(pfn + i, 1 << order, true);
+ free_contig_range(pfn + i, 1 << order);
+ adjust_managed_page_count(page, 1 << order);
}
}
}
@@ -1228,28 +1230,46 @@ static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
page_ref_inc(pfn_to_page(pfn + i));
}
-static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
+static void virtio_mem_online_page(struct virtio_mem *vm,
+ struct page *page, unsigned int order)
{
- const unsigned long addr = page_to_phys(page);
- unsigned long id, sb_id;
- struct virtio_mem *vm;
+ const unsigned long start = page_to_phys(page);
+ const unsigned long end = start + PFN_PHYS(1 << order);
+ unsigned long addr, next, id, sb_id, count;
bool do_online;
- rcu_read_lock();
- list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
- if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order)))
- continue;
+ /*
+ * We can get called with any order up to MAX_ORDER - 1. If our
+ * subblock size is smaller than that and we have a mixture of plugged
+ * and unplugged subblocks within such a page, we have to process in
+ * smaller granularity. In that case we'll adjust the order exactly once
+ * within the loop.
+ */
+ for (addr = start; addr < end; ) {
+ next = addr + PFN_PHYS(1 << order);
if (vm->in_sbm) {
- /*
- * We exploit here that subblocks have at least
- * MAX_ORDER_NR_PAGES size/alignment - so we cannot
- * cross subblocks within one call.
- */
id = virtio_mem_phys_to_mb_id(addr);
sb_id = virtio_mem_phys_to_sb_id(vm, addr);
- do_online = virtio_mem_sbm_test_sb_plugged(vm, id,
- sb_id, 1);
+ count = virtio_mem_phys_to_sb_id(vm, next - 1) - sb_id + 1;
+
+ if (virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, count)) {
+ /* Fully plugged. */
+ do_online = true;
+ } else if (count == 1 ||
+ virtio_mem_sbm_test_sb_unplugged(vm, id, sb_id, count)) {
+ /* Fully unplugged. */
+ do_online = false;
+ } else {
+ /*
+ * Mixture, process sub-blocks instead. This
+ * will be at least the size of a pageblock.
+ * We'll run into this case exactly once.
+ */
+ order = ilog2(vm->sbm.sb_size) - PAGE_SHIFT;
+ do_online = virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, 1);
+ continue;
+ }
} else {
/*
* If the whole block is marked fake offline, keep
@@ -1260,18 +1280,38 @@ static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
VIRTIO_MEM_BBM_BB_FAKE_OFFLINE;
}
+ if (do_online)
+ generic_online_page(pfn_to_page(PFN_DOWN(addr)), order);
+ else
+ virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
+ false);
+ addr = next;
+ }
+}
+
+static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
+{
+ const unsigned long addr = page_to_phys(page);
+ struct virtio_mem *vm;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
/*
- * virtio_mem_set_fake_offline() might sleep, we don't need
- * the device anymore. See virtio_mem_remove() how races
+ * Pages we're onlining will never cross memory blocks and,
+ * therefore, not virtio-mem devices.
+ */
+ if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order)))
+ continue;
+
+ /*
+ * virtio_mem_set_fake_offline() might sleep. We can safely
+ * drop the RCU lock at this point because the device
+ * cannot go away. See virtio_mem_remove() how races
* between memory onlining and device removal are handled.
*/
rcu_read_unlock();
- if (do_online)
- generic_online_page(page, order);
- else
- virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
- false);
+ virtio_mem_online_page(vm, page, order);
return;
}
rcu_read_unlock();
@@ -2438,8 +2478,6 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
/*
* We want subblocks to span at least MAX_ORDER_NR_PAGES and
* pageblock_nr_pages pages. This:
- * - Simplifies our page onlining code (virtio_mem_online_page_cb)
- * and fake page onlining code (virtio_mem_fake_online).
* - Is required for now for alloc_contig_range() to work reliably -
* it doesn't properly handle smaller granularity on ZONE_NORMAL.
*/
@@ -2850,7 +2888,7 @@ static void virtio_mem_remove(struct virtio_device *vdev)
virtio_mem_deinit_hotplug(vm);
/* reset the device and cleanup the queues */
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
kfree(vm);
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index b3f8128..34141b9 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -138,7 +138,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
if (q_pfn >> 32) {
dev_err(&vp_dev->pci_dev->dev,
- "platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+ "platform bug: legacy virtio-pci must not be used with RAM above 0x%llxGB\n",
0x1ULL << (32 + PAGE_SHIFT - 30));
err = -E2BIG;
goto out_del_vq;
diff --git a/drivers/virtio/virtio_pci_legacy_dev.c b/drivers/virtio/virtio_pci_legacy_dev.c
index 9b97680d..677d1f6 100644
--- a/drivers/virtio/virtio_pci_legacy_dev.c
+++ b/drivers/virtio/virtio_pci_legacy_dev.c
@@ -45,8 +45,10 @@ int vp_legacy_probe(struct virtio_pci_legacy_device *ldev)
return rc;
ldev->ioaddr = pci_iomap(pci_dev, 0, 0);
- if (!ldev->ioaddr)
+ if (!ldev->ioaddr) {
+ rc = -EIO;
goto err_iomap;
+ }
ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR;
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index e11ed74..e8b3ff2 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -345,7 +345,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
EXPORT_SYMBOL_GPL(vp_modern_probe);
/*
- * vp_modern_probe: remove and cleanup the modern virtio pci device
+ * vp_modern_remove: remove and cleanup the modern virtio pci device
* @mdev: the modern virtio-pci device
*/
void vp_modern_remove(struct virtio_pci_modern_device *mdev)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 028b05d..962f147 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1197,8 +1197,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
if (virtqueue_use_indirect(_vq, total_sg)) {
err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs,
in_sgs, data, gfp);
- if (err != -ENOMEM)
+ if (err != -ENOMEM) {
+ END_USE(vq);
return err;
+ }
/* fall back on direct */
}
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index f85f860..7767a7f 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -91,9 +91,8 @@ static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
{
struct vdpa_device *vdpa = vd_get_vdpa(vdev);
- const struct vdpa_config_ops *ops = vdpa->config;
- return ops->set_status(vdpa, status);
+ return vdpa_set_status(vdpa, status);
}
static void virtio_vdpa_reset(struct virtio_device *vdev)
@@ -308,7 +307,7 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
struct vdpa_device *vdpa = vd_get_vdpa(vdev);
const struct vdpa_config_ops *ops = vdpa->config;
- return ops->get_features(vdpa);
+ return ops->get_device_features(vdpa);
}
static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
@@ -318,7 +317,7 @@ static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
- return vdpa_set_features(vdpa, vdev->features);
+ return vdpa_set_features(vdpa, vdev->features, false);
}
static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index adbb3a1..5156821 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -355,7 +355,6 @@ int adfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct super_block *sb = inode->i_sb;
struct object_info obj;
- int ret;
obj.indaddr = ADFS_I(inode)->indaddr;
obj.name_len = 0;
@@ -365,6 +364,5 @@ int adfs_write_inode(struct inode *inode, struct writeback_control *wbc)
obj.attr = ADFS_I(inode)->attr;
obj.size = inode->i_size;
- ret = adfs_dir_update(sb, &obj, wbc->sync_mode == WB_SYNC_ALL);
- return ret;
+ return adfs_dir_update(sb, &obj, wbc->sync_mode == WB_SYNC_ALL);
}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f8c7f26..605017e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1116,11 +1116,11 @@ static int load_elf_binary(struct linux_binprm *bprm)
* independently randomized mmap region (0 load_bias
* without MAP_FIXED nor MAP_FIXED_NOREPLACE).
*/
- if (interpreter) {
+ alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
+ if (alignment > ELF_MIN_ALIGN) {
load_bias = ELF_ET_DYN_BASE;
if (current->flags & PF_RANDOMIZE)
load_bias += arch_mmap_rnd();
- alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
if (alignment)
load_bias &= ~(alignment - 1);
elf_flags |= MAP_FIXED_NOREPLACE;
@@ -1585,7 +1585,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid));
SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid));
rcu_read_unlock();
- strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
+ get_task_comm(psinfo->pr_fname, p);
return 0;
}
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 520a0f6..183e5c4 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -18,8 +18,7 @@
select RAID6_PQ
select XOR_BLOCKS
select SRCU
- depends on !PPC_256K_PAGES # powerpc
- depends on !PAGE_SIZE_256KB # hexagon
+ depends on PAGE_SIZE_LESS_THAN_256KB
help
Btrfs is a general purpose copy-on-write filesystem with extents,
diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c
index ce4d478..7077f72 100644
--- a/fs/cachefiles/cache.c
+++ b/fs/cachefiles/cache.c
@@ -49,11 +49,19 @@ int cachefiles_add_cache(struct cachefiles_cache *cache)
goto error_unsupported;
}
- /* check parameters */
+ /* Check features of the backing filesystem:
+ * - Directories must support looking up and directory creation
+ * - We create tmpfiles to handle invalidation
+ * - We use xattrs to store metadata
+ * - We need to be able to query the amount of space available
+ * - We want to be able to sync the filesystem when stopping the cache
+ * - We use DIO to/from pages, so the blocksize mustn't be too big.
+ */
ret = -EOPNOTSUPP;
if (d_is_negative(root) ||
!d_backing_inode(root)->i_op->lookup ||
!d_backing_inode(root)->i_op->mkdir ||
+ !d_backing_inode(root)->i_op->tmpfile ||
!(d_backing_inode(root)->i_opflags & IOP_XATTR) ||
!root->d_sb->s_op->statfs ||
!root->d_sb->s_op->sync_fs ||
@@ -84,9 +92,7 @@ int cachefiles_add_cache(struct cachefiles_cache *cache)
goto error_unsupported;
cache->bsize = stats.f_bsize;
- cache->bshift = 0;
- if (stats.f_bsize < PAGE_SIZE)
- cache->bshift = PAGE_SHIFT - ilog2(stats.f_bsize);
+ cache->bshift = ilog2(stats.f_bsize);
_debug("blksize %u (shift %u)",
cache->bsize, cache->bshift);
@@ -106,7 +112,6 @@ int cachefiles_add_cache(struct cachefiles_cache *cache)
(unsigned long long) cache->fcull,
(unsigned long long) cache->fstop);
- stats.f_blocks >>= cache->bshift;
do_div(stats.f_blocks, 100);
cache->bstop = stats.f_blocks * cache->bstop_percent;
cache->bcull = stats.f_blocks * cache->bcull_percent;
@@ -209,7 +214,7 @@ int cachefiles_has_space(struct cachefiles_cache *cache,
return ret;
}
- b_avail = stats.f_bavail >> cache->bshift;
+ b_avail = stats.f_bavail;
b_writing = atomic_long_read(&cache->b_writing);
if (b_avail > b_writing)
b_avail -= b_writing;
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 40a7924..7ac04ee 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -703,6 +703,17 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
return -EBUSY;
}
+ /* Make sure we have copies of the tag string */
+ if (!cache->tag) {
+ /*
+ * The tag string is released by the fops->release()
+ * function, so we don't release it on error here
+ */
+ cache->tag = kstrdup("CacheFiles", GFP_KERNEL);
+ if (!cache->tag)
+ return -ENOMEM;
+ }
+
return cachefiles_add_cache(cache);
}
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 8dd54d9..c793d33 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -86,7 +86,7 @@ struct cachefiles_cache {
unsigned bcull_percent; /* when to start culling (% blocks) */
unsigned bstop_percent; /* when to stop allocating (% blocks) */
unsigned bsize; /* cache's block size */
- unsigned bshift; /* min(ilog2(PAGE_SIZE / bsize), 0) */
+ unsigned bshift; /* ilog2(bsize) */
uint64_t frun; /* when to stop culling */
uint64_t fcull; /* when to start culling */
uint64_t fstop; /* when to stop allocating */
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 60b1eac..04eb5273 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -264,7 +264,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres,
ki->term_func = term_func;
ki->term_func_priv = term_func_priv;
ki->was_async = true;
- ki->b_writing = (len + (1 << cache->bshift)) >> cache->bshift;
+ ki->b_writing = (len + (1 << cache->bshift) - 1) >> cache->bshift;
if (ki->term_func)
ki->iocb.ki_complete = cachefiles_write_complete;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 9bd6928..f256c8a 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -25,7 +25,9 @@ static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object,
trace_cachefiles_mark_active(object, inode);
can_use = true;
} else {
- pr_notice("cachefiles: Inode already in use: %pd\n", dentry);
+ trace_cachefiles_mark_failed(object, inode);
+ pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n",
+ dentry, inode->i_ino);
}
return can_use;
@@ -101,6 +103,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
subdir = lookup_one_len(dirname, dir, strlen(dirname));
else
subdir = ERR_PTR(ret);
+ trace_cachefiles_lookup(NULL, dir, subdir);
if (IS_ERR(subdir)) {
trace_cachefiles_vfs_error(NULL, d_backing_inode(dir),
PTR_ERR(subdir),
@@ -135,6 +138,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
cachefiles_trace_mkdir_error);
goto mkdir_error;
}
+ trace_cachefiles_mkdir(dir, subdir);
if (unlikely(d_unhashed(subdir))) {
cachefiles_put_directory(subdir);
@@ -233,7 +237,7 @@ static int cachefiles_unlink(struct cachefiles_cache *cache,
};
int ret;
- trace_cachefiles_unlink(object, dentry, why);
+ trace_cachefiles_unlink(object, d_inode(dentry)->i_ino, why);
ret = security_path_unlink(&path, dentry);
if (ret < 0) {
cachefiles_io_error(cache, "Unlink security error");
@@ -386,7 +390,7 @@ int cachefiles_bury_object(struct cachefiles_cache *cache,
.new_dir = d_inode(cache->graveyard),
.new_dentry = grave,
};
- trace_cachefiles_rename(object, rep, grave, why);
+ trace_cachefiles_rename(object, d_inode(rep)->i_ino, why);
ret = cachefiles_inject_read_error();
if (ret == 0)
ret = vfs_rename(&rd);
@@ -617,7 +621,7 @@ bool cachefiles_look_up_object(struct cachefiles_object *object)
object->d_name_len);
else
dentry = ERR_PTR(ret);
- trace_cachefiles_lookup(object, dentry);
+ trace_cachefiles_lookup(object, fan, dentry);
if (IS_ERR(dentry)) {
if (dentry == ERR_PTR(-ENOENT))
goto new_file;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b3d9459..c98e523 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -297,10 +297,6 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
dout("%s: result %d\n", __func__, err);
}
-static void ceph_init_rreq(struct netfs_read_request *rreq, struct file *file)
-{
-}
-
static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
{
struct inode *inode = mapping->host;
@@ -312,7 +308,6 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
}
static const struct netfs_read_request_ops ceph_netfs_read_ops = {
- .init_rreq = ceph_init_rreq,
.is_cache_enabled = ceph_is_cache_enabled,
.begin_cache_operation = ceph_begin_cache_operation,
.issue_op = ceph_netfs_issue_op,
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 7d2c33c..7d305b9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3376,8 +3376,7 @@ static void handle_cap_grant(struct inode *inode,
if ((newcaps & CEPH_CAP_LINK_SHARED) &&
(extra_info->issued & CEPH_CAP_LINK_EXCL) == 0) {
set_nlink(inode, le32_to_cpu(grant->nlink));
- if (inode->i_nlink == 0 &&
- (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
+ if (inode->i_nlink == 0)
deleted_inode = true;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 9d9304e..5b9104b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -204,6 +204,8 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
int fmode, bool isdir)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_mount_options *opt =
+ ceph_inode_to_client(&ci->vfs_inode)->mount_options;
struct ceph_file_info *fi;
dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
@@ -225,6 +227,9 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
if (!fi)
return -ENOMEM;
+ if (opt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
+ fi->flags |= CEPH_F_SYNC;
+
file->private_data = fi;
}
@@ -1541,7 +1546,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
struct ceph_inode_info *ci = ceph_inode(inode);
bool direct_lock = iocb->ki_flags & IOCB_DIRECT;
ssize_t ret;
- int want, got = 0;
+ int want = 0, got = 0;
int retry_op = 0, read = 0;
again:
@@ -1556,13 +1561,14 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
else
ceph_start_io_read(inode);
+ if (!(fi->flags & CEPH_F_SYNC) && !direct_lock)
+ want |= CEPH_CAP_FILE_CACHE;
if (fi->fmode & CEPH_FILE_MODE_LAZY)
- want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
- else
- want = CEPH_CAP_FILE_CACHE;
+ want |= CEPH_CAP_FILE_LAZYIO;
+
ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, &got);
if (ret < 0) {
- if (iocb->ki_flags & IOCB_DIRECT)
+ if (direct_lock)
ceph_end_io_direct(inode);
else
ceph_end_io_read(inode);
@@ -1696,7 +1702,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct ceph_osd_client *osdc = &fsc->client->osdc;
struct ceph_cap_flush *prealloc_cf;
ssize_t count, written = 0;
- int err, want, got;
+ int err, want = 0, got;
bool direct_lock = false;
u32 map_flags;
u64 pool_flags;
@@ -1771,10 +1777,10 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
inode, ceph_vinop(inode), pos, count, i_size_read(inode));
+ if (!(fi->flags & CEPH_F_SYNC) && !direct_lock)
+ want |= CEPH_CAP_FILE_BUFFER;
if (fi->fmode & CEPH_FILE_MODE_LAZY)
- want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
- else
- want = CEPH_CAP_FILE_BUFFER;
+ want |= CEPH_CAP_FILE_LAZYIO;
got = 0;
err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count, &got);
if (err < 0)
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index c57699d..0fcba68 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -160,8 +160,6 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
msg->hdr.version = cpu_to_le16(1);
msg->hdr.compat_version = cpu_to_le16(1);
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
- dout("client%llu send metrics to mds%d\n",
- ceph_client_gid(mdsc->fsc->client), s->s_mds);
ceph_con_send(&s->s_con, msg);
return true;
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 620c691..a338a3e 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -30,6 +30,9 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode)
/* if root is the real CephFS root, we don't have quota realms */
if (root && ceph_ino(root) == CEPH_INO_ROOT)
return false;
+ /* MDS stray dirs have no quota realms */
+ if (ceph_vino_is_reserved(ceph_inode(inode)->i_vino))
+ return false;
/* otherwise, we can't know for sure */
return true;
}
@@ -494,10 +497,24 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
if (ci->i_max_bytes) {
total = ci->i_max_bytes >> CEPH_BLOCK_SHIFT;
used = ci->i_rbytes >> CEPH_BLOCK_SHIFT;
+ /* For quota size less than 4MB, use 4KB block size */
+ if (!total) {
+ total = ci->i_max_bytes >> CEPH_4K_BLOCK_SHIFT;
+ used = ci->i_rbytes >> CEPH_4K_BLOCK_SHIFT;
+ buf->f_frsize = 1 << CEPH_4K_BLOCK_SHIFT;
+ }
/* It is possible for a quota to be exceeded.
* Report 'zero' in that case
*/
free = total > used ? total - used : 0;
+ /* For quota size less than 4KB, report the
+ * total=used=4KB,free=0 when quota is full
+ * and total=free=4KB, used=0 otherwise */
+ if (!total) {
+ total = 1;
+ free = ci->i_max_bytes > ci->i_rbytes ? 1 : 0;
+ buf->f_frsize = 1 << CEPH_4K_BLOCK_SHIFT;
+ }
}
spin_unlock(&ci->i_ceph_lock);
if (total) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bea89bd..bf79f36 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,8 @@
#include <linux/ceph/auth.h>
#include <linux/ceph/debugfs.h>
+#include <uapi/linux/magic.h>
+
static DEFINE_SPINLOCK(ceph_fsc_lock);
static LIST_HEAD(ceph_fsc_list);
@@ -146,6 +148,7 @@ enum {
Opt_mds_namespace,
Opt_recover_session,
Opt_source,
+ Opt_mon_addr,
/* string args above */
Opt_dirstat,
Opt_rbytes,
@@ -159,6 +162,7 @@ enum {
Opt_quotadf,
Opt_copyfrom,
Opt_wsync,
+ Opt_pagecache,
};
enum ceph_recover_session_mode {
@@ -197,8 +201,10 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
fsparam_u32 ("rsize", Opt_rsize),
fsparam_string ("snapdirname", Opt_snapdirname),
fsparam_string ("source", Opt_source),
+ fsparam_string ("mon_addr", Opt_mon_addr),
fsparam_u32 ("wsize", Opt_wsize),
fsparam_flag_no ("wsync", Opt_wsync),
+ fsparam_flag_no ("pagecache", Opt_pagecache),
{}
};
@@ -228,9 +234,92 @@ static void canonicalize_path(char *path)
}
/*
- * Parse the source parameter. Distinguish the server list from the path.
+ * Check if the mds namespace in ceph_mount_options matches
+ * the passed in namespace string. First time match (when
+ * ->mds_namespace is NULL) is treated specially, since
+ * ->mds_namespace needs to be initialized by the caller.
+ */
+static int namespace_equals(struct ceph_mount_options *fsopt,
+ const char *namespace, size_t len)
+{
+ return !(fsopt->mds_namespace &&
+ (strlen(fsopt->mds_namespace) != len ||
+ strncmp(fsopt->mds_namespace, namespace, len)));
+}
+
+static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end,
+ struct fs_context *fc)
+{
+ int r;
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
+
+ if (*dev_name_end != ':')
+ return invalfc(fc, "separator ':' missing in source");
+
+ r = ceph_parse_mon_ips(dev_name, dev_name_end - dev_name,
+ pctx->copts, fc->log.log, ',');
+ if (r)
+ return r;
+
+ fsopt->new_dev_syntax = false;
+ return 0;
+}
+
+static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end,
+ struct fs_context *fc)
+{
+ size_t len;
+ struct ceph_fsid fsid;
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
+ char *fsid_start, *fs_name_start;
+
+ if (*dev_name_end != '=') {
+ dout("separator '=' missing in source");
+ return -EINVAL;
+ }
+
+ fsid_start = strchr(dev_name, '@');
+ if (!fsid_start)
+ return invalfc(fc, "missing cluster fsid");
+ ++fsid_start; /* start of cluster fsid */
+
+ fs_name_start = strchr(fsid_start, '.');
+ if (!fs_name_start)
+ return invalfc(fc, "missing file system name");
+
+ if (ceph_parse_fsid(fsid_start, &fsid))
+ return invalfc(fc, "Invalid FSID");
+
+ ++fs_name_start; /* start of file system name */
+ len = dev_name_end - fs_name_start;
+
+ if (!namespace_equals(fsopt, fs_name_start, len))
+ return invalfc(fc, "Mismatching mds_namespace");
+ kfree(fsopt->mds_namespace);
+ fsopt->mds_namespace = kstrndup(fs_name_start, len, GFP_KERNEL);
+ if (!fsopt->mds_namespace)
+ return -ENOMEM;
+ dout("file system (mds namespace) '%s'\n", fsopt->mds_namespace);
+
+ fsopt->new_dev_syntax = true;
+ return 0;
+}
+
+/*
+ * Parse the source parameter for new device format. Distinguish the device
+ * spec from the path. Try parsing new device format and fallback to old
+ * format if needed.
*
- * The source will look like:
+ * New device syntax will looks like:
+ * <device_spec>=/<path>
+ * where
+ * <device_spec> is name@fsid.fsname
+ * <path> is optional, but if present must begin with '/'
+ * (monitor addresses are passed via mount option)
+ *
+ * Old device syntax is:
* <server_spec>[,<server_spec>...]:[<path>]
* where
* <server_spec> is <ip>[:<port>]
@@ -263,24 +352,44 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc)
dev_name_end = dev_name + strlen(dev_name);
}
- dev_name_end--; /* back up to ':' separator */
- if (dev_name_end < dev_name || *dev_name_end != ':')
- return invalfc(fc, "No path or : separator in source");
+ dev_name_end--; /* back up to separator */
+ if (dev_name_end < dev_name)
+ return invalfc(fc, "Path missing in source");
dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
if (fsopt->server_path)
dout("server path '%s'\n", fsopt->server_path);
- ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name,
- pctx->copts, fc->log.log);
- if (ret)
- return ret;
+ dout("trying new device syntax");
+ ret = ceph_parse_new_source(dev_name, dev_name_end, fc);
+ if (ret) {
+ if (ret != -EINVAL)
+ return ret;
+ dout("trying old device syntax");
+ ret = ceph_parse_old_source(dev_name, dev_name_end, fc);
+ if (ret)
+ return ret;
+ }
fc->source = param->string;
param->string = NULL;
return 0;
}
+static int ceph_parse_mon_addr(struct fs_parameter *param,
+ struct fs_context *fc)
+{
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
+
+ kfree(fsopt->mon_addr);
+ fsopt->mon_addr = param->string;
+ param->string = NULL;
+
+ return ceph_parse_mon_ips(fsopt->mon_addr, strlen(fsopt->mon_addr),
+ pctx->copts, fc->log.log, '/');
+}
+
static int ceph_parse_mount_param(struct fs_context *fc,
struct fs_parameter *param)
{
@@ -306,6 +415,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
param->string = NULL;
break;
case Opt_mds_namespace:
+ if (!namespace_equals(fsopt, param->string, strlen(param->string)))
+ return invalfc(fc, "Mismatching mds_namespace");
kfree(fsopt->mds_namespace);
fsopt->mds_namespace = param->string;
param->string = NULL;
@@ -323,6 +434,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
if (fc->source)
return invalfc(fc, "Multiple sources specified");
return ceph_parse_source(param, fc);
+ case Opt_mon_addr:
+ return ceph_parse_mon_addr(param, fc);
case Opt_wsize:
if (result.uint_32 < PAGE_SIZE ||
result.uint_32 > CEPH_MAX_WRITE_SIZE)
@@ -455,6 +568,12 @@ static int ceph_parse_mount_param(struct fs_context *fc,
else
fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS;
break;
+ case Opt_pagecache:
+ if (result.negated)
+ fsopt->flags |= CEPH_MOUNT_OPT_NOPAGECACHE;
+ else
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE;
+ break;
default:
BUG();
}
@@ -474,6 +593,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
kfree(args->mds_namespace);
kfree(args->server_path);
kfree(args->fscache_uniq);
+ kfree(args->mon_addr);
kfree(args);
}
@@ -517,6 +637,10 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
if (ret)
return ret;
+ ret = strcmp_null(fsopt1->mon_addr, fsopt2->mon_addr);
+ if (ret)
+ return ret;
+
return ceph_compare_options(new_opt, fsc->client);
}
@@ -572,15 +696,22 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0)
seq_puts(m, ",copyfrom");
- if (fsopt->mds_namespace)
+ /* dump mds_namespace when old device syntax is in use */
+ if (fsopt->mds_namespace && !fsopt->new_dev_syntax)
seq_show_option(m, "mds_namespace", fsopt->mds_namespace);
+ if (fsopt->mon_addr)
+ seq_printf(m, ",mon_addr=%s", fsopt->mon_addr);
+
if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER)
seq_show_option(m, "recover_session", "clean");
if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
seq_puts(m, ",wsync");
+ if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
+ seq_puts(m, ",nopagecache");
+
if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
seq_printf(m, ",wsize=%u", fsopt->wsize);
if (fsopt->rsize != CEPH_MAX_READ_SIZE)
@@ -1052,6 +1183,7 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
static int ceph_get_tree(struct fs_context *fc)
{
struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
struct super_block *sb;
struct ceph_fs_client *fsc;
struct dentry *res;
@@ -1063,6 +1195,8 @@ static int ceph_get_tree(struct fs_context *fc)
if (!fc->source)
return invalfc(fc, "No source");
+ if (fsopt->new_dev_syntax && !fsopt->mon_addr)
+ return invalfc(fc, "No monitor address");
/* create client (which we may/may not use) */
fsc = create_fs_client(pctx->opts, pctx->copts);
@@ -1148,6 +1282,13 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
else
ceph_clear_mount_opt(fsc, ASYNC_DIROPS);
+ if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) {
+ kfree(fsc->mount_options->mon_addr);
+ fsc->mount_options->mon_addr = fsopt->mon_addr;
+ fsopt->mon_addr = NULL;
+ pr_notice("ceph: monitor addresses recorded, but not used for reconnection");
+ }
+
sync_filesystem(fc->root->d_sb);
return 0;
}
@@ -1325,6 +1466,14 @@ bool disable_send_metrics = false;
module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644);
MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
+/* for both v1 and v2 syntax */
+static bool mount_support = true;
+static const struct kernel_param_ops param_ops_mount_syntax = {
+ .get = param_get_bool,
+};
+module_param_cb(mount_syntax_v1, ¶m_ops_mount_syntax, &mount_support, 0444);
+module_param_cb(mount_syntax_v2, ¶m_ops_mount_syntax, &mount_support, 0444);
+
module_init(init_ceph);
module_exit(exit_ceph);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d0142cc..67f145e 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -24,13 +24,11 @@
#include <linux/fscache.h>
#endif
-/* f_type in struct statfs */
-#define CEPH_SUPER_MAGIC 0x00c36400
-
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
#define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
+#define CEPH_4K_BLOCK_SHIFT 12 /* 4 KB */
#define CEPH_MOUNT_OPT_CLEANRECOVER (1<<1) /* auto reonnect (clean mode) after blocklisted */
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
@@ -44,6 +42,7 @@
#define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */
#define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */
#define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */
+#define CEPH_MOUNT_OPT_NOPAGECACHE (1<<16) /* bypass pagecache altogether */
#define CEPH_MOUNT_OPT_DEFAULT \
(CEPH_MOUNT_OPT_DCACHE | \
@@ -88,6 +87,8 @@ struct ceph_mount_options {
unsigned int max_readdir; /* max readdir result (entries) */
unsigned int max_readdir_bytes; /* max readdir result (bytes) */
+ bool new_dev_syntax;
+
/*
* everything above this point can be memcmp'd; everything below
* is handled in compare_mount_options()
@@ -97,6 +98,7 @@ struct ceph_mount_options {
char *mds_namespace; /* default NULL */
char *server_path; /* default NULL (means "/") */
char *fscache_uniq; /* default NULL */
+ char *mon_addr;
};
struct ceph_fs_client {
@@ -534,19 +536,23 @@ static inline int ceph_ino_compare(struct inode *inode, void *data)
*
* These come from src/mds/mdstypes.h in the ceph sources.
*/
-#define CEPH_MAX_MDS 0x100
-#define CEPH_NUM_STRAY 10
+#define CEPH_MAX_MDS 0x100
+#define CEPH_NUM_STRAY 10
#define CEPH_MDS_INO_MDSDIR_OFFSET (1 * CEPH_MAX_MDS)
+#define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS)
#define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY))
static inline bool ceph_vino_is_reserved(const struct ceph_vino vino)
{
- if (vino.ino < CEPH_INO_SYSTEM_BASE &&
- vino.ino >= CEPH_MDS_INO_MDSDIR_OFFSET) {
- WARN_RATELIMIT(1, "Attempt to access reserved inode number 0x%llx", vino.ino);
- return true;
- }
- return false;
+ if (vino.ino >= CEPH_INO_SYSTEM_BASE ||
+ vino.ino < CEPH_MDS_INO_MDSDIR_OFFSET)
+ return false;
+
+ /* Don't warn on mdsdirs */
+ WARN_RATELIMIT(vino.ino >= CEPH_MDS_INO_LOG_OFFSET,
+ "Attempt to access reserved inode number 0x%llx",
+ vino.ino);
+ return true;
}
static inline struct inode *ceph_find_inode(struct super_block *sb,
diff --git a/fs/exec.c b/fs/exec.c
index 82db656..3c3c366 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1207,7 +1207,8 @@ static int unshare_sighand(struct task_struct *me)
char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
{
task_lock(tsk);
- strncpy(buf, tsk->comm, buf_size);
+ /* Always NUL terminated and zero-padded */
+ strscpy_pad(buf, tsk->comm, buf_size);
task_unlock(tsk);
return buf;
}
@@ -1222,7 +1223,7 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
{
task_lock(tsk);
trace_task_rename(tsk, buf);
- strlcpy(tsk->comm, buf, sizeof(tsk->comm));
+ strscpy_pad(tsk->comm, buf, sizeof(tsk->comm));
task_unlock(tsk);
perf_event_comm(tsk, exec);
}
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 7eea3cf..f46a733 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -7,6 +7,7 @@
select CRYPTO_CRC32
select F2FS_FS_XATTR if FS_ENCRYPTION
select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+ select FS_IOMAP
select LZ4_COMPRESS if F2FS_FS_LZ4
select LZ4_DECOMPRESS if F2FS_FS_LZ4
select LZ4HC_COMPRESS if F2FS_FS_LZ4HC
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f1693d4..982f017 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -664,7 +664,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
/* truncate all the data during iput */
iput(inode);
- err = f2fs_get_node_info(sbi, ino, &ni);
+ err = f2fs_get_node_info(sbi, ino, &ni, false);
if (err)
goto err_out;
@@ -1302,8 +1302,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
unsigned long flags;
if (cpc->reason & CP_UMOUNT) {
- if (le32_to_cpu(ckpt->cp_pack_total_block_count) >
- sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks) {
+ if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
+ NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) {
clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
f2fs_notice(sbi, "Disable nat_bits due to no space");
} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 49121a2..d0c3aeb 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -154,6 +154,7 @@ void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse)
cc->rpages = NULL;
cc->nr_rpages = 0;
cc->nr_cpages = 0;
+ cc->valid_nr_cpages = 0;
if (!reuse)
cc->cluster_idx = NULL_CLUSTER;
}
@@ -620,7 +621,6 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
const struct f2fs_compress_ops *cops =
f2fs_cops[fi->i_compress_algorithm];
unsigned int max_len, new_nr_cpages;
- struct page **new_cpages;
u32 chksum = 0;
int i, ret;
@@ -635,6 +635,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
max_len = COMPRESS_HEADER_SIZE + cc->clen;
cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE);
+ cc->valid_nr_cpages = cc->nr_cpages;
cc->cpages = page_array_alloc(cc->inode, cc->nr_cpages);
if (!cc->cpages) {
@@ -685,13 +686,6 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
new_nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
- /* Now we're going to cut unnecessary tail pages */
- new_cpages = page_array_alloc(cc->inode, new_nr_cpages);
- if (!new_cpages) {
- ret = -ENOMEM;
- goto out_vunmap_cbuf;
- }
-
/* zero out any unused part of the last page */
memset(&cc->cbuf->cdata[cc->clen], 0,
(new_nr_cpages * PAGE_SIZE) -
@@ -701,10 +695,8 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
vm_unmap_ram(cc->rbuf, cc->cluster_size);
for (i = 0; i < cc->nr_cpages; i++) {
- if (i < new_nr_cpages) {
- new_cpages[i] = cc->cpages[i];
+ if (i < new_nr_cpages)
continue;
- }
f2fs_compress_free_page(cc->cpages[i]);
cc->cpages[i] = NULL;
}
@@ -712,9 +704,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
if (cops->destroy_compress_ctx)
cops->destroy_compress_ctx(cc);
- page_array_free(cc->inode, cc->cpages, cc->nr_cpages);
- cc->cpages = new_cpages;
- cc->nr_cpages = new_nr_cpages;
+ cc->valid_nr_cpages = new_nr_cpages;
trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
cc->clen, ret);
@@ -1296,7 +1286,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
- err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
if (err)
goto out_put_dnode;
@@ -1308,14 +1298,14 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
cic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
cic->inode = inode;
- atomic_set(&cic->pending_pages, cc->nr_cpages);
+ atomic_set(&cic->pending_pages, cc->valid_nr_cpages);
cic->rpages = page_array_alloc(cc->inode, cc->cluster_size);
if (!cic->rpages)
goto out_put_cic;
cic->nr_rpages = cc->cluster_size;
- for (i = 0; i < cc->nr_cpages; i++) {
+ for (i = 0; i < cc->valid_nr_cpages; i++) {
f2fs_set_compressed_page(cc->cpages[i], inode,
cc->rpages[i + 1]->index, cic);
fio.compressed_page = cc->cpages[i];
@@ -1360,7 +1350,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
if (fio.compr_blocks && __is_valid_data_blkaddr(blkaddr))
fio.compr_blocks++;
- if (i > cc->nr_cpages) {
+ if (i > cc->valid_nr_cpages) {
if (__is_valid_data_blkaddr(blkaddr)) {
f2fs_invalidate_blocks(sbi, blkaddr);
f2fs_update_data_blkaddr(&dn, NEW_ADDR);
@@ -1385,8 +1375,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
if (fio.compr_blocks)
f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false);
- f2fs_i_compr_blocks_update(inode, cc->nr_cpages, true);
- add_compr_block_stat(inode, cc->nr_cpages);
+ f2fs_i_compr_blocks_update(inode, cc->valid_nr_cpages, true);
+ add_compr_block_stat(inode, cc->valid_nr_cpages);
set_inode_flag(cc->inode, FI_APPEND_WRITE);
if (cc->cluster_idx == 0)
@@ -1424,9 +1414,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
else
f2fs_unlock_op(sbi);
out_free:
- for (i = 0; i < cc->nr_cpages; i++) {
- if (!cc->cpages[i])
- continue;
+ for (i = 0; i < cc->valid_nr_cpages; i++) {
f2fs_compress_free_page(cc->cpages[i]);
cc->cpages[i] = NULL;
}
@@ -1468,25 +1456,38 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
enum iostat_type io_type)
{
struct address_space *mapping = cc->inode->i_mapping;
- int _submitted, compr_blocks, ret;
- int i = -1, err = 0;
+ int _submitted, compr_blocks, ret, i;
compr_blocks = f2fs_compressed_blocks(cc);
- if (compr_blocks < 0) {
- err = compr_blocks;
- goto out_err;
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (!cc->rpages[i])
+ continue;
+
+ redirty_page_for_writepage(wbc, cc->rpages[i]);
+ unlock_page(cc->rpages[i]);
}
+ if (compr_blocks < 0)
+ return compr_blocks;
+
for (i = 0; i < cc->cluster_size; i++) {
if (!cc->rpages[i])
continue;
retry_write:
+ lock_page(cc->rpages[i]);
+
if (cc->rpages[i]->mapping != mapping) {
+continue_unlock:
unlock_page(cc->rpages[i]);
continue;
}
- BUG_ON(!PageLocked(cc->rpages[i]));
+ if (!PageDirty(cc->rpages[i]))
+ goto continue_unlock;
+
+ if (!clear_page_dirty_for_io(cc->rpages[i]))
+ goto continue_unlock;
ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
NULL, NULL, wbc, io_type,
@@ -1501,26 +1502,15 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
* avoid deadlock caused by cluster update race
* from foreground operation.
*/
- if (IS_NOQUOTA(cc->inode)) {
- err = 0;
- goto out_err;
- }
+ if (IS_NOQUOTA(cc->inode))
+ return 0;
ret = 0;
cond_resched();
congestion_wait(BLK_RW_ASYNC,
DEFAULT_IO_TIMEOUT);
- lock_page(cc->rpages[i]);
-
- if (!PageDirty(cc->rpages[i])) {
- unlock_page(cc->rpages[i]);
- continue;
- }
-
- clear_page_dirty_for_io(cc->rpages[i]);
goto retry_write;
}
- err = ret;
- goto out_err;
+ return ret;
}
*submitted += _submitted;
@@ -1529,14 +1519,6 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
f2fs_balance_fs(F2FS_M_SB(mapping), true);
return 0;
-out_err:
- for (++i; i < cc->cluster_size; i++) {
- if (!cc->rpages[i])
- continue;
- redirty_page_for_writepage(wbc, cc->rpages[i]);
- unlock_page(cc->rpages[i]);
- }
- return err;
}
int f2fs_write_multi_pages(struct compress_ctx *cc,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index aacf5e4..0a1d236 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -21,6 +21,7 @@
#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
+#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
@@ -1354,7 +1355,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- err = f2fs_get_node_info(sbi, dn->nid, &ni);
+ err = f2fs_get_node_info(sbi, dn->nid, &ni, false);
if (err)
return err;
@@ -1376,61 +1377,9 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
f2fs_invalidate_compress_page(sbi, old_blkaddr);
}
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
-
- /*
- * i_size will be updated by direct_IO. Otherwise, we'll get stale
- * data from unwritten block via dio_read.
- */
return 0;
}
-int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- struct f2fs_map_blocks map;
- int flag;
- int err = 0;
- bool direct_io = iocb->ki_flags & IOCB_DIRECT;
-
- map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
- map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
- if (map.m_len > map.m_lblk)
- map.m_len -= map.m_lblk;
- else
- map.m_len = 0;
-
- map.m_next_pgofs = NULL;
- map.m_next_extent = NULL;
- map.m_seg_type = NO_CHECK_TYPE;
- map.m_may_create = true;
-
- if (direct_io) {
- map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
- flag = f2fs_force_buffered_io(inode, iocb, from) ?
- F2FS_GET_BLOCK_PRE_AIO :
- F2FS_GET_BLOCK_PRE_DIO;
- goto map_blocks;
- }
- if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
- err = f2fs_convert_inline_inode(inode);
- if (err)
- return err;
- }
- if (f2fs_has_inline_data(inode))
- return err;
-
- flag = F2FS_GET_BLOCK_PRE_AIO;
-
-map_blocks:
- err = f2fs_map_blocks(inode, &map, 1, flag);
- if (map.m_len > 0 && err == -ENOSPC) {
- if (!direct_io)
- set_inode_flag(inode, FI_NO_PREALLOC);
- err = 0;
- }
- return err;
-}
-
void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
@@ -1590,8 +1539,11 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
flag != F2FS_GET_BLOCK_DIO);
err = __allocate_data_block(&dn,
map->m_seg_type);
- if (!err)
+ if (!err) {
+ if (flag == F2FS_GET_BLOCK_PRE_DIO)
+ file_need_truncate(inode);
set_inode_flag(inode, FI_APPEND_WRITE);
+ }
}
if (err)
goto sync_out;
@@ -1786,50 +1738,6 @@ static inline u64 blks_to_bytes(struct inode *inode, u64 blks)
return (blks << inode->i_blkbits);
}
-static int __get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create, int flag,
- pgoff_t *next_pgofs, int seg_type, bool may_write)
-{
- struct f2fs_map_blocks map;
- int err;
-
- map.m_lblk = iblock;
- map.m_len = bytes_to_blks(inode, bh->b_size);
- map.m_next_pgofs = next_pgofs;
- map.m_next_extent = NULL;
- map.m_seg_type = seg_type;
- map.m_may_create = may_write;
-
- err = f2fs_map_blocks(inode, &map, create, flag);
- if (!err) {
- map_bh(bh, inode->i_sb, map.m_pblk);
- bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
- bh->b_size = blks_to_bytes(inode, map.m_len);
-
- if (map.m_multidev_dio)
- bh->b_bdev = map.m_bdev;
- }
- return err;
-}
-
-static int get_data_block_dio_write(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_DIO, NULL,
- f2fs_rw_hint_to_seg_type(inode->i_write_hint),
- true);
-}
-
-static int get_data_block_dio(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_DIO, NULL,
- f2fs_rw_hint_to_seg_type(inode->i_write_hint),
- false);
-}
-
static int f2fs_xattr_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo)
{
@@ -1849,7 +1757,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
- err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+ err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false);
if (err) {
f2fs_put_page(page, 1);
return err;
@@ -1881,7 +1789,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
- err = f2fs_get_node_info(sbi, xnid, &ni);
+ err = f2fs_get_node_info(sbi, xnid, &ni, false);
if (err) {
f2fs_put_page(page, 1);
return err;
@@ -2617,6 +2525,11 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ /* The below cases were checked when setting it. */
+ if (f2fs_is_pinned_file(inode))
+ return false;
+ if (fio && is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+ return true;
if (f2fs_lfs_mode(sbi))
return true;
if (S_ISDIR(inode->i_mode))
@@ -2625,8 +2538,6 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
return true;
if (f2fs_is_atomic_file(inode))
return true;
- if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
- return true;
/* swap file is migrating in aligned write mode */
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
@@ -2738,7 +2649,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
fio->need_lock = LOCK_REQ;
}
- err = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(fio->sbi, dn.nid, &ni, false);
if (err)
goto out_writepage;
@@ -2987,6 +2898,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
.rpages = NULL,
.nr_rpages = 0,
.cpages = NULL,
+ .valid_nr_cpages = 0,
.rbuf = NULL,
.cbuf = NULL,
.rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size,
@@ -3305,7 +3217,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
FS_CP_DATA_IO : FS_DATA_IO);
}
-static void f2fs_write_failed(struct inode *inode, loff_t to)
+void f2fs_write_failed(struct inode *inode, loff_t to)
{
loff_t i_size = i_size_read(inode);
@@ -3339,12 +3251,10 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
int flag;
/*
- * we already allocated all the blocks, so we don't need to get
- * the block addresses when there is no need to fill the page.
+ * If a whole page is being written and we already preallocated all the
+ * blocks, then there is no need to get a block address now.
*/
- if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
- !is_inode_flag_set(inode, FI_NO_PREALLOC) &&
- !f2fs_verity_in_progress(inode))
+ if (len == PAGE_SIZE && is_inode_flag_set(inode, FI_PREALLOCATED_ALL))
return 0;
/* f2fs_lock_op avoids race between write CP and convert_inline_page */
@@ -3595,158 +3505,6 @@ static int f2fs_write_end(struct file *file,
return copied;
}
-static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
- loff_t offset)
-{
- unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
- unsigned blkbits = i_blkbits;
- unsigned blocksize_mask = (1 << blkbits) - 1;
- unsigned long align = offset | iov_iter_alignment(iter);
- struct block_device *bdev = inode->i_sb->s_bdev;
-
- if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
- return 1;
-
- if (align & blocksize_mask) {
- if (bdev)
- blkbits = blksize_bits(bdev_logical_block_size(bdev));
- blocksize_mask = (1 << blkbits) - 1;
- if (align & blocksize_mask)
- return -EINVAL;
- return 1;
- }
- return 0;
-}
-
-static void f2fs_dio_end_io(struct bio *bio)
-{
- struct f2fs_private_dio *dio = bio->bi_private;
-
- dec_page_count(F2FS_I_SB(dio->inode),
- dio->write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
-
- bio->bi_private = dio->orig_private;
- bio->bi_end_io = dio->orig_end_io;
-
- kfree(dio);
-
- bio_endio(bio);
-}
-
-static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode,
- loff_t file_offset)
-{
- struct f2fs_private_dio *dio;
- bool write = (bio_op(bio) == REQ_OP_WRITE);
-
- dio = f2fs_kzalloc(F2FS_I_SB(inode),
- sizeof(struct f2fs_private_dio), GFP_NOFS);
- if (!dio)
- goto out;
-
- dio->inode = inode;
- dio->orig_end_io = bio->bi_end_io;
- dio->orig_private = bio->bi_private;
- dio->write = write;
-
- bio->bi_end_io = f2fs_dio_end_io;
- bio->bi_private = dio;
-
- inc_page_count(F2FS_I_SB(inode),
- write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
-
- submit_bio(bio);
- return;
-out:
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
-}
-
-static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- size_t count = iov_iter_count(iter);
- loff_t offset = iocb->ki_pos;
- int rw = iov_iter_rw(iter);
- int err;
- enum rw_hint hint = iocb->ki_hint;
- int whint_mode = F2FS_OPTION(sbi).whint_mode;
- bool do_opu;
-
- err = check_direct_IO(inode, iter, offset);
- if (err)
- return err < 0 ? err : 0;
-
- if (f2fs_force_buffered_io(inode, iocb, iter))
- return 0;
-
- do_opu = rw == WRITE && f2fs_lfs_mode(sbi);
-
- trace_f2fs_direct_IO_enter(inode, offset, count, rw);
-
- if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
- iocb->ki_hint = WRITE_LIFE_NOT_SET;
-
- if (iocb->ki_flags & IOCB_NOWAIT) {
- if (!down_read_trylock(&fi->i_gc_rwsem[rw])) {
- iocb->ki_hint = hint;
- err = -EAGAIN;
- goto out;
- }
- if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) {
- up_read(&fi->i_gc_rwsem[rw]);
- iocb->ki_hint = hint;
- err = -EAGAIN;
- goto out;
- }
- } else {
- down_read(&fi->i_gc_rwsem[rw]);
- if (do_opu)
- down_read(&fi->i_gc_rwsem[READ]);
- }
-
- err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, rw == WRITE ? get_data_block_dio_write :
- get_data_block_dio, NULL, f2fs_dio_submit_bio,
- rw == WRITE ? DIO_LOCKING | DIO_SKIP_HOLES :
- DIO_SKIP_HOLES);
-
- if (do_opu)
- up_read(&fi->i_gc_rwsem[READ]);
-
- up_read(&fi->i_gc_rwsem[rw]);
-
- if (rw == WRITE) {
- if (whint_mode == WHINT_MODE_OFF)
- iocb->ki_hint = hint;
- if (err > 0) {
- f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
- err);
- if (!do_opu)
- set_inode_flag(inode, FI_UPDATE_WRITE);
- } else if (err == -EIOCBQUEUED) {
- f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
- count - iov_iter_count(iter));
- } else if (err < 0) {
- f2fs_write_failed(inode, offset + count);
- }
- } else {
- if (err > 0)
- f2fs_update_iostat(sbi, APP_DIRECT_READ_IO, err);
- else if (err == -EIOCBQUEUED)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_READ_IO,
- count - iov_iter_count(iter));
- }
-
-out:
- trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
-
- return err;
-}
-
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
@@ -3770,12 +3528,9 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
clear_page_private_gcing(page);
- if (test_opt(sbi, COMPRESS_CACHE)) {
- if (f2fs_compressed_file(inode))
- f2fs_invalidate_compress_pages(sbi, inode->i_ino);
- if (inode->i_ino == F2FS_COMPRESS_INO(sbi))
- clear_page_private_data(page);
- }
+ if (test_opt(sbi, COMPRESS_CACHE) &&
+ inode->i_ino == F2FS_COMPRESS_INO(sbi))
+ clear_page_private_data(page);
if (page_private_atomic(page))
return f2fs_drop_inmem_page(inode, page);
@@ -3795,12 +3550,9 @@ int f2fs_release_page(struct page *page, gfp_t wait)
return 0;
if (test_opt(F2FS_P_SB(page), COMPRESS_CACHE)) {
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct inode *inode = page->mapping->host;
- if (f2fs_compressed_file(inode))
- f2fs_invalidate_compress_pages(sbi, inode->i_ino);
- if (inode->i_ino == F2FS_COMPRESS_INO(sbi))
+ if (inode->i_ino == F2FS_COMPRESS_INO(F2FS_I_SB(inode)))
clear_page_private_data(page);
}
@@ -4202,7 +3954,7 @@ const struct address_space_operations f2fs_dblock_aops = {
.set_page_dirty = f2fs_set_data_page_dirty,
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
- .direct_IO = f2fs_direct_IO,
+ .direct_IO = noop_direct_IO,
.bmap = f2fs_bmap,
.swap_activate = f2fs_swap_activate,
.swap_deactivate = f2fs_swap_deactivate,
@@ -4282,3 +4034,58 @@ void f2fs_destroy_bio_entry_cache(void)
{
kmem_cache_destroy(bio_entry_slab);
}
+
+static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned int flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ struct f2fs_map_blocks map = {};
+ pgoff_t next_pgofs = 0;
+ int err;
+
+ map.m_lblk = bytes_to_blks(inode, offset);
+ map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1;
+ map.m_next_pgofs = &next_pgofs;
+ map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+ if (flags & IOMAP_WRITE)
+ map.m_may_create = true;
+
+ err = f2fs_map_blocks(inode, &map, flags & IOMAP_WRITE,
+ F2FS_GET_BLOCK_DIO);
+ if (err)
+ return err;
+
+ iomap->offset = blks_to_bytes(inode, map.m_lblk);
+
+ if (map.m_flags & (F2FS_MAP_MAPPED | F2FS_MAP_UNWRITTEN)) {
+ iomap->length = blks_to_bytes(inode, map.m_len);
+ if (map.m_flags & F2FS_MAP_MAPPED) {
+ iomap->type = IOMAP_MAPPED;
+ iomap->flags |= IOMAP_F_MERGED;
+ } else {
+ iomap->type = IOMAP_UNWRITTEN;
+ }
+ if (WARN_ON_ONCE(!__is_valid_data_blkaddr(map.m_pblk)))
+ return -EINVAL;
+
+ iomap->bdev = map.m_bdev;
+ iomap->addr = blks_to_bytes(inode, map.m_pblk);
+ } else {
+ iomap->length = blks_to_bytes(inode, next_pgofs) -
+ iomap->offset;
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
+ }
+
+ if (map.m_flags & F2FS_MAP_NEW)
+ iomap->flags |= IOMAP_F_NEW;
+ if ((inode->i_state & I_DIRTY_DATASYNC) ||
+ offset + length > i_size_read(inode))
+ iomap->flags |= IOMAP_F_DIRTY;
+
+ return 0;
+}
+
+const struct iomap_ops f2fs_iomap_ops = {
+ .iomap_begin = f2fs_iomap_begin,
+};
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d0d6031..eb22fa9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -58,6 +58,7 @@ enum {
FAULT_WRITE_IO,
FAULT_SLAB_ALLOC,
FAULT_DQUOT_INIT,
+ FAULT_LOCK_OP,
FAULT_MAX,
};
@@ -656,6 +657,7 @@ enum {
#define FADVISE_KEEP_SIZE_BIT 0x10
#define FADVISE_HOT_BIT 0x20
#define FADVISE_VERITY_BIT 0x40
+#define FADVISE_TRUNC_BIT 0x80
#define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT)
@@ -683,6 +685,10 @@ enum {
#define file_is_verity(inode) is_file(inode, FADVISE_VERITY_BIT)
#define file_set_verity(inode) set_file(inode, FADVISE_VERITY_BIT)
+#define file_should_truncate(inode) is_file(inode, FADVISE_TRUNC_BIT)
+#define file_need_truncate(inode) set_file(inode, FADVISE_TRUNC_BIT)
+#define file_dont_truncate(inode) clear_file(inode, FADVISE_TRUNC_BIT)
+
#define DEF_DIR_LEVEL 0
enum {
@@ -717,7 +723,7 @@ enum {
FI_INLINE_DOTS, /* indicate inline dot dentries */
FI_DO_DEFRAG, /* indicate defragment is running */
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
- FI_NO_PREALLOC, /* indicate skipped preallocated blocks */
+ FI_PREALLOCATED_ALL, /* all blocks for write were preallocated */
FI_HOT_DATA, /* indicate file is hot */
FI_EXTRA_ATTR, /* indicate file has extra attribute */
FI_PROJ_INHERIT, /* indicate file inherits projectid */
@@ -1020,6 +1026,7 @@ struct f2fs_sm_info {
unsigned int segment_count; /* total # of segments */
unsigned int main_segments; /* # of segments in main area */
unsigned int reserved_segments; /* # of reserved segments */
+ unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
unsigned int ovp_segments; /* # of overprovision segments */
/* a threshold to reclaim prefree segments */
@@ -1488,6 +1495,7 @@ struct compress_ctx {
unsigned int nr_rpages; /* total page number in rpages */
struct page **cpages; /* pages store compressed data in cluster */
unsigned int nr_cpages; /* total page number in cpages */
+ unsigned int valid_nr_cpages; /* valid page number in cpages */
void *rbuf; /* virtual mapped address on rpages */
struct compress_data *cbuf; /* virtual mapped address on cpages */
size_t rlen; /* valid data length in rbuf */
@@ -1679,6 +1687,9 @@ struct f2fs_sb_info {
unsigned int cur_victim_sec; /* current victim section num */
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
+ spinlock_t gc_urgent_high_lock;
+ bool gc_urgent_high_limited; /* indicates having limited trial count */
+ unsigned int gc_urgent_high_remaining; /* remaining trial count for GC_URGENT_HIGH */
/* for skip statistic */
unsigned int atomic_files; /* # of opened atomic file */
@@ -1803,13 +1814,6 @@ struct f2fs_sb_info {
#endif
};
-struct f2fs_private_dio {
- struct inode *inode;
- void *orig_private;
- bio_end_io_t *orig_end_io;
- bool write;
-};
-
#ifdef CONFIG_F2FS_FAULT_INJECTION
#define f2fs_show_injection_info(sbi, type) \
printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", \
@@ -2095,6 +2099,10 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
+ if (time_to_inject(sbi, FAULT_LOCK_OP)) {
+ f2fs_show_injection_info(sbi, FAULT_LOCK_OP);
+ return 0;
+ }
return down_read_trylock(&sbi->cp_rwsem);
}
@@ -2200,6 +2208,11 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
if (!__allow_reserved_blocks(sbi, inode, true))
avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (F2FS_IO_ALIGNED(sbi))
+ avail_user_block_count -= sbi->blocks_per_seg *
+ SM_I(sbi)->additional_reserved_segments;
+
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (avail_user_block_count > sbi->unusable_block_count)
avail_user_block_count -= sbi->unusable_block_count;
@@ -2446,6 +2459,11 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
if (!__allow_reserved_blocks(sbi, inode, false))
valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (F2FS_IO_ALIGNED(sbi))
+ valid_block_count += sbi->blocks_per_seg *
+ SM_I(sbi)->additional_reserved_segments;
+
user_block_count = sbi->user_block_count;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
user_block_count -= sbi->unusable_block_count;
@@ -3118,12 +3136,16 @@ static inline int is_file(struct inode *inode, int type)
static inline void set_file(struct inode *inode, int type)
{
+ if (is_file(inode, type))
+ return;
F2FS_I(inode)->i_advise |= type;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void clear_file(struct inode *inode, int type)
{
+ if (!is_file(inode, type))
+ return;
F2FS_I(inode)->i_advise &= ~type;
f2fs_mark_inode_dirty_sync(inode, true);
}
@@ -3408,7 +3430,7 @@ int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
- struct node_info *ni);
+ struct node_info *ni, bool checkpoint_context);
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
@@ -3616,7 +3638,6 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
@@ -3639,6 +3660,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
struct writeback_control *wbc,
enum iostat_type io_type,
int compr_blocks, bool allow_balance);
+void f2fs_write_failed(struct inode *inode, loff_t to);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3652,6 +3674,7 @@ int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
+extern const struct iomap_ops f2fs_iomap_ops;
/*
* gc.c
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 92ec269..3c98ef6 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -24,6 +24,7 @@
#include <linux/sched/signal.h>
#include <linux/fileattr.h>
#include <linux/fadvise.h>
+#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
@@ -1232,7 +1233,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
if (ret)
return ret;
- ret = f2fs_get_node_info(sbi, dn.nid, &ni);
+ ret = f2fs_get_node_info(sbi, dn.nid, &ni, false);
if (ret) {
f2fs_put_dnode(&dn);
return ret;
@@ -1687,6 +1688,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+ file_dont_truncate(inode);
up_write(&sbi->pin_sem);
@@ -1748,7 +1750,11 @@ static long f2fs_fallocate(struct file *file, int mode,
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
- if (f2fs_compressed_file(inode) &&
+ /*
+ * Pinned file should not support partial trucation since the block
+ * can be used by applications.
+ */
+ if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) &&
(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
@@ -3143,17 +3149,17 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
inode_lock(inode);
- if (f2fs_should_update_outplace(inode, NULL)) {
- ret = -EINVAL;
- goto out;
- }
-
if (!pin) {
clear_inode_flag(inode, FI_PIN_FILE);
f2fs_i_gc_failures_write(inode, 0);
goto done;
}
+ if (f2fs_should_update_outplace(inode, NULL)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (f2fs_pin_file_control(inode, false)) {
ret = -EAGAIN;
goto out;
@@ -4218,27 +4224,385 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return __f2fs_ioctl(filp, cmd, arg);
}
-static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+/*
+ * Return %true if the given read or write request should use direct I/O, or
+ * %false if it should use buffered I/O.
+ */
+static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb,
+ struct iov_iter *iter)
+{
+ unsigned int align;
+
+ if (!(iocb->ki_flags & IOCB_DIRECT))
+ return false;
+
+ if (f2fs_force_buffered_io(inode, iocb, iter))
+ return false;
+
+ /*
+ * Direct I/O not aligned to the disk's logical_block_size will be
+ * attempted, but will fail with -EINVAL.
+ *
+ * f2fs additionally requires that direct I/O be aligned to the
+ * filesystem block size, which is often a stricter requirement.
+ * However, f2fs traditionally falls back to buffered I/O on requests
+ * that are logical_block_size-aligned but not fs-block aligned.
+ *
+ * The below logic implements this behavior.
+ */
+ align = iocb->ki_pos | iov_iter_alignment(iter);
+ if (!IS_ALIGNED(align, i_blocksize(inode)) &&
+ IS_ALIGNED(align, bdev_logical_block_size(inode->i_sb->s_bdev)))
+ return false;
+
+ return true;
+}
+
+static int f2fs_dio_read_end_io(struct kiocb *iocb, ssize_t size, int error,
+ unsigned int flags)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp));
+
+ dec_page_count(sbi, F2FS_DIO_READ);
+ if (error)
+ return error;
+ f2fs_update_iostat(sbi, APP_DIRECT_READ_IO, size);
+ return 0;
+}
+
+static const struct iomap_dio_ops f2fs_iomap_dio_read_ops = {
+ .end_io = f2fs_dio_read_end_io,
+};
+
+static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
- int ret;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ const loff_t pos = iocb->ki_pos;
+ const size_t count = iov_iter_count(to);
+ struct iomap_dio *dio;
+ ssize_t ret;
+
+ if (count == 0)
+ return 0; /* skip atime update */
+
+ trace_f2fs_direct_IO_enter(inode, iocb, count, READ);
+
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!down_read_trylock(&fi->i_gc_rwsem[READ])) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ } else {
+ down_read(&fi->i_gc_rwsem[READ]);
+ }
+
+ /*
+ * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of
+ * the higher-level function iomap_dio_rw() in order to ensure that the
+ * F2FS_DIO_READ counter will be decremented correctly in all cases.
+ */
+ inc_page_count(sbi, F2FS_DIO_READ);
+ dio = __iomap_dio_rw(iocb, to, &f2fs_iomap_ops,
+ &f2fs_iomap_dio_read_ops, 0, 0);
+ if (IS_ERR_OR_NULL(dio)) {
+ ret = PTR_ERR_OR_ZERO(dio);
+ if (ret != -EIOCBQUEUED)
+ dec_page_count(sbi, F2FS_DIO_READ);
+ } else {
+ ret = iomap_dio_complete(dio);
+ }
+
+ up_read(&fi->i_gc_rwsem[READ]);
+
+ file_accessed(file);
+out:
+ trace_f2fs_direct_IO_exit(inode, pos, count, READ, ret);
+ return ret;
+}
+
+static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ ssize_t ret;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
- ret = generic_file_read_iter(iocb, iter);
+ if (f2fs_should_use_dio(inode, iocb, to))
+ return f2fs_dio_read_iter(iocb, to);
+ ret = filemap_read(iocb, to, 0);
if (ret > 0)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_READ_IO, ret);
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_READ_IO, ret);
+ return ret;
+}
+static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ ssize_t count;
+ int err;
+
+ if (IS_IMMUTABLE(inode))
+ return -EPERM;
+
+ if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
+ return -EPERM;
+
+ count = generic_write_checks(iocb, from);
+ if (count <= 0)
+ return count;
+
+ err = file_modified(file);
+ if (err)
+ return err;
+ return count;
+}
+
+/*
+ * Preallocate blocks for a write request, if it is possible and helpful to do
+ * so. Returns a positive number if blocks may have been preallocated, 0 if no
+ * blocks were preallocated, or a negative errno value if something went
+ * seriously wrong. Also sets FI_PREALLOCATED_ALL on the inode if *all* the
+ * requested blocks (not just some of them) have been allocated.
+ */
+static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter,
+ bool dio)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ const loff_t pos = iocb->ki_pos;
+ const size_t count = iov_iter_count(iter);
+ struct f2fs_map_blocks map = {};
+ int flag;
+ int ret;
+
+ /* If it will be an out-of-place direct write, don't bother. */
+ if (dio && f2fs_lfs_mode(sbi))
+ return 0;
+ /*
+ * Don't preallocate holes aligned to DIO_SKIP_HOLES which turns into
+ * buffered IO, if DIO meets any holes.
+ */
+ if (dio && i_size_read(inode) &&
+ (F2FS_BYTES_TO_BLK(pos) < F2FS_BLK_ALIGN(i_size_read(inode))))
+ return 0;
+
+ /* No-wait I/O can't allocate blocks. */
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return 0;
+
+ /* If it will be a short write, don't bother. */
+ if (fault_in_iov_iter_readable(iter, count))
+ return 0;
+
+ if (f2fs_has_inline_data(inode)) {
+ /* If the data will fit inline, don't bother. */
+ if (pos + count <= MAX_INLINE_DATA(inode))
+ return 0;
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+
+ /* Do not preallocate blocks that will be written partially in 4KB. */
+ map.m_lblk = F2FS_BLK_ALIGN(pos);
+ map.m_len = F2FS_BYTES_TO_BLK(pos + count);
+ if (map.m_len > map.m_lblk)
+ map.m_len -= map.m_lblk;
+ else
+ map.m_len = 0;
+ map.m_may_create = true;
+ if (dio) {
+ map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+ flag = F2FS_GET_BLOCK_PRE_DIO;
+ } else {
+ map.m_seg_type = NO_CHECK_TYPE;
+ flag = F2FS_GET_BLOCK_PRE_AIO;
+ }
+
+ ret = f2fs_map_blocks(inode, &map, 1, flag);
+ /* -ENOSPC|-EDQUOT are fine to report the number of allocated blocks. */
+ if (ret < 0 && !((ret == -ENOSPC || ret == -EDQUOT) && map.m_len > 0))
+ return ret;
+ if (ret == 0)
+ set_inode_flag(inode, FI_PREALLOCATED_ALL);
+ return map.m_len;
+}
+
+static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ ssize_t ret;
+
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EOPNOTSUPP;
+
+ current->backing_dev_info = inode_to_bdi(inode);
+ ret = generic_perform_write(file, from, iocb->ki_pos);
+ current->backing_dev_info = NULL;
+
+ if (ret > 0) {
+ iocb->ki_pos += ret;
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_IO, ret);
+ }
+ return ret;
+}
+
+static int f2fs_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error,
+ unsigned int flags)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp));
+
+ dec_page_count(sbi, F2FS_DIO_WRITE);
+ if (error)
+ return error;
+ f2fs_update_iostat(sbi, APP_DIRECT_IO, size);
+ return 0;
+}
+
+static const struct iomap_dio_ops f2fs_iomap_dio_write_ops = {
+ .end_io = f2fs_dio_write_end_io,
+};
+
+static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
+ bool *may_need_sync)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ const bool do_opu = f2fs_lfs_mode(sbi);
+ const int whint_mode = F2FS_OPTION(sbi).whint_mode;
+ const loff_t pos = iocb->ki_pos;
+ const ssize_t count = iov_iter_count(from);
+ const enum rw_hint hint = iocb->ki_hint;
+ unsigned int dio_flags;
+ struct iomap_dio *dio;
+ ssize_t ret;
+
+ trace_f2fs_direct_IO_enter(inode, iocb, count, WRITE);
+
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ /* f2fs_convert_inline_inode() and block allocation can block */
+ if (f2fs_has_inline_data(inode) ||
+ !f2fs_overwrite_io(inode, pos, count)) {
+ ret = -EAGAIN;
+ goto out;
+ }
+
+ if (!down_read_trylock(&fi->i_gc_rwsem[WRITE])) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) {
+ up_read(&fi->i_gc_rwsem[WRITE]);
+ ret = -EAGAIN;
+ goto out;
+ }
+ } else {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto out;
+
+ down_read(&fi->i_gc_rwsem[WRITE]);
+ if (do_opu)
+ down_read(&fi->i_gc_rwsem[READ]);
+ }
+ if (whint_mode == WHINT_MODE_OFF)
+ iocb->ki_hint = WRITE_LIFE_NOT_SET;
+
+ /*
+ * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of
+ * the higher-level function iomap_dio_rw() in order to ensure that the
+ * F2FS_DIO_WRITE counter will be decremented correctly in all cases.
+ */
+ inc_page_count(sbi, F2FS_DIO_WRITE);
+ dio_flags = 0;
+ if (pos + count > inode->i_size)
+ dio_flags |= IOMAP_DIO_FORCE_WAIT;
+ dio = __iomap_dio_rw(iocb, from, &f2fs_iomap_ops,
+ &f2fs_iomap_dio_write_ops, dio_flags, 0);
+ if (IS_ERR_OR_NULL(dio)) {
+ ret = PTR_ERR_OR_ZERO(dio);
+ if (ret == -ENOTBLK)
+ ret = 0;
+ if (ret != -EIOCBQUEUED)
+ dec_page_count(sbi, F2FS_DIO_WRITE);
+ } else {
+ ret = iomap_dio_complete(dio);
+ }
+
+ if (whint_mode == WHINT_MODE_OFF)
+ iocb->ki_hint = hint;
+ if (do_opu)
+ up_read(&fi->i_gc_rwsem[READ]);
+ up_read(&fi->i_gc_rwsem[WRITE]);
+
+ if (ret < 0)
+ goto out;
+ if (pos + ret > inode->i_size)
+ f2fs_i_size_write(inode, pos + ret);
+ if (!do_opu)
+ set_inode_flag(inode, FI_UPDATE_WRITE);
+
+ if (iov_iter_count(from)) {
+ ssize_t ret2;
+ loff_t bufio_start_pos = iocb->ki_pos;
+
+ /*
+ * The direct write was partial, so we need to fall back to a
+ * buffered write for the remainder.
+ */
+
+ ret2 = f2fs_buffered_write_iter(iocb, from);
+ if (iov_iter_count(from))
+ f2fs_write_failed(inode, iocb->ki_pos);
+ if (ret2 < 0)
+ goto out;
+
+ /*
+ * Ensure that the pagecache pages are written to disk and
+ * invalidated to preserve the expected O_DIRECT semantics.
+ */
+ if (ret2 > 0) {
+ loff_t bufio_end_pos = bufio_start_pos + ret2 - 1;
+
+ ret += ret2;
+
+ ret2 = filemap_write_and_wait_range(file->f_mapping,
+ bufio_start_pos,
+ bufio_end_pos);
+ if (ret2 < 0)
+ goto out;
+ invalidate_mapping_pages(file->f_mapping,
+ bufio_start_pos >> PAGE_SHIFT,
+ bufio_end_pos >> PAGE_SHIFT);
+ }
+ } else {
+ /* iomap_dio_rw() already handled the generic_write_sync(). */
+ *may_need_sync = false;
+ }
+out:
+ trace_f2fs_direct_IO_exit(inode, pos, count, WRITE, ret);
return ret;
}
static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file_inode(file);
+ struct inode *inode = file_inode(iocb->ki_filp);
+ const loff_t orig_pos = iocb->ki_pos;
+ const size_t orig_count = iov_iter_count(from);
+ loff_t target_size;
+ bool dio;
+ bool may_need_sync = true;
+ int preallocated;
ssize_t ret;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
@@ -4260,91 +4624,42 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
inode_lock(inode);
}
- if (unlikely(IS_IMMUTABLE(inode))) {
- ret = -EPERM;
- goto unlock;
+ ret = f2fs_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out_unlock;
+
+ /* Determine whether we will do a direct write or a buffered write. */
+ dio = f2fs_should_use_dio(inode, iocb, from);
+
+ /* Possibly preallocate the blocks for the write. */
+ target_size = iocb->ki_pos + iov_iter_count(from);
+ preallocated = f2fs_preallocate_blocks(iocb, from, dio);
+ if (preallocated < 0)
+ ret = preallocated;
+ else
+ /* Do the actual write. */
+ ret = dio ?
+ f2fs_dio_write_iter(iocb, from, &may_need_sync):
+ f2fs_buffered_write_iter(iocb, from);
+
+ /* Don't leave any preallocated blocks around past i_size. */
+ if (preallocated && i_size_read(inode) < target_size) {
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ filemap_invalidate_lock(inode->i_mapping);
+ if (!f2fs_truncate(inode))
+ file_dont_truncate(inode);
+ filemap_invalidate_unlock(inode->i_mapping);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ } else {
+ file_dont_truncate(inode);
}
- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
- ret = -EPERM;
- goto unlock;
- }
-
- ret = generic_write_checks(iocb, from);
- if (ret > 0) {
- bool preallocated = false;
- size_t target_size = 0;
- int err;
-
- if (fault_in_iov_iter_readable(from, iov_iter_count(from)))
- set_inode_flag(inode, FI_NO_PREALLOC);
-
- if ((iocb->ki_flags & IOCB_NOWAIT)) {
- if (!f2fs_overwrite_io(inode, iocb->ki_pos,
- iov_iter_count(from)) ||
- f2fs_has_inline_data(inode) ||
- f2fs_force_buffered_io(inode, iocb, from)) {
- clear_inode_flag(inode, FI_NO_PREALLOC);
- inode_unlock(inode);
- ret = -EAGAIN;
- goto out;
- }
- goto write;
- }
-
- if (is_inode_flag_set(inode, FI_NO_PREALLOC))
- goto write;
-
- if (iocb->ki_flags & IOCB_DIRECT) {
- /*
- * Convert inline data for Direct I/O before entering
- * f2fs_direct_IO().
- */
- err = f2fs_convert_inline_inode(inode);
- if (err)
- goto out_err;
- /*
- * If force_buffere_io() is true, we have to allocate
- * blocks all the time, since f2fs_direct_IO will fall
- * back to buffered IO.
- */
- if (!f2fs_force_buffered_io(inode, iocb, from) &&
- f2fs_lfs_mode(F2FS_I_SB(inode)))
- goto write;
- }
- preallocated = true;
- target_size = iocb->ki_pos + iov_iter_count(from);
-
- err = f2fs_preallocate_blocks(iocb, from);
- if (err) {
-out_err:
- clear_inode_flag(inode, FI_NO_PREALLOC);
- inode_unlock(inode);
- ret = err;
- goto out;
- }
-write:
- ret = __generic_file_write_iter(iocb, from);
- clear_inode_flag(inode, FI_NO_PREALLOC);
-
- /* if we couldn't write data, we should deallocate blocks. */
- if (preallocated && i_size_read(inode) < target_size) {
- down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- filemap_invalidate_lock(inode->i_mapping);
- f2fs_truncate(inode);
- filemap_invalidate_unlock(inode->i_mapping);
- up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- }
-
- if (ret > 0)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
- }
-unlock:
+ clear_inode_flag(inode, FI_PREALLOCATED_ALL);
+out_unlock:
inode_unlock(inode);
out:
- trace_f2fs_file_write_iter(inode, iocb->ki_pos,
- iov_iter_count(from), ret);
- if (ret > 0)
+ trace_f2fs_file_write_iter(inode, orig_pos, orig_count, ret);
+ if (ret > 0 && may_need_sync)
ret = generic_write_sync(iocb, ret);
return ret;
}
@@ -4352,12 +4667,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len,
int advice)
{
- struct inode *inode;
struct address_space *mapping;
struct backing_dev_info *bdi;
+ struct inode *inode = file_inode(filp);
+ int err;
if (advice == POSIX_FADV_SEQUENTIAL) {
- inode = file_inode(filp);
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
@@ -4374,7 +4689,13 @@ static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len,
return 0;
}
- return generic_fadvise(filp, offset, len, advice);
+ err = generic_fadvise(filp, offset, len, advice);
+ if (!err && advice == POSIX_FADV_DONTNEED &&
+ test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) &&
+ f2fs_compressed_file(inode))
+ f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino);
+
+ return err;
}
#ifdef CONFIG_COMPAT
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 374bbb5..ee308a8 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -92,6 +92,18 @@ static int gc_thread_func(void *data)
* So, I'd like to wait some time to collect dirty segments.
*/
if (sbi->gc_mode == GC_URGENT_HIGH) {
+ spin_lock(&sbi->gc_urgent_high_lock);
+ if (sbi->gc_urgent_high_limited) {
+ if (!sbi->gc_urgent_high_remaining) {
+ sbi->gc_urgent_high_limited = false;
+ spin_unlock(&sbi->gc_urgent_high_lock);
+ sbi->gc_mode = GC_NORMAL;
+ continue;
+ }
+ sbi->gc_urgent_high_remaining--;
+ }
+ spin_unlock(&sbi->gc_urgent_high_lock);
+
wait_ms = gc_th->urgent_sleep_time;
down_write(&sbi->gc_lock);
goto do_gc;
@@ -947,7 +959,7 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
continue;
}
- if (f2fs_get_node_info(sbi, nid, &ni)) {
+ if (f2fs_get_node_info(sbi, nid, &ni, false)) {
f2fs_put_page(node_page, 1);
continue;
}
@@ -1015,7 +1027,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (IS_ERR(node_page))
return false;
- if (f2fs_get_node_info(sbi, nid, dni)) {
+ if (f2fs_get_node_info(sbi, nid, dni, false)) {
f2fs_put_page(node_page, 1);
return false;
}
@@ -1026,6 +1038,9 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
set_sbi_flag(sbi, SBI_NEED_FSCK);
}
+ if (f2fs_check_nid_range(sbi, dni->ino))
+ return false;
+
*nofs = ofs_of_node(node_page);
source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node);
f2fs_put_page(node_page, 1);
@@ -1039,7 +1054,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (!test_and_set_bit(segno, SIT_I(sbi)->invalid_segmap)) {
f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u",
blkaddr, source_blkaddr, segno);
- f2fs_bug_on(sbi, 1);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
}
}
#endif
@@ -1206,7 +1221,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
- err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
if (err)
goto put_out;
@@ -1456,7 +1471,8 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (phase == 3) {
inode = f2fs_iget(sb, dni.ino);
- if (IS_ERR(inode) || is_bad_inode(inode))
+ if (IS_ERR(inode) || is_bad_inode(inode) ||
+ special_file(inode->i_mode))
continue;
if (!down_write_trylock(
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ea08f0d..4b5cefa 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -131,7 +131,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
if (err)
return err;
- err = f2fs_get_node_info(fio.sbi, dn->nid, &ni);
+ err = f2fs_get_node_info(fio.sbi, dn->nid, &ni, false);
if (err) {
f2fs_truncate_data_blocks_range(dn, 1);
f2fs_put_dnode(dn);
@@ -786,7 +786,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
ilen = start + len;
ilen -= start;
- err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+ err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni, false);
if (err)
goto out;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 4c11254..0ec8e32 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -516,6 +516,11 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
} else if (ino == F2FS_COMPRESS_INO(sbi)) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
inode->i_mapping->a_ops = &f2fs_compress_aops;
+ /*
+ * generic_error_remove_page only truncates pages of regular
+ * inode
+ */
+ inode->i_mode |= S_IFREG;
#endif
mapping_set_gfp_mask(inode->i_mapping,
GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
@@ -544,6 +549,14 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
goto bad_inode;
}
f2fs_set_inode_flags(inode);
+
+ if (file_should_truncate(inode)) {
+ ret = f2fs_truncate(inode);
+ if (ret)
+ goto bad_inode;
+ file_dont_truncate(inode);
+ }
+
unlock_new_inode(inode);
trace_f2fs_iget(inode);
return inode;
@@ -738,7 +751,8 @@ void f2fs_evict_inode(struct inode *inode)
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
- if (test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
+ if ((inode->i_nlink || is_bad_inode(inode)) &&
+ test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
f2fs_invalidate_compress_pages(sbi, inode->i_ino);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
@@ -868,7 +882,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
- err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+ err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "May loss orphan inode, run fsck to fix.");
diff --git a/fs/f2fs/iostat.c b/fs/f2fs/iostat.c
index cdcf54a..be599f3 100644
--- a/fs/f2fs/iostat.c
+++ b/fs/f2fs/iostat.c
@@ -92,7 +92,7 @@ static inline void __record_iostat_latency(struct f2fs_sb_info *sbi)
struct f2fs_iostat_latency iostat_lat[MAX_IO_TYPE][NR_PAGE_TYPE];
struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
- spin_lock_irq(&sbi->iostat_lat_lock);
+ spin_lock_bh(&sbi->iostat_lat_lock);
for (idx = 0; idx < MAX_IO_TYPE; idx++) {
for (io = 0; io < NR_PAGE_TYPE; io++) {
cnt = io_lat->bio_cnt[idx][io];
@@ -106,7 +106,7 @@ static inline void __record_iostat_latency(struct f2fs_sb_info *sbi)
io_lat->bio_cnt[idx][io] = 0;
}
}
- spin_unlock_irq(&sbi->iostat_lat_lock);
+ spin_unlock_bh(&sbi->iostat_lat_lock);
trace_f2fs_iostat_latency(sbi, iostat_lat);
}
@@ -120,9 +120,9 @@ static inline void f2fs_record_iostat(struct f2fs_sb_info *sbi)
return;
/* Need double check under the lock */
- spin_lock(&sbi->iostat_lock);
+ spin_lock_bh(&sbi->iostat_lock);
if (time_is_after_jiffies(sbi->iostat_next_period)) {
- spin_unlock(&sbi->iostat_lock);
+ spin_unlock_bh(&sbi->iostat_lock);
return;
}
sbi->iostat_next_period = jiffies +
@@ -133,7 +133,7 @@ static inline void f2fs_record_iostat(struct f2fs_sb_info *sbi)
sbi->prev_rw_iostat[i];
sbi->prev_rw_iostat[i] = sbi->rw_iostat[i];
}
- spin_unlock(&sbi->iostat_lock);
+ spin_unlock_bh(&sbi->iostat_lock);
trace_f2fs_iostat(sbi, iostat_diff);
@@ -145,16 +145,16 @@ void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
int i;
- spin_lock(&sbi->iostat_lock);
+ spin_lock_bh(&sbi->iostat_lock);
for (i = 0; i < NR_IO_TYPE; i++) {
sbi->rw_iostat[i] = 0;
sbi->prev_rw_iostat[i] = 0;
}
- spin_unlock(&sbi->iostat_lock);
+ spin_unlock_bh(&sbi->iostat_lock);
- spin_lock_irq(&sbi->iostat_lat_lock);
+ spin_lock_bh(&sbi->iostat_lat_lock);
memset(io_lat, 0, sizeof(struct iostat_lat_info));
- spin_unlock_irq(&sbi->iostat_lat_lock);
+ spin_unlock_bh(&sbi->iostat_lat_lock);
}
void f2fs_update_iostat(struct f2fs_sb_info *sbi,
@@ -163,19 +163,16 @@ void f2fs_update_iostat(struct f2fs_sb_info *sbi,
if (!sbi->iostat_enable)
return;
- spin_lock(&sbi->iostat_lock);
+ spin_lock_bh(&sbi->iostat_lock);
sbi->rw_iostat[type] += io_bytes;
- if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
- sbi->rw_iostat[APP_BUFFERED_IO] =
- sbi->rw_iostat[APP_WRITE_IO] -
- sbi->rw_iostat[APP_DIRECT_IO];
+ if (type == APP_BUFFERED_IO || type == APP_DIRECT_IO)
+ sbi->rw_iostat[APP_WRITE_IO] += io_bytes;
- if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
- sbi->rw_iostat[APP_BUFFERED_READ_IO] =
- sbi->rw_iostat[APP_READ_IO] -
- sbi->rw_iostat[APP_DIRECT_READ_IO];
- spin_unlock(&sbi->iostat_lock);
+ if (type == APP_BUFFERED_READ_IO || type == APP_DIRECT_READ_IO)
+ sbi->rw_iostat[APP_READ_IO] += io_bytes;
+
+ spin_unlock_bh(&sbi->iostat_lock);
f2fs_record_iostat(sbi);
}
@@ -185,7 +182,6 @@ static inline void __update_iostat_latency(struct bio_iostat_ctx *iostat_ctx,
{
unsigned long ts_diff;
unsigned int iotype = iostat_ctx->type;
- unsigned long flags;
struct f2fs_sb_info *sbi = iostat_ctx->sbi;
struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
int idx;
@@ -206,12 +202,12 @@ static inline void __update_iostat_latency(struct bio_iostat_ctx *iostat_ctx,
idx = WRITE_ASYNC_IO;
}
- spin_lock_irqsave(&sbi->iostat_lat_lock, flags);
+ spin_lock_bh(&sbi->iostat_lat_lock);
io_lat->sum_lat[idx][iotype] += ts_diff;
io_lat->bio_cnt[idx][iotype]++;
if (ts_diff > io_lat->peak_lat[idx][iotype])
io_lat->peak_lat[idx][iotype] = ts_diff;
- spin_unlock_irqrestore(&sbi->iostat_lat_lock, flags);
+ spin_unlock_bh(&sbi->iostat_lat_lock);
}
void iostat_update_and_unbind_ctx(struct bio *bio, int rw)
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 219506c..50b2874 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -430,6 +430,10 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *new, *e;
+ /* Let's mitigate lock contention of nat_tree_lock during checkpoint */
+ if (rwsem_is_locked(&sbi->cp_global_sem))
+ return;
+
new = __alloc_nat_entry(sbi, nid, false);
if (!new)
return;
@@ -539,7 +543,7 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
}
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
- struct node_info *ni)
+ struct node_info *ni, bool checkpoint_context)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -572,9 +576,10 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
* nat_tree_lock. Therefore, we should retry, if we failed to grab here
* while not bothering checkpoint.
*/
- if (!rwsem_is_locked(&sbi->cp_global_sem)) {
+ if (!rwsem_is_locked(&sbi->cp_global_sem) || checkpoint_context) {
down_read(&curseg->journal_rwsem);
- } else if (!down_read_trylock(&curseg->journal_rwsem)) {
+ } else if (rwsem_is_contended(&nm_i->nat_tree_lock) ||
+ !down_read_trylock(&curseg->journal_rwsem)) {
up_read(&nm_i->nat_tree_lock);
goto retry;
}
@@ -887,7 +892,7 @@ static int truncate_node(struct dnode_of_data *dn)
int err;
pgoff_t index;
- err = f2fs_get_node_info(sbi, dn->nid, &ni);
+ err = f2fs_get_node_info(sbi, dn->nid, &ni, false);
if (err)
return err;
@@ -1286,7 +1291,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
goto fail;
#ifdef CONFIG_F2FS_CHECK_FS
- err = f2fs_get_node_info(sbi, dn->nid, &new_ni);
+ err = f2fs_get_node_info(sbi, dn->nid, &new_ni, false);
if (err) {
dec_valid_node_count(sbi, dn->inode, !ofs);
goto fail;
@@ -1348,7 +1353,7 @@ static int read_node_page(struct page *page, int op_flags)
return LOCKED_PAGE;
}
- err = f2fs_get_node_info(sbi, page->index, &ni);
+ err = f2fs_get_node_info(sbi, page->index, &ni, false);
if (err)
return err;
@@ -1600,7 +1605,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
nid = nid_of_node(page);
f2fs_bug_on(sbi, page->index != nid);
- if (f2fs_get_node_info(sbi, nid, &ni))
+ if (f2fs_get_node_info(sbi, nid, &ni, !do_balance))
goto redirty_out;
if (wbc->for_reclaim) {
@@ -2701,7 +2706,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
goto recover_xnid;
/* 1: invalidate the previous xattr nid */
- err = f2fs_get_node_info(sbi, prev_xnid, &ni);
+ err = f2fs_get_node_info(sbi, prev_xnid, &ni, false);
if (err)
return err;
@@ -2741,7 +2746,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
struct page *ipage;
int err;
- err = f2fs_get_node_info(sbi, ino, &old_ni);
+ err = f2fs_get_node_info(sbi, ino, &old_ni, false);
if (err)
return err;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index d1664a0..9683c80 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -596,7 +596,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
- err = f2fs_get_node_info(sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
if (err)
goto err;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 40fdb4a..575d3dc 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -253,7 +253,7 @@ static int __revoke_inmem_pages(struct inode *inode,
goto next;
}
- err = f2fs_get_node_info(sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
if (err) {
f2fs_put_dnode(&dn);
return err;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 46fde9f..0291cd5 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -538,7 +538,8 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
{
- return SM_I(sbi)->reserved_segments;
+ return SM_I(sbi)->reserved_segments +
+ SM_I(sbi)->additional_reserved_segments;
}
static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 15f12ec..76e6a3d 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -59,6 +59,7 @@ const char *f2fs_fault_name[FAULT_MAX] = {
[FAULT_WRITE_IO] = "write IO error",
[FAULT_SLAB_ALLOC] = "slab alloc",
[FAULT_DQUOT_INIT] = "dquot initialize",
+ [FAULT_LOCK_OP] = "lock_op",
};
void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
@@ -321,6 +322,46 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).s_resgid));
}
+static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
+{
+ unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
+ unsigned int avg_vblocks;
+ unsigned int wanted_reserved_segments;
+ block_t avail_user_block_count;
+
+ if (!F2FS_IO_ALIGNED(sbi))
+ return 0;
+
+ /* average valid block count in section in worst case */
+ avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
+
+ /*
+ * we need enough free space when migrating one section in worst case
+ */
+ wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
+ reserved_segments(sbi);
+ wanted_reserved_segments -= reserved_segments(sbi);
+
+ avail_user_block_count = sbi->user_block_count -
+ sbi->current_reserved_blocks -
+ F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (wanted_reserved_segments * sbi->blocks_per_seg >
+ avail_user_block_count) {
+ f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
+ wanted_reserved_segments,
+ avail_user_block_count >> sbi->log_blocks_per_seg);
+ return -ENOSPC;
+ }
+
+ SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
+
+ f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
+ wanted_reserved_segments);
+
+ return 0;
+}
+
static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
{
if (!F2FS_OPTION(sbi).unusable_cap_perc)
@@ -3540,6 +3581,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->seq_file_ra_mul = MIN_RA_MUL;
sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
+ spin_lock_init(&sbi->gc_urgent_high_lock);
sbi->dir_level = DEF_DIR_LEVEL;
sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
@@ -4179,6 +4221,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
goto free_nm;
}
+ err = adjust_reserved_segment(sbi);
+ if (err)
+ goto free_nm;
+
/* For write statistics */
sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 8408f77..df406c1 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -118,6 +118,15 @@ static ssize_t sb_status_show(struct f2fs_attr *a,
return sprintf(buf, "%lx\n", sbi->s_flag);
}
+static ssize_t pending_discard_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ if (!SM_I(sbi)->dcc_info)
+ return -EINVAL;
+ return sprintf(buf, "%llu\n", (unsigned long long)atomic_read(
+ &SM_I(sbi)->dcc_info->discard_cmd_cnt));
+}
+
static ssize_t features_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -414,7 +423,9 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
if (a->struct_type == RESERVED_BLOCKS) {
spin_lock(&sbi->stat_lock);
if (t > (unsigned long)(sbi->user_block_count -
- F2FS_OPTION(sbi).root_reserved_blocks)) {
+ F2FS_OPTION(sbi).root_reserved_blocks -
+ sbi->blocks_per_seg *
+ SM_I(sbi)->additional_reserved_segments)) {
spin_unlock(&sbi->stat_lock);
return -EINVAL;
}
@@ -477,6 +488,15 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
return count;
}
+ if (!strcmp(a->attr.name, "gc_urgent_high_remaining")) {
+ spin_lock(&sbi->gc_urgent_high_lock);
+ sbi->gc_urgent_high_limited = t != 0;
+ sbi->gc_urgent_high_remaining = t;
+ spin_unlock(&sbi->gc_urgent_high_lock);
+
+ return count;
+ }
+
#ifdef CONFIG_F2FS_IOSTAT
if (!strcmp(a->attr.name, "iostat_enable")) {
sbi->iostat_enable = !!t;
@@ -732,6 +752,7 @@ F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
#endif
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, data_io_flag, data_io_flag);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent_high_remaining, gc_urgent_high_remaining);
F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, ckpt_thread_ioprio, ckpt_thread_ioprio);
F2FS_GENERAL_RO_ATTR(dirty_segments);
F2FS_GENERAL_RO_ATTR(free_segments);
@@ -743,6 +764,7 @@ F2FS_GENERAL_RO_ATTR(unusable);
F2FS_GENERAL_RO_ATTR(encoding);
F2FS_GENERAL_RO_ATTR(mounted_time_sec);
F2FS_GENERAL_RO_ATTR(main_blkaddr);
+F2FS_GENERAL_RO_ATTR(pending_discard);
#ifdef CONFIG_F2FS_STAT_FS
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
@@ -811,6 +833,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(main_blkaddr),
ATTR_LIST(max_small_discards),
ATTR_LIST(discard_granularity),
+ ATTR_LIST(pending_discard),
ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
@@ -843,6 +866,7 @@ static struct attribute *f2fs_attrs[] = {
#endif
ATTR_LIST(data_io_flag),
ATTR_LIST(node_io_flag),
+ ATTR_LIST(gc_urgent_high_remaining),
ATTR_LIST(ckpt_thread_ioprio),
ATTR_LIST(dirty_segments),
ATTR_LIST(free_segments),
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index e348f33..8e5cd9c 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -226,15 +226,18 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int index)
}
static struct f2fs_xattr_entry *__find_xattr(void *base_addr,
- void *last_base_addr, int index,
- size_t len, const char *name)
+ void *last_base_addr, void **last_addr,
+ int index, size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
list_for_each_xattr(entry, base_addr) {
if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
- (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr)
+ (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+ if (last_addr)
+ *last_addr = entry;
return NULL;
+ }
if (entry->e_name_index != index)
continue;
@@ -254,19 +257,9 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
unsigned int inline_size = inline_xattr_size(inode);
void *max_addr = base_addr + inline_size;
- list_for_each_xattr(entry, base_addr) {
- if ((void *)entry + sizeof(__u32) > max_addr ||
- (void *)XATTR_NEXT_ENTRY(entry) > max_addr) {
- *last_addr = entry;
- return NULL;
- }
- if (entry->e_name_index != index)
- continue;
- if (entry->e_name_len != len)
- continue;
- if (!memcmp(entry->e_name, name, len))
- break;
- }
+ entry = __find_xattr(base_addr, max_addr, last_addr, index, len, name);
+ if (!entry)
+ return NULL;
/* inline xattr header or entry across max inline xattr size */
if (IS_XATTR_LAST_ENTRY(entry) &&
@@ -368,7 +361,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
else
cur_addr = txattr_addr;
- *xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name);
+ *xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name);
if (!*xe) {
f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
inode->i_ino);
@@ -659,7 +652,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
/* find entry with wanted name. */
- here = __find_xattr(base_addr, last_base_addr, index, len, name);
+ here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name);
if (!here) {
f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
inode->i_ino);
@@ -684,8 +677,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
}
last = here;
- while (!IS_XATTR_LAST_ENTRY(last))
+ while (!IS_XATTR_LAST_ENTRY(last)) {
+ if ((void *)(last) + sizeof(__u32) > last_base_addr ||
+ (void *)XATTR_NEXT_ENTRY(last) > last_base_addr) {
+ f2fs_err(F2FS_I_SB(inode), "inode (%lu) has invalid last xattr entry, entry_size: %zu",
+ inode->i_ino, ENTRY_SIZE(last));
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+ error = -EFSCORRUPTED;
+ goto exit;
+ }
last = XATTR_NEXT_ENTRY(last);
+ }
newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 13855ba..a5a309f 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -175,9 +175,10 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
static int fat_file_release(struct inode *inode, struct file *filp)
{
if ((filp->f_mode & FMODE_WRITE) &&
- MSDOS_SB(inode->i_sb)->options.flush) {
+ MSDOS_SB(inode->i_sb)->options.flush) {
fat_flush_inodes(inode->i_sb, inode, NULL);
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ io_schedule_timeout(HZ/10);
}
return 0;
}
diff --git a/fs/fs_context.c b/fs/fs_context.c
index b7e43a7..24ce12f 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -548,7 +548,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param)
param->key);
}
- if (len > PAGE_SIZE - 2 - size)
+ if (size + len + 2 > PAGE_SIZE)
return invalf(fc, "VFS: Legacy: Cumulative options too large");
if (strchr(param->key, ',') ||
(param->type == fs_value_is_string &&
diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c
index a57c6cb..f2aa7db 100644
--- a/fs/fscache/volume.c
+++ b/fs/fscache/volume.c
@@ -142,12 +142,12 @@ static void fscache_wait_on_volume_collision(struct fscache_volume *candidate,
unsigned int collidee_debug_id)
{
wait_var_event_timeout(&candidate->flags,
- fscache_is_acquire_pending(candidate), 20 * HZ);
+ !fscache_is_acquire_pending(candidate), 20 * HZ);
if (!fscache_is_acquire_pending(candidate)) {
pr_notice("Potential volume collision new=%08x old=%08x",
candidate->debug_id, collidee_debug_id);
fscache_stat(&fscache_n_volumes_collision);
- wait_var_event(&candidate->flags, fscache_is_acquire_pending(candidate));
+ wait_var_event(&candidate->flags, !fscache_is_acquire_pending(candidate));
}
}
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 74e6271..9d73790 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -891,7 +891,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
return 0;
out_vqs:
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtio_fs_cleanup_vqs(vdev, fs);
kfree(fs->vqs);
@@ -923,7 +923,7 @@ static void virtio_fs_remove(struct virtio_device *vdev)
list_del_init(&fs->list);
virtio_fs_stop_all_queues(fs);
virtio_fs_drain_all_queues_locked(fs);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
virtio_fs_cleanup_vqs(vdev, fs);
vdev->priv = NULL;
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 456e87a..68b4240 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -260,8 +260,10 @@ struct hfsplus_cat_folder {
__be32 access_date;
__be32 backup_date;
struct hfsplus_perm permissions;
- struct DInfo user_info;
- struct DXInfo finder_info;
+ struct_group_attr(info, __packed,
+ struct DInfo user_info;
+ struct DXInfo finder_info;
+ );
__be32 text_encoding;
__be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */
} __packed;
@@ -294,8 +296,10 @@ struct hfsplus_cat_file {
__be32 access_date;
__be32 backup_date;
struct hfsplus_perm permissions;
- struct FInfo user_info;
- struct FXInfo finder_info;
+ struct_group_attr(info, __packed,
+ struct FInfo user_info;
+ struct FXInfo finder_info;
+ );
__be32 text_encoding;
u32 reserved2;
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index e2855ce..49891b1 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -296,7 +296,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name,
sizeof(hfsplus_cat_entry));
if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) {
if (size == folder_finderinfo_len) {
- memcpy(&entry.folder.user_info, value,
+ memcpy(&entry.folder.info, value,
folder_finderinfo_len);
hfs_bnode_write(cat_fd.bnode, &entry,
cat_fd.entryoffset,
@@ -309,7 +309,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name,
}
} else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) {
if (size == file_finderinfo_len) {
- memcpy(&entry.file.user_info, value,
+ memcpy(&entry.file.info, value,
file_finderinfo_len);
hfs_bnode_write(cat_fd.bnode, &entry,
cat_fd.entryoffset,
diff --git a/fs/io-wq.c b/fs/io-wq.c
index a776312..bb7f161 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -48,7 +48,8 @@ struct io_worker {
struct io_wqe *wqe;
struct io_wq_work *cur_work;
- spinlock_t lock;
+ struct io_wq_work *next_work;
+ raw_spinlock_t lock;
struct completion ref_done;
@@ -405,8 +406,7 @@ static void io_wqe_dec_running(struct io_worker *worker)
* Worker will start processing some work. Move it to the busy list, if
* it's currently on the freelist
*/
-static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker,
- struct io_wq_work *work)
+static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker)
__must_hold(wqe->lock)
{
if (worker->flags & IO_WORKER_F_FREE) {
@@ -529,9 +529,10 @@ static void io_assign_current_work(struct io_worker *worker,
cond_resched();
}
- spin_lock(&worker->lock);
+ raw_spin_lock(&worker->lock);
worker->cur_work = work;
- spin_unlock(&worker->lock);
+ worker->next_work = NULL;
+ raw_spin_unlock(&worker->lock);
}
static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
@@ -546,7 +547,7 @@ static void io_worker_handle_work(struct io_worker *worker)
do {
struct io_wq_work *work;
-get_next:
+
/*
* If we got some work, mark us as busy. If we didn't, but
* the list isn't empty, it means we stalled on hashed work.
@@ -555,9 +556,20 @@ static void io_worker_handle_work(struct io_worker *worker)
* clear the stalled flag.
*/
work = io_get_next_work(acct, worker);
- if (work)
- __io_worker_busy(wqe, worker, work);
+ if (work) {
+ __io_worker_busy(wqe, worker);
+ /*
+ * Make sure cancelation can find this, even before
+ * it becomes the active work. That avoids a window
+ * where the work has been removed from our general
+ * work list, but isn't yet discoverable as the
+ * current work item for this worker.
+ */
+ raw_spin_lock(&worker->lock);
+ worker->next_work = work;
+ raw_spin_unlock(&worker->lock);
+ }
raw_spin_unlock(&wqe->lock);
if (!work)
break;
@@ -594,11 +606,6 @@ static void io_worker_handle_work(struct io_worker *worker)
spin_unlock_irq(&wq->hash->wait.lock);
if (wq_has_sleeper(&wq->hash->wait))
wake_up(&wq->hash->wait);
- raw_spin_lock(&wqe->lock);
- /* skip unnecessary unlock-lock wqe->lock */
- if (!work)
- goto get_next;
- raw_spin_unlock(&wqe->lock);
}
} while (work);
@@ -815,7 +822,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
refcount_set(&worker->ref, 1);
worker->wqe = wqe;
- spin_lock_init(&worker->lock);
+ raw_spin_lock_init(&worker->lock);
init_completion(&worker->ref_done);
if (index == IO_WQ_ACCT_BOUND)
@@ -973,6 +980,19 @@ void io_wq_hash_work(struct io_wq_work *work, void *val)
work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
}
+static bool __io_wq_worker_cancel(struct io_worker *worker,
+ struct io_cb_cancel_data *match,
+ struct io_wq_work *work)
+{
+ if (work && match->fn(work, match->data)) {
+ work->flags |= IO_WQ_WORK_CANCEL;
+ set_notify_signal(worker->task);
+ return true;
+ }
+
+ return false;
+}
+
static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
{
struct io_cb_cancel_data *match = data;
@@ -981,13 +1001,11 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
* Hold the lock to avoid ->cur_work going out of scope, caller
* may dereference the passed in work.
*/
- spin_lock(&worker->lock);
- if (worker->cur_work &&
- match->fn(worker->cur_work, match->data)) {
- set_notify_signal(worker->task);
+ raw_spin_lock(&worker->lock);
+ if (__io_wq_worker_cancel(worker, match, worker->cur_work) ||
+ __io_wq_worker_cancel(worker, match, worker->next_work))
match->nr_running++;
- }
- spin_unlock(&worker->lock);
+ raw_spin_unlock(&worker->lock);
return match->nr_running && !match->cancel_all;
}
@@ -1039,17 +1057,16 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
{
int i;
retry:
- raw_spin_lock(&wqe->lock);
for (i = 0; i < IO_WQ_ACCT_NR; i++) {
struct io_wqe_acct *acct = io_get_acct(wqe, i == 0);
if (io_acct_cancel_pending_work(wqe, acct, match)) {
+ raw_spin_lock(&wqe->lock);
if (match->cancel_all)
goto retry;
- return;
+ break;
}
}
- raw_spin_unlock(&wqe->lock);
}
static void io_wqe_cancel_running_work(struct io_wqe *wqe,
@@ -1074,25 +1091,27 @@ enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
* First check pending list, if we're lucky we can just remove it
* from there. CANCEL_OK means that the work is returned as-new,
* no completion will be posted for it.
- */
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
-
- io_wqe_cancel_pending_work(wqe, &match);
- if (match.nr_pending && !match.cancel_all)
- return IO_WQ_CANCEL_OK;
- }
-
- /*
- * Now check if a free (going busy) or busy worker has the work
+ *
+ * Then check if a free (going busy) or busy worker has the work
* currently running. If we find it there, we'll return CANCEL_RUNNING
* as an indication that we attempt to signal cancellation. The
* completion will run normally in this case.
+ *
+ * Do both of these while holding the wqe->lock, to ensure that
+ * we'll find a work item regardless of state.
*/
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
+ raw_spin_lock(&wqe->lock);
+ io_wqe_cancel_pending_work(wqe, &match);
+ if (match.nr_pending && !match.cancel_all) {
+ raw_spin_unlock(&wqe->lock);
+ return IO_WQ_CANCEL_OK;
+ }
+
io_wqe_cancel_running_work(wqe, &match);
+ raw_spin_unlock(&wqe->lock);
if (match.nr_running && !match.cancel_all)
return IO_WQ_CANCEL_RUNNING;
}
@@ -1263,7 +1282,9 @@ static void io_wq_destroy(struct io_wq *wq)
.fn = io_wq_work_match_all,
.cancel_all = true,
};
+ raw_spin_lock(&wqe->lock);
io_wqe_cancel_pending_work(wqe, &match);
+ raw_spin_unlock(&wqe->lock);
free_cpumask_var(wqe->cpu_mask);
kfree(wqe);
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index de9c9de..e54c412 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1192,12 +1192,6 @@ static inline bool req_ref_put_and_test(struct io_kiocb *req)
return atomic_dec_and_test(&req->refs);
}
-static inline void req_ref_put(struct io_kiocb *req)
-{
- WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
- WARN_ON_ONCE(req_ref_put_and_test(req));
-}
-
static inline void req_ref_get(struct io_kiocb *req)
{
WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
@@ -5468,12 +5462,14 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
{
- struct wait_queue_head *head = poll->head;
+ struct wait_queue_head *head = smp_load_acquire(&poll->head);
- spin_lock_irq(&head->lock);
- list_del_init(&poll->wait.entry);
- poll->head = NULL;
- spin_unlock_irq(&head->lock);
+ if (head) {
+ spin_lock_irq(&head->lock);
+ list_del_init(&poll->wait.entry);
+ poll->head = NULL;
+ spin_unlock_irq(&head->lock);
+ }
}
static void io_poll_remove_entries(struct io_kiocb *req)
@@ -5481,10 +5477,26 @@ static void io_poll_remove_entries(struct io_kiocb *req)
struct io_poll_iocb *poll = io_poll_get_single(req);
struct io_poll_iocb *poll_double = io_poll_get_double(req);
- if (poll->head)
- io_poll_remove_entry(poll);
- if (poll_double && poll_double->head)
+ /*
+ * While we hold the waitqueue lock and the waitqueue is nonempty,
+ * wake_up_pollfree() will wait for us. However, taking the waitqueue
+ * lock in the first place can race with the waitqueue being freed.
+ *
+ * We solve this as eventpoll does: by taking advantage of the fact that
+ * all users of wake_up_pollfree() will RCU-delay the actual free. If
+ * we enter rcu_read_lock() and see that the pointer to the queue is
+ * non-NULL, we can then lock it without the memory being freed out from
+ * under us.
+ *
+ * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+ * case the caller deletes the entry from the queue, leaving it empty.
+ * In that case, only RCU prevents the queue memory from being freed.
+ */
+ rcu_read_lock();
+ io_poll_remove_entry(poll);
+ if (poll_double)
io_poll_remove_entry(poll_double);
+ rcu_read_unlock();
}
/*
@@ -5624,6 +5636,30 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
wait);
__poll_t mask = key_to_poll(key);
+ if (unlikely(mask & POLLFREE)) {
+ io_poll_mark_cancelled(req);
+ /* we have to kick tw in case it's not already */
+ io_poll_execute(req, 0);
+
+ /*
+ * If the waitqueue is being freed early but someone is already
+ * holds ownership over it, we have to tear down the request as
+ * best we can. That means immediately removing the request from
+ * its waitqueue and preventing all further accesses to the
+ * waitqueue via the request.
+ */
+ list_del_init(&poll->wait.entry);
+
+ /*
+ * Careful: this *must* be the last step, since as soon
+ * as req->head is NULL'ed out, the request can be
+ * completed and freed, since aio_poll_complete_work()
+ * will no longer need to take the waitqueue lock.
+ */
+ smp_store_release(&poll->head, NULL);
+ return 1;
+ }
+
/* for instances that support it check for an event match first */
if (mask && !(mask & poll->events))
return 0;
@@ -6350,16 +6386,21 @@ static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr)
WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current);
ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
- if (ret != -ENOENT)
- return ret;
+ /*
+ * Fall-through even for -EALREADY, as we may have poll armed
+ * that need unarming.
+ */
+ if (!ret)
+ return 0;
spin_lock(&ctx->completion_lock);
+ ret = io_poll_cancel(ctx, sqe_addr, false);
+ if (ret != -ENOENT)
+ goto out;
+
spin_lock_irq(&ctx->timeout_lock);
ret = io_timeout_cancel(ctx, sqe_addr);
spin_unlock_irq(&ctx->timeout_lock);
- if (ret != -ENOENT)
- goto out;
- ret = io_poll_cancel(ctx, sqe_addr, false);
out:
spin_unlock(&ctx->completion_lock);
return ret;
diff --git a/fs/ksmbd/asn1.c b/fs/ksmbd/asn1.c
index b014f46..c03eba0 100644
--- a/fs/ksmbd/asn1.c
+++ b/fs/ksmbd/asn1.c
@@ -21,101 +21,11 @@
#include "ksmbd_spnego_negtokeninit.asn1.h"
#include "ksmbd_spnego_negtokentarg.asn1.h"
-#define SPNEGO_OID_LEN 7
#define NTLMSSP_OID_LEN 10
-#define KRB5_OID_LEN 7
-#define KRB5U2U_OID_LEN 8
-#define MSKRB5_OID_LEN 7
-static unsigned long SPNEGO_OID[7] = { 1, 3, 6, 1, 5, 5, 2 };
-static unsigned long NTLMSSP_OID[10] = { 1, 3, 6, 1, 4, 1, 311, 2, 2, 10 };
-static unsigned long KRB5_OID[7] = { 1, 2, 840, 113554, 1, 2, 2 };
-static unsigned long KRB5U2U_OID[8] = { 1, 2, 840, 113554, 1, 2, 2, 3 };
-static unsigned long MSKRB5_OID[7] = { 1, 2, 840, 48018, 1, 2, 2 };
static char NTLMSSP_OID_STR[NTLMSSP_OID_LEN] = { 0x2b, 0x06, 0x01, 0x04, 0x01,
0x82, 0x37, 0x02, 0x02, 0x0a };
-static bool
-asn1_subid_decode(const unsigned char **begin, const unsigned char *end,
- unsigned long *subid)
-{
- const unsigned char *ptr = *begin;
- unsigned char ch;
-
- *subid = 0;
-
- do {
- if (ptr >= end)
- return false;
-
- ch = *ptr++;
- *subid <<= 7;
- *subid |= ch & 0x7F;
- } while ((ch & 0x80) == 0x80);
-
- *begin = ptr;
- return true;
-}
-
-static bool asn1_oid_decode(const unsigned char *value, size_t vlen,
- unsigned long **oid, size_t *oidlen)
-{
- const unsigned char *iptr = value, *end = value + vlen;
- unsigned long *optr;
- unsigned long subid;
-
- vlen += 1;
- if (vlen < 2 || vlen > UINT_MAX / sizeof(unsigned long))
- goto fail_nullify;
-
- *oid = kmalloc(vlen * sizeof(unsigned long), GFP_KERNEL);
- if (!*oid)
- return false;
-
- optr = *oid;
-
- if (!asn1_subid_decode(&iptr, end, &subid))
- goto fail;
-
- if (subid < 40) {
- optr[0] = 0;
- optr[1] = subid;
- } else if (subid < 80) {
- optr[0] = 1;
- optr[1] = subid - 40;
- } else {
- optr[0] = 2;
- optr[1] = subid - 80;
- }
-
- *oidlen = 2;
- optr += 2;
-
- while (iptr < end) {
- if (++(*oidlen) > vlen)
- goto fail;
-
- if (!asn1_subid_decode(&iptr, end, optr++))
- goto fail;
- }
- return true;
-
-fail:
- kfree(*oid);
-fail_nullify:
- *oid = NULL;
- return false;
-}
-
-static bool oid_eq(unsigned long *oid1, unsigned int oid1len,
- unsigned long *oid2, unsigned int oid2len)
-{
- if (oid1len != oid2len)
- return false;
-
- return memcmp(oid1, oid2, oid1len) == 0;
-}
-
int
ksmbd_decode_negTokenInit(unsigned char *security_blob, int length,
struct ksmbd_conn *conn)
@@ -252,26 +162,18 @@ int build_spnego_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
int ksmbd_gssapi_this_mech(void *context, size_t hdrlen, unsigned char tag,
const void *value, size_t vlen)
{
- unsigned long *oid;
- size_t oidlen;
- int err = 0;
+ enum OID oid;
- if (!asn1_oid_decode(value, vlen, &oid, &oidlen)) {
- err = -EBADMSG;
- goto out;
- }
-
- if (!oid_eq(oid, oidlen, SPNEGO_OID, SPNEGO_OID_LEN))
- err = -EBADMSG;
- kfree(oid);
-out:
- if (err) {
+ oid = look_up_OID(value, vlen);
+ if (oid != OID_spnego) {
char buf[50];
sprint_oid(value, vlen, buf, sizeof(buf));
ksmbd_debug(AUTH, "Unexpected OID: %s\n", buf);
+ return -EBADMSG;
}
- return err;
+
+ return 0;
}
int ksmbd_neg_token_init_mech_type(void *context, size_t hdrlen,
@@ -279,37 +181,31 @@ int ksmbd_neg_token_init_mech_type(void *context, size_t hdrlen,
size_t vlen)
{
struct ksmbd_conn *conn = context;
- unsigned long *oid;
- size_t oidlen;
+ enum OID oid;
int mech_type;
- char buf[50];
- if (!asn1_oid_decode(value, vlen, &oid, &oidlen))
- goto fail;
-
- if (oid_eq(oid, oidlen, NTLMSSP_OID, NTLMSSP_OID_LEN))
+ oid = look_up_OID(value, vlen);
+ if (oid == OID_ntlmssp) {
mech_type = KSMBD_AUTH_NTLMSSP;
- else if (oid_eq(oid, oidlen, MSKRB5_OID, MSKRB5_OID_LEN))
+ } else if (oid == OID_mskrb5) {
mech_type = KSMBD_AUTH_MSKRB5;
- else if (oid_eq(oid, oidlen, KRB5_OID, KRB5_OID_LEN))
+ } else if (oid == OID_krb5) {
mech_type = KSMBD_AUTH_KRB5;
- else if (oid_eq(oid, oidlen, KRB5U2U_OID, KRB5U2U_OID_LEN))
+ } else if (oid == OID_krb5u2u) {
mech_type = KSMBD_AUTH_KRB5U2U;
- else
- goto fail;
+ } else {
+ char buf[50];
+
+ sprint_oid(value, vlen, buf, sizeof(buf));
+ ksmbd_debug(AUTH, "Unexpected OID: %s\n", buf);
+ return -EBADMSG;
+ }
conn->auth_mechs |= mech_type;
if (conn->preferred_auth_mech == 0)
conn->preferred_auth_mech = mech_type;
- kfree(oid);
return 0;
-
-fail:
- kfree(oid);
- sprint_oid(value, vlen, buf, sizeof(buf));
- ksmbd_debug(AUTH, "Unexpected OID: %s\n", buf);
- return -EBADMSG;
}
int ksmbd_neg_token_init_mech_token(void *context, size_t hdrlen,
diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c
index 3503b1c..dc3d061 100644
--- a/fs/ksmbd/auth.c
+++ b/fs/ksmbd/auth.c
@@ -215,7 +215,7 @@ static int calc_ntlmv2_hash(struct ksmbd_session *sess, char *ntlmv2_hash,
* Return: 0 on success, error number on error
*/
int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2,
- int blen, char *domain_name)
+ int blen, char *domain_name, char *cryptkey)
{
char ntlmv2_hash[CIFS_ENCPWD_SIZE];
char ntlmv2_rsp[CIFS_HMAC_MD5_HASH_SIZE];
@@ -256,7 +256,7 @@ int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2,
goto out;
}
- memcpy(construct, sess->ntlmssp.cryptkey, CIFS_CRYPTO_KEY_SIZE);
+ memcpy(construct, cryptkey, CIFS_CRYPTO_KEY_SIZE);
memcpy(construct + CIFS_CRYPTO_KEY_SIZE, &ntlmv2->blob_signature, blen);
rc = crypto_shash_update(CRYPTO_HMACMD5(ctx), construct, len);
@@ -295,7 +295,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2,
* Return: 0 on success, error number on error
*/
int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
- int blob_len, struct ksmbd_session *sess)
+ int blob_len, struct ksmbd_conn *conn,
+ struct ksmbd_session *sess)
{
char *domain_name;
unsigned int nt_off, dn_off;
@@ -324,7 +325,7 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
/* TODO : use domain name that imported from configuration file */
domain_name = smb_strndup_from_utf16((const char *)authblob + dn_off,
- dn_len, true, sess->conn->local_nls);
+ dn_len, true, conn->local_nls);
if (IS_ERR(domain_name))
return PTR_ERR(domain_name);
@@ -333,7 +334,7 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
domain_name);
ret = ksmbd_auth_ntlmv2(sess, (struct ntlmv2_resp *)((char *)authblob + nt_off),
nt_len - CIFS_ENCPWD_SIZE,
- domain_name);
+ domain_name, conn->ntlmssp.cryptkey);
kfree(domain_name);
return ret;
}
@@ -347,7 +348,7 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
*
*/
int ksmbd_decode_ntlmssp_neg_blob(struct negotiate_message *negblob,
- int blob_len, struct ksmbd_session *sess)
+ int blob_len, struct ksmbd_conn *conn)
{
if (blob_len < sizeof(struct negotiate_message)) {
ksmbd_debug(AUTH, "negotiate blob len %d too small\n",
@@ -361,7 +362,7 @@ int ksmbd_decode_ntlmssp_neg_blob(struct negotiate_message *negblob,
return -EINVAL;
}
- sess->ntlmssp.client_flags = le32_to_cpu(negblob->NegotiateFlags);
+ conn->ntlmssp.client_flags = le32_to_cpu(negblob->NegotiateFlags);
return 0;
}
@@ -375,14 +376,14 @@ int ksmbd_decode_ntlmssp_neg_blob(struct negotiate_message *negblob,
*/
unsigned int
ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
- struct ksmbd_session *sess)
+ struct ksmbd_conn *conn)
{
struct target_info *tinfo;
wchar_t *name;
__u8 *target_name;
unsigned int flags, blob_off, blob_len, type, target_info_len = 0;
int len, uni_len, conv_len;
- int cflags = sess->ntlmssp.client_flags;
+ int cflags = conn->ntlmssp.client_flags;
memcpy(chgblob->Signature, NTLMSSP_SIGNATURE, 8);
chgblob->MessageType = NtLmChallenge;
@@ -403,7 +404,7 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
if (cflags & NTLMSSP_REQUEST_TARGET)
flags |= NTLMSSP_REQUEST_TARGET;
- if (sess->conn->use_spnego &&
+ if (conn->use_spnego &&
(cflags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
flags |= NTLMSSP_NEGOTIATE_EXTENDED_SEC;
@@ -414,7 +415,7 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
return -ENOMEM;
conv_len = smb_strtoUTF16((__le16 *)name, ksmbd_netbios_name(), len,
- sess->conn->local_nls);
+ conn->local_nls);
if (conv_len < 0 || conv_len > len) {
kfree(name);
return -EINVAL;
@@ -430,8 +431,8 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
chgblob->TargetName.BufferOffset = cpu_to_le32(blob_off);
/* Initialize random conn challenge */
- get_random_bytes(sess->ntlmssp.cryptkey, sizeof(__u64));
- memcpy(chgblob->Challenge, sess->ntlmssp.cryptkey,
+ get_random_bytes(conn->ntlmssp.cryptkey, sizeof(__u64));
+ memcpy(chgblob->Challenge, conn->ntlmssp.cryptkey,
CIFS_CRYPTO_KEY_SIZE);
/* Add Target Information to security buffer */
diff --git a/fs/ksmbd/auth.h b/fs/ksmbd/auth.h
index 9c2d4ba..9562965 100644
--- a/fs/ksmbd/auth.h
+++ b/fs/ksmbd/auth.h
@@ -38,16 +38,16 @@ struct kvec;
int ksmbd_crypt_message(struct ksmbd_conn *conn, struct kvec *iov,
unsigned int nvec, int enc);
void ksmbd_copy_gss_neg_header(void *buf);
-int ksmbd_auth_ntlm(struct ksmbd_session *sess, char *pw_buf);
int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2,
- int blen, char *domain_name);
+ int blen, char *domain_name, char *cryptkey);
int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
- int blob_len, struct ksmbd_session *sess);
+ int blob_len, struct ksmbd_conn *conn,
+ struct ksmbd_session *sess);
int ksmbd_decode_ntlmssp_neg_blob(struct negotiate_message *negblob,
- int blob_len, struct ksmbd_session *sess);
+ int blob_len, struct ksmbd_conn *conn);
unsigned int
ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
- struct ksmbd_session *sess);
+ struct ksmbd_conn *conn);
int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob,
int in_len, char *out_blob, int *out_len);
int ksmbd_sign_smb2_pdu(struct ksmbd_conn *conn, char *key, struct kvec *iov,
diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c
index 83a94d0..208d2cf 100644
--- a/fs/ksmbd/connection.c
+++ b/fs/ksmbd/connection.c
@@ -62,6 +62,7 @@ struct ksmbd_conn *ksmbd_conn_alloc(void)
atomic_set(&conn->req_running, 0);
atomic_set(&conn->r_count, 0);
conn->total_credits = 1;
+ conn->outstanding_credits = 1;
init_waitqueue_head(&conn->req_running_q);
INIT_LIST_HEAD(&conn->conns_list);
@@ -386,17 +387,24 @@ int ksmbd_conn_transport_init(void)
static void stop_sessions(void)
{
struct ksmbd_conn *conn;
+ struct ksmbd_transport *t;
again:
read_lock(&conn_list_lock);
list_for_each_entry(conn, &conn_list, conns_list) {
struct task_struct *task;
- task = conn->transport->handler;
+ t = conn->transport;
+ task = t->handler;
if (task)
ksmbd_debug(CONN, "Stop session handler %s/%d\n",
task->comm, task_pid_nr(task));
conn->status = KSMBD_SESS_EXITING;
+ if (t->ops->shutdown) {
+ read_unlock(&conn_list_lock);
+ t->ops->shutdown(t);
+ read_lock(&conn_list_lock);
+ }
}
read_unlock(&conn_list_lock);
diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h
index e5403c5..7a59aac 100644
--- a/fs/ksmbd/connection.h
+++ b/fs/ksmbd/connection.h
@@ -61,8 +61,8 @@ struct ksmbd_conn {
atomic_t req_running;
/* References which are made for this Server object*/
atomic_t r_count;
- unsigned short total_credits;
- unsigned short max_credits;
+ unsigned int total_credits;
+ unsigned int outstanding_credits;
spinlock_t credits_lock;
wait_queue_head_t req_running_q;
/* Lock to protect requests list*/
@@ -72,12 +72,7 @@ struct ksmbd_conn {
int connection_type;
struct ksmbd_stats stats;
char ClientGUID[SMB2_CLIENT_GUID_SIZE];
- union {
- /* pending trans request table */
- struct trans_state *recent_trans;
- /* Used by ntlmssp */
- char *ntlmssp_cryptkey;
- };
+ struct ntlmssp_auth ntlmssp;
spinlock_t llist_lock;
struct list_head lock_list;
@@ -122,6 +117,7 @@ struct ksmbd_conn_ops {
struct ksmbd_transport_ops {
int (*prepare)(struct ksmbd_transport *t);
void (*disconnect)(struct ksmbd_transport *t);
+ void (*shutdown)(struct ksmbd_transport *t);
int (*read)(struct ksmbd_transport *t, char *buf, unsigned int size);
int (*writev)(struct ksmbd_transport *t, struct kvec *iovs, int niov,
int size, bool need_invalidate_rkey,
diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h
index c6718a0..71bfb7d 100644
--- a/fs/ksmbd/ksmbd_netlink.h
+++ b/fs/ksmbd/ksmbd_netlink.h
@@ -103,6 +103,8 @@ struct ksmbd_startup_request {
* we set the SPARSE_FILES bit (0x40).
*/
__u32 sub_auth[3]; /* Subauth value for Security ID */
+ __u32 smb2_max_credits; /* MAX credits */
+ __u32 reserved[128]; /* Reserved room */
__u32 ifc_list_sz; /* interfaces list size */
__s8 ____payload[];
};
@@ -113,7 +115,7 @@ struct ksmbd_startup_request {
* IPC request to shutdown ksmbd server.
*/
struct ksmbd_shutdown_request {
- __s32 reserved;
+ __s32 reserved[16];
};
/*
@@ -122,6 +124,7 @@ struct ksmbd_shutdown_request {
struct ksmbd_login_request {
__u32 handle;
__s8 account[KSMBD_REQ_MAX_ACCOUNT_NAME_SZ]; /* user account name */
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -135,6 +138,7 @@ struct ksmbd_login_response {
__u16 status;
__u16 hash_sz; /* hash size */
__s8 hash[KSMBD_REQ_MAX_HASH_SZ]; /* password hash */
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -143,6 +147,7 @@ struct ksmbd_login_response {
struct ksmbd_share_config_request {
__u32 handle;
__s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; /* share name */
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -157,6 +162,7 @@ struct ksmbd_share_config_response {
__u16 force_directory_mode;
__u16 force_uid;
__u16 force_gid;
+ __u32 reserved[128]; /* Reserved room */
__u32 veto_list_sz;
__s8 ____payload[];
};
@@ -187,6 +193,7 @@ struct ksmbd_tree_connect_request {
__s8 account[KSMBD_REQ_MAX_ACCOUNT_NAME_SZ];
__s8 share[KSMBD_REQ_MAX_SHARE_NAME];
__s8 peer_addr[64];
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -196,6 +203,7 @@ struct ksmbd_tree_connect_response {
__u32 handle;
__u16 status;
__u16 connection_flags;
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -204,6 +212,7 @@ struct ksmbd_tree_connect_response {
struct ksmbd_tree_disconnect_request {
__u64 session_id; /* session id */
__u64 connect_id; /* tree connection id */
+ __u32 reserved[16]; /* Reserved room */
};
/*
@@ -212,6 +221,7 @@ struct ksmbd_tree_disconnect_request {
struct ksmbd_logout_request {
__s8 account[KSMBD_REQ_MAX_ACCOUNT_NAME_SZ]; /* user account name */
__u32 account_flags;
+ __u32 reserved[16]; /* Reserved room */
};
/*
diff --git a/fs/ksmbd/mgmt/user_config.c b/fs/ksmbd/mgmt/user_config.c
index 1019d36..279d00f 100644
--- a/fs/ksmbd/mgmt/user_config.c
+++ b/fs/ksmbd/mgmt/user_config.c
@@ -67,3 +67,13 @@ int ksmbd_anonymous_user(struct ksmbd_user *user)
return 1;
return 0;
}
+
+bool ksmbd_compare_user(struct ksmbd_user *u1, struct ksmbd_user *u2)
+{
+ if (strcmp(u1->name, u2->name))
+ return false;
+ if (memcmp(u1->passkey, u2->passkey, u1->passkey_sz))
+ return false;
+
+ return true;
+}
diff --git a/fs/ksmbd/mgmt/user_config.h b/fs/ksmbd/mgmt/user_config.h
index aff80b0..6a44109 100644
--- a/fs/ksmbd/mgmt/user_config.h
+++ b/fs/ksmbd/mgmt/user_config.h
@@ -64,4 +64,5 @@ struct ksmbd_user *ksmbd_login_user(const char *account);
struct ksmbd_user *ksmbd_alloc_user(struct ksmbd_login_response *resp);
void ksmbd_free_user(struct ksmbd_user *user);
int ksmbd_anonymous_user(struct ksmbd_user *user);
+bool ksmbd_compare_user(struct ksmbd_user *u1, struct ksmbd_user *u2);
#endif /* __USER_CONFIG_MANAGEMENT_H__ */
diff --git a/fs/ksmbd/mgmt/user_session.h b/fs/ksmbd/mgmt/user_session.h
index 82289c3..e241f16 100644
--- a/fs/ksmbd/mgmt/user_session.h
+++ b/fs/ksmbd/mgmt/user_session.h
@@ -45,7 +45,6 @@ struct ksmbd_session {
int state;
__u8 *Preauth_HashValue;
- struct ntlmssp_auth ntlmssp;
char sess_key[CIFS_KEY_SIZE];
struct hlist_node hlist;
diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c
index 50d0b10..4a94601 100644
--- a/fs/ksmbd/smb2misc.c
+++ b/fs/ksmbd/smb2misc.c
@@ -289,7 +289,7 @@ static int smb2_validate_credit_charge(struct ksmbd_conn *conn,
unsigned int req_len = 0, expect_resp_len = 0, calc_credit_num, max_len;
unsigned short credit_charge = le16_to_cpu(hdr->CreditCharge);
void *__hdr = hdr;
- int ret;
+ int ret = 0;
switch (hdr->Command) {
case SMB2_QUERY_INFO:
@@ -326,21 +326,27 @@ static int smb2_validate_credit_charge(struct ksmbd_conn *conn,
ksmbd_debug(SMB, "Insufficient credit charge, given: %d, needed: %d\n",
credit_charge, calc_credit_num);
return 1;
- } else if (credit_charge > conn->max_credits) {
+ } else if (credit_charge > conn->vals->max_credits) {
ksmbd_debug(SMB, "Too large credit charge: %d\n", credit_charge);
return 1;
}
spin_lock(&conn->credits_lock);
- if (credit_charge <= conn->total_credits) {
- conn->total_credits -= credit_charge;
- ret = 0;
- } else {
+ if (credit_charge > conn->total_credits) {
ksmbd_debug(SMB, "Insufficient credits granted, given: %u, granted: %u\n",
credit_charge, conn->total_credits);
ret = 1;
}
+
+ if ((u64)conn->outstanding_credits + credit_charge > conn->vals->max_credits) {
+ ksmbd_debug(SMB, "Limits exceeding the maximum allowable outstanding requests, given : %u, pending : %u\n",
+ credit_charge, conn->outstanding_credits);
+ ret = 1;
+ } else
+ conn->outstanding_credits += credit_charge;
+
spin_unlock(&conn->credits_lock);
+
return ret;
}
diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c
index 02a44d2..ab23da2 100644
--- a/fs/ksmbd/smb2ops.c
+++ b/fs/ksmbd/smb2ops.c
@@ -19,6 +19,7 @@ static struct smb_version_values smb21_server_values = {
.max_read_size = SMB21_DEFAULT_IOSIZE,
.max_write_size = SMB21_DEFAULT_IOSIZE,
.max_trans_size = SMB21_DEFAULT_IOSIZE,
+ .max_credits = SMB2_MAX_CREDITS,
.large_lock_type = 0,
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE,
.shared_lock_type = SMB2_LOCKFLAG_SHARED,
@@ -44,6 +45,7 @@ static struct smb_version_values smb30_server_values = {
.max_read_size = SMB3_DEFAULT_IOSIZE,
.max_write_size = SMB3_DEFAULT_IOSIZE,
.max_trans_size = SMB3_DEFAULT_TRANS_SIZE,
+ .max_credits = SMB2_MAX_CREDITS,
.large_lock_type = 0,
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE,
.shared_lock_type = SMB2_LOCKFLAG_SHARED,
@@ -70,6 +72,7 @@ static struct smb_version_values smb302_server_values = {
.max_read_size = SMB3_DEFAULT_IOSIZE,
.max_write_size = SMB3_DEFAULT_IOSIZE,
.max_trans_size = SMB3_DEFAULT_TRANS_SIZE,
+ .max_credits = SMB2_MAX_CREDITS,
.large_lock_type = 0,
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE,
.shared_lock_type = SMB2_LOCKFLAG_SHARED,
@@ -96,6 +99,7 @@ static struct smb_version_values smb311_server_values = {
.max_read_size = SMB3_DEFAULT_IOSIZE,
.max_write_size = SMB3_DEFAULT_IOSIZE,
.max_trans_size = SMB3_DEFAULT_TRANS_SIZE,
+ .max_credits = SMB2_MAX_CREDITS,
.large_lock_type = 0,
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE,
.shared_lock_type = SMB2_LOCKFLAG_SHARED,
@@ -197,7 +201,6 @@ void init_smb2_1_server(struct ksmbd_conn *conn)
conn->ops = &smb2_0_server_ops;
conn->cmds = smb2_0_server_cmds;
conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
- conn->max_credits = SMB2_MAX_CREDITS;
conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
@@ -215,7 +218,6 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
conn->ops = &smb3_0_server_ops;
conn->cmds = smb2_0_server_cmds;
conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
- conn->max_credits = SMB2_MAX_CREDITS;
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
@@ -240,7 +242,6 @@ void init_smb3_02_server(struct ksmbd_conn *conn)
conn->ops = &smb3_0_server_ops;
conn->cmds = smb2_0_server_cmds;
conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
- conn->max_credits = SMB2_MAX_CREDITS;
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
@@ -265,7 +266,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
conn->ops = &smb3_11_server_ops;
conn->cmds = smb2_0_server_cmds;
conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
- conn->max_credits = SMB2_MAX_CREDITS;
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
@@ -304,3 +304,11 @@ void init_smb2_max_trans_size(unsigned int sz)
smb302_server_values.max_trans_size = sz;
smb311_server_values.max_trans_size = sz;
}
+
+void init_smb2_max_credits(unsigned int sz)
+{
+ smb21_server_values.max_credits = sz;
+ smb30_server_values.max_credits = sz;
+ smb302_server_values.max_credits = sz;
+ smb311_server_values.max_credits = sz;
+}
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index b8b3a4c..1866c81 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -299,16 +299,15 @@ int smb2_set_rsp_credits(struct ksmbd_work *work)
struct smb2_hdr *req_hdr = ksmbd_req_buf_next(work);
struct smb2_hdr *hdr = ksmbd_resp_buf_next(work);
struct ksmbd_conn *conn = work->conn;
- unsigned short credits_requested;
+ unsigned short credits_requested, aux_max;
unsigned short credit_charge, credits_granted = 0;
- unsigned short aux_max, aux_credits;
if (work->send_no_response)
return 0;
hdr->CreditCharge = req_hdr->CreditCharge;
- if (conn->total_credits > conn->max_credits) {
+ if (conn->total_credits > conn->vals->max_credits) {
hdr->CreditRequest = 0;
pr_err("Total credits overflow: %d\n", conn->total_credits);
return -EINVAL;
@@ -316,6 +315,14 @@ int smb2_set_rsp_credits(struct ksmbd_work *work)
credit_charge = max_t(unsigned short,
le16_to_cpu(req_hdr->CreditCharge), 1);
+ if (credit_charge > conn->total_credits) {
+ ksmbd_debug(SMB, "Insufficient credits granted, given: %u, granted: %u\n",
+ credit_charge, conn->total_credits);
+ return -EINVAL;
+ }
+
+ conn->total_credits -= credit_charge;
+ conn->outstanding_credits -= credit_charge;
credits_requested = max_t(unsigned short,
le16_to_cpu(req_hdr->CreditRequest), 1);
@@ -325,16 +332,14 @@ int smb2_set_rsp_credits(struct ksmbd_work *work)
* TODO: Need to adjuct CreditRequest value according to
* current cpu load
*/
- aux_credits = credits_requested - 1;
if (hdr->Command == SMB2_NEGOTIATE)
- aux_max = 0;
+ aux_max = 1;
else
- aux_max = conn->max_credits - credit_charge;
- aux_credits = min_t(unsigned short, aux_credits, aux_max);
- credits_granted = credit_charge + aux_credits;
+ aux_max = conn->vals->max_credits - credit_charge;
+ credits_granted = min_t(unsigned short, credits_requested, aux_max);
- if (conn->max_credits - conn->total_credits < credits_granted)
- credits_granted = conn->max_credits -
+ if (conn->vals->max_credits - conn->total_credits < credits_granted)
+ credits_granted = conn->vals->max_credits -
conn->total_credits;
conn->total_credits += credits_granted;
@@ -610,16 +615,14 @@ static void destroy_previous_session(struct ksmbd_user *user, u64 id)
/**
* smb2_get_name() - get filename string from on the wire smb format
- * @share: ksmbd_share_config pointer
* @src: source buffer
* @maxlen: maxlen of source string
- * @nls_table: nls_table pointer
+ * @local_nls: nls_table pointer
*
* Return: matching converted filename on success, otherwise error ptr
*/
static char *
-smb2_get_name(struct ksmbd_share_config *share, const char *src,
- const int maxlen, struct nls_table *local_nls)
+smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls)
{
char *name;
@@ -1303,7 +1306,7 @@ static int ntlm_negotiate(struct ksmbd_work *work,
int sz, rc;
ksmbd_debug(SMB, "negotiate phase\n");
- rc = ksmbd_decode_ntlmssp_neg_blob(negblob, negblob_len, work->sess);
+ rc = ksmbd_decode_ntlmssp_neg_blob(negblob, negblob_len, work->conn);
if (rc)
return rc;
@@ -1313,7 +1316,7 @@ static int ntlm_negotiate(struct ksmbd_work *work,
memset(chgblob, 0, sizeof(struct challenge_message));
if (!work->conn->use_spnego) {
- sz = ksmbd_build_ntlmssp_challenge_blob(chgblob, work->sess);
+ sz = ksmbd_build_ntlmssp_challenge_blob(chgblob, work->conn);
if (sz < 0)
return -ENOMEM;
@@ -1329,7 +1332,7 @@ static int ntlm_negotiate(struct ksmbd_work *work,
return -ENOMEM;
chgblob = (struct challenge_message *)neg_blob;
- sz = ksmbd_build_ntlmssp_challenge_blob(chgblob, work->sess);
+ sz = ksmbd_build_ntlmssp_challenge_blob(chgblob, work->conn);
if (sz < 0) {
rc = -ENOMEM;
goto out;
@@ -1450,60 +1453,62 @@ static int ntlm_authenticate(struct ksmbd_work *work)
ksmbd_free_user(user);
return 0;
}
- ksmbd_free_user(sess->user);
- }
- sess->user = user;
- if (user_guest(sess->user)) {
- if (conn->sign) {
- ksmbd_debug(SMB, "Guest login not allowed when signing enabled\n");
+ if (!ksmbd_compare_user(sess->user, user)) {
+ ksmbd_free_user(user);
return -EPERM;
}
+ ksmbd_free_user(user);
+ } else {
+ sess->user = user;
+ }
+ if (user_guest(sess->user)) {
rsp->SessionFlags = SMB2_SESSION_FLAG_IS_GUEST_LE;
} else {
struct authenticate_message *authblob;
authblob = user_authblob(conn, req);
sz = le16_to_cpu(req->SecurityBufferLength);
- rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, sess);
+ rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess);
if (rc) {
set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD);
ksmbd_debug(SMB, "authentication failed\n");
return -EPERM;
}
+ }
+ /*
+ * If session state is SMB2_SESSION_VALID, We can assume
+ * that it is reauthentication. And the user/password
+ * has been verified, so return it here.
+ */
+ if (sess->state == SMB2_SESSION_VALID) {
+ if (conn->binding)
+ goto binding_session;
+ return 0;
+ }
+
+ if ((rsp->SessionFlags != SMB2_SESSION_FLAG_IS_GUEST_LE &&
+ (conn->sign || server_conf.enforced_signing)) ||
+ (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED))
+ sess->sign = true;
+
+ if (smb3_encryption_negotiated(conn) &&
+ !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) {
+ rc = conn->ops->generate_encryptionkey(sess);
+ if (rc) {
+ ksmbd_debug(SMB,
+ "SMB3 encryption key generation failed\n");
+ return -EINVAL;
+ }
+ sess->enc = true;
+ rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE;
/*
- * If session state is SMB2_SESSION_VALID, We can assume
- * that it is reauthentication. And the user/password
- * has been verified, so return it here.
+ * signing is disable if encryption is enable
+ * on this session
*/
- if (sess->state == SMB2_SESSION_VALID) {
- if (conn->binding)
- goto binding_session;
- return 0;
- }
-
- if ((conn->sign || server_conf.enforced_signing) ||
- (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED))
- sess->sign = true;
-
- if (smb3_encryption_negotiated(conn) &&
- !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) {
- rc = conn->ops->generate_encryptionkey(sess);
- if (rc) {
- ksmbd_debug(SMB,
- "SMB3 encryption key generation failed\n");
- return -EINVAL;
- }
- sess->enc = true;
- rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE;
- /*
- * signing is disable if encryption is enable
- * on this session
- */
- sess->sign = false;
- }
+ sess->sign = false;
}
binding_session:
@@ -2057,9 +2062,6 @@ int smb2_session_logoff(struct ksmbd_work *work)
ksmbd_debug(SMB, "request\n");
- /* Got a valid session, set connection state */
- WARN_ON(sess->conn != conn);
-
/* setting CifsExiting here may race with start_tcp_sess */
ksmbd_conn_set_need_reconnect(work);
ksmbd_close_session_fds(work);
@@ -2530,8 +2532,7 @@ int smb2_open(struct ksmbd_work *work)
goto err_out1;
}
- name = smb2_get_name(share,
- req->Buffer,
+ name = smb2_get_name(req->Buffer,
le16_to_cpu(req->NameLength),
work->conn->local_nls);
if (IS_ERR(name)) {
@@ -3392,7 +3393,6 @@ static int dentry_name(struct ksmbd_dir_info *d_info, int info_level)
* @conn: connection instance
* @info_level: smb information level
* @d_info: structure included variables for query dir
- * @user_ns: user namespace
* @ksmbd_kstat: ksmbd wrapper of dirent stat information
*
* if directory has many entries, find first can't read it fully.
@@ -4018,6 +4018,7 @@ int smb2_query_dir(struct ksmbd_work *work)
* buffer_check_err() - helper function to check buffer errors
* @reqOutputBufferLength: max buffer length expected in command response
* @rsp: query info response buffer contains output buffer length
+ * @rsp_org: base response buffer pointer in case of chained response
* @infoclass_size: query info class response buffer size
*
* Return: 0 on success, otherwise error
@@ -5398,8 +5399,7 @@ static int smb2_rename(struct ksmbd_work *work,
goto out;
}
- new_name = smb2_get_name(share,
- file_info->FileName,
+ new_name = smb2_get_name(file_info->FileName,
le32_to_cpu(file_info->FileNameLength),
local_nls);
if (IS_ERR(new_name)) {
@@ -5510,8 +5510,7 @@ static int smb2_create_link(struct ksmbd_work *work,
if (!pathname)
return -ENOMEM;
- link_name = smb2_get_name(share,
- file_info->FileName,
+ link_name = smb2_get_name(file_info->FileName,
le32_to_cpu(file_info->FileNameLength),
local_nls);
if (IS_ERR(link_name) || S_ISDIR(file_inode(filp)->i_mode)) {
@@ -5849,7 +5848,7 @@ static int set_file_mode_info(struct ksmbd_file *fp,
* smb2_set_info_file() - handler for smb2 set info command
* @work: smb work containing set info command buffer
* @fp: ksmbd_file pointer
- * @info_class: smb2 set info class
+ * @req: request buffer pointer
* @share: ksmbd_share_config pointer
*
* Return: 0 on success, otherwise error
@@ -6121,6 +6120,26 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
return err;
}
+static int smb2_set_remote_key_for_rdma(struct ksmbd_work *work,
+ struct smb2_buffer_desc_v1 *desc,
+ __le32 Channel,
+ __le16 ChannelInfoOffset,
+ __le16 ChannelInfoLength)
+{
+ if (work->conn->dialect == SMB30_PROT_ID &&
+ Channel != SMB2_CHANNEL_RDMA_V1)
+ return -EINVAL;
+
+ if (ChannelInfoOffset == 0 ||
+ le16_to_cpu(ChannelInfoLength) < sizeof(*desc))
+ return -EINVAL;
+
+ work->need_invalidate_rkey =
+ (Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE);
+ work->remote_key = le32_to_cpu(desc->token);
+ return 0;
+}
+
static ssize_t smb2_read_rdma_channel(struct ksmbd_work *work,
struct smb2_read_req *req, void *data_buf,
size_t length)
@@ -6129,18 +6148,6 @@ static ssize_t smb2_read_rdma_channel(struct ksmbd_work *work,
(struct smb2_buffer_desc_v1 *)&req->Buffer[0];
int err;
- if (work->conn->dialect == SMB30_PROT_ID &&
- req->Channel != SMB2_CHANNEL_RDMA_V1)
- return -EINVAL;
-
- if (req->ReadChannelInfoOffset == 0 ||
- le16_to_cpu(req->ReadChannelInfoLength) < sizeof(*desc))
- return -EINVAL;
-
- work->need_invalidate_rkey =
- (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE);
- work->remote_key = le32_to_cpu(desc->token);
-
err = ksmbd_conn_rdma_write(work->conn, data_buf, length,
le32_to_cpu(desc->token),
le64_to_cpu(desc->offset),
@@ -6162,7 +6169,7 @@ int smb2_read(struct ksmbd_work *work)
struct ksmbd_conn *conn = work->conn;
struct smb2_read_req *req;
struct smb2_read_rsp *rsp;
- struct ksmbd_file *fp;
+ struct ksmbd_file *fp = NULL;
loff_t offset;
size_t length, mincount;
ssize_t nbytes = 0, remain_bytes = 0;
@@ -6176,6 +6183,18 @@ int smb2_read(struct ksmbd_work *work)
return smb2_read_pipe(work);
}
+ if (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE ||
+ req->Channel == SMB2_CHANNEL_RDMA_V1) {
+ err = smb2_set_remote_key_for_rdma(work,
+ (struct smb2_buffer_desc_v1 *)
+ &req->Buffer[0],
+ req->Channel,
+ req->ReadChannelInfoOffset,
+ req->ReadChannelInfoLength);
+ if (err)
+ goto out;
+ }
+
fp = ksmbd_lookup_fd_slow(work, le64_to_cpu(req->VolatileFileId),
le64_to_cpu(req->PersistentFileId));
if (!fp) {
@@ -6361,21 +6380,6 @@ static ssize_t smb2_write_rdma_channel(struct ksmbd_work *work,
desc = (struct smb2_buffer_desc_v1 *)&req->Buffer[0];
- if (work->conn->dialect == SMB30_PROT_ID &&
- req->Channel != SMB2_CHANNEL_RDMA_V1)
- return -EINVAL;
-
- if (req->Length != 0 || req->DataOffset != 0)
- return -EINVAL;
-
- if (req->WriteChannelInfoOffset == 0 ||
- le16_to_cpu(req->WriteChannelInfoLength) < sizeof(*desc))
- return -EINVAL;
-
- work->need_invalidate_rkey =
- (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE);
- work->remote_key = le32_to_cpu(desc->token);
-
data_buf = kvmalloc(length, GFP_KERNEL | __GFP_ZERO);
if (!data_buf)
return -ENOMEM;
@@ -6422,6 +6426,20 @@ int smb2_write(struct ksmbd_work *work)
return smb2_write_pipe(work);
}
+ if (req->Channel == SMB2_CHANNEL_RDMA_V1 ||
+ req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE) {
+ if (req->Length != 0 || req->DataOffset != 0)
+ return -EINVAL;
+ err = smb2_set_remote_key_for_rdma(work,
+ (struct smb2_buffer_desc_v1 *)
+ &req->Buffer[0],
+ req->Channel,
+ req->WriteChannelInfoOffset,
+ req->WriteChannelInfoLength);
+ if (err)
+ goto out;
+ }
+
if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) {
ksmbd_debug(SMB, "User does not have write permission\n");
err = -EACCES;
@@ -7243,15 +7261,10 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
struct sockaddr_storage_rsp *sockaddr_storage;
unsigned int flags;
unsigned long long speed;
- struct sockaddr_in6 *csin6 = (struct sockaddr_in6 *)&conn->peer_addr;
rtnl_lock();
for_each_netdev(&init_net, netdev) {
- if (out_buf_len <
- nbytes + sizeof(struct network_interface_info_ioctl_rsp)) {
- rtnl_unlock();
- return -ENOSPC;
- }
+ bool ipv4_set = false;
if (netdev->type == ARPHRD_LOOPBACK)
continue;
@@ -7259,12 +7272,20 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
flags = dev_get_flags(netdev);
if (!(flags & IFF_RUNNING))
continue;
+ipv6_retry:
+ if (out_buf_len <
+ nbytes + sizeof(struct network_interface_info_ioctl_rsp)) {
+ rtnl_unlock();
+ return -ENOSPC;
+ }
nii_rsp = (struct network_interface_info_ioctl_rsp *)
&rsp->Buffer[nbytes];
nii_rsp->IfIndex = cpu_to_le32(netdev->ifindex);
nii_rsp->Capability = 0;
+ if (netdev->real_num_tx_queues > 1)
+ nii_rsp->Capability |= cpu_to_le32(RSS_CAPABLE);
if (ksmbd_rdma_capable_netdev(netdev))
nii_rsp->Capability |= cpu_to_le32(RDMA_CAPABLE);
@@ -7289,8 +7310,7 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
nii_rsp->SockAddr_Storage;
memset(sockaddr_storage, 0, 128);
- if (conn->peer_addr.ss_family == PF_INET ||
- ipv6_addr_v4mapped(&csin6->sin6_addr)) {
+ if (!ipv4_set) {
struct in_device *idev;
sockaddr_storage->Family = cpu_to_le16(INTERNETWORK);
@@ -7301,6 +7321,9 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
continue;
sockaddr_storage->addr4.IPv4address =
idev_ipv4_address(idev);
+ nbytes += sizeof(struct network_interface_info_ioctl_rsp);
+ ipv4_set = true;
+ goto ipv6_retry;
} else {
struct inet6_dev *idev6;
struct inet6_ifaddr *ifa;
@@ -7322,9 +7345,8 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
break;
}
sockaddr_storage->addr6.ScopeId = 0;
+ nbytes += sizeof(struct network_interface_info_ioctl_rsp);
}
-
- nbytes += sizeof(struct network_interface_info_ioctl_rsp);
}
rtnl_unlock();
diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h
index 4a3e433..725b800 100644
--- a/fs/ksmbd/smb2pdu.h
+++ b/fs/ksmbd/smb2pdu.h
@@ -980,6 +980,7 @@ int init_smb3_11_server(struct ksmbd_conn *conn);
void init_smb2_max_read_size(unsigned int sz);
void init_smb2_max_write_size(unsigned int sz);
void init_smb2_max_trans_size(unsigned int sz);
+void init_smb2_max_credits(unsigned int sz);
bool is_smb2_neg_cmd(struct ksmbd_work *work);
bool is_smb2_rsp(struct ksmbd_work *work);
diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h
index 5059084..e1369b4 100644
--- a/fs/ksmbd/smb_common.h
+++ b/fs/ksmbd/smb_common.h
@@ -365,6 +365,7 @@ struct smb_version_values {
__u32 max_read_size;
__u32 max_write_size;
__u32 max_trans_size;
+ __u32 max_credits;
__u32 large_lock_type;
__u32 exclusive_lock_type;
__u32 shared_lock_type;
diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c
index 1acf189..3ad6881 100644
--- a/fs/ksmbd/transport_ipc.c
+++ b/fs/ksmbd/transport_ipc.c
@@ -301,6 +301,8 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
init_smb2_max_write_size(req->smb2_max_write);
if (req->smb2_max_trans)
init_smb2_max_trans_size(req->smb2_max_trans);
+ if (req->smb2_max_credits)
+ init_smb2_max_credits(req->smb2_max_credits);
ret = ksmbd_set_netbios_name(req->netbios_name);
ret |= ksmbd_set_server_string(req->server_string);
diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c
index 7e57cbb..3c1ec1a 100644
--- a/fs/ksmbd/transport_rdma.c
+++ b/fs/ksmbd/transport_rdma.c
@@ -34,7 +34,8 @@
#include "smbstatus.h"
#include "transport_rdma.h"
-#define SMB_DIRECT_PORT 5445
+#define SMB_DIRECT_PORT_IWARP 5445
+#define SMB_DIRECT_PORT_INFINIBAND 445
#define SMB_DIRECT_VERSION_LE cpu_to_le16(0x0100)
@@ -60,6 +61,10 @@
* as defined in [MS-SMBD] 3.1.1.1
* Those may change after a SMB_DIRECT negotiation
*/
+
+/* Set 445 port to SMB Direct port by default */
+static int smb_direct_port = SMB_DIRECT_PORT_INFINIBAND;
+
/* The local peer's maximum number of credits to grant to the peer */
static int smb_direct_receive_credit_max = 255;
@@ -75,10 +80,18 @@ static int smb_direct_max_fragmented_recv_size = 1024 * 1024;
/* The maximum single-message size which can be received */
static int smb_direct_max_receive_size = 8192;
-static int smb_direct_max_read_write_size = 1024 * 1024;
+static int smb_direct_max_read_write_size = 1048512;
static int smb_direct_max_outstanding_rw_ops = 8;
+static LIST_HEAD(smb_direct_device_list);
+static DEFINE_RWLOCK(smb_direct_device_lock);
+
+struct smb_direct_device {
+ struct ib_device *ib_dev;
+ struct list_head list;
+};
+
static struct smb_direct_listener {
struct rdma_cm_id *cm_id;
} smb_direct_listener;
@@ -415,6 +428,7 @@ static void free_transport(struct smb_direct_transport *t)
if (t->qp) {
ib_drain_qp(t->qp);
+ ib_mr_pool_destroy(t->qp, &t->qp->rdma_mrs);
ib_destroy_qp(t->qp);
}
@@ -555,6 +569,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
}
t->negotiation_requested = true;
t->full_packet_received = true;
+ enqueue_reassembly(t, recvmsg, 0);
wake_up_interruptible(&t->wait_status);
break;
case SMB_DIRECT_MSG_DATA_TRANSFER: {
@@ -1438,6 +1453,15 @@ static void smb_direct_disconnect(struct ksmbd_transport *t)
free_transport(st);
}
+static void smb_direct_shutdown(struct ksmbd_transport *t)
+{
+ struct smb_direct_transport *st = smb_trans_direct_transfort(t);
+
+ ksmbd_debug(RDMA, "smb-direct shutdown cm_id=%p\n", st->cm_id);
+
+ smb_direct_disconnect_rdma_work(&st->disconnect_work);
+}
+
static int smb_direct_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
@@ -1581,19 +1605,13 @@ static int smb_direct_accept_client(struct smb_direct_transport *t)
pr_err("error at rdma_accept: %d\n", ret);
return ret;
}
-
- wait_event_interruptible(t->wait_status,
- t->status != SMB_DIRECT_CS_NEW);
- if (t->status != SMB_DIRECT_CS_CONNECTED)
- return -ENOTCONN;
return 0;
}
-static int smb_direct_negotiate(struct smb_direct_transport *t)
+static int smb_direct_prepare_negotiation(struct smb_direct_transport *t)
{
int ret;
struct smb_direct_recvmsg *recvmsg;
- struct smb_direct_negotiate_req *req;
recvmsg = get_free_recvmsg(t);
if (!recvmsg)
@@ -1603,44 +1621,20 @@ static int smb_direct_negotiate(struct smb_direct_transport *t)
ret = smb_direct_post_recv(t, recvmsg);
if (ret) {
pr_err("Can't post recv: %d\n", ret);
- goto out;
+ goto out_err;
}
t->negotiation_requested = false;
ret = smb_direct_accept_client(t);
if (ret) {
pr_err("Can't accept client\n");
- goto out;
+ goto out_err;
}
smb_direct_post_recv_credits(&t->post_recv_credits_work.work);
-
- ksmbd_debug(RDMA, "Waiting for SMB_DIRECT negotiate request\n");
- ret = wait_event_interruptible_timeout(t->wait_status,
- t->negotiation_requested ||
- t->status == SMB_DIRECT_CS_DISCONNECTED,
- SMB_DIRECT_NEGOTIATE_TIMEOUT * HZ);
- if (ret <= 0 || t->status == SMB_DIRECT_CS_DISCONNECTED) {
- ret = ret < 0 ? ret : -ETIMEDOUT;
- goto out;
- }
-
- ret = smb_direct_check_recvmsg(recvmsg);
- if (ret == -ECONNABORTED)
- goto out;
-
- req = (struct smb_direct_negotiate_req *)recvmsg->packet;
- t->max_recv_size = min_t(int, t->max_recv_size,
- le32_to_cpu(req->preferred_send_size));
- t->max_send_size = min_t(int, t->max_send_size,
- le32_to_cpu(req->max_receive_size));
- t->max_fragmented_send_size =
- le32_to_cpu(req->max_fragmented_size);
-
- ret = smb_direct_send_negotiate_response(t, ret);
-out:
- if (recvmsg)
- put_recvmsg(t, recvmsg);
+ return 0;
+out_err:
+ put_recvmsg(t, recvmsg);
return ret;
}
@@ -1724,7 +1718,9 @@ static int smb_direct_init_params(struct smb_direct_transport *t,
cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES;
cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES;
cap->max_inline_data = 0;
- cap->max_rdma_ctxs = 0;
+ cap->max_rdma_ctxs =
+ rdma_rw_mr_factor(device, t->cm_id->port_num, max_pages) *
+ smb_direct_max_outstanding_rw_ops;
return 0;
}
@@ -1806,6 +1802,7 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t,
{
int ret;
struct ib_qp_init_attr qp_attr;
+ int pages_per_rw;
t->pd = ib_alloc_pd(t->cm_id->device, 0);
if (IS_ERR(t->pd)) {
@@ -1853,6 +1850,23 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t,
t->qp = t->cm_id->qp;
t->cm_id->event_handler = smb_direct_cm_handler;
+ pages_per_rw = DIV_ROUND_UP(t->max_rdma_rw_size, PAGE_SIZE) + 1;
+ if (pages_per_rw > t->cm_id->device->attrs.max_sgl_rd) {
+ int pages_per_mr, mr_count;
+
+ pages_per_mr = min_t(int, pages_per_rw,
+ t->cm_id->device->attrs.max_fast_reg_page_list_len);
+ mr_count = DIV_ROUND_UP(pages_per_rw, pages_per_mr) *
+ atomic_read(&t->rw_avail_ops);
+ ret = ib_mr_pool_init(t->qp, &t->qp->rdma_mrs, mr_count,
+ IB_MR_TYPE_MEM_REG, pages_per_mr, 0);
+ if (ret) {
+ pr_err("failed to init mr pool count %d pages %d\n",
+ mr_count, pages_per_mr);
+ goto err;
+ }
+ }
+
return 0;
err:
if (t->qp) {
@@ -1877,6 +1891,49 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t,
static int smb_direct_prepare(struct ksmbd_transport *t)
{
struct smb_direct_transport *st = smb_trans_direct_transfort(t);
+ struct smb_direct_recvmsg *recvmsg;
+ struct smb_direct_negotiate_req *req;
+ int ret;
+
+ ksmbd_debug(RDMA, "Waiting for SMB_DIRECT negotiate request\n");
+ ret = wait_event_interruptible_timeout(st->wait_status,
+ st->negotiation_requested ||
+ st->status == SMB_DIRECT_CS_DISCONNECTED,
+ SMB_DIRECT_NEGOTIATE_TIMEOUT * HZ);
+ if (ret <= 0 || st->status == SMB_DIRECT_CS_DISCONNECTED)
+ return ret < 0 ? ret : -ETIMEDOUT;
+
+ recvmsg = get_first_reassembly(st);
+ if (!recvmsg)
+ return -ECONNABORTED;
+
+ ret = smb_direct_check_recvmsg(recvmsg);
+ if (ret == -ECONNABORTED)
+ goto out;
+
+ req = (struct smb_direct_negotiate_req *)recvmsg->packet;
+ st->max_recv_size = min_t(int, st->max_recv_size,
+ le32_to_cpu(req->preferred_send_size));
+ st->max_send_size = min_t(int, st->max_send_size,
+ le32_to_cpu(req->max_receive_size));
+ st->max_fragmented_send_size =
+ le32_to_cpu(req->max_fragmented_size);
+ st->max_fragmented_recv_size =
+ (st->recv_credit_max * st->max_recv_size) / 2;
+
+ ret = smb_direct_send_negotiate_response(st, ret);
+out:
+ spin_lock_irq(&st->reassembly_queue_lock);
+ st->reassembly_queue_length--;
+ list_del(&recvmsg->list);
+ spin_unlock_irq(&st->reassembly_queue_lock);
+ put_recvmsg(st, recvmsg);
+
+ return ret;
+}
+
+static int smb_direct_connect(struct smb_direct_transport *st)
+{
int ret;
struct ib_qp_cap qp_cap;
@@ -1898,13 +1955,11 @@ static int smb_direct_prepare(struct ksmbd_transport *t)
return ret;
}
- ret = smb_direct_negotiate(st);
+ ret = smb_direct_prepare_negotiation(st);
if (ret) {
pr_err("Can't negotiate: %d\n", ret);
return ret;
}
-
- st->status = SMB_DIRECT_CS_CONNECTED;
return 0;
}
@@ -1920,6 +1975,7 @@ static bool rdma_frwr_is_supported(struct ib_device_attr *attrs)
static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
{
struct smb_direct_transport *t;
+ int ret;
if (!rdma_frwr_is_supported(&new_cm_id->device->attrs)) {
ksmbd_debug(RDMA,
@@ -1932,18 +1988,23 @@ static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
if (!t)
return -ENOMEM;
+ ret = smb_direct_connect(t);
+ if (ret)
+ goto out_err;
+
KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop,
KSMBD_TRANS(t)->conn, "ksmbd:r%u",
- SMB_DIRECT_PORT);
+ smb_direct_port);
if (IS_ERR(KSMBD_TRANS(t)->handler)) {
- int ret = PTR_ERR(KSMBD_TRANS(t)->handler);
-
+ ret = PTR_ERR(KSMBD_TRANS(t)->handler);
pr_err("Can't start thread\n");
- free_transport(t);
- return ret;
+ goto out_err;
}
return 0;
+out_err:
+ free_transport(t);
+ return ret;
}
static int smb_direct_listen_handler(struct rdma_cm_id *cm_id,
@@ -2007,12 +2068,65 @@ static int smb_direct_listen(int port)
return ret;
}
+static int smb_direct_ib_client_add(struct ib_device *ib_dev)
+{
+ struct smb_direct_device *smb_dev;
+
+ /* Set 5445 port if device type is iWARP(No IB) */
+ if (ib_dev->node_type != RDMA_NODE_IB_CA)
+ smb_direct_port = SMB_DIRECT_PORT_IWARP;
+
+ if (!ib_dev->ops.get_netdev ||
+ !rdma_frwr_is_supported(&ib_dev->attrs))
+ return 0;
+
+ smb_dev = kzalloc(sizeof(*smb_dev), GFP_KERNEL);
+ if (!smb_dev)
+ return -ENOMEM;
+ smb_dev->ib_dev = ib_dev;
+
+ write_lock(&smb_direct_device_lock);
+ list_add(&smb_dev->list, &smb_direct_device_list);
+ write_unlock(&smb_direct_device_lock);
+
+ ksmbd_debug(RDMA, "ib device added: name %s\n", ib_dev->name);
+ return 0;
+}
+
+static void smb_direct_ib_client_remove(struct ib_device *ib_dev,
+ void *client_data)
+{
+ struct smb_direct_device *smb_dev, *tmp;
+
+ write_lock(&smb_direct_device_lock);
+ list_for_each_entry_safe(smb_dev, tmp, &smb_direct_device_list, list) {
+ if (smb_dev->ib_dev == ib_dev) {
+ list_del(&smb_dev->list);
+ kfree(smb_dev);
+ break;
+ }
+ }
+ write_unlock(&smb_direct_device_lock);
+}
+
+static struct ib_client smb_direct_ib_client = {
+ .name = "ksmbd_smb_direct_ib",
+ .add = smb_direct_ib_client_add,
+ .remove = smb_direct_ib_client_remove,
+};
+
int ksmbd_rdma_init(void)
{
int ret;
smb_direct_listener.cm_id = NULL;
+ ret = ib_register_client(&smb_direct_ib_client);
+ if (ret) {
+ pr_err("failed to ib_register_client\n");
+ return ret;
+ }
+
/* When a client is running out of send credits, the credits are
* granted by the server's sending a packet using this queue.
* This avoids the situation that a clients cannot send packets
@@ -2023,7 +2137,7 @@ int ksmbd_rdma_init(void)
if (!smb_direct_wq)
return -ENOMEM;
- ret = smb_direct_listen(SMB_DIRECT_PORT);
+ ret = smb_direct_listen(smb_direct_port);
if (ret) {
destroy_workqueue(smb_direct_wq);
smb_direct_wq = NULL;
@@ -2036,36 +2150,67 @@ int ksmbd_rdma_init(void)
return 0;
}
-int ksmbd_rdma_destroy(void)
+void ksmbd_rdma_destroy(void)
{
- if (smb_direct_listener.cm_id)
- rdma_destroy_id(smb_direct_listener.cm_id);
+ if (!smb_direct_listener.cm_id)
+ return;
+
+ ib_unregister_client(&smb_direct_ib_client);
+ rdma_destroy_id(smb_direct_listener.cm_id);
+
smb_direct_listener.cm_id = NULL;
if (smb_direct_wq) {
destroy_workqueue(smb_direct_wq);
smb_direct_wq = NULL;
}
- return 0;
}
bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
{
- struct ib_device *ibdev;
+ struct smb_direct_device *smb_dev;
+ int i;
bool rdma_capable = false;
- ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN);
- if (ibdev) {
- if (rdma_frwr_is_supported(&ibdev->attrs))
- rdma_capable = true;
- ib_device_put(ibdev);
+ read_lock(&smb_direct_device_lock);
+ list_for_each_entry(smb_dev, &smb_direct_device_list, list) {
+ for (i = 0; i < smb_dev->ib_dev->phys_port_cnt; i++) {
+ struct net_device *ndev;
+
+ ndev = smb_dev->ib_dev->ops.get_netdev(smb_dev->ib_dev,
+ i + 1);
+ if (!ndev)
+ continue;
+
+ if (ndev == netdev) {
+ dev_put(ndev);
+ rdma_capable = true;
+ goto out;
+ }
+ dev_put(ndev);
+ }
}
+out:
+ read_unlock(&smb_direct_device_lock);
+
+ if (rdma_capable == false) {
+ struct ib_device *ibdev;
+
+ ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN);
+ if (ibdev) {
+ if (rdma_frwr_is_supported(&ibdev->attrs))
+ rdma_capable = true;
+ ib_device_put(ibdev);
+ }
+ }
+
return rdma_capable;
}
static struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = {
.prepare = smb_direct_prepare,
.disconnect = smb_direct_disconnect,
+ .shutdown = smb_direct_shutdown,
.writev = smb_direct_writev,
.read = smb_direct_read,
.rdma_read = smb_direct_rdma_read,
diff --git a/fs/ksmbd/transport_rdma.h b/fs/ksmbd/transport_rdma.h
index 0fa8adc..5567d93 100644
--- a/fs/ksmbd/transport_rdma.h
+++ b/fs/ksmbd/transport_rdma.h
@@ -7,8 +7,6 @@
#ifndef __KSMBD_TRANSPORT_RDMA_H__
#define __KSMBD_TRANSPORT_RDMA_H__
-#define SMB_DIRECT_PORT 5445
-
/* SMB DIRECT negotiation request packet [MS-SMBD] 2.2.1 */
struct smb_direct_negotiate_req {
__le16 min_version;
@@ -52,7 +50,7 @@ struct smb_direct_data_transfer {
#ifdef CONFIG_SMB_SERVER_SMBDIRECT
int ksmbd_rdma_init(void);
-int ksmbd_rdma_destroy(void);
+void ksmbd_rdma_destroy(void);
bool ksmbd_rdma_capable_netdev(struct net_device *netdev);
#else
static inline int ksmbd_rdma_init(void) { return 0; }
diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c
index c14320e..82a1429 100644
--- a/fs/ksmbd/transport_tcp.c
+++ b/fs/ksmbd/transport_tcp.c
@@ -404,7 +404,7 @@ static int create_socket(struct interface *iface)
&ksmbd_socket);
if (ret) {
pr_err("Can't create socket for ipv4: %d\n", ret);
- goto out_error;
+ goto out_clear;
}
sin.sin_family = PF_INET;
@@ -462,6 +462,7 @@ static int create_socket(struct interface *iface)
out_error:
tcp_destroy_socket(ksmbd_socket);
+out_clear:
iface->ksmbd_socket = NULL;
return ret;
}
diff --git a/fs/ksmbd/vfs_cache.h b/fs/ksmbd/vfs_cache.h
index 448576f..36239ce 100644
--- a/fs/ksmbd/vfs_cache.h
+++ b/fs/ksmbd/vfs_cache.h
@@ -96,16 +96,6 @@ struct ksmbd_file {
int durable_timeout;
- /* for SMB1 */
- int pid;
-
- /* conflict lock fail count for SMB1 */
- unsigned int cflock_cnt;
- /* last lock failure start offset for SMB1 */
- unsigned long long llock_fstart;
-
- int dirent_offset;
-
/* if ls is happening on directory, below is valid*/
struct ksmbd_readdir_data readdir_data;
int dot_dotdot[2];
diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
index 6169659..501da99 100644
--- a/fs/netfs/read_helper.c
+++ b/fs/netfs/read_helper.c
@@ -55,7 +55,8 @@ static struct netfs_read_request *netfs_alloc_read_request(
INIT_WORK(&rreq->work, netfs_rreq_work);
refcount_set(&rreq->usage, 1);
__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
- ops->init_rreq(rreq, file);
+ if (ops->init_rreq)
+ ops->init_rreq(rreq, file);
netfs_stat(&netfs_n_rh_rreq);
}
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index bc3e2cd..063dd16 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -195,12 +195,12 @@ void nilfs_page_bug(struct page *page)
*/
static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
{
- struct buffer_head *dbh, *dbufs, *sbh, *sbufs;
+ struct buffer_head *dbh, *dbufs, *sbh;
unsigned long mask = NILFS_BUFFER_INHERENT_BITS;
BUG_ON(PageWriteback(dst));
- sbh = sbufs = page_buffers(src);
+ sbh = page_buffers(src);
if (!page_has_buffers(dst))
create_empty_buffers(dst, sbh->b_size, 0);
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
index 538e839..b501dc0 100644
--- a/fs/orangefs/orangefs-bufmap.c
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -176,7 +176,7 @@ orangefs_bufmap_free(struct orangefs_bufmap *bufmap)
{
kfree(bufmap->page_array);
kfree(bufmap->desc_array);
- kfree(bufmap->buffer_index_array);
+ bitmap_free(bufmap->buffer_index_array);
kfree(bufmap);
}
@@ -226,8 +226,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc)
bufmap->desc_size = user_desc->size;
bufmap->desc_shift = ilog2(bufmap->desc_size);
- bufmap->buffer_index_array =
- kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL);
+ bufmap->buffer_index_array = bitmap_zalloc(bufmap->desc_count, GFP_KERNEL);
if (!bufmap->buffer_index_array)
goto out_free_bufmap;
@@ -250,7 +249,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc)
out_free_desc_array:
kfree(bufmap->desc_array);
out_free_index_array:
- kfree(bufmap->buffer_index_array);
+ bitmap_free(bufmap->buffer_index_array);
out_free_bufmap:
kfree(bufmap);
out:
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
index 3627ea9..de80b62 100644
--- a/fs/orangefs/orangefs-sysfs.c
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -894,10 +894,11 @@ static struct attribute *orangefs_default_attrs[] = {
&perf_time_interval_secs_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(orangefs_default);
static struct kobj_type orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = orangefs_default_attrs,
+ .default_groups = orangefs_default_groups,
};
static struct orangefs_attribute acache_hard_limit_attribute =
@@ -931,10 +932,11 @@ static struct attribute *acache_orangefs_default_attrs[] = {
&acache_timeout_msecs_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(acache_orangefs_default);
static struct kobj_type acache_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = acache_orangefs_default_attrs,
+ .default_groups = acache_orangefs_default_groups,
};
static struct orangefs_attribute capcache_hard_limit_attribute =
@@ -968,10 +970,11 @@ static struct attribute *capcache_orangefs_default_attrs[] = {
&capcache_timeout_secs_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(capcache_orangefs_default);
static struct kobj_type capcache_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = capcache_orangefs_default_attrs,
+ .default_groups = capcache_orangefs_default_groups,
};
static struct orangefs_attribute ccache_hard_limit_attribute =
@@ -1005,10 +1008,11 @@ static struct attribute *ccache_orangefs_default_attrs[] = {
&ccache_timeout_secs_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(ccache_orangefs_default);
static struct kobj_type ccache_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = ccache_orangefs_default_attrs,
+ .default_groups = ccache_orangefs_default_groups,
};
static struct orangefs_attribute ncache_hard_limit_attribute =
@@ -1042,10 +1046,11 @@ static struct attribute *ncache_orangefs_default_attrs[] = {
&ncache_timeout_msecs_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(ncache_orangefs_default);
static struct kobj_type ncache_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = ncache_orangefs_default_attrs,
+ .default_groups = ncache_orangefs_default_groups,
};
static struct orangefs_attribute pc_acache_attribute =
@@ -1072,10 +1077,11 @@ static struct attribute *pc_orangefs_default_attrs[] = {
&pc_ncache_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(pc_orangefs_default);
static struct kobj_type pc_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = pc_orangefs_default_attrs,
+ .default_groups = pc_orangefs_default_groups,
};
static struct orangefs_attribute stats_reads_attribute =
@@ -1095,10 +1101,11 @@ static struct attribute *stats_orangefs_default_attrs[] = {
&stats_writes_attribute.attr,
NULL,
};
+ATTRIBUTE_GROUPS(stats_orangefs_default);
static struct kobj_type stats_orangefs_ktype = {
.sysfs_ops = &orangefs_sysfs_ops,
- .default_attrs = stats_orangefs_default_attrs,
+ .default_groups = stats_orangefs_default_groups,
};
static struct kobject *orangefs_obj;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 43a7abd..fd8b0c1 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -92,6 +92,7 @@
#include <linux/string_helpers.h>
#include <linux/user_namespace.h>
#include <linux/fs_struct.h>
+#include <linux/kthread.h>
#include <asm/processor.h>
#include "internal.h"
@@ -102,6 +103,8 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
if (p->flags & PF_WQ_WORKER)
wq_worker_comm(tcomm, sizeof(tcomm), p);
+ else if (p->flags & PF_KTHREAD)
+ get_kthread_comm(tcomm, sizeof(tcomm), p);
else
__get_task_comm(tcomm, sizeof(tcomm), p);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 13eda8d..d654ce7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -670,10 +670,10 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
/************************************************************************/
/* permission checks */
-static int proc_fd_access_allowed(struct inode *inode)
+static bool proc_fd_access_allowed(struct inode *inode)
{
struct task_struct *task;
- int allowed = 0;
+ bool allowed = false;
/* Allow access to a task's file descriptors if it is us or we
* may use ptrace attach to the process and find out that
* information.
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5d66fae..389e1e4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -163,7 +163,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
else {
pr_err("sysctl duplicate entry: ");
sysctl_print_dir(head->parent);
- pr_cont("/%s\n", entry->procname);
+ pr_cont("%s\n", entry->procname);
return -EEXIST;
}
}
@@ -1020,8 +1020,8 @@ static struct ctl_dir *get_subdir(struct ctl_dir *dir,
if (IS_ERR(subdir)) {
pr_err("sysctl could not get directory: ");
sysctl_print_dir(dir);
- pr_cont("/%*.*s %ld\n",
- namelen, namelen, name, PTR_ERR(subdir));
+ pr_cont("%*.*s %ld\n", namelen, namelen, name,
+ PTR_ERR(subdir));
}
drop_sysctl_table(&dir->header);
if (new)
@@ -1053,7 +1053,6 @@ static int sysctl_follow_link(struct ctl_table_header **phead,
struct ctl_dir *dir;
int ret;
- ret = 0;
spin_lock(&sysctl_lock);
root = (*pentry)->data;
set = lookup_header_set(root);
@@ -1626,7 +1625,7 @@ static void put_links(struct ctl_table_header *header)
else {
pr_err("sysctl link missing during unregister: ");
sysctl_print_dir(parent);
- pr_cont("/%s\n", name);
+ pr_cont("%s\n", name);
}
}
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 509f851..702754d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -65,8 +65,6 @@ static size_t vmcoredd_orig_sz;
static DECLARE_RWSEM(vmcore_cb_rwsem);
/* List of registered vmcore callbacks. */
static LIST_HEAD(vmcore_cb_list);
-/* Whether we had a surprise unregistration of a callback. */
-static bool vmcore_cb_unstable;
/* Whether the vmcore has been opened once. */
static bool vmcore_opened;
@@ -94,10 +92,8 @@ void unregister_vmcore_cb(struct vmcore_cb *cb)
* very unusual (e.g., forced driver removal), but we cannot stop
* unregistering.
*/
- if (vmcore_opened) {
+ if (vmcore_opened)
pr_warn_once("Unexpected vmcore callback unregistration\n");
- vmcore_cb_unstable = true;
- }
up_write(&vmcore_cb_rwsem);
}
EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
@@ -108,8 +104,6 @@ static bool pfn_is_ram(unsigned long pfn)
bool ret = true;
lockdep_assert_held_read(&vmcore_cb_rwsem);
- if (unlikely(vmcore_cb_unstable))
- return false;
list_for_each_entry(cb, &vmcore_cb_list, next) {
if (unlikely(!cb->pfn_is_ram))
@@ -581,7 +575,7 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
* looping over all pages without a reason.
*/
down_read(&vmcore_cb_rwsem);
- if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable)
+ if (!list_empty(&vmcore_cb_list))
ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
else
ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index c43877c..505533c4 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -93,21 +93,6 @@ struct getbmapx {
#define XFS_FMR_OWN_DEFECTIVE FMR_OWNER('X', 8) /* bad blocks */
/*
- * Structure for XFS_IOC_FSSETDM.
- * For use by backup and restore programs to set the XFS on-disk inode
- * fields di_dmevmask and di_dmstate. These must be set to exactly and
- * only values previously obtained via xfs_bulkstat! (Specifically the
- * struct xfs_bstat fields bs_dmevmask and bs_dmstate.)
- */
-#ifndef HAVE_FSDMIDATA
-struct fsdmidata {
- __u32 fsd_dmevmask; /* corresponds to di_dmevmask */
- __u16 fsd_padding;
- __u16 fsd_dmstate; /* corresponds to di_dmstate */
-};
-#endif
-
-/*
* File segment locking set data type for 64 bit access.
* Also used for all the RESV/FREE interfaces.
*/
@@ -562,16 +547,10 @@ typedef struct xfs_fsop_handlereq {
/*
* Compound structures for passing args through Handle Request interfaces
- * xfs_fssetdm_by_handle, xfs_attrlist_by_handle, xfs_attrmulti_by_handle
- * - ioctls: XFS_IOC_FSSETDM_BY_HANDLE, XFS_IOC_ATTRLIST_BY_HANDLE, and
- * XFS_IOC_ATTRMULTI_BY_HANDLE
+ * xfs_attrlist_by_handle, xfs_attrmulti_by_handle
+ * - ioctls: XFS_IOC_ATTRLIST_BY_HANDLE, and XFS_IOC_ATTRMULTI_BY_HANDLE
*/
-typedef struct xfs_fsop_setdm_handlereq {
- struct xfs_fsop_handlereq hreq; /* handle information */
- struct fsdmidata __user *data; /* DMAPI data */
-} xfs_fsop_setdm_handlereq_t;
-
/*
* Flags passed in xfs_attr_multiop.am_flags for the attr ioctl interface.
*
@@ -781,15 +760,15 @@ struct xfs_scrub_metadata {
* For 'documentation' purposed more than anything else,
* the "cmd #" field reflects the IRIX fcntl number.
*/
-#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64)
-#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64)
+/* XFS_IOC_ALLOCSP ------- deprecated 10 */
+/* XFS_IOC_FREESP -------- deprecated 11 */
#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr)
#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
-#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64)
-#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64)
+/* XFS_IOC_ALLOCSP64 ----- deprecated 36 */
+/* XFS_IOC_FREESP64 ------ deprecated 37 */
#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap)
-#define XFS_IOC_FSSETDM _IOW ('X', 39, struct fsdmidata)
+/* XFS_IOC_FSSETDM ------- deprecated 39 */
#define XFS_IOC_RESVSP _IOW ('X', 40, struct xfs_flock64)
#define XFS_IOC_UNRESVSP _IOW ('X', 41, struct xfs_flock64)
#define XFS_IOC_RESVSP64 _IOW ('X', 42, struct xfs_flock64)
@@ -831,7 +810,7 @@ struct xfs_scrub_metadata {
#define XFS_IOC_FREEZE _IOWR('X', 119, int) /* aka FIFREEZE */
#define XFS_IOC_THAW _IOWR('X', 120, int) /* aka FITHAW */
-#define XFS_IOC_FSSETDM_BY_HANDLE _IOW ('X', 121, struct xfs_fsop_setdm_handlereq)
+/* XFS_IOC_FSSETDM_BY_HANDLE -- deprecated 121 */
#define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq)
#define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq)
#define XFS_IOC_FSGEOMETRY_V4 _IOR ('X', 124, struct xfs_fsop_geom_v4)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 797ea0c..d4a387d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -771,8 +771,7 @@ int
xfs_alloc_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
- xfs_off_t len,
- int alloc_type)
+ xfs_off_t len)
{
xfs_mount_t *mp = ip->i_mount;
xfs_off_t count;
@@ -865,8 +864,8 @@ xfs_alloc_file_space(
goto error;
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
- allocatesize_fsb, alloc_type, 0, imapp,
- &nimaps);
+ allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
+ &nimaps);
if (error)
goto error;
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 9f99316..24b37d2 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -54,7 +54,7 @@ int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
/* preallocation and hole punch interface */
int xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
- xfs_off_t len, int alloc_type);
+ xfs_off_t len);
int xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t len);
int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8d4c5ca..22ad207 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1051,8 +1051,7 @@ xfs_file_fallocate(
}
if (!xfs_is_always_cow_inode(ip)) {
- error = xfs_alloc_file_space(ip, offset, len,
- XFS_BMAPI_PREALLOC);
+ error = xfs_alloc_file_space(ip, offset, len);
if (error)
goto out_unlock;
}
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 2e71872..9644f93 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1854,28 +1854,20 @@ xfs_inodegc_worker(
}
/*
- * Force all currently queued inode inactivation work to run immediately, and
- * wait for the work to finish. Two pass - queue all the work first pass, wait
- * for it in a second pass.
+ * Force all currently queued inode inactivation work to run immediately and
+ * wait for the work to finish.
*/
void
xfs_inodegc_flush(
struct xfs_mount *mp)
{
- struct xfs_inodegc *gc;
- int cpu;
-
if (!xfs_is_inodegc_enabled(mp))
return;
trace_xfs_inodegc_flush(mp, __return_address);
xfs_inodegc_queue_all(mp);
-
- for_each_online_cpu(cpu) {
- gc = per_cpu_ptr(mp->m_inodegc, cpu);
- flush_work(&gc->work);
- }
+ flush_workqueue(mp->m_inodegc_wq);
}
/*
@@ -1886,18 +1878,12 @@ void
xfs_inodegc_stop(
struct xfs_mount *mp)
{
- struct xfs_inodegc *gc;
- int cpu;
-
if (!xfs_clear_inodegc_enabled(mp))
return;
xfs_inodegc_queue_all(mp);
+ drain_workqueue(mp->m_inodegc_wq);
- for_each_online_cpu(cpu) {
- gc = per_cpu_ptr(mp->m_inodegc, cpu);
- cancel_work_sync(&gc->work);
- }
trace_xfs_inodegc_stop(mp, __return_address);
}
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 8ea47a9..03a6198 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -627,87 +627,6 @@ xfs_attrmulti_by_handle(
return error;
}
-int
-xfs_ioc_space(
- struct file *filp,
- xfs_flock64_t *bf)
-{
- struct inode *inode = file_inode(filp);
- struct xfs_inode *ip = XFS_I(inode);
- struct iattr iattr;
- enum xfs_prealloc_flags flags = XFS_PREALLOC_CLEAR;
- uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
- int error;
-
- if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
- return -EPERM;
-
- if (!(filp->f_mode & FMODE_WRITE))
- return -EBADF;
-
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
- if (xfs_is_always_cow_inode(ip))
- return -EOPNOTSUPP;
-
- if (filp->f_flags & O_DSYNC)
- flags |= XFS_PREALLOC_SYNC;
- if (filp->f_mode & FMODE_NOCMTIME)
- flags |= XFS_PREALLOC_INVISIBLE;
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
-
- xfs_ilock(ip, iolock);
- error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
- if (error)
- goto out_unlock;
- inode_dio_wait(inode);
-
- switch (bf->l_whence) {
- case 0: /*SEEK_SET*/
- break;
- case 1: /*SEEK_CUR*/
- bf->l_start += filp->f_pos;
- break;
- case 2: /*SEEK_END*/
- bf->l_start += XFS_ISIZE(ip);
- break;
- default:
- error = -EINVAL;
- goto out_unlock;
- }
-
- if (bf->l_start < 0 || bf->l_start > inode->i_sb->s_maxbytes) {
- error = -EINVAL;
- goto out_unlock;
- }
-
- if (bf->l_start > XFS_ISIZE(ip)) {
- error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
- bf->l_start - XFS_ISIZE(ip),
- XFS_BMAPI_PREALLOC);
- if (error)
- goto out_unlock;
- }
-
- iattr.ia_valid = ATTR_SIZE;
- iattr.ia_size = bf->l_start;
- error = xfs_vn_setattr_size(file_mnt_user_ns(filp), file_dentry(filp),
- &iattr);
- if (error)
- goto out_unlock;
-
- error = xfs_update_prealloc_flags(ip, flags);
-
-out_unlock:
- xfs_iunlock(ip, iolock);
- mnt_drop_write_file(filp);
- return error;
-}
-
/* Return 0 on success or positive error */
int
xfs_fsbulkstat_one_fmt(
@@ -1936,6 +1855,15 @@ xfs_fs_eofblocks_from_user(
}
/*
+ * These long-unused ioctls were removed from the official ioctl API in 5.17,
+ * but retain these definitions so that we can log warnings about them.
+ */
+#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64)
+#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64)
+#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64)
+#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64)
+
+/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
* So we don't "sign flip" like most other routines. This means
@@ -1965,13 +1893,11 @@ xfs_file_ioctl(
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_ALLOCSP64:
- case XFS_IOC_FREESP64: {
- xfs_flock64_t bf;
-
- if (copy_from_user(&bf, arg, sizeof(bf)))
- return -EFAULT;
- return xfs_ioc_space(filp, &bf);
- }
+ case XFS_IOC_FREESP64:
+ xfs_warn_once(mp,
+ "%s should use fallocate; XFS_IOC_{ALLOC,FREE}SP ioctl unsupported",
+ current->comm);
+ return -ENOTTY;
case XFS_IOC_DIOINFO: {
struct xfs_buftarg *target = xfs_inode_buftarg(ip);
struct dioattr da;
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 845d3bc..d4abba2 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -10,12 +10,6 @@ struct xfs_bstat;
struct xfs_ibulk;
struct xfs_inogrp;
-
-extern int
-xfs_ioc_space(
- struct file *filp,
- xfs_flock64_t *bf);
-
int
xfs_ioc_swapext(
xfs_swapext_t *sxp);
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 8783af2..004ed2a 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -28,22 +28,6 @@
#ifdef BROKEN_X86_ALIGNMENT
STATIC int
-xfs_compat_flock64_copyin(
- xfs_flock64_t *bf,
- compat_xfs_flock64_t __user *arg32)
-{
- if (get_user(bf->l_type, &arg32->l_type) ||
- get_user(bf->l_whence, &arg32->l_whence) ||
- get_user(bf->l_start, &arg32->l_start) ||
- get_user(bf->l_len, &arg32->l_len) ||
- get_user(bf->l_sysid, &arg32->l_sysid) ||
- get_user(bf->l_pid, &arg32->l_pid) ||
- copy_from_user(bf->l_pad, &arg32->l_pad, 4*sizeof(u32)))
- return -EFAULT;
- return 0;
-}
-
-STATIC int
xfs_compat_ioc_fsgeometry_v1(
struct xfs_mount *mp,
compat_xfs_fsop_geom_v1_t __user *arg32)
@@ -445,17 +429,6 @@ xfs_file_compat_ioctl(
switch (cmd) {
#if defined(BROKEN_X86_ALIGNMENT)
- case XFS_IOC_ALLOCSP_32:
- case XFS_IOC_FREESP_32:
- case XFS_IOC_ALLOCSP64_32:
- case XFS_IOC_FREESP64_32: {
- struct xfs_flock64 bf;
-
- if (xfs_compat_flock64_copyin(&bf, arg))
- return -EFAULT;
- cmd = _NATIVE_IOC(cmd, struct xfs_flock64);
- return xfs_ioc_space(filp, &bf);
- }
case XFS_IOC_FSGEOMETRY_V1_32:
return xfs_compat_ioc_fsgeometry_v1(ip->i_mount, arg);
case XFS_IOC_FSGROWFSDATA_32: {
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 9929482..c148523 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -142,28 +142,6 @@ typedef struct compat_xfs_fsop_attrmulti_handlereq {
_IOW('X', 123, struct compat_xfs_fsop_attrmulti_handlereq)
#ifdef BROKEN_X86_ALIGNMENT
-/* on ia32 l_start is on a 32-bit boundary */
-typedef struct compat_xfs_flock64 {
- __s16 l_type;
- __s16 l_whence;
- __s64 l_start __attribute__((packed));
- /* len == 0 means until end of file */
- __s64 l_len __attribute__((packed));
- __s32 l_sysid;
- __u32 l_pid;
- __s32 l_pad[4]; /* reserve area */
-} compat_xfs_flock64_t;
-
-#define XFS_IOC_ALLOCSP_32 _IOW('X', 10, struct compat_xfs_flock64)
-#define XFS_IOC_FREESP_32 _IOW('X', 11, struct compat_xfs_flock64)
-#define XFS_IOC_ALLOCSP64_32 _IOW('X', 36, struct compat_xfs_flock64)
-#define XFS_IOC_FREESP64_32 _IOW('X', 37, struct compat_xfs_flock64)
-#define XFS_IOC_RESVSP_32 _IOW('X', 40, struct compat_xfs_flock64)
-#define XFS_IOC_UNRESVSP_32 _IOW('X', 41, struct compat_xfs_flock64)
-#define XFS_IOC_RESVSP64_32 _IOW('X', 42, struct compat_xfs_flock64)
-#define XFS_IOC_UNRESVSP64_32 _IOW('X', 43, struct compat_xfs_flock64)
-#define XFS_IOC_ZERO_RANGE_32 _IOW('X', 57, struct compat_xfs_flock64)
-
typedef struct compat_xfs_fsop_geom_v1 {
__u32 blocksize; /* filesystem (data) block size */
__u32 rtextsize; /* realtime extent size */
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 3d503e7..fd7e8fb 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -285,7 +285,7 @@ do { \
* write-combining memory accesses before this macro with those after it.
*/
#ifndef io_stop_wc
-#define io_stop_wc do { } while (0)
+#define io_stop_wc() do { } while (0)
#endif
#endif /* !__ASSEMBLY__ */
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 02932ef..977bea1 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -147,6 +147,15 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
#if CONFIG_PGTABLE_LEVELS > 3
+static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ gfp_t gfp = GFP_PGTABLE_USER;
+
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+ return (pud_t *)get_zeroed_page(gfp);
+}
+
#ifndef __HAVE_ARCH_PUD_ALLOC_ONE
/**
* pud_alloc_one - allocate a page for PUD-level page table
@@ -159,20 +168,23 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
*/
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- gfp_t gfp = GFP_PGTABLE_USER;
-
- if (mm == &init_mm)
- gfp = GFP_PGTABLE_KERNEL;
- return (pud_t *)get_zeroed_page(gfp);
+ return __pud_alloc_one(mm, addr);
}
#endif
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
{
BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
free_page((unsigned long)pud);
}
+#ifndef __HAVE_ARCH_PUD_FREE
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+ __pud_free(mm, pud);
+}
+#endif
+
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
#ifndef __HAVE_ARCH_PGD_FREE
diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h
index df3c6c2..f9ffd39 100644
--- a/include/crypto/blake2s.h
+++ b/include/crypto/blake2s.h
@@ -101,7 +101,4 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
blake2s_final(&state, out);
}
-void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
- const size_t keylen);
-
#endif /* _CRYPTO_BLAKE2S_H */
diff --git a/include/kunit/assert.h b/include/kunit/assert.h
index ad889b5..ccbc36c 100644
--- a/include/kunit/assert.h
+++ b/include/kunit/assert.h
@@ -10,7 +10,7 @@
#define _KUNIT_ASSERT_H
#include <linux/err.h>
-#include <linux/kernel.h>
+#include <linux/printk.h>
struct kunit;
struct string_stream;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6e947cd..fa517ae6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -316,7 +316,12 @@ enum bpf_type_flag {
*/
MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS),
- __BPF_TYPE_LAST_FLAG = MEM_RDONLY,
+ /* MEM was "allocated" from a different helper, and cannot be mixed
+ * with regular non-MEM_ALLOC'ed MEM types.
+ */
+ MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS),
+
+ __BPF_TYPE_LAST_FLAG = MEM_ALLOC,
};
/* Max number of base types. */
@@ -400,7 +405,7 @@ enum bpf_return_type {
RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET,
RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
- RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
+ RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
/* This must be the last entry. Its purpose is to ensure the enum is
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 143401d..e999317 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -519,8 +519,8 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
void
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
-int check_ctx_reg(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno);
+int check_ptr_off_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno);
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno, u32 mem_size);
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 309acbc..6a89ea4 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -295,12 +295,13 @@ extern bool libceph_compatible(void *data);
extern const char *ceph_msg_type_name(int type);
extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+extern int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid);
struct fs_parameter;
struct fc_log;
struct ceph_options *ceph_alloc_options(void);
int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt,
- struct fc_log *l);
+ struct fc_log *l, char delim);
int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
struct fc_log *l);
int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 0e6e9ad..ff99ce0 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -532,7 +532,7 @@ extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr);
extern int ceph_parse_ips(const char *c, const char *end,
struct ceph_entity_addr *addr,
- int max_count, int *count);
+ int max_count, int *count, char delim);
extern int ceph_msgr_init(void);
extern void ceph_msgr_exit(void);
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index af7e6eb..3e03d01 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -9,18 +9,9 @@
#include <uapi/linux/taskstats.h>
-/*
- * Per-task flags relevant to delay accounting
- * maintained privately to avoid exhausting similar flags in sched.h:PF_*
- * Used to set current->delays->flags
- */
-#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */
-#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */
-
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
raw_spinlock_t lock;
- unsigned int flags; /* Private per-task flags */
/* For each stat XXX, add following, aligned appropriately
*
@@ -37,13 +28,13 @@ struct task_delay_info {
* associated with the operation is added to XXX_delay.
* XXX_delay contains the accumulated delay time in nanoseconds.
*/
- u64 blkio_start; /* Shared by blkio, swapin */
+ u64 blkio_start;
u64 blkio_delay; /* wait for sync block io completion */
- u64 swapin_delay; /* wait for swapin block io completion */
+ u64 swapin_start;
+ u64 swapin_delay; /* wait for swapin */
u32 blkio_count; /* total count of the number of sync block */
/* io operations performed */
- u32 swapin_count; /* total count of the number of swapin block */
- /* io operations performed */
+ u32 swapin_count; /* total count of swapin */
u64 freepages_start;
u64 freepages_delay; /* wait for memory reclaim */
@@ -51,8 +42,12 @@ struct task_delay_info {
u64 thrashing_start;
u64 thrashing_delay; /* wait for thrashing page */
+ u64 compact_start;
+ u64 compact_delay; /* wait for memory compact */
+
u32 freepages_count; /* total count of memory reclaim */
u32 thrashing_count; /* total count of thrash waits */
+ u32 compact_count; /* total count of memory compact */
};
#endif
@@ -79,26 +74,10 @@ extern void __delayacct_freepages_start(void);
extern void __delayacct_freepages_end(void);
extern void __delayacct_thrashing_start(void);
extern void __delayacct_thrashing_end(void);
-
-static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
-{
- if (p->delays)
- return (p->delays->flags & DELAYACCT_PF_BLKIO);
- else
- return 0;
-}
-
-static inline void delayacct_set_flag(struct task_struct *p, int flag)
-{
- if (p->delays)
- p->delays->flags |= flag;
-}
-
-static inline void delayacct_clear_flag(struct task_struct *p, int flag)
-{
- if (p->delays)
- p->delays->flags &= ~flag;
-}
+extern void __delayacct_swapin_start(void);
+extern void __delayacct_swapin_end(void);
+extern void __delayacct_compact_start(void);
+extern void __delayacct_compact_end(void);
static inline void delayacct_tsk_init(struct task_struct *tsk)
{
@@ -123,7 +102,6 @@ static inline void delayacct_blkio_start(void)
if (!static_branch_unlikely(&delayacct_key))
return;
- delayacct_set_flag(current, DELAYACCT_PF_BLKIO);
if (current->delays)
__delayacct_blkio_start();
}
@@ -135,7 +113,6 @@ static inline void delayacct_blkio_end(struct task_struct *p)
if (p->delays)
__delayacct_blkio_end(p);
- delayacct_clear_flag(p, DELAYACCT_PF_BLKIO);
}
static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk)
@@ -147,33 +124,77 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk)
static inline void delayacct_freepages_start(void)
{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
if (current->delays)
__delayacct_freepages_start();
}
static inline void delayacct_freepages_end(void)
{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
if (current->delays)
__delayacct_freepages_end();
}
static inline void delayacct_thrashing_start(void)
{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
if (current->delays)
__delayacct_thrashing_start();
}
static inline void delayacct_thrashing_end(void)
{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
if (current->delays)
__delayacct_thrashing_end();
}
+static inline void delayacct_swapin_start(void)
+{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
+ if (current->delays)
+ __delayacct_swapin_start();
+}
+
+static inline void delayacct_swapin_end(void)
+{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
+ if (current->delays)
+ __delayacct_swapin_end();
+}
+
+static inline void delayacct_compact_start(void)
+{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
+ if (current->delays)
+ __delayacct_compact_start();
+}
+
+static inline void delayacct_compact_end(void)
+{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
+ if (current->delays)
+ __delayacct_compact_end();
+}
+
#else
-static inline void delayacct_set_flag(struct task_struct *p, int flag)
-{}
-static inline void delayacct_clear_flag(struct task_struct *p, int flag)
-{}
static inline void delayacct_init(void)
{}
static inline void delayacct_tsk_init(struct task_struct *tsk)
@@ -199,6 +220,14 @@ static inline void delayacct_thrashing_start(void)
{}
static inline void delayacct_thrashing_end(void)
{}
+static inline void delayacct_swapin_start(void)
+{}
+static inline void delayacct_swapin_end(void)
+{}
+static inline void delayacct_compact_start(void)
+{}
+static inline void delayacct_compact_end(void)
+{}
#endif /* CONFIG_TASK_DELAY_ACCT */
diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h
index 83a1377..02a4adf 100644
--- a/include/linux/dma/xilinx_dpdma.h
+++ b/include/linux/dma/xilinx_dpdma.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_DMA_XILINX_DPDMA_H
#define __LINUX_DMA_XILINX_DPDMA_H
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 0349b35..842d4f7 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -50,6 +50,7 @@ enum dma_status {
*/
enum dma_transaction_type {
DMA_MEMCPY,
+ DMA_MEMCPY_SG,
DMA_XOR,
DMA_PQ,
DMA_XOR_VAL,
@@ -887,6 +888,11 @@ struct dma_device {
struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
size_t len, unsigned long flags);
+ struct dma_async_tx_descriptor *(*device_prep_dma_memcpy_sg)(
+ struct dma_chan *chan,
+ struct scatterlist *dst_sg, unsigned int dst_nents,
+ struct scatterlist *src_sg, unsigned int src_nents,
+ unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
unsigned int src_cnt, size_t len, unsigned long flags);
@@ -1047,6 +1053,20 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy(
len, flags);
}
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy_sg(
+ struct dma_chan *chan,
+ struct scatterlist *dst_sg, unsigned int dst_nents,
+ struct scatterlist *src_sg, unsigned int src_nents,
+ unsigned long flags)
+{
+ if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy_sg)
+ return NULL;
+
+ return chan->device->device_prep_dma_memcpy_sg(chan, dst_sg, dst_nents,
+ src_sg, src_nents,
+ flags);
+}
+
static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan,
enum dma_desc_metadata_mode mode)
{
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0de9fb1..ccd4d3f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -148,6 +148,52 @@ typedef struct {
u32 imagesize;
} efi_capsule_header_t;
+/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER */
+struct efi_manage_capsule_header {
+ u32 ver;
+ u16 emb_drv_cnt;
+ u16 payload_cnt;
+ /*
+ * Variable-size array of the size given by the sum of
+ * emb_drv_cnt and payload_cnt.
+ */
+ u64 offset_list[];
+} __packed;
+
+/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER */
+struct efi_manage_capsule_image_header {
+ u32 ver;
+ efi_guid_t image_type_id;
+ u8 image_index;
+ u8 reserved_bytes[3];
+ u32 image_size;
+ u32 vendor_code_size;
+ /* hw_ins was introduced in version 2 */
+ u64 hw_ins;
+ /* capsule_support was introduced in version 3 */
+ u64 capsule_support;
+} __packed;
+
+/* WIN_CERTIFICATE */
+struct win_cert {
+ u32 len;
+ u16 rev;
+ u16 cert_type;
+};
+
+/* WIN_CERTIFICATE_UEFI_GUID */
+struct win_cert_uefi_guid {
+ struct win_cert hdr;
+ efi_guid_t cert_type;
+ u8 cert_data[];
+};
+
+/* EFI_FIRMWARE_IMAGE_AUTHENTICATION */
+struct efi_image_auth {
+ u64 mon_count;
+ struct win_cert_uefi_guid auth_info;
+};
+
/*
* EFI capsule flags
*/
diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h
index e272c3d..54feb64 100644
--- a/include/linux/elfcore-compat.h
+++ b/include/linux/elfcore-compat.h
@@ -43,6 +43,11 @@ struct compat_elf_prpsinfo
__compat_uid_t pr_uid;
__compat_gid_t pr_gid;
compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid;
+ /*
+ * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be
+ * changed as it is exposed to userspace. We'd better make it hard-coded
+ * here.
+ */
char pr_fname[16];
char pr_psargs[ELF_PRARGSZ];
};
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 957ebec..746e081 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -65,6 +65,11 @@ struct elf_prpsinfo
__kernel_gid_t pr_gid;
pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid;
/* Lots missing */
+ /*
+ * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be
+ * changed as it is exposed to userspace. We'd better make it hard-coded
+ * here.
+ */
char pr_fname[16]; /* filename of executable */
char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */
};
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index ede5040..296c5f1 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -665,6 +665,11 @@ static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie,
static inline
void fscache_note_page_release(struct fscache_cookie *cookie)
{
+ /* If we've written data to the cache (HAVE_DATA) and there wasn't any
+ * data in the cache when we started (NO_DATA_TO_READ), it may no
+ * longer be true that we can skip reading from the cache - so clear
+ * the flag that causes reads to be skipped.
+ */
if (cookie &&
test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) &&
test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags))
diff --git a/include/linux/hash.h b/include/linux/hash.h
index ad6fa21..38edaa0 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val)
return val * GOLDEN_RATIO_32;
}
-#ifndef HAVE_ARCH_HASH_32
-#define hash_32 hash_32_generic
-#endif
-static inline u32 hash_32_generic(u32 val, unsigned int bits)
+static inline u32 hash_32(u32 val, unsigned int bits)
{
/* High bits are more random, so use them. */
return __hash_32(val) >> (32 - bits);
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 055eb20..33f47a9 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -1,4 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NOTE:
+ *
+ * This header has combined a lot of unrelated to each other stuff.
+ * The process of splitting its content is in progress while keeping
+ * backward compatibility. That's why it's highly recommended NOT to
+ * include this header inside another header file, especially under
+ * generic or architectural include/ directory.
+ */
#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index b6c8aafa..3df4ea0 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -33,6 +33,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
unsigned int cpu,
const char *namefmt);
+void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk);
bool set_kthread_struct(struct task_struct *p);
void kthread_set_per_cpu(struct task_struct *k, int cpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d89d564..06912d6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -309,9 +309,6 @@ struct kvm_vcpu {
u64 requests;
unsigned long guest_debug;
- int pre_pcpu;
- struct list_head blocked_vcpu_list;
-
struct mutex mutex;
struct kvm_run *run;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 2a8404b..605756f 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -39,25 +39,9 @@
* compile-time options: to be removed as soon as all the drivers are
* converted to the new debugging mechanism
*/
-#undef ATA_DEBUG /* debugging output */
-#undef ATA_VERBOSE_DEBUG /* yet more debugging output */
#undef ATA_IRQ_TRAP /* define to ack screaming irqs */
-#undef ATA_NDEBUG /* define to disable quick runtime checks */
-/* note: prints function name for you */
-#ifdef ATA_DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args)
-#ifdef ATA_VERBOSE_DEBUG
-#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args)
-#else
-#define VPRINTK(fmt, args...)
-#endif /* ATA_VERBOSE_DEBUG */
-#else
-#define DPRINTK(fmt, args...)
-#define VPRINTK(fmt, args...)
-#endif /* ATA_DEBUG */
-
#define ata_print_version_once(dev, version) \
({ \
static bool __print_once; \
@@ -68,38 +52,6 @@
} \
})
-/* NEW: debug levels */
-#define HAVE_LIBATA_MSG 1
-
-enum {
- ATA_MSG_DRV = 0x0001,
- ATA_MSG_INFO = 0x0002,
- ATA_MSG_PROBE = 0x0004,
- ATA_MSG_WARN = 0x0008,
- ATA_MSG_MALLOC = 0x0010,
- ATA_MSG_CTL = 0x0020,
- ATA_MSG_INTR = 0x0040,
- ATA_MSG_ERR = 0x0080,
-};
-
-#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV)
-#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO)
-#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE)
-#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN)
-#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC)
-#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL)
-#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR)
-#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR)
-
-static inline u32 ata_msg_init(int dval, int default_msg_enable_bits)
-{
- if (dval < 0 || dval >= (sizeof(u32) * 8))
- return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */
- if (!dval)
- return 0;
- return (1 << dval) - 1;
-}
-
/* defines only for the constants which don't work well as enums */
#define ATA_TAG_POISON 0xfafbfcfdU
@@ -191,7 +143,7 @@ enum {
ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */
ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */
ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */
- ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */
+ ATA_LFLAG_NO_DEBOUNCE_DELAY = (1 << 11), /* no debounce delay on link resume */
/* struct ata_port flags */
ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */
@@ -884,7 +836,6 @@ struct ata_port {
unsigned int hsm_task_state;
- u32 msg_enable;
struct list_head eh_done_q;
wait_queue_head_t eh_wait_q;
int eh_tries;
@@ -933,7 +884,8 @@ struct ata_port_operations {
void (*set_piomode)(struct ata_port *ap, struct ata_device *dev);
void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev);
int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev);
- unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id);
+ unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf,
+ __le16 *id);
void (*dev_config)(struct ata_device *dev);
@@ -1160,13 +1112,15 @@ extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc);
extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
unsigned int n_elem);
extern unsigned int ata_dev_classify(const struct ata_taskfile *tf);
+extern unsigned int ata_port_classify(struct ata_port *ap,
+ const struct ata_taskfile *tf);
extern void ata_dev_disable(struct ata_device *adev);
extern void ata_id_string(const u16 *id, unsigned char *s,
unsigned int ofs, unsigned int len);
extern void ata_id_c_string(const u16 *id, unsigned char *s,
unsigned int ofs, unsigned int len);
extern unsigned int ata_do_dev_read_id(struct ata_device *dev,
- struct ata_taskfile *tf, u16 *id);
+ struct ata_taskfile *tf, __le16 *id);
extern void ata_qc_complete(struct ata_queued_cmd *qc);
extern u64 ata_qc_get_active(struct ata_port *ap);
extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
@@ -1432,6 +1386,12 @@ extern const struct attribute_group *ata_common_sdev_groups[];
.tag_alloc_policy = BLK_TAG_ALLOC_RR, \
.slave_configure = ata_scsi_slave_config
+#define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \
+ __ATA_BASE_SHT(drv_name), \
+ .can_queue = drv_qd, \
+ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \
+ .slave_configure = ata_scsi_slave_config
+
#define ATA_BASE_SHT(drv_name) \
ATA_SUBBASE_SHT(drv_name), \
.sdev_groups = ata_common_sdev_groups
@@ -1443,6 +1403,11 @@ extern const struct attribute_group *ata_ncq_sdev_groups[];
ATA_SUBBASE_SHT(drv_name), \
.sdev_groups = ata_ncq_sdev_groups, \
.change_queue_depth = ata_scsi_change_queue_depth
+
+#define ATA_NCQ_SHT_QD(drv_name, drv_qd) \
+ ATA_SUBBASE_SHT_QD(drv_name, drv_qd), \
+ .sdev_groups = ata_ncq_sdev_groups, \
+ .change_queue_depth = ata_scsi_change_queue_depth
#endif
/*
@@ -1487,51 +1452,61 @@ static inline int sata_srst_pmp(struct ata_link *link)
return link->pmp;
}
-/*
- * printk helpers
- */
-__printf(3, 4)
-void ata_port_printk(const struct ata_port *ap, const char *level,
- const char *fmt, ...);
-__printf(3, 4)
-void ata_link_printk(const struct ata_link *link, const char *level,
- const char *fmt, ...);
-__printf(3, 4)
-void ata_dev_printk(const struct ata_device *dev, const char *level,
- const char *fmt, ...);
+#define ata_port_printk(level, ap, fmt, ...) \
+ pr_ ## level ("ata%u: " fmt, (ap)->print_id, ##__VA_ARGS__)
#define ata_port_err(ap, fmt, ...) \
- ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__)
+ ata_port_printk(err, ap, fmt, ##__VA_ARGS__)
#define ata_port_warn(ap, fmt, ...) \
- ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__)
+ ata_port_printk(warn, ap, fmt, ##__VA_ARGS__)
#define ata_port_notice(ap, fmt, ...) \
- ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__)
+ ata_port_printk(notice, ap, fmt, ##__VA_ARGS__)
#define ata_port_info(ap, fmt, ...) \
- ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__)
+ ata_port_printk(info, ap, fmt, ##__VA_ARGS__)
#define ata_port_dbg(ap, fmt, ...) \
- ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__)
+ ata_port_printk(debug, ap, fmt, ##__VA_ARGS__)
+
+#define ata_link_printk(level, link, fmt, ...) \
+do { \
+ if (sata_pmp_attached((link)->ap) || \
+ (link)->ap->slave_link) \
+ pr_ ## level ("ata%u.%02u: " fmt, \
+ (link)->ap->print_id, \
+ (link)->pmp, \
+ ##__VA_ARGS__); \
+ else \
+ pr_ ## level ("ata%u: " fmt, \
+ (link)->ap->print_id, \
+ ##__VA_ARGS__); \
+} while (0)
#define ata_link_err(link, fmt, ...) \
- ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__)
+ ata_link_printk(err, link, fmt, ##__VA_ARGS__)
#define ata_link_warn(link, fmt, ...) \
- ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__)
+ ata_link_printk(warn, link, fmt, ##__VA_ARGS__)
#define ata_link_notice(link, fmt, ...) \
- ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__)
+ ata_link_printk(notice, link, fmt, ##__VA_ARGS__)
#define ata_link_info(link, fmt, ...) \
- ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__)
+ ata_link_printk(info, link, fmt, ##__VA_ARGS__)
#define ata_link_dbg(link, fmt, ...) \
- ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__)
+ ata_link_printk(debug, link, fmt, ##__VA_ARGS__)
+
+#define ata_dev_printk(level, dev, fmt, ...) \
+ pr_ ## level("ata%u.%02u: " fmt, \
+ (dev)->link->ap->print_id, \
+ (dev)->link->pmp + (dev)->devno, \
+ ##__VA_ARGS__)
#define ata_dev_err(dev, fmt, ...) \
- ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__)
+ ata_dev_printk(err, dev, fmt, ##__VA_ARGS__)
#define ata_dev_warn(dev, fmt, ...) \
- ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__)
+ ata_dev_printk(warn, dev, fmt, ##__VA_ARGS__)
#define ata_dev_notice(dev, fmt, ...) \
- ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__)
+ ata_dev_printk(notice, dev, fmt, ##__VA_ARGS__)
#define ata_dev_info(dev, fmt, ...) \
- ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__)
+ ata_dev_printk(info, dev, fmt, ##__VA_ARGS__)
#define ata_dev_dbg(dev, fmt, ...) \
- ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__)
+ ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__)
void ata_print_version(const struct device *dev, const char *version);
@@ -2065,11 +2040,8 @@ static inline u8 ata_wait_idle(struct ata_port *ap)
{
u8 status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000);
-#ifdef ATA_DEBUG
if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ)))
- ata_port_printk(ap, KERN_DEBUG, "abnormal Status 0x%X\n",
- status);
-#endif
+ ata_port_dbg(ap, "abnormal Status 0x%X\n", status);
return status;
}
diff --git a/include/linux/list.h b/include/linux/list.h
index 6636fc0..dd6c204 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -258,8 +258,7 @@ static inline void list_bulk_move_tail(struct list_head *head,
* @list: the entry to test
* @head: the head of the list
*/
-static inline int list_is_first(const struct list_head *list,
- const struct list_head *head)
+static inline int list_is_first(const struct list_head *list, const struct list_head *head)
{
return list->prev == head;
}
@@ -269,13 +268,22 @@ static inline int list_is_first(const struct list_head *list,
* @list: the entry to test
* @head: the head of the list
*/
-static inline int list_is_last(const struct list_head *list,
- const struct list_head *head)
+static inline int list_is_last(const struct list_head *list, const struct list_head *head)
{
return list->next == head;
}
/**
+ * list_is_head - tests whether @list is the list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_head(const struct list_head *list, const struct list_head *head)
+{
+ return list == head;
+}
+
+/**
* list_empty - tests whether a list is empty
* @head: the list to test.
*/
@@ -318,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry)
static inline int list_empty_careful(const struct list_head *head)
{
struct list_head *next = smp_load_acquire(&head->next);
- return (next == head) && (next == head->prev);
+ return list_is_head(next, head) && (next == head->prev);
}
/**
@@ -393,10 +401,9 @@ static inline void list_cut_position(struct list_head *list,
{
if (list_empty(head))
return;
- if (list_is_singular(head) &&
- (head->next != entry && head != entry))
+ if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next))
return;
- if (entry == head)
+ if (list_is_head(entry, head))
INIT_LIST_HEAD(list);
else
__list_cut_position(list, head, entry);
@@ -570,7 +577,7 @@ static inline void list_splice_tail_init(struct list_head *list,
* @head: the head for your list.
*/
#define list_for_each(pos, head) \
- for (pos = (head)->next; pos != (head); pos = pos->next)
+ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
/**
* list_for_each_continue - continue iteration over a list
@@ -580,7 +587,7 @@ static inline void list_splice_tail_init(struct list_head *list,
* Continue to iterate over a list, continuing after the current position.
*/
#define list_for_each_continue(pos, head) \
- for (pos = pos->next; pos != (head); pos = pos->next)
+ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next)
/**
* list_for_each_prev - iterate over a list backwards
@@ -588,7 +595,7 @@ static inline void list_splice_tail_init(struct list_head *list,
* @head: the head for your list.
*/
#define list_for_each_prev(pos, head) \
- for (pos = (head)->prev; pos != (head); pos = pos->prev)
+ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev)
/**
* list_for_each_safe - iterate over a list safe against removal of list entry
@@ -597,8 +604,9 @@ static inline void list_splice_tail_init(struct list_head *list,
* @head: the head for your list.
*/
#define list_for_each_safe(pos, n, head) \
- for (pos = (head)->next, n = pos->next; pos != (head); \
- pos = n, n = pos->next)
+ for (pos = (head)->next, n = pos->next; \
+ !list_is_head(pos, (head)); \
+ pos = n, n = pos->next)
/**
* list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
@@ -608,7 +616,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_prev_safe(pos, n, head) \
for (pos = (head)->prev, n = pos->prev; \
- pos != (head); \
+ !list_is_head(pos, (head)); \
pos = n, n = pos->prev)
/**
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index 0661af1..808bb4c 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -123,7 +123,11 @@ struct cmos_rtc_board_info {
#define RTC_IO_EXTENT_USED RTC_IO_EXTENT
#endif /* ARCH_RTC_LOCATION */
-unsigned int mc146818_get_time(struct rtc_time *time);
+bool mc146818_does_rtc_work(void);
+int mc146818_get_time(struct rtc_time *time);
int mc146818_set_time(struct rtc_time *time);
+bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+ void *param);
+
#endif /* _MC146818RTC_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index aa47705..e1a84b1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1199,6 +1199,26 @@ static inline void folio_put(struct folio *folio)
__put_page(&folio->page);
}
+/**
+ * folio_put_refs - Reduce the reference count on a folio.
+ * @folio: The folio.
+ * @refs: The amount to subtract from the folio's reference count.
+ *
+ * If the folio's reference count reaches zero, the memory will be
+ * released back to the page allocator and may be used by another
+ * allocation immediately. Do not access the memory or the struct folio
+ * after calling folio_put_refs() unless you can be sure that these weren't
+ * the last references.
+ *
+ * Context: May be called in process or interrupt context, but not in NMI
+ * context. May be called while holding a spinlock.
+ */
+static inline void folio_put_refs(struct folio *folio, int refs)
+{
+ if (folio_ref_sub_and_test(folio, refs))
+ __put_page(&folio->page);
+}
+
static inline void put_page(struct page *page)
{
struct folio *folio = page_folio(page);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3764c1b..9db36dc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -119,31 +119,6 @@ struct page {
atomic_long_t pp_frag_count;
};
};
- struct { /* slab, slob and slub */
- union {
- struct list_head slab_list;
- struct { /* Partial pages */
- struct page *next;
-#ifdef CONFIG_64BIT
- int pages; /* Nr of pages left */
-#else
- short int pages;
-#endif
- };
- };
- struct kmem_cache *slab_cache; /* not slob */
- /* Double-word boundary */
- void *freelist; /* first free object */
- union {
- void *s_mem; /* slab: first object */
- unsigned long counters; /* SLUB */
- struct { /* SLUB */
- unsigned inuse:16;
- unsigned objects:15;
- unsigned frozen:1;
- };
- };
- };
struct { /* Tail pages of compound page */
unsigned long compound_head; /* Bit zero is set */
@@ -207,9 +182,6 @@ struct page {
* which are currently stored here.
*/
unsigned int page_type;
-
- unsigned int active; /* SLAB */
- int units; /* SLOB */
};
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
diff --git a/include/linux/of.h b/include/linux/of.h
index ff143a0..2dc7743 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -364,18 +364,12 @@ extern const struct of_device_id *of_match_node(
const struct of_device_id *matches, const struct device_node *node);
extern int of_modalias_node(struct device_node *node, char *modalias, int len);
extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args);
-extern struct device_node *of_parse_phandle(const struct device_node *np,
- const char *phandle_name,
- int index);
-extern int of_parse_phandle_with_args(const struct device_node *np,
- const char *list_name, const char *cells_name, int index,
- struct of_phandle_args *out_args);
+extern int __of_parse_phandle_with_args(const struct device_node *np,
+ const char *list_name, const char *cells_name, int cell_count,
+ int index, struct of_phandle_args *out_args);
extern int of_parse_phandle_with_args_map(const struct device_node *np,
const char *list_name, const char *stem_name, int index,
struct of_phandle_args *out_args);
-extern int of_parse_phandle_with_fixed_args(const struct device_node *np,
- const char *list_name, int cells_count, int index,
- struct of_phandle_args *out_args);
extern int of_count_phandle_with_args(const struct device_node *np,
const char *list_name, const char *cells_name);
@@ -416,130 +410,6 @@ extern int of_detach_node(struct device_node *);
#define of_match_ptr(_ptr) (_ptr)
-/**
- * of_property_read_u8_array - Find and read an array of u8 from a property.
- *
- * @np: device node from which the property value is to be read.
- * @propname: name of the property to be searched.
- * @out_values: pointer to return value, modified only if return value is 0.
- * @sz: number of array elements to read
- *
- * Search for a property in a device node and read 8-bit value(s) from
- * it.
- *
- * dts entry of array should be like:
- * ``property = /bits/ 8 <0x50 0x60 0x70>;``
- *
- * Return: 0 on success, -EINVAL if the property does not exist,
- * -ENODATA if property does not have a value, and -EOVERFLOW if the
- * property data isn't large enough.
- *
- * The out_values is modified only if a valid u8 value can be decoded.
- */
-static inline int of_property_read_u8_array(const struct device_node *np,
- const char *propname,
- u8 *out_values, size_t sz)
-{
- int ret = of_property_read_variable_u8_array(np, propname, out_values,
- sz, 0);
- if (ret >= 0)
- return 0;
- else
- return ret;
-}
-
-/**
- * of_property_read_u16_array - Find and read an array of u16 from a property.
- *
- * @np: device node from which the property value is to be read.
- * @propname: name of the property to be searched.
- * @out_values: pointer to return value, modified only if return value is 0.
- * @sz: number of array elements to read
- *
- * Search for a property in a device node and read 16-bit value(s) from
- * it.
- *
- * dts entry of array should be like:
- * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;``
- *
- * Return: 0 on success, -EINVAL if the property does not exist,
- * -ENODATA if property does not have a value, and -EOVERFLOW if the
- * property data isn't large enough.
- *
- * The out_values is modified only if a valid u16 value can be decoded.
- */
-static inline int of_property_read_u16_array(const struct device_node *np,
- const char *propname,
- u16 *out_values, size_t sz)
-{
- int ret = of_property_read_variable_u16_array(np, propname, out_values,
- sz, 0);
- if (ret >= 0)
- return 0;
- else
- return ret;
-}
-
-/**
- * of_property_read_u32_array - Find and read an array of 32 bit integers
- * from a property.
- *
- * @np: device node from which the property value is to be read.
- * @propname: name of the property to be searched.
- * @out_values: pointer to return value, modified only if return value is 0.
- * @sz: number of array elements to read
- *
- * Search for a property in a device node and read 32-bit value(s) from
- * it.
- *
- * Return: 0 on success, -EINVAL if the property does not exist,
- * -ENODATA if property does not have a value, and -EOVERFLOW if the
- * property data isn't large enough.
- *
- * The out_values is modified only if a valid u32 value can be decoded.
- */
-static inline int of_property_read_u32_array(const struct device_node *np,
- const char *propname,
- u32 *out_values, size_t sz)
-{
- int ret = of_property_read_variable_u32_array(np, propname, out_values,
- sz, 0);
- if (ret >= 0)
- return 0;
- else
- return ret;
-}
-
-/**
- * of_property_read_u64_array - Find and read an array of 64 bit integers
- * from a property.
- *
- * @np: device node from which the property value is to be read.
- * @propname: name of the property to be searched.
- * @out_values: pointer to return value, modified only if return value is 0.
- * @sz: number of array elements to read
- *
- * Search for a property in a device node and read 64-bit value(s) from
- * it.
- *
- * Return: 0 on success, -EINVAL if the property does not exist,
- * -ENODATA if property does not have a value, and -EOVERFLOW if the
- * property data isn't large enough.
- *
- * The out_values is modified only if a valid u64 value can be decoded.
- */
-static inline int of_property_read_u64_array(const struct device_node *np,
- const char *propname,
- u64 *out_values, size_t sz)
-{
- int ret = of_property_read_variable_u64_array(np, propname, out_values,
- sz, 0);
- if (ret >= 0)
- return 0;
- else
- return ret;
-}
-
/*
* struct property *prop;
* const __be32 *p;
@@ -734,32 +604,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np,
return -ENOSYS;
}
-static inline int of_property_read_u8_array(const struct device_node *np,
- const char *propname, u8 *out_values, size_t sz)
-{
- return -ENOSYS;
-}
-
-static inline int of_property_read_u16_array(const struct device_node *np,
- const char *propname, u16 *out_values, size_t sz)
-{
- return -ENOSYS;
-}
-
-static inline int of_property_read_u32_array(const struct device_node *np,
- const char *propname,
- u32 *out_values, size_t sz)
-{
- return -ENOSYS;
-}
-
-static inline int of_property_read_u64_array(const struct device_node *np,
- const char *propname,
- u64 *out_values, size_t sz)
-{
- return -ENOSYS;
-}
-
static inline int of_property_read_u32_index(const struct device_node *np,
const char *propname, u32 index, u32 *out_value)
{
@@ -865,18 +709,12 @@ static inline int of_property_read_string_helper(const struct device_node *np,
return -ENOSYS;
}
-static inline struct device_node *of_parse_phandle(const struct device_node *np,
- const char *phandle_name,
- int index)
-{
- return NULL;
-}
-
-static inline int of_parse_phandle_with_args(const struct device_node *np,
- const char *list_name,
- const char *cells_name,
- int index,
- struct of_phandle_args *out_args)
+static inline int __of_parse_phandle_with_args(const struct device_node *np,
+ const char *list_name,
+ const char *cells_name,
+ int cell_count,
+ int index,
+ struct of_phandle_args *out_args)
{
return -ENOSYS;
}
@@ -890,13 +728,6 @@ static inline int of_parse_phandle_with_args_map(const struct device_node *np,
return -ENOSYS;
}
-static inline int of_parse_phandle_with_fixed_args(const struct device_node *np,
- const char *list_name, int cells_count, int index,
- struct of_phandle_args *out_args)
-{
- return -ENOSYS;
-}
-
static inline int of_count_phandle_with_args(const struct device_node *np,
const char *list_name,
const char *cells_name)
@@ -1078,6 +909,117 @@ static inline bool of_node_is_type(const struct device_node *np, const char *typ
}
/**
+ * of_parse_phandle - Resolve a phandle property to a device_node pointer
+ * @np: Pointer to device node holding phandle property
+ * @phandle_name: Name of property holding a phandle value
+ * @index: For properties holding a table of phandles, this is the index into
+ * the table
+ *
+ * Return: The device_node pointer with refcount incremented. Use
+ * of_node_put() on it when done.
+ */
+static inline struct device_node *of_parse_phandle(const struct device_node *np,
+ const char *phandle_name,
+ int index)
+{
+ struct of_phandle_args args;
+
+ if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0,
+ index, &args))
+ return NULL;
+
+ return args.np;
+}
+
+/**
+ * of_parse_phandle_with_args() - Find a node pointed by phandle in a list
+ * @np: pointer to a device tree node containing a list
+ * @list_name: property name that contains a list
+ * @cells_name: property name that specifies phandles' arguments count
+ * @index: index of a phandle to parse out
+ * @out_args: optional pointer to output arguments structure (will be filled)
+ *
+ * This function is useful to parse lists of phandles and their arguments.
+ * Returns 0 on success and fills out_args, on error returns appropriate
+ * errno value.
+ *
+ * Caller is responsible to call of_node_put() on the returned out_args->np
+ * pointer.
+ *
+ * Example::
+ *
+ * phandle1: node1 {
+ * #list-cells = <2>;
+ * };
+ *
+ * phandle2: node2 {
+ * #list-cells = <1>;
+ * };
+ *
+ * node3 {
+ * list = <&phandle1 1 2 &phandle2 3>;
+ * };
+ *
+ * To get a device_node of the ``node2`` node you may call this:
+ * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args);
+ */
+static inline int of_parse_phandle_with_args(const struct device_node *np,
+ const char *list_name,
+ const char *cells_name,
+ int index,
+ struct of_phandle_args *out_args)
+{
+ int cell_count = -1;
+
+ /* If cells_name is NULL we assume a cell count of 0 */
+ if (!cells_name)
+ cell_count = 0;
+
+ return __of_parse_phandle_with_args(np, list_name, cells_name,
+ cell_count, index, out_args);
+}
+
+/**
+ * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list
+ * @np: pointer to a device tree node containing a list
+ * @list_name: property name that contains a list
+ * @cell_count: number of argument cells following the phandle
+ * @index: index of a phandle to parse out
+ * @out_args: optional pointer to output arguments structure (will be filled)
+ *
+ * This function is useful to parse lists of phandles and their arguments.
+ * Returns 0 on success and fills out_args, on error returns appropriate
+ * errno value.
+ *
+ * Caller is responsible to call of_node_put() on the returned out_args->np
+ * pointer.
+ *
+ * Example::
+ *
+ * phandle1: node1 {
+ * };
+ *
+ * phandle2: node2 {
+ * };
+ *
+ * node3 {
+ * list = <&phandle1 0 2 &phandle2 2 3>;
+ * };
+ *
+ * To get a device_node of the ``node2`` node you may call this:
+ * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args);
+ */
+static inline int of_parse_phandle_with_fixed_args(const struct device_node *np,
+ const char *list_name,
+ int cell_count,
+ int index,
+ struct of_phandle_args *out_args)
+{
+ return __of_parse_phandle_with_args(np, list_name, NULL, cell_count,
+ index, out_args);
+}
+
+/**
* of_property_count_u8_elems - Count the number of u8 elements in a property
*
* @np: device node from which the property value is to be read.
@@ -1236,6 +1178,130 @@ static inline bool of_property_read_bool(const struct device_node *np,
return prop ? true : false;
}
+/**
+ * of_property_read_u8_array - Find and read an array of u8 from a property.
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @out_values: pointer to return value, modified only if return value is 0.
+ * @sz: number of array elements to read
+ *
+ * Search for a property in a device node and read 8-bit value(s) from
+ * it.
+ *
+ * dts entry of array should be like:
+ * ``property = /bits/ 8 <0x50 0x60 0x70>;``
+ *
+ * Return: 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u8 value can be decoded.
+ */
+static inline int of_property_read_u8_array(const struct device_node *np,
+ const char *propname,
+ u8 *out_values, size_t sz)
+{
+ int ret = of_property_read_variable_u8_array(np, propname, out_values,
+ sz, 0);
+ if (ret >= 0)
+ return 0;
+ else
+ return ret;
+}
+
+/**
+ * of_property_read_u16_array - Find and read an array of u16 from a property.
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @out_values: pointer to return value, modified only if return value is 0.
+ * @sz: number of array elements to read
+ *
+ * Search for a property in a device node and read 16-bit value(s) from
+ * it.
+ *
+ * dts entry of array should be like:
+ * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;``
+ *
+ * Return: 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u16 value can be decoded.
+ */
+static inline int of_property_read_u16_array(const struct device_node *np,
+ const char *propname,
+ u16 *out_values, size_t sz)
+{
+ int ret = of_property_read_variable_u16_array(np, propname, out_values,
+ sz, 0);
+ if (ret >= 0)
+ return 0;
+ else
+ return ret;
+}
+
+/**
+ * of_property_read_u32_array - Find and read an array of 32 bit integers
+ * from a property.
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @out_values: pointer to return value, modified only if return value is 0.
+ * @sz: number of array elements to read
+ *
+ * Search for a property in a device node and read 32-bit value(s) from
+ * it.
+ *
+ * Return: 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u32 value can be decoded.
+ */
+static inline int of_property_read_u32_array(const struct device_node *np,
+ const char *propname,
+ u32 *out_values, size_t sz)
+{
+ int ret = of_property_read_variable_u32_array(np, propname, out_values,
+ sz, 0);
+ if (ret >= 0)
+ return 0;
+ else
+ return ret;
+}
+
+/**
+ * of_property_read_u64_array - Find and read an array of 64 bit integers
+ * from a property.
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @out_values: pointer to return value, modified only if return value is 0.
+ * @sz: number of array elements to read
+ *
+ * Search for a property in a device node and read 64-bit value(s) from
+ * it.
+ *
+ * Return: 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u64 value can be decoded.
+ */
+static inline int of_property_read_u64_array(const struct device_node *np,
+ const char *propname,
+ u64 *out_values, size_t sz)
+{
+ int ret = of_property_read_variable_u64_array(np, propname, out_values,
+ sz, 0);
+ if (ret >= 0)
+ return 0;
+ else
+ return ret;
+}
+
static inline int of_property_read_u8(const struct device_node *np,
const char *propname,
u8 *out_value)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1294210..1c3b6e5 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -920,43 +920,6 @@ extern bool is_free_buddy_page(struct page *page);
__PAGEFLAG(Isolated, isolated, PF_ANY);
-/*
- * If network-based swap is enabled, sl*b must keep track of whether pages
- * were allocated from pfmemalloc reserves.
- */
-static inline int PageSlabPfmemalloc(struct page *page)
-{
- VM_BUG_ON_PAGE(!PageSlab(page), page);
- return PageActive(page);
-}
-
-/*
- * A version of PageSlabPfmemalloc() for opportunistic checks where the page
- * might have been freed under us and not be a PageSlab anymore.
- */
-static inline int __PageSlabPfmemalloc(struct page *page)
-{
- return PageActive(page);
-}
-
-static inline void SetPageSlabPfmemalloc(struct page *page)
-{
- VM_BUG_ON_PAGE(!PageSlab(page), page);
- SetPageActive(page);
-}
-
-static inline void __ClearPageSlabPfmemalloc(struct page *page)
-{
- VM_BUG_ON_PAGE(!PageSlab(page), page);
- __ClearPageActive(page);
-}
-
-static inline void ClearPageSlabPfmemalloc(struct page *page)
-{
- VM_BUG_ON_PAGE(!PageSlab(page), page);
- ClearPageActive(page);
-}
-
#ifdef CONFIG_MMU
#define __PG_MLOCKED (1UL << PG_mlocked)
#else
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index dda8d58..67b1246 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -111,6 +111,7 @@ static_assert(offsetof(struct pagevec, pages) ==
static inline void folio_batch_init(struct folio_batch *fbatch)
{
fbatch->nr = 0;
+ fbatch->percpu_pvec_drained = false;
}
static inline unsigned int folio_batch_count(struct folio_batch *fbatch)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index ae4004e..f1ec5ad 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -94,10 +94,7 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR];
extern enum pcpu_fc pcpu_chosen_fc;
-typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size,
- size_t align);
-typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size);
-typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr);
+typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu);
typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to);
extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
@@ -111,15 +108,13 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
- pcpu_fc_alloc_fn_t alloc_fn,
- pcpu_fc_free_fn_t free_fn);
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn);
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+void __init pcpu_populate_pte(unsigned long addr);
extern int __init pcpu_page_first_chunk(size_t reserved_size,
- pcpu_fc_alloc_fn_t alloc_fn,
- pcpu_fc_free_fn_t free_fn,
- pcpu_fc_populate_pte_fn_t populate_pte_fn);
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn);
#endif
extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index e1e9402..f7d2be6 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -8,6 +8,7 @@
#ifndef _LINUX_PM_H
#define _LINUX_PM_H
+#include <linux/export.h>
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/spinlock.h>
@@ -357,13 +358,47 @@ struct dev_pm_ops {
#define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn)
#endif
+#define _DEFINE_DEV_PM_OPS(name, \
+ suspend_fn, resume_fn, \
+ runtime_suspend_fn, runtime_resume_fn, idle_fn) \
+const struct dev_pm_ops name = { \
+ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
+ RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \
+}
+
+#ifdef CONFIG_PM
+#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
+ runtime_resume_fn, idle_fn, sec) \
+ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
+ runtime_resume_fn, idle_fn); \
+ _EXPORT_SYMBOL(name, sec)
+#else
+#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
+ runtime_resume_fn, idle_fn, sec) \
+static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \
+ resume_fn, runtime_suspend_fn, \
+ runtime_resume_fn, idle_fn)
+#endif
+
/*
* Use this if you want to use the same suspend and resume callbacks for suspend
* to RAM and hibernation.
+ *
+ * If the underlying dev_pm_ops struct symbol has to be exported, use
+ * EXPORT_SIMPLE_DEV_PM_OPS() or EXPORT_GPL_SIMPLE_DEV_PM_OPS() instead.
*/
#define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
-static const struct dev_pm_ops name = { \
- SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
+ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL)
+
+#define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
+ _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "")
+#define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
+ _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl")
+
+/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */
+#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
+const struct dev_pm_ops __maybe_unused name = { \
+ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
}
/*
@@ -378,20 +413,10 @@ static const struct dev_pm_ops name = { \
* suspend and "early" resume callback pointers, .suspend_late() and
* .resume_early(), to the same routines as .runtime_suspend() and
* .runtime_resume(), respectively (and analogously for hibernation).
+ *
+ * Deprecated. You most likely don't want this macro. Use
+ * DEFINE_RUNTIME_DEV_PM_OPS() instead.
*/
-#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
-static const struct dev_pm_ops name = { \
- SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
- RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
-}
-
-/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */
-#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
-const struct dev_pm_ops __maybe_unused name = { \
- SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
-}
-
-/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */
#define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
const struct dev_pm_ops __maybe_unused name = { \
SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 016de57..9f09601 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -22,6 +22,30 @@
usage_count */
#define RPM_AUTO 0x08 /* Use autosuspend_delay */
+/*
+ * Use this for defining a set of PM operations to be used in all situations
+ * (system suspend, hibernation or runtime PM).
+ *
+ * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS()
+ * macro, which uses the provided callbacks for both runtime PM and system
+ * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend()
+ * and pm_runtime_force_resume() for its system sleep callbacks.
+ *
+ * If the underlying dev_pm_ops struct symbol has to be exported, use
+ * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead.
+ */
+#define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
+ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \
+ pm_runtime_force_resume, suspend_fn, \
+ resume_fn, idle_fn)
+
+#define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
+ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
+ suspend_fn, resume_fn, idle_fn, "")
+#define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
+ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
+ suspend_fn, resume_fn, idle_fn, "_gpl")
+
#ifdef CONFIG_PM
extern struct workqueue_struct *pm_wq;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 069c7fd..01b9268 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -178,8 +178,16 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
#define proc_create_seq(name, mode, parent, ops) ({NULL;})
#define proc_create_single(name, mode, parent, show) ({NULL;})
#define proc_create_single_data(name, mode, parent, show, data) ({NULL;})
-#define proc_create(name, mode, parent, proc_ops) ({NULL;})
-#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;})
+
+static inline struct proc_dir_entry *
+proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent,
+ const struct proc_ops *proc_ops)
+{ return NULL; }
+
+static inline struct proc_dir_entry *
+proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent,
+ const struct proc_ops *proc_ops, void *data)
+{ return NULL; }
static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {}
static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {}
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index fc0357a..95df357 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -416,6 +416,17 @@ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq)
}
/**
+ * sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch
+ * @sbq: Bitmap queue to recalculate wake batch.
+ * @users: Number of shares.
+ *
+ * Like sbitmap_queue_update_wake_batch(), this will calculate wake batch
+ * by depth. This interface is for HCTX shared tags or queue shared tags.
+ */
+void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int users);
+
+/**
* sbitmap_queue_resize() - Resize a &struct sbitmap_queue.
* @sbq: Bitmap queue to resize.
* @depth: New number of bits to resize to.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a6a2db5..508b91d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -274,8 +274,13 @@ struct task_group;
#define get_current_state() READ_ONCE(current->__state)
-/* Task command name length: */
-#define TASK_COMM_LEN 16
+/*
+ * Define the task command name length as enum, then it can be visible to
+ * BPF programs.
+ */
+enum {
+ TASK_COMM_LEN = 16,
+};
extern void scheduler_tick(void);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 367366f..37bde99 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -403,8 +403,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size,
if (size <= 16 * 1024 * 1024) return 24;
if (size <= 32 * 1024 * 1024) return 25;
- if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000)
- && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant)
+ if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant)
BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()");
else
BUG();
diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h
index c0d817d..f4c8eaf 100644
--- a/include/linux/unaligned/packed_struct.h
+++ b/include/linux/unaligned/packed_struct.h
@@ -1,7 +1,7 @@
#ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H
#define _LINUX_UNALIGNED_PACKED_STRUCT_H
-#include <linux/kernel.h>
+#include <linux/types.h>
struct __una_u16 { u16 x; } __packed;
struct __una_u32 { u32 x; } __packed;
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index c3011cc..2de442e 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -64,6 +64,7 @@ struct vdpa_mgmt_dev;
* struct vdpa_device - representation of a vDPA device
* @dev: underlying device
* @dma_dev: the actual device that is performing DMA
+ * @driver_override: driver name to force a match
* @config: the configuration ops for this device.
* @cf_mutex: Protects get and set access to configuration layout.
* @index: device index
@@ -76,6 +77,7 @@ struct vdpa_mgmt_dev;
struct vdpa_device {
struct device dev;
struct device *dma_dev;
+ const char *driver_override;
const struct vdpa_config_ops *config;
struct mutex cf_mutex; /* Protects get/set config */
unsigned int index;
@@ -99,6 +101,7 @@ struct vdpa_dev_set_config {
struct {
u8 mac[ETH_ALEN];
u16 mtu;
+ u16 max_vq_pairs;
} net;
u64 mask;
};
@@ -155,7 +158,7 @@ struct vdpa_map_file {
* @vdev: vdpa device
* @idx: virtqueue index
* @state: pointer to returned state (last_avail_idx)
- * @get_vq_notification: Get the notification area for a virtqueue
+ * @get_vq_notification: Get the notification area for a virtqueue (optional)
* @vdev: vdpa device
* @idx: virtqueue index
* Returns the notifcation area
@@ -169,14 +172,17 @@ struct vdpa_map_file {
* for the device
* @vdev: vdpa device
* Returns virtqueue algin requirement
- * @get_features: Get virtio features supported by the device
+ * @get_device_features: Get virtio features supported by the device
* @vdev: vdpa device
* Returns the virtio features support by the
* device
- * @set_features: Set virtio features supported by the driver
+ * @set_driver_features: Set virtio features supported by the driver
* @vdev: vdpa device
* @features: feature support by the driver
* Returns integer: success (0) or error (< 0)
+ * @get_driver_features: Get the virtio driver features in action
+ * @vdev: vdpa device
+ * Returns the virtio features accepted
* @set_config_cb: Set the config interrupt callback
* @vdev: vdpa device
* @cb: virtio-vdev interrupt callback structure
@@ -276,8 +282,9 @@ struct vdpa_config_ops {
/* Device ops */
u32 (*get_vq_align)(struct vdpa_device *vdev);
- u64 (*get_features)(struct vdpa_device *vdev);
- int (*set_features)(struct vdpa_device *vdev, u64 features);
+ u64 (*get_device_features)(struct vdpa_device *vdev);
+ int (*set_driver_features)(struct vdpa_device *vdev, u64 features);
+ u64 (*get_driver_features)(struct vdpa_device *vdev);
void (*set_config_cb)(struct vdpa_device *vdev,
struct vdpa_callback *cb);
u16 (*get_vq_num_max)(struct vdpa_device *vdev);
@@ -385,23 +392,37 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
static inline int vdpa_reset(struct vdpa_device *vdev)
{
const struct vdpa_config_ops *ops = vdev->config;
+ int ret;
+ mutex_lock(&vdev->cf_mutex);
vdev->features_valid = false;
- return ops->reset(vdev);
+ ret = ops->reset(vdev);
+ mutex_unlock(&vdev->cf_mutex);
+ return ret;
}
-static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
+static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features, bool locked)
{
const struct vdpa_config_ops *ops = vdev->config;
+ int ret;
+
+ if (!locked)
+ mutex_lock(&vdev->cf_mutex);
vdev->features_valid = true;
- return ops->set_features(vdev, features);
+ ret = ops->set_driver_features(vdev, features);
+ if (!locked)
+ mutex_unlock(&vdev->cf_mutex);
+
+ return ret;
}
void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
void *buf, unsigned int len);
void vdpa_set_config(struct vdpa_device *dev, unsigned int offset,
const void *buf, unsigned int length);
+void vdpa_set_status(struct vdpa_device *vdev, u8 status);
+
/**
* struct vdpa_mgmtdev_ops - vdpa device ops
* @dev_add: Add a vdpa device using alloc and register
@@ -438,6 +459,8 @@ struct vdpa_mgmt_dev {
const struct virtio_device_id *id_table;
u64 config_attr_mask;
struct list_head list;
+ u64 supported_features;
+ u32 max_supported_vqs;
};
int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 41edbc0..72292a6 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -138,6 +138,7 @@ int virtio_finalize_features(struct virtio_device *dev);
int virtio_device_freeze(struct virtio_device *dev);
int virtio_device_restore(struct virtio_device *dev);
#endif
+void virtio_reset_device(struct virtio_device *dev);
size_t virtio_max_dma_size(struct virtio_device *vdev);
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 48cc5795..63540be 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -117,8 +117,15 @@ int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net);
static inline void fqdir_pre_exit(struct fqdir *fqdir)
{
- fqdir->high_thresh = 0; /* prevent creation of new frags */
- fqdir->dead = true;
+ /* Prevent creation of new frags.
+ * Pairs with READ_ONCE() in inet_frag_find().
+ */
+ WRITE_ONCE(fqdir->high_thresh, 0);
+
+ /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
+ * and ip6frag_expire_frag_queue().
+ */
+ WRITE_ONCE(fqdir->dead, true);
}
void fqdir_exit(struct fqdir *fqdir);
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 851029e..0a47791 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -67,7 +67,8 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
struct sk_buff *head;
rcu_read_lock();
- if (fq->q.fqdir->dead)
+ /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
+ if (READ_ONCE(fq->q.fqdir->dead))
goto out_rcu_unlock;
spin_lock(&fq->q.lock);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index ebef45e..676cb8e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -218,8 +218,10 @@ static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net,
#ifdef CONFIG_NET_CLS_ACT
exts->type = 0;
exts->nr_actions = 0;
+ /* Note: we do not own yet a reference on net.
+ * This reference might be taken later from tcf_exts_get_net().
+ */
exts->net = net;
- netns_tracker_alloc(net, &exts->ns_tracker, GFP_KERNEL);
exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *),
GFP_KERNEL);
if (!exts->actions)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c11dbac..472843e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1244,6 +1244,7 @@ struct psched_ratecfg {
u64 rate_bytes_ps; /* bytes per second */
u32 mult;
u16 overhead;
+ u16 mpu;
u8 linklayer;
u8 shift;
};
@@ -1253,6 +1254,9 @@ static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
{
len += r->overhead;
+ if (len < r->mpu)
+ len = r->mpu;
+
if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
@@ -1275,6 +1279,7 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
res->rate = min_t(u64, r->rate_bytes_ps, ~0U);
res->overhead = r->overhead;
+ res->mpu = r->mpu;
res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index ab7557d..647c53b 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -415,9 +415,8 @@ extern int scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
int retries, struct scsi_mode_data *data,
struct scsi_sense_hdr *);
extern int scsi_mode_select(struct scsi_device *sdev, int pf, int sp,
- int modepage, unsigned char *buffer, int len,
- int timeout, int retries,
- struct scsi_mode_data *data,
+ unsigned char *buffer, int len, int timeout,
+ int retries, struct scsi_mode_data *data,
struct scsi_sense_hdr *);
extern int scsi_test_unit_ready(struct scsi_device *sdev, int timeout,
int retries, struct scsi_sense_hdr *sshdr);
diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h
index 1172529..c6f5aa7 100644
--- a/include/trace/events/cachefiles.h
+++ b/include/trace/events/cachefiles.h
@@ -233,25 +233,48 @@ TRACE_EVENT(cachefiles_ref,
TRACE_EVENT(cachefiles_lookup,
TP_PROTO(struct cachefiles_object *obj,
+ struct dentry *dir,
struct dentry *de),
- TP_ARGS(obj, de),
+ TP_ARGS(obj, dir, de),
TP_STRUCT__entry(
__field(unsigned int, obj )
__field(short, error )
+ __field(unsigned long, dino )
__field(unsigned long, ino )
),
TP_fast_assign(
- __entry->obj = obj->debug_id;
+ __entry->obj = obj ? obj->debug_id : 0;
+ __entry->dino = d_backing_inode(dir)->i_ino;
__entry->ino = (!IS_ERR(de) && d_backing_inode(de) ?
d_backing_inode(de)->i_ino : 0);
__entry->error = IS_ERR(de) ? PTR_ERR(de) : 0;
),
- TP_printk("o=%08x i=%lx e=%d",
- __entry->obj, __entry->ino, __entry->error)
+ TP_printk("o=%08x dB=%lx B=%lx e=%d",
+ __entry->obj, __entry->dino, __entry->ino, __entry->error)
+ );
+
+TRACE_EVENT(cachefiles_mkdir,
+ TP_PROTO(struct dentry *dir, struct dentry *subdir),
+
+ TP_ARGS(dir, subdir),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, dir )
+ __field(unsigned int, subdir )
+ ),
+
+ TP_fast_assign(
+ __entry->dir = d_backing_inode(dir)->i_ino;
+ __entry->subdir = d_backing_inode(subdir)->i_ino;
+ ),
+
+ TP_printk("dB=%x sB=%x",
+ __entry->dir,
+ __entry->subdir)
);
TRACE_EVENT(cachefiles_tmpfile,
@@ -269,7 +292,7 @@ TRACE_EVENT(cachefiles_tmpfile,
__entry->backer = backer->i_ino;
),
- TP_printk("o=%08x b=%08x",
+ TP_printk("o=%08x B=%x",
__entry->obj,
__entry->backer)
);
@@ -289,61 +312,58 @@ TRACE_EVENT(cachefiles_link,
__entry->backer = backer->i_ino;
),
- TP_printk("o=%08x b=%08x",
+ TP_printk("o=%08x B=%x",
__entry->obj,
__entry->backer)
);
TRACE_EVENT(cachefiles_unlink,
TP_PROTO(struct cachefiles_object *obj,
- struct dentry *de,
+ ino_t ino,
enum fscache_why_object_killed why),
- TP_ARGS(obj, de, why),
+ TP_ARGS(obj, ino, why),
/* Note that obj may be NULL */
TP_STRUCT__entry(
__field(unsigned int, obj )
- __field(struct dentry *, de )
+ __field(unsigned int, ino )
__field(enum fscache_why_object_killed, why )
),
TP_fast_assign(
__entry->obj = obj ? obj->debug_id : UINT_MAX;
- __entry->de = de;
+ __entry->ino = ino;
__entry->why = why;
),
- TP_printk("o=%08x d=%p w=%s",
- __entry->obj, __entry->de,
+ TP_printk("o=%08x B=%x w=%s",
+ __entry->obj, __entry->ino,
__print_symbolic(__entry->why, cachefiles_obj_kill_traces))
);
TRACE_EVENT(cachefiles_rename,
TP_PROTO(struct cachefiles_object *obj,
- struct dentry *de,
- struct dentry *to,
+ ino_t ino,
enum fscache_why_object_killed why),
- TP_ARGS(obj, de, to, why),
+ TP_ARGS(obj, ino, why),
/* Note that obj may be NULL */
TP_STRUCT__entry(
__field(unsigned int, obj )
- __field(struct dentry *, de )
- __field(struct dentry *, to )
+ __field(unsigned int, ino )
__field(enum fscache_why_object_killed, why )
),
TP_fast_assign(
__entry->obj = obj ? obj->debug_id : UINT_MAX;
- __entry->de = de;
- __entry->to = to;
+ __entry->ino = ino;
__entry->why = why;
),
- TP_printk("o=%08x d=%p t=%p w=%s",
- __entry->obj, __entry->de, __entry->to,
+ TP_printk("o=%08x B=%x w=%s",
+ __entry->obj, __entry->ino,
__print_symbolic(__entry->why, cachefiles_obj_kill_traces))
);
@@ -370,7 +390,7 @@ TRACE_EVENT(cachefiles_coherency,
__entry->ino = ino;
),
- TP_printk("o=%08x %s i=%llx c=%u",
+ TP_printk("o=%08x %s B=%llx c=%u",
__entry->obj,
__print_symbolic(__entry->why, cachefiles_coherency_traces),
__entry->ino,
@@ -397,7 +417,7 @@ TRACE_EVENT(cachefiles_vol_coherency,
__entry->ino = ino;
),
- TP_printk("V=%08x %s i=%llx",
+ TP_printk("V=%08x %s B=%llx",
__entry->vol,
__print_symbolic(__entry->why, cachefiles_coherency_traces),
__entry->ino)
@@ -435,7 +455,7 @@ TRACE_EVENT(cachefiles_prep_read,
__entry->cache_inode = cache_inode;
),
- TP_printk("R=%08x[%u] %s %s f=%02x s=%llx %zx ni=%x b=%x",
+ TP_printk("R=%08x[%u] %s %s f=%02x s=%llx %zx ni=%x B=%x",
__entry->rreq, __entry->index,
__print_symbolic(__entry->source, netfs_sreq_sources),
__print_symbolic(__entry->why, cachefiles_prepare_read_traces),
@@ -466,7 +486,7 @@ TRACE_EVENT(cachefiles_read,
__entry->len = len;
),
- TP_printk("o=%08x b=%08x s=%llx l=%zx",
+ TP_printk("o=%08x B=%x s=%llx l=%zx",
__entry->obj,
__entry->backer,
__entry->start,
@@ -495,7 +515,7 @@ TRACE_EVENT(cachefiles_write,
__entry->len = len;
),
- TP_printk("o=%08x b=%08x s=%llx l=%zx",
+ TP_printk("o=%08x B=%x s=%llx l=%zx",
__entry->obj,
__entry->backer,
__entry->start,
@@ -524,7 +544,7 @@ TRACE_EVENT(cachefiles_trunc,
__entry->why = why;
),
- TP_printk("o=%08x b=%08x %s l=%llx->%llx",
+ TP_printk("o=%08x B=%x %s l=%llx->%llx",
__entry->obj,
__entry->backer,
__print_symbolic(__entry->why, cachefiles_trunc_traces),
@@ -549,7 +569,28 @@ TRACE_EVENT(cachefiles_mark_active,
__entry->inode = inode->i_ino;
),
- TP_printk("o=%08x i=%lx",
+ TP_printk("o=%08x B=%lx",
+ __entry->obj, __entry->inode)
+ );
+
+TRACE_EVENT(cachefiles_mark_failed,
+ TP_PROTO(struct cachefiles_object *obj,
+ struct inode *inode),
+
+ TP_ARGS(obj, inode),
+
+ /* Note that obj may be NULL */
+ TP_STRUCT__entry(
+ __field(unsigned int, obj )
+ __field(ino_t, inode )
+ ),
+
+ TP_fast_assign(
+ __entry->obj = obj ? obj->debug_id : 0;
+ __entry->inode = inode->i_ino;
+ ),
+
+ TP_printk("o=%08x B=%lx",
__entry->obj, __entry->inode)
);
@@ -570,7 +611,7 @@ TRACE_EVENT(cachefiles_mark_inactive,
__entry->inode = inode->i_ino;
),
- TP_printk("o=%08x i=%lx",
+ TP_printk("o=%08x B=%lx",
__entry->obj, __entry->inode)
);
@@ -594,7 +635,7 @@ TRACE_EVENT(cachefiles_vfs_error,
__entry->where = where;
),
- TP_printk("o=%08x b=%08x %s e=%d",
+ TP_printk("o=%08x B=%x %s e=%d",
__entry->obj,
__entry->backer,
__print_symbolic(__entry->where, cachefiles_error_traces),
@@ -621,7 +662,7 @@ TRACE_EVENT(cachefiles_io_error,
__entry->where = where;
),
- TP_printk("o=%08x b=%08x %s e=%d",
+ TP_printk("o=%08x B=%x %s e=%d",
__entry->obj,
__entry->backer,
__print_symbolic(__entry->where, cachefiles_error_traces),
diff --git a/include/trace/events/error_report.h b/include/trace/events/error_report.h
index 96f64bf2..a1922a8 100644
--- a/include/trace/events/error_report.h
+++ b/include/trace/events/error_report.h
@@ -17,14 +17,16 @@
enum error_detector {
ERROR_DETECTOR_KFENCE,
- ERROR_DETECTOR_KASAN
+ ERROR_DETECTOR_KASAN,
+ ERROR_DETECTOR_WARN,
};
#endif /* __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY */
-#define error_detector_list \
+#define error_detector_list \
EM(ERROR_DETECTOR_KFENCE, "kfence") \
- EMe(ERROR_DETECTOR_KASAN, "kasan")
+ EM(ERROR_DETECTOR_KASAN, "kasan") \
+ EMe(ERROR_DETECTOR_WARN, "warning")
/* Always end the list with an EMe. */
#undef EM
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index f8cb916..f701bb23 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -540,17 +540,17 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
TRACE_EVENT(f2fs_file_write_iter,
- TP_PROTO(struct inode *inode, unsigned long offset,
- unsigned long length, int ret),
+ TP_PROTO(struct inode *inode, loff_t offset, size_t length,
+ ssize_t ret),
TP_ARGS(inode, offset, length, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
- __field(unsigned long, offset)
- __field(unsigned long, length)
- __field(int, ret)
+ __field(loff_t, offset)
+ __field(size_t, length)
+ __field(ssize_t, ret)
),
TP_fast_assign(
@@ -562,7 +562,7 @@ TRACE_EVENT(f2fs_file_write_iter,
),
TP_printk("dev = (%d,%d), ino = %lu, "
- "offset = %lu, length = %lu, written(err) = %d",
+ "offset = %lld, length = %zu, written(err) = %zd",
show_dev_ino(__entry),
__entry->offset,
__entry->length,
@@ -936,14 +936,14 @@ TRACE_EVENT(f2fs_fallocate,
TRACE_EVENT(f2fs_direct_IO_enter,
- TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw),
+ TP_PROTO(struct inode *inode, struct kiocb *iocb, long len, int rw),
- TP_ARGS(inode, offset, len, rw),
+ TP_ARGS(inode, iocb, len, rw),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
- __field(loff_t, pos)
+ __field(struct kiocb *, iocb)
__field(unsigned long, len)
__field(int, rw)
),
@@ -951,15 +951,18 @@ TRACE_EVENT(f2fs_direct_IO_enter,
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
- __entry->pos = offset;
+ __entry->iocb = iocb;
__entry->len = len;
__entry->rw = rw;
),
- TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu rw = %d",
+ TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_hint = %x ki_ioprio = %x rw = %d",
show_dev_ino(__entry),
- __entry->pos,
+ __entry->iocb->ki_pos,
__entry->len,
+ __entry->iocb->ki_flags,
+ __entry->iocb->ki_hint,
+ __entry->iocb->ki_ioprio,
__entry->rw)
);
diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h
index ab69434..d4e631a 100644
--- a/include/trace/events/libata.h
+++ b/include/trace/events/libata.h
@@ -132,9 +132,37 @@
ata_protocol_name(ATAPI_PROT_PIO), \
ata_protocol_name(ATAPI_PROT_DMA))
+#define ata_class_name(class) { class, #class }
+#define show_class_name(val) \
+ __print_symbolic(val, \
+ ata_class_name(ATA_DEV_UNKNOWN), \
+ ata_class_name(ATA_DEV_ATA), \
+ ata_class_name(ATA_DEV_ATA_UNSUP), \
+ ata_class_name(ATA_DEV_ATAPI), \
+ ata_class_name(ATA_DEV_ATAPI_UNSUP), \
+ ata_class_name(ATA_DEV_PMP), \
+ ata_class_name(ATA_DEV_PMP_UNSUP), \
+ ata_class_name(ATA_DEV_SEMB), \
+ ata_class_name(ATA_DEV_SEMB_UNSUP), \
+ ata_class_name(ATA_DEV_ZAC), \
+ ata_class_name(ATA_DEV_ZAC_UNSUP), \
+ ata_class_name(ATA_DEV_NONE))
+
+#define ata_sff_hsm_state_name(state) { state, #state }
+#define show_sff_hsm_state_name(val) \
+ __print_symbolic(val, \
+ ata_sff_hsm_state_name(HSM_ST_IDLE), \
+ ata_sff_hsm_state_name(HSM_ST_FIRST), \
+ ata_sff_hsm_state_name(HSM_ST), \
+ ata_sff_hsm_state_name(HSM_ST_LAST), \
+ ata_sff_hsm_state_name(HSM_ST_ERR))
+
const char *libata_trace_parse_status(struct trace_seq*, unsigned char);
#define __parse_status(s) libata_trace_parse_status(p, s)
+const char *libata_trace_parse_host_stat(struct trace_seq *, unsigned char);
+#define __parse_host_stat(s) libata_trace_parse_host_stat(p, s)
+
const char *libata_trace_parse_eh_action(struct trace_seq *, unsigned int);
#define __parse_eh_action(a) libata_trace_parse_eh_action(p, a)
@@ -144,11 +172,14 @@ const char *libata_trace_parse_eh_err_mask(struct trace_seq *, unsigned int);
const char *libata_trace_parse_qc_flags(struct trace_seq *, unsigned int);
#define __parse_qc_flags(f) libata_trace_parse_qc_flags(p, f)
+const char *libata_trace_parse_tf_flags(struct trace_seq *, unsigned int);
+#define __parse_tf_flags(f) libata_trace_parse_tf_flags(p, f)
+
const char *libata_trace_parse_subcmd(struct trace_seq *, unsigned char,
unsigned char, unsigned char);
#define __parse_subcmd(c,f,h) libata_trace_parse_subcmd(p, c, f, h)
-TRACE_EVENT(ata_qc_issue,
+DECLARE_EVENT_CLASS(ata_qc_issue_template,
TP_PROTO(struct ata_queued_cmd *qc),
@@ -207,6 +238,14 @@ TRACE_EVENT(ata_qc_issue,
__entry->dev)
);
+DEFINE_EVENT(ata_qc_issue_template, ata_qc_prep,
+ TP_PROTO(struct ata_queued_cmd *qc),
+ TP_ARGS(qc));
+
+DEFINE_EVENT(ata_qc_issue_template, ata_qc_issue,
+ TP_PROTO(struct ata_queued_cmd *qc),
+ TP_ARGS(qc));
+
DECLARE_EVENT_CLASS(ata_qc_complete_template,
TP_PROTO(struct ata_queued_cmd *qc),
@@ -275,6 +314,128 @@ DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_done,
TP_PROTO(struct ata_queued_cmd *qc),
TP_ARGS(qc));
+TRACE_EVENT(ata_tf_load,
+
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf),
+
+ TP_ARGS(ap, tf),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned char, cmd )
+ __field( unsigned char, dev )
+ __field( unsigned char, lbal )
+ __field( unsigned char, lbam )
+ __field( unsigned char, lbah )
+ __field( unsigned char, nsect )
+ __field( unsigned char, feature )
+ __field( unsigned char, hob_lbal )
+ __field( unsigned char, hob_lbam )
+ __field( unsigned char, hob_lbah )
+ __field( unsigned char, hob_nsect )
+ __field( unsigned char, hob_feature )
+ __field( unsigned char, proto )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = ap->print_id;
+ __entry->proto = tf->protocol;
+ __entry->cmd = tf->command;
+ __entry->dev = tf->device;
+ __entry->lbal = tf->lbal;
+ __entry->lbam = tf->lbam;
+ __entry->lbah = tf->lbah;
+ __entry->hob_lbal = tf->hob_lbal;
+ __entry->hob_lbam = tf->hob_lbam;
+ __entry->hob_lbah = tf->hob_lbah;
+ __entry->feature = tf->feature;
+ __entry->hob_feature = tf->hob_feature;
+ __entry->nsect = tf->nsect;
+ __entry->hob_nsect = tf->hob_nsect;
+ ),
+
+ TP_printk("ata_port=%u proto=%s cmd=%s%s " \
+ " tf=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)",
+ __entry->ata_port,
+ show_protocol_name(__entry->proto),
+ show_opcode_name(__entry->cmd),
+ __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect),
+ __entry->cmd, __entry->feature, __entry->nsect,
+ __entry->lbal, __entry->lbam, __entry->lbah,
+ __entry->hob_feature, __entry->hob_nsect,
+ __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah,
+ __entry->dev)
+);
+
+DECLARE_EVENT_CLASS(ata_exec_command_template,
+
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag),
+
+ TP_ARGS(ap, tf, tag),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned int, tag )
+ __field( unsigned char, cmd )
+ __field( unsigned char, feature )
+ __field( unsigned char, hob_nsect )
+ __field( unsigned char, proto )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = ap->print_id;
+ __entry->tag = tag;
+ __entry->proto = tf->protocol;
+ __entry->cmd = tf->command;
+ __entry->feature = tf->feature;
+ __entry->hob_nsect = tf->hob_nsect;
+ ),
+
+ TP_printk("ata_port=%u tag=%d proto=%s cmd=%s%s",
+ __entry->ata_port, __entry->tag,
+ show_protocol_name(__entry->proto),
+ show_opcode_name(__entry->cmd),
+ __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect))
+);
+
+DEFINE_EVENT(ata_exec_command_template, ata_exec_command,
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag),
+ TP_ARGS(ap, tf, tag));
+
+DEFINE_EVENT(ata_exec_command_template, ata_bmdma_setup,
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag),
+ TP_ARGS(ap, tf, tag));
+
+DEFINE_EVENT(ata_exec_command_template, ata_bmdma_start,
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag),
+ TP_ARGS(ap, tf, tag));
+
+DEFINE_EVENT(ata_exec_command_template, ata_bmdma_stop,
+ TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag),
+ TP_ARGS(ap, tf, tag));
+
+TRACE_EVENT(ata_bmdma_status,
+
+ TP_PROTO(struct ata_port *ap, unsigned int host_stat),
+
+ TP_ARGS(ap, host_stat),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned int, tag )
+ __field( unsigned char, host_stat )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = ap->print_id;
+ __entry->host_stat = host_stat;
+ ),
+
+ TP_printk("ata_port=%u host_stat=%s",
+ __entry->ata_port,
+ __parse_host_stat(__entry->host_stat))
+);
+
TRACE_EVENT(ata_eh_link_autopsy,
TP_PROTO(struct ata_device *dev, unsigned int eh_action, unsigned int eh_err_mask),
@@ -329,6 +490,259 @@ TRACE_EVENT(ata_eh_link_autopsy_qc,
__parse_eh_err_mask(__entry->eh_err_mask))
);
+DECLARE_EVENT_CLASS(ata_eh_action_template,
+
+ TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action),
+
+ TP_ARGS(link, devno, eh_action),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned int, ata_dev )
+ __field( unsigned int, eh_action )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = link->ap->print_id;
+ __entry->ata_dev = link->pmp + devno;
+ __entry->eh_action = eh_action;
+ ),
+
+ TP_printk("ata_port=%u ata_dev=%u eh_action=%s",
+ __entry->ata_port, __entry->ata_dev,
+ __parse_eh_action(__entry->eh_action))
+);
+
+DEFINE_EVENT(ata_eh_action_template, ata_eh_about_to_do,
+ TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action),
+ TP_ARGS(link, devno, eh_action));
+
+DEFINE_EVENT(ata_eh_action_template, ata_eh_done,
+ TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action),
+ TP_ARGS(link, devno, eh_action));
+
+DECLARE_EVENT_CLASS(ata_link_reset_begin_template,
+
+ TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline),
+
+ TP_ARGS(link, class, deadline),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __array( unsigned int, class, 2 )
+ __field( unsigned long, deadline )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = link->ap->print_id;
+ memcpy(__entry->class, class, 2);
+ __entry->deadline = deadline;
+ ),
+
+ TP_printk("ata_port=%u deadline=%lu classes=[%s,%s]",
+ __entry->ata_port, __entry->deadline,
+ show_class_name(__entry->class[0]),
+ show_class_name(__entry->class[1]))
+);
+
+DEFINE_EVENT(ata_link_reset_begin_template, ata_link_hardreset_begin,
+ TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline),
+ TP_ARGS(link, class, deadline));
+
+DEFINE_EVENT(ata_link_reset_begin_template, ata_slave_hardreset_begin,
+ TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline),
+ TP_ARGS(link, class, deadline));
+
+DEFINE_EVENT(ata_link_reset_begin_template, ata_link_softreset_begin,
+ TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline),
+ TP_ARGS(link, class, deadline));
+
+DECLARE_EVENT_CLASS(ata_link_reset_end_template,
+
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+
+ TP_ARGS(link, class, rc),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __array( unsigned int, class, 2 )
+ __field( int, rc )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = link->ap->print_id;
+ memcpy(__entry->class, class, 2);
+ __entry->rc = rc;
+ ),
+
+ TP_printk("ata_port=%u rc=%d class=[%s,%s]",
+ __entry->ata_port, __entry->rc,
+ show_class_name(__entry->class[0]),
+ show_class_name(__entry->class[1]))
+);
+
+DEFINE_EVENT(ata_link_reset_end_template, ata_link_hardreset_end,
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+ TP_ARGS(link, class, rc));
+
+DEFINE_EVENT(ata_link_reset_end_template, ata_slave_hardreset_end,
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+ TP_ARGS(link, class, rc));
+
+DEFINE_EVENT(ata_link_reset_end_template, ata_link_softreset_end,
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+ TP_ARGS(link, class, rc));
+
+DEFINE_EVENT(ata_link_reset_end_template, ata_link_postreset,
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+ TP_ARGS(link, class, rc));
+
+DEFINE_EVENT(ata_link_reset_end_template, ata_slave_postreset,
+ TP_PROTO(struct ata_link *link, unsigned int *class, int rc),
+ TP_ARGS(link, class, rc));
+
+DECLARE_EVENT_CLASS(ata_port_eh_begin_template,
+
+ TP_PROTO(struct ata_port *ap),
+
+ TP_ARGS(ap),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = ap->print_id;
+ ),
+
+ TP_printk("ata_port=%u", __entry->ata_port)
+);
+
+DEFINE_EVENT(ata_port_eh_begin_template, ata_std_sched_eh,
+ TP_PROTO(struct ata_port *ap),
+ TP_ARGS(ap));
+
+DEFINE_EVENT(ata_port_eh_begin_template, ata_port_freeze,
+ TP_PROTO(struct ata_port *ap),
+ TP_ARGS(ap));
+
+DEFINE_EVENT(ata_port_eh_begin_template, ata_port_thaw,
+ TP_PROTO(struct ata_port *ap),
+ TP_ARGS(ap));
+
+DECLARE_EVENT_CLASS(ata_sff_hsm_template,
+
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned char status),
+
+ TP_ARGS(qc, status),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned int, ata_dev )
+ __field( unsigned int, tag )
+ __field( unsigned int, qc_flags )
+ __field( unsigned int, protocol )
+ __field( unsigned int, hsm_state )
+ __field( unsigned char, dev_state )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = qc->ap->print_id;
+ __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno;
+ __entry->tag = qc->tag;
+ __entry->qc_flags = qc->flags;
+ __entry->protocol = qc->tf.protocol;
+ __entry->hsm_state = qc->ap->hsm_task_state;
+ __entry->dev_state = status;
+ ),
+
+ TP_printk("ata_port=%u ata_dev=%u tag=%d proto=%s flags=%s task_state=%s dev_stat=0x%X",
+ __entry->ata_port, __entry->ata_dev, __entry->tag,
+ show_protocol_name(__entry->protocol),
+ __parse_qc_flags(__entry->qc_flags),
+ show_sff_hsm_state_name(__entry->hsm_state),
+ __entry->dev_state)
+);
+
+DEFINE_EVENT(ata_sff_hsm_template, ata_sff_hsm_state,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned char state),
+ TP_ARGS(qc, state));
+
+DEFINE_EVENT(ata_sff_hsm_template, ata_sff_hsm_command_complete,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned char state),
+ TP_ARGS(qc, state));
+
+DEFINE_EVENT(ata_sff_hsm_template, ata_sff_port_intr,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned char state),
+ TP_ARGS(qc, state));
+
+DECLARE_EVENT_CLASS(ata_transfer_data_template,
+
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count),
+
+ TP_ARGS(qc, offset, count),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned int, ata_dev )
+ __field( unsigned int, tag )
+ __field( unsigned int, flags )
+ __field( unsigned int, offset )
+ __field( unsigned int, bytes )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = qc->ap->print_id;
+ __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno;
+ __entry->tag = qc->tag;
+ __entry->flags = qc->tf.flags;
+ __entry->offset = offset;
+ __entry->bytes = count;
+ ),
+
+ TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s offset=%u bytes=%u",
+ __entry->ata_port, __entry->ata_dev, __entry->tag,
+ __parse_tf_flags(__entry->flags),
+ __entry->offset, __entry->bytes)
+);
+
+DEFINE_EVENT(ata_transfer_data_template, ata_sff_pio_transfer_data,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count),
+ TP_ARGS(qc, offset, count));
+
+DEFINE_EVENT(ata_transfer_data_template, atapi_pio_transfer_data,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count),
+ TP_ARGS(qc, offset, count));
+
+DEFINE_EVENT(ata_transfer_data_template, atapi_send_cdb,
+ TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count),
+ TP_ARGS(qc, offset, count));
+
+DECLARE_EVENT_CLASS(ata_sff_template,
+
+ TP_PROTO(struct ata_port *ap),
+
+ TP_ARGS(ap),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ata_port )
+ __field( unsigned char, hsm_state )
+ ),
+
+ TP_fast_assign(
+ __entry->ata_port = ap->print_id;
+ __entry->hsm_state = ap->hsm_task_state;
+ ),
+
+ TP_printk("ata_port=%u task_state=%s",
+ __entry->ata_port,
+ show_sff_hsm_state_name(__entry->hsm_state))
+);
+
+DEFINE_EVENT(ata_sff_template, ata_sff_flush_pio_task,
+ TP_PROTO(struct ata_port *ap),
+ TP_ARGS(ap));
+
#endif /* _TRACE_LIBATA_H */
/* This part must be outside protection */
diff --git a/include/trace/events/random.h b/include/trace/events/random.h
index 3d7b432..a2d9aa1 100644
--- a/include/trace/events/random.h
+++ b/include/trace/events/random.h
@@ -28,80 +28,71 @@ TRACE_EVENT(add_device_randomness,
);
DECLARE_EVENT_CLASS(random__mix_pool_bytes,
- TP_PROTO(const char *pool_name, int bytes, unsigned long IP),
+ TP_PROTO(int bytes, unsigned long IP),
- TP_ARGS(pool_name, bytes, IP),
+ TP_ARGS(bytes, IP),
TP_STRUCT__entry(
- __field( const char *, pool_name )
__field( int, bytes )
__field(unsigned long, IP )
),
TP_fast_assign(
- __entry->pool_name = pool_name;
__entry->bytes = bytes;
__entry->IP = IP;
),
- TP_printk("%s pool: bytes %d caller %pS",
- __entry->pool_name, __entry->bytes, (void *)__entry->IP)
+ TP_printk("input pool: bytes %d caller %pS",
+ __entry->bytes, (void *)__entry->IP)
);
DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes,
- TP_PROTO(const char *pool_name, int bytes, unsigned long IP),
+ TP_PROTO(int bytes, unsigned long IP),
- TP_ARGS(pool_name, bytes, IP)
+ TP_ARGS(bytes, IP)
);
DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock,
- TP_PROTO(const char *pool_name, int bytes, unsigned long IP),
+ TP_PROTO(int bytes, unsigned long IP),
- TP_ARGS(pool_name, bytes, IP)
+ TP_ARGS(bytes, IP)
);
TRACE_EVENT(credit_entropy_bits,
- TP_PROTO(const char *pool_name, int bits, int entropy_count,
- unsigned long IP),
+ TP_PROTO(int bits, int entropy_count, unsigned long IP),
- TP_ARGS(pool_name, bits, entropy_count, IP),
+ TP_ARGS(bits, entropy_count, IP),
TP_STRUCT__entry(
- __field( const char *, pool_name )
__field( int, bits )
__field( int, entropy_count )
__field(unsigned long, IP )
),
TP_fast_assign(
- __entry->pool_name = pool_name;
__entry->bits = bits;
__entry->entropy_count = entropy_count;
__entry->IP = IP;
),
- TP_printk("%s pool: bits %d entropy_count %d caller %pS",
- __entry->pool_name, __entry->bits,
- __entry->entropy_count, (void *)__entry->IP)
+ TP_printk("input pool: bits %d entropy_count %d caller %pS",
+ __entry->bits, __entry->entropy_count, (void *)__entry->IP)
);
TRACE_EVENT(debit_entropy,
- TP_PROTO(const char *pool_name, int debit_bits),
+ TP_PROTO(int debit_bits),
- TP_ARGS(pool_name, debit_bits),
+ TP_ARGS( debit_bits),
TP_STRUCT__entry(
- __field( const char *, pool_name )
__field( int, debit_bits )
),
TP_fast_assign(
- __entry->pool_name = pool_name;
__entry->debit_bits = debit_bits;
),
- TP_printk("%s: debit_bits %d", __entry->pool_name,
- __entry->debit_bits)
+ TP_printk("input pool: debit_bits %d", __entry->debit_bits)
);
TRACE_EVENT(add_input_randomness,
@@ -170,36 +161,31 @@ DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch,
);
DECLARE_EVENT_CLASS(random__extract_entropy,
- TP_PROTO(const char *pool_name, int nbytes, int entropy_count,
- unsigned long IP),
+ TP_PROTO(int nbytes, int entropy_count, unsigned long IP),
- TP_ARGS(pool_name, nbytes, entropy_count, IP),
+ TP_ARGS(nbytes, entropy_count, IP),
TP_STRUCT__entry(
- __field( const char *, pool_name )
__field( int, nbytes )
__field( int, entropy_count )
__field(unsigned long, IP )
),
TP_fast_assign(
- __entry->pool_name = pool_name;
__entry->nbytes = nbytes;
__entry->entropy_count = entropy_count;
__entry->IP = IP;
),
- TP_printk("%s pool: nbytes %d entropy_count %d caller %pS",
- __entry->pool_name, __entry->nbytes, __entry->entropy_count,
- (void *)__entry->IP)
+ TP_printk("input pool: nbytes %d entropy_count %d caller %pS",
+ __entry->nbytes, __entry->entropy_count, (void *)__entry->IP)
);
DEFINE_EVENT(random__extract_entropy, extract_entropy,
- TP_PROTO(const char *pool_name, int nbytes, int entropy_count,
- unsigned long IP),
+ TP_PROTO(int nbytes, int entropy_count, unsigned long IP),
- TP_ARGS(pool_name, nbytes, entropy_count, IP)
+ TP_ARGS(nbytes, entropy_count, IP)
);
TRACE_EVENT(urandom_read,
diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index c750eac..a8f0ff7 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -28,6 +28,7 @@ enum idxd_scmd_stat {
IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000,
IDXD_SCMD_WQ_NO_SIZE = 0x800e0000,
IDXD_SCMD_WQ_NO_PRIV = 0x800f0000,
+ IDXD_SCMD_WQ_IRQ_ERR = 0x80100000,
};
#define IDXD_SCMD_SOFTERR_MASK 0x80000000
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index dae5df8..0425cd7 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -6,6 +6,7 @@
#define AFFS_SUPER_MAGIC 0xadff
#define AFS_SUPER_MAGIC 0x5346414F
#define AUTOFS_SUPER_MAGIC 0x0187
+#define CEPH_SUPER_MAGIC 0x00c36400
#define CODA_SUPER_MAGIC 0x73757245
#define CRAMFS_MAGIC 0x28cd3d45 /* some random number */
#define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */
diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h
new file mode 100644
index 0000000..42fa15f
--- /dev/null
+++ b/include/uapi/linux/pfrut.h
@@ -0,0 +1,262 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Platform Firmware Runtime Update header
+ *
+ * Copyright(c) 2021 Intel Corporation. All rights reserved.
+ */
+#ifndef __PFRUT_H__
+#define __PFRUT_H__
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define PFRUT_IOCTL_MAGIC 0xEE
+
+/**
+ * PFRU_IOC_SET_REV - _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int)
+ *
+ * Return:
+ * * 0 - success
+ * * -EFAULT - fail to read the revision id
+ * * -EINVAL - user provides an invalid revision id
+ *
+ * Set the Revision ID for Platform Firmware Runtime Update.
+ */
+#define PFRU_IOC_SET_REV _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int)
+
+/**
+ * PFRU_IOC_STAGE - _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - stage phase returns invalid result
+ *
+ * Stage a capsule image from communication buffer and perform authentication.
+ */
+#define PFRU_IOC_STAGE _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int)
+
+/**
+ * PFRU_IOC_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - activate phase returns invalid result
+ *
+ * Activate a previously staged capsule image.
+ */
+#define PFRU_IOC_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int)
+
+/**
+ * PFRU_IOC_STAGE_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - stage/activate phase returns invalid result.
+ *
+ * Perform both stage and activation action.
+ */
+#define PFRU_IOC_STAGE_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int)
+
+/**
+ * PFRU_IOC_QUERY_CAP - _IOR(PFRUT_IOCTL_MAGIC, 0x05,
+ * struct pfru_update_cap_info)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - query phase returns invalid result
+ * * -EFAULT - the result fails to be copied to userspace
+ *
+ * Retrieve information on the Platform Firmware Runtime Update capability.
+ * The information is a struct pfru_update_cap_info.
+ */
+#define PFRU_IOC_QUERY_CAP _IOR(PFRUT_IOCTL_MAGIC, 0x05, struct pfru_update_cap_info)
+
+/**
+ * struct pfru_payload_hdr - Capsule file payload header.
+ *
+ * @sig: Signature of this capsule file.
+ * @hdr_version: Revision of this header structure.
+ * @hdr_size: Size of this header, including the OemHeader bytes.
+ * @hw_ver: The supported firmware version.
+ * @rt_ver: Version of the code injection image.
+ * @platform_id: A platform specific GUID to specify the platform what
+ * this capsule image support.
+ */
+struct pfru_payload_hdr {
+ __u32 sig;
+ __u32 hdr_version;
+ __u32 hdr_size;
+ __u32 hw_ver;
+ __u32 rt_ver;
+ __u8 platform_id[16];
+};
+
+enum pfru_dsm_status {
+ DSM_SUCCEED = 0,
+ DSM_FUNC_NOT_SUPPORT = 1,
+ DSM_INVAL_INPUT = 2,
+ DSM_HARDWARE_ERR = 3,
+ DSM_RETRY_SUGGESTED = 4,
+ DSM_UNKNOWN = 5,
+ DSM_FUNC_SPEC_ERR = 6,
+};
+
+/**
+ * struct pfru_update_cap_info - Runtime update capability information.
+ *
+ * @status: Indicator of whether this query succeed.
+ * @update_cap: Bitmap to indicate whether the feature is supported.
+ * @code_type: A buffer containing an image type GUID.
+ * @fw_version: Platform firmware version.
+ * @code_rt_version: Code injection runtime version for anti-rollback.
+ * @drv_type: A buffer containing an image type GUID.
+ * @drv_rt_version: The version of the driver update runtime code.
+ * @drv_svn: The secure version number(SVN) of the driver update runtime code.
+ * @platform_id: A buffer containing a platform ID GUID.
+ * @oem_id: A buffer containing an OEM ID GUID.
+ * @oem_info_len: Length of the buffer containing the vendor specific information.
+ */
+struct pfru_update_cap_info {
+ __u32 status;
+ __u32 update_cap;
+
+ __u8 code_type[16];
+ __u32 fw_version;
+ __u32 code_rt_version;
+
+ __u8 drv_type[16];
+ __u32 drv_rt_version;
+ __u32 drv_svn;
+
+ __u8 platform_id[16];
+ __u8 oem_id[16];
+
+ __u32 oem_info_len;
+};
+
+/**
+ * struct pfru_com_buf_info - Communication buffer information.
+ *
+ * @status: Indicator of whether this query succeed.
+ * @ext_status: Implementation specific query result.
+ * @addr_lo: Low 32bit physical address of the communication buffer to hold
+ * a runtime update package.
+ * @addr_hi: High 32bit physical address of the communication buffer to hold
+ * a runtime update package.
+ * @buf_size: Maximum size in bytes of the communication buffer.
+ */
+struct pfru_com_buf_info {
+ __u32 status;
+ __u32 ext_status;
+ __u64 addr_lo;
+ __u64 addr_hi;
+ __u32 buf_size;
+};
+
+/**
+ * struct pfru_updated_result - Platform firmware runtime update result information.
+ * @status: Indicator of whether this update succeed.
+ * @ext_status: Implementation specific update result.
+ * @low_auth_time: Low 32bit value of image authentication time in nanosecond.
+ * @high_auth_time: High 32bit value of image authentication time in nanosecond.
+ * @low_exec_time: Low 32bit value of image execution time in nanosecond.
+ * @high_exec_time: High 32bit value of image execution time in nanosecond.
+ */
+struct pfru_updated_result {
+ __u32 status;
+ __u32 ext_status;
+ __u64 low_auth_time;
+ __u64 high_auth_time;
+ __u64 low_exec_time;
+ __u64 high_exec_time;
+};
+
+/**
+ * struct pfrt_log_data_info - Log Data from telemetry service.
+ * @status: Indicator of whether this update succeed.
+ * @ext_status: Implementation specific update result.
+ * @chunk1_addr_lo: Low 32bit physical address of the telemetry data chunk1
+ * starting address.
+ * @chunk1_addr_hi: High 32bit physical address of the telemetry data chunk1
+ * starting address.
+ * @chunk2_addr_lo: Low 32bit physical address of the telemetry data chunk2
+ * starting address.
+ * @chunk2_addr_hi: High 32bit physical address of the telemetry data chunk2
+ * starting address.
+ * @max_data_size: Maximum supported size of data of all data chunks combined.
+ * @chunk1_size: Data size in bytes of the telemetry data chunk1 buffer.
+ * @chunk2_size: Data size in bytes of the telemetry data chunk2 buffer.
+ * @rollover_cnt: Number of times telemetry data buffer is overwritten
+ * since telemetry buffer reset.
+ * @reset_cnt: Number of times telemetry services resets that results in
+ * rollover count and data chunk buffers are reset.
+ */
+struct pfrt_log_data_info {
+ __u32 status;
+ __u32 ext_status;
+ __u64 chunk1_addr_lo;
+ __u64 chunk1_addr_hi;
+ __u64 chunk2_addr_lo;
+ __u64 chunk2_addr_hi;
+ __u32 max_data_size;
+ __u32 chunk1_size;
+ __u32 chunk2_size;
+ __u32 rollover_cnt;
+ __u32 reset_cnt;
+};
+
+/**
+ * struct pfrt_log_info - Telemetry log information.
+ * @log_level: The telemetry log level.
+ * @log_type: The telemetry log type(history and execution).
+ * @log_revid: The telemetry log revision id.
+ */
+struct pfrt_log_info {
+ __u32 log_level;
+ __u32 log_type;
+ __u32 log_revid;
+};
+
+/**
+ * PFRT_LOG_IOC_SET_INFO - _IOW(PFRUT_IOCTL_MAGIC, 0x06,
+ * struct pfrt_log_info)
+ *
+ * Return:
+ * * 0 - success
+ * * -EFAULT - fail to get the setting parameter
+ * * -EINVAL - fail to set the log level
+ *
+ * Set the PFRT log level and log type. The input information is
+ * a struct pfrt_log_info.
+ */
+#define PFRT_LOG_IOC_SET_INFO _IOW(PFRUT_IOCTL_MAGIC, 0x06, struct pfrt_log_info)
+
+/**
+ * PFRT_LOG_IOC_GET_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x07,
+ * struct pfrt_log_info)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - fail to get the log level
+ * * -EFAULT - fail to copy the result back to userspace
+ *
+ * Retrieve log level and log type of the telemetry. The information is
+ * a struct pfrt_log_info.
+ */
+#define PFRT_LOG_IOC_GET_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x07, struct pfrt_log_info)
+
+/**
+ * PFRT_LOG_IOC_GET_DATA_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x08,
+ * struct pfrt_log_data_info)
+ *
+ * Return:
+ * * 0 - success
+ * * -EINVAL - fail to get the log buffer information
+ * * -EFAULT - fail to copy the log buffer information to userspace
+ *
+ * Retrieve data information about the telemetry. The information
+ * is a struct pfrt_log_data_info.
+ */
+#define PFRT_LOG_IOC_GET_DATA_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x08, struct pfrt_log_data_info)
+
+#endif /* __PFRUT_H__ */
diff --git a/include/uapi/linux/soundcard.h b/include/uapi/linux/soundcard.h
index f3b21f9..ac13187 100644
--- a/include/uapi/linux/soundcard.h
+++ b/include/uapi/linux/soundcard.h
@@ -1051,7 +1051,7 @@ typedef struct mixer_vol_table {
* the GPL version of OSS-4.x and build against that version
* of the header.
*
- * We redefine the extern keyword so that make headers_check
+ * We redefine the extern keyword so that usr/include/headers_check.pl
* does not complain about SEQ_USE_EXTBUF.
*/
#define SEQ_DECLAREBUF() SEQ_USE_EXTBUF()
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index ccbd087..12327d3 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -34,7 +34,7 @@
*/
-#define TASKSTATS_VERSION 10
+#define TASKSTATS_VERSION 11
#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
* in linux/sched.h */
@@ -172,6 +172,10 @@ struct taskstats {
/* v10: 64-bit btime to avoid overflow */
__u64 ac_btime64; /* 64-bit begin time */
+
+ /* Delay waiting for memory compact */
+ __u64 compact_count;
+ __u64 compact_delay_total;
};
diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h
index e5a7eec..c0f4bd9 100644
--- a/include/uapi/linux/uuid.h
+++ b/include/uapi/linux/uuid.h
@@ -1,18 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* DO NOT USE in new code! This is solely for MEI due to legacy reasons */
/*
* UUID/GUID definition
*
* Copyright (C) 2010, Intel Corp.
* Huang Ying <ying.huang@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation;
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#ifndef _UAPI_LINUX_UUID_H_
diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h
index a252f06..1061d8d 100644
--- a/include/uapi/linux/vdpa.h
+++ b/include/uapi/linux/vdpa.h
@@ -23,6 +23,9 @@ enum vdpa_command {
enum vdpa_attr {
VDPA_ATTR_UNSPEC,
+ /* Pad attribute for 64b alignment */
+ VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC,
+
/* bus name (optional) + dev name together make the parent device handle */
VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */
VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */
@@ -40,6 +43,9 @@ enum vdpa_attr {
VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */
VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */
+ VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */
+ VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */
+ VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */
/* new attributes must be added above here */
VDPA_ATTR_MAX,
};
diff --git a/init/Kconfig b/init/Kconfig
index fc61bfa..e9119bf 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1414,7 +1414,6 @@
config LD_ORPHAN_WARN
def_bool y
depends on ARCH_WANT_LD_ORPHAN_WARN
- depends on !LD_IS_LLD || LLD_VERSION >= 110000
depends on $(ld-option,--orphan-handling=warn)
config SYSCTL
diff --git a/init/Makefile b/init/Makefile
index 04eeee12..06326e3 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -31,7 +31,7 @@
cmd_compile.h = \
$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)" \
- "$(CONFIG_PREEMPT_RT)" $(CONFIG_CC_VERSION_TEXT) "$(LD)"
+ "$(CONFIG_PREEMPT_RT)" "$(CONFIG_CC_VERSION_TEXT)" "$(LD)"
include/generated/compile.h: FORCE
$(call cmd,compile.h)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 33bb8ae..e16dafe 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5686,7 +5686,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
i, btf_type_str(t));
return -EINVAL;
}
- if (check_ctx_reg(env, reg, regno))
+ if (check_ptr_off_reg(env, reg, regno))
return -EINVAL;
} else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) {
const struct btf_type *reg_ref_t;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 80da1db..5a8d9f7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -648,12 +648,22 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
int opt;
opt = fs_parse(fc, bpf_fs_parameters, param, &result);
- if (opt < 0)
+ if (opt < 0) {
/* We might like to report bad mount options here, but
* traditionally we've ignored all mount options, so we'd
* better continue to ignore non-existing options for bpf.
*/
- return opt == -ENOPARAM ? 0 : opt;
+ if (opt == -ENOPARAM) {
+ opt = vfs_parse_fs_param_source(fc, param);
+ if (opt != -ENOPARAM)
+ return opt;
+
+ return 0;
+ }
+
+ if (opt < 0)
+ return opt;
+ }
switch (opt) {
case OPT_MODE:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bfb4538..a39eede 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -570,6 +570,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
if (type & MEM_RDONLY)
strncpy(prefix, "rdonly_", 16);
+ if (type & MEM_ALLOC)
+ strncpy(prefix, "alloc_", 16);
snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
prefix, str[base_type(type)], postfix);
@@ -616,7 +618,7 @@ static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
{
- env->scratched_stack_slots |= 1UL << spi;
+ env->scratched_stack_slots |= 1ULL << spi;
}
static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
@@ -637,14 +639,14 @@ static bool verifier_state_scratched(const struct bpf_verifier_env *env)
static void mark_verifier_state_clean(struct bpf_verifier_env *env)
{
env->scratched_regs = 0U;
- env->scratched_stack_slots = 0UL;
+ env->scratched_stack_slots = 0ULL;
}
/* Used for printing the entire verifier state. */
static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
{
env->scratched_regs = ~0U;
- env->scratched_stack_slots = ~0UL;
+ env->scratched_stack_slots = ~0ULL;
}
/* The reg state of a pointer or a bounded scalar was saved when
@@ -3969,16 +3971,17 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
}
#endif
-int check_ctx_reg(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno)
+static int __check_ptr_off_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno,
+ bool fixed_off_ok)
{
- /* Access to ctx or passing it to a helper is only allowed in
- * its original, unmodified form.
+ /* Access to this pointer-typed register or passing it to a helper
+ * is only allowed in its original, unmodified form.
*/
- if (reg->off) {
- verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
- regno, reg->off);
+ if (!fixed_off_ok && reg->off) {
+ verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n",
+ reg_type_str(env, reg->type), regno, reg->off);
return -EACCES;
}
@@ -3986,13 +3989,20 @@ int check_ctx_reg(struct bpf_verifier_env *env,
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
+ verbose(env, "variable %s access var_off=%s disallowed\n",
+ reg_type_str(env, reg->type), tn_buf);
return -EACCES;
}
return 0;
}
+int check_ptr_off_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno)
+{
+ return __check_ptr_off_reg(env, reg, regno, false);
+}
+
static int __check_buffer_access(struct bpf_verifier_env *env,
const char *buf_info,
const struct bpf_reg_state *reg,
@@ -4437,7 +4447,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
return -EACCES;
}
- err = check_ctx_reg(env, reg, regno);
+ err = check_ptr_off_reg(env, reg, regno);
if (err < 0)
return err;
@@ -5127,6 +5137,7 @@ static const struct bpf_reg_types mem_types = {
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
PTR_TO_MEM,
+ PTR_TO_MEM | MEM_ALLOC,
PTR_TO_BUF,
},
};
@@ -5144,7 +5155,7 @@ static const struct bpf_reg_types int_ptr_types = {
static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
-static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } };
static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
@@ -5244,12 +5255,6 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
kernel_type_name(btf_vmlinux, *arg_btf_id));
return -EACCES;
}
-
- if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
- verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
- regno);
- return -EACCES;
- }
}
return 0;
@@ -5304,10 +5309,33 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
if (err)
return err;
- if (type == PTR_TO_CTX) {
- err = check_ctx_reg(env, reg, regno);
+ switch ((u32)type) {
+ case SCALAR_VALUE:
+ /* Pointer types where reg offset is explicitly allowed: */
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
+ case PTR_TO_MAP_KEY:
+ case PTR_TO_MAP_VALUE:
+ case PTR_TO_MEM:
+ case PTR_TO_MEM | MEM_RDONLY:
+ case PTR_TO_MEM | MEM_ALLOC:
+ case PTR_TO_BUF:
+ case PTR_TO_BUF | MEM_RDONLY:
+ case PTR_TO_STACK:
+ /* Some of the argument types nevertheless require a
+ * zero register offset.
+ */
+ if (arg_type == ARG_PTR_TO_ALLOC_MEM)
+ goto force_off_check;
+ break;
+ /* All the rest must be rejected: */
+ default:
+force_off_check:
+ err = __check_ptr_off_reg(env, reg, regno,
+ type == PTR_TO_BTF_ID);
if (err < 0)
return err;
+ break;
}
skip_type_check:
@@ -9507,9 +9535,13 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
- if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
- mark_reg_known_zero(env, regs, insn->dst_reg);
+ /* All special src_reg cases are listed below. From this point onwards
+ * we either succeed and assign a corresponding dst_reg->type after
+ * zeroing the offset, or fail and reject the program.
+ */
+ mark_reg_known_zero(env, regs, insn->dst_reg);
+ if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
dst_reg->type = aux->btf_var.reg_type;
switch (base_type(dst_reg->type)) {
case PTR_TO_MEM:
@@ -9547,7 +9579,6 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
map = env->used_maps[aux->map_index];
- mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->map_ptr = map;
if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
@@ -9651,7 +9682,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
- err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg);
+ err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg);
if (err < 0)
return err;
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
new file mode 100644
index 0000000..e9ffb0c
--- /dev/null
+++ b/kernel/configs/debug.config
@@ -0,0 +1,105 @@
+# The config is based on running daily CI for enterprise Linux distros to
+# seek regressions on linux-next builds on different bare-metal and virtual
+# platforms. It can be used for example,
+#
+# $ make ARCH=arm64 defconfig debug.config
+#
+# Keep alphabetically sorted inside each section.
+#
+# printk and dmesg options
+#
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DYNAMIC_DEBUG=y
+CONFIG_PRINTK_CALLER=y
+CONFIG_PRINTK_TIME=y
+CONFIG_SYMBOLIC_ERRNAME=y
+#
+# Compile-time checks and compiler options
+#
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_FRAME_WARN=2048
+CONFIG_SECTION_MISMATCH_WARN_ONLY=y
+#
+# Generic Kernel Debugging Instruments
+#
+# CONFIG_UBSAN_ALIGNMENT is not set
+# CONFIG_UBSAN_DIV_ZERO is not set
+# CONFIG_UBSAN_TRAP is not set
+# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_FS_ALLOW_ALL=y
+CONFIG_DEBUG_IRQFLAGS=y
+CONFIG_UBSAN=y
+CONFIG_UBSAN_BOOL=y
+CONFIG_UBSAN_BOUNDS=y
+CONFIG_UBSAN_ENUM=y
+CONFIG_UBSAN_SHIFT=y
+CONFIG_UBSAN_UNREACHABLE=y
+#
+# Memory Debugging
+#
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF is not set
+# CONFIG_DEBUG_RODATA_TEST is not set
+# CONFIG_DEBUG_WX is not set
+# CONFIG_KFENCE is not set
+# CONFIG_PAGE_POISONING is not set
+# CONFIG_SLUB_STATS is not set
+CONFIG_PAGE_EXTENSION=y
+CONFIG_PAGE_OWNER=y
+CONFIG_DEBUG_KMEMLEAK=y
+CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
+CONFIG_DEBUG_OBJECTS_FREE=y
+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_DEBUG_OBJECTS_TIMERS=y
+CONFIG_DEBUG_OBJECTS_WORK=y
+CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_VIRTUAL=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_PGFLAGS=y
+CONFIG_DEBUG_VM_RB=y
+CONFIG_DEBUG_VM_VMACACHE=y
+CONFIG_GENERIC_PTDUMP=y
+CONFIG_KASAN=y
+CONFIG_KASAN_GENERIC=y
+CONFIG_KASAN_INLINE=y
+CONFIG_KASAN_VMALLOC=y
+CONFIG_PTDUMP_DEBUGFS=y
+CONFIG_SCHED_STACK_END_CHECK=y
+CONFIG_SLUB_DEBUG_ON=y
+#
+# Debug Oops, Lockups and Hangs
+#
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PANIC_TIMEOUT=0
+CONFIG_SOFTLOCKUP_DETECTOR=y
+#
+# Lock Debugging (spinlocks, mutexes, etc...)
+#
+# CONFIG_PROVE_RAW_LOCK_NESTING is not set
+CONFIG_PROVE_LOCKING=y
+#
+# Debug kernel data structures
+#
+CONFIG_BUG_ON_DATA_CORRUPTION=y
+#
+# RCU Debugging
+#
+CONFIG_PROVE_RCU=y
+CONFIG_PROVE_RCU_LIST=y
+#
+# Tracers
+#
+CONFIG_BRANCH_PROFILE_NONE=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 51530d5..c5e8cea 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -100,19 +100,10 @@ void __delayacct_blkio_start(void)
*/
void __delayacct_blkio_end(struct task_struct *p)
{
- struct task_delay_info *delays = p->delays;
- u64 *total;
- u32 *count;
-
- if (p->delays->flags & DELAYACCT_PF_SWAPIN) {
- total = &delays->swapin_delay;
- count = &delays->swapin_count;
- } else {
- total = &delays->blkio_delay;
- count = &delays->blkio_count;
- }
-
- delayacct_end(&delays->lock, &delays->blkio_start, total, count);
+ delayacct_end(&p->delays->lock,
+ &p->delays->blkio_start,
+ &p->delays->blkio_delay,
+ &p->delays->blkio_count);
}
int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
@@ -164,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
+ tmp = d->compact_delay_total + tsk->delays->compact_delay;
+ d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
d->thrashing_count += tsk->delays->thrashing_count;
+ d->compact_count += tsk->delays->compact_count;
raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
@@ -179,8 +173,7 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
unsigned long flags;
raw_spin_lock_irqsave(&tsk->delays->lock, flags);
- ret = nsec_to_clock_t(tsk->delays->blkio_delay +
- tsk->delays->swapin_delay);
+ ret = nsec_to_clock_t(tsk->delays->blkio_delay);
raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return ret;
}
@@ -210,3 +203,29 @@ void __delayacct_thrashing_end(void)
¤t->delays->thrashing_delay,
¤t->delays->thrashing_count);
}
+
+void __delayacct_swapin_start(void)
+{
+ current->delays->swapin_start = local_clock();
+}
+
+void __delayacct_swapin_end(void)
+{
+ delayacct_end(¤t->delays->lock,
+ ¤t->delays->swapin_start,
+ ¤t->delays->swapin_delay,
+ ¤t->delays->swapin_count);
+}
+
+void __delayacct_compact_start(void)
+{
+ current->delays->compact_start = local_clock();
+}
+
+void __delayacct_compact_end(void)
+{
+ delayacct_end(¤t->delays->lock,
+ ¤t->delays->compact_start,
+ ¤t->delays->compact_delay,
+ ¤t->delays->compact_count);
+}
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 0534471..04f4ebd 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -4,7 +4,6 @@
config GCOV_KERNEL
bool "Enable gcov-based kernel profiling"
depends on DEBUG_FS
- depends on !CC_IS_CLANG || CLANG_VERSION >= 110000
depends on !ARCH_WANTS_NO_INSTR || CC_HAS_NO_PROFILE_FN_ATTR
select CONSTRUCTORS
default n
diff --git a/kernel/kthread.c b/kernel/kthread.c
index a2c156e..38c6dd8 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -61,6 +61,8 @@ struct kthread {
#ifdef CONFIG_BLK_CGROUP
struct cgroup_subsys_state *blkcg_css;
#endif
+ /* To store the full name if task comm is truncated. */
+ char *full_name;
};
enum KTHREAD_BITS {
@@ -94,6 +96,18 @@ static inline struct kthread *__to_kthread(struct task_struct *p)
return kthread;
}
+void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
+{
+ struct kthread *kthread = to_kthread(tsk);
+
+ if (!kthread || !kthread->full_name) {
+ __get_task_comm(buf, buf_size, tsk);
+ return;
+ }
+
+ strscpy_pad(buf, kthread->full_name, buf_size);
+}
+
bool set_kthread_struct(struct task_struct *p)
{
struct kthread *kthread;
@@ -121,10 +135,14 @@ void free_kthread_struct(struct task_struct *k)
* Can be NULL if kmalloc() in set_kthread_struct() failed.
*/
kthread = to_kthread(k);
+ if (!kthread)
+ return;
+
#ifdef CONFIG_BLK_CGROUP
- WARN_ON_ONCE(kthread && kthread->blkcg_css);
+ WARN_ON_ONCE(kthread->blkcg_css);
#endif
k->worker_private = NULL;
+ kfree(kthread->full_name);
kfree(kthread);
}
@@ -438,12 +456,22 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
char name[TASK_COMM_LEN];
+ va_list aq;
+ int len;
/*
* task is already visible to other tasks, so updating
* COMM must be protected.
*/
- vsnprintf(name, sizeof(name), namefmt, args);
+ va_copy(aq, args);
+ len = vsnprintf(name, sizeof(name), namefmt, aq);
+ va_end(aq);
+ if (len >= TASK_COMM_LEN) {
+ struct kthread *kthread = to_kthread(task);
+
+ /* leave it truncated when out of memory. */
+ kthread->full_name = kvasprintf(GFP_KERNEL, namefmt, args);
+ }
set_task_comm(task, name);
}
kfree(create);
diff --git a/kernel/panic.c b/kernel/panic.c
index cefd7d8..55b50e0 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -32,6 +32,7 @@
#include <linux/bug.h>
#include <linux/ratelimit.h>
#include <linux/debugfs.h>
+#include <trace/events/error_report.h>
#include <asm/sections.h>
#define PANIC_TIMER_STEP 100
@@ -533,26 +534,9 @@ void oops_enter(void)
trigger_all_cpu_backtrace();
}
-/*
- * 64-bit random ID for oopses:
- */
-static u64 oops_id;
-
-static int init_oops_id(void)
-{
- if (!oops_id)
- get_random_bytes(&oops_id, sizeof(oops_id));
- else
- oops_id++;
-
- return 0;
-}
-late_initcall(init_oops_id);
-
static void print_oops_end_marker(void)
{
- init_oops_id();
- pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
+ pr_warn("---[ end trace %016llx ]---\n", 0ULL);
}
/*
@@ -609,6 +593,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
print_irqtrace_events(current);
print_oops_end_marker();
+ trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller);
/* Just a warning, don't kill lockdep. */
add_taint(taint, LOCKDEP_STILL_OK);
diff --git a/kernel/sys.c b/kernel/sys.c
index 2450a9f..ecc4cf0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -220,7 +220,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
niceval = MAX_NICE;
rcu_read_lock();
- read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
@@ -235,9 +234,11 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
@@ -249,16 +250,15 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
if (!user)
goto out_unlock; /* No processes for this user */
}
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p))
error = set_one_prio(p, niceval, error);
- } while_each_thread(g, p);
+ }
if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
out_unlock:
- read_unlock(&tasklist_lock);
rcu_read_unlock();
out:
return error;
@@ -283,7 +283,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
return -EINVAL;
rcu_read_lock();
- read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
@@ -301,11 +300,13 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
@@ -317,19 +318,18 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
if (!user)
goto out_unlock; /* No processes for this user */
}
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) {
niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
- } while_each_thread(g, p);
+ }
if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
out_unlock:
- read_unlock(&tasklist_lock);
rcu_read_unlock();
return retval;
diff --git a/lib/Kconfig b/lib/Kconfig
index 655b0e43..c20b68a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -122,6 +122,8 @@
mmio accesses when the IO memory address is not a registered
emulated region.
+source "lib/crypto/Kconfig"
+
config CRC_CCITT
tristate "CRC-CCITT functions"
help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c77fe36..14b89aa 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1984,6 +1984,8 @@
bool "Code coverage for fuzzing"
depends on ARCH_HAS_KCOV
depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS
+ depends on !ARCH_WANTS_NO_INSTR || STACK_VALIDATION || \
+ GCC_VERSION >= 120000 || CLANG_VERSION >= 130000
select DEBUG_FS
select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC
help
@@ -2222,12 +2224,11 @@
If unsure, say N.
-config TEST_HASH
- tristate "Perform selftest on hash functions"
+config TEST_SIPHASH
+ tristate "Perform selftest on siphash functions"
help
- Enable this option to test the kernel's integer (<linux/hash.h>),
- string (<linux/stringhash.h>), and siphash (<linux/siphash.h>)
- hash functions on boot (or module load).
+ Enable this option to test the kernel's siphash (<linux/siphash.h>) hash
+ functions on boot (or module load).
This is intended to help people writing architecture-specific
optimized versions. If unsure, say N.
@@ -2371,6 +2372,25 @@
If unsure, say N.
+config HASH_KUNIT_TEST
+ tristate "KUnit Test for integer hash functions" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ default KUNIT_ALL_TESTS
+ help
+ Enable this option to test the kernel's string (<linux/stringhash.h>), and
+ integer (<linux/hash.h>) hash functions on boot.
+
+ KUnit tests run during boot and output the results to the debug log
+ in TAP format (https://testanything.org/). Only useful for kernel devs
+ running the KUnit test harness, and not intended for inclusion into a
+ production build.
+
+ For more information on KUnit and unit tests in general please refer
+ to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+ This is intended to help people writing architecture-specific
+ optimized versions. If unsure, say N.
+
config RESOURCE_KUNIT_TEST
tristate "KUnit test for resource API"
depends on KUNIT
@@ -2502,6 +2522,7 @@
depends on m
depends on NETDEVICES && NET_CORE && INET # for TUN
depends on BLOCK
+ depends on PAGE_SIZE_LESS_THAN_256KB # for BTRFS
select TEST_LKM
select XFS_FS
select TUN
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index e5372a1..236c5ce 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -112,19 +112,6 @@
This option enables -fsanitize=unreachable which checks for control
flow reaching an expected-to-be-unreachable position.
-config UBSAN_OBJECT_SIZE
- bool "Perform checking for accesses beyond the end of objects"
- default UBSAN
- # gcc hugely expands stack usage with -fsanitize=object-size
- # https://lore.kernel.org/lkml/CAHk-=wjPasyJrDuwDnpHJS2TuQfExwe=px-SzLeN8GFMAQJPmQ@mail.gmail.com/
- depends on !CC_IS_GCC
- depends on $(cc-option,-fsanitize=object-size)
- help
- This option enables -fsanitize=object-size which checks for accesses
- beyond the end of objects where the optimizer can determine both the
- object being operated on and its size, usually seen with bad downcasts,
- or access to struct members from NULL pointers.
-
config UBSAN_BOOL
bool "Perform checking for non-boolean values used as boolean"
default UBSAN
diff --git a/lib/Makefile b/lib/Makefile
index b213a7b..300f569 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -61,7 +61,8 @@
obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
CFLAGS_test_bitops.o += -Werror
obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
-obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
+obj-$(CONFIG_TEST_SIPHASH) += test_siphash.o
+obj-$(CONFIG_HASH_KUNIT_TEST) += test_hash.o
obj-$(CONFIG_TEST_IDA) += test_ida.o
obj-$(CONFIG_KASAN_KUNIT_TEST) += test_kasan.o
CFLAGS_test_kasan.o += -fno-builtin
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 8620f38..e8e5256 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -1,5 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
+menu "Crypto library routines"
+
config CRYPTO_LIB_AES
tristate
@@ -31,7 +33,7 @@
config CRYPTO_LIB_CHACHA_GENERIC
tristate
- select CRYPTO_ALGAPI
+ select XOR_BLOCKS
help
This symbol can be depended upon by arch implementations of the
ChaCha library interface that require the generic code as a
@@ -40,7 +42,8 @@
of CRYPTO_LIB_CHACHA.
config CRYPTO_LIB_CHACHA
- tristate
+ tristate "ChaCha library interface"
+ depends on CRYPTO
depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n
help
@@ -65,7 +68,7 @@
of CRYPTO_LIB_CURVE25519.
config CRYPTO_LIB_CURVE25519
- tristate
+ tristate "Curve25519 scalar multiplication library"
depends on CRYPTO_ARCH_HAVE_LIB_CURVE25519 || !CRYPTO_ARCH_HAVE_LIB_CURVE25519
select CRYPTO_LIB_CURVE25519_GENERIC if CRYPTO_ARCH_HAVE_LIB_CURVE25519=n
help
@@ -100,7 +103,7 @@
of CRYPTO_LIB_POLY1305.
config CRYPTO_LIB_POLY1305
- tristate
+ tristate "Poly1305 library interface"
depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305
select CRYPTO_LIB_POLY1305_GENERIC if CRYPTO_ARCH_HAVE_LIB_POLY1305=n
help
@@ -109,14 +112,18 @@
is available and enabled.
config CRYPTO_LIB_CHACHA20POLY1305
- tristate
+ tristate "ChaCha20-Poly1305 AEAD support (8-byte nonce library version)"
depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305
+ depends on CRYPTO
select CRYPTO_LIB_CHACHA
select CRYPTO_LIB_POLY1305
+ select CRYPTO_ALGAPI
config CRYPTO_LIB_SHA256
tristate
config CRYPTO_LIB_SM4
tristate
+
+endmenu
diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c
index 5d9ea53..409e4b7 100644
--- a/lib/crypto/blake2s-selftest.c
+++ b/lib/crypto/blake2s-selftest.c
@@ -15,7 +15,6 @@
* #include <stdio.h>
*
* #include <openssl/evp.h>
- * #include <openssl/hmac.h>
*
* #define BLAKE2S_TESTVEC_COUNT 256
*
@@ -58,16 +57,6 @@
* }
* printf("};\n\n");
*
- * printf("static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n");
- *
- * HMAC(EVP_blake2s256(), key, sizeof(key), buf, sizeof(buf), hash, NULL);
- * print_vec(hash, BLAKE2S_OUTBYTES);
- *
- * HMAC(EVP_blake2s256(), buf, sizeof(buf), key, sizeof(key), hash, NULL);
- * print_vec(hash, BLAKE2S_OUTBYTES);
- *
- * printf("};\n");
- *
* return 0;
*}
*/
@@ -554,15 +543,6 @@ static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {
0xd6, 0x98, 0x6b, 0x07, 0x10, 0x65, 0x52, 0x65, },
};
-static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {
- { 0xce, 0xe1, 0x57, 0x69, 0x82, 0xdc, 0xbf, 0x43, 0xad, 0x56, 0x4c, 0x70,
- 0xed, 0x68, 0x16, 0x96, 0xcf, 0xa4, 0x73, 0xe8, 0xe8, 0xfc, 0x32, 0x79,
- 0x08, 0x0a, 0x75, 0x82, 0xda, 0x3f, 0x05, 0x11, },
- { 0x77, 0x2f, 0x0c, 0x71, 0x41, 0xf4, 0x4b, 0x2b, 0xb3, 0xc6, 0xb6, 0xf9,
- 0x60, 0xde, 0xe4, 0x52, 0x38, 0x66, 0xe8, 0xbf, 0x9b, 0x96, 0xc4, 0x9f,
- 0x60, 0xd9, 0x24, 0x37, 0x99, 0xd6, 0xec, 0x31, },
-};
-
bool __init blake2s_selftest(void)
{
u8 key[BLAKE2S_KEY_SIZE];
@@ -607,16 +587,5 @@ bool __init blake2s_selftest(void)
}
}
- if (success) {
- blake2s256_hmac(hash, buf, key, sizeof(buf), sizeof(key));
- success &= !memcmp(hash, blake2s_hmac_testvecs[0], BLAKE2S_HASH_SIZE);
-
- blake2s256_hmac(hash, key, buf, sizeof(key), sizeof(buf));
- success &= !memcmp(hash, blake2s_hmac_testvecs[1], BLAKE2S_HASH_SIZE);
-
- if (!success)
- pr_err("blake2s256_hmac self-test: FAIL\n");
- }
-
return success;
}
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index 93f2ae0..9364f79 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -30,43 +30,6 @@ void blake2s_final(struct blake2s_state *state, u8 *out)
}
EXPORT_SYMBOL(blake2s_final);
-void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
- const size_t keylen)
-{
- struct blake2s_state state;
- u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 };
- u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32));
- int i;
-
- if (keylen > BLAKE2S_BLOCK_SIZE) {
- blake2s_init(&state, BLAKE2S_HASH_SIZE);
- blake2s_update(&state, key, keylen);
- blake2s_final(&state, x_key);
- } else
- memcpy(x_key, key, keylen);
-
- for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
- x_key[i] ^= 0x36;
-
- blake2s_init(&state, BLAKE2S_HASH_SIZE);
- blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
- blake2s_update(&state, in, inlen);
- blake2s_final(&state, i_hash);
-
- for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
- x_key[i] ^= 0x5c ^ 0x36;
-
- blake2s_init(&state, BLAKE2S_HASH_SIZE);
- blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
- blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE);
- blake2s_final(&state, i_hash);
-
- memcpy(out, i_hash, BLAKE2S_HASH_SIZE);
- memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE);
- memzero_explicit(i_hash, BLAKE2S_HASH_SIZE);
-}
-EXPORT_SYMBOL(blake2s256_hmac);
-
static int __init blake2s_mod_init(void)
{
if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 059b8b0..886510d 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -22,6 +22,7 @@
#include "kstrtox.h"
+noinline
const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
{
if (*base == 0) {
@@ -47,6 +48,7 @@ const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
*
* Don't you dare use this function.
*/
+noinline
unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p,
size_t max_chars)
{
@@ -85,6 +87,7 @@ unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned lon
return rv;
}
+noinline
unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p)
{
return _parse_integer_limit(s, base, p, INT_MAX);
@@ -125,6 +128,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoull(). Return code must be checked.
*/
+noinline
int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
{
if (s[0] == '+')
@@ -148,6 +152,7 @@ EXPORT_SYMBOL(kstrtoull);
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoll(). Return code must be checked.
*/
+noinline
int kstrtoll(const char *s, unsigned int base, long long *res)
{
unsigned long long tmp;
@@ -219,6 +224,7 @@ EXPORT_SYMBOL(_kstrtol);
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoul(). Return code must be checked.
*/
+noinline
int kstrtouint(const char *s, unsigned int base, unsigned int *res)
{
unsigned long long tmp;
@@ -249,6 +255,7 @@ EXPORT_SYMBOL(kstrtouint);
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtol(). Return code must be checked.
*/
+noinline
int kstrtoint(const char *s, unsigned int base, int *res)
{
long long tmp;
@@ -264,6 +271,7 @@ int kstrtoint(const char *s, unsigned int base, int *res)
}
EXPORT_SYMBOL(kstrtoint);
+noinline
int kstrtou16(const char *s, unsigned int base, u16 *res)
{
unsigned long long tmp;
@@ -279,6 +287,7 @@ int kstrtou16(const char *s, unsigned int base, u16 *res)
}
EXPORT_SYMBOL(kstrtou16);
+noinline
int kstrtos16(const char *s, unsigned int base, s16 *res)
{
long long tmp;
@@ -294,6 +303,7 @@ int kstrtos16(const char *s, unsigned int base, s16 *res)
}
EXPORT_SYMBOL(kstrtos16);
+noinline
int kstrtou8(const char *s, unsigned int base, u8 *res)
{
unsigned long long tmp;
@@ -309,6 +319,7 @@ int kstrtou8(const char *s, unsigned int base, u8 *res)
}
EXPORT_SYMBOL(kstrtou8);
+noinline
int kstrtos8(const char *s, unsigned int base, s8 *res)
{
long long tmp;
@@ -333,6 +344,7 @@ EXPORT_SYMBOL(kstrtos8);
* [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value
* pointed to by res is updated upon finding a match.
*/
+noinline
int kstrtobool(const char *s, bool *res)
{
if (!s)
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 5d5424b..9daa3fb 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -49,11 +49,11 @@ bool __list_del_entry_valid(struct list_head *entry)
"list_del corruption, %px->prev is LIST_POISON2 (%px)\n",
entry, LIST_POISON2) ||
CHECK_DATA_CORRUPTION(prev->next != entry,
- "list_del corruption. prev->next should be %px, but was %px\n",
- entry, prev->next) ||
+ "list_del corruption. prev->next should be %px, but was %px. (prev=%px)\n",
+ entry, prev->next, prev) ||
CHECK_DATA_CORRUPTION(next->prev != entry,
- "list_del corruption. next->prev should be %px, but was %px\n",
- entry, next->prev))
+ "list_del corruption. next->prev should be %px, but was %px. (next=%px)\n",
+ entry, next->prev, next))
return false;
return true;
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 673bd20..330aa53 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -36,6 +36,8 @@
*/
#include <asm/unaligned.h>
+
+#include <linux/bitops.h>
#include <linux/string.h> /* memset, memcpy */
#define FORCE_INLINE __always_inline
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index 0ae2e66..a6789c0 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -69,9 +69,12 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir,
unsigned long entries[REF_TRACKER_STACK_ENTRIES];
struct ref_tracker *tracker;
unsigned int nr_entries;
+ gfp_t gfp_mask = gfp;
unsigned long flags;
- *trackerp = tracker = kzalloc(sizeof(*tracker), gfp | __GFP_NOFAIL);
+ if (gfp & __GFP_DIRECT_RECLAIM)
+ gfp_mask |= __GFP_NOFAIL;
+ *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask);
if (unlikely(!tracker)) {
pr_err_once("memory allocation failure, unreliable refcount tracker.\n");
refcount_inc(&dir->untracked);
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 2709ab8..6220fa6 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -457,10 +457,9 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
}
EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
-static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
- unsigned int depth)
+static inline void __sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int wake_batch)
{
- unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth);
int i;
if (sbq->wake_batch != wake_batch) {
@@ -476,6 +475,26 @@ static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
}
}
+static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int depth)
+{
+ unsigned int wake_batch;
+
+ wake_batch = sbq_calc_wake_batch(sbq, depth);
+ __sbitmap_queue_update_wake_batch(sbq, wake_batch);
+}
+
+void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int users)
+{
+ unsigned int wake_batch;
+
+ wake_batch = clamp_val((sbq->sb.depth + users - 1) /
+ users, 4, SBQ_WAKE_BATCH);
+ __sbitmap_queue_update_wake_batch(sbq, wake_batch);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch);
+
void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
{
sbitmap_queue_update_wake_batch(sbq, depth);
diff --git a/lib/sha1.c b/lib/sha1.c
index 9bd1935..0494766 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/bitops.h>
+#include <linux/string.h>
#include <crypto/sha1.h>
#include <asm/unaligned.h>
@@ -55,7 +56,8 @@
#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
__u32 TEMP = input(t); setW(t, TEMP); \
E += TEMP + rol32(A,5) + (fn) + (constant); \
- B = ror32(B, 2); } while (0)
+ B = ror32(B, 2); \
+ TEMP = E; E = D; D = C; C = B; B = A; A = TEMP; } while (0)
#define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
@@ -84,6 +86,7 @@
void sha1_transform(__u32 *digest, const char *data, __u32 *array)
{
__u32 A, B, C, D, E;
+ unsigned int i = 0;
A = digest[0];
B = digest[1];
@@ -92,94 +95,24 @@ void sha1_transform(__u32 *digest, const char *data, __u32 *array)
E = digest[4];
/* Round 1 - iterations 0-16 take their input from 'data' */
- T_0_15( 0, A, B, C, D, E);
- T_0_15( 1, E, A, B, C, D);
- T_0_15( 2, D, E, A, B, C);
- T_0_15( 3, C, D, E, A, B);
- T_0_15( 4, B, C, D, E, A);
- T_0_15( 5, A, B, C, D, E);
- T_0_15( 6, E, A, B, C, D);
- T_0_15( 7, D, E, A, B, C);
- T_0_15( 8, C, D, E, A, B);
- T_0_15( 9, B, C, D, E, A);
- T_0_15(10, A, B, C, D, E);
- T_0_15(11, E, A, B, C, D);
- T_0_15(12, D, E, A, B, C);
- T_0_15(13, C, D, E, A, B);
- T_0_15(14, B, C, D, E, A);
- T_0_15(15, A, B, C, D, E);
+ for (; i < 16; ++i)
+ T_0_15(i, A, B, C, D, E);
/* Round 1 - tail. Input from 512-bit mixing array */
- T_16_19(16, E, A, B, C, D);
- T_16_19(17, D, E, A, B, C);
- T_16_19(18, C, D, E, A, B);
- T_16_19(19, B, C, D, E, A);
+ for (; i < 20; ++i)
+ T_16_19(i, A, B, C, D, E);
/* Round 2 */
- T_20_39(20, A, B, C, D, E);
- T_20_39(21, E, A, B, C, D);
- T_20_39(22, D, E, A, B, C);
- T_20_39(23, C, D, E, A, B);
- T_20_39(24, B, C, D, E, A);
- T_20_39(25, A, B, C, D, E);
- T_20_39(26, E, A, B, C, D);
- T_20_39(27, D, E, A, B, C);
- T_20_39(28, C, D, E, A, B);
- T_20_39(29, B, C, D, E, A);
- T_20_39(30, A, B, C, D, E);
- T_20_39(31, E, A, B, C, D);
- T_20_39(32, D, E, A, B, C);
- T_20_39(33, C, D, E, A, B);
- T_20_39(34, B, C, D, E, A);
- T_20_39(35, A, B, C, D, E);
- T_20_39(36, E, A, B, C, D);
- T_20_39(37, D, E, A, B, C);
- T_20_39(38, C, D, E, A, B);
- T_20_39(39, B, C, D, E, A);
+ for (; i < 40; ++i)
+ T_20_39(i, A, B, C, D, E);
/* Round 3 */
- T_40_59(40, A, B, C, D, E);
- T_40_59(41, E, A, B, C, D);
- T_40_59(42, D, E, A, B, C);
- T_40_59(43, C, D, E, A, B);
- T_40_59(44, B, C, D, E, A);
- T_40_59(45, A, B, C, D, E);
- T_40_59(46, E, A, B, C, D);
- T_40_59(47, D, E, A, B, C);
- T_40_59(48, C, D, E, A, B);
- T_40_59(49, B, C, D, E, A);
- T_40_59(50, A, B, C, D, E);
- T_40_59(51, E, A, B, C, D);
- T_40_59(52, D, E, A, B, C);
- T_40_59(53, C, D, E, A, B);
- T_40_59(54, B, C, D, E, A);
- T_40_59(55, A, B, C, D, E);
- T_40_59(56, E, A, B, C, D);
- T_40_59(57, D, E, A, B, C);
- T_40_59(58, C, D, E, A, B);
- T_40_59(59, B, C, D, E, A);
+ for (; i < 60; ++i)
+ T_40_59(i, A, B, C, D, E);
/* Round 4 */
- T_60_79(60, A, B, C, D, E);
- T_60_79(61, E, A, B, C, D);
- T_60_79(62, D, E, A, B, C);
- T_60_79(63, C, D, E, A, B);
- T_60_79(64, B, C, D, E, A);
- T_60_79(65, A, B, C, D, E);
- T_60_79(66, E, A, B, C, D);
- T_60_79(67, D, E, A, B, C);
- T_60_79(68, C, D, E, A, B);
- T_60_79(69, B, C, D, E, A);
- T_60_79(70, A, B, C, D, E);
- T_60_79(71, E, A, B, C, D);
- T_60_79(72, D, E, A, B, C);
- T_60_79(73, C, D, E, A, B);
- T_60_79(74, B, C, D, E, A);
- T_60_79(75, A, B, C, D, E);
- T_60_79(76, E, A, B, C, D);
- T_60_79(77, D, E, A, B, C);
- T_60_79(78, C, D, E, A, B);
- T_60_79(79, B, C, D, E, A);
+ for (; i < 80; ++i)
+ T_60_79(i, A, B, C, D, E);
digest[0] += A;
digest[1] += B;
diff --git a/lib/test_hash.c b/lib/test_hash.c
index 0ee40b4..bb25fda3 100644
--- a/lib/test_hash.c
+++ b/lib/test_hash.c
@@ -14,17 +14,15 @@
* and hash_64().
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt "\n"
-
#include <linux/compiler.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/hash.h>
#include <linux/stringhash.h>
-#include <linux/printk.h>
+#include <kunit/test.h>
/* 32-bit XORSHIFT generator. Seed must not be zero. */
-static u32 __init __attribute_const__
+static u32 __attribute_const__
xorshift(u32 seed)
{
seed ^= seed << 13;
@@ -34,7 +32,7 @@ xorshift(u32 seed)
}
/* Given a non-zero x, returns a non-zero byte. */
-static u8 __init __attribute_const__
+static u8 __attribute_const__
mod255(u32 x)
{
x = (x & 0xffff) + (x >> 16); /* 1 <= x <= 0x1fffe */
@@ -45,8 +43,7 @@ mod255(u32 x)
}
/* Fill the buffer with non-zero bytes. */
-static void __init
-fill_buf(char *buf, size_t len, u32 seed)
+static void fill_buf(char *buf, size_t len, u32 seed)
{
size_t i;
@@ -56,6 +53,50 @@ fill_buf(char *buf, size_t len, u32 seed)
}
}
+/* Holds most testing variables for the int test. */
+struct test_hash_params {
+ /* Pointer to integer to be hashed. */
+ unsigned long long *h64;
+ /* Low 32-bits of integer to be hashed. */
+ u32 h0;
+ /* Arch-specific hash result. */
+ u32 h1;
+ /* Generic hash result. */
+ u32 h2;
+ /* ORed hashes of given size (in bits). */
+ u32 (*hash_or)[33];
+};
+
+#ifdef HAVE_ARCH__HASH_32
+static void
+test_int__hash_32(struct kunit *test, struct test_hash_params *params)
+{
+ params->hash_or[1][0] |= params->h2 = __hash_32_generic(params->h0);
+#if HAVE_ARCH__HASH_32 == 1
+ KUNIT_EXPECT_EQ_MSG(test, params->h1, params->h2,
+ "__hash_32(%#x) = %#x != __hash_32_generic() = %#x",
+ params->h0, params->h1, params->h2);
+#endif
+}
+#endif
+
+#ifdef HAVE_ARCH_HASH_64
+static void
+test_int_hash_64(struct kunit *test, struct test_hash_params *params, u32 const *m, int *k)
+{
+ params->h2 = hash_64_generic(*params->h64, *k);
+#if HAVE_ARCH_HASH_64 == 1
+ KUNIT_EXPECT_EQ_MSG(test, params->h1, params->h2,
+ "hash_64(%#llx, %d) = %#x != hash_64_generic() = %#x",
+ *params->h64, *k, params->h1, params->h2);
+#else
+ KUNIT_EXPECT_LE_MSG(test, params->h1, params->h2,
+ "hash_64_generic(%#llx, %d) = %#x > %#x",
+ *params->h64, *k, params->h1, *m);
+#endif
+}
+#endif
+
/*
* Test the various integer hash functions. h64 (or its low-order bits)
* is the integer to hash. hash_or accumulates the OR of the hash values,
@@ -65,23 +106,16 @@ fill_buf(char *buf, size_t len, u32 seed)
* inline, the code being tested is actually in the module, and you can
* recompile and re-test the module without rebooting.
*/
-static bool __init
-test_int_hash(unsigned long long h64, u32 hash_or[2][33])
+static void
+test_int_hash(struct kunit *test, unsigned long long h64, u32 hash_or[2][33])
{
int k;
- u32 h0 = (u32)h64, h1, h2;
+ struct test_hash_params params = { &h64, (u32)h64, 0, 0, hash_or };
/* Test __hash32 */
- hash_or[0][0] |= h1 = __hash_32(h0);
+ hash_or[0][0] |= params.h1 = __hash_32(params.h0);
#ifdef HAVE_ARCH__HASH_32
- hash_or[1][0] |= h2 = __hash_32_generic(h0);
-#if HAVE_ARCH__HASH_32 == 1
- if (h1 != h2) {
- pr_err("__hash_32(%#x) = %#x != __hash_32_generic() = %#x",
- h0, h1, h2);
- return false;
- }
-#endif
+ test_int__hash_32(test, ¶ms);
#endif
/* Test k = 1..32 bits */
@@ -89,63 +123,53 @@ test_int_hash(unsigned long long h64, u32 hash_or[2][33])
u32 const m = ((u32)2 << (k-1)) - 1; /* Low k bits set */
/* Test hash_32 */
- hash_or[0][k] |= h1 = hash_32(h0, k);
- if (h1 > m) {
- pr_err("hash_32(%#x, %d) = %#x > %#x", h0, k, h1, m);
- return false;
- }
-#ifdef HAVE_ARCH_HASH_32
- h2 = hash_32_generic(h0, k);
-#if HAVE_ARCH_HASH_32 == 1
- if (h1 != h2) {
- pr_err("hash_32(%#x, %d) = %#x != hash_32_generic() "
- " = %#x", h0, k, h1, h2);
- return false;
- }
-#else
- if (h2 > m) {
- pr_err("hash_32_generic(%#x, %d) = %#x > %#x",
- h0, k, h1, m);
- return false;
- }
-#endif
-#endif
+ hash_or[0][k] |= params.h1 = hash_32(params.h0, k);
+ KUNIT_EXPECT_LE_MSG(test, params.h1, m,
+ "hash_32(%#x, %d) = %#x > %#x",
+ params.h0, k, params.h1, m);
+
/* Test hash_64 */
- hash_or[1][k] |= h1 = hash_64(h64, k);
- if (h1 > m) {
- pr_err("hash_64(%#llx, %d) = %#x > %#x", h64, k, h1, m);
- return false;
- }
+ hash_or[1][k] |= params.h1 = hash_64(h64, k);
+ KUNIT_EXPECT_LE_MSG(test, params.h1, m,
+ "hash_64(%#llx, %d) = %#x > %#x",
+ h64, k, params.h1, m);
#ifdef HAVE_ARCH_HASH_64
- h2 = hash_64_generic(h64, k);
-#if HAVE_ARCH_HASH_64 == 1
- if (h1 != h2) {
- pr_err("hash_64(%#llx, %d) = %#x != hash_64_generic() "
- "= %#x", h64, k, h1, h2);
- return false;
- }
-#else
- if (h2 > m) {
- pr_err("hash_64_generic(%#llx, %d) = %#x > %#x",
- h64, k, h1, m);
- return false;
- }
-#endif
+ test_int_hash_64(test, ¶ms, &m, &k);
#endif
}
-
- (void)h2; /* Suppress unused variable warning */
- return true;
}
#define SIZE 256 /* Run time is cubic in SIZE */
-static int __init
-test_hash_init(void)
+static void test_string_or(struct kunit *test)
{
char buf[SIZE+1];
- u32 string_or = 0, hash_or[2][33] = { { 0, } };
- unsigned tests = 0;
+ u32 string_or = 0;
+ int i, j;
+
+ fill_buf(buf, SIZE, 1);
+
+ /* Test every possible non-empty substring in the buffer. */
+ for (j = SIZE; j > 0; --j) {
+ buf[j] = '\0';
+
+ for (i = 0; i <= j; i++) {
+ u32 h0 = full_name_hash(buf+i, buf+i, j-i);
+
+ string_or |= h0;
+ } /* i */
+ } /* j */
+
+ /* The OR of all the hash values should cover all the bits */
+ KUNIT_EXPECT_EQ_MSG(test, string_or, -1u,
+ "OR of all string hash results = %#x != %#x",
+ string_or, -1u);
+}
+
+static void test_hash_or(struct kunit *test)
+{
+ char buf[SIZE+1];
+ u32 hash_or[2][33] = { { 0, } };
unsigned long long h64 = 0;
int i, j;
@@ -160,46 +184,27 @@ test_hash_init(void)
u32 h0 = full_name_hash(buf+i, buf+i, j-i);
/* Check that hashlen_string gets the length right */
- if (hashlen_len(hashlen) != j-i) {
- pr_err("hashlen_string(%d..%d) returned length"
- " %u, expected %d",
- i, j, hashlen_len(hashlen), j-i);
- return -EINVAL;
- }
+ KUNIT_EXPECT_EQ_MSG(test, hashlen_len(hashlen), j-i,
+ "hashlen_string(%d..%d) returned length %u, expected %d",
+ i, j, hashlen_len(hashlen), j-i);
/* Check that the hashes match */
- if (hashlen_hash(hashlen) != h0) {
- pr_err("hashlen_string(%d..%d) = %08x != "
- "full_name_hash() = %08x",
- i, j, hashlen_hash(hashlen), h0);
- return -EINVAL;
- }
+ KUNIT_EXPECT_EQ_MSG(test, hashlen_hash(hashlen), h0,
+ "hashlen_string(%d..%d) = %08x != full_name_hash() = %08x",
+ i, j, hashlen_hash(hashlen), h0);
- string_or |= h0;
h64 = h64 << 32 | h0; /* For use with hash_64 */
- if (!test_int_hash(h64, hash_or))
- return -EINVAL;
- tests++;
+ test_int_hash(test, h64, hash_or);
} /* i */
} /* j */
- /* The OR of all the hash values should cover all the bits */
- if (~string_or) {
- pr_err("OR of all string hash results = %#x != %#x",
- string_or, -1u);
- return -EINVAL;
- }
- if (~hash_or[0][0]) {
- pr_err("OR of all __hash_32 results = %#x != %#x",
- hash_or[0][0], -1u);
- return -EINVAL;
- }
+ KUNIT_EXPECT_EQ_MSG(test, hash_or[0][0], -1u,
+ "OR of all __hash_32 results = %#x != %#x",
+ hash_or[0][0], -1u);
#ifdef HAVE_ARCH__HASH_32
#if HAVE_ARCH__HASH_32 != 1 /* Test is pointless if results match */
- if (~hash_or[1][0]) {
- pr_err("OR of all __hash_32_generic results = %#x != %#x",
- hash_or[1][0], -1u);
- return -EINVAL;
- }
+ KUNIT_EXPECT_EQ_MSG(test, hash_or[1][0], -1u,
+ "OR of all __hash_32_generic results = %#x != %#x",
+ hash_or[1][0], -1u);
#endif
#endif
@@ -207,51 +212,27 @@ test_hash_init(void)
for (i = 1; i <= 32; i++) {
u32 const m = ((u32)2 << (i-1)) - 1; /* Low i bits set */
- if (hash_or[0][i] != m) {
- pr_err("OR of all hash_32(%d) results = %#x "
- "(%#x expected)", i, hash_or[0][i], m);
- return -EINVAL;
- }
- if (hash_or[1][i] != m) {
- pr_err("OR of all hash_64(%d) results = %#x "
- "(%#x expected)", i, hash_or[1][i], m);
- return -EINVAL;
- }
+ KUNIT_EXPECT_EQ_MSG(test, hash_or[0][i], m,
+ "OR of all hash_32(%d) results = %#x (%#x expected)",
+ i, hash_or[0][i], m);
+ KUNIT_EXPECT_EQ_MSG(test, hash_or[1][i], m,
+ "OR of all hash_64(%d) results = %#x (%#x expected)",
+ i, hash_or[1][i], m);
}
-
- /* Issue notices about skipped tests. */
-#ifdef HAVE_ARCH__HASH_32
-#if HAVE_ARCH__HASH_32 != 1
- pr_info("__hash_32() is arch-specific; not compared to generic.");
-#endif
-#else
- pr_info("__hash_32() has no arch implementation to test.");
-#endif
-#ifdef HAVE_ARCH_HASH_32
-#if HAVE_ARCH_HASH_32 != 1
- pr_info("hash_32() is arch-specific; not compared to generic.");
-#endif
-#else
- pr_info("hash_32() has no arch implementation to test.");
-#endif
-#ifdef HAVE_ARCH_HASH_64
-#if HAVE_ARCH_HASH_64 != 1
- pr_info("hash_64() is arch-specific; not compared to generic.");
-#endif
-#else
- pr_info("hash_64() has no arch implementation to test.");
-#endif
-
- pr_notice("%u tests passed.", tests);
-
- return 0;
}
-static void __exit test_hash_exit(void)
-{
-}
+static struct kunit_case hash_test_cases[] __refdata = {
+ KUNIT_CASE(test_string_or),
+ KUNIT_CASE(test_hash_or),
+ {}
+};
-module_init(test_hash_init); /* Does everything */
-module_exit(test_hash_exit); /* Does nothing */
+static struct kunit_suite hash_test_suite = {
+ .name = "hash",
+ .test_cases = hash_test_cases,
+};
+
+
+kunit_test_suite(hash_test_suite);
MODULE_LICENSE("GPL");
diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index e4f706a..3ca717f 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -337,6 +337,7 @@ static int __init do_kmem_cache_size_bulk(int size, int *total_failures)
if (num)
kmem_cache_free_bulk(c, num, objects);
}
+ kmem_cache_destroy(c);
*total_failures += fail;
return 1;
}
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
index 7e7bbd0..2062be1 100644
--- a/lib/test_ubsan.c
+++ b/lib/test_ubsan.c
@@ -79,15 +79,6 @@ static void test_ubsan_load_invalid_value(void)
eval2 = eval;
}
-static void test_ubsan_null_ptr_deref(void)
-{
- volatile int *ptr = NULL;
- int val;
-
- UBSAN_TEST(CONFIG_UBSAN_OBJECT_SIZE);
- val = *ptr;
-}
-
static void test_ubsan_misaligned_access(void)
{
volatile char arr[5] __aligned(4) = {1, 2, 3, 4, 5};
@@ -98,29 +89,16 @@ static void test_ubsan_misaligned_access(void)
*ptr = val;
}
-static void test_ubsan_object_size_mismatch(void)
-{
- /* "((aligned(8)))" helps this not into be misaligned for ptr-access. */
- volatile int val __aligned(8) = 4;
- volatile long long *ptr, val2;
-
- UBSAN_TEST(CONFIG_UBSAN_OBJECT_SIZE);
- ptr = (long long *)&val;
- val2 = *ptr;
-}
-
static const test_ubsan_fp test_ubsan_array[] = {
test_ubsan_shift_out_of_bounds,
test_ubsan_out_of_bounds,
test_ubsan_load_invalid_value,
test_ubsan_misaligned_access,
- test_ubsan_object_size_mismatch,
};
/* Excluded because they Oops the module. */
static const test_ubsan_fp skip_ubsan_array[] = {
test_ubsan_divrem_overflow,
- test_ubsan_null_ptr_deref,
};
static int __init test_ubsan_init(void)
diff --git a/mm/Kconfig b/mm/Kconfig
index 53d7485..a99bd49 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -432,6 +432,18 @@
bool
default y
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+ bool
+
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
+ bool
+
+config USE_PERCPU_NUMA_NODE_ID
+ bool
+
+config HAVE_SETUP_PER_CPU_AREA
+ bool
+
config CLEANCACHE
bool "Enable cleancache driver to cache clean pages if tmem is present"
help
diff --git a/mm/filemap.c b/mm/filemap.c
index 2fd9b2f..afc8f5c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -231,17 +231,15 @@ void __filemap_remove_folio(struct folio *folio, void *shadow)
void filemap_free_folio(struct address_space *mapping, struct folio *folio)
{
void (*freepage)(struct page *);
+ int refs = 1;
freepage = mapping->a_ops->freepage;
if (freepage)
freepage(&folio->page);
- if (folio_test_large(folio) && !folio_test_hugetlb(folio)) {
- folio_ref_sub(folio, folio_nr_pages(folio));
- VM_BUG_ON_FOLIO(folio_ref_count(folio) <= 0, folio);
- } else {
- folio_put(folio);
- }
+ if (folio_test_large(folio) && !folio_test_hugetlb(folio))
+ refs = folio_nr_pages(folio);
+ folio_put_refs(folio, refs);
}
/**
diff --git a/mm/memory.c b/mm/memory.c
index f306e69..c125c49 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3529,7 +3529,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
if (unlikely(!si))
goto out;
- delayacct_set_flag(current, DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry, vma, vmf->address);
swapcache = page;
@@ -3577,7 +3576,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
vmf->address, &vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
- delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
goto unlock;
}
@@ -3591,13 +3589,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
* owner processes (which may be unknown at hwpoison time)
*/
ret = VM_FAULT_HWPOISON;
- delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
goto out_release;
}
locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags);
- delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
if (!locked) {
ret |= VM_FAULT_RETRY;
goto out_release;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d4205e5..3589feb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -74,6 +74,7 @@
#include <linux/padata.h>
#include <linux/khugepaged.h>
#include <linux/buffer_head.h>
+#include <linux/delayacct.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -4365,6 +4366,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
psi_memstall_enter(&pflags);
+ delayacct_compact_start();
noreclaim_flag = memalloc_noreclaim_save();
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
@@ -4372,6 +4374,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
+ delayacct_compact_end();
if (*compact_result == COMPACT_SKIPPED)
return NULL;
diff --git a/mm/page_io.c b/mm/page_io.c
index 9725c7e..0bf8e40 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -25,6 +25,7 @@
#include <linux/psi.h>
#include <linux/uio.h>
#include <linux/sched/task.h>
+#include <linux/delayacct.h>
void end_swap_bio_write(struct bio *bio)
{
@@ -370,6 +371,7 @@ int swap_readpage(struct page *page, bool synchronous)
* significant part of overall IO time.
*/
psi_memstall_enter(&pflags);
+ delayacct_swapin_start();
if (frontswap_load(page) == 0) {
SetPageUptodate(page);
@@ -432,6 +434,7 @@ int swap_readpage(struct page *page, bool synchronous)
out:
psi_memstall_leave(&pflags);
+ delayacct_swapin_end();
return ret;
}
diff --git a/mm/percpu.c b/mm/percpu.c
index 4199a06..a188ac9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2992,6 +2992,42 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
return ai;
}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align,
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
+{
+ const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NUMA
+ int node = NUMA_NO_NODE;
+ void *ptr;
+
+ if (cpu_to_nd_fn)
+ node = cpu_to_nd_fn(cpu);
+
+ if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) {
+ ptr = memblock_alloc_from(size, align, goal);
+ pr_info("cpu %d has no node %d or node-local memory\n",
+ cpu, node);
+ pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n",
+ cpu, size, (u64)__pa(ptr));
+ } else {
+ ptr = memblock_alloc_try_nid(size, align, goal,
+ MEMBLOCK_ALLOC_ACCESSIBLE,
+ node);
+
+ pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n",
+ cpu, size, node, (u64)__pa(ptr));
+ }
+ return ptr;
+#else
+ return memblock_alloc_from(size, align, goal);
+#endif
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+ memblock_free(ptr, size);
+}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
#if defined(BUILD_EMBED_FIRST_CHUNK)
@@ -3001,14 +3037,13 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
* @dyn_size: minimum free size for dynamic allocation in bytes
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
- * @alloc_fn: function to allocate percpu page
- * @free_fn: function to free percpu page
+ * @cpu_to_nd_fn: callback to convert cpu to it's node, optional
*
* This is a helper to ease setting up embedded first percpu chunk and
* can be called where pcpu_setup_first_chunk() is expected.
*
* If this function is used to setup the first chunk, it is allocated
- * by calling @alloc_fn and used as-is without being mapped into
+ * by calling pcpu_fc_alloc and used as-is without being mapped into
* vmalloc area. Allocations are always whole multiples of @atom_size
* aligned to @atom_size.
*
@@ -3022,7 +3057,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
* @dyn_size specifies the minimum dynamic area size.
*
* If the needed size is smaller than the minimum or specified unit
- * size, the leftover is returned using @free_fn.
+ * size, the leftover is returned using pcpu_fc_free.
*
* RETURNS:
* 0 on success, -errno on failure.
@@ -3030,8 +3065,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
- pcpu_fc_alloc_fn_t alloc_fn,
- pcpu_fc_free_fn_t free_fn)
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
void *base = (void *)ULONG_MAX;
void **areas = NULL;
@@ -3066,7 +3100,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
BUG_ON(cpu == NR_CPUS);
/* allocate space for the whole group */
- ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
+ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn);
if (!ptr) {
rc = -ENOMEM;
goto out_free_areas;
@@ -3105,12 +3139,12 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
if (gi->cpu_map[i] == NR_CPUS) {
/* unused unit, free whole */
- free_fn(ptr, ai->unit_size);
+ pcpu_fc_free(ptr, ai->unit_size);
continue;
}
/* copy and return the unused part */
memcpy(ptr, __per_cpu_load, ai->static_size);
- free_fn(ptr + size_sum, ai->unit_size - size_sum);
+ pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
}
}
@@ -3129,7 +3163,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
out_free_areas:
for (group = 0; group < ai->nr_groups; group++)
if (areas[group])
- free_fn(areas[group],
+ pcpu_fc_free(areas[group],
ai->groups[group].nr_units * ai->unit_size);
out_free:
pcpu_free_alloc_info(ai);
@@ -3140,12 +3174,79 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
#endif /* BUILD_EMBED_FIRST_CHUNK */
#ifdef BUILD_PAGE_FIRST_CHUNK
+#include <asm/pgalloc.h>
+
+#ifndef P4D_TABLE_SIZE
+#define P4D_TABLE_SIZE PAGE_SIZE
+#endif
+
+#ifndef PUD_TABLE_SIZE
+#define PUD_TABLE_SIZE PAGE_SIZE
+#endif
+
+#ifndef PMD_TABLE_SIZE
+#define PMD_TABLE_SIZE PAGE_SIZE
+#endif
+
+#ifndef PTE_TABLE_SIZE
+#define PTE_TABLE_SIZE PAGE_SIZE
+#endif
+void __init __weak pcpu_populate_pte(unsigned long addr)
+{
+ pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ if (pgd_none(*pgd)) {
+ p4d_t *new;
+
+ new = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ pgd_populate(&init_mm, pgd, new);
+ }
+
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d)) {
+ pud_t *new;
+
+ new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ p4d_populate(&init_mm, p4d, new);
+ }
+
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud)) {
+ pmd_t *new;
+
+ new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ pud_populate(&init_mm, pud, new);
+ }
+
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd)) {
+ pte_t *new;
+
+ new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ pmd_populate_kernel(&init_mm, pmd, new);
+ }
+
+ return;
+
+err_alloc:
+ panic("%s: Failed to allocate memory\n", __func__);
+}
+
/**
* pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
* @reserved_size: the size of reserved percpu area in bytes
- * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
- * @free_fn: function to free percpu page, always called with PAGE_SIZE
- * @populate_pte_fn: function to populate pte
+ * @cpu_to_nd_fn: callback to convert cpu to it's node, optional
*
* This is a helper to ease setting up page-remapped first percpu
* chunk and can be called where pcpu_setup_first_chunk() is expected.
@@ -3156,10 +3257,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
* RETURNS:
* 0 on success, -errno on failure.
*/
-int __init pcpu_page_first_chunk(size_t reserved_size,
- pcpu_fc_alloc_fn_t alloc_fn,
- pcpu_fc_free_fn_t free_fn,
- pcpu_fc_populate_pte_fn_t populate_pte_fn)
+int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
static struct vm_struct vm;
struct pcpu_alloc_info *ai;
@@ -3201,7 +3299,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
for (i = 0; i < unit_pages; i++) {
void *ptr;
- ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
+ ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn);
if (!ptr) {
pr_warn("failed to allocate %s page for cpu%u\n",
psize_str, cpu);
@@ -3223,7 +3321,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
(unsigned long)vm.addr + unit * ai->unit_size;
for (i = 0; i < unit_pages; i++)
- populate_pte_fn(unit_addr + (i << PAGE_SHIFT));
+ pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT));
/* pte already populated, the following shouldn't fail */
rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages],
@@ -3253,7 +3351,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
enomem:
while (--j >= 0)
- free_fn(page_address(pages[j]), PAGE_SIZE);
+ pcpu_fc_free(page_address(pages[j]), PAGE_SIZE);
rc = -ENOMEM;
out_free_ar:
memblock_free(pages, pages_size);
@@ -3278,17 +3376,6 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
-static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
- size_t align)
-{
- return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS));
-}
-
-static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
@@ -3299,9 +3386,8 @@ void __init setup_per_cpu_areas(void)
* Always reserve area for module percpu variables. That's
* what the legacy allocator did.
*/
- rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
- PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
- pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE,
+ PAGE_SIZE, NULL, NULL);
if (rc < 0)
panic("Failed to initialize percpu areas.");
diff --git a/mm/slab.h b/mm/slab.h
index 7edb7d2..c7f2abc 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -67,14 +67,8 @@ struct slab {
static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
SLAB_MATCH(flags, __page_flags);
SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */
-SLAB_MATCH(slab_list, slab_list);
#ifndef CONFIG_SLOB
SLAB_MATCH(rcu_head, rcu_head);
-SLAB_MATCH(slab_cache, slab_cache);
-#endif
-#ifdef CONFIG_SLAB
-SLAB_MATCH(s_mem, s_mem);
-SLAB_MATCH(active, active);
#endif
SLAB_MATCH(_refcount, __page_refcount);
#ifdef CONFIG_MEMCG
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index f7dc561..b24a4fb 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -721,7 +721,7 @@ static void p9_virtio_remove(struct virtio_device *vdev)
mutex_unlock(&virtio_9p_lock);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
vdev->config->del_vqs(vdev);
sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index a52ad81..55f47ca 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -615,6 +615,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
err = dev_set_allmulti(dev, 1);
if (err) {
br_multicast_del_port(p);
+ dev_put_track(dev, &p->dev_tracker);
kfree(p); /* kobject not yet init'd, manually free */
goto err1;
}
@@ -724,10 +725,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
sysfs_remove_link(br->ifobj, p->dev->name);
err2:
br_multicast_del_port(p);
+ dev_put_track(dev, &p->dev_tracker);
kobject_put(&p->kobj);
dev_set_allmulti(dev, -1);
err1:
- dev_put(dev);
return err;
}
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 9441b4a..ecc400a 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -190,14 +190,14 @@ int ceph_compare_options(struct ceph_options *new_opt,
}
EXPORT_SYMBOL(ceph_compare_options);
-static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid)
{
int i = 0;
char tmp[3];
int err = -EINVAL;
int d;
- dout("parse_fsid '%s'\n", str);
+ dout("%s '%s'\n", __func__, str);
tmp[2] = 0;
while (*str && i < 16) {
if (ispunct(*str)) {
@@ -217,9 +217,10 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid)
if (i == 16)
err = 0;
- dout("parse_fsid ret %d got fsid %pU\n", err, fsid);
+ dout("%s ret %d got fsid %pU\n", __func__, err, fsid);
return err;
}
+EXPORT_SYMBOL(ceph_parse_fsid);
/*
* ceph options
@@ -395,14 +396,14 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name,
}
int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt,
- struct fc_log *l)
+ struct fc_log *l, char delim)
{
struct p_log log = {.prefix = "libceph", .log = l};
int ret;
- /* ip1[:port1][,ip2[:port2]...] */
+ /* ip1[:port1][<delim>ip2[:port2]...] */
ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON,
- &opt->num_mon);
+ &opt->num_mon, delim);
if (ret) {
error_plog(&log, "Failed to parse monitor IPs: %d", ret);
return ret;
@@ -428,8 +429,7 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
case Opt_ip:
err = ceph_parse_ips(param->string,
param->string + param->size,
- &opt->my_addr,
- 1, NULL);
+ &opt->my_addr, 1, NULL, ',');
if (err) {
error_plog(&log, "Failed to parse ip: %d", err);
return err;
@@ -438,7 +438,7 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
break;
case Opt_fsid:
- err = parse_fsid(param->string, &opt->fsid);
+ err = ceph_parse_fsid(param->string, &opt->fsid);
if (err) {
error_plog(&log, "Failed to parse fsid: %d", err);
return err;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 7b891be..45eba2d 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1267,30 +1267,31 @@ static int ceph_parse_server_name(const char *name, size_t namelen,
*/
int ceph_parse_ips(const char *c, const char *end,
struct ceph_entity_addr *addr,
- int max_count, int *count)
+ int max_count, int *count, char delim)
{
int i, ret = -EINVAL;
const char *p = c;
dout("parse_ips on '%.*s'\n", (int)(end-c), c);
for (i = 0; i < max_count; i++) {
+ char cur_delim = delim;
const char *ipend;
int port;
- char delim = ',';
if (*p == '[') {
- delim = ']';
+ cur_delim = ']';
p++;
}
- ret = ceph_parse_server_name(p, end - p, &addr[i], delim, &ipend);
+ ret = ceph_parse_server_name(p, end - p, &addr[i], cur_delim,
+ &ipend);
if (ret)
goto bad;
ret = -EINVAL;
p = ipend;
- if (delim == ']') {
+ if (cur_delim == ']') {
if (*p != ']') {
dout("missing matching ']'\n");
goto bad;
@@ -1326,11 +1327,11 @@ int ceph_parse_ips(const char *c, const char *end,
addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
addr[i].nonce = 0;
- dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
+ dout("%s got %s\n", __func__, ceph_pr_addr(&addr[i]));
if (p == end)
break;
- if (*p != ',')
+ if (*p != delim)
goto bad;
p++;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 84a0d95..1baab07 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8981,6 +8981,12 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
goto out_unlock;
}
old_prog = link->prog;
+ if (old_prog->type != new_prog->type ||
+ old_prog->expected_attach_type != new_prog->expected_attach_type) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
if (old_prog == new_prog) {
/* no-op, don't disturb drivers */
bpf_prog_put(new_prog);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 9b7171c..a5b5bb99 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -164,8 +164,10 @@ static void ops_exit_list(const struct pernet_operations *ops,
{
struct net *net;
if (ops->exit) {
- list_for_each_entry(net, net_exit_list, exit_list)
+ list_for_each_entry(net, net_exit_list, exit_list) {
ops->exit(net);
+ cond_resched();
+ }
}
if (ops->exit_batch)
ops->exit_batch(net_exit_list);
diff --git a/net/core/of_net.c b/net/core/of_net.c
index 95a64c8..f1a9bf7 100644
--- a/net/core/of_net.c
+++ b/net/core/of_net.c
@@ -61,7 +61,7 @@ static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr)
{
struct platform_device *pdev = of_find_device_by_node(np);
struct nvmem_cell *cell;
- const void *buf;
+ const void *mac;
size_t len;
int ret;
@@ -78,32 +78,21 @@ static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr)
if (IS_ERR(cell))
return PTR_ERR(cell);
- buf = nvmem_cell_read(cell, &len);
+ mac = nvmem_cell_read(cell, &len);
nvmem_cell_put(cell);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
+ if (IS_ERR(mac))
+ return PTR_ERR(mac);
- ret = 0;
- if (len == ETH_ALEN) {
- if (is_valid_ether_addr(buf))
- memcpy(addr, buf, ETH_ALEN);
- else
- ret = -EINVAL;
- } else if (len == 3 * ETH_ALEN - 1) {
- u8 mac[ETH_ALEN];
-
- if (mac_pton(buf, mac))
- memcpy(addr, mac, ETH_ALEN);
- else
- ret = -EINVAL;
- } else {
- ret = -EINVAL;
+ if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
+ kfree(mac);
+ return -EINVAL;
}
- kfree(buf);
+ memcpy(addr, mac, ETH_ALEN);
+ kfree(mac);
- return ret;
+ return 0;
}
/**
diff --git a/net/core/sock.c b/net/core/sock.c
index e21485a..4ff806d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -844,6 +844,8 @@ static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
}
num = ethtool_get_phc_vclocks(dev, &vclock_index);
+ dev_put(dev);
+
for (i = 0; i < num; i++) {
if (*(vclock_index + i) == phc_index) {
match = true;
@@ -2047,6 +2049,9 @@ void sk_destruct(struct sock *sk)
{
bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
+ WARN_ON_ONCE(!llist_empty(&sk->defer_list));
+ sk_defer_free_flush(sk);
+
if (rcu_access_pointer(sk->sk_reuseport_cb)) {
reuseport_detach_sock(sk);
use_call_rcu = true;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 828de17..b4589861 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -29,6 +29,7 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/netlink.h>
+#include <linux/hash.h>
#include <net/arp.h>
#include <net/ip.h>
@@ -51,6 +52,7 @@ static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_info_hash_size;
+static unsigned int fib_info_hash_bits;
static unsigned int fib_info_cnt;
#define DEVINDEX_HASHBITS 8
@@ -249,7 +251,6 @@ void free_fib_info(struct fib_info *fi)
pr_warn("Freeing alive fib_info %p\n", fi);
return;
}
- fib_info_cnt--;
call_rcu(&fi->rcu, free_fib_info_rcu);
}
@@ -260,6 +261,10 @@ void fib_release_info(struct fib_info *fi)
spin_lock_bh(&fib_info_lock);
if (fi && refcount_dec_and_test(&fi->fib_treeref)) {
hlist_del(&fi->fib_hash);
+
+ /* Paired with READ_ONCE() in fib_create_info(). */
+ WRITE_ONCE(fib_info_cnt, fib_info_cnt - 1);
+
if (fi->fib_prefsrc)
hlist_del(&fi->fib_lhash);
if (fi->nh) {
@@ -316,11 +321,15 @@ static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi)
static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
- unsigned int mask = DEVINDEX_HASHSIZE - 1;
+ return hash_32(val, DEVINDEX_HASHBITS);
+}
- return (val ^
- (val >> DEVINDEX_HASHBITS) ^
- (val >> (DEVINDEX_HASHBITS * 2))) & mask;
+static struct hlist_head *
+fib_info_devhash_bucket(const struct net_device *dev)
+{
+ u32 val = net_hash_mix(dev_net(dev)) ^ dev->ifindex;
+
+ return &fib_info_devhash[fib_devindex_hashfn(val)];
}
static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
@@ -430,12 +439,11 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
struct hlist_head *head;
struct fib_nh *nh;
- unsigned int hash;
spin_lock(&fib_info_lock);
- hash = fib_devindex_hashfn(dev->ifindex);
- head = &fib_info_devhash[hash];
+ head = fib_info_devhash_bucket(dev);
+
hlist_for_each_entry(nh, head, nh_hash) {
if (nh->fib_nh_dev == dev &&
nh->fib_nh_gw4 == gw &&
@@ -1240,13 +1248,13 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
return err;
}
-static inline unsigned int fib_laddr_hashfn(__be32 val)
+static struct hlist_head *
+fib_info_laddrhash_bucket(const struct net *net, __be32 val)
{
- unsigned int mask = (fib_info_hash_size - 1);
+ u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
+ fib_info_hash_bits);
- return ((__force u32)val ^
- ((__force u32)val >> 7) ^
- ((__force u32)val >> 14)) & mask;
+ return &fib_info_laddrhash[slot];
}
static struct hlist_head *fib_info_hash_alloc(int bytes)
@@ -1282,6 +1290,7 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
old_info_hash = fib_info_hash;
old_laddrhash = fib_info_laddrhash;
fib_info_hash_size = new_size;
+ fib_info_hash_bits = ilog2(new_size);
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &fib_info_hash[i];
@@ -1299,21 +1308,20 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
}
fib_info_hash = new_info_hash;
+ fib_info_laddrhash = new_laddrhash;
for (i = 0; i < old_size; i++) {
- struct hlist_head *lhead = &fib_info_laddrhash[i];
+ struct hlist_head *lhead = &old_laddrhash[i];
struct hlist_node *n;
struct fib_info *fi;
hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
struct hlist_head *ldest;
- unsigned int new_hash;
- new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
- ldest = &new_laddrhash[new_hash];
+ ldest = fib_info_laddrhash_bucket(fi->fib_net,
+ fi->fib_prefsrc);
hlist_add_head(&fi->fib_lhash, ldest);
}
}
- fib_info_laddrhash = new_laddrhash;
spin_unlock_bh(&fib_info_lock);
@@ -1430,7 +1438,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
#endif
err = -ENOBUFS;
- if (fib_info_cnt >= fib_info_hash_size) {
+
+ /* Paired with WRITE_ONCE() in fib_release_info() */
+ if (READ_ONCE(fib_info_cnt) >= fib_info_hash_size) {
unsigned int new_size = fib_info_hash_size << 1;
struct hlist_head *new_info_hash;
struct hlist_head *new_laddrhash;
@@ -1462,7 +1472,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
return ERR_PTR(err);
}
- fib_info_cnt++;
fi->fib_net = net;
fi->fib_protocol = cfg->fc_protocol;
fi->fib_scope = cfg->fc_scope;
@@ -1591,12 +1600,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
refcount_set(&fi->fib_treeref, 1);
refcount_set(&fi->fib_clntref, 1);
spin_lock_bh(&fib_info_lock);
+ fib_info_cnt++;
hlist_add_head(&fi->fib_hash,
&fib_info_hash[fib_info_hashfn(fi)]);
if (fi->fib_prefsrc) {
struct hlist_head *head;
- head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
+ head = fib_info_laddrhash_bucket(net, fi->fib_prefsrc);
hlist_add_head(&fi->fib_lhash, head);
}
if (fi->nh) {
@@ -1604,12 +1614,10 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
} else {
change_nexthops(fi) {
struct hlist_head *head;
- unsigned int hash;
if (!nexthop_nh->fib_nh_dev)
continue;
- hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex);
- head = &fib_info_devhash[hash];
+ head = fib_info_devhash_bucket(nexthop_nh->fib_nh_dev);
hlist_add_head(&nexthop_nh->nh_hash, head);
} endfor_nexthops(fi)
}
@@ -1870,16 +1878,16 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
*/
int fib_sync_down_addr(struct net_device *dev, __be32 local)
{
- int ret = 0;
- unsigned int hash = fib_laddr_hashfn(local);
- struct hlist_head *head = &fib_info_laddrhash[hash];
int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
struct net *net = dev_net(dev);
+ struct hlist_head *head;
struct fib_info *fi;
+ int ret = 0;
if (!fib_info_laddrhash || local == 0)
return 0;
+ head = fib_info_laddrhash_bucket(net, local);
hlist_for_each_entry(fi, head, fib_lhash) {
if (!net_eq(fi->fib_net, net) ||
fi->fib_tb_id != tb_id)
@@ -1961,8 +1969,7 @@ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
{
- unsigned int hash = fib_devindex_hashfn(dev->ifindex);
- struct hlist_head *head = &fib_info_devhash[hash];
+ struct hlist_head *head = fib_info_devhash_bucket(dev);
struct fib_nh *nh;
hlist_for_each_entry(nh, head, nh_hash) {
@@ -1981,12 +1988,11 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
*/
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
{
- int ret = 0;
- int scope = RT_SCOPE_NOWHERE;
+ struct hlist_head *head = fib_info_devhash_bucket(dev);
struct fib_info *prev_fi = NULL;
- unsigned int hash = fib_devindex_hashfn(dev->ifindex);
- struct hlist_head *head = &fib_info_devhash[hash];
+ int scope = RT_SCOPE_NOWHERE;
struct fib_nh *nh;
+ int ret = 0;
if (force)
scope = -1;
@@ -2131,7 +2137,6 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
{
struct fib_info *prev_fi;
- unsigned int hash;
struct hlist_head *head;
struct fib_nh *nh;
int ret;
@@ -2147,8 +2152,7 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
}
prev_fi = NULL;
- hash = fib_devindex_hashfn(dev->ifindex);
- head = &fib_info_devhash[hash];
+ head = fib_info_devhash_bucket(dev);
ret = 0;
hlist_for_each_entry(nh, head, nh_hash) {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 05cd198..3410968 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -235,9 +235,9 @@ void inet_frag_kill(struct inet_frag_queue *fq)
/* The RCU read lock provides a memory barrier
* guaranteeing that if fqdir->dead is false then
* the hash table destruction will not start until
- * after we unlock. Paired with inet_frags_exit_net().
+ * after we unlock. Paired with fqdir_pre_exit().
*/
- if (!fqdir->dead) {
+ if (!READ_ONCE(fqdir->dead)) {
rhashtable_remove_fast(&fqdir->rhashtable, &fq->node,
fqdir->f->rhash_params);
refcount_dec(&fq->refcnt);
@@ -352,9 +352,11 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
{
+ /* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */
+ long high_thresh = READ_ONCE(fqdir->high_thresh);
struct inet_frag_queue *fq = NULL, *prev;
- if (!fqdir->high_thresh || frag_mem_limit(fqdir) > fqdir->high_thresh)
+ if (!high_thresh || frag_mem_limit(fqdir) > high_thresh)
return NULL;
rcu_read_lock();
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cfeb889..fad803d 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -144,7 +144,8 @@ static void ip_expire(struct timer_list *t)
rcu_read_lock();
- if (qp->q.fqdir->dead)
+ /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */
+ if (READ_ONCE(qp->q.fqdir->dead))
goto out_rcu_unlock;
spin_lock(&qp->q.lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2ac2b95..99db2e4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -604,8 +604,9 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
key = &info->key;
ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
- tunnel_id_to_key32(key->tun_id), key->tos, 0,
- skb->mark, skb_get_hash(skb));
+ tunnel_id_to_key32(key->tun_id),
+ key->tos & ~INET_ECN_MASK, 0, skb->mark,
+ skb_get_hash(skb));
rt = ip_route_output_key(dev_net(dev), &fl4);
if (IS_ERR(rt))
return PTR_ERR(rt);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a618dce..c0b138c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -956,7 +956,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr);
}
- if (rt->rt_type != RTN_UNICAST) {
+ if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
ip_rt_put(rt);
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 86ad15a..750f9f9 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -285,7 +285,7 @@ static void __mctp_route_test_init(struct kunit *test,
struct mctp_test_route **rtp,
struct socket **sockp)
{
- struct sockaddr_mctp addr;
+ struct sockaddr_mctp addr = {0};
struct mctp_test_route *rt;
struct mctp_test_dev *dev;
struct socket *sock;
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index 58dcafe..7d00a14 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -206,7 +206,7 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src)
struct nft_connlimit *priv_src = nft_expr_priv(src);
priv_dst->list = kmalloc(sizeof(*priv_dst->list), GFP_ATOMIC);
- if (priv_dst->list)
+ if (!priv_dst->list)
return -ENOMEM;
nf_conncount_list_init(priv_dst->list);
diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c
index 5ee33d0..4f745a4 100644
--- a/net/netfilter/nft_last.c
+++ b/net/netfilter/nft_last.c
@@ -106,7 +106,7 @@ static int nft_last_clone(struct nft_expr *dst, const struct nft_expr *src)
struct nft_last_priv *priv_dst = nft_expr_priv(dst);
priv_dst->last = kzalloc(sizeof(*priv_dst->last), GFP_ATOMIC);
- if (priv_dst->last)
+ if (!priv_dst->last)
return -ENOMEM;
return 0;
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index f04be5b..c4f3084 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -145,7 +145,7 @@ static int nft_limit_clone(struct nft_limit_priv *priv_dst,
priv_dst->invert = priv_src->invert;
priv_dst->limit = kmalloc(sizeof(*priv_dst->limit), GFP_ATOMIC);
- if (priv_dst->limit)
+ if (!priv_dst->limit)
return -ENOMEM;
spin_lock_init(&priv_dst->limit->lock);
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index 0484aef..f394a0b 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -237,7 +237,7 @@ static int nft_quota_clone(struct nft_expr *dst, const struct nft_expr *src)
struct nft_quota *priv_dst = nft_expr_priv(dst);
priv_dst->consumed = kmalloc(sizeof(*priv_dst->consumed), GFP_ATOMIC);
- if (priv_dst->consumed)
+ if (!priv_dst->consumed)
return -ENOMEM;
atomic64_set(priv_dst->consumed, 0);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 6cfd30f..0b93a17 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -789,6 +789,11 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg,
lock_sock(sk);
+ if (!llcp_sock->local) {
+ release_sock(sk);
+ return -ENODEV;
+ }
+
if (sk->sk_type == SOCK_DGRAM) {
DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr,
msg->msg_name);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c9c6f49..2cb496c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1062,7 +1062,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
qdisc_offload_graft_root(dev, new, old, extack);
- if (new && new->ops->attach)
+ if (new && new->ops->attach && !ingress)
goto skip;
for (i = 0; i < num_q; i++) {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b07bd1c..f893d9a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1529,6 +1529,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r,
{
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
+ r->mpu = conf->mpu;
r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index aa3bcaa..961854e 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -634,9 +634,13 @@ static void smc_conn_abort(struct smc_sock *smc, int local_first)
{
struct smc_connection *conn = &smc->conn;
struct smc_link_group *lgr = conn->lgr;
+ bool lgr_valid = false;
+
+ if (smc_conn_lgr_valid(conn))
+ lgr_valid = true;
smc_conn_free(conn);
- if (local_first)
+ if (local_first && lgr_valid)
smc_lgr_cleanup_early(lgr);
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 1a4fc1c..3d0b8e3 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -221,6 +221,7 @@ struct smc_connection {
*/
u64 peer_token; /* SMC-D token of peer */
u8 killed : 1; /* abnormal termination */
+ u8 freed : 1; /* normal termiation */
u8 out_of_sync : 1; /* out of sync with peer */
};
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 84c8a43..9d5a971 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -197,7 +197,8 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
{
int rc;
- if (!conn->lgr || (conn->lgr->is_smcd && conn->lgr->peer_shutdown))
+ if (!smc_conn_lgr_valid(conn) ||
+ (conn->lgr->is_smcd && conn->lgr->peer_shutdown))
return -EPIPE;
if (conn->lgr->is_smcd) {
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 6be95a2..ce27399 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -774,7 +774,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version)
dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX;
dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ?
SMC_FIRST_CONTACT_MASK : 0;
- if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) &&
+ if ((!smc_conn_lgr_valid(&smc->conn) || !smc->conn.lgr->is_smcd) &&
smc_ib_is_valid_local_systemid())
memcpy(dclc.id_for_peer, local_systemid,
sizeof(local_systemid));
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 8935ef4..29525d0 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -211,14 +211,13 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
{
struct smc_link_group *lgr = conn->lgr;
- if (!lgr)
+ if (!smc_conn_lgr_valid(conn))
return;
write_lock_bh(&lgr->conns_lock);
if (conn->alert_token_local) {
__smc_lgr_unregister_conn(conn);
}
write_unlock_bh(&lgr->conns_lock);
- conn->lgr = NULL;
}
int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
@@ -749,9 +748,12 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
}
get_device(&lnk->smcibdev->ibdev->dev);
atomic_inc(&lnk->smcibdev->lnk_cnt);
+ refcount_set(&lnk->refcnt, 1); /* link refcnt is set to 1 */
+ lnk->clearing = 0;
lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu;
lnk->link_id = smcr_next_link_id(lgr);
lnk->lgr = lgr;
+ smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */
lnk->link_idx = link_idx;
smc_ibdev_cnt_inc(lnk);
smcr_copy_dev_info_to_link(lnk);
@@ -806,6 +808,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
lnk->state = SMC_LNK_UNUSED;
if (!atomic_dec_return(&smcibdev->lnk_cnt))
wake_up(&smcibdev->lnks_deleted);
+ smc_lgr_put(lgr); /* lgr_hold above */
return rc;
}
@@ -844,6 +847,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
lgr->terminating = 0;
lgr->freeing = 0;
lgr->vlan_id = ini->vlan_id;
+ refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */
mutex_init(&lgr->sndbufs_lock);
mutex_init(&lgr->rmbs_lock);
rwlock_init(&lgr->conns_lock);
@@ -996,8 +1000,12 @@ void smc_switch_link_and_count(struct smc_connection *conn,
struct smc_link *to_lnk)
{
atomic_dec(&conn->lnk->conn_cnt);
+ /* link_hold in smc_conn_create() */
+ smcr_link_put(conn->lnk);
conn->lnk = to_lnk;
atomic_inc(&conn->lnk->conn_cnt);
+ /* link_put in smc_conn_free() */
+ smcr_link_hold(conn->lnk);
}
struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
@@ -1130,8 +1138,19 @@ void smc_conn_free(struct smc_connection *conn)
{
struct smc_link_group *lgr = conn->lgr;
- if (!lgr)
+ if (!lgr || conn->freed)
+ /* Connection has never been registered in a
+ * link group, or has already been freed.
+ */
return;
+
+ conn->freed = 1;
+ if (!smc_conn_lgr_valid(conn))
+ /* Connection has already unregistered from
+ * link group.
+ */
+ goto lgr_put;
+
if (lgr->is_smcd) {
if (!list_empty(&lgr->list))
smc_ism_unset_conn(conn);
@@ -1148,6 +1167,10 @@ void smc_conn_free(struct smc_connection *conn)
if (!lgr->conns_num)
smc_lgr_schedule_free_work(lgr);
+lgr_put:
+ if (!lgr->is_smcd)
+ smcr_link_put(conn->lnk); /* link_hold in smc_conn_create() */
+ smc_lgr_put(lgr); /* lgr_hold in smc_conn_create() */
}
/* unregister a link from a buf_desc */
@@ -1203,21 +1226,11 @@ static void smcr_rtoken_clear_link(struct smc_link *lnk)
}
}
-/* must be called under lgr->llc_conf_mutex lock */
-void smcr_link_clear(struct smc_link *lnk, bool log)
+static void __smcr_link_clear(struct smc_link *lnk)
{
+ struct smc_link_group *lgr = lnk->lgr;
struct smc_ib_device *smcibdev;
- if (!lnk->lgr || lnk->state == SMC_LNK_UNUSED)
- return;
- lnk->peer_qpn = 0;
- smc_llc_link_clear(lnk, log);
- smcr_buf_unmap_lgr(lnk);
- smcr_rtoken_clear_link(lnk);
- smc_ib_modify_qp_error(lnk);
- smc_wr_free_link(lnk);
- smc_ib_destroy_queue_pair(lnk);
- smc_ib_dealloc_protection_domain(lnk);
smc_wr_free_link_mem(lnk);
smc_ibdev_cnt_dec(lnk);
put_device(&lnk->smcibdev->ibdev->dev);
@@ -1226,6 +1239,36 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
lnk->state = SMC_LNK_UNUSED;
if (!atomic_dec_return(&smcibdev->lnk_cnt))
wake_up(&smcibdev->lnks_deleted);
+ smc_lgr_put(lgr); /* lgr_hold in smcr_link_init() */
+}
+
+/* must be called under lgr->llc_conf_mutex lock */
+void smcr_link_clear(struct smc_link *lnk, bool log)
+{
+ if (!lnk->lgr || lnk->clearing ||
+ lnk->state == SMC_LNK_UNUSED)
+ return;
+ lnk->clearing = 1;
+ lnk->peer_qpn = 0;
+ smc_llc_link_clear(lnk, log);
+ smcr_buf_unmap_lgr(lnk);
+ smcr_rtoken_clear_link(lnk);
+ smc_ib_modify_qp_error(lnk);
+ smc_wr_free_link(lnk);
+ smc_ib_destroy_queue_pair(lnk);
+ smc_ib_dealloc_protection_domain(lnk);
+ smcr_link_put(lnk); /* theoretically last link_put */
+}
+
+void smcr_link_hold(struct smc_link *lnk)
+{
+ refcount_inc(&lnk->refcnt);
+}
+
+void smcr_link_put(struct smc_link *lnk)
+{
+ if (refcount_dec_and_test(&lnk->refcnt))
+ __smcr_link_clear(lnk);
}
static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
@@ -1290,6 +1333,21 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr)
__smc_lgr_free_bufs(lgr, true);
}
+/* won't be freed until no one accesses to lgr anymore */
+static void __smc_lgr_free(struct smc_link_group *lgr)
+{
+ smc_lgr_free_bufs(lgr);
+ if (lgr->is_smcd) {
+ if (!atomic_dec_return(&lgr->smcd->lgr_cnt))
+ wake_up(&lgr->smcd->lgrs_deleted);
+ } else {
+ smc_wr_free_lgr_mem(lgr);
+ if (!atomic_dec_return(&lgr_cnt))
+ wake_up(&lgrs_deleted);
+ }
+ kfree(lgr);
+}
+
/* remove a link group */
static void smc_lgr_free(struct smc_link_group *lgr)
{
@@ -1305,19 +1363,23 @@ static void smc_lgr_free(struct smc_link_group *lgr)
smc_llc_lgr_clear(lgr);
}
- smc_lgr_free_bufs(lgr);
destroy_workqueue(lgr->tx_wq);
if (lgr->is_smcd) {
smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
put_device(&lgr->smcd->dev);
- if (!atomic_dec_return(&lgr->smcd->lgr_cnt))
- wake_up(&lgr->smcd->lgrs_deleted);
- } else {
- smc_wr_free_lgr_mem(lgr);
- if (!atomic_dec_return(&lgr_cnt))
- wake_up(&lgrs_deleted);
}
- kfree(lgr);
+ smc_lgr_put(lgr); /* theoretically last lgr_put */
+}
+
+void smc_lgr_hold(struct smc_link_group *lgr)
+{
+ refcount_inc(&lgr->refcnt);
+}
+
+void smc_lgr_put(struct smc_link_group *lgr)
+{
+ if (refcount_dec_and_test(&lgr->refcnt))
+ __smc_lgr_free(lgr);
}
static void smc_sk_wake_ups(struct smc_sock *smc)
@@ -1469,16 +1531,11 @@ void smc_smcd_terminate_all(struct smcd_dev *smcd)
/* Called when an SMCR device is removed or the smc module is unloaded.
* If smcibdev is given, all SMCR link groups using this device are terminated.
* If smcibdev is NULL, all SMCR link groups are terminated.
- *
- * We must wait here for QPs been destroyed before we destroy the CQs,
- * or we won't received any CQEs and cdc_pend_tx_wr cannot reach 0 thus
- * smc_sock cannot be released.
*/
void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
{
struct smc_link_group *lgr, *lg;
LIST_HEAD(lgr_free_list);
- LIST_HEAD(lgr_linkdown_list);
int i;
spin_lock_bh(&smc_lgr_list.lock);
@@ -1490,7 +1547,7 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) {
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (lgr->lnk[i].smcibdev == smcibdev)
- list_move_tail(&lgr->list, &lgr_linkdown_list);
+ smcr_link_down_cond_sched(&lgr->lnk[i]);
}
}
}
@@ -1502,16 +1559,6 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
__smc_lgr_terminate(lgr, false);
}
- list_for_each_entry_safe(lgr, lg, &lgr_linkdown_list, list) {
- for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
- if (lgr->lnk[i].smcibdev == smcibdev) {
- mutex_lock(&lgr->llc_conf_mutex);
- smcr_link_down_cond(&lgr->lnk[i]);
- mutex_unlock(&lgr->llc_conf_mutex);
- }
- }
- }
-
if (smcibdev) {
if (atomic_read(&smcibdev->lnk_cnt))
wait_event(smcibdev->lnks_deleted,
@@ -1856,6 +1903,10 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
goto out;
}
}
+ smc_lgr_hold(conn->lgr); /* lgr_put in smc_conn_free() */
+ if (!conn->lgr->is_smcd)
+ smcr_link_hold(conn->lnk); /* link_put in smc_conn_free() */
+ conn->freed = 0;
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
@@ -2240,14 +2291,16 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
{
- if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk))
+ if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd ||
+ !smc_link_active(conn->lnk))
return;
smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE);
}
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
{
- if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk))
+ if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd ||
+ !smc_link_active(conn->lnk))
return;
smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE);
}
@@ -2256,7 +2309,7 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
{
int i;
- if (!conn->lgr || conn->lgr->is_smcd)
+ if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd)
return;
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (!smc_link_active(&conn->lgr->lnk[i]))
@@ -2270,7 +2323,7 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
{
int i;
- if (!conn->lgr || conn->lgr->is_smcd)
+ if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd)
return;
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (!smc_link_active(&conn->lgr->lnk[i]))
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 521c64a..4cb03e9 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -137,6 +137,8 @@ struct smc_link {
u8 peer_link_uid[SMC_LGR_ID_SIZE]; /* peer uid */
u8 link_idx; /* index in lgr link array */
u8 link_is_asym; /* is link asymmetric? */
+ u8 clearing : 1; /* link is being cleared */
+ refcount_t refcnt; /* link reference count */
struct smc_link_group *lgr; /* parent link group */
struct work_struct link_down_wrk; /* wrk to bring link down */
char ibname[IB_DEVICE_NAME_MAX]; /* ib device name */
@@ -249,6 +251,7 @@ struct smc_link_group {
u8 terminating : 1;/* lgr is terminating */
u8 freeing : 1; /* lgr is being freed */
+ refcount_t refcnt; /* lgr reference count */
bool is_smcd; /* SMC-R or SMC-D */
u8 smc_version;
u8 negotiated_eid[SMC_MAX_EID_LEN];
@@ -409,6 +412,11 @@ static inline struct smc_connection *smc_lgr_find_conn(
return res;
}
+static inline bool smc_conn_lgr_valid(struct smc_connection *conn)
+{
+ return conn->lgr && conn->alert_token_local;
+}
+
/*
* Returns true if the specified link is usable.
*
@@ -487,6 +495,8 @@ struct smc_clc_msg_accept_confirm;
void smc_lgr_cleanup_early(struct smc_link_group *lgr);
void smc_lgr_terminate_sched(struct smc_link_group *lgr);
+void smc_lgr_hold(struct smc_link_group *lgr);
+void smc_lgr_put(struct smc_link_group *lgr);
void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport);
void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport);
void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
@@ -518,6 +528,8 @@ void smc_core_exit(void);
int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
u8 link_idx, struct smc_init_info *ini);
void smcr_link_clear(struct smc_link *lnk, bool log);
+void smcr_link_hold(struct smc_link *lnk);
+void smcr_link_put(struct smc_link *lnk);
void smc_switch_link_and_count(struct smc_connection *conn,
struct smc_link *to_lnk);
int smcr_buf_map_lgr(struct smc_link *lnk);
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 7c8dad2..b8898c7 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -89,7 +89,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
r->diag_state = sk->sk_state;
if (smc->use_fallback)
r->diag_mode = SMC_DIAG_MODE_FALLBACK_TCP;
- else if (smc->conn.lgr && smc->conn.lgr->is_smcd)
+ else if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd)
r->diag_mode = SMC_DIAG_MODE_SMCD;
else
r->diag_mode = SMC_DIAG_MODE_SMCR;
@@ -142,7 +142,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
goto errout;
}
- if (smc->conn.lgr && !smc->conn.lgr->is_smcd &&
+ if (smc_conn_lgr_valid(&smc->conn) && !smc->conn.lgr->is_smcd &&
(req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
!list_empty(&smc->conn.lgr->list)) {
struct smc_link *link = smc->conn.lnk;
@@ -164,7 +164,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
goto errout;
}
- if (smc->conn.lgr && smc->conn.lgr->is_smcd &&
+ if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd &&
(req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
!list_empty(&smc->conn.lgr->list)) {
struct smc_connection *conn = &smc->conn;
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index db9825c0..291f148 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -369,7 +369,8 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net,
memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN);
strncpy(new_pe->eth_name, eth_name, IFNAMSIZ);
new_pe->ndev = ndev;
- netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_KERNEL);
+ if (ndev)
+ netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_KERNEL);
rc = -EEXIST;
new_netdev = true;
write_lock(&pnettable->lock);
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 47512cc..a54e90a 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -125,10 +125,6 @@ int smc_wr_tx_v2_send(struct smc_link *link,
int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
unsigned long timeout);
void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context);
-void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
- smc_wr_tx_filter filter,
- smc_wr_tx_dismisser dismisser,
- unsigned long data);
void smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 95e774f..efc84845 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2059,6 +2059,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
splice_read_end:
release_sock(sk);
+ sk_defer_free_flush(sk);
return copied ? : err;
}
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 12e2dda..d45d536 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -192,8 +192,11 @@ void wait_for_unix_gc(void)
{
/* If number of inflight sockets is insane,
* force a garbage collect right now.
+ * Paired with the WRITE_ONCE() in unix_inflight(),
+ * unix_notinflight() and gc_in_progress().
*/
- if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
+ if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC &&
+ !READ_ONCE(gc_in_progress))
unix_gc();
wait_event(unix_gc_wait, gc_in_progress == false);
}
@@ -213,7 +216,9 @@ void unix_gc(void)
if (gc_in_progress)
goto out;
- gc_in_progress = true;
+ /* Paired with READ_ONCE() in wait_for_unix_gc(). */
+ WRITE_ONCE(gc_in_progress, true);
+
/* First, select candidates for garbage collection. Only
* in-flight sockets are considered, and from those only ones
* which don't have any external reference.
@@ -299,7 +304,10 @@ void unix_gc(void)
/* All candidates should have been detached by now. */
BUG_ON(!list_empty(&gc_candidates));
- gc_in_progress = false;
+
+ /* Paired with READ_ONCE() in wait_for_unix_gc(). */
+ WRITE_ONCE(gc_in_progress, false);
+
wake_up(&unix_gc_wait);
out:
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 052ae70..aa27a02 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -60,7 +60,8 @@ void unix_inflight(struct user_struct *user, struct file *fp)
} else {
BUG_ON(list_empty(&u->link));
}
- unix_tot_inflight++;
+ /* Paired with READ_ONCE() in wait_for_unix_gc() */
+ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
}
user->unix_inflight++;
spin_unlock(&unix_gc_lock);
@@ -80,7 +81,8 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
if (atomic_long_dec_and_test(&u->inflight))
list_del_init(&u->link);
- unix_tot_inflight--;
+ /* Paired with READ_ONCE() in wait_for_unix_gc() */
+ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
}
user->unix_inflight--;
spin_unlock(&unix_gc_lock);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 4f7c99d..fb3302f 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -665,7 +665,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
vsock_for_each_connected_socket(virtio_vsock_reset_sock);
/* Stop all work handlers to make sure no one is accessing the device,
- * so we can safely call vdev->config->reset().
+ * so we can safely call virtio_reset_device().
*/
mutex_lock(&vsock->rx_lock);
vsock->rx_run = false;
@@ -682,7 +682,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
/* Flush all device writes and interrupts, device will not use any
* more buffers.
*/
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
mutex_lock(&vsock->rx_lock);
while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX])))
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index 756e7de..1e9be50 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -33,8 +33,8 @@
echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \
) > $@
-$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \
- $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509)
+$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDI) \
+ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509)
@$(kecho) " GEN $@"
$(Q)(set -e; \
allf=""; \
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dccb8f3..04d1ce9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -31,6 +31,7 @@
#include <linux/if_tunnel.h>
#include <net/dst.h>
#include <net/flow.h>
+#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/gre.h>
@@ -3295,7 +3296,7 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
fl4->flowi4_proto = iph->protocol;
fl4->daddr = reverse ? iph->saddr : iph->daddr;
fl4->saddr = reverse ? iph->daddr : iph->saddr;
- fl4->flowi4_tos = iph->tos;
+ fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index 4866afd..eb4d947 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -113,11 +113,11 @@ static inline int update_counts(void *ctx, u32 pid, u64 delta)
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c
index f6d593e..8fdd2c9 100644
--- a/samples/bpf/test_overhead_kprobe_kern.c
+++ b/samples/bpf/test_overhead_kprobe_kern.c
@@ -6,6 +6,7 @@
*/
#include <linux/version.h>
#include <linux/ptrace.h>
+#include <linux/sched.h>
#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
@@ -22,17 +23,17 @@ int prog(struct pt_regs *ctx)
{
struct signal_struct *signal;
struct task_struct *tsk;
- char oldcomm[16] = {};
- char newcomm[16] = {};
+ char oldcomm[TASK_COMM_LEN] = {};
+ char newcomm[TASK_COMM_LEN] = {};
u16 oom_score_adj;
u32 pid;
tsk = (void *)PT_REGS_PARM1(ctx);
pid = _(tsk->pid);
- bpf_probe_read_kernel(oldcomm, sizeof(oldcomm), &tsk->comm);
- bpf_probe_read_kernel(newcomm, sizeof(newcomm),
- (void *)PT_REGS_PARM2(ctx));
+ bpf_probe_read_kernel_str(oldcomm, sizeof(oldcomm), &tsk->comm);
+ bpf_probe_read_kernel_str(newcomm, sizeof(newcomm),
+ (void *)PT_REGS_PARM2(ctx));
signal = _(tsk->signal);
oom_score_adj = _(signal->oom_score_adj);
return 0;
diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c
index eaa3269..80edada 100644
--- a/samples/bpf/test_overhead_tp_kern.c
+++ b/samples/bpf/test_overhead_tp_kern.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#include <linux/sched.h>
#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
@@ -11,8 +12,8 @@
struct task_rename {
__u64 pad;
__u32 pid;
- char oldcomm[16];
- char newcomm[16];
+ char oldcomm[TASK_COMM_LEN];
+ char newcomm[TASK_COMM_LEN];
__u16 oom_score_adj;
};
SEC("tracepoint/task/task_rename")
diff --git a/scripts/.gitignore b/scripts/.gitignore
index e83c620..eed308b 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
/asn1_compiler
/bin2c
-/extract-cert
/insert-sys-cert
/kallsyms
/module.lds
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index cdec220..3514c21 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -196,53 +196,6 @@
endif
###############################################################################
-#
-# When a Kconfig string contains a filename, it is suitable for
-# passing to shell commands. It is surrounded by double-quotes, and
-# any double-quotes or backslashes within it are escaped by
-# backslashes.
-#
-# This is no use for dependencies or $(wildcard). We need to strip the
-# surrounding quotes and the escaping from quotes and backslashes, and
-# we *do* need to escape any spaces in the string. So, for example:
-#
-# Usage: $(eval $(call config_filename,FOO))
-#
-# Defines FOO_FILENAME based on the contents of the CONFIG_FOO option,
-# transformed as described above to be suitable for use within the
-# makefile.
-#
-# Also, if the filename is a relative filename and exists in the source
-# tree but not the build tree, define FOO_SRCPREFIX as $(srctree)/ to
-# be prefixed to *both* command invocation and dependencies.
-#
-# Note: We also print the filenames in the quiet_cmd_foo text, and
-# perhaps ought to have a version specially escaped for that purpose.
-# But it's only cosmetic, and $(patsubst "%",%,$(CONFIG_FOO)) is good
-# enough. It'll strip the quotes in the common case where there's no
-# space and it's a simple filename, and it'll retain the quotes when
-# there's a space. There are some esoteric cases in which it'll print
-# the wrong thing, but we don't really care. The actual dependencies
-# and commands *do* get it right, with various combinations of single
-# and double quotes, backslashes and spaces in the filenames.
-#
-###############################################################################
-#
-define config_filename
-ifneq ($$(CONFIG_$(1)),"")
-$(1)_FILENAME := $$(subst \\,\,$$(subst \$$(quote),$$(quote),$$(subst $$(space_escape),\$$(space),$$(patsubst "%",%,$$(subst $$(space),$$(space_escape),$$(CONFIG_$(1)))))))
-ifneq ($$(patsubst /%,%,$$(firstword $$($(1)_FILENAME))),$$(firstword $$($(1)_FILENAME)))
-else
-ifeq ($$(wildcard $$($(1)_FILENAME)),)
-ifneq ($$(wildcard $$(srctree)/$$($(1)_FILENAME)),)
-$(1)_SRCPREFIX := $(srctree)/
-endif
-endif
-endif
-endif
-endef
-#
-###############################################################################
# delete partially updated (i.e. corrupted) files on error
.DELETE_ON_ERROR:
diff --git a/scripts/Makefile b/scripts/Makefile
index b082d2f..ecd3aca 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -3,26 +3,19 @@
# scripts contains sources for various helper programs used throughout
# the kernel for the build process.
-CRYPTO_LIBS = $(shell pkg-config --libs libcrypto 2> /dev/null || echo -lcrypto)
-CRYPTO_CFLAGS = $(shell pkg-config --cflags libcrypto 2> /dev/null)
-
hostprogs-always-$(CONFIG_BUILD_BIN2C) += bin2c
hostprogs-always-$(CONFIG_KALLSYMS) += kallsyms
hostprogs-always-$(BUILD_C_RECORDMCOUNT) += recordmcount
hostprogs-always-$(CONFIG_BUILDTIME_TABLE_SORT) += sorttable
hostprogs-always-$(CONFIG_ASN1) += asn1_compiler
hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file
-hostprogs-always-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert
hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert
-hostprogs-always-$(CONFIG_SYSTEM_REVOCATION_LIST) += extract-cert
HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include
HOSTLDLIBS_sorttable = -lpthread
HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
-HOSTCFLAGS_sign-file.o = $(CRYPTO_CFLAGS)
-HOSTLDLIBS_sign-file = $(CRYPTO_LIBS)
-HOSTCFLAGS_extract-cert.o = $(CRYPTO_CFLAGS)
-HOSTLDLIBS_extract-cert = $(CRYPTO_LIBS)
+HOSTCFLAGS_sign-file.o = $(shell pkg-config --cflags libcrypto 2> /dev/null)
+HOSTLDLIBS_sign-file = $(shell pkg-config --libs libcrypto 2> /dev/null || echo -lcrypto)
ifdef CONFIG_UNWINDER_ORC
ifeq ($(ARCH),x86_64)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index ab17f7b..79be57f 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -399,20 +399,35 @@
} \
)
+quiet_cmd_file_size = GEN $@
+ cmd_file_size = $(size_append) > $@
+
quiet_cmd_bzip2 = BZIP2 $@
- cmd_bzip2 = { cat $(real-prereqs) | $(KBZIP2) -9; $(size_append); } > $@
+ cmd_bzip2 = cat $(real-prereqs) | $(KBZIP2) -9 > $@
+
+quiet_cmd_bzip2_with_size = BZIP2 $@
+ cmd_bzip2_with_size = { cat $(real-prereqs) | $(KBZIP2) -9; $(size_append); } > $@
# Lzma
# ---------------------------------------------------------------------------
quiet_cmd_lzma = LZMA $@
- cmd_lzma = { cat $(real-prereqs) | $(LZMA) -9; $(size_append); } > $@
+ cmd_lzma = cat $(real-prereqs) | $(LZMA) -9 > $@
+
+quiet_cmd_lzma_with_size = LZMA $@
+ cmd_lzma_with_size = { cat $(real-prereqs) | $(LZMA) -9; $(size_append); } > $@
quiet_cmd_lzo = LZO $@
- cmd_lzo = { cat $(real-prereqs) | $(KLZOP) -9; $(size_append); } > $@
+ cmd_lzo = cat $(real-prereqs) | $(KLZOP) -9 > $@
+
+quiet_cmd_lzo_with_size = LZO $@
+ cmd_lzo_with_size = { cat $(real-prereqs) | $(KLZOP) -9; $(size_append); } > $@
quiet_cmd_lz4 = LZ4 $@
- cmd_lz4 = { cat $(real-prereqs) | $(LZ4) -l -c1 stdin stdout; \
+ cmd_lz4 = cat $(real-prereqs) | $(LZ4) -l -c1 stdin stdout > $@
+
+quiet_cmd_lz4_with_size = LZ4 $@
+ cmd_lz4_with_size = { cat $(real-prereqs) | $(LZ4) -l -c1 stdin stdout; \
$(size_append); } > $@
# U-Boot mkimage
@@ -455,7 +470,10 @@
# big dictionary would increase the memory usage too much in the multi-call
# decompression mode. A BCJ filter isn't used either.
quiet_cmd_xzkern = XZKERN $@
- cmd_xzkern = { cat $(real-prereqs) | sh $(srctree)/scripts/xz_wrap.sh; \
+ cmd_xzkern = cat $(real-prereqs) | sh $(srctree)/scripts/xz_wrap.sh > $@
+
+quiet_cmd_xzkern_with_size = XZKERN $@
+ cmd_xzkern_with_size = { cat $(real-prereqs) | sh $(srctree)/scripts/xz_wrap.sh; \
$(size_append); } > $@
quiet_cmd_xzmisc = XZMISC $@
@@ -478,10 +496,13 @@
# be used because it would require zstd to allocate a 128 MB buffer.
quiet_cmd_zstd = ZSTD $@
- cmd_zstd = { cat $(real-prereqs) | $(ZSTD) -19; $(size_append); } > $@
+ cmd_zstd = cat $(real-prereqs) | $(ZSTD) -19 > $@
quiet_cmd_zstd22 = ZSTD22 $@
- cmd_zstd22 = { cat $(real-prereqs) | $(ZSTD) -22 --ultra; $(size_append); } > $@
+ cmd_zstd22 = cat $(real-prereqs) | $(ZSTD) -22 --ultra > $@
+
+quiet_cmd_zstd22_with_size = ZSTD22 $@
+ cmd_zstd22_with_size = { cat $(real-prereqs) | $(ZSTD) -22 --ultra; $(size_append); } > $@
# ASM offsets
# ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index ff9b09e..c2c43a0 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -66,9 +66,9 @@
# Don't stop modules_install even if we can't sign external modules.
#
ifeq ($(CONFIG_MODULE_SIG_ALL),y)
+sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY)
quiet_cmd_sign = SIGN $@
-$(eval $(call config_filename,MODULE_SIG_KEY))
- cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY) certs/signing_key.x509 $@ \
+ cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \
$(if $(KBUILD_EXTMOD),|| true)
else
quiet_cmd_sign :=
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index 9e2092f..7099c60 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -8,7 +8,6 @@
ubsan-cflags-$(CONFIG_UBSAN_SHIFT) += -fsanitize=shift
ubsan-cflags-$(CONFIG_UBSAN_DIV_ZERO) += -fsanitize=integer-divide-by-zero
ubsan-cflags-$(CONFIG_UBSAN_UNREACHABLE) += -fsanitize=unreachable
-ubsan-cflags-$(CONFIG_UBSAN_OBJECT_SIZE) += -fsanitize=object-size
ubsan-cflags-$(CONFIG_UBSAN_BOOL) += -fsanitize=bool
ubsan-cflags-$(CONFIG_UBSAN_ENUM) += -fsanitize=enum
ubsan-cflags-$(CONFIG_UBSAN_TRAP) += -fsanitize-undefined-trap-on-error
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 1784921..b01c36a 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3172,7 +3172,7 @@
length($line) > 75 &&
!($line =~ /^\s*[a-zA-Z0-9_\/\.]+\s+\|\s+\d+/ ||
# file delta changes
- $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ ||
+ $line =~ /^\s*(?:[\w\.\-\+]*\/)++[\w\.\-\+]+:/ ||
# filename then :
$line =~ /^\s*(?:Fixes:|Link:|$signature_tags)/i ||
# A Fixes: or Link: line or signature tag line
@@ -3479,47 +3479,47 @@
# Kconfig supports named choices), so use a word boundary
# (\b) rather than a whitespace character (\s)
$line =~ /^\+\s*(?:config|menuconfig|choice)\b/) {
- my $length = 0;
- my $cnt = $realcnt;
- my $ln = $linenr + 1;
- my $f;
- my $is_start = 0;
- my $is_end = 0;
- for (; $cnt > 0 && defined $lines[$ln - 1]; $ln++) {
- $f = $lines[$ln - 1];
- $cnt-- if ($lines[$ln - 1] !~ /^-/);
- $is_end = $lines[$ln - 1] =~ /^\+/;
+ my $ln = $linenr;
+ my $needs_help = 0;
+ my $has_help = 0;
+ my $help_length = 0;
+ while (defined $lines[$ln]) {
+ my $f = $lines[$ln++];
next if ($f =~ /^-/);
- last if (!$file && $f =~ /^\@\@/);
+ last if ($f !~ /^[\+ ]/); # !patch context
- if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) {
- $is_start = 1;
- } elsif ($lines[$ln - 1] =~ /^\+\s*(?:---)?help(?:---)?$/) {
- $length = -1;
+ if ($f =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) {
+ $needs_help = 1;
+ next;
+ }
+ if ($f =~ /^\+\s*help\s*$/) {
+ $has_help = 1;
+ next;
}
- $f =~ s/^.//;
- $f =~ s/#.*//;
- $f =~ s/^\s+//;
- next if ($f =~ /^$/);
+ $f =~ s/^.//; # strip patch context [+ ]
+ $f =~ s/#.*//; # strip # directives
+ $f =~ s/^\s+//; # strip leading blanks
+ next if ($f =~ /^$/); # skip blank lines
+ # At the end of this Kconfig block:
# This only checks context lines in the patch
# and so hopefully shouldn't trigger false
# positives, even though some of these are
# common words in help texts
- if ($f =~ /^\s*(?:config|menuconfig|choice|endchoice|
- if|endif|menu|endmenu|source)\b/x) {
- $is_end = 1;
+ if ($f =~ /^(?:config|menuconfig|choice|endchoice|
+ if|endif|menu|endmenu|source)\b/x) {
last;
}
- $length++;
+ $help_length++ if ($has_help);
}
- if ($is_start && $is_end && $length < $min_conf_desc_length) {
+ if ($needs_help &&
+ $help_length < $min_conf_desc_length) {
+ my $stat_real = get_stat_real($linenr, $ln - 1);
WARN("CONFIG_DESCRIPTION",
- "please write a paragraph that describes the config symbol fully\n" . $herecurr);
+ "please write a help paragraph that fully describes the config symbol\n" . "$here\n$stat_real\n");
}
- #print "is_start<$is_start> is_end<$is_end> length<$length>\n";
}
# check MAINTAINERS entries
diff --git a/scripts/const_structs.checkpatch b/scripts/const_structs.checkpatch
index 3980985..1eeb7b4 100644
--- a/scripts/const_structs.checkpatch
+++ b/scripts/const_structs.checkpatch
@@ -12,19 +12,27 @@
drm_connector_funcs
drm_encoder_funcs
drm_encoder_helper_funcs
+dvb_frontend_ops
+dvb_tuner_ops
ethtool_ops
extent_io_ops
+fb_ops
file_lock_operations
file_operations
hv_ops
+hwmon_ops
+ib_device_ops
ide_dma_ops
ide_port_ops
+ieee80211_ops
+iio_buffer_setup_ops
inode_operations
intel_dvo_dev_ops
irq_domain_ops
item_operations
iwl_cfg
iwl_ops
+kernel_param_ops
kgdb_arch
kgdb_io
kset_uevent_ops
@@ -32,25 +40,33 @@
machine_desc
microcode_ops
mlxsw_reg_info
+mtd_ooblayout_ops
mtrr_ops
+nand_controller_ops
neigh_ops
net_device_ops
+nft_expr_ops
nlmsvc_binding
nvkm_device_chip
of_device_id
pci_raw_ops
phy_ops
+pinconf_ops
pinctrl_ops
pinmux_ops
pipe_buf_operations
platform_hibernation_ops
platform_suspend_ops
+proc_ops
proto_ops
+pwm_ops
regmap_access_table
regulator_ops
+reset_control_ops
rpc_pipe_ops
rtc_class_ops
sd_desc
+sdhci_ops
seq_operations
sirfsoc_padmux
snd_ac97_build_ops
@@ -67,6 +83,13 @@
usb_mon_operations
v4l2_ctrl_ops
v4l2_ioctl_ops
+v4l2_subdev_core_ops
+v4l2_subdev_internal_ops
+v4l2_subdev_ops
+v4l2_subdev_pad_ops
+v4l2_subdev_video_ops
+vb2_ops
vm_operations_struct
wacom_features
+watchdog_ops
wd_ops
diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff
index d3422ee..f2bbde4 100755
--- a/scripts/dtc/dtx_diff
+++ b/scripts/dtc/dtx_diff
@@ -59,12 +59,8 @@
or '/include/' to be processed.
If DTx_1 and DTx_2 are in different architectures, then this script
- may not work since \${ARCH} is part of the include path. Two possible
- workarounds:
-
- `basename $0` \\
- <(ARCH=arch_of_dtx_1 `basename $0` DTx_1) \\
- <(ARCH=arch_of_dtx_2 `basename $0` DTx_2)
+ may not work since \${ARCH} is part of the include path. The following
+ workaround can be used:
`basename $0` ARCH=arch_of_dtx_1 DTx_1 >tmp_dtx_1.dts
`basename $0` ARCH=arch_of_dtx_2 DTx_2 >tmp_dtx_2.dts
diff --git a/scripts/gen_autoksyms.sh b/scripts/gen_autoksyms.sh
index 6ed0d22..120225c 100755
--- a/scripts/gen_autoksyms.sh
+++ b/scripts/gen_autoksyms.sh
@@ -16,20 +16,15 @@
;;
esac
-# We need access to CONFIG_ symbols
-. include/config/auto.conf
-
needed_symbols=
# Special case for modversions (see modpost.c)
-if [ -n "$CONFIG_MODVERSIONS" ]; then
+if grep -q "^CONFIG_MODVERSIONS=y$" include/config/auto.conf; then
needed_symbols="$needed_symbols module_layout"
fi
-ksym_wl=
-if [ -n "$CONFIG_UNUSED_KSYMS_WHITELIST" ]; then
- # Use 'eval' to expand the whitelist path and check if it is relative
- eval ksym_wl="$CONFIG_UNUSED_KSYMS_WHITELIST"
+ksym_wl=$(sed -n 's/^CONFIG_UNUSED_KSYMS_WHITELIST=\(.*\)$/\1/p' include/config/auto.conf)
+if [ -n "$ksym_wl" ]; then
[ "${ksym_wl}" != "${ksym_wl#/}" ] || ksym_wl="$abs_srctree/$ksym_wl"
if [ ! -f "$ksym_wl" ] || [ ! -r "$ksym_wl" ]; then
echo "ERROR: '$ksym_wl' whitelist file not found" >&2
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 2075db0..6bd5221 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -1718,7 +1718,7 @@
%VCS_cmds = %VCS_cmds_hg;
return 2 if eval $VCS_cmds{"available"};
%VCS_cmds = ();
- if (!$printed_novcs) {
+ if (!$printed_novcs && $email_git) {
warn("$P: No supported VCS found. Add --nogit to options?\n");
warn("Using a git repository produces better results.\n");
warn("Try Linus Torvalds' latest git repository using:\n");
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 5a21588..b8ef0fb 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -69,7 +69,7 @@
# deprecated for external use
simple-targets := oldconfig allnoconfig allyesconfig allmodconfig \
alldefconfig randconfig listnewconfig olddefconfig syncconfig \
- helpnewconfig yes2modconfig mod2yesconfig
+ helpnewconfig yes2modconfig mod2yesconfig mod2noconfig
PHONY += $(simple-targets)
@@ -134,6 +134,7 @@
@echo ' randconfig - New config with random answer to all options'
@echo ' yes2modconfig - Change answers from yes to mod if possible'
@echo ' mod2yesconfig - Change answers from mod to yes if possible'
+ @echo ' mod2noconfig - Change answers from mod to no if possible'
@echo ' listnewconfig - List new options'
@echo ' helpnewconfig - List new options and help text'
@echo ' olddefconfig - Same as oldconfig but sets new symbols to their'
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 971da35..4178065 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -35,6 +35,7 @@ enum input_mode {
olddefconfig,
yes2modconfig,
mod2yesconfig,
+ mod2noconfig,
};
static enum input_mode input_mode = oldaskconfig;
static int input_mode_opt;
@@ -163,8 +164,6 @@ enum conf_def_mode {
def_default,
def_yes,
def_mod,
- def_y2m,
- def_m2y,
def_no,
def_random
};
@@ -302,12 +301,10 @@ static bool conf_set_all_new_symbols(enum conf_def_mode mode)
return has_changed;
}
-static void conf_rewrite_mod_or_yes(enum conf_def_mode mode)
+static void conf_rewrite_tristates(tristate old_val, tristate new_val)
{
struct symbol *sym;
int i;
- tristate old_val = (mode == def_y2m) ? yes : mod;
- tristate new_val = (mode == def_y2m) ? mod : yes;
for_all_symbols(i, sym) {
if (sym_get_type(sym) == S_TRISTATE &&
@@ -685,6 +682,7 @@ static const struct option long_opts[] = {
{"olddefconfig", no_argument, &input_mode_opt, olddefconfig},
{"yes2modconfig", no_argument, &input_mode_opt, yes2modconfig},
{"mod2yesconfig", no_argument, &input_mode_opt, mod2yesconfig},
+ {"mod2noconfig", no_argument, &input_mode_opt, mod2noconfig},
{NULL, 0, NULL, 0}
};
@@ -713,6 +711,7 @@ static void conf_usage(const char *progname)
printf(" --randconfig New config with random answer to all options\n");
printf(" --yes2modconfig Change answers from yes to mod if possible\n");
printf(" --mod2yesconfig Change answers from mod to yes if possible\n");
+ printf(" --mod2noconfig Change answers from mod to no if possible\n");
printf(" (If none of the above is given, --oldaskconfig is the default)\n");
}
@@ -788,6 +787,7 @@ int main(int ac, char **av)
case olddefconfig:
case yes2modconfig:
case mod2yesconfig:
+ case mod2noconfig:
conf_read(NULL);
break;
case allnoconfig:
@@ -862,10 +862,13 @@ int main(int ac, char **av)
case savedefconfig:
break;
case yes2modconfig:
- conf_rewrite_mod_or_yes(def_y2m);
+ conf_rewrite_tristates(yes, mod);
break;
case mod2yesconfig:
- conf_rewrite_mod_or_yes(def_m2y);
+ conf_rewrite_tristates(mod, yes);
+ break;
+ case mod2noconfig:
+ conf_rewrite_tristates(mod, no);
break;
case oldaskconfig:
rootEntry = &rootmenu;
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 42bc56e..59717be3 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -244,19 +244,21 @@ static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p)
p, sym->name);
return 1;
case S_STRING:
- if (*p++ != '"')
- break;
- for (p2 = p; (p2 = strpbrk(p2, "\"\\")); p2++) {
- if (*p2 == '"') {
- *p2 = 0;
+ /* No escaping for S_DEF_AUTO (include/config/auto.conf) */
+ if (def != S_DEF_AUTO) {
+ if (*p++ != '"')
break;
+ for (p2 = p; (p2 = strpbrk(p2, "\"\\")); p2++) {
+ if (*p2 == '"') {
+ *p2 = 0;
+ break;
+ }
+ memmove(p2, p2 + 1, strlen(p2));
}
- memmove(p2, p2 + 1, strlen(p2));
- }
- if (!p2) {
- if (def != S_DEF_AUTO)
+ if (!p2) {
conf_warning("invalid string found");
- return 1;
+ return 1;
+ }
}
/* fall through */
case S_INT:
@@ -700,7 +702,7 @@ static void print_symbol_for_dotconfig(FILE *fp, struct symbol *sym)
static void print_symbol_for_autoconf(FILE *fp, struct symbol *sym)
{
- __print_symbol(fp, sym, OUTPUT_N_NONE, true);
+ __print_symbol(fp, sym, OUTPUT_N_NONE, false);
}
void print_symbol_for_listconfig(struct symbol *sym)
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 1a5fea0..3387ad7 100755
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -170,7 +170,7 @@
$source =~ s/\$\($env\)/$ENV{$env}/;
}
- open(my $kinfile, '<', $source) || die "Can't open $kconfig";
+ open(my $kinfile, '<', $source) || die "Can't open $source";
while (<$kinfile>) {
chomp;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 82bc736..666f7bb 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -34,6 +34,10 @@
KBUILD_LDFLAGS="$2"
LDFLAGS_vmlinux="$3"
+is_enabled() {
+ grep -q "^$1=y" include/config/auto.conf
+}
+
# Nice output in kbuild format
# Will be supressed by "make -s"
info()
@@ -80,11 +84,11 @@
${KBUILD_VMLINUX_LIBS} \
--end-group"
- if [ -n "${CONFIG_LTO_CLANG}" ]; then
+ if is_enabled CONFIG_LTO_CLANG; then
gen_initcalls
lds="-T .tmp_initcalls.lds"
- if [ -n "${CONFIG_MODVERSIONS}" ]; then
+ if is_enabled CONFIG_MODVERSIONS; then
gen_symversions
lds="${lds} -T .tmp_symversions.lds"
fi
@@ -104,21 +108,21 @@
local objtoolcmd;
local objtoolopt;
- if [ "${CONFIG_LTO_CLANG} ${CONFIG_STACK_VALIDATION}" = "y y" ]; then
+ if is_enabled CONFIG_LTO_CLANG && is_enabled CONFIG_STACK_VALIDATION; then
# Don't perform vmlinux validation unless explicitly requested,
# but run objtool on vmlinux.o now that we have an object file.
- if [ -n "${CONFIG_UNWINDER_ORC}" ]; then
+ if is_enabled CONFIG_UNWINDER_ORC; then
objtoolcmd="orc generate"
fi
objtoolopt="${objtoolopt} --duplicate"
- if [ -n "${CONFIG_FTRACE_MCOUNT_USE_OBJTOOL}" ]; then
+ if is_enabled CONFIG_FTRACE_MCOUNT_USE_OBJTOOL; then
objtoolopt="${objtoolopt} --mcount"
fi
fi
- if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then
+ if is_enabled CONFIG_VMLINUX_VALIDATION; then
objtoolopt="${objtoolopt} --noinstr"
fi
@@ -127,19 +131,19 @@
objtoolcmd="check"
fi
objtoolopt="${objtoolopt} --vmlinux"
- if [ -z "${CONFIG_FRAME_POINTER}" ]; then
+ if ! is_enabled CONFIG_FRAME_POINTER; then
objtoolopt="${objtoolopt} --no-fp"
fi
- if [ -n "${CONFIG_GCOV_KERNEL}" ] || [ -n "${CONFIG_LTO_CLANG}" ]; then
+ if is_enabled CONFIG_GCOV_KERNEL || is_enabled CONFIG_LTO_CLANG; then
objtoolopt="${objtoolopt} --no-unreachable"
fi
- if [ -n "${CONFIG_RETPOLINE}" ]; then
+ if is_enabled CONFIG_RETPOLINE; then
objtoolopt="${objtoolopt} --retpoline"
fi
- if [ -n "${CONFIG_X86_SMAP}" ]; then
+ if is_enabled CONFIG_X86_SMAP; then
objtoolopt="${objtoolopt} --uaccess"
fi
- if [ -n "${CONFIG_SLS}" ]; then
+ if is_enabled CONFIG_SLS; then
objtoolopt="${objtoolopt} --sls"
fi
info OBJTOOL ${1}
@@ -164,7 +168,7 @@
# skip output file argument
shift
- if [ -n "${CONFIG_LTO_CLANG}" ]; then
+ if is_enabled CONFIG_LTO_CLANG; then
# Use vmlinux.o instead of performing the slow LTO link again.
objs=vmlinux.o
libs=
@@ -192,7 +196,7 @@
ldflags="${ldflags} ${wl}--strip-debug"
fi
- if [ -n "${CONFIG_VMLINUX_MAP}" ]; then
+ if is_enabled CONFIG_VMLINUX_MAP; then
ldflags="${ldflags} ${wl}-Map=${output}.map"
fi
@@ -242,15 +246,15 @@
{
local kallsymopt;
- if [ -n "${CONFIG_KALLSYMS_ALL}" ]; then
+ if is_enabled CONFIG_KALLSYMS_ALL; then
kallsymopt="${kallsymopt} --all-symbols"
fi
- if [ -n "${CONFIG_KALLSYMS_ABSOLUTE_PERCPU}" ]; then
+ if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
kallsymopt="${kallsymopt} --absolute-percpu"
fi
- if [ -n "${CONFIG_KALLSYMS_BASE_RELATIVE}" ]; then
+ if is_enabled CONFIG_KALLSYMS_BASE_RELATIVE; then
kallsymopt="${kallsymopt} --base-relative"
fi
@@ -315,9 +319,6 @@
exit 0
fi
-# We need access to CONFIG_ symbols
-. include/config/auto.conf
-
# Update version
info GEN .version
if [ -r .version ]; then
@@ -346,7 +347,7 @@
tr ' ' '\n' | uniq | sed -e 's:^:kernel/:' -e 's/$/.ko/' > modules.builtin
btf_vmlinux_bin_o=""
-if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
+if is_enabled CONFIG_DEBUG_INFO_BTF; then
btf_vmlinux_bin_o=.btf.vmlinux.bin.o
if ! gen_btf .tmp_vmlinux.btf $btf_vmlinux_bin_o ; then
echo >&2 "Failed to generate BTF for vmlinux"
@@ -358,7 +359,7 @@
kallsymso=""
kallsymso_prev=""
kallsyms_vmlinux=""
-if [ -n "${CONFIG_KALLSYMS}" ]; then
+if is_enabled CONFIG_KALLSYMS; then
# kallsyms support
# Generate section listing all symbols and add it into vmlinux
@@ -398,7 +399,7 @@
vmlinux_link vmlinux "${kallsymso}" ${btf_vmlinux_bin_o}
# fill in BTF IDs
-if [ -n "${CONFIG_DEBUG_INFO_BTF}" -a -n "${CONFIG_BPF}" ]; then
+if is_enabled CONFIG_DEBUG_INFO_BTF && is_enabled CONFIG_BPF; then
info BTFIDS vmlinux
${RESOLVE_BTFIDS} vmlinux
fi
@@ -406,7 +407,7 @@
info SYSMAP System.map
mksysmap vmlinux System.map
-if [ -n "${CONFIG_BUILDTIME_TABLE_SORT}" ]; then
+if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then
info SORTTAB vmlinux
if ! sorttable vmlinux; then
echo >&2 Failed to sort kernel tables
@@ -415,7 +416,7 @@
fi
# step a (see comment above)
-if [ -n "${CONFIG_KALLSYMS}" ]; then
+if is_enabled CONFIG_KALLSYMS; then
mksysmap ${kallsyms_vmlinux} .tmp_System.map
if ! cmp -s System.map .tmp_System.map; then
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 4edc708..7c20252a 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -28,7 +28,7 @@
if [ "$SRCARCH" = s390 ]; then
echo 13.0.0
else
- echo 10.0.1
+ echo 11.0.0
fi
;;
*)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index cb8ab7d..6bfa3321 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1830,6 +1830,14 @@ static int addend_mips_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
return 0;
}
+#ifndef EM_RISCV
+#define EM_RISCV 243
+#endif
+
+#ifndef R_RISCV_SUB32
+#define R_RISCV_SUB32 39
+#endif
+
static void section_rela(const char *modname, struct elf_info *elf,
Elf_Shdr *sechdr)
{
@@ -1866,6 +1874,13 @@ static void section_rela(const char *modname, struct elf_info *elf,
r_sym = ELF_R_SYM(r.r_info);
#endif
r.r_addend = TO_NATIVE(rela->r_addend);
+ switch (elf->hdr->e_machine) {
+ case EM_RISCV:
+ if (!strcmp("__ex_table", fromsec) &&
+ ELF_R_TYPE(r.r_info) == R_RISCV_SUB32)
+ continue;
+ break;
+ }
sym = elf->symtab_start + r_sym;
/* Skip special sections */
if (is_shndx_special(sym->st_shndx))
diff --git a/scripts/remove-stale-files b/scripts/remove-stale-files
index 80430b8..7adab46 100755
--- a/scripts/remove-stale-files
+++ b/scripts/remove-stale-files
@@ -39,3 +39,5 @@
rm -f arch/parisc/boot/compressed/${f}
done
fi
+
+rm -f scripts/extract-cert
diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 6b54e46..af4754a 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -111,9 +111,7 @@
exit
fi
-if test -e include/config/auto.conf; then
- . include/config/auto.conf
-else
+if ! test -e include/config/auto.conf; then
echo "Error: kernelrelease not valid - run 'make prepare' to update it" >&2
exit 1
fi
@@ -125,10 +123,11 @@
fi
# CONFIG_LOCALVERSION and LOCALVERSION (if set)
-res="${res}${CONFIG_LOCALVERSION}${LOCALVERSION}"
+config_localversion=$(sed -n 's/^CONFIG_LOCALVERSION=\(.*\)$/\1/p' include/config/auto.conf)
+res="${res}${config_localversion}${LOCALVERSION}"
# scm version string if not at a tagged commit
-if test "$CONFIG_LOCALVERSION_AUTO" = "y"; then
+if grep -q "^CONFIG_LOCALVERSION_AUTO=y$" include/config/auto.conf; then
# full scm version string
res="$res$(scm_version)"
elif [ "${LOCALVERSION+set}" != "set" ]; then
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
index 70bdc78..3a8ea5e 100644
--- a/scripts/sorttable.c
+++ b/scripts/sorttable.c
@@ -233,7 +233,7 @@ static void sort_relative_table(char *extab_image, int image_size)
}
}
-static void arm64_sort_relative_table(char *extab_image, int image_size)
+static void sort_relative_table_with_data(char *extab_image, int image_size)
{
int i = 0;
@@ -261,34 +261,6 @@ static void arm64_sort_relative_table(char *extab_image, int image_size)
}
}
-static void x86_sort_relative_table(char *extab_image, int image_size)
-{
- int i = 0;
-
- while (i < image_size) {
- uint32_t *loc = (uint32_t *)(extab_image + i);
-
- w(r(loc) + i, loc);
- w(r(loc + 1) + i + 4, loc + 1);
- /* Don't touch the fixup type */
-
- i += sizeof(uint32_t) * 3;
- }
-
- qsort(extab_image, image_size / 12, 12, compare_relative_table);
-
- i = 0;
- while (i < image_size) {
- uint32_t *loc = (uint32_t *)(extab_image + i);
-
- w(r(loc) - i, loc);
- w(r(loc + 1) - (i + 4), loc + 1);
- /* Don't touch the fixup type */
-
- i += sizeof(uint32_t) * 3;
- }
-}
-
static void s390_sort_relative_table(char *extab_image, int image_size)
{
int i;
@@ -366,15 +338,14 @@ static int do_file(char const *const fname, void *addr)
switch (r2(&ehdr->e_machine)) {
case EM_386:
+ case EM_AARCH64:
+ case EM_RISCV:
case EM_X86_64:
- custom_sort = x86_sort_relative_table;
+ custom_sort = sort_relative_table_with_data;
break;
case EM_S390:
custom_sort = s390_sort_relative_table;
break;
- case EM_AARCH64:
- custom_sort = arm64_sort_relative_table;
- break;
case EM_PARISC:
case EM_PPC:
case EM_PPC64:
@@ -385,7 +356,6 @@ static int do_file(char const *const fname, void *addr)
case EM_ARM:
case EM_MICROBLAZE:
case EM_MIPS:
- case EM_RISCV:
case EM_XTENSA:
break;
default:
diff --git a/scripts/sorttable.h b/scripts/sorttable.h
index 1e8b779..deb7c1d 100644
--- a/scripts/sorttable.h
+++ b/scripts/sorttable.h
@@ -199,6 +199,8 @@ static int compare_extable(const void *a, const void *b)
return 0;
}
#ifdef MCOUNT_SORT_ENABLED
+pthread_t mcount_sort_thread;
+
struct elf_mcount_loc {
Elf_Ehdr *ehdr;
Elf_Shdr *init_data_sec;
@@ -282,10 +284,9 @@ static int do_sort(Elf_Ehdr *ehdr,
unsigned int shnum;
unsigned int shstrndx;
#ifdef MCOUNT_SORT_ENABLED
- struct elf_mcount_loc mstruct;
+ struct elf_mcount_loc mstruct = {0};
uint_t _start_mcount_loc = 0;
uint_t _stop_mcount_loc = 0;
- pthread_t mcount_sort_thread;
#endif
#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
unsigned int orc_ip_size = 0;
diff --git a/sound/core/init.c b/sound/core/init.c
index ac335f5..31ba702 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -1111,29 +1111,14 @@ EXPORT_SYMBOL(snd_card_file_remove);
*/
int snd_power_ref_and_wait(struct snd_card *card)
{
- wait_queue_entry_t wait;
- int result = 0;
-
snd_power_ref(card);
- /* fastpath */
if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0)
return 0;
- init_waitqueue_entry(&wait, current);
- add_wait_queue(&card->power_sleep, &wait);
- while (1) {
- if (card->shutdown) {
- result = -ENODEV;
- break;
- }
- if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0)
- break;
- snd_power_unref(card);
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(30 * HZ);
- snd_power_ref(card);
- }
- remove_wait_queue(&card->power_sleep, &wait);
- return result;
+ wait_event_cmd(card->power_sleep,
+ card->shutdown ||
+ snd_power_get_state(card) == SNDRV_CTL_POWER_D0,
+ snd_power_unref(card), snd_power_ref(card));
+ return card->shutdown ? -ENODEV : 0;
}
EXPORT_SYMBOL_GPL(snd_power_ref_and_wait);
diff --git a/sound/core/misc.c b/sound/core/misc.c
index 3579dd7..50e4aaa 100644
--- a/sound/core/misc.c
+++ b/sound/core/misc.c
@@ -112,7 +112,7 @@ snd_pci_quirk_lookup_id(u16 vendor, u16 device,
{
const struct snd_pci_quirk *q;
- for (q = list; q->subvendor; q++) {
+ for (q = list; q->subvendor || q->subdevice; q++) {
if (q->subvendor != vendor)
continue;
if (!q->subdevice ||
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index 30b40d8..7185953 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
//
-// cs35l41.c -- CS35l41 ALSA HDA audio driver
+// CS35l41 ALSA HDA audio driver
//
// Copyright 2021 Cirrus Logic, Inc.
//
@@ -17,19 +17,19 @@
#include "cs35l41_hda.h"
static const struct reg_sequence cs35l41_hda_config[] = {
- { CS35L41_PLL_CLK_CTRL, 0x00000430 }, //3200000Hz, BCLK Input, PLL_REFCLK_EN = 1
- { CS35L41_GLOBAL_CLK_CTRL, 0x00000003 }, //GLOBAL_FS = 48 kHz
- { CS35L41_SP_ENABLES, 0x00010000 }, //ASP_RX1_EN = 1
- { CS35L41_SP_RATE_CTRL, 0x00000021 }, //ASP_BCLK_FREQ = 3.072 MHz
- { CS35L41_SP_FORMAT, 0x20200200 }, //24 bits, I2S, BCLK Slave, FSYNC Slave
- { CS35L41_DAC_PCM1_SRC, 0x00000008 }, //DACPCM1_SRC = ASPRX1
- { CS35L41_AMP_DIG_VOL_CTRL, 0x00000000 }, //AMP_VOL_PCM 0.0 dB
- { CS35L41_AMP_GAIN_CTRL, 0x00000084 }, //AMP_GAIN_PCM 4.5 dB
- { CS35L41_PWR_CTRL2, 0x00000001 }, //AMP_EN = 1
+ { CS35L41_PLL_CLK_CTRL, 0x00000430 }, // 3200000Hz, BCLK Input, PLL_REFCLK_EN = 1
+ { CS35L41_GLOBAL_CLK_CTRL, 0x00000003 }, // GLOBAL_FS = 48 kHz
+ { CS35L41_SP_ENABLES, 0x00010000 }, // ASP_RX1_EN = 1
+ { CS35L41_SP_RATE_CTRL, 0x00000021 }, // ASP_BCLK_FREQ = 3.072 MHz
+ { CS35L41_SP_FORMAT, 0x20200200 }, // 24 bits, I2S, BCLK Slave, FSYNC Slave
+ { CS35L41_DAC_PCM1_SRC, 0x00000008 }, // DACPCM1_SRC = ASPRX1
+ { CS35L41_AMP_DIG_VOL_CTRL, 0x00000000 }, // AMP_VOL_PCM 0.0 dB
+ { CS35L41_AMP_GAIN_CTRL, 0x00000084 }, // AMP_GAIN_PCM 4.5 dB
+ { CS35L41_PWR_CTRL2, 0x00000001 }, // AMP_EN = 1
};
static const struct reg_sequence cs35l41_hda_start_bst[] = {
- { CS35L41_PWR_CTRL2, 0x00000021 }, //BST_EN = 10, AMP_EN = 1
+ { CS35L41_PWR_CTRL2, 0x00000021 }, // BST_EN = 10, AMP_EN = 1
{ CS35L41_PWR_CTRL1, 0x00000001, 3000}, // set GLOBAL_EN = 1
};
@@ -60,7 +60,7 @@ static const struct reg_sequence cs35l41_stop_ext_vspk[] = {
{ 0x00000040, 0x00000055 },
{ 0x00000040, 0x000000AA },
{ 0x00007438, 0x00585941 },
- { 0x00002014, 0x00000000, 3000}, //set GLOBAL_EN = 0
+ { 0x00002014, 0x00000000, 3000}, // set GLOBAL_EN = 0
{ 0x0000742C, 0x00000009 },
{ 0x00007438, 0x00580941 },
{ 0x00011008, 0x00000001 },
@@ -78,7 +78,7 @@ static const struct reg_sequence cs35l41_safe_to_active[] = {
{ 0x0000742C, 0x0000000F },
{ 0x0000742C, 0x00000079 },
{ 0x00007438, 0x00585941 },
- { CS35L41_PWR_CTRL1, 0x00000001, 2000 }, //GLOBAL_EN = 1
+ { CS35L41_PWR_CTRL1, 0x00000001, 2000 }, // GLOBAL_EN = 1
{ 0x0000742C, 0x000000F9 },
{ 0x00007438, 0x00580941 },
{ 0x00000040, 0x000000CC },
@@ -89,8 +89,8 @@ static const struct reg_sequence cs35l41_active_to_safe[] = {
{ 0x00000040, 0x00000055 },
{ 0x00000040, 0x000000AA },
{ 0x00007438, 0x00585941 },
- { CS35L41_AMP_DIG_VOL_CTRL, 0x0000A678 }, //AMP_VOL_PCM Mute
- { CS35L41_PWR_CTRL2, 0x00000000 }, //AMP_EN = 0
+ { CS35L41_AMP_DIG_VOL_CTRL, 0x0000A678 }, // AMP_VOL_PCM Mute
+ { CS35L41_PWR_CTRL2, 0x00000000 }, // AMP_EN = 0
{ CS35L41_PWR_CTRL1, 0x00000000 },
{ 0x0000742C, 0x00000009, 2000 },
{ 0x00007438, 0x00580941 },
@@ -161,11 +161,13 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action)
if (reg_seq->close)
ret = regmap_multi_reg_write(reg, reg_seq->close, reg_seq->num_close);
break;
+ default:
+ ret = -EINVAL;
+ break;
}
if (ret)
dev_warn(cs35l41->dev, "Failed to apply multi reg write: %d\n", ret);
-
}
static int cs35l41_hda_channel_map(struct device *dev, unsigned int tx_num, unsigned int *tx_slot,
@@ -182,20 +184,19 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas
struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
struct hda_component *comps = master_data;
- if (comps && cs35l41->index >= 0 && cs35l41->index < HDA_MAX_COMPONENTS)
- comps = &comps[cs35l41->index];
- else
+ if (!comps || cs35l41->index < 0 || cs35l41->index >= HDA_MAX_COMPONENTS)
return -EINVAL;
- if (!comps->dev) {
- comps->dev = dev;
- strscpy(comps->name, dev_name(dev), sizeof(comps->name));
- comps->playback_hook = cs35l41_hda_playback_hook;
- comps->set_channel_map = cs35l41_hda_channel_map;
- return 0;
- }
+ comps = &comps[cs35l41->index];
+ if (comps->dev)
+ return -EBUSY;
- return -EBUSY;
+ comps->dev = dev;
+ strscpy(comps->name, dev_name(dev), sizeof(comps->name));
+ comps->playback_hook = cs35l41_hda_playback_hook;
+ comps->set_channel_map = cs35l41_hda_channel_map;
+
+ return 0;
}
static void cs35l41_hda_unbind(struct device *dev, struct device *master, void *master_data)
@@ -227,6 +228,8 @@ static int cs35l41_hda_apply_properties(struct cs35l41_hda *cs35l41,
internal_boost = true;
switch (hw_cfg->gpio1_func) {
+ case CS35L41_NOT_USED:
+ break;
case CS35l41_VSPK_SWITCH:
regmap_update_bits(cs35l41->regmap, CS35L41_GPIO_PAD_CONTROL,
CS35L41_GPIO1_CTRL_MASK, 1 << CS35L41_GPIO1_CTRL_SHIFT);
@@ -235,13 +238,21 @@ static int cs35l41_hda_apply_properties(struct cs35l41_hda *cs35l41,
regmap_update_bits(cs35l41->regmap, CS35L41_GPIO_PAD_CONTROL,
CS35L41_GPIO1_CTRL_MASK, 2 << CS35L41_GPIO1_CTRL_SHIFT);
break;
+ default:
+ dev_err(cs35l41->dev, "Invalid function %d for GPIO1\n", hw_cfg->gpio1_func);
+ return -EINVAL;
}
switch (hw_cfg->gpio2_func) {
+ case CS35L41_NOT_USED:
+ break;
case CS35L41_INTERRUPT:
regmap_update_bits(cs35l41->regmap, CS35L41_GPIO_PAD_CONTROL,
CS35L41_GPIO2_CTRL_MASK, 2 << CS35L41_GPIO2_CTRL_SHIFT);
break;
+ default:
+ dev_err(cs35l41->dev, "Invalid function %d for GPIO2\n", hw_cfg->gpio2_func);
+ return -EINVAL;
}
if (internal_boost) {
@@ -256,11 +267,7 @@ static int cs35l41_hda_apply_properties(struct cs35l41_hda *cs35l41,
cs35l41->reg_seq = &cs35l41_hda_reg_seq_ext_bst;
}
- ret = cs35l41_hda_channel_map(cs35l41->dev, 0, NULL, 1, (unsigned int *)&hw_cfg->spk_pos);
- if (ret)
- return ret;
-
- return 0;
+ return cs35l41_hda_channel_map(cs35l41->dev, 0, NULL, 1, (unsigned int *)&hw_cfg->spk_pos);
}
static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *cs35l41,
@@ -269,7 +276,7 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
struct cs35l41_hda_hw_config *hw_cfg;
u32 values[HDA_MAX_COMPONENTS];
struct acpi_device *adev;
- struct device *acpi_dev;
+ struct device *physdev;
char *property;
size_t nval;
int i, ret;
@@ -280,11 +287,11 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
return ERR_PTR(-ENODEV);
}
- acpi_dev = get_device(acpi_get_first_physical_node(adev));
+ physdev = get_device(acpi_get_first_physical_node(adev));
acpi_dev_put(adev);
property = "cirrus,dev-index";
- ret = device_property_count_u32(acpi_dev, property);
+ ret = device_property_count_u32(physdev, property);
if (ret <= 0)
goto no_acpi_dsd;
@@ -294,7 +301,7 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
}
nval = ret;
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret)
goto err;
@@ -311,7 +318,9 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
goto err;
}
- /* No devm_ version as CLSA0100, in no_acpi_dsd case, can't use devm version */
+ /* To use the same release code for all laptop variants we can't use devm_ version of
+ * gpiod_get here, as CLSA010* don't have a fully functional bios with an _DSD node
+ */
cs35l41->reset_gpio = fwnode_gpiod_get_index(&adev->fwnode, "reset", cs35l41->index,
GPIOD_OUT_LOW, "cs35l41-reset");
@@ -322,46 +331,46 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
}
property = "cirrus,speaker-position";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret)
goto err_free;
hw_cfg->spk_pos = values[cs35l41->index];
property = "cirrus,gpio1-func";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret)
goto err_free;
hw_cfg->gpio1_func = values[cs35l41->index];
property = "cirrus,gpio2-func";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret)
goto err_free;
hw_cfg->gpio2_func = values[cs35l41->index];
property = "cirrus,boost-peak-milliamp";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret == 0)
hw_cfg->bst_ipk = values[cs35l41->index];
property = "cirrus,boost-ind-nanohenry";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret == 0)
hw_cfg->bst_ind = values[cs35l41->index];
property = "cirrus,boost-cap-microfarad";
- ret = device_property_read_u32_array(acpi_dev, property, values, nval);
+ ret = device_property_read_u32_array(physdev, property, values, nval);
if (ret == 0)
hw_cfg->bst_cap = values[cs35l41->index];
- put_device(acpi_dev);
+ put_device(physdev);
return hw_cfg;
err_free:
kfree(hw_cfg);
err:
- put_device(acpi_dev);
+ put_device(physdev);
dev_err(cs35l41->dev, "Failed property %s: %d\n", property, ret);
return ERR_PTR(ret);
@@ -370,18 +379,18 @@ static struct cs35l41_hda_hw_config *cs35l41_hda_read_acpi(struct cs35l41_hda *c
/*
* Device CLSA0100 doesn't have _DSD so a gpiod_get by the label reset won't work.
* And devices created by i2c-multi-instantiate don't have their device struct pointing to
- * the correct fwnode, so acpi_dev must be used here
+ * the correct fwnode, so acpi_dev must be used here.
* And devm functions expect that the device requesting the resource has the correct
- * fwnode
+ * fwnode.
*/
if (strncmp(hid, "CLSA0100", 8) != 0)
return ERR_PTR(-EINVAL);
/* check I2C address to assign the index */
cs35l41->index = id == 0x40 ? 0 : 1;
- cs35l41->reset_gpio = gpiod_get_index(acpi_dev, NULL, 0, GPIOD_OUT_HIGH);
+ cs35l41->reset_gpio = gpiod_get_index(physdev, NULL, 0, GPIOD_OUT_HIGH);
cs35l41->vspk_always_on = true;
- put_device(acpi_dev);
+ put_device(physdev);
return NULL;
}
@@ -416,8 +425,7 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
if (ret == -EBUSY) {
dev_info(cs35l41->dev, "Reset line busy, assuming shared reset\n");
} else {
- if (ret != -EPROBE_DEFER)
- dev_err(cs35l41->dev, "Failed to get reset GPIO: %d\n", ret);
+ dev_err_probe(cs35l41->dev, ret, "Failed to get reset GPIO: %d\n", ret);
goto err;
}
}
@@ -437,7 +445,8 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
ret = regmap_read(cs35l41->regmap, CS35L41_IRQ1_STATUS3, &int_sts);
if (ret || (int_sts & CS35L41_OTP_BOOT_ERR)) {
- dev_err(cs35l41->dev, "OTP Boot error\n");
+ dev_err(cs35l41->dev, "OTP Boot status %x error: %d\n",
+ int_sts & CS35L41_OTP_BOOT_ERR, ret);
ret = -EIO;
goto err;
}
@@ -463,6 +472,10 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
goto err;
}
+ ret = cs35l41_test_key_unlock(cs35l41->dev, cs35l41->regmap);
+ if (ret)
+ goto err;
+
ret = cs35l41_register_errata_patch(cs35l41->dev, cs35l41->regmap, reg_revid);
if (ret)
goto err;
@@ -473,6 +486,10 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
goto err;
}
+ ret = cs35l41_test_key_lock(cs35l41->dev, cs35l41->regmap);
+ if (ret)
+ goto err;
+
ret = cs35l41_hda_apply_properties(cs35l41, acpi_hw_cfg);
if (ret)
goto err;
@@ -480,8 +497,8 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
acpi_hw_cfg = NULL;
if (cs35l41->reg_seq->probe) {
- ret = regmap_register_patch(cs35l41->regmap, cs35l41->reg_seq->probe,
- cs35l41->reg_seq->num_probe);
+ ret = regmap_multi_reg_write(cs35l41->regmap, cs35l41->reg_seq->probe,
+ cs35l41->reg_seq->num_probe);
if (ret) {
dev_err(cs35l41->dev, "Fail to apply probe reg patch: %d\n", ret);
goto err;
@@ -506,9 +523,9 @@ int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int i
return ret;
}
-EXPORT_SYMBOL_GPL(cs35l41_hda_probe);
+EXPORT_SYMBOL_NS_GPL(cs35l41_hda_probe, SND_HDA_SCODEC_CS35L41);
-int cs35l41_hda_remove(struct device *dev)
+void cs35l41_hda_remove(struct device *dev)
{
struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
@@ -517,11 +534,8 @@ int cs35l41_hda_remove(struct device *dev)
if (!cs35l41->vspk_always_on)
gpiod_set_value_cansleep(cs35l41->reset_gpio, 0);
gpiod_put(cs35l41->reset_gpio);
-
- return 0;
}
-EXPORT_SYMBOL_GPL(cs35l41_hda_remove);
-
+EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
MODULE_DESCRIPTION("CS35L41 HDA Driver");
MODULE_AUTHOR("Lucas Tanure, Cirrus Logic Inc, <tanureal@opensource.cirrus.com>");
diff --git a/sound/pci/hda/cs35l41_hda.h b/sound/pci/hda/cs35l41_hda.h
index 76c69a8..7495100 100644
--- a/sound/pci/hda/cs35l41_hda.h
+++ b/sound/pci/hda/cs35l41_hda.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0
*
- * cs35l41_hda.h -- CS35L41 ALSA HDA audio driver
+ * CS35L41 ALSA HDA audio driver
*
* Copyright 2021 Cirrus Logic, Inc.
*
@@ -64,6 +64,6 @@ struct cs35l41_hda {
int cs35l41_hda_probe(struct device *dev, const char *device_name, int id, int irq,
struct regmap *regmap);
-int cs35l41_hda_remove(struct device *dev);
+void cs35l41_hda_remove(struct device *dev);
#endif /*__CS35L41_HDA_H__*/
diff --git a/sound/pci/hda/cs35l41_hda_i2c.c b/sound/pci/hda/cs35l41_hda_i2c.c
index 4a9462f..e810b27 100644
--- a/sound/pci/hda/cs35l41_hda_i2c.c
+++ b/sound/pci/hda/cs35l41_hda_i2c.c
@@ -32,7 +32,9 @@ static int cs35l41_hda_i2c_probe(struct i2c_client *clt, const struct i2c_device
static int cs35l41_hda_i2c_remove(struct i2c_client *clt)
{
- return cs35l41_hda_remove(&clt->dev);
+ cs35l41_hda_remove(&clt->dev);
+
+ return 0;
}
static const struct i2c_device_id cs35l41_hda_i2c_id[] = {
@@ -58,9 +60,9 @@ static struct i2c_driver cs35l41_i2c_driver = {
.probe = cs35l41_hda_i2c_probe,
.remove = cs35l41_hda_i2c_remove,
};
-
module_i2c_driver(cs35l41_i2c_driver);
MODULE_DESCRIPTION("HDA CS35L41 driver");
+MODULE_IMPORT_NS(SND_HDA_SCODEC_CS35L41);
MODULE_AUTHOR("Lucas Tanure <tanureal@opensource.cirrus.com>");
MODULE_LICENSE("GPL");
diff --git a/sound/pci/hda/cs35l41_hda_spi.c b/sound/pci/hda/cs35l41_hda_spi.c
index 77426e9..9f81238 100644
--- a/sound/pci/hda/cs35l41_hda_spi.c
+++ b/sound/pci/hda/cs35l41_hda_spi.c
@@ -30,7 +30,9 @@ static int cs35l41_hda_spi_probe(struct spi_device *spi)
static int cs35l41_hda_spi_remove(struct spi_device *spi)
{
- return cs35l41_hda_remove(&spi->dev);
+ cs35l41_hda_remove(&spi->dev);
+
+ return 0;
}
static const struct spi_device_id cs35l41_hda_spi_id[] = {
@@ -55,9 +57,9 @@ static struct spi_driver cs35l41_spi_driver = {
.probe = cs35l41_hda_spi_probe,
.remove = cs35l41_hda_spi_remove,
};
-
module_spi_driver(cs35l41_spi_driver);
MODULE_DESCRIPTION("HDA CS35L41 driver");
+MODULE_IMPORT_NS(SND_HDA_SCODEC_CS35L41);
MODULE_AUTHOR("Lucas Tanure <tanureal@opensource.cirrus.com>");
MODULE_LICENSE("GPL");
diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c
index df0b452..2d1fa70 100644
--- a/sound/pci/hda/patch_cs8409-tables.c
+++ b/sound/pci/hda/patch_cs8409-tables.c
@@ -490,6 +490,8 @@ const struct snd_pci_quirk cs8409_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0ADC, "Warlock", CS8409_WARLOCK),
SND_PCI_QUIRK(0x1028, 0x0AF4, "Warlock", CS8409_WARLOCK),
SND_PCI_QUIRK(0x1028, 0x0AF5, "Warlock", CS8409_WARLOCK),
+ SND_PCI_QUIRK(0x1028, 0x0BB5, "Warlock N3 15 TGL-U Nuvoton EC", CS8409_WARLOCK),
+ SND_PCI_QUIRK(0x1028, 0x0BB6, "Warlock V3 15 TGL-U Nuvoton EC", CS8409_WARLOCK),
SND_PCI_QUIRK(0x1028, 0x0A77, "Cyborg", CS8409_CYBORG),
SND_PCI_QUIRK(0x1028, 0x0A78, "Cyborg", CS8409_CYBORG),
SND_PCI_QUIRK(0x1028, 0x0A79, "Cyborg", CS8409_CYBORG),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index eef9736..668274e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6948,6 +6948,7 @@ enum {
ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE,
ALC287_FIXUP_LEGION_16ACHG6,
ALC287_FIXUP_CS35L41_I2C_2,
+ ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED,
};
static const struct hda_fixup alc269_fixups[] = {
@@ -8698,6 +8699,16 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = cs35l41_fixup_i2c_two,
},
+ [ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x19 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x8e11 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC285_FIXUP_HP_MUTE_LED,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -8911,6 +8922,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8895, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 5d391f6..96991dd 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -431,6 +431,14 @@ static const struct usbmix_name_map aorus_master_alc1220vb_map[] = {
{}
};
+/* MSI MPG X570S Carbon Max Wifi with ALC4080 */
+static const struct usbmix_name_map msi_mpg_x570s_carbon_max_wifi_alc4080_map[] = {
+ { 29, "Speaker Playback" },
+ { 30, "Front Headphone Playback" },
+ { 32, "IEC958 Playback" },
+ {}
+};
+
/*
* Control map entries
*/
@@ -577,6 +585,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
.map = trx40_mobo_map,
.connector_map = trx40_mobo_connector_map,
},
+ { /* MSI MPG X570S Carbon Max Wifi */
+ .id = USB_ID(0x0db0, 0x419c),
+ .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map,
+ },
{ /* MSI TRX40 */
.id = USB_ID(0x0db0, 0x543d),
.map = trx40_mobo_map,
diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c
index 150ab3e..e2847c0 100644
--- a/sound/virtio/virtio_card.c
+++ b/sound/virtio/virtio_card.c
@@ -350,7 +350,7 @@ static void virtsnd_remove(struct virtio_device *vdev)
snd_card_free(snd->card);
vdev->config->del_vqs(vdev);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
for (i = 0; snd->substreams && i < snd->nsubstreams; ++i) {
struct virtio_pcm_substream *vss = &snd->substreams[i];
@@ -379,7 +379,7 @@ static int virtsnd_freeze(struct virtio_device *vdev)
virtsnd_ctl_msg_cancel_all(snd);
vdev->config->del_vqs(vdev);
- vdev->config->reset(vdev);
+ virtio_reset_device(vdev);
for (i = 0; i < snd->nsubstreams; ++i)
cancel_work_sync(&snd->substreams[i].elapsed_period);
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 5ef1c15..11e8673 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t)
"RECLAIM %12s%15s%15s\n"
" %15llu%15llu%15llums\n"
"THRASHING%12s%15s%15s\n"
+ " %15llu%15llu%15llums\n"
+ "COMPACT %12s%15s%15s\n"
" %15llu%15llu%15llums\n",
"count", "real total", "virtual total",
"delay total", "delay average",
@@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t)
"count", "delay total", "delay average",
(unsigned long long)t->thrashing_count,
(unsigned long long)t->thrashing_delay_total,
- average_ms(t->thrashing_delay_total, t->thrashing_count));
+ average_ms(t->thrashing_delay_total, t->thrashing_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->compact_count,
+ (unsigned long long)t->compact_delay_total,
+ average_ms(t->compact_delay_total, t->compact_count));
}
static void task_context_switch_counts(struct taskstats *t)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d5b5f2a..18de5f7 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -315,6 +315,7 @@
#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 01e2650..3faf0f9 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -486,6 +486,23 @@
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+/* AMD Collaborative Processor Performance Control MSRs */
+#define MSR_AMD_CPPC_CAP1 0xc00102b0
+#define MSR_AMD_CPPC_ENABLE 0xc00102b1
+#define MSR_AMD_CPPC_CAP2 0xc00102b2
+#define MSR_AMD_CPPC_REQ 0xc00102b3
+#define MSR_AMD_CPPC_STATUS 0xc00102b4
+
+#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff)
+#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff)
+#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff)
+#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff)
+
+#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0)
+#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8)
+#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16)
+#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 1cc9da6..59cf234 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -39,7 +39,7 @@
rep movsq
movl %edx, %ecx
rep movsb
- ret
+ RET
SYM_FUNC_END(memcpy)
SYM_FUNC_END_ALIAS(__memcpy)
EXPORT_SYMBOL(memcpy)
@@ -53,7 +53,7 @@
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
- ret
+ RET
SYM_FUNC_END(memcpy_erms)
SYM_FUNC_START_LOCAL(memcpy_orig)
@@ -137,7 +137,7 @@
movq %r9, 1*8(%rdi)
movq %r10, -2*8(%rdi, %rdx)
movq %r11, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_16bytes:
cmpl $8, %edx
@@ -149,7 +149,7 @@
movq -1*8(%rsi, %rdx), %r9
movq %r8, 0*8(%rdi)
movq %r9, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_8bytes:
cmpl $4, %edx
@@ -162,7 +162,7 @@
movl -4(%rsi, %rdx), %r8d
movl %ecx, (%rdi)
movl %r8d, -4(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_3bytes:
subl $1, %edx
@@ -180,7 +180,7 @@
movb %cl, (%rdi)
.Lend:
- retq
+ RET
SYM_FUNC_END(memcpy_orig)
.popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 9827ae2..d624f2b 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -40,7 +40,7 @@
movl %edx,%ecx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(__memset)
SYM_FUNC_END_ALIAS(memset)
EXPORT_SYMBOL(memset)
@@ -63,7 +63,7 @@
movq %rdx,%rcx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(memset_erms)
SYM_FUNC_START_LOCAL(memset_orig)
@@ -125,7 +125,7 @@
.Lende:
movq %r10,%rax
- ret
+ RET
.Lbad_alignment:
cmpq $7,%rdx
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index d9b4209..f70702f 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -71,8 +71,8 @@ int iter(struct bpf_iter__task_file *ctx)
e.pid = task->tgid;
e.id = get_obj_id(file->private_data, obj_type);
- bpf_probe_read_kernel(&e.comm, sizeof(e.comm),
- task->group_leader->comm);
+ bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm),
+ task->group_leader->comm);
bpf_seq_write(ctx->meta->seq, &e, sizeof(e));
return 0;
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 2cf3b1b..c2a95ab 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -99,7 +99,7 @@
###
## HOSTCC C flags
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
# output directory for tests below
TMPOUT = .tmp_$$$$
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index ad6fa21..38edaa0 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val)
return val * GOLDEN_RATIO_32;
}
-#ifndef HAVE_ARCH_HASH_32
-#define hash_32 hash_32_generic
-#endif
-static inline u32 hash_32_generic(u32 val, unsigned int bits)
+static inline u32 hash_32(u32 val, unsigned int bits)
{
/* High bits are more random, so use them. */
return __hash_32(val) >> (32 - bits);
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 3b810b5..6428085 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1096,6 +1096,24 @@ extern "C" {
#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer)
#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Planes are valid until one has a
+ * zero handle -- this can be used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ */
#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
/*
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f066637..9563d29 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1131,7 +1131,8 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
#define KVM_CAP_ARM_MTE 205
#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
-#define KVM_CAP_XSAVE2 207
+#define KVM_CAP_VM_GPA_BITS 207
+#define KVM_CAP_XSAVE2 208
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1163,11 +1164,20 @@ struct kvm_irq_routing_hv_sint {
__u32 sint;
};
+struct kvm_irq_routing_xen_evtchn {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+};
+
+#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1))
+
/* gsi routing entry types */
#define KVM_IRQ_ROUTING_IRQCHIP 1
#define KVM_IRQ_ROUTING_MSI 2
#define KVM_IRQ_ROUTING_S390_ADAPTER 3
#define KVM_IRQ_ROUTING_HV_SINT 4
+#define KVM_IRQ_ROUTING_XEN_EVTCHN 5
struct kvm_irq_routing_entry {
__u32 gsi;
@@ -1179,6 +1189,7 @@ struct kvm_irq_routing_entry {
struct kvm_irq_routing_msi msi;
struct kvm_irq_routing_s390_adapter adapter;
struct kvm_irq_routing_hv_sint hv_sint;
+ struct kvm_irq_routing_xen_evtchn xen_evtchn;
__u32 pad[8];
} u;
};
@@ -1209,6 +1220,7 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
struct kvm_xen_hvm_config {
__u32 flags;
@@ -1552,8 +1564,6 @@ struct kvm_s390_ucas_mapping {
/* Available with KVM_CAP_XSAVE */
#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave)
#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave)
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
/* Available with KVM_CAP_XCRS */
#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs)
#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs)
@@ -1613,6 +1623,9 @@ struct kvm_enc_region {
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
+
struct kvm_s390_pv_sec_parm {
__u64 origin;
__u64 length;
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bd8860e..4cd39aa 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1332,7 +1332,10 @@ union perf_mem_data_src {
/* hop level */
#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */
-/* 2-7 available */
+#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3 0x04 /* remote board */
+/* 5-7 available */
#define PERF_MEM_HOPS_SHIFT 43
#define PERF_MEM_S(a, s) \
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 63ae5e0..32c5051 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -48,6 +48,7 @@
int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
bool perf_cpu_map__empty(const struct perf_cpu_map *map);
int perf_cpu_map__max(struct perf_cpu_map *map);
+ bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
#define perf_cpu_map__for_each_cpu(cpu, idx, cpus)
--
@@ -135,16 +136,16 @@
int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
void perf_evsel__close(struct perf_evsel *evsel);
- void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+ void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
void perf_evsel__munmap(struct perf_evsel *evsel);
- void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
- int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+ void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+ int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count);
int perf_evsel__enable(struct perf_evsel *evsel);
- int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
int perf_evsel__disable(struct perf_evsel *evsel);
- int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+ int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index adaad3d..ee66760 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -10,15 +10,24 @@
#include <ctype.h>
#include <limits.h>
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
{
- struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+ struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
if (cpus != NULL) {
- cpus->nr = 1;
- cpus->map[0] = -1;
+ cpus->nr = nr_cpus;
refcount_set(&cpus->refcnt, 1);
+
}
+ return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+{
+ struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+ if (cpus)
+ cpus->map[0].cpu = -1;
return cpus;
}
@@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void)
if (nr_cpus < 0)
return NULL;
- cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+ cpus = perf_cpu_map__alloc(nr_cpus);
if (cpus != NULL) {
int i;
for (i = 0; i < nr_cpus; ++i)
- cpus->map[i] = i;
-
- cpus->nr = nr_cpus;
- refcount_set(&cpus->refcnt, 1);
+ cpus->map[i].cpu = i;
}
return cpus;
@@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void)
return cpu_map__default_new();
}
-static int cmp_int(const void *a, const void *b)
+
+static int cmp_cpu(const void *a, const void *b)
{
- return *(const int *)a - *(const int*)b;
+ const struct perf_cpu *cpu_a = a, *cpu_b = b;
+
+ return cpu_a->cpu - cpu_b->cpu;
}
-static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
+static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
{
- size_t payload_size = nr_cpus * sizeof(int);
- struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+ size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
+ struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
int i, j;
if (cpus != NULL) {
memcpy(cpus->map, tmp_cpus, payload_size);
- qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+ qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
/* Remove dups */
j = 0;
for (i = 0; i < nr_cpus; i++) {
- if (i == 0 || cpus->map[i] != cpus->map[i - 1])
- cpus->map[j++] = cpus->map[i];
+ if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
+ cpus->map[j++].cpu = cpus->map[i].cpu;
}
cpus->nr = j;
assert(j <= nr_cpus);
- refcount_set(&cpus->refcnt, 1);
}
-
return cpus;
}
@@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
{
struct perf_cpu_map *cpus = NULL;
int nr_cpus = 0;
- int *tmp_cpus = NULL, *tmp;
+ struct perf_cpu *tmp_cpus = NULL, *tmp;
int max_entries = 0;
int n, cpu, prev;
char sep;
@@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
if (new_max >= max_entries) {
max_entries = new_max + MAX_NR_CPUS / 2;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto out_free_tmp;
tmp_cpus = tmp;
}
while (++prev < cpu)
- tmp_cpus[nr_cpus++] = prev;
+ tmp_cpus[nr_cpus++].cpu = prev;
}
if (nr_cpus == max_entries) {
max_entries += MAX_NR_CPUS;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto out_free_tmp;
tmp_cpus = tmp;
}
- tmp_cpus[nr_cpus++] = cpu;
+ tmp_cpus[nr_cpus++].cpu = cpu;
if (n == 2 && sep == '-')
prev = cpu;
else
@@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
unsigned long start_cpu, end_cpu = 0;
char *p = NULL;
int i, nr_cpus = 0;
- int *tmp_cpus = NULL, *tmp;
+ struct perf_cpu *tmp_cpus = NULL, *tmp;
int max_entries = 0;
if (!cpu_list)
@@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
for (; start_cpu <= end_cpu; start_cpu++) {
/* check for duplicates */
for (i = 0; i < nr_cpus; i++)
- if (tmp_cpus[i] == (int)start_cpu)
+ if (tmp_cpus[i].cpu == (int)start_cpu)
goto invalid;
if (nr_cpus == max_entries) {
max_entries += MAX_NR_CPUS;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto invalid;
tmp_cpus = tmp;
}
- tmp_cpus[nr_cpus++] = (int)start_cpu;
+ tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
}
if (*p)
++p;
@@ -250,12 +257,16 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
return cpus;
}
-int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
+ struct perf_cpu result = {
+ .cpu = -1
+ };
+
if (cpus && idx < cpus->nr)
return cpus->map[idx];
- return -1;
+ return result;
}
int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
@@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
bool perf_cpu_map__empty(const struct perf_cpu_map *map)
{
- return map ? map->map[0] == -1 : true;
+ return map ? map->map[0].cpu == -1 : true;
}
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
- int low = 0, high = cpus->nr;
+ int low, high;
+ if (!cpus)
+ return -1;
+
+ low = 0;
+ high = cpus->nr;
while (low < high) {
- int idx = (low + high) / 2,
- cpu_at_idx = cpus->map[idx];
+ int idx = (low + high) / 2;
+ struct perf_cpu cpu_at_idx = cpus->map[idx];
- if (cpu_at_idx == cpu)
+ if (cpu_at_idx.cpu == cpu.cpu)
return idx;
- if (cpu_at_idx > cpu)
+ if (cpu_at_idx.cpu > cpu.cpu)
high = idx;
else
low = idx + 1;
@@ -288,10 +304,19 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
return -1;
}
-int perf_cpu_map__max(struct perf_cpu_map *map)
+bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
+ return perf_cpu_map__idx(cpus, cpu) != -1;
+}
+
+struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+{
+ struct perf_cpu result = {
+ .cpu = -1
+ };
+
// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
- return map->nr > 0 ? map->map[map->nr - 1] : -1;
+ return map->nr > 0 ? map->map[map->nr - 1] : result;
}
/*
@@ -305,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other)
{
- int *tmp_cpus;
+ struct perf_cpu *tmp_cpus;
int tmp_len;
int i, j, k;
struct perf_cpu_map *merged;
@@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
if (!other)
return orig;
if (orig->nr == other->nr &&
- !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+ !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
return orig;
tmp_len = orig->nr + other->nr;
- tmp_cpus = malloc(tmp_len * sizeof(int));
+ tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
if (!tmp_cpus)
return NULL;
/* Standard merge algorithm from wikipedia */
i = j = k = 0;
while (i < orig->nr && j < other->nr) {
- if (orig->map[i] <= other->map[j]) {
- if (orig->map[i] == other->map[j])
+ if (orig->map[i].cpu <= other->map[j].cpu) {
+ if (orig->map[i].cpu == other->map[j].cpu)
j++;
tmp_cpus[k++] = orig->map[i++];
} else
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e37dfad..9a770bf 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
static int
perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int output, int cpu)
+ int output, struct perf_cpu cpu)
{
return perf_mmap__mmap(map, mp, output, cpu);
}
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
int idx, struct perf_mmap_param *mp, int cpu_idx,
int thread, int *_output, int *_output_overwrite)
{
- int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+ struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
struct perf_evsel *evsel;
int revent;
@@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
}
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
{
- struct perf_evsel *evsel, *leader;
+ struct perf_evsel *first, *last, *evsel;
- leader = list_entry(list->next, struct perf_evsel, node);
- evsel = list_entry(list->prev, struct perf_evsel, node);
+ first = list_first_entry(list, struct perf_evsel, node);
+ last = list_last_entry(list, struct perf_evsel, node);
- leader->nr_members = evsel->idx - leader->idx + 1;
+ leader->nr_members = last->idx - first->idx + 1;
__perf_evlist__for_each_entry(list, evsel)
evsel->leader = leader;
@@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list)
void perf_evlist__set_leader(struct perf_evlist *evlist)
{
if (evlist->nr_entries) {
+ struct perf_evsel *first = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
- __perf_evlist__set_leader(&evlist->entries);
+ __perf_evlist__set_leader(&evlist->entries, first);
}
}
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8441e3e..7ea86a4 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel)
free(evsel);
}
-#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
-#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
+#define FD(_evsel, _cpu_map_idx, _thread) \
+ ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
+#define MMAP(_evsel, _cpu_map_idx, _thread) \
+ (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
+ : NULL)
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
- int cpu, thread;
- for (cpu = 0; cpu < ncpus; cpu++) {
+ int idx, thread;
+
+ for (idx = 0; idx < ncpus; idx++) {
for (thread = 0; thread < nthreads; thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
if (fd)
*fd = -1;
@@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre
static int
sys_perf_event_open(struct perf_event_attr *attr,
- pid_t pid, int cpu, int group_fd,
+ pid_t pid, struct perf_cpu cpu, int group_fd,
unsigned long flags)
{
- return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+ return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
}
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
+static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
{
struct perf_evsel *leader = evsel->leader;
int *fd;
@@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
if (!leader->fd)
return -ENOTCONN;
- fd = FD(leader, cpu, thread);
+ fd = FD(leader, cpu_map_idx, thread);
if (fd == NULL || *fd == -1)
return -EBADF;
@@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads)
{
- int cpu, thread, err = 0;
+ struct perf_cpu cpu;
+ int idx, thread, err = 0;
if (cpus == NULL) {
static struct perf_cpu_map *empty_cpu_map;
@@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
return -ENOMEM;
- for (cpu = 0; cpu < cpus->nr; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
for (thread = 0; thread < threads->nr; thread++) {
int fd, group_fd, *evsel_fd;
- evsel_fd = FD(evsel, cpu, thread);
+ evsel_fd = FD(evsel, idx, thread);
if (evsel_fd == NULL)
return -EINVAL;
- err = get_group_fd(evsel, cpu, thread, &group_fd);
+ err = get_group_fd(evsel, idx, thread, &group_fd);
if (err < 0)
return err;
fd = sys_perf_event_open(&evsel->attr,
threads->map[thread].pid,
- cpus->map[cpu], group_fd, 0);
+ cpu, group_fd, 0);
if (fd < 0)
return -errno;
@@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
return err;
}
-static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
int thread;
for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
if (fd && *fd >= 0) {
close(*fd);
@@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
void perf_evsel__close_fd(struct perf_evsel *evsel)
{
- int cpu;
-
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
- perf_evsel__close_fd_cpu(evsel, cpu);
+ for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
+ perf_evsel__close_fd_cpu(evsel, idx);
}
void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel)
perf_evsel__free_fd(evsel);
}
-void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
if (evsel->fd == NULL)
return;
- perf_evsel__close_fd_cpu(evsel, cpu);
+ perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
}
void perf_evsel__munmap(struct perf_evsel *evsel)
{
- int cpu, thread;
+ int idx, thread;
if (evsel->fd == NULL || evsel->mmap == NULL)
return;
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+ for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
if (fd == NULL || *fd < 0)
continue;
- perf_mmap__munmap(MMAP(evsel, cpu, thread));
+ perf_mmap__munmap(MMAP(evsel, idx, thread));
}
}
@@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
{
- int ret, cpu, thread;
+ int ret, idx, thread;
struct perf_mmap_param mp = {
.prot = PROT_READ | PROT_WRITE,
.mask = (pages * page_size) - 1,
@@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
return -ENOMEM;
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+ for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
struct perf_mmap *map;
+ struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);
if (fd == NULL || *fd < 0)
continue;
- map = MMAP(evsel, cpu, thread);
+ map = MMAP(evsel, idx, thread);
perf_mmap__init(map, NULL, false, NULL);
ret = perf_mmap__mmap(map, &mp, *fd, cpu);
@@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
return 0;
}
-void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
{
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
- if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
+ if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
return NULL;
- return MMAP(evsel, cpu, thread)->base;
+ return MMAP(evsel, cpu_map_idx, thread)->base;
}
int perf_evsel__read_size(struct perf_evsel *evsel)
@@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
return size;
}
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
size_t size = perf_evsel__read_size(evsel);
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
memset(count, 0, sizeof(*count));
if (fd == NULL || *fd < 0)
return -EINVAL;
- if (MMAP(evsel, cpu, thread) &&
- !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+ if (MMAP(evsel, cpu_map_idx, thread) &&
+ !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
return 0;
if (readn(*fd, count->values, size) <= 0)
@@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
int ioc, void *arg,
- int cpu)
+ int cpu_map_idx)
{
int thread;
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
int err;
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
if (fd == NULL || *fd < 0)
return -1;
@@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
return 0;
}
-int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
}
int perf_evsel__enable(struct perf_evsel *evsel)
@@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel)
return err;
}
-int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
}
int perf_evsel__disable(struct perf_evsel *evsel)
@@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
zfree(&evsel->id);
evsel->ids = 0;
}
+
+void perf_counts_values__scale(struct perf_counts_values *count,
+ bool scale, __s8 *pscaled)
+{
+ s8 scaled = 0;
+
+ if (scale) {
+ if (count->run == 0) {
+ scaled = -1;
+ count->val = 0;
+ } else if (count->run < count->ena) {
+ scaled = 1;
+ count->val = (u64)((double)count->val * count->ena / count->run);
+ }
+ }
+
+ if (pscaled)
+ *pscaled = scaled;
+}
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 840d403..581f9ff 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -4,16 +4,30 @@
#include <linux/refcount.h>
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+ int cpu;
+};
+
+/**
+ * A sized, reference counted, sorted array of integers representing CPU
+ * numbers. This is commonly used to capture which CPUs a PMU is associated
+ * with. The indices into the cpumap are frequently used as they avoid having
+ * gaps if CPU numbers were used. For events associated with a pid, rather than
+ * a CPU, a single dummy map with an entry of -1 is used.
+ */
struct perf_cpu_map {
refcount_t refcnt;
+ /** Length of the map array. */
int nr;
- int map[];
+ /** The CPU values. */
+ struct perf_cpu map[];
};
#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 2048
#endif
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu);
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
#endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index f366dbad6..4cefade 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -4,6 +4,7 @@
#include <linux/list.h>
#include <api/fd/array.h>
+#include <internal/cpumap.h>
#include <internal/evsel.h>
#define PERF_EVLIST__HLIST_BITS 8
@@ -36,7 +37,7 @@ typedef void
typedef struct perf_mmap*
(*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
typedef int
-(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int);
+(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu);
struct perf_evlist_mmap_ops {
perf_evlist_mmap__cb_idx_t idx;
@@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
-void __perf_evlist__set_leader(struct list_head *list);
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader);
#endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1f3eacb..cfc9ebd 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -6,8 +6,8 @@
#include <linux/perf_event.h>
#include <stdbool.h>
#include <sys/types.h>
+#include <internal/cpumap.h>
-struct perf_cpu_map;
struct perf_thread_map;
struct xyarray;
@@ -27,7 +27,7 @@ struct perf_sample_id {
* queue number.
*/
int idx;
- int cpu;
+ struct perf_cpu cpu;
pid_t tid;
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5e3422f..5a062af 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -6,6 +6,7 @@
#include <linux/refcount.h>
#include <linux/types.h>
#include <stdbool.h>
+#include <internal/cpumap.h>
/* perf sample has 16 bits size limit */
#define PERF_SAMPLE_MAX_SIZE (1 << 16)
@@ -24,7 +25,7 @@ struct perf_mmap {
void *base;
int mask;
int fd;
- int cpu;
+ struct perf_cpu cpu;
refcount_t refcnt;
u64 prev;
u64 start;
@@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map);
void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
bool overwrite, libperf_unmap_cb_t unmap_cb);
int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int fd, int cpu);
+ int fd, struct perf_cpu cpu);
void perf_mmap__munmap(struct perf_mmap *map);
void perf_mmap__get(struct perf_mmap *map);
void perf_mmap__put(struct perf_mmap *map);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 7c27766..15b8faa 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,11 +3,10 @@
#define __LIBPERF_CPUMAP_H
#include <perf/core.h>
+#include <perf/cpumap.h>
#include <stdio.h>
#include <stdbool.h>
-struct perf_cpu_map;
-
LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
@@ -16,10 +15,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \
for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 60eae25..2a9516b 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -4,6 +4,8 @@
#include <stdint.h>
#include <perf/core.h>
+#include <stdbool.h>
+#include <linux/types.h>
struct perf_evsel;
struct perf_event_attr;
@@ -26,18 +28,20 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
-LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel);
-LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count);
LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
+LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count,
+ bool scale, __s8 *pscaled);
#endif /* __LIBPERF_EVSEL_H */
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 7146860..93696af 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -10,6 +10,7 @@
perf_cpu_map__cpu;
perf_cpu_map__empty;
perf_cpu_map__max;
+ perf_cpu_map__has;
perf_thread_map__new_dummy;
perf_thread_map__set_pid;
perf_thread_map__comm;
@@ -50,6 +51,7 @@
perf_mmap__read_init;
perf_mmap__read_done;
perf_mmap__read_event;
+ perf_counts_values__scale;
local:
*;
};
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index c89dfa5..f7ee07c 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -32,7 +32,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
}
int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int fd, int cpu)
+ int fd, struct perf_cpu cpu)
{
map->prev = 0;
map->mask = mp->mask;
@@ -353,8 +353,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count
count->ena += delta;
if (idx)
count->run += delta;
-
- cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
}
count->val = cnt;
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ce91a58..b3479df 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -21,6 +21,9 @@
#include "tests.h"
#include <internal/evsel.h>
+#define EVENT_NUM 15
+#define WAIT_COUNT 100000000UL
+
static int libperf_print(enum libperf_print_level level,
const char *fmt, va_list ap)
{
@@ -331,7 +334,8 @@ static int test_mmap_cpus(void)
};
cpu_set_t saved_mask;
char path[PATH_MAX];
- int id, err, cpu, tmp;
+ int id, err, tmp;
+ struct perf_cpu cpu;
union perf_event *event;
int count = 0;
@@ -374,7 +378,7 @@ static int test_mmap_cpus(void)
cpu_set_t mask;
CPU_ZERO(&mask);
- CPU_SET(cpu, &mask);
+ CPU_SET(cpu.cpu, &mask);
err = sched_setaffinity(0, sizeof(mask), &mask);
__T("sched_setaffinity failed", err == 0);
@@ -413,6 +417,159 @@ static int test_mmap_cpus(void)
return 0;
}
+static double display_error(long long average,
+ long long high,
+ long long low,
+ long long expected)
+{
+ double error;
+
+ error = (((double)average - expected) / expected) * 100.0;
+
+ __T_VERBOSE(" Expected: %lld\n", expected);
+ __T_VERBOSE(" High: %lld Low: %lld Average: %lld\n",
+ high, low, average);
+
+ __T_VERBOSE(" Average Error = %.2f%%\n", error);
+
+ return error;
+}
+
+static int test_stat_multiplexing(void)
+{
+ struct perf_counts_values expected_counts = { .val = 0 };
+ struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },};
+ struct perf_thread_map *threads;
+ struct perf_evlist *evlist;
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_INSTRUCTIONS,
+ .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+ PERF_FORMAT_TOTAL_TIME_RUNNING,
+ .disabled = 1,
+ };
+ int err, i, nonzero = 0;
+ unsigned long count;
+ long long max = 0, min = 0, avg = 0;
+ double error = 0.0;
+ s8 scaled = 0;
+
+ /* read for non-multiplexing event count */
+ threads = perf_thread_map__new_dummy();
+ __T("failed to create threads", threads);
+
+ perf_thread_map__set_pid(threads, 0, 0);
+
+ evsel = perf_evsel__new(&attr);
+ __T("failed to create evsel", evsel);
+
+ err = perf_evsel__open(evsel, NULL, threads);
+ __T("failed to open evsel", err == 0);
+
+ err = perf_evsel__enable(evsel);
+ __T("failed to enable evsel", err == 0);
+
+ /* wait loop */
+ count = WAIT_COUNT;
+ while (count--)
+ ;
+
+ perf_evsel__read(evsel, 0, 0, &expected_counts);
+ __T("failed to read value for evsel", expected_counts.val != 0);
+ __T("failed to read non-multiplexing event count",
+ expected_counts.ena == expected_counts.run);
+
+ err = perf_evsel__disable(evsel);
+ __T("failed to enable evsel", err == 0);
+
+ perf_evsel__close(evsel);
+ perf_evsel__delete(evsel);
+
+ perf_thread_map__put(threads);
+
+ /* read for multiplexing event count */
+ threads = perf_thread_map__new_dummy();
+ __T("failed to create threads", threads);
+
+ perf_thread_map__set_pid(threads, 0, 0);
+
+ evlist = perf_evlist__new();
+ __T("failed to create evlist", evlist);
+
+ for (i = 0; i < EVENT_NUM; i++) {
+ evsel = perf_evsel__new(&attr);
+ __T("failed to create evsel", evsel);
+
+ perf_evlist__add(evlist, evsel);
+ }
+ perf_evlist__set_maps(evlist, NULL, threads);
+
+ err = perf_evlist__open(evlist);
+ __T("failed to open evsel", err == 0);
+
+ perf_evlist__enable(evlist);
+
+ /* wait loop */
+ count = WAIT_COUNT;
+ while (count--)
+ ;
+
+ i = 0;
+ perf_evlist__for_each_evsel(evlist, evsel) {
+ perf_evsel__read(evsel, 0, 0, &counts[i]);
+ __T("failed to read value for evsel", counts[i].val != 0);
+ i++;
+ }
+
+ perf_evlist__disable(evlist);
+
+ min = counts[0].val;
+ for (i = 0; i < EVENT_NUM; i++) {
+ __T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n",
+ i, counts[i].val, counts[i].run, counts[i].ena);
+
+ perf_counts_values__scale(&counts[i], true, &scaled);
+ if (scaled == 1) {
+ __T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n",
+ counts[i].val,
+ (double)counts[i].run / (double)counts[i].ena * 100.0,
+ counts[i].run, counts[i].ena);
+ } else if (scaled == -1) {
+ __T_VERBOSE("\t Not Running\n");
+ } else {
+ __T_VERBOSE("\t Not Scaling\n");
+ }
+
+ if (counts[i].val > max)
+ max = counts[i].val;
+
+ if (counts[i].val < min)
+ min = counts[i].val;
+
+ avg += counts[i].val;
+
+ if (counts[i].val != 0)
+ nonzero++;
+ }
+
+ if (nonzero != 0)
+ avg = avg / nonzero;
+ else
+ avg = 0;
+
+ error = display_error(avg, max, min, expected_counts.val);
+
+ __T("Error out of range!", ((error <= 1.0) && (error >= -1.0)));
+
+ perf_evlist__close(evlist);
+ perf_evlist__delete(evlist);
+
+ perf_thread_map__put(threads);
+
+ return 0;
+}
+
int test_evlist(int argc, char **argv)
{
__T_START;
@@ -424,6 +581,7 @@ int test_evlist(int argc, char **argv)
test_stat_thread_enable();
test_mmap_thread();
test_mmap_cpus();
+ test_stat_multiplexing();
__T_END;
return tests_failed == 0 ? 0 : -1;
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index cd8ce6e..7e44b41 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -74,12 +74,15 @@
used when creating a uprobe for a process that resides in a
different mount namespace from the perf(1) utility.
---debuginfod=URLs::
+--debuginfod[=URLs]::
Specify debuginfod URL to be used when retrieving perf.data binaries,
it follows the same syntax as the DEBUGINFOD_URLS variable, like:
buildid-cache.debuginfod=http://192.168.122.174:8002
+ If the URLs is not specified, the value of DEBUGINFOD_URLS
+ system environment variable is used.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 3bb75c1..0420e71 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -587,6 +587,15 @@
Use 'n' control blocks in asynchronous (Posix AIO) trace writing
mode ('n' default: 1, max: 4).
+ record.debuginfod::
+ Specify debuginfod URL to be used when cacheing perf.data binaries,
+ it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+ http://192.168.122.174:8002
+
+ If the URLs is 'system', the value of DEBUGINFOD_URLS system environment
+ variable is used.
+
diff.*::
diff.order::
This option sets the number of columns to sort the result.
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 4dc8d0a..57384a9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -81,7 +81,11 @@
The precise modifier works with event types 0x76 (cpu-cycles, CPU
clocks not halted) and 0xC1 (micro-ops retired). Both events map to
IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+(IbsOpCntCtl) set respectively (see the
+Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
+section of the [AMD Processor Programming Reference (PPR)] relevant to the
+family, model and stepping of the processor being used).
+
Manual Volume 2: System Programming, 13.3 Instruction-Based
Sampling). Examples to use IBS:
@@ -94,10 +98,12 @@
Even when an event is not available in a symbolic form within perf right now,
it can be encoded in a per processor specific way.
-For instance For x86 CPUs NNN represents the raw register encoding with the
+For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
-of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
-Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the
+Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the
+[AMD Processor Programming Reference (PPR)] relevant to the family, model
+and stepping of the processor being used).
Note: Only the following bit fields can be set in x86 counter
registers: event, umask, edge, inv, cmask. Esp. guest/host only and
@@ -126,6 +132,38 @@
perf record -e cpu/r1a8/ ...
perf record -e cpu/r0x1a8/ ...
+Some processors, like those from AMD, support event codes and unit masks
+larger than a byte. In such cases, the bits corresponding to the event
+configuration parameters can be seen with:
+
+ cat /sys/bus/event_source/devices/<pmu>/format/<config>
+
+Example:
+
+If the AMD docs for an EPYC 7713 processor describe an event as:
+
+ Event Umask Event Mask
+ Num. Value Mnemonic Description
+
+ 28FH 03H op_cache_hit_miss.op_cache_hit Counts Op Cache micro-tag
+ hit events.
+
+raw encoding of 0x0328F cannot be used since the upper nibble of the
+EventSelect bits have to be specified via bits 32-35 as can be seen with:
+
+ cat /sys/bus/event_source/devices/cpu/format/event
+
+raw encoding of 0x20000038F should be used instead:
+
+ perf stat -e r20000038f -a sleep 1
+ perf record -e r20000038f ...
+
+It's also possible to use pmu syntax:
+
+ perf record -e r20000038f -a sleep 1
+ perf record -e cpu/r20000038f/ ...
+ perf record -e cpu/r0x20000038f/ ...
+
You should refer to the processor specific documentation for getting these
details. Some of them are referenced in the SEE ALSO section below.
@@ -316,4 +354,4 @@
linkperf:perf-stat[1], linkperf:perf-top[1],
linkperf:perf-record[1],
http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3cf7bac..9ccc759 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -30,8 +30,10 @@
- a symbolic event name (use 'perf list' to list all events)
- - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ - a raw PMU event in the form of rN where N is a hexadecimal value
+ that represents the raw register encoding with the layout of the
+ event control registers as described by entries in
+ /sys/bus/event_sources/devices/cpu/format/*.
- a symbolic or raw PMU event followed by an optional colon
and a list of event modifiers, e.g., cpu-cycles:p. See the
@@ -713,6 +715,15 @@
include::intel-hybrid.txt[]
+--debuginfod[=URLs]::
+ Specify debuginfod URL to be used when cacheing perf.data binaries,
+ it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+ http://192.168.122.174:8002
+
+ If the URLs is not specified, the value of DEBUGINFOD_URLS
+ system environment variable is used.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 7e6fb7c..c06c341e 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -36,8 +36,10 @@
- a symbolic event name (use 'perf list' to list all events)
- - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ - a raw PMU event in the form of rN where N is a hexadecimal value
+ that represents the raw register encoding with the layout of the
+ event control registers as described by entries in
+ /sys/bus/event_sources/devices/cpu/format/*.
- a symbolic or raw PMU event followed by an optional colon
and a list of event modifiers, e.g., cpu-cycles:p. See the
@@ -493,6 +495,10 @@
$ perf config stat.no-csv-summary=true
+--cputype::
+Only enable events on applying cpu with this type for hybrid platform
+(e.g. core or atom)"
+
EXAMPLES
--------
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 9898a32..cac3dfb 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -38,9 +38,10 @@
-e <event>::
--event=<event>::
Select the PMU event. Selection can be a symbolic event name
- (use 'perf list' to list all events) or a raw PMU
- event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ (use 'perf list' to list all events) or a raw PMU event in the form
+ of rN where N is a hexadecimal value that represents the raw register
+ encoding with the layout of the event control registers as described
+ by entries in /sys/bus/event_sources/devices/cpu/format/*.
-E <entries>::
--entries=<entries>::
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 3df74cf..96ad944 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -17,6 +17,7 @@
detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
+HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
include $(srctree)/tools/scripts/Makefile.arch
@@ -143,7 +144,10 @@
ifdef CSINCLUDES
LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
endif
-OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++
+OPENCSDLIBS := -lopencsd_c_api
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+ OPENCSDLIBS += -lopencsd -lstdc++
+endif
ifdef CSLIBS
LIBOPENCSD_LDFLAGS := -L$(CSLIBS)
endif
@@ -211,6 +215,7 @@
ifneq ($(WERROR),0)
CORE_CFLAGS += -Werror
CXXFLAGS += -Werror
+ HOSTCFLAGS += -Werror
endif
ifndef DEBUG
@@ -290,6 +295,9 @@
CXXFLAGS += -funwind-tables
CXXFLAGS += -Wno-strict-aliasing
+HOSTCFLAGS += -Wall
+HOSTCFLAGS += -Wextra
+
# Enforce a non-executable stack, as we may regress (again) in the future by
# adding assembler files missing the .GNU-stack linker note.
LDFLAGS += -Wl,-z,noexecstack
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 80522bc..ac861e4 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -226,7 +226,7 @@
endif
export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR
+export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
include $(srctree)/tools/build/Makefile.include
@@ -1041,7 +1041,7 @@
SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp)
SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
-SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h
+SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
$(SKEL_TMP_OUT) $(LIBBPF_OUTPUT):
$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index 4085419..99a0655 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_ARM_PC
#define PERF_REG_SP PERF_REG_ARM_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_ARM_R0:
- return "r0";
- case PERF_REG_ARM_R1:
- return "r1";
- case PERF_REG_ARM_R2:
- return "r2";
- case PERF_REG_ARM_R3:
- return "r3";
- case PERF_REG_ARM_R4:
- return "r4";
- case PERF_REG_ARM_R5:
- return "r5";
- case PERF_REG_ARM_R6:
- return "r6";
- case PERF_REG_ARM_R7:
- return "r7";
- case PERF_REG_ARM_R8:
- return "r8";
- case PERF_REG_ARM_R9:
- return "r9";
- case PERF_REG_ARM_R10:
- return "r10";
- case PERF_REG_ARM_FP:
- return "fp";
- case PERF_REG_ARM_IP:
- return "ip";
- case PERF_REG_ARM_SP:
- return "sp";
- case PERF_REG_ARM_LR:
- return "lr";
- case PERF_REG_ARM_PC:
- return "pc";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 293a23b..2e8b2c4 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -203,9 +203,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
/* Set option of each CPU we have */
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(event_cpus, i) ||
- !cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(event_cpus, cpu) ||
+ !perf_cpu_map__has(online_cpus, cpu))
continue;
if (option & BIT(ETM_OPT_CTXTID)) {
@@ -407,25 +409,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
}
- /* Validate auxtrace_mmap_pages provided by user */
- if (opts->auxtrace_mmap_pages) {
- unsigned int max_page = (KiB(128) / page_size);
- size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
-
- if (!privileged &&
- opts->auxtrace_mmap_pages > max_page) {
- opts->auxtrace_mmap_pages = max_page;
- pr_err("auxtrace too big, truncating to %d\n",
- max_page);
- }
-
- if (!is_power_of_2(sz)) {
- pr_err("Invalid mmap size for %s: must be a power of 2\n",
- CORESIGHT_ETM_PMU_NAME);
- return -EINVAL;
- }
- }
-
if (opts->auxtrace_snapshot_mode)
pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
opts->auxtrace_snapshot_size);
@@ -541,9 +524,11 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
/* cpu map is not empty, we have specific CPUs to work with */
if (!perf_cpu_map__empty(event_cpus)) {
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(event_cpus, i) ||
- !cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(event_cpus, cpu) ||
+ !perf_cpu_map__has(online_cpus, cpu))
continue;
if (cs_etm_is_ete(itr, i))
@@ -555,8 +540,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
}
} else {
/* get configuration for all CPUs in the system */
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(online_cpus, cpu))
continue;
if (cs_etm_is_ete(itr, i))
@@ -741,8 +728,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
} else {
/* Make sure all specified CPUs are online */
for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
- if (cpu_map__has(event_cpus, i) &&
- !cpu_map__has(online_cpus, i))
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (perf_cpu_map__has(event_cpus, cpu) &&
+ !perf_cpu_map__has(online_cpus, cpu))
return -EINVAL;
}
@@ -762,9 +751,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
offset = CS_ETM_SNAPSHOT + 1;
- for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
- if (cpu_map__has(cpu_map, i))
+ for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (perf_cpu_map__has(cpu_map, cpu))
cs_etm_get_metadata(i, &offset, itr, info);
+ }
perf_cpu_map__put(online_cpus);
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index fa3e0745..35a3cc7 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -4,7 +4,9 @@
#include <stdlib.h>
#include <linux/types.h>
+#define perf_event_arm_regs perf_event_arm64_regs
#include <asm/perf_regs.h>
+#undef perf_event_arm_regs
void perf_regs_load(u64 *regs);
@@ -15,80 +17,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_ARM64_PC
#define PERF_REG_SP PERF_REG_ARM64_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_ARM64_X0:
- return "x0";
- case PERF_REG_ARM64_X1:
- return "x1";
- case PERF_REG_ARM64_X2:
- return "x2";
- case PERF_REG_ARM64_X3:
- return "x3";
- case PERF_REG_ARM64_X4:
- return "x4";
- case PERF_REG_ARM64_X5:
- return "x5";
- case PERF_REG_ARM64_X6:
- return "x6";
- case PERF_REG_ARM64_X7:
- return "x7";
- case PERF_REG_ARM64_X8:
- return "x8";
- case PERF_REG_ARM64_X9:
- return "x9";
- case PERF_REG_ARM64_X10:
- return "x10";
- case PERF_REG_ARM64_X11:
- return "x11";
- case PERF_REG_ARM64_X12:
- return "x12";
- case PERF_REG_ARM64_X13:
- return "x13";
- case PERF_REG_ARM64_X14:
- return "x14";
- case PERF_REG_ARM64_X15:
- return "x15";
- case PERF_REG_ARM64_X16:
- return "x16";
- case PERF_REG_ARM64_X17:
- return "x17";
- case PERF_REG_ARM64_X18:
- return "x18";
- case PERF_REG_ARM64_X19:
- return "x19";
- case PERF_REG_ARM64_X20:
- return "x20";
- case PERF_REG_ARM64_X21:
- return "x21";
- case PERF_REG_ARM64_X22:
- return "x22";
- case PERF_REG_ARM64_X23:
- return "x23";
- case PERF_REG_ARM64_X24:
- return "x24";
- case PERF_REG_ARM64_X25:
- return "x25";
- case PERF_REG_ARM64_X26:
- return "x26";
- case PERF_REG_ARM64_X27:
- return "x27";
- case PERF_REG_ARM64_X28:
- return "x28";
- case PERF_REG_ARM64_X29:
- return "x29";
- case PERF_REG_ARM64_SP:
- return "sp";
- case PERF_REG_ARM64_LR:
- return "lr";
- case PERF_REG_ARM64_PC:
- return "pc";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index 7e77142..d2ce31e 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -5,6 +5,8 @@
#include <string.h>
#include "debug.h"
#include "symbol.h"
+#include "callchain.h"
+#include "record.h"
/* On arm64, kernel text segment starts at high memory address,
* for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
@@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
p->end = c->start;
pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
}
+
+void arch__add_leaf_frame_record_opts(struct record_opts *opts)
+{
+ opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
+}
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index d3a18f9..79124bb 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -15,7 +15,7 @@ const struct pmu_events_map *pmu_events_map__find(void)
* The cpumap should cover all CPUs. Otherwise, some CPUs may
* not support some events or have different event IDs.
*/
- if (pmu->cpus->nr != cpu__max_cpu())
+ if (pmu->cpus->nr != cpu__max_cpu().cpu)
return NULL;
return perf_pmu__find_map(pmu);
diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h
index 25ac3bd..1afcc0e 100644
--- a/tools/perf/arch/csky/include/perf_regs.h
+++ b/tools/perf/arch/csky/include/perf_regs.h
@@ -15,86 +15,4 @@
#define PERF_REG_IP PERF_REG_CSKY_PC
#define PERF_REG_SP PERF_REG_CSKY_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_CSKY_A0:
- return "a0";
- case PERF_REG_CSKY_A1:
- return "a1";
- case PERF_REG_CSKY_A2:
- return "a2";
- case PERF_REG_CSKY_A3:
- return "a3";
- case PERF_REG_CSKY_REGS0:
- return "regs0";
- case PERF_REG_CSKY_REGS1:
- return "regs1";
- case PERF_REG_CSKY_REGS2:
- return "regs2";
- case PERF_REG_CSKY_REGS3:
- return "regs3";
- case PERF_REG_CSKY_REGS4:
- return "regs4";
- case PERF_REG_CSKY_REGS5:
- return "regs5";
- case PERF_REG_CSKY_REGS6:
- return "regs6";
- case PERF_REG_CSKY_REGS7:
- return "regs7";
- case PERF_REG_CSKY_REGS8:
- return "regs8";
- case PERF_REG_CSKY_REGS9:
- return "regs9";
- case PERF_REG_CSKY_SP:
- return "sp";
- case PERF_REG_CSKY_LR:
- return "lr";
- case PERF_REG_CSKY_PC:
- return "pc";
-#if defined(__CSKYABIV2__)
- case PERF_REG_CSKY_EXREGS0:
- return "exregs0";
- case PERF_REG_CSKY_EXREGS1:
- return "exregs1";
- case PERF_REG_CSKY_EXREGS2:
- return "exregs2";
- case PERF_REG_CSKY_EXREGS3:
- return "exregs3";
- case PERF_REG_CSKY_EXREGS4:
- return "exregs4";
- case PERF_REG_CSKY_EXREGS5:
- return "exregs5";
- case PERF_REG_CSKY_EXREGS6:
- return "exregs6";
- case PERF_REG_CSKY_EXREGS7:
- return "exregs7";
- case PERF_REG_CSKY_EXREGS8:
- return "exregs8";
- case PERF_REG_CSKY_EXREGS9:
- return "exregs9";
- case PERF_REG_CSKY_EXREGS10:
- return "exregs10";
- case PERF_REG_CSKY_EXREGS11:
- return "exregs11";
- case PERF_REG_CSKY_EXREGS12:
- return "exregs12";
- case PERF_REG_CSKY_EXREGS13:
- return "exregs13";
- case PERF_REG_CSKY_EXREGS14:
- return "exregs14";
- case PERF_REG_CSKY_TLS:
- return "tls";
- case PERF_REG_CSKY_HI:
- return "hi";
- case PERF_REG_CSKY_LO:
- return "lo";
-#endif
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h
index ee73b36..b8cd8bb 100644
--- a/tools/perf/arch/mips/include/perf_regs.h
+++ b/tools/perf/arch/mips/include/perf_regs.h
@@ -12,73 +12,4 @@
#define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1)
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_MIPS_PC:
- return "PC";
- case PERF_REG_MIPS_R1:
- return "$1";
- case PERF_REG_MIPS_R2:
- return "$2";
- case PERF_REG_MIPS_R3:
- return "$3";
- case PERF_REG_MIPS_R4:
- return "$4";
- case PERF_REG_MIPS_R5:
- return "$5";
- case PERF_REG_MIPS_R6:
- return "$6";
- case PERF_REG_MIPS_R7:
- return "$7";
- case PERF_REG_MIPS_R8:
- return "$8";
- case PERF_REG_MIPS_R9:
- return "$9";
- case PERF_REG_MIPS_R10:
- return "$10";
- case PERF_REG_MIPS_R11:
- return "$11";
- case PERF_REG_MIPS_R12:
- return "$12";
- case PERF_REG_MIPS_R13:
- return "$13";
- case PERF_REG_MIPS_R14:
- return "$14";
- case PERF_REG_MIPS_R15:
- return "$15";
- case PERF_REG_MIPS_R16:
- return "$16";
- case PERF_REG_MIPS_R17:
- return "$17";
- case PERF_REG_MIPS_R18:
- return "$18";
- case PERF_REG_MIPS_R19:
- return "$19";
- case PERF_REG_MIPS_R20:
- return "$20";
- case PERF_REG_MIPS_R21:
- return "$21";
- case PERF_REG_MIPS_R22:
- return "$22";
- case PERF_REG_MIPS_R23:
- return "$23";
- case PERF_REG_MIPS_R24:
- return "$24";
- case PERF_REG_MIPS_R25:
- return "$25";
- case PERF_REG_MIPS_R28:
- return "$28";
- case PERF_REG_MIPS_R29:
- return "$29";
- case PERF_REG_MIPS_R30:
- return "$30";
- case PERF_REG_MIPS_R31:
- return "$31";
- default:
- break;
- }
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 93339d1..9bb17c3 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -19,70 +19,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_POWERPC_NIP
#define PERF_REG_SP PERF_REG_POWERPC_R1
-static const char *reg_names[] = {
- [PERF_REG_POWERPC_R0] = "r0",
- [PERF_REG_POWERPC_R1] = "r1",
- [PERF_REG_POWERPC_R2] = "r2",
- [PERF_REG_POWERPC_R3] = "r3",
- [PERF_REG_POWERPC_R4] = "r4",
- [PERF_REG_POWERPC_R5] = "r5",
- [PERF_REG_POWERPC_R6] = "r6",
- [PERF_REG_POWERPC_R7] = "r7",
- [PERF_REG_POWERPC_R8] = "r8",
- [PERF_REG_POWERPC_R9] = "r9",
- [PERF_REG_POWERPC_R10] = "r10",
- [PERF_REG_POWERPC_R11] = "r11",
- [PERF_REG_POWERPC_R12] = "r12",
- [PERF_REG_POWERPC_R13] = "r13",
- [PERF_REG_POWERPC_R14] = "r14",
- [PERF_REG_POWERPC_R15] = "r15",
- [PERF_REG_POWERPC_R16] = "r16",
- [PERF_REG_POWERPC_R17] = "r17",
- [PERF_REG_POWERPC_R18] = "r18",
- [PERF_REG_POWERPC_R19] = "r19",
- [PERF_REG_POWERPC_R20] = "r20",
- [PERF_REG_POWERPC_R21] = "r21",
- [PERF_REG_POWERPC_R22] = "r22",
- [PERF_REG_POWERPC_R23] = "r23",
- [PERF_REG_POWERPC_R24] = "r24",
- [PERF_REG_POWERPC_R25] = "r25",
- [PERF_REG_POWERPC_R26] = "r26",
- [PERF_REG_POWERPC_R27] = "r27",
- [PERF_REG_POWERPC_R28] = "r28",
- [PERF_REG_POWERPC_R29] = "r29",
- [PERF_REG_POWERPC_R30] = "r30",
- [PERF_REG_POWERPC_R31] = "r31",
- [PERF_REG_POWERPC_NIP] = "nip",
- [PERF_REG_POWERPC_MSR] = "msr",
- [PERF_REG_POWERPC_ORIG_R3] = "orig_r3",
- [PERF_REG_POWERPC_CTR] = "ctr",
- [PERF_REG_POWERPC_LINK] = "link",
- [PERF_REG_POWERPC_XER] = "xer",
- [PERF_REG_POWERPC_CCR] = "ccr",
- [PERF_REG_POWERPC_SOFTE] = "softe",
- [PERF_REG_POWERPC_TRAP] = "trap",
- [PERF_REG_POWERPC_DAR] = "dar",
- [PERF_REG_POWERPC_DSISR] = "dsisr",
- [PERF_REG_POWERPC_SIER] = "sier",
- [PERF_REG_POWERPC_MMCRA] = "mmcra",
- [PERF_REG_POWERPC_MMCR0] = "mmcr0",
- [PERF_REG_POWERPC_MMCR1] = "mmcr1",
- [PERF_REG_POWERPC_MMCR2] = "mmcr2",
- [PERF_REG_POWERPC_MMCR3] = "mmcr3",
- [PERF_REG_POWERPC_SIER2] = "sier2",
- [PERF_REG_POWERPC_SIER3] = "sier3",
- [PERF_REG_POWERPC_PMC1] = "pmc1",
- [PERF_REG_POWERPC_PMC2] = "pmc2",
- [PERF_REG_POWERPC_PMC3] = "pmc3",
- [PERF_REG_POWERPC_PMC4] = "pmc4",
- [PERF_REG_POWERPC_PMC5] = "pmc5",
- [PERF_REG_POWERPC_PMC6] = "pmc6",
- [PERF_REG_POWERPC_SDAR] = "sdar",
- [PERF_REG_POWERPC_SIAR] = "siar",
-};
-
-static inline const char *__perf_reg_name(int id)
-{
- return reg_names[id];
-}
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c
index 3bf4412..cf430a4 100644
--- a/tools/perf/arch/powerpc/util/event.c
+++ b/tools/perf/arch/powerpc/util/event.c
@@ -40,8 +40,12 @@ const char *arch_perf_header_entry(const char *se_header)
{
if (!strcmp(se_header, "Local INSTR Latency"))
return "Finish Cyc";
- else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ else if (!strcmp(se_header, "INSTR Latency"))
+ return "Global Finish_cyc";
+ else if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
return "Dispatch Cyc";
+ else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ return "Global Dispatch_cyc";
return se_header;
}
@@ -49,5 +53,7 @@ int arch_support_sort_key(const char *sort_key)
{
if (!strcmp(sort_key, "p_stage_cyc"))
return 1;
+ if (!strcmp(sort_key, "local_p_stage_cyc"))
+ return 1;
return 0;
}
diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h
index 6b02a76..6944bf0 100644
--- a/tools/perf/arch/riscv/include/perf_regs.h
+++ b/tools/perf/arch/riscv/include/perf_regs.h
@@ -19,78 +19,4 @@
#define PERF_REG_IP PERF_REG_RISCV_PC
#define PERF_REG_SP PERF_REG_RISCV_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_RISCV_PC:
- return "pc";
- case PERF_REG_RISCV_RA:
- return "ra";
- case PERF_REG_RISCV_SP:
- return "sp";
- case PERF_REG_RISCV_GP:
- return "gp";
- case PERF_REG_RISCV_TP:
- return "tp";
- case PERF_REG_RISCV_T0:
- return "t0";
- case PERF_REG_RISCV_T1:
- return "t1";
- case PERF_REG_RISCV_T2:
- return "t2";
- case PERF_REG_RISCV_S0:
- return "s0";
- case PERF_REG_RISCV_S1:
- return "s1";
- case PERF_REG_RISCV_A0:
- return "a0";
- case PERF_REG_RISCV_A1:
- return "a1";
- case PERF_REG_RISCV_A2:
- return "a2";
- case PERF_REG_RISCV_A3:
- return "a3";
- case PERF_REG_RISCV_A4:
- return "a4";
- case PERF_REG_RISCV_A5:
- return "a5";
- case PERF_REG_RISCV_A6:
- return "a6";
- case PERF_REG_RISCV_A7:
- return "a7";
- case PERF_REG_RISCV_S2:
- return "s2";
- case PERF_REG_RISCV_S3:
- return "s3";
- case PERF_REG_RISCV_S4:
- return "s4";
- case PERF_REG_RISCV_S5:
- return "s5";
- case PERF_REG_RISCV_S6:
- return "s6";
- case PERF_REG_RISCV_S7:
- return "s7";
- case PERF_REG_RISCV_S8:
- return "s8";
- case PERF_REG_RISCV_S9:
- return "s9";
- case PERF_REG_RISCV_S10:
- return "s10";
- case PERF_REG_RISCV_S11:
- return "s11";
- case PERF_REG_RISCV_T3:
- return "t3";
- case PERF_REG_RISCV_T4:
- return "t4";
- case PERF_REG_RISCV_T5:
- return "t5";
- case PERF_REG_RISCV_T6:
- return "t6";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
index ce30315..52fcc08 100644
--- a/tools/perf/arch/s390/include/perf_regs.h
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -14,82 +14,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_S390_PC
#define PERF_REG_SP PERF_REG_S390_R15
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_S390_R0:
- return "R0";
- case PERF_REG_S390_R1:
- return "R1";
- case PERF_REG_S390_R2:
- return "R2";
- case PERF_REG_S390_R3:
- return "R3";
- case PERF_REG_S390_R4:
- return "R4";
- case PERF_REG_S390_R5:
- return "R5";
- case PERF_REG_S390_R6:
- return "R6";
- case PERF_REG_S390_R7:
- return "R7";
- case PERF_REG_S390_R8:
- return "R8";
- case PERF_REG_S390_R9:
- return "R9";
- case PERF_REG_S390_R10:
- return "R10";
- case PERF_REG_S390_R11:
- return "R11";
- case PERF_REG_S390_R12:
- return "R12";
- case PERF_REG_S390_R13:
- return "R13";
- case PERF_REG_S390_R14:
- return "R14";
- case PERF_REG_S390_R15:
- return "R15";
- case PERF_REG_S390_FP0:
- return "FP0";
- case PERF_REG_S390_FP1:
- return "FP1";
- case PERF_REG_S390_FP2:
- return "FP2";
- case PERF_REG_S390_FP3:
- return "FP3";
- case PERF_REG_S390_FP4:
- return "FP4";
- case PERF_REG_S390_FP5:
- return "FP5";
- case PERF_REG_S390_FP6:
- return "FP6";
- case PERF_REG_S390_FP7:
- return "FP7";
- case PERF_REG_S390_FP8:
- return "FP8";
- case PERF_REG_S390_FP9:
- return "FP9";
- case PERF_REG_S390_FP10:
- return "FP10";
- case PERF_REG_S390_FP11:
- return "FP11";
- case PERF_REG_S390_FP12:
- return "FP12";
- case PERF_REG_S390_FP13:
- return "FP13";
- case PERF_REG_S390_FP14:
- return "FP14";
- case PERF_REG_S390_FP15:
- return "FP15";
- case PERF_REG_S390_MASK:
- return "MASK";
- case PERF_REG_S390_PC:
- return "PC";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index cddc4cd..16e23b7 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -23,86 +23,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_X86_IP
#define PERF_REG_SP PERF_REG_X86_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_X86_AX:
- return "AX";
- case PERF_REG_X86_BX:
- return "BX";
- case PERF_REG_X86_CX:
- return "CX";
- case PERF_REG_X86_DX:
- return "DX";
- case PERF_REG_X86_SI:
- return "SI";
- case PERF_REG_X86_DI:
- return "DI";
- case PERF_REG_X86_BP:
- return "BP";
- case PERF_REG_X86_SP:
- return "SP";
- case PERF_REG_X86_IP:
- return "IP";
- case PERF_REG_X86_FLAGS:
- return "FLAGS";
- case PERF_REG_X86_CS:
- return "CS";
- case PERF_REG_X86_SS:
- return "SS";
- case PERF_REG_X86_DS:
- return "DS";
- case PERF_REG_X86_ES:
- return "ES";
- case PERF_REG_X86_FS:
- return "FS";
- case PERF_REG_X86_GS:
- return "GS";
-#ifdef HAVE_ARCH_X86_64_SUPPORT
- case PERF_REG_X86_R8:
- return "R8";
- case PERF_REG_X86_R9:
- return "R9";
- case PERF_REG_X86_R10:
- return "R10";
- case PERF_REG_X86_R11:
- return "R11";
- case PERF_REG_X86_R12:
- return "R12";
- case PERF_REG_X86_R13:
- return "R13";
- case PERF_REG_X86_R14:
- return "R14";
- case PERF_REG_X86_R15:
- return "R15";
-#endif /* HAVE_ARCH_X86_64_SUPPORT */
-
-#define XMM(x) \
- case PERF_REG_X86_XMM ## x: \
- case PERF_REG_X86_XMM ## x + 1: \
- return "XMM" #x;
- XMM(0)
- XMM(1)
- XMM(2)
- XMM(3)
- XMM(4)
- XMM(5)
- XMM(6)
- XMM(7)
- XMM(8)
- XMM(9)
- XMM(10)
- XMM(11)
- XMM(12)
- XMM(13)
- XMM(14)
- XMM(15)
-#undef XMM
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 0b09510..f924246 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
else
return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
}
+
+struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ struct evsel *evsel, *first;
+
+ first = list_first_entry(list, struct evsel, core.node);
+
+ if (!pmu_have_event("cpu", "slots"))
+ return first;
+
+ __evlist__for_each_entry(list, evsel) {
+ if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
+ evsel->name && strstr(evsel->name, "slots"))
+ return evsel;
+ }
+ return first;
+}
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index ddaca75..1a17ec8 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -253,7 +253,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
if (!noaffinity) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 79d13db..0d1dd88 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -342,7 +342,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
if (!noaffinity) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fcdea3e..9627b6a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -177,7 +177,7 @@ int bench_futex_hash(int argc, const char **argv)
goto errmem;
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 137890f..a512a32 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -136,7 +136,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
worker[i].futex = &global_futex;
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index f7a5ffe..aca47ce 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -131,7 +131,7 @@ static void block_threads(pthread_t *w,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 0983f40..888ee60 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -152,7 +152,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 2226a475..aa82db5 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -105,7 +105,7 @@ static void block_threads(pthread_t *w,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index d089516..d291f3a 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -226,7 +226,6 @@ static void run_collection(struct collection *coll)
if (!bench->fn)
break;
printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
- fflush(stdout);
argv[1] = bench->name;
run_bench(coll->name, bench->name, bench->fn, 1, argv);
@@ -247,6 +246,9 @@ int cmd_bench(int argc, const char **argv)
struct collection *coll;
int ret = 0;
+ /* Unbuffered output */
+ setvbuf(stdout, NULL, _IONBF, 0);
+
if (argc < 2) {
/* No collection specified. */
print_usage();
@@ -300,7 +302,6 @@ int cmd_bench(int argc, const char **argv)
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
- fflush(stdout);
ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
goto end;
}
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 0db3cfc..cd38169 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -351,10 +351,14 @@ static int build_id_cache__show_all(void)
static int perf_buildid_cache_config(const char *var, const char *value, void *cb)
{
- const char **debuginfod = cb;
+ struct perf_debuginfod *di = cb;
- if (!strcmp(var, "buildid-cache.debuginfod"))
- *debuginfod = strdup(value);
+ if (!strcmp(var, "buildid-cache.debuginfod")) {
+ di->urls = strdup(value);
+ if (!di->urls)
+ return -ENOMEM;
+ di->set = true;
+ }
return 0;
}
@@ -373,8 +377,8 @@ int cmd_buildid_cache(int argc, const char **argv)
*purge_name_list_str = NULL,
*missing_filename = NULL,
*update_name_list_str = NULL,
- *kcore_filename = NULL,
- *debuginfod = NULL;
+ *kcore_filename = NULL;
+ struct perf_debuginfod debuginfod = { };
char sbuf[STRERR_BUFSIZE];
struct perf_data data = {
@@ -399,8 +403,10 @@ int cmd_buildid_cache(int argc, const char **argv)
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_STRING('u', "update", &update_name_list_str, "file list",
"file(s) to update"),
- OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url",
- "set debuginfod url"),
+ OPT_STRING_OPTARG_SET(0, "debuginfod", &debuginfod.urls,
+ &debuginfod.set, "debuginfod urls",
+ "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+ "system"),
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"),
OPT_END()
@@ -425,10 +431,7 @@ int cmd_buildid_cache(int argc, const char **argv)
if (argc || !(list_files || opts_flag))
usage_with_options(buildid_cache_usage, buildid_cache_options);
- if (debuginfod) {
- pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod);
- setenv("DEBUGINFOD_URLS", debuginfod, 1);
- }
+ perf_debuginfod_setup(&debuginfod);
/* -l is exclusive. It can not be used with other options. */
if (list_files && opts_flag) {
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index b5c67ef..77dd4af 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2015,7 +2015,8 @@ static int setup_nodes(struct perf_session *session)
{
struct numa_node *n;
unsigned long **nodes;
- int node, cpu;
+ int node, idx;
+ struct perf_cpu cpu;
int *cpu2node;
if (c2c.node_info > 2)
@@ -2038,8 +2039,8 @@ static int setup_nodes(struct perf_session *session)
if (!cpu2node)
return -ENOMEM;
- for (cpu = 0; cpu < c2c.cpus_cnt; cpu++)
- cpu2node[cpu] = -1;
+ for (idx = 0; idx < c2c.cpus_cnt; idx++)
+ cpu2node[idx] = -1;
c2c.cpu2node = cpu2node;
@@ -2057,13 +2058,13 @@ static int setup_nodes(struct perf_session *session)
if (perf_cpu_map__empty(map))
continue;
- for (cpu = 0; cpu < map->nr; cpu++) {
- set_bit(map->map[cpu], set);
+ perf_cpu_map__for_each_cpu(cpu, idx, map) {
+ set_bit(cpu.cpu, set);
- if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug"))
+ if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug"))
return -EINVAL;
- cpu2node[map->map[cpu]] = node;
+ cpu2node[cpu.cpu] = node;
}
}
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 87cb11a..7145259 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -13,7 +13,9 @@
#include <signal.h>
#include <stdlib.h>
#include <fcntl.h>
+#include <math.h>
#include <poll.h>
+#include <ctype.h>
#include <linux/capability.h>
#include <linux/string.h>
@@ -28,36 +30,12 @@
#include "strfilter.h"
#include "util/cap.h"
#include "util/config.h"
+#include "util/ftrace.h"
#include "util/units.h"
#include "util/parse-sublevel-options.h"
#define DEFAULT_TRACER "function_graph"
-struct perf_ftrace {
- struct evlist *evlist;
- struct target target;
- const char *tracer;
- struct list_head filters;
- struct list_head notrace;
- struct list_head graph_funcs;
- struct list_head nograph_funcs;
- int graph_depth;
- unsigned long percpu_buffer_size;
- bool inherit;
- int func_stack_trace;
- int func_irq_info;
- int graph_nosleep_time;
- int graph_noirqs;
- int graph_verbose;
- int graph_thresh;
- unsigned int initial_delay;
-};
-
-struct filter_entry {
- struct list_head list;
- char name[];
-};
-
static volatile int workload_exec_errno;
static bool done;
@@ -303,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
int ret;
int last_cpu;
- last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+ last_cpu = perf_cpu_map__cpu(cpumap, cpumap->nr - 1).cpu;
mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
@@ -565,7 +543,24 @@ static int set_tracing_options(struct perf_ftrace *ftrace)
return 0;
}
-static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+static void select_tracer(struct perf_ftrace *ftrace)
+{
+ bool graph = !list_empty(&ftrace->graph_funcs) ||
+ !list_empty(&ftrace->nograph_funcs);
+ bool func = !list_empty(&ftrace->filters) ||
+ !list_empty(&ftrace->notrace);
+
+ /* The function_graph has priority over function tracer. */
+ if (graph)
+ ftrace->tracer = "function_graph";
+ else if (func)
+ ftrace->tracer = "function";
+ /* Otherwise, the default tracer is used. */
+
+ pr_debug("%s tracer is used\n", ftrace->tracer);
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace)
{
char *trace_file;
int trace_fd;
@@ -586,10 +581,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
return -1;
}
- signal(SIGINT, sig_handler);
- signal(SIGUSR1, sig_handler);
- signal(SIGCHLD, sig_handler);
- signal(SIGPIPE, sig_handler);
+ select_tracer(ftrace);
if (reset_tracing_files(ftrace) < 0) {
pr_err("failed to reset ftrace\n");
@@ -600,11 +592,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
if (write_tracing_file("trace", "0") < 0)
goto out;
- if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false,
- ftrace__workload_exec_failed_signal) < 0) {
- goto out;
- }
-
if (set_tracing_options(ftrace) < 0)
goto out_reset;
@@ -693,6 +680,270 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
return (done && !workload_exec_errno) ? 0 : -1;
}
+static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf)
+{
+ char *p, *q;
+ char *unit;
+ double num;
+ int i;
+
+ /* ensure NUL termination */
+ buf[len] = '\0';
+
+ /* handle data line by line */
+ for (p = buf; (q = strchr(p, '\n')) != NULL; p = q + 1) {
+ *q = '\0';
+ /* move it to the line buffer */
+ strcat(linebuf, p);
+
+ /*
+ * parse trace output to get function duration like in
+ *
+ * # tracer: function_graph
+ * #
+ * # CPU DURATION FUNCTION CALLS
+ * # | | | | | | |
+ * 1) + 10.291 us | do_filp_open();
+ * 1) 4.889 us | do_filp_open();
+ * 1) 6.086 us | do_filp_open();
+ *
+ */
+ if (linebuf[0] == '#')
+ goto next;
+
+ /* ignore CPU */
+ p = strchr(linebuf, ')');
+ if (p == NULL)
+ p = linebuf;
+
+ while (*p && !isdigit(*p) && (*p != '|'))
+ p++;
+
+ /* no duration */
+ if (*p == '\0' || *p == '|')
+ goto next;
+
+ num = strtod(p, &unit);
+ if (!unit || strncmp(unit, " us", 3))
+ goto next;
+
+ i = log2(num);
+ if (i < 0)
+ i = 0;
+ if (i >= NUM_BUCKET)
+ i = NUM_BUCKET - 1;
+
+ buckets[i]++;
+
+next:
+ /* empty the line buffer for the next output */
+ linebuf[0] = '\0';
+ }
+
+ /* preserve any remaining output (before newline) */
+ strcat(linebuf, p);
+}
+
+static void display_histogram(int buckets[])
+{
+ int i;
+ int total = 0;
+ int bar_total = 46; /* to fit in 80 column */
+ char bar[] = "###############################################";
+ int bar_len;
+
+ for (i = 0; i < NUM_BUCKET; i++)
+ total += buckets[i];
+
+ if (total == 0) {
+ printf("No data found\n");
+ return;
+ }
+
+ printf("# %14s | %10s | %-*s |\n",
+ " DURATION ", "COUNT", bar_total, "GRAPH");
+
+ bar_len = buckets[0] * bar_total / total;
+ printf(" %4d - %-4d %s | %10d | %.*s%*s |\n",
+ 0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, "");
+
+ for (i = 1; i < NUM_BUCKET - 1; i++) {
+ int start = (1 << (i - 1));
+ int stop = 1 << i;
+ const char *unit = "us";
+
+ if (start >= 1024) {
+ start >>= 10;
+ stop >>= 10;
+ unit = "ms";
+ }
+ bar_len = buckets[i] * bar_total / total;
+ printf(" %4d - %-4d %s | %10d | %.*s%*s |\n",
+ start, stop, unit, buckets[i], bar_len, bar,
+ bar_total - bar_len, "");
+ }
+
+ bar_len = buckets[NUM_BUCKET - 1] * bar_total / total;
+ printf(" %4d - %-4s %s | %10d | %.*s%*s |\n",
+ 1, "...", " s", buckets[NUM_BUCKET - 1], bar_len, bar,
+ bar_total - bar_len, "");
+
+}
+
+static int prepare_func_latency(struct perf_ftrace *ftrace)
+{
+ char *trace_file;
+ int fd;
+
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_prepare_bpf(ftrace);
+
+ if (reset_tracing_files(ftrace) < 0) {
+ pr_err("failed to reset ftrace\n");
+ return -1;
+ }
+
+ /* reset ftrace buffer */
+ if (write_tracing_file("trace", "0") < 0)
+ return -1;
+
+ if (set_tracing_options(ftrace) < 0)
+ return -1;
+
+ /* force to use the function_graph tracer to track duration */
+ if (write_tracing_file("current_tracer", "function_graph") < 0) {
+ pr_err("failed to set current_tracer to function_graph\n");
+ return -1;
+ }
+
+ trace_file = get_tracing_file("trace_pipe");
+ if (!trace_file) {
+ pr_err("failed to open trace_pipe\n");
+ return -1;
+ }
+
+ fd = open(trace_file, O_RDONLY);
+ if (fd < 0)
+ pr_err("failed to open trace_pipe\n");
+
+ put_tracing_file(trace_file);
+ return fd;
+}
+
+static int start_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_start_bpf(ftrace);
+
+ if (write_tracing_file("tracing_on", "1") < 0) {
+ pr_err("can't enable tracing\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int stop_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_stop_bpf(ftrace);
+
+ write_tracing_file("tracing_on", "0");
+ return 0;
+}
+
+static int read_func_latency(struct perf_ftrace *ftrace, int buckets[])
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_read_bpf(ftrace, buckets);
+
+ return 0;
+}
+
+static int cleanup_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_cleanup_bpf(ftrace);
+
+ reset_tracing_files(ftrace);
+ return 0;
+}
+
+static int __cmd_latency(struct perf_ftrace *ftrace)
+{
+ int trace_fd;
+ char buf[4096];
+ char line[256];
+ struct pollfd pollfd = {
+ .events = POLLIN,
+ };
+ int buckets[NUM_BUCKET] = { };
+
+ if (!(perf_cap__capable(CAP_PERFMON) ||
+ perf_cap__capable(CAP_SYS_ADMIN))) {
+ pr_err("ftrace only works for %s!\n",
+#ifdef HAVE_LIBCAP_SUPPORT
+ "users with the CAP_PERFMON or CAP_SYS_ADMIN capability"
+#else
+ "root"
+#endif
+ );
+ return -1;
+ }
+
+ trace_fd = prepare_func_latency(ftrace);
+ if (trace_fd < 0)
+ goto out;
+
+ fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+ pollfd.fd = trace_fd;
+
+ if (start_func_latency(ftrace) < 0)
+ goto out;
+
+ evlist__start_workload(ftrace->evlist);
+
+ line[0] = '\0';
+ while (!done) {
+ if (poll(&pollfd, 1, -1) < 0)
+ break;
+
+ if (pollfd.revents & POLLIN) {
+ int n = read(trace_fd, buf, sizeof(buf) - 1);
+ if (n < 0)
+ break;
+
+ make_histogram(buckets, buf, n, line);
+ }
+ }
+
+ stop_func_latency(ftrace);
+
+ if (workload_exec_errno) {
+ const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf));
+ pr_err("workload failed: %s\n", emsg);
+ goto out;
+ }
+
+ /* read remaining buffer contents */
+ while (!ftrace->target.use_bpf) {
+ int n = read(trace_fd, buf, sizeof(buf) - 1);
+ if (n <= 0)
+ break;
+ make_histogram(buckets, buf, n, line);
+ }
+
+ read_func_latency(ftrace, buckets);
+
+ display_histogram(buckets);
+
+out:
+ close(trace_fd);
+ cleanup_func_latency(ftrace);
+
+ return (done && !workload_exec_errno) ? 0 : -1;
+}
+
static int perf_ftrace_config(const char *var, const char *value, void *cb)
{
struct perf_ftrace *ftrace = cb;
@@ -855,22 +1106,11 @@ static int parse_graph_tracer_opts(const struct option *opt,
return 0;
}
-static void select_tracer(struct perf_ftrace *ftrace)
-{
- bool graph = !list_empty(&ftrace->graph_funcs) ||
- !list_empty(&ftrace->nograph_funcs);
- bool func = !list_empty(&ftrace->filters) ||
- !list_empty(&ftrace->notrace);
-
- /* The function_graph has priority over function tracer. */
- if (graph)
- ftrace->tracer = "function_graph";
- else if (func)
- ftrace->tracer = "function";
- /* Otherwise, the default tracer is used. */
-
- pr_debug("%s tracer is used\n", ftrace->tracer);
-}
+enum perf_ftrace_subcommand {
+ PERF_FTRACE_NONE,
+ PERF_FTRACE_TRACE,
+ PERF_FTRACE_LATENCY,
+};
int cmd_ftrace(int argc, const char **argv)
{
@@ -879,17 +1119,7 @@ int cmd_ftrace(int argc, const char **argv)
.tracer = DEFAULT_TRACER,
.target = { .uid = UINT_MAX, },
};
- const char * const ftrace_usage[] = {
- "perf ftrace [<options>] [<command>]",
- "perf ftrace [<options>] -- <command> [<options>]",
- NULL
- };
- const struct option ftrace_options[] = {
- OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
- "Tracer to use: function_graph(default) or function"),
- OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
- "Show available functions to filter",
- opt_list_avail_functions, "*"),
+ const struct option common_options[] = {
OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
"Trace on existing process id"),
/* TODO: Add short option -t after -t/--tracer can be removed. */
@@ -901,6 +1131,14 @@ int cmd_ftrace(int argc, const char **argv)
"System-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
"List of cpus to monitor"),
+ OPT_END()
+ };
+ const struct option ftrace_options[] = {
+ OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+ "Tracer to use: function_graph(default) or function"),
+ OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+ "Show available functions to filter",
+ opt_list_avail_functions, "*"),
OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
"Trace given functions using function tracer",
parse_filter_func),
@@ -923,24 +1161,65 @@ int cmd_ftrace(int argc, const char **argv)
"Trace children processes"),
OPT_UINTEGER('D', "delay", &ftrace.initial_delay,
"Number of milliseconds to wait before starting tracing after program start"),
- OPT_END()
+ OPT_PARENT(common_options),
};
+ const struct option latency_options[] = {
+ OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
+ "Show latency of given function", parse_filter_func),
+#ifdef HAVE_BPF_SKEL
+ OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf,
+ "Use BPF to measure function latency"),
+#endif
+ OPT_PARENT(common_options),
+ };
+ const struct option *options = ftrace_options;
+
+ const char * const ftrace_usage[] = {
+ "perf ftrace [<options>] [<command>]",
+ "perf ftrace [<options>] -- [<command>] [<options>]",
+ "perf ftrace {trace|latency} [<options>] [<command>]",
+ "perf ftrace {trace|latency} [<options>] -- [<command>] [<options>]",
+ NULL
+ };
+ enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE;
INIT_LIST_HEAD(&ftrace.filters);
INIT_LIST_HEAD(&ftrace.notrace);
INIT_LIST_HEAD(&ftrace.graph_funcs);
INIT_LIST_HEAD(&ftrace.nograph_funcs);
+ signal(SIGINT, sig_handler);
+ signal(SIGUSR1, sig_handler);
+ signal(SIGCHLD, sig_handler);
+ signal(SIGPIPE, sig_handler);
+
ret = perf_config(perf_ftrace_config, &ftrace);
if (ret < 0)
return -1;
- argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc && target__none(&ftrace.target))
- ftrace.target.system_wide = true;
+ if (argc > 1) {
+ if (!strcmp(argv[1], "trace")) {
+ subcmd = PERF_FTRACE_TRACE;
+ } else if (!strcmp(argv[1], "latency")) {
+ subcmd = PERF_FTRACE_LATENCY;
+ options = latency_options;
+ }
- select_tracer(&ftrace);
+ if (subcmd != PERF_FTRACE_NONE) {
+ argc--;
+ argv++;
+ }
+ }
+ /* for backward compatibility */
+ if (subcmd == PERF_FTRACE_NONE)
+ subcmd = PERF_FTRACE_TRACE;
+
+ argc = parse_options(argc, argv, options, ftrace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc < 0) {
+ ret = -EINVAL;
+ goto out_delete_filters;
+ }
ret = target__validate(&ftrace.target);
if (ret) {
@@ -961,7 +1240,35 @@ int cmd_ftrace(int argc, const char **argv)
if (ret < 0)
goto out_delete_evlist;
- ret = __cmd_ftrace(&ftrace, argc, argv);
+ if (argc) {
+ ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target,
+ argv, false,
+ ftrace__workload_exec_failed_signal);
+ if (ret < 0)
+ goto out_delete_evlist;
+ }
+
+ switch (subcmd) {
+ case PERF_FTRACE_TRACE:
+ if (!argc && target__none(&ftrace.target))
+ ftrace.target.system_wide = true;
+ ret = __cmd_ftrace(&ftrace);
+ break;
+ case PERF_FTRACE_LATENCY:
+ if (list_empty(&ftrace.filters)) {
+ pr_err("Should provide a function to measure\n");
+ parse_options_usage(ftrace_usage, options, "T", 1);
+ ret = -EINVAL;
+ goto out_delete_evlist;
+ }
+ ret = __cmd_latency(&ftrace);
+ break;
+ case PERF_FTRACE_NONE:
+ default:
+ pr_err("Invalid subcommand\n");
+ ret = -EINVAL;
+ break;
+ }
out_delete_evlist:
evlist__delete(ftrace.evlist);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index da03a34..99d7ff9 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -192,7 +192,7 @@ static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_samp
int ret = evsel__process_alloc_event(evsel, sample);
if (!ret) {
- int node1 = cpu__get_node(sample->cpu),
+ int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
node2 = evsel__intval(evsel, sample, "node");
if (node1 != node2)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0338b81..bb716c9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -111,6 +111,7 @@ struct record {
unsigned long long samples;
struct mmap_cpu_mask affinity_mask;
unsigned long output_max_size; /* = 0: unlimited */
+ struct perf_debuginfod debuginfod;
};
static volatile int done;
@@ -2177,6 +2178,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
rec->opts.nr_cblocks = nr_cblocks_default;
}
#endif
+ if (!strcmp(var, "record.debuginfod")) {
+ rec->debuginfod.urls = strdup(value);
+ if (!rec->debuginfod.urls)
+ return -ENOMEM;
+ rec->debuginfod.set = true;
+ }
return 0;
}
@@ -2267,6 +2274,10 @@ static int record__parse_mmap_pages(const struct option *opt,
return ret;
}
+void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
+{
+}
+
static int parse_control_option(const struct option *opt,
const char *str,
int unset __maybe_unused)
@@ -2663,6 +2674,10 @@ static struct option __record_options[] = {
parse_control_option),
OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
"Fine-tune event synthesis: default=all", parse_record_synth_option),
+ OPT_STRING_OPTARG_SET(0, "debuginfod", &record.debuginfod.urls,
+ &record.debuginfod.set, "debuginfod urls",
+ "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+ "system"),
OPT_END()
};
@@ -2716,6 +2731,8 @@ int cmd_record(int argc, const char **argv)
if (err)
return err;
+ perf_debuginfod_setup(&record.debuginfod);
+
/* Make system wide (-a) the default target. */
if (!argc && target__none(&rec->opts.target))
rec->opts.target.system_wide = true;
@@ -2792,7 +2809,7 @@ int cmd_record(int argc, const char **argv)
symbol__init(NULL);
if (rec->opts.affinity != PERF_AFFINITY_SYS) {
- rec->affinity_mask.nbits = cpu__max_cpu();
+ rec->affinity_mask.nbits = cpu__max_cpu().cpu;
rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits);
if (!rec->affinity_mask.bits) {
pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
@@ -2898,6 +2915,10 @@ int cmd_record(int argc, const char **argv)
}
rec->opts.target.hybrid = perf_pmu__has_hybrid();
+
+ if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP)
+ arch__add_leaf_frame_record_opts(&rec->opts);
+
err = -ENOMEM;
if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8ae4004..1dd92d8 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep)
}
}
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env));
if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
@@ -1127,7 +1127,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused,
* on events sample_type.
*/
sample_type = evlist__combined_sample_type(*pevlist);
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
return 0;
}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 4527f63..72d446d 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -167,7 +167,7 @@ struct trace_sched_handler {
struct perf_sched_map {
DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS);
- int *comp_cpus;
+ struct perf_cpu *comp_cpus;
bool comp;
struct perf_thread_map *color_pids;
const char *color_pids_str;
@@ -191,7 +191,7 @@ struct perf_sched {
* Track the current task - that way we can know whether there's any
* weird events, such as a task being switched away that is not current.
*/
- int max_cpu;
+ struct perf_cpu max_cpu;
u32 curr_pid[MAX_CPUS];
struct thread *curr_thread[MAX_CPUS];
char next_shortname1;
@@ -1535,28 +1535,31 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
int new_shortname;
u64 timestamp0, timestamp = sample->time;
s64 delta;
- int i, this_cpu = sample->cpu;
+ int i;
+ struct perf_cpu this_cpu = {
+ .cpu = sample->cpu,
+ };
int cpus_nr;
bool new_cpu = false;
const char *color = PERF_COLOR_NORMAL;
char stimestamp[32];
- BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
+ BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
- if (this_cpu > sched->max_cpu)
+ if (this_cpu.cpu > sched->max_cpu.cpu)
sched->max_cpu = this_cpu;
if (sched->map.comp) {
cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS);
- if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) {
+ if (!test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) {
sched->map.comp_cpus[cpus_nr++] = this_cpu;
new_cpu = true;
}
} else
- cpus_nr = sched->max_cpu;
+ cpus_nr = sched->max_cpu.cpu;
- timestamp0 = sched->cpu_last_switched[this_cpu];
- sched->cpu_last_switched[this_cpu] = timestamp;
+ timestamp0 = sched->cpu_last_switched[this_cpu.cpu];
+ sched->cpu_last_switched[this_cpu.cpu] = timestamp;
if (timestamp0)
delta = timestamp - timestamp0;
else
@@ -1577,7 +1580,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
return -1;
}
- sched->curr_thread[this_cpu] = thread__get(sched_in);
+ sched->curr_thread[this_cpu.cpu] = thread__get(sched_in);
printf(" ");
@@ -1608,8 +1611,10 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
}
for (i = 0; i < cpus_nr; i++) {
- int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
- struct thread *curr_thread = sched->curr_thread[cpu];
+ struct perf_cpu cpu = {
+ .cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i,
+ };
+ struct thread *curr_thread = sched->curr_thread[cpu.cpu];
struct thread_runtime *curr_tr;
const char *pid_color = color;
const char *cpu_color = color;
@@ -1617,19 +1622,19 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
if (curr_thread && thread__has_color(curr_thread))
pid_color = COLOR_PIDS;
- if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu))
+ if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, cpu))
continue;
- if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu))
+ if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu))
cpu_color = COLOR_CPUS;
- if (cpu != this_cpu)
+ if (cpu.cpu != this_cpu.cpu)
color_fprintf(stdout, color, " ");
else
color_fprintf(stdout, cpu_color, "*");
- if (sched->curr_thread[cpu]) {
- curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+ if (sched->curr_thread[cpu.cpu]) {
+ curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]);
if (curr_tr == NULL) {
thread__put(sched_in);
return -1;
@@ -1639,7 +1644,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
color_fprintf(stdout, color, " ");
}
- if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
+ if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu))
goto out;
timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
@@ -1929,7 +1934,7 @@ static char *timehist_get_commstr(struct thread *thread)
static void timehist_header(struct perf_sched *sched)
{
- u32 ncpus = sched->max_cpu + 1;
+ u32 ncpus = sched->max_cpu.cpu + 1;
u32 i, j;
printf("%15s %6s ", "time", "cpu");
@@ -2008,7 +2013,7 @@ static void timehist_print_sample(struct perf_sched *sched,
struct thread_runtime *tr = thread__priv(thread);
const char *next_comm = evsel__strval(evsel, sample, "next_comm");
const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
- u32 max_cpus = sched->max_cpu + 1;
+ u32 max_cpus = sched->max_cpu.cpu + 1;
char tstr[64];
char nstr[30];
u64 wait_time;
@@ -2389,7 +2394,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
printf("%15s [%04d] ", tstr, sample->cpu);
if (sched->show_cpu_visual)
- printf(" %*s ", sched->max_cpu + 1, "");
+ printf(" %*s ", sched->max_cpu.cpu + 1, "");
printf(" %-*s ", comm_width, timehist_get_commstr(thread));
@@ -2449,13 +2454,13 @@ static void timehist_print_migration_event(struct perf_sched *sched,
{
struct thread *thread;
char tstr[64];
- u32 max_cpus = sched->max_cpu + 1;
+ u32 max_cpus;
u32 ocpu, dcpu;
if (sched->summary_only)
return;
- max_cpus = sched->max_cpu + 1;
+ max_cpus = sched->max_cpu.cpu + 1;
ocpu = evsel__intval(evsel, sample, "orig_cpu");
dcpu = evsel__intval(evsel, sample, "dest_cpu");
@@ -2918,7 +2923,7 @@ static void timehist_print_summary(struct perf_sched *sched,
printf(" Total scheduling time (msec): ");
print_sched_time(hist_time, 2);
- printf(" (x %d)\n", sched->max_cpu);
+ printf(" (x %d)\n", sched->max_cpu.cpu);
}
typedef int (*sched_handler)(struct perf_tool *tool,
@@ -2935,9 +2940,11 @@ static int perf_timehist__process_sample(struct perf_tool *tool,
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
int err = 0;
- int this_cpu = sample->cpu;
+ struct perf_cpu this_cpu = {
+ .cpu = sample->cpu,
+ };
- if (this_cpu > sched->max_cpu)
+ if (this_cpu.cpu > sched->max_cpu.cpu)
sched->max_cpu = this_cpu;
if (evsel->handler != NULL) {
@@ -3054,10 +3061,10 @@ static int perf_sched__timehist(struct perf_sched *sched)
goto out;
/* pre-allocate struct for per-CPU idle stats */
- sched->max_cpu = session->header.env.nr_cpus_online;
- if (sched->max_cpu == 0)
- sched->max_cpu = 4;
- if (init_idle_threads(sched->max_cpu))
+ sched->max_cpu.cpu = session->header.env.nr_cpus_online;
+ if (sched->max_cpu.cpu == 0)
+ sched->max_cpu.cpu = 4;
+ if (init_idle_threads(sched->max_cpu.cpu))
goto out;
/* summary_only implies summary option, but don't overwrite summary if set */
@@ -3209,10 +3216,10 @@ static int setup_map_cpus(struct perf_sched *sched)
{
struct perf_cpu_map *map;
- sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
+ sched->max_cpu.cpu = sysconf(_SC_NPROCESSORS_CONF);
if (sched->map.comp) {
- sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int));
+ sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int));
if (!sched->map.comp_cpus)
return -1;
}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c82b033..ecd4f99 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -15,6 +15,7 @@
#include "util/symbol.h"
#include "util/thread.h"
#include "util/trace-event.h"
+#include "util/env.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/evsel_fprintf.h"
@@ -648,7 +649,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
return 0;
}
-static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
+static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch,
FILE *fp)
{
unsigned i = 0, r;
@@ -661,7 +662,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
u64 val = regs->regs[i++];
- printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+ printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val);
}
return printed;
@@ -718,17 +719,17 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen,
}
static int perf_sample__fprintf_iregs(struct perf_sample *sample,
- struct perf_event_attr *attr, FILE *fp)
+ struct perf_event_attr *attr, const char *arch, FILE *fp)
{
return perf_sample__fprintf_regs(&sample->intr_regs,
- attr->sample_regs_intr, fp);
+ attr->sample_regs_intr, arch, fp);
}
static int perf_sample__fprintf_uregs(struct perf_sample *sample,
- struct perf_event_attr *attr, FILE *fp)
+ struct perf_event_attr *attr, const char *arch, FILE *fp)
{
return perf_sample__fprintf_regs(&sample->user_regs,
- attr->sample_regs_user, fp);
+ attr->sample_regs_user, arch, fp);
}
static int perf_sample__fprintf_start(struct perf_script *script,
@@ -2000,6 +2001,7 @@ static void process_event(struct perf_script *script,
struct evsel_script *es = evsel->priv;
FILE *fp = es->fp;
char str[PAGE_SIZE_NAME_LEN];
+ const char *arch = perf_env__arch(machine->env);
if (output[type].fields == 0)
return;
@@ -2066,10 +2068,10 @@ static void process_event(struct perf_script *script,
}
if (PRINT_FIELD(IREGS))
- perf_sample__fprintf_iregs(sample, attr, fp);
+ perf_sample__fprintf_iregs(sample, attr, arch, fp);
if (PRINT_FIELD(UREGS))
- perf_sample__fprintf_uregs(sample, attr, fp);
+ perf_sample__fprintf_uregs(sample, attr, arch, fp);
if (PRINT_FIELD(BRSTACK))
perf_sample__fprintf_brstack(sample, thread, attr, fp);
@@ -2113,8 +2115,8 @@ static struct scripting_ops *scripting_ops;
static void __process_stat(struct evsel *counter, u64 tstamp)
{
int nthreads = perf_thread_map__nr(counter->core.threads);
- int ncpus = evsel__nr_cpus(counter);
- int cpu, thread;
+ int idx, thread;
+ struct perf_cpu cpu;
static int header_printed;
if (counter->core.system_wide)
@@ -2127,13 +2129,13 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
}
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
struct perf_counts_values *counts;
- counts = perf_counts(counter->counts, cpu, thread);
+ counts = perf_counts(counter->counts, idx, thread);
printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
- counter->core.cpus->map[cpu],
+ cpu.cpu,
perf_thread_map__pid(counter->core.threads, thread),
counts->val,
counts->ena,
@@ -2316,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
* on events sample_type.
*/
sample_type = evlist__combined_sample_type(evlist);
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
/* Enable fields for callchain entries */
if (symbol_conf.use_callchain &&
@@ -3466,16 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script)
struct perf_session *session = script->session;
u64 sample_type = evlist__combined_sample_type(session->evlist);
- if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
- if ((sample_type & PERF_SAMPLE_REGS_USER) &&
- (sample_type & PERF_SAMPLE_STACK_USER)) {
- callchain_param.record_mode = CALLCHAIN_DWARF;
- dwarf_callchain_users = true;
- } else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
- callchain_param.record_mode = CALLCHAIN_LBR;
- else
- callchain_param.record_mode = CALLCHAIN_FP;
- }
+ callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env));
if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7974933..973ade1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -234,7 +234,7 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b)
return false;
for (int i = 0; i < a->core.cpus->nr; i++) {
- if (a->core.cpus->map[i] != b->core.cpus->map[i])
+ if (a->core.cpus->map[i].cpu != b->core.cpus->map[i].cpu)
return false;
}
@@ -327,34 +327,35 @@ static int write_stat_round_event(u64 tm, u64 type)
#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
-static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
+static int evsel__write_stat_event(struct evsel *counter, int cpu_map_idx, u32 thread,
struct perf_counts_values *count)
{
- struct perf_sample_id *sid = SID(counter, cpu, thread);
+ struct perf_sample_id *sid = SID(counter, cpu_map_idx, thread);
+ struct perf_cpu cpu = perf_cpu_map__cpu(evsel__cpus(counter), cpu_map_idx);
return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
process_synthesized_event, NULL);
}
-static int read_single_counter(struct evsel *counter, int cpu,
+static int read_single_counter(struct evsel *counter, int cpu_map_idx,
int thread, struct timespec *rs)
{
if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
struct perf_counts_values *count =
- perf_counts(counter->counts, cpu, thread);
+ perf_counts(counter->counts, cpu_map_idx, thread);
count->ena = count->run = val;
count->val = val;
return 0;
}
- return evsel__read_counter(counter, cpu, thread);
+ return evsel__read_counter(counter, cpu_map_idx, thread);
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
-static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_map_idx)
{
int nthreads = perf_thread_map__nr(evsel_list->core.threads);
int thread;
@@ -368,24 +369,24 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
for (thread = 0; thread < nthreads; thread++) {
struct perf_counts_values *count;
- count = perf_counts(counter->counts, cpu, thread);
+ count = perf_counts(counter->counts, cpu_map_idx, thread);
/*
* The leader's group read loads data into its group members
* (via evsel__read_counter()) and sets their count->loaded.
*/
- if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
- read_single_counter(counter, cpu, thread, rs)) {
+ if (!perf_counts__is_loaded(counter->counts, cpu_map_idx, thread) &&
+ read_single_counter(counter, cpu_map_idx, thread, rs)) {
counter->counts->scaled = -1;
- perf_counts(counter->counts, cpu, thread)->ena = 0;
- perf_counts(counter->counts, cpu, thread)->run = 0;
+ perf_counts(counter->counts, cpu_map_idx, thread)->ena = 0;
+ perf_counts(counter->counts, cpu_map_idx, thread)->run = 0;
return -1;
}
- perf_counts__set_loaded(counter->counts, cpu, thread, false);
+ perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, false);
if (STAT_RECORD) {
- if (evsel__write_stat_event(counter, cpu, thread, count)) {
+ if (evsel__write_stat_event(counter, cpu_map_idx, thread, count)) {
pr_err("failed to write stat event\n");
return -1;
}
@@ -395,7 +396,8 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
fprintf(stat_config.output,
"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
evsel__name(counter),
- cpu,
+ perf_cpu_map__cpu(evsel__cpus(counter),
+ cpu_map_idx).cpu,
count->val, count->ena, count->run);
}
}
@@ -405,36 +407,33 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
static int read_affinity_counters(struct timespec *rs)
{
- struct evsel *counter;
- struct affinity affinity;
- int i, ncpus, cpu;
+ struct evlist_cpu_iterator evlist_cpu_itr;
+ struct affinity saved_affinity, *affinity;
if (all_counters_use_bpf)
return 0;
- if (affinity__setup(&affinity) < 0)
- return -1;
-
- ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
if (!target__has_cpu(&target) || target__has_per_thread(&target))
- ncpus = 1;
- evlist__for_each_cpu(evsel_list, i, cpu) {
- if (i >= ncpus)
- break;
- affinity__set(&affinity, cpu);
+ affinity = NULL;
+ else if (affinity__setup(&saved_affinity) < 0)
+ return -1;
+ else
+ affinity = &saved_affinity;
- evlist__for_each_entry(evsel_list, counter) {
- if (evsel__cpu_iter_skip(counter, cpu))
- continue;
- if (evsel__is_bpf(counter))
- continue;
- if (!counter->err) {
- counter->err = read_counter_cpu(counter, rs,
- counter->cpu_iter - 1);
- }
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+ struct evsel *counter = evlist_cpu_itr.evsel;
+
+ if (evsel__is_bpf(counter))
+ continue;
+
+ if (!counter->err) {
+ counter->err = read_counter_cpu(counter, rs,
+ evlist_cpu_itr.cpu_map_idx);
}
}
- affinity__cleanup(&affinity);
+ if (affinity)
+ affinity__cleanup(&saved_affinity);
+
return 0;
}
@@ -788,8 +787,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
int status = 0;
const bool forks = (argc > 0);
bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
+ struct evlist_cpu_iterator evlist_cpu_itr;
struct affinity affinity;
- int i, cpu, err;
+ int err;
bool second_pass = false;
if (forks) {
@@ -813,56 +813,53 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
all_counters_use_bpf = false;
}
- evlist__for_each_cpu (evsel_list, i, cpu) {
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+ counter = evlist_cpu_itr.evsel;
+
/*
* bperf calls evsel__open_per_cpu() in bperf__load(), so
* no need to call it again here.
*/
if (target.use_bpf)
break;
- affinity__set(&affinity, cpu);
- evlist__for_each_entry(evsel_list, counter) {
- if (evsel__cpu_iter_skip(counter, cpu))
- continue;
- if (counter->reset_group || counter->errored)
- continue;
- if (evsel__is_bpf(counter))
- continue;
+ if (counter->reset_group || counter->errored)
+ continue;
+ if (evsel__is_bpf(counter))
+ continue;
try_again:
- if (create_perf_stat_counter(counter, &stat_config, &target,
- counter->cpu_iter - 1) < 0) {
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ evlist_cpu_itr.cpu_map_idx) < 0) {
- /*
- * Weak group failed. We cannot just undo this here
- * because earlier CPUs might be in group mode, and the kernel
- * doesn't support mixing group and non group reads. Defer
- * it to later.
- * Don't close here because we're in the wrong affinity.
- */
- if ((errno == EINVAL || errno == EBADF) &&
- evsel__leader(counter) != counter &&
- counter->weak_group) {
- evlist__reset_weak_group(evsel_list, counter, false);
- assert(counter->reset_group);
- second_pass = true;
- continue;
- }
-
- switch (stat_handle_error(counter)) {
- case COUNTER_FATAL:
- return -1;
- case COUNTER_RETRY:
- goto try_again;
- case COUNTER_SKIP:
- continue;
- default:
- break;
- }
-
+ /*
+ * Weak group failed. We cannot just undo this here
+ * because earlier CPUs might be in group mode, and the kernel
+ * doesn't support mixing group and non group reads. Defer
+ * it to later.
+ * Don't close here because we're in the wrong affinity.
+ */
+ if ((errno == EINVAL || errno == EBADF) &&
+ evsel__leader(counter) != counter &&
+ counter->weak_group) {
+ evlist__reset_weak_group(evsel_list, counter, false);
+ assert(counter->reset_group);
+ second_pass = true;
+ continue;
}
- counter->supported = true;
+
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again;
+ case COUNTER_SKIP:
+ continue;
+ default:
+ break;
+ }
+
}
+ counter->supported = true;
}
if (second_pass) {
@@ -871,42 +868,40 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
* and also close errored counters.
*/
- evlist__for_each_cpu(evsel_list, i, cpu) {
- affinity__set(&affinity, cpu);
- /* First close errored or weak retry */
- evlist__for_each_entry(evsel_list, counter) {
- if (!counter->reset_group && !counter->errored)
- continue;
- if (evsel__cpu_iter_skip_no_inc(counter, cpu))
- continue;
- perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
- }
- /* Now reopen weak */
- evlist__for_each_entry(evsel_list, counter) {
- if (!counter->reset_group && !counter->errored)
- continue;
- if (evsel__cpu_iter_skip(counter, cpu))
- continue;
- if (!counter->reset_group)
- continue;
-try_again_reset:
- pr_debug2("reopening weak %s\n", evsel__name(counter));
- if (create_perf_stat_counter(counter, &stat_config, &target,
- counter->cpu_iter - 1) < 0) {
+ /* First close errored or weak retry */
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+ counter = evlist_cpu_itr.evsel;
- switch (stat_handle_error(counter)) {
- case COUNTER_FATAL:
- return -1;
- case COUNTER_RETRY:
- goto try_again_reset;
- case COUNTER_SKIP:
- continue;
- default:
- break;
- }
+ if (!counter->reset_group && !counter->errored)
+ continue;
+
+ perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx);
+ }
+ /* Now reopen weak */
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+ counter = evlist_cpu_itr.evsel;
+
+ if (!counter->reset_group && !counter->errored)
+ continue;
+ if (!counter->reset_group)
+ continue;
+try_again_reset:
+ pr_debug2("reopening weak %s\n", evsel__name(counter));
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ evlist_cpu_itr.cpu_map_idx) < 0) {
+
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again_reset;
+ case COUNTER_SKIP:
+ continue;
+ default:
+ break;
}
- counter->supported = true;
}
+ counter->supported = true;
}
}
affinity__cleanup(&affinity);
@@ -1168,6 +1163,26 @@ static int parse_stat_cgroups(const struct option *opt,
return parse_cgroups(opt, str, unset);
}
+static int parse_hybrid_type(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct evlist *evlist = *(struct evlist **)opt->value;
+
+ if (!list_empty(&evlist->core.entries)) {
+ fprintf(stderr, "Must define cputype before events/metrics\n");
+ return -1;
+ }
+
+ evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str);
+ if (!evlist->hybrid_pmu_name) {
+ fprintf(stderr, "--cputype %s is not supported!\n", str);
+ return -1;
+ }
+
+ return 0;
+}
+
static struct option stat_options[] = {
OPT_BOOLEAN('T', "transaction", &transaction_run,
"hardware transaction statistics"),
@@ -1282,6 +1297,10 @@ static struct option stat_options[] = {
"don't print 'summary' for CSV summary output"),
OPT_BOOLEAN(0, "quiet", &stat_config.quiet,
"don't print output (useful with record)"),
+ OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
+ "Only enable events on applying cpu with this type "
+ "for hybrid platform (e.g. core or atom)",
+ parse_hybrid_type),
#ifdef HAVE_LIBPFM
OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
"libpfm4 event selector. use 'perf list' to list available events",
@@ -1298,70 +1317,75 @@ static struct option stat_options[] = {
OPT_END()
};
+static const char *const aggr_mode__string[] = {
+ [AGGR_CORE] = "core",
+ [AGGR_DIE] = "die",
+ [AGGR_GLOBAL] = "global",
+ [AGGR_NODE] = "node",
+ [AGGR_NONE] = "none",
+ [AGGR_SOCKET] = "socket",
+ [AGGR_THREAD] = "thread",
+ [AGGR_UNSET] = "unset",
+};
+
static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_socket(map, cpu, NULL);
+ return aggr_cpu_id__socket(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_die(map, cpu, NULL);
+ return aggr_cpu_id__die(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_core(map, cpu, NULL);
+ return aggr_cpu_id__core(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_node(map, cpu, NULL);
+ return aggr_cpu_id__node(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
- aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
+ aggr_get_id_t get_id, struct perf_cpu cpu)
{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (idx >= map->nr)
- return id;
+ if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu]))
+ config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu);
- cpu = map->map[idx];
-
- if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu]))
- config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
-
- id = config->cpus_aggr_map->map[cpu];
+ id = config->cpus_aggr_map->map[cpu.cpu];
return id;
}
static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_socket, cpu);
}
static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_die, cpu);
}
static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_core, cpu);
}
static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_node, cpu);
}
static bool term_percore_set(void)
@@ -1376,54 +1400,67 @@ static bool term_percore_set(void)
return false;
}
-static int perf_stat_init_aggr_mode(void)
+static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode)
{
- int nr;
-
- switch (stat_config.aggr_mode) {
+ switch (aggr_mode) {
case AGGR_SOCKET:
- if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build socket map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_socket_cached;
- break;
+ return aggr_cpu_id__socket;
case AGGR_DIE:
- if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build die map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_die_cached;
- break;
+ return aggr_cpu_id__die;
case AGGR_CORE:
- if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_cached;
- break;
+ return aggr_cpu_id__core;
case AGGR_NODE:
- if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_node_cached;
- break;
+ return aggr_cpu_id__node;
case AGGR_NONE:
- if (term_percore_set()) {
- if (cpu_map__build_core_map(evsel_list->core.cpus,
- &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_cached;
- }
- break;
+ if (term_percore_set())
+ return aggr_cpu_id__core;
+
+ return NULL;
case AGGR_GLOBAL:
case AGGR_THREAD:
case AGGR_UNSET:
default:
- break;
+ return NULL;
+ }
+}
+
+static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode)
+{
+ switch (aggr_mode) {
+ case AGGR_SOCKET:
+ return perf_stat__get_socket_cached;
+ case AGGR_DIE:
+ return perf_stat__get_die_cached;
+ case AGGR_CORE:
+ return perf_stat__get_core_cached;
+ case AGGR_NODE:
+ return perf_stat__get_node_cached;
+ case AGGR_NONE:
+ if (term_percore_set()) {
+ return perf_stat__get_core_cached;
+ }
+ return NULL;
+ case AGGR_GLOBAL:
+ case AGGR_THREAD:
+ case AGGR_UNSET:
+ default:
+ return NULL;
+ }
+}
+
+static int perf_stat_init_aggr_mode(void)
+{
+ int nr;
+ aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
+
+ if (get_id) {
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus,
+ get_id, /*data=*/NULL);
+ if (!stat_config.aggr_map) {
+ pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+ return -1;
+ }
+ stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
}
/*
@@ -1431,7 +1468,7 @@ static int perf_stat_init_aggr_mode(void)
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- nr = perf_cpu_map__max(evsel_list->core.cpus);
+ nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
}
@@ -1459,169 +1496,139 @@ static void perf_stat__exit_aggr_mode(void)
stat_config.cpus_aggr_map = NULL;
}
-static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx)
-{
- int cpu;
-
- if (idx > map->nr)
- return -1;
-
- cpu = map->map[idx];
-
- if (cpu >= env->nr_cpus_avail)
- return -1;
-
- return cpu;
-}
-
-static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- int cpu = perf_env__get_cpu(env, map, idx);
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1)
- id.socket = env->cpu[cpu].socket_id;
+ if (cpu.cpu != -1)
+ id.socket = env->cpu[cpu.cpu].socket_id;
return id;
}
-static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
- int cpu = perf_env__get_cpu(env, map, idx);
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1) {
+ if (cpu.cpu != -1) {
/*
* die_id is relative to socket, so start
* with the socket ID and then add die to
* make a unique ID.
*/
- id.socket = env->cpu[cpu].socket_id;
- id.die = env->cpu[cpu].die_id;
+ id.socket = env->cpu[cpu.cpu].socket_id;
+ id.die = env->cpu[cpu.cpu].die_id;
}
return id;
}
-static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
- int cpu = perf_env__get_cpu(env, map, idx);
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1) {
+ if (cpu.cpu != -1) {
/*
* core_id is relative to socket and die,
* we need a global id. So we set
* socket, die id and core id
*/
- id.socket = env->cpu[cpu].socket_id;
- id.die = env->cpu[cpu].die_id;
- id.core = env->cpu[cpu].core_id;
+ id.socket = env->cpu[cpu.cpu].socket_id;
+ id.die = env->cpu[cpu.cpu].die_id;
+ id.core = env->cpu[cpu.cpu].core_id;
}
return id;
}
-static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
- int cpu = perf_env__get_cpu(data, map, idx);
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
id.node = perf_env__numa_node(data, cpu);
return id;
}
-static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **sockp)
-{
- return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
-}
-
-static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **diep)
-{
- return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
-}
-
-static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **corep)
-{
- return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
-}
-
-static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **nodep)
-{
- return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
-}
-
static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_die(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_node(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
-static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode)
{
- struct perf_env *env = &st->session->header.env;
-
- switch (stat_config.aggr_mode) {
+ switch (aggr_mode) {
case AGGR_SOCKET:
- if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build socket map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_socket_file;
- break;
+ return perf_env__get_socket_aggr_by_cpu;
case AGGR_DIE:
- if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build die map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_die_file;
- break;
+ return perf_env__get_die_aggr_by_cpu;
case AGGR_CORE:
- if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_file;
- break;
+ return perf_env__get_core_aggr_by_cpu;
case AGGR_NODE:
- if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_node_file;
- break;
+ return perf_env__get_node_aggr_by_cpu;
case AGGR_NONE:
case AGGR_GLOBAL:
case AGGR_THREAD:
case AGGR_UNSET:
default:
- break;
+ return NULL;
}
+}
+static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode)
+{
+ switch (aggr_mode) {
+ case AGGR_SOCKET:
+ return perf_stat__get_socket_file;
+ case AGGR_DIE:
+ return perf_stat__get_die_file;
+ case AGGR_CORE:
+ return perf_stat__get_core_file;
+ case AGGR_NODE:
+ return perf_stat__get_node_file;
+ case AGGR_NONE:
+ case AGGR_GLOBAL:
+ case AGGR_THREAD:
+ case AGGR_UNSET:
+ default:
+ return NULL;
+ }
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+ struct perf_env *env = &st->session->header.env;
+ aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
+
+ if (!get_id)
+ return 0;
+
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env);
+ if (!stat_config.aggr_map) {
+ pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+ return -1;
+ }
+ stat_config.aggr_get_id = aggr_mode__get_id_file(stat_config.aggr_mode);
return 0;
}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 273237a..32844d8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3964,6 +3964,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
evlist__add(evlist, pgfault_min);
}
+ /* Enable ignoring missing threads when -u/-p option is defined. */
+ trace->opts.ignore_missing_thread = trace->opts.target.uid != UINT_MAX || trace->opts.target.pid;
+
if (trace->sched &&
evlist__add_newtp(evlist, "sched", "sched_stat_runtime", trace__sched_stat_runtime))
goto out_error_sched_stat_runtime;
diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c
index 7565a18..b17eb52 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v0.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c
@@ -308,8 +308,6 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
{
- struct filter_data *d = data;
-
pr_debug("%s API\n", __func__);
return do_checks(data, sample, ctx, false);
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
new file mode 100644
index 0000000..79f2016
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
@@ -0,0 +1,8 @@
+[
+ {
+ "ArchStdEvent": "BR_MIS_PRED"
+ },
+ {
+ "ArchStdEvent": "BR_PRED"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
new file mode 100644
index 0000000..579c1c9
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
@@ -0,0 +1,20 @@
+[
+ {
+ "ArchStdEvent": "CPU_CYCLES"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS"
+ },
+ {
+ "ArchStdEvent": "BUS_CYCLES"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS_RD"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS_WR"
+ },
+ {
+ "ArchStdEvent": "CNT_CYCLES"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
new file mode 100644
index 0000000..0141f74
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
@@ -0,0 +1,155 @@
+[
+ {
+ "ArchStdEvent": "L1I_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1I_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1I_CACHE"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_ALLOCATE"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB"
+ },
+ {
+ "ArchStdEvent": "L1I_TLB"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_ALLOCATE"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB"
+ },
+ {
+ "ArchStdEvent": "DTLB_WALK"
+ },
+ {
+ "ArchStdEvent": "ITLB_WALK"
+ },
+ {
+ "ArchStdEvent": "LL_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "LL_CACHE_MISS_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_LMISS_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_INNER"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_OUTER"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_VICTIM"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_CLEAN"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_INVAL"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_INVAL"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_WR"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L1I_CACHE_LMISS"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_LMISS_RD"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_LMISS_RD"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
new file mode 100644
index 0000000..344a2d5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
@@ -0,0 +1,47 @@
+[
+ {
+ "ArchStdEvent": "EXC_TAKEN"
+ },
+ {
+ "ArchStdEvent": "MEMORY_ERROR"
+ },
+ {
+ "ArchStdEvent": "EXC_UNDEF"
+ },
+ {
+ "ArchStdEvent": "EXC_SVC"
+ },
+ {
+ "ArchStdEvent": "EXC_PABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_DABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_IRQ"
+ },
+ {
+ "ArchStdEvent": "EXC_FIQ"
+ },
+ {
+ "ArchStdEvent": "EXC_SMC"
+ },
+ {
+ "ArchStdEvent": "EXC_HVC"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_PABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_DABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_OTHER"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_IRQ"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_FIQ"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
new file mode 100644
index 0000000..e57cd55
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
@@ -0,0 +1,143 @@
+[
+ {
+ "ArchStdEvent": "SW_INCR"
+ },
+ {
+ "ArchStdEvent": "INST_RETIRED"
+ },
+ {
+ "ArchStdEvent": "EXC_RETURN"
+ },
+ {
+ "ArchStdEvent": "CID_WRITE_RETIRED"
+ },
+ {
+ "ArchStdEvent": "INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "TTBR_WRITE_RETIRED"
+ },
+ {
+ "ArchStdEvent": "BR_RETIRED"
+ },
+ {
+ "ArchStdEvent": "BR_MIS_PRED_RETIRED"
+ },
+ {
+ "ArchStdEvent": "OP_RETIRED"
+ },
+ {
+ "ArchStdEvent": "OP_SPEC"
+ },
+ {
+ "ArchStdEvent": "LDREX_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_PASS_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_FAIL_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_SPEC"
+ },
+ {
+ "ArchStdEvent": "LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "DP_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SPEC"
+ },
+ {
+ "ArchStdEvent": "VFP_SPEC"
+ },
+ {
+ "ArchStdEvent": "PC_WRITE_SPEC"
+ },
+ {
+ "ArchStdEvent": "CRYPTO_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_IMMED_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_RETURN_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_INDIRECT_SPEC"
+ },
+ {
+ "ArchStdEvent": "ISB_SPEC"
+ },
+ {
+ "ArchStdEvent": "DSB_SPEC"
+ },
+ {
+ "ArchStdEvent": "DMB_SPEC"
+ },
+ {
+ "ArchStdEvent": "RC_LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "RC_ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_HP_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_SP_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_DP_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_EMPTY_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_FULL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_LDFF_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_LDFF_FAULT_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_SCALE_OPS_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_FIXED_OPS_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT8_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT16_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT32_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT64_SPEC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
new file mode 100644
index 0000000..e522113
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
@@ -0,0 +1,38 @@
+[
+ {
+ "ArchStdEvent": "MEM_ACCESS"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_RD"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_WR"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LDST_SPEC"
+ },
+ {
+ "ArchStdEvent": "LDST_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "LD_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "ST_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
new file mode 100644
index 0000000..20d8365
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
@@ -0,0 +1,5 @@
+[
+ {
+ "ArchStdEvent": "REMOTE_ACCESS"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
new file mode 100644
index 0000000..f9fae15
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
@@ -0,0 +1,23 @@
+[
+ {
+ "ArchStdEvent": "STALL_FRONTEND"
+ },
+ {
+ "ArchStdEvent": "STALL_BACKEND"
+ },
+ {
+ "ArchStdEvent": "STALL"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT_BACKEND"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT_FRONTEND"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT"
+ },
+ {
+ "ArchStdEvent": "STALL_BACKEND_MEM"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
new file mode 100644
index 0000000..20f2165
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
@@ -0,0 +1,14 @@
+[
+ {
+ "ArchStdEvent": "SAMPLE_POP"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_FEED"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_FILTRATE"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_COLLISION"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
new file mode 100644
index 0000000..3116135
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
@@ -0,0 +1,29 @@
+[
+ {
+ "ArchStdEvent": "TRB_WRAP"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT0"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT1"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT2"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT3"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT4"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT5"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT6"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT7"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
similarity index 76%
rename from tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json
rename to tools/perf/pmu-events/arch/arm64/common-and-microarch.json
index 4237675..80d7a70 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json
+++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
@@ -300,6 +300,30 @@
"BriefDescription": "No operation sent for execution on a slot"
},
{
+ "PublicDescription": "Sample Population",
+ "EventCode": "0x4000",
+ "EventName": "SAMPLE_POP",
+ "BriefDescription": "Sample Population"
+ },
+ {
+ "PublicDescription": "Sample Taken",
+ "EventCode": "0x4001",
+ "EventName": "SAMPLE_FEED",
+ "BriefDescription": "Sample Taken"
+ },
+ {
+ "PublicDescription": "Sample Taken and not removed by filtering",
+ "EventCode": "0x4002",
+ "EventName": "SAMPLE_FILTRATE",
+ "BriefDescription": "Sample Taken and not removed by filtering"
+ },
+ {
+ "PublicDescription": "Sample collided with previous sample",
+ "EventCode": "0x4003",
+ "EventName": "SAMPLE_COLLISION",
+ "BriefDescription": "Sample collided with previous sample"
+ },
+ {
"PublicDescription": "Constant frequency cycles. The counter increments at a constant frequency equal to the rate of increment of the system counter, CNTPCT_EL0.",
"EventCode": "0x4004",
"EventName": "CNT_CYCLES",
@@ -330,6 +354,96 @@
"BriefDescription": "Level 3 data cache long-latency read miss"
},
{
+ "PublicDescription": "Trace buffer current write pointer wrapped",
+ "EventCode": "0x400C",
+ "EventName": "TRB_WRAP",
+ "BriefDescription": "Trace buffer current write pointer wrapped"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 0",
+ "EventCode": "0x4010",
+ "EventName": "TRCEXTOUT0",
+ "BriefDescription": "PE Trace Unit external output 0"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 1",
+ "EventCode": "0x4011",
+ "EventName": "TRCEXTOUT1",
+ "BriefDescription": "PE Trace Unit external output 1"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 2",
+ "EventCode": "0x4012",
+ "EventName": "TRCEXTOUT2",
+ "BriefDescription": "PE Trace Unit external output 2"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 3",
+ "EventCode": "0x4013",
+ "EventName": "TRCEXTOUT3",
+ "BriefDescription": "PE Trace Unit external output 3"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 4",
+ "EventCode": "0x4018",
+ "EventName": "CTI_TRIGOUT4",
+ "BriefDescription": "Cross-trigger Interface output trigger 4"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 5 ",
+ "EventCode": "0x4019",
+ "EventName": "CTI_TRIGOUT5",
+ "BriefDescription": "Cross-trigger Interface output trigger 5 "
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 6",
+ "EventCode": "0x401A",
+ "EventName": "CTI_TRIGOUT6",
+ "BriefDescription": "Cross-trigger Interface output trigger 6"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 7",
+ "EventCode": "0x401B",
+ "EventName": "CTI_TRIGOUT7",
+ "BriefDescription": "Cross-trigger Interface output trigger 7"
+ },
+ {
+ "PublicDescription": "Access with additional latency from alignment",
+ "EventCode": "0x4020",
+ "EventName": "LDST_ALIGN_LAT",
+ "BriefDescription": "Access with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Load with additional latency from alignment",
+ "EventCode": "0x4021",
+ "EventName": "LD_ALIGN_LAT",
+ "BriefDescription": "Load with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Store with additional latency from alignment",
+ "EventCode": "0x4022",
+ "EventName": "ST_ALIGN_LAT",
+ "BriefDescription": "Store with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Checked data memory access",
+ "EventCode": "0x4024",
+ "EventName": "MEM_ACCESS_CHECKED",
+ "BriefDescription": "Checked data memory access"
+ },
+ {
+ "PublicDescription": "Checked data memory access, read",
+ "EventCode": "0x4025",
+ "EventName": "MEM_ACCESS_CHECKED_RD",
+ "BriefDescription": "Checked data memory access, read"
+ },
+ {
+ "PublicDescription": "Checked data memory access, write",
+ "EventCode": "0x4026",
+ "EventName": "MEM_ACCESS_CHECKED_WR",
+ "BriefDescription": "Checked data memory access, write"
+ },
+ {
"PublicDescription": "SIMD Instruction architecturally executed.",
"EventCode": "0x8000",
"EventName": "SIMD_INST_RETIRED",
@@ -342,6 +456,18 @@
"BriefDescription": "Instruction architecturally executed, SVE."
},
{
+ "PublicDescription": "ASE operations speculatively executed",
+ "EventCode": "0x8005",
+ "EventName": "ASE_INST_SPEC",
+ "BriefDescription": "ASE operations speculatively executed"
+ },
+ {
+ "PublicDescription": "SVE operations speculatively executed",
+ "EventCode": "0x8006",
+ "EventName": "SVE_INST_SPEC",
+ "BriefDescription": "SVE operations speculatively executed"
+ },
+ {
"PublicDescription": "Microarchitectural operation, Operations speculatively executed.",
"EventCode": "0x8008",
"EventName": "UOP_SPEC",
@@ -360,6 +486,24 @@
"BriefDescription": "Floating-point Operations speculatively executed."
},
{
+ "PublicDescription": "Floating-point half-precision operations speculatively executed",
+ "EventCode": "0x8014",
+ "EventName": "FP_HP_SPEC",
+ "BriefDescription": "Floating-point half-precision operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Floating-point single-precision operations speculatively executed",
+ "EventCode": "0x8018",
+ "EventName": "FP_SP_SPEC",
+ "BriefDescription": "Floating-point single-precision operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Floating-point double-precision operations speculatively executed",
+ "EventCode": "0x801C",
+ "EventName": "FP_DP_SPEC",
+ "BriefDescription": "Floating-point double-precision operations speculatively executed"
+ },
+ {
"PublicDescription": "Floating-point FMA Operations speculatively executed.",
"EventCode": "0x8028",
"EventName": "FP_FMA_SPEC",
@@ -390,6 +534,30 @@
"BriefDescription": "SVE predicated Operations speculatively executed."
},
{
+ "PublicDescription": "SVE predicated operations with no active predicates speculatively executed",
+ "EventCode": "0x8075",
+ "EventName": "SVE_PRED_EMPTY_SPEC",
+ "BriefDescription": "SVE predicated operations with no active predicates speculatively executed"
+ },
+ {
+ "PublicDescription": "SVE predicated operations speculatively executed with all active predicates",
+ "EventCode": "0x8076",
+ "EventName": "SVE_PRED_FULL_SPEC",
+ "BriefDescription": "SVE predicated operations speculatively executed with all active predicates"
+ },
+ {
+ "PublicDescription": "SVE predicated operations speculatively executed with partially active predicates",
+ "EventCode": "0x8077",
+ "EventName": "SVE_PRED_PARTIAL_SPEC",
+ "BriefDescription": "SVE predicated operations speculatively executed with partially active predicates"
+ },
+ {
+ "PublicDescription": "SVE predicated operations with empty or partially active predicates",
+ "EventCode": "0x8079",
+ "EventName": "SVE_PRED_NOT_FULL_SPEC",
+ "BriefDescription": "SVE predicated operations with empty or partially active predicates"
+ },
+ {
"PublicDescription": "SVE MOVPRFX Operations speculatively executed.",
"EventCode": "0x807C",
"EventName": "SVE_MOVPRFX_SPEC",
@@ -498,6 +666,12 @@
"BriefDescription": "SVE First-fault load Operations speculatively executed."
},
{
+ "PublicDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0",
+ "EventCode": "0x80BD",
+ "EventName": "SVE_LDFF_FAULT_SPEC",
+ "BriefDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0"
+ },
+ {
"PublicDescription": "Scalable floating-point element Operations speculatively executed.",
"EventCode": "0x80C0",
"EventName": "FP_SCALE_OPS_SPEC",
@@ -544,5 +718,29 @@
"EventCode": "0x80C7",
"EventName": "FP_DP_FIXED_OPS_SPEC",
"BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed."
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed",
+ "EventCode": "0x80E3",
+ "EventName": "ASE_SVE_INT8_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed",
+ "EventCode": "0x80E7",
+ "EventName": "ASE_SVE_INT16_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed",
+ "EventCode": "0x80EB",
+ "EventName": "ASE_SVE_INT32_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed",
+ "EventCode": "0x80EF",
+ "EventName": "ASE_SVE_INT64_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed"
}
]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 31d8b57..b899db4 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -19,6 +19,7 @@
0x00000000410fd0b0,v1,arm/cortex-a76-n1,core
0x00000000410fd0c0,v1,arm/cortex-a76-n1,core
0x00000000410fd400,v1,arm/neoverse-v1,core
+0x00000000410fd490,v1,arm/neoverse-n2,core
0x00000000420f5160,v1,cavium/thunderx2,core
0x00000000430f0af0,v1,cavium/thunderx2,core
0x00000000460f0010,v1,fujitsu/a64fx,core
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json
similarity index 96%
rename from tools/perf/pmu-events/arch/arm64/armv8-recommended.json
rename to tools/perf/pmu-events/arch/arm64/recommended.json
index d0a1986..210afa8 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json
+++ b/tools/perf/pmu-events/arch/arm64/recommended.json
@@ -148,305 +148,305 @@
"EventCode": "0x60",
"EventName": "BUS_ACCESS_RD",
"BriefDescription": "Bus access read"
- },
- {
+ },
+ {
"PublicDescription": "Bus access write",
"EventCode": "0x61",
"EventName": "BUS_ACCESS_WR",
"BriefDescription": "Bus access write"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, Normal, Cacheable, Shareable",
"EventCode": "0x62",
"EventName": "BUS_ACCESS_SHARED",
"BriefDescription": "Bus access, Normal, Cacheable, Shareable"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, not Normal, Cacheable, Shareable",
"EventCode": "0x63",
"EventName": "BUS_ACCESS_NOT_SHARED",
"BriefDescription": "Bus access, not Normal, Cacheable, Shareable"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, Normal",
"EventCode": "0x64",
"EventName": "BUS_ACCESS_NORMAL",
"BriefDescription": "Bus access, Normal"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, peripheral",
"EventCode": "0x65",
"EventName": "BUS_ACCESS_PERIPH",
"BriefDescription": "Bus access, peripheral"
- },
- {
+ },
+ {
"PublicDescription": "Data memory access, read",
"EventCode": "0x66",
"EventName": "MEM_ACCESS_RD",
"BriefDescription": "Data memory access, read"
- },
- {
+ },
+ {
"PublicDescription": "Data memory access, write",
"EventCode": "0x67",
"EventName": "MEM_ACCESS_WR",
"BriefDescription": "Data memory access, write"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access, read",
"EventCode": "0x68",
"EventName": "UNALIGNED_LD_SPEC",
"BriefDescription": "Unaligned access, read"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access, write",
"EventCode": "0x69",
"EventName": "UNALIGNED_ST_SPEC",
"BriefDescription": "Unaligned access, write"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access",
"EventCode": "0x6a",
"EventName": "UNALIGNED_LDST_SPEC",
"BriefDescription": "Unaligned access"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX",
"EventCode": "0x6c",
"EventName": "LDREX_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass",
"EventCode": "0x6d",
"EventName": "STREX_PASS_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail",
"EventCode": "0x6e",
"EventName": "STREX_FAIL_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX",
"EventCode": "0x6f",
"EventName": "STREX_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, load",
"EventCode": "0x70",
"EventName": "LD_SPEC",
"BriefDescription": "Operation speculatively executed, load"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, store",
"EventCode": "0x71",
"EventName": "ST_SPEC",
"BriefDescription": "Operation speculatively executed, store"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, load or store",
"EventCode": "0x72",
"EventName": "LDST_SPEC",
"BriefDescription": "Operation speculatively executed, load or store"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, integer data processing",
"EventCode": "0x73",
"EventName": "DP_SPEC",
"BriefDescription": "Operation speculatively executed, integer data processing"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, Advanced SIMD instruction",
"EventCode": "0x74",
"EventName": "ASE_SPEC",
"BriefDescription": "Operation speculatively executed, Advanced SIMD instruction"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, floating-point instruction",
"EventCode": "0x75",
"EventName": "VFP_SPEC",
"BriefDescription": "Operation speculatively executed, floating-point instruction"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, software change of the PC",
"EventCode": "0x76",
"EventName": "PC_WRITE_SPEC",
"BriefDescription": "Operation speculatively executed, software change of the PC"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, Cryptographic instruction",
"EventCode": "0x77",
"EventName": "CRYPTO_SPEC",
"BriefDescription": "Operation speculatively executed, Cryptographic instruction"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, immediate branch",
"EventCode": "0x78",
"EventName": "BR_IMMED_SPEC",
"BriefDescription": "Branch speculatively executed, immediate branch"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, procedure return",
"EventCode": "0x79",
"EventName": "BR_RETURN_SPEC",
"BriefDescription": "Branch speculatively executed, procedure return"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, indirect branch",
"EventCode": "0x7a",
"EventName": "BR_INDIRECT_SPEC",
"BriefDescription": "Branch speculatively executed, indirect branch"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, ISB",
"EventCode": "0x7c",
"EventName": "ISB_SPEC",
"BriefDescription": "Barrier speculatively executed, ISB"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, DSB",
"EventCode": "0x7d",
"EventName": "DSB_SPEC",
"BriefDescription": "Barrier speculatively executed, DSB"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, DMB",
"EventCode": "0x7e",
"EventName": "DMB_SPEC",
"BriefDescription": "Barrier speculatively executed, DMB"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Other synchronous",
"EventCode": "0x81",
"EventName": "EXC_UNDEF",
"BriefDescription": "Exception taken, Other synchronous"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Supervisor Call",
"EventCode": "0x82",
"EventName": "EXC_SVC",
"BriefDescription": "Exception taken, Supervisor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Instruction Abort",
"EventCode": "0x83",
"EventName": "EXC_PABORT",
"BriefDescription": "Exception taken, Instruction Abort"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Data Abort and SError",
"EventCode": "0x84",
"EventName": "EXC_DABORT",
"BriefDescription": "Exception taken, Data Abort and SError"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, IRQ",
"EventCode": "0x86",
"EventName": "EXC_IRQ",
"BriefDescription": "Exception taken, IRQ"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, FIQ",
"EventCode": "0x87",
"EventName": "EXC_FIQ",
"BriefDescription": "Exception taken, FIQ"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Secure Monitor Call",
"EventCode": "0x88",
"EventName": "EXC_SMC",
"BriefDescription": "Exception taken, Secure Monitor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Hypervisor Call",
"EventCode": "0x8a",
"EventName": "EXC_HVC",
"BriefDescription": "Exception taken, Hypervisor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Instruction Abort not taken locally",
"EventCode": "0x8b",
"EventName": "EXC_TRAP_PABORT",
"BriefDescription": "Exception taken, Instruction Abort not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Data Abort or SError not taken locally",
"EventCode": "0x8c",
"EventName": "EXC_TRAP_DABORT",
"BriefDescription": "Exception taken, Data Abort or SError not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Other traps not taken locally",
"EventCode": "0x8d",
"EventName": "EXC_TRAP_OTHER",
"BriefDescription": "Exception taken, Other traps not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, IRQ not taken locally",
"EventCode": "0x8e",
"EventName": "EXC_TRAP_IRQ",
"BriefDescription": "Exception taken, IRQ not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, FIQ not taken locally",
"EventCode": "0x8f",
"EventName": "EXC_TRAP_FIQ",
"BriefDescription": "Exception taken, FIQ not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Release consistency operation speculatively executed, Load-Acquire",
"EventCode": "0x90",
"EventName": "RC_LD_SPEC",
"BriefDescription": "Release consistency operation speculatively executed, Load-Acquire"
- },
- {
+ },
+ {
"PublicDescription": "Release consistency operation speculatively executed, Store-Release",
"EventCode": "0x91",
"EventName": "RC_ST_SPEC",
"BriefDescription": "Release consistency operation speculatively executed, Store-Release"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, read",
"EventCode": "0xa0",
"EventName": "L3D_CACHE_RD",
"BriefDescription": "Attributable Level 3 data or unified cache access, read"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, write",
"EventCode": "0xa1",
"EventName": "L3D_CACHE_WR",
"BriefDescription": "Attributable Level 3 data or unified cache access, write"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache refill, read",
"EventCode": "0xa2",
"EventName": "L3D_CACHE_REFILL_RD",
"BriefDescription": "Attributable Level 3 data or unified cache refill, read"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache refill, write",
"EventCode": "0xa3",
"EventName": "L3D_CACHE_REFILL_WR",
"BriefDescription": "Attributable Level 3 data or unified cache refill, write"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim",
"EventCode": "0xa6",
"EventName": "L3D_CACHE_WB_VICTIM",
"BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean",
"EventCode": "0xa7",
"EventName": "L3D_CACHE_WB_CLEAN",
"BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, invalidate",
"EventCode": "0xa8",
"EventName": "L3D_CACHE_INVAL",
"BriefDescription": "Attributable Level 3 data or unified cache access, invalidate"
- }
+ }
]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 2e7c415..1a57c3f 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -672,8 +672,6 @@ static int json_events(const char *fn,
addfield(map, &je.metric_constraint, "", "", val);
} else if (json_streq(map, field, "MetricExpr")) {
addfield(map, &je.metric_expr, "", "", val);
- for (s = je.metric_expr; *s; s++)
- *s = tolower(*s);
} else if (json_streq(map, field, "ArchStdEvent")) {
addfield(map, &arch_std, "", "", val);
for (s = arch_std; *s; s++)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 803ca42..af2b37e 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -65,6 +65,7 @@
perf-y += expand-cgroup.o
perf-y += perf-time-to-tsc.o
perf-y += dlfilter-test.o
+perf-y += sigtrap.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0f73e30..56fba08 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -65,7 +65,7 @@ do { \
#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
-static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
FILE *file;
@@ -93,7 +93,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
/* syscall arguments */
__WRITE_ASS(fd, "d", fd);
__WRITE_ASS(group_fd, "d", group_fd);
- __WRITE_ASS(cpu, "d", cpu);
+ __WRITE_ASS(cpu, "d", cpu.cpu);
__WRITE_ASS(pid, "d", pid);
__WRITE_ASS(flags, "lu", flags);
@@ -144,7 +144,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
return 0;
}
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
int errno_saved = errno;
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 3848563..0bf399c 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -18,7 +18,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
if (map && bm) {
for (i = 0; i < map->nr; i++)
- set_bit(map->map[i], bm);
+ set_bit(map->map[i].cpu, bm);
}
if (map)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8cb5a1c..fac3717 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -107,6 +107,7 @@ static struct test_suite *generic_tests[] = {
&suite__expand_cgroup_events,
&suite__perf_time_to_tsc,
&suite__dlfilter,
+ &suite__sigtrap,
NULL,
};
@@ -420,7 +421,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
continue;
st.file = ent->d_name;
- pr_info("%2d: %-*s:", i, width, test_suite.desc);
+ pr_info("%3d: %-*s:", i, width, test_suite.desc);
if (intlist__find(skiplist, i)) {
color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -470,7 +471,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
continue;
}
- pr_info("%2d: %-*s:", i, width, test_description(t, -1));
+ pr_info("%3d: %-*s:", i, width, test_description(t, -1));
if (intlist__find(skiplist, i)) {
color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -510,7 +511,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
curr, argc, argv))
continue;
- pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+ pr_info("%3d.%1d: %-*s:", i, subi + 1, subw,
test_description(t, subi));
test_and_print(t, subi);
}
@@ -545,7 +546,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
if (!perf_test__matches(t.desc, curr, argc, argv))
continue;
- pr_info("%2d: %s\n", i, t.desc);
+ pr_info("%3d: %s\n", i, t.desc);
}
@@ -567,14 +568,14 @@ static int perf_test__list(int argc, const char **argv)
if (!perf_test__matches(test_description(t, -1), curr, argc, argv))
continue;
- pr_info("%2d: %s\n", i, test_description(t, -1));
+ pr_info("%3d: %s\n", i, test_description(t, -1));
if (has_subtests(t)) {
int subn = num_subtests(t);
int subi;
for (subi = 0; subi < subn; subi++)
- pr_info("%2d:%1d: %s\n", i, subi + 1,
+ pr_info("%3d:%1d: %s\n", i, subi + 1,
test_description(t, subi));
}
}
@@ -606,6 +607,9 @@ int cmd_test(int argc, const char **argv)
if (ret < 0)
return ret;
+ /* Unbuffered output */
+ setvbuf(stdout, NULL, _IONBF, 0);
+
argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
if (argc >= 1 && !strcmp(argv[0], "list"))
return perf_test__list(argc - 1, argv + 1);
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 89a1550..84e87e3 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -38,7 +38,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
TEST_ASSERT_VAL("wrong nr", map->nr == 20);
for (i = 0; i < 20; i++) {
- TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
+ TEST_ASSERT_VAL("wrong cpu", map->map[i].cpu == i);
}
perf_cpu_map__put(map);
@@ -67,8 +67,8 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
map = cpu_map__new_data(data);
TEST_ASSERT_VAL("wrong nr", map->nr == 2);
- TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
- TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
+ TEST_ASSERT_VAL("wrong cpu", map->map[0].cpu == 1);
+ TEST_ASSERT_VAL("wrong cpu", map->map[1].cpu == 256);
TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
perf_cpu_map__put(map);
return 0;
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index d01532d..16b6d6f 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -76,9 +76,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
- TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
- TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
- TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
+ TEST_ASSERT_VAL("wrong cpus", map->map[0].cpu == 1);
+ TEST_ASSERT_VAL("wrong cpus", map->map[1].cpu == 2);
+ TEST_ASSERT_VAL("wrong cpus", map->map[2].cpu == 3);
perf_cpu_map__put(map);
return 0;
}
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index b17b863..f4a4aba 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -31,7 +31,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
if (map && bm) {
for (i = 0; i < map->nr; i++) {
- set_bit(map->map[i], bm);
+ set_bit(map->map[i].cpu, bm);
}
}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 90b2fed..0ad6291 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -59,11 +59,11 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
}
CPU_ZERO(&cpu_set);
- CPU_SET(cpus->map[0], &cpu_set);
+ CPU_SET(cpus->map[0].cpu, &cpu_set);
sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
+ cpus->map[0].cpu, str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_free_cpus;
}
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index cd3dd46..1ab3623 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -22,7 +22,8 @@
static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused,
int subtest __maybe_unused)
{
- int err = -1, fd, cpu;
+ int err = -1, fd, idx;
+ struct perf_cpu cpu;
struct perf_cpu_map *cpus;
struct evsel *evsel;
unsigned int nr_openat_calls = 111, i;
@@ -58,23 +59,23 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
goto out_evsel_delete;
}
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
- unsigned int ncalls = nr_openat_calls + cpu;
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ unsigned int ncalls = nr_openat_calls + idx;
/*
* XXX eventually lift this restriction in a way that
* keeps perf building on older glibc installations
* without CPU_ALLOC. 1024 cpus in 2010 still seems
* a reasonable upper limit tho :-)
*/
- if (cpus->map[cpu] >= CPU_SETSIZE) {
- pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+ if (cpu.cpu >= CPU_SETSIZE) {
+ pr_debug("Ignoring CPU %d\n", cpu.cpu);
continue;
}
- CPU_SET(cpus->map[cpu], &cpu_set);
+ CPU_SET(cpu.cpu, &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[cpu],
+ cpu.cpu,
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_close_fd;
}
@@ -82,37 +83,29 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
fd = openat(0, "/etc/passwd", O_RDONLY);
close(fd);
}
- CPU_CLR(cpus->map[cpu], &cpu_set);
+ CPU_CLR(cpu.cpu, &cpu_set);
}
- /*
- * Here we need to explicitly preallocate the counts, as if
- * we use the auto allocation it will allocate just for 1 cpu,
- * as we start by cpu 0.
- */
- if (evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
- pr_debug("evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
- goto out_close_fd;
- }
+ evsel->core.cpus = perf_cpu_map__get(cpus);
err = 0;
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
unsigned int expected;
- if (cpus->map[cpu] >= CPU_SETSIZE)
+ if (cpu.cpu >= CPU_SETSIZE)
continue;
- if (evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+ if (evsel__read_on_cpu(evsel, idx, 0) < 0) {
pr_debug("evsel__read_on_cpu\n");
err = -1;
break;
}
- expected = nr_openat_calls + cpu;
- if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
+ expected = nr_openat_calls + idx;
+ if (perf_counts(evsel->counts, idx, 0)->val != expected) {
pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
- expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
+ expected, cpu.cpu, perf_counts(evsel->counts, idx, 0)->val);
err = -1;
}
}
diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
index de24d37..cb35e48 100755
--- a/tools/perf/tests/shell/stat_all_metricgroups.sh
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -6,7 +6,7 @@
for m in $(perf list --raw-dump metricgroups); do
echo "Testing $m"
- perf stat -M "$m" true
+ perf stat -M "$m" -a true
done
exit 0
diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
new file mode 100644
index 0000000..1f147fe
--- /dev/null
+++ b/tools/perf/tests/sigtrap.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic test for sigtrap support.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#include <errno.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/string.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "cloexec.h"
+#include "debug.h"
+#include "event.h"
+#include "tests.h"
+#include "../perf-sys.h"
+
+/*
+ * PowerPC and S390 do not support creation of instruction breakpoints using the
+ * perf_event interface.
+ *
+ * Just disable the test for these architectures until these issues are
+ * resolved.
+ */
+#if defined(__powerpc__) || defined(__s390x__)
+#define BP_ACCOUNT_IS_SUPPORTED 0
+#else
+#define BP_ACCOUNT_IS_SUPPORTED 1
+#endif
+
+#define NUM_THREADS 5
+
+static struct {
+ int tids_want_signal; /* Which threads still want a signal. */
+ int signal_count; /* Sanity check number of signals received. */
+ volatile int iterate_on; /* Variable to set breakpoint on. */
+ siginfo_t first_siginfo; /* First observed siginfo_t. */
+} ctx;
+
+#define TEST_SIG_DATA (~(unsigned long)(&ctx.iterate_on))
+
+static struct perf_event_attr make_event_attr(void)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_BREAKPOINT,
+ .size = sizeof(attr),
+ .sample_period = 1,
+ .disabled = 1,
+ .bp_addr = (unsigned long)&ctx.iterate_on,
+ .bp_type = HW_BREAKPOINT_RW,
+ .bp_len = HW_BREAKPOINT_LEN_1,
+ .inherit = 1, /* Children inherit events ... */
+ .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
+ .remove_on_exec = 1, /* Required by sigtrap. */
+ .sigtrap = 1, /* Request synchronous SIGTRAP on event. */
+ .sig_data = TEST_SIG_DATA,
+ .exclude_kernel = 1, /* To allow */
+ .exclude_hv = 1, /* running as !root */
+ };
+ return attr;
+}
+
+static void
+sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused)
+{
+ if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
+ ctx.first_siginfo = *info;
+ __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED);
+}
+
+static void *test_thread(void *arg)
+{
+ pthread_barrier_t *barrier = (pthread_barrier_t *)arg;
+ pid_t tid = syscall(SYS_gettid);
+ int i;
+
+ pthread_barrier_wait(barrier);
+
+ __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+ for (i = 0; i < ctx.iterate_on - 1; i++)
+ __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+
+ return NULL;
+}
+
+static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier)
+{
+ int i;
+
+ pthread_barrier_wait(barrier);
+ for (i = 0; i < NUM_THREADS; i++)
+ TEST_ASSERT_EQUAL("pthread_join() failed", pthread_join(threads[i], NULL), 0);
+
+ return TEST_OK;
+}
+
+static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier)
+{
+ int ret;
+
+ ctx.iterate_on = 3000;
+
+ TEST_ASSERT_EQUAL("misfired signal?", ctx.signal_count, 0);
+ TEST_ASSERT_EQUAL("enable failed", ioctl(fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+ ret = run_test_threads(threads, barrier);
+ TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0);
+
+ TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+ TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0);
+ TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on);
+#if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */
+ TEST_ASSERT_EQUAL("unexpected si_perf_type", ctx.first_siginfo.si_perf_type,
+ PERF_TYPE_BREAKPOINT);
+ TEST_ASSERT_EQUAL("unexpected si_perf_data", ctx.first_siginfo.si_perf_data,
+ TEST_SIG_DATA);
+#endif
+
+ return ret;
+}
+
+static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+ struct perf_event_attr attr = make_event_attr();
+ struct sigaction action = {};
+ struct sigaction oldact;
+ pthread_t threads[NUM_THREADS];
+ pthread_barrier_t barrier;
+ char sbuf[STRERR_BUFSIZE];
+ int i, fd, ret = TEST_FAIL;
+
+ if (!BP_ACCOUNT_IS_SUPPORTED) {
+ pr_debug("Test not supported on this architecture");
+ return TEST_SKIP;
+ }
+
+ pthread_barrier_init(&barrier, NULL, NUM_THREADS + 1);
+
+ action.sa_flags = SA_SIGINFO | SA_NODEFER;
+ action.sa_sigaction = sigtrap_handler;
+ sigemptyset(&action.sa_mask);
+ if (sigaction(SIGTRAP, &action, &oldact)) {
+ pr_debug("FAILED sigaction(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out;
+ }
+
+ fd = sys_perf_event_open(&attr, 0, -1, -1, perf_event_open_cloexec_flag());
+ if (fd < 0) {
+ pr_debug("FAILED sys_perf_event_open(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out_restore_sigaction;
+ }
+
+ for (i = 0; i < NUM_THREADS; i++) {
+ if (pthread_create(&threads[i], NULL, test_thread, &barrier)) {
+ pr_debug("FAILED pthread_create(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out_close_perf_event;
+ }
+ }
+
+ ret = run_stress_test(fd, threads, &barrier);
+
+out_close_perf_event:
+ close(fd);
+out_restore_sigaction:
+ sigaction(SIGTRAP, &oldact, NULL);
+out:
+ pthread_barrier_destroy(&barrier);
+ return ret;
+}
+
+DEFINE_SUITE("Sigtrap", sigtrap);
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 2eb096b..5009740 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -87,7 +87,8 @@ static int test__synthesize_stat(struct test_suite *test __maybe_unused, int sub
count.run = 300;
TEST_ASSERT_VAL("failed to synthesize stat_config",
- !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
+ !perf_event__synthesize_stat(NULL, (struct perf_cpu){.cpu = 1}, 2, 3,
+ &count, process_stat_event, NULL));
return 0;
}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8f65098..5bbb8f6 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -146,6 +146,7 @@ DECLARE_SUITE(pe_file_parsing);
DECLARE_SUITE(expand_cgroup_events);
DECLARE_SUITE(perf_time_to_tsc);
DECLARE_SUITE(dlfilter);
+DECLARE_SUITE(sigtrap);
/*
* PowerPC and S390 do not support creation of instruction breakpoints using the
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 8699861..c4ef0c7 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -112,62 +112,83 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
- if (!cpu_map__has(map, i))
+ struct perf_cpu cpu = { .cpu = i };
+
+ if (!perf_cpu_map__has(map, cpu))
continue;
pr_debug("CPU %d, core %d, socket %d\n", i,
session->header.env.cpu[i].core_id,
session->header.env.cpu[i].socket_id);
}
+ // Test that CPU ID contains socket, die, core and CPU
+ for (i = 0; i < map->nr; i++) {
+ id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL);
+ TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match", map->map[i].cpu == id.cpu.cpu);
+
+ TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
+ session->header.env.cpu[map->map[i].cpu].core_id == id.core);
+ TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
+ session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
+
+ TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
+ session->header.env.cpu[map->map[i].cpu].die_id == id.die);
+ TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
+ TEST_ASSERT_VAL("Cpu map - Thread is set", id.thread == -1);
+ }
+
// Test that core ID contains socket, die and core
for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_core(map, i, NULL);
+ id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Core map - Core ID doesn't match",
- session->header.env.cpu[map->map[i]].core_id == id.core);
+ session->header.env.cpu[map->map[i].cpu].core_id == id.core);
TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
TEST_ASSERT_VAL("Core map - Die ID doesn't match",
- session->header.env.cpu[map->map[i]].die_id == id.die);
+ session->header.env.cpu[map->map[i].cpu].die_id == id.die);
TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1);
}
// Test that die ID contains socket and die
for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_die(map, i, NULL);
+ id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
TEST_ASSERT_VAL("Die map - Die ID doesn't match",
- session->header.env.cpu[map->map[i]].die_id == id.die);
+ session->header.env.cpu[map->map[i].cpu].die_id == id.die);
TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1);
}
// Test that socket ID contains only socket
for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_socket(map, i, NULL);
+ id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1);
}
// Test that node ID contains only node
for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_node(map, i, NULL);
+ id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Node map - Node ID doesn't match",
cpu__get_node(map->map[i]) == id.node);
TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1);
}
perf_session__delete(session);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e81c249..44ba900 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -966,6 +966,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
.opts = opts,
};
int ret = -1, err;
+ int not_annotated = list_empty(¬es->src->source);
if (sym == NULL)
return -1;
@@ -973,13 +974,15 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
if (ms->map->dso->annotate_warned)
return -1;
- err = symbol__annotate2(ms, evsel, opts, &browser.arch);
- if (err) {
- char msg[BUFSIZ];
- ms->map->dso->annotate_warned = true;
- symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
- ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
- goto out_free_offsets;
+ if (not_annotated) {
+ err = symbol__annotate2(ms, evsel, opts, &browser.arch);
+ if (err) {
+ char msg[BUFSIZ];
+ ms->map->dso->annotate_warned = true;
+ symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
+ ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
+ goto out_free_offsets;
+ }
}
ui_helpline__push("Press ESC to exit");
@@ -994,9 +997,11 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
ret = annotate_browser__run(&browser, evsel, hbt);
- annotated_source__purge(notes->src);
+ if(not_annotated)
+ annotated_source__purge(notes->src);
out_free_offsets:
- zfree(¬es->offsets);
+ if(not_annotated)
+ zfree(¬es->offsets);
return ret;
}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2e5bfbb..2a403ce 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,4 @@
+perf-y += arm64-frame-pointer-unwind-support.o
perf-y += annotate.o
perf-y += block-info.o
perf-y += block-range.o
@@ -144,6 +145,7 @@
perf-$(CONFIG_LIBBPF) += bpf_map.o
perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
perf-$(CONFIG_LIBELF) += symbol-elf.o
perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index 7b12bd7..f1e30d5 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -11,7 +11,7 @@
static int get_cpu_set_size(void)
{
- int sz = cpu__max_cpu() + 8 - 1;
+ int sz = cpu__max_cpu().cpu + 8 - 1;
/*
* sched_getaffinity doesn't like masks smaller than the kernel.
* Hopefully that's big enough.
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 3fc528c..5e390a1 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
decoder->record.phys_addr = ip;
break;
case ARM_SPE_COUNTER:
+ if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+ decoder->record.latency = payload;
break;
case ARM_SPE_CONTEXT:
decoder->record.context_id = payload;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 46a8556..69b3108 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -33,6 +33,7 @@ struct arm_spe_record {
enum arm_spe_sample_type type;
int err;
u32 op;
+ u32 latency;
u64 from_ip;
u64 to_ip;
u64 timestamp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index fccac06..d2b64e3 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -58,6 +58,8 @@ struct arm_spe {
u8 sample_branch;
u8 sample_remote_access;
u8 sample_memory;
+ u8 sample_instructions;
+ u64 instructions_sample_period;
u64 l1d_miss_id;
u64 l1d_access_id;
@@ -68,6 +70,7 @@ struct arm_spe {
u64 branch_miss_id;
u64 remote_access_id;
u64 memory_id;
+ u64 instructions_id;
u64 kernel_start;
@@ -90,6 +93,7 @@ struct arm_spe_queue {
u64 time;
u64 timestamp;
struct thread *thread;
+ u64 period_instructions;
};
static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
@@ -202,6 +206,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe,
speq->pid = -1;
speq->tid = -1;
speq->cpu = -1;
+ speq->period_instructions = 0;
/* params set */
params.get_trace = arm_spe_get_trace;
@@ -330,6 +335,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
sample.addr = record->virt_addr;
sample.phys_addr = record->phys_addr;
sample.data_src = data_src;
+ sample.weight = record->latency;
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -347,6 +353,36 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
sample.id = spe_events_id;
sample.stream_id = spe_events_id;
sample.addr = record->to_ip;
+ sample.weight = record->latency;
+
+ return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+}
+
+static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
+ u64 spe_events_id, u64 data_src)
+{
+ struct arm_spe *spe = speq->spe;
+ struct arm_spe_record *record = &speq->decoder->record;
+ union perf_event *event = speq->event_buf;
+ struct perf_sample sample = { .ip = 0, };
+
+ /*
+ * Handles perf instruction sampling period.
+ */
+ speq->period_instructions++;
+ if (speq->period_instructions < spe->instructions_sample_period)
+ return 0;
+ speq->period_instructions = 0;
+
+ arm_spe_prep_sample(spe, speq, event, &sample);
+
+ sample.id = spe_events_id;
+ sample.stream_id = spe_events_id;
+ sample.addr = record->virt_addr;
+ sample.phys_addr = record->phys_addr;
+ sample.data_src = data_src;
+ sample.period = spe->instructions_sample_period;
+ sample.weight = record->latency;
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -480,6 +516,12 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
return err;
}
+ if (spe->sample_instructions) {
+ err = arm_spe__synth_instruction_sample(speq, spe->instructions_id, data_src);
+ if (err)
+ return err;
+ }
+
return 0;
}
@@ -993,7 +1035,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
attr.type = PERF_TYPE_HARDWARE;
attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
- PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
+ PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_WEIGHT;
if (spe->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
@@ -1107,8 +1150,30 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
return err;
spe->memory_id = id;
arm_spe_set_event_name(evlist, id, "memory");
+ id += 1;
}
+ if (spe->synth_opts.instructions) {
+ if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) {
+ pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n");
+ goto synth_instructions_out;
+ }
+ if (spe->synth_opts.period > 1)
+ pr_warning("Arm SPE has a hardware-based sample period.\n"
+ "Additional instruction events will be discarded by --itrace\n");
+
+ spe->sample_instructions = true;
+ attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+ attr.sample_period = spe->synth_opts.period;
+ spe->instructions_sample_period = attr.sample_period;
+ err = arm_spe_synth_event(session, &attr, id);
+ if (err)
+ return err;
+ spe->instructions_id = id;
+ arm_spe_set_event_name(evlist, id, "instructions");
+ }
+synth_instructions_out:
+
return 0;
}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
new file mode 100644
index 0000000..2242a88
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arm64-frame-pointer-unwind-support.h"
+#include "callchain.h"
+#include "event.h"
+#include "perf_regs.h" // SMPL_REG_MASK
+#include "unwind.h"
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+struct entries {
+ u64 stack[2];
+ size_t length;
+};
+
+static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
+{
+ return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
+ && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
+}
+
+static int add_entry(struct unwind_entry *entry, void *arg)
+{
+ struct entries *entries = arg;
+
+ entries->stack[entries->length++] = entry->ip;
+ return 0;
+}
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx)
+{
+ int ret;
+ struct entries entries = {};
+ struct regs_dump old_regs = sample->user_regs;
+
+ if (!get_leaf_frame_caller_enabled(sample))
+ return 0;
+
+ /*
+ * If PC and SP are not recorded, get the value of PC from the stack
+ * and set its mask. SP is not used when doing the unwinding but it
+ * still needs to be set to prevent failures.
+ */
+
+ if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
+ sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
+ sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
+ }
+
+ if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
+ sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
+ sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
+ }
+
+ ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+ sample->user_regs = old_regs;
+
+ if (ret || entries.length != 2)
+ return ret;
+
+ return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1];
+}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
new file mode 100644
index 0000000..32af9ce
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+
+#include "event.h"
+#include "thread.h"
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
+
+#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c679394..5632efc 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -123,7 +123,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
mm->prev = 0;
mm->idx = mp->idx;
mm->tid = mp->tid;
- mm->cpu = mp->cpu;
+ mm->cpu = mp->cpu.cpu;
if (!mp->len) {
mm->base = NULL;
@@ -180,7 +180,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
else
mp->tid = -1;
} else {
- mp->cpu = -1;
+ mp->cpu.cpu = -1;
mp->tid = perf_thread_map__pid(evlist->core.threads, idx);
}
}
@@ -292,7 +292,7 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
if (!queue->set) {
queue->set = true;
queue->tid = buffer->tid;
- queue->cpu = buffer->cpu;
+ queue->cpu = buffer->cpu.cpu;
}
buffer->buffer_nr = queues->next_buffer_nr++;
@@ -339,11 +339,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
return 0;
}
-static bool filter_cpu(struct perf_session *session, int cpu)
+static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu)
{
unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
- return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+ return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap);
}
static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
@@ -399,7 +399,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
struct auxtrace_buffer buffer = {
.pid = -1,
.tid = event->auxtrace.tid,
- .cpu = event->auxtrace.cpu,
+ .cpu = { event->auxtrace.cpu },
.data_offset = data_offset,
.offset = event->auxtrace.offset,
.reference = event->auxtrace.reference,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bbf0d78..19910b9 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -15,6 +15,7 @@
#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
+#include <internal/cpumap.h>
#include <asm/bitsperlong.h>
#include <asm/barrier.h>
@@ -240,7 +241,7 @@ struct auxtrace_buffer {
size_t size;
pid_t pid;
pid_t tid;
- int cpu;
+ struct perf_cpu cpu;
void *data;
off_t data_offset;
void *mmap_addr;
@@ -350,7 +351,7 @@ struct auxtrace_mmap_params {
int prot;
int idx;
pid_t tid;
- int cpu;
+ struct perf_cpu cpu;
};
/**
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 528aeb0..7ecfaac 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -424,7 +424,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
size_t prologue_cnt = 0;
int i, err;
- if (IS_ERR(priv) || !priv || priv->is_tp)
+ if (IS_ERR_OR_NULL(priv) || priv->is_tp)
goto errout;
pev = &priv->pev;
@@ -573,7 +573,7 @@ static int hook_load_preprocessor(struct bpf_program *prog)
bool need_prologue = false;
int err, i;
- if (IS_ERR(priv) || !priv) {
+ if (IS_ERR_OR_NULL(priv)) {
pr_debug("Internal error when hook preprocessor\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
@@ -645,8 +645,11 @@ int bpf__probe(struct bpf_object *obj)
goto out;
priv = bpf_program__priv(prog);
- if (IS_ERR(priv) || !priv) {
- err = PTR_ERR(priv);
+ if (IS_ERR_OR_NULL(priv)) {
+ if (!priv)
+ err = -BPF_LOADER_ERRNO__INTERNAL;
+ else
+ err = PTR_ERR(priv);
goto out;
}
@@ -696,7 +699,7 @@ int bpf__unprobe(struct bpf_object *obj)
struct bpf_prog_priv *priv = bpf_program__priv(prog);
int i;
- if (IS_ERR(priv) || !priv || priv->is_tp)
+ if (IS_ERR_OR_NULL(priv) || priv->is_tp)
continue;
for (i = 0; i < priv->pev.ntevs; i++) {
@@ -754,7 +757,7 @@ int bpf__foreach_event(struct bpf_object *obj,
struct perf_probe_event *pev;
int i, fd;
- if (IS_ERR(priv) || !priv) {
+ if (IS_ERR_OR_NULL(priv)) {
pr_debug("bpf: failed to get private field\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 5a97fd7..3ce8d03 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel)
return 0;
}
-static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
+static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx,
int fd)
{
struct bpf_prog_profiler_bpf *skel;
@@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
assert(skel != NULL);
ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events),
- &cpu, &fd, BPF_ANY);
+ &cpu_map_idx, &fd, BPF_ANY);
if (ret)
return ret;
}
@@ -554,7 +554,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
filter_type == BPERF_FILTER_TGID)
key = evsel->core.threads->map[i].pid;
else if (filter_type == BPERF_FILTER_CPU)
- key = evsel->core.cpus->map[i];
+ key = evsel->core.cpus->map[i].cpu;
else
break;
@@ -580,12 +580,12 @@ static int bperf__load(struct evsel *evsel, struct target *target)
return err;
}
-static int bperf__install_pe(struct evsel *evsel, int cpu, int fd)
+static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
{
struct bperf_leader_bpf *skel = evsel->leader_skel;
return bpf_map_update_elem(bpf_map__fd(skel->maps.events),
- &cpu, &fd, BPF_ANY);
+ &cpu_map_idx, &fd, BPF_ANY);
}
/*
@@ -598,7 +598,7 @@ static int bperf_sync_counters(struct evsel *evsel)
num_cpu = all_cpu_map->nr;
for (i = 0; i < num_cpu; i++) {
- cpu = all_cpu_map->map[i];
+ cpu = all_cpu_map->map[i].cpu;
bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu);
}
return 0;
@@ -619,15 +619,17 @@ static int bperf__disable(struct evsel *evsel)
static int bperf__read(struct evsel *evsel)
{
struct bperf_follower_bpf *skel = evsel->follower_skel;
- __u32 num_cpu_bpf = cpu__max_cpu();
+ __u32 num_cpu_bpf = cpu__max_cpu().cpu;
struct bpf_perf_event_value values[num_cpu_bpf];
int reading_map_fd, err = 0;
- __u32 i, j, num_cpu;
+ __u32 i;
+ int j;
bperf_sync_counters(evsel);
reading_map_fd = bpf_map__fd(skel->maps.accum_readings);
for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) {
+ struct perf_cpu entry;
__u32 cpu;
err = bpf_map_lookup_elem(reading_map_fd, &i, values);
@@ -637,16 +639,15 @@ static int bperf__read(struct evsel *evsel)
case BPERF_FILTER_GLOBAL:
assert(i == 0);
- num_cpu = all_cpu_map->nr;
- for (j = 0; j < num_cpu; j++) {
- cpu = all_cpu_map->map[j];
+ perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) {
+ cpu = entry.cpu;
perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter;
perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled;
perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running;
}
break;
case BPERF_FILTER_CPU:
- cpu = evsel->core.cpus->map[i];
+ cpu = evsel->core.cpus->map[i].cpu;
perf_counts(evsel->counts, i, 0)->val = values[cpu].counter;
perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled;
perf_counts(evsel->counts, i, 0)->run = values[cpu].running;
@@ -771,11 +772,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel)
evsel->follower_skel == NULL;
}
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd)
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
{
if (bpf_counter_skip(evsel))
return 0;
- return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd);
+ return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd);
}
int bpf_counter__load(struct evsel *evsel, struct target *target)
diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h
index 65ebaa6..4dbf264 100644
--- a/tools/perf/util/bpf_counter.h
+++ b/tools/perf/util/bpf_counter.h
@@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel);
typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel,
struct target *target);
typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel,
- int cpu,
+ int cpu_map_idx,
int fd);
struct bpf_counter_ops {
@@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel);
int bpf_counter__disable(struct evsel *evsel);
int bpf_counter__read(struct evsel *evsel);
void bpf_counter__destroy(struct evsel *evsel);
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd);
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd);
#else /* HAVE_BPF_SKEL */
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index cbc6c2bc..631e34a 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist)
struct cgroup *cgrp, *leader_cgrp;
__u32 i, cpu;
__u32 nr_cpus = evlist->core.all_cpus->nr;
- int total_cpus = cpu__max_cpu();
+ int total_cpus = cpu__max_cpu().cpu;
int map_size, map_fd;
int prog_fd, err;
@@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist)
for (cpu = 0; cpu < nr_cpus; cpu++) {
int fd = FD(evsel, cpu);
__u32 idx = evsel->core.idx * total_cpus +
- evlist->core.all_cpus->map[cpu];
+ evlist->core.all_cpus->map[cpu].cpu;
err = bpf_map_update_elem(map_fd, &idx, &fd,
BPF_ANY);
@@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist)
int prog_fd = bpf_program__fd(skel->progs.trigger_read);
for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i];
+ cpu = evlist->core.all_cpus->map[i].cpu;
bperf_trigger_reading(prog_fd, cpu);
}
@@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
{
struct evlist *evlist = evsel->evlist;
int i, cpu, nr_cpus = evlist->core.all_cpus->nr;
- int total_cpus = cpu__max_cpu();
+ int total_cpus = cpu__max_cpu().cpu;
struct perf_counts_values *counts;
struct bpf_perf_event_value *values;
int reading_map_fd, err = 0;
@@ -272,7 +272,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
}
for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i];
+ cpu = evlist->core.all_cpus->map[i].cpu;
counts = perf_counts(evsel->counts, i, 0);
counts->val = values[cpu].counter;
diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c
new file mode 100644
index 0000000..d756cc6
--- /dev/null
+++ b/tools/perf/util/bpf_ftrace.c
@@ -0,0 +1,152 @@
+#include <stdio.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include <linux/err.h>
+
+#include "util/ftrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/bpf_counter.h"
+
+#include "util/bpf_skel/func_latency.skel.h"
+
+static struct func_latency_bpf *skel;
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
+{
+ int fd, err;
+ int i, ncpus = 1, ntasks = 1;
+ struct filter_entry *func;
+
+ if (!list_is_singular(&ftrace->filters)) {
+ pr_err("ERROR: %s target function(s).\n",
+ list_empty(&ftrace->filters) ? "No" : "Too many");
+ return -1;
+ }
+
+ func = list_first_entry(&ftrace->filters, struct filter_entry, list);
+
+ skel = func_latency_bpf__open();
+ if (!skel) {
+ pr_err("Failed to open func latency skeleton\n");
+ return -1;
+ }
+
+ /* don't need to set cpu filter for system-wide mode */
+ if (ftrace->target.cpu_list) {
+ ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus);
+ bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+ }
+
+ if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
+ ntasks = perf_thread_map__nr(ftrace->evlist->core.threads);
+ bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+ }
+
+ set_max_rlimit();
+
+ err = func_latency_bpf__load(skel);
+ if (err) {
+ pr_err("Failed to load func latency skeleton\n");
+ goto out;
+ }
+
+ if (ftrace->target.cpu_list) {
+ u32 cpu;
+ u8 val = 1;
+
+ skel->bss->has_cpu = 1;
+ fd = bpf_map__fd(skel->maps.cpu_filter);
+
+ for (i = 0; i < ncpus; i++) {
+ cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu;
+ bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+ }
+ }
+
+ if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
+ u32 pid;
+ u8 val = 1;
+
+ skel->bss->has_task = 1;
+ fd = bpf_map__fd(skel->maps.task_filter);
+
+ for (i = 0; i < ntasks; i++) {
+ pid = perf_thread_map__pid(ftrace->evlist->core.threads, i);
+ bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+ }
+ }
+
+ skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin,
+ false, func->name);
+ if (IS_ERR(skel->links.func_begin)) {
+ pr_err("Failed to attach fentry program\n");
+ err = PTR_ERR(skel->links.func_begin);
+ goto out;
+ }
+
+ skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end,
+ true, func->name);
+ if (IS_ERR(skel->links.func_end)) {
+ pr_err("Failed to attach fexit program\n");
+ err = PTR_ERR(skel->links.func_end);
+ goto out;
+ }
+
+ /* XXX: we don't actually use this fd - just for poll() */
+ return open("/dev/null", O_RDONLY);
+
+out:
+ return err;
+}
+
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ skel->bss->enabled = 1;
+ return 0;
+}
+
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ skel->bss->enabled = 0;
+ return 0;
+}
+
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+ int buckets[])
+{
+ int i, fd, err;
+ u32 idx;
+ u64 *hist;
+ int ncpus = cpu__max_cpu().cpu;
+
+ fd = bpf_map__fd(skel->maps.latency);
+
+ hist = calloc(ncpus, sizeof(*hist));
+ if (hist == NULL)
+ return -ENOMEM;
+
+ for (idx = 0; idx < NUM_BUCKET; idx++) {
+ err = bpf_map_lookup_elem(fd, &idx, hist);
+ if (err) {
+ buckets[idx] = 0;
+ continue;
+ }
+
+ for (i = 0; i < ncpus; i++)
+ buckets[idx] += hist[i];
+ }
+
+ free(hist);
+ return 0;
+}
+
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ func_latency_bpf__destroy(skel);
+ return 0;
+}
diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
new file mode 100644
index 0000000..ea94187fe
--- /dev/null
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2021 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+// This should be in sync with "util/ftrace.h"
+#define NUM_BUCKET 22
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u64));
+ __uint(value_size, sizeof(__u64));
+ __uint(max_entries, 10000);
+} functime SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u8));
+ __uint(max_entries, 1);
+} cpu_filter SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u8));
+ __uint(max_entries, 1);
+} task_filter SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u64));
+ __uint(max_entries, NUM_BUCKET);
+} latency SEC(".maps");
+
+
+int enabled = 0;
+int has_cpu = 0;
+int has_task = 0;
+
+SEC("kprobe/func")
+int BPF_PROG(func_begin)
+{
+ __u64 key, now;
+
+ if (!enabled)
+ return 0;
+
+ key = bpf_get_current_pid_tgid();
+
+ if (has_cpu) {
+ __u32 cpu = bpf_get_smp_processor_id();
+ __u8 *ok;
+
+ ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
+ if (!ok)
+ return 0;
+ }
+
+ if (has_task) {
+ __u32 pid = key & 0xffffffff;
+ __u8 *ok;
+
+ ok = bpf_map_lookup_elem(&task_filter, &pid);
+ if (!ok)
+ return 0;
+ }
+
+ now = bpf_ktime_get_ns();
+
+ // overwrite timestamp for nested functions
+ bpf_map_update_elem(&functime, &key, &now, BPF_ANY);
+ return 0;
+}
+
+SEC("kretprobe/func")
+int BPF_PROG(func_end)
+{
+ __u64 tid;
+ __u64 *start;
+
+ if (!enabled)
+ return 0;
+
+ tid = bpf_get_current_pid_tgid();
+
+ start = bpf_map_lookup_elem(&functime, &tid);
+ if (start) {
+ __s64 delta = bpf_ktime_get_ns() - *start;
+ __u32 key;
+ __u64 *hist;
+
+ bpf_map_delete_elem(&functime, &tid);
+
+ if (delta < 0)
+ return 0;
+
+ // calculate index using delta in usec
+ for (key = 0; key < (NUM_BUCKET - 1); key++) {
+ if (delta < ((1000UL) << key))
+ break;
+ }
+
+ hist = bpf_map_lookup_elem(&latency, &key);
+ if (!hist)
+ return 0;
+
+ *hist += 1;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8e27771..131207b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor)
map__zput(node->ms.map);
}
-void callchain_param_setup(u64 sample_type)
+void callchain_param_setup(u64 sample_type, const char *arch)
{
if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
if ((sample_type & PERF_SAMPLE_REGS_USER) &&
@@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type)
else
callchain_param.record_mode = CALLCHAIN_FP;
}
+
+ /*
+ * It's necessary to use libunwind to reliably determine the caller of
+ * a leaf function on aarch64, as otherwise we cannot know whether to
+ * start from the LR or FP.
+ *
+ * Always starting from the LR can result in duplicate or entirely
+ * erroneous entries. Always skipping the LR and starting from the FP
+ * can result in missing entries.
+ */
+ if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64"))
+ dwarf_callchain_users = true;
}
static bool chain_match(struct callchain_list *base_chain,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 5824134..d95615d 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
}
#endif
+void arch__add_leaf_frame_record_opts(struct record_opts *opts);
+
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso);
char *callchain_node__scnprintf_value(struct callchain_node *node,
@@ -298,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root,
u64 *branch_count, u64 *predicted_count,
u64 *abort_count, u64 *cycles_count);
-void callchain_param_setup(u64 sample_type);
+void callchain_param_setup(u64 sample_type, const char *arch);
bool callchain_cnode_matched(struct callchain_node *base_cnode,
struct callchain_node *pair_cnode);
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 582f3ae..2b81707 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -4,6 +4,7 @@
#include <string.h>
#include "evsel.h"
#include "counts.h"
+#include <perf/threadmap.h>
#include <linux/zalloc.h>
struct perf_counts *perf_counts__new(int ncpus, int nthreads)
@@ -55,9 +56,12 @@ void evsel__reset_counts(struct evsel *evsel)
perf_counts__reset(evsel->counts);
}
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads)
+int evsel__alloc_counts(struct evsel *evsel)
{
- evsel->counts = perf_counts__new(ncpus, nthreads);
+ struct perf_cpu_map *cpus = evsel__cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
+
+ evsel->counts = perf_counts__new(cpus ? cpus->nr : 1, nthreads);
return evsel->counts != NULL ? 0 : -ENOMEM;
}
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 7ff36bf..5de2751 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -18,21 +18,21 @@ struct perf_counts {
static inline struct perf_counts_values*
-perf_counts(struct perf_counts *counts, int cpu, int thread)
+perf_counts(struct perf_counts *counts, int cpu_map_idx, int thread)
{
- return xyarray__entry(counts->values, cpu, thread);
+ return xyarray__entry(counts->values, cpu_map_idx, thread);
}
static inline bool
-perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread)
+perf_counts__is_loaded(struct perf_counts *counts, int cpu_map_idx, int thread)
{
- return *((bool *) xyarray__entry(counts->loaded, cpu, thread));
+ return *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread));
}
static inline void
-perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded)
+perf_counts__set_loaded(struct perf_counts *counts, int cpu_map_idx, int thread, bool loaded)
{
- *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded;
+ *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)) = loaded;
}
struct perf_counts *perf_counts__new(int ncpus, int nthreads);
@@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts);
void perf_counts__reset(struct perf_counts *counts);
void evsel__reset_counts(struct evsel *evsel);
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
+int evsel__alloc_counts(struct evsel *evsel);
void evsel__free_counts(struct evsel *evsel);
#endif /* __PERF_COUNTS_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 87d3eca..12b2243 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -13,9 +13,13 @@
#include <linux/ctype.h>
#include <linux/zalloc.h>
-static int max_cpu_num;
-static int max_present_cpu_num;
+static struct perf_cpu max_cpu_num;
+static struct perf_cpu max_present_cpu_num;
static int max_node_num;
+/**
+ * The numa node X as read from /sys/devices/system/node/nodeX indexed by the
+ * CPU number.
+ */
static int *cpunode_map;
static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
@@ -33,9 +37,9 @@ static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
* otherwise it would become 65535.
*/
if (cpus->cpu[i] == (u16) -1)
- map->map[i] = -1;
+ map->map[i].cpu = -1;
else
- map->map[i] = (int) cpus->cpu[i];
+ map->map[i].cpu = (int) cpus->cpu[i];
}
}
@@ -54,7 +58,7 @@ static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map
int cpu, i = 0;
for_each_set_bit(cpu, mask->mask, nbits)
- map->map[i++] = cpu;
+ map->map[i++].cpu = cpu;
}
return map;
@@ -87,7 +91,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
cpus->nr = nr;
for (i = 0; i < nr; i++)
- cpus->map[i] = -1;
+ cpus->map[i].cpu = -1;
refcount_set(&cpus->refcnt, 1);
}
@@ -104,7 +108,7 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
cpus->nr = nr;
for (i = 0; i < nr; i++)
- cpus->map[i] = cpu_map__empty_aggr_cpu_id();
+ cpus->map[i] = aggr_cpu_id__empty();
refcount_set(&cpus->refcnt, 1);
}
@@ -122,28 +126,21 @@ static int cpu__get_topology_int(int cpu, const char *name, int *value)
return sysfs__read_int(path, value);
}
-int cpu_map__get_socket_id(int cpu)
+int cpu__get_socket_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "physical_package_id", &value);
return ret ?: value;
}
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx,
- void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data __maybe_unused)
{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (idx > map->nr)
- return id;
-
- cpu = map->map[idx];
-
- id.socket = cpu_map__get_socket_id(cpu);
+ id.socket = cpu__get_socket_id(cpu);
return id;
}
-static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
+static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer)
{
struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer;
struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer;
@@ -160,57 +157,64 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
return a->thread - b->thread;
}
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
- struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
- void *data)
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+ aggr_cpu_id_get_t get_id,
+ void *data)
{
- int nr = cpus->nr;
- struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr);
- int cpu, s2;
- struct aggr_cpu_id s1;
+ int idx;
+ struct perf_cpu cpu;
+ struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr);
if (!c)
- return -1;
+ return NULL;
/* Reset size as it may only be partially filled */
c->nr = 0;
- for (cpu = 0; cpu < nr; cpu++) {
- s1 = f(cpus, cpu, data);
- for (s2 = 0; s2 < c->nr; s2++) {
- if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2]))
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ bool duplicate = false;
+ struct aggr_cpu_id cpu_id = get_id(cpu, data);
+
+ for (int j = 0; j < c->nr; j++) {
+ if (aggr_cpu_id__equal(&cpu_id, &c->map[j])) {
+ duplicate = true;
break;
+ }
}
- if (s2 == c->nr) {
- c->map[c->nr] = s1;
+ if (!duplicate) {
+ c->map[c->nr] = cpu_id;
c->nr++;
}
}
- /* ensure we process id in increasing order */
- qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id);
+ /* Trim. */
+ if (c->nr != cpus->nr) {
+ struct cpu_aggr_map *trimmed_c =
+ realloc(c,
+ sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr);
- *res = c;
- return 0;
+ if (trimmed_c)
+ c = trimmed_c;
+ }
+ /* ensure we process id in increasing order */
+ qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp);
+
+ return c;
+
}
-int cpu_map__get_die_id(int cpu)
+int cpu__get_die_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "die_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "die_id", &value);
return ret ?: value;
}
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data)
{
- int cpu, die;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id;
+ int die;
- if (idx > map->nr)
- return id;
-
- cpu = map->map[idx];
-
- die = cpu_map__get_die_id(cpu);
+ die = cpu__get_die_id(cpu);
/* There is no die_id on legacy system. */
if (die == -1)
die = 0;
@@ -220,79 +224,59 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat
* with the socket ID and then add die to
* make a unique ID.
*/
- id = cpu_map__get_socket(map, idx, data);
- if (cpu_map__aggr_cpu_id_is_empty(id))
+ id = aggr_cpu_id__socket(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
id.die = die;
return id;
}
-int cpu_map__get_core_id(int cpu)
+int cpu__get_core_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value);
return ret ?: value;
}
-int cpu_map__get_node_id(int cpu)
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data)
{
- return cpu__get_node(cpu);
-}
+ struct aggr_cpu_id id;
+ int core = cpu__get_core_id(cpu);
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
-{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
-
- if (idx > map->nr)
- return id;
-
- cpu = map->map[idx];
-
- cpu = cpu_map__get_core_id(cpu);
-
- /* cpu_map__get_die returns a struct with socket and die set*/
- id = cpu_map__get_die(map, idx, data);
- if (cpu_map__aggr_cpu_id_is_empty(id))
+ /* aggr_cpu_id__die returns a struct with socket and die set. */
+ id = aggr_cpu_id__die(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
/*
* core_id is relative to socket and die, we need a global id.
* So we combine the result from cpu_map__get_die with the core id
*/
- id.core = cpu;
+ id.core = core;
return id;
+
}
-struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data)
{
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id;
- if (idx < 0 || idx >= map->nr)
+ /* aggr_cpu_id__core returns a struct with socket, die and core set. */
+ id = aggr_cpu_id__core(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
- id.node = cpu_map__get_node_id(map->map[idx]);
+ id.cpu = cpu;
return id;
+
}
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp)
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data __maybe_unused)
{
- return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
-}
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep)
-{
- return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
-}
-
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep)
-{
- return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
-}
-
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap)
-{
- return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
+ id.node = cpu__get_node(cpu);
+ return id;
}
/* setup simple routines to easily access node numbers given a cpu number */
@@ -335,8 +319,8 @@ static void set_max_cpu_num(void)
int ret = -1;
/* set up default */
- max_cpu_num = 4096;
- max_present_cpu_num = 4096;
+ max_cpu_num.cpu = 4096;
+ max_present_cpu_num.cpu = 4096;
mnt = sysfs__mountpoint();
if (!mnt)
@@ -349,7 +333,7 @@ static void set_max_cpu_num(void)
goto out;
}
- ret = get_max_num(path, &max_cpu_num);
+ ret = get_max_num(path, &max_cpu_num.cpu);
if (ret)
goto out;
@@ -360,11 +344,11 @@ static void set_max_cpu_num(void)
goto out;
}
- ret = get_max_num(path, &max_present_cpu_num);
+ ret = get_max_num(path, &max_present_cpu_num.cpu);
out:
if (ret)
- pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+ pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
}
/* Determine highest possible node in the system for sparse allocation */
@@ -403,31 +387,31 @@ int cpu__max_node(void)
return max_node_num;
}
-int cpu__max_cpu(void)
+struct perf_cpu cpu__max_cpu(void)
{
- if (unlikely(!max_cpu_num))
+ if (unlikely(!max_cpu_num.cpu))
set_max_cpu_num();
return max_cpu_num;
}
-int cpu__max_present_cpu(void)
+struct perf_cpu cpu__max_present_cpu(void)
{
- if (unlikely(!max_present_cpu_num))
+ if (unlikely(!max_present_cpu_num.cpu))
set_max_cpu_num();
return max_present_cpu_num;
}
-int cpu__get_node(int cpu)
+int cpu__get_node(struct perf_cpu cpu)
{
if (unlikely(cpunode_map == NULL)) {
pr_debug("cpu_map not initialized\n");
return -1;
}
- return cpunode_map[cpu];
+ return cpunode_map[cpu.cpu];
}
static int init_cpunode_map(void)
@@ -437,13 +421,13 @@ static int init_cpunode_map(void)
set_max_cpu_num();
set_max_node_num();
- cpunode_map = calloc(max_cpu_num, sizeof(int));
+ cpunode_map = calloc(max_cpu_num.cpu, sizeof(int));
if (!cpunode_map) {
pr_err("%s: calloc failed\n", __func__);
return -1;
}
- for (i = 0; i < max_cpu_num; i++)
+ for (i = 0; i < max_cpu_num.cpu; i++)
cpunode_map[i] = -1;
return 0;
@@ -502,47 +486,39 @@ int cpu__setup_cpunode_map(void)
return 0;
}
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu)
-{
- return perf_cpu_map__idx(cpus, cpu) != -1;
-}
-
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx)
-{
- return cpus->map[idx];
-}
-
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
{
- int i, cpu, start = -1;
+ int i, start = -1;
bool first = true;
size_t ret = 0;
#define COMMA first ? "" : ","
for (i = 0; i < map->nr + 1; i++) {
+ struct perf_cpu cpu = { .cpu = INT_MAX };
bool last = i == map->nr;
- cpu = last ? INT_MAX : map->map[i];
+ if (!last)
+ cpu = map->map[i];
if (start == -1) {
start = i;
if (last) {
ret += snprintf(buf + ret, size - ret,
"%s%d", COMMA,
- map->map[i]);
+ map->map[i].cpu);
}
- } else if (((i - start) != (cpu - map->map[start])) || last) {
+ } else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) {
int end = i - 1;
if (start == end) {
ret += snprintf(buf + ret, size - ret,
"%s%d", COMMA,
- map->map[start]);
+ map->map[start].cpu);
} else {
ret += snprintf(buf + ret, size - ret,
"%s%d-%d", COMMA,
- map->map[start], map->map[end]);
+ map->map[start].cpu, map->map[end].cpu);
}
first = false;
start = i;
@@ -569,23 +545,23 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
int i, cpu;
char *ptr = buf;
unsigned char *bitmap;
- int last_cpu = cpu_map__cpu(map, map->nr - 1);
+ struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1);
if (buf == NULL)
return 0;
- bitmap = zalloc(last_cpu / 8 + 1);
+ bitmap = zalloc(last_cpu.cpu / 8 + 1);
if (bitmap == NULL) {
buf[0] = '\0';
return 0;
}
for (i = 0; i < map->nr; i++) {
- cpu = cpu_map__cpu(map, i);
+ cpu = perf_cpu_map__cpu(map, i).cpu;
bitmap[cpu / 8] |= 1 << (cpu % 8);
}
- for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+ for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
unsigned char bits = bitmap[cpu / 8];
if (cpu % 8)
@@ -614,32 +590,35 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
return online;
}
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b)
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b)
{
- return a.thread == b.thread &&
- a.node == b.node &&
- a.socket == b.socket &&
- a.die == b.die &&
- a.core == b.core;
+ return a->thread == b->thread &&
+ a->node == b->node &&
+ a->socket == b->socket &&
+ a->die == b->die &&
+ a->core == b->core &&
+ a->cpu.cpu == b->cpu.cpu;
}
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a)
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a)
{
- return a.thread == -1 &&
- a.node == -1 &&
- a.socket == -1 &&
- a.die == -1 &&
- a.core == -1;
+ return a->thread == -1 &&
+ a->node == -1 &&
+ a->socket == -1 &&
+ a->die == -1 &&
+ a->core == -1 &&
+ a->cpu.cpu == -1;
}
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void)
+struct aggr_cpu_id aggr_cpu_id__empty(void)
{
struct aggr_cpu_id ret = {
.thread = -1,
.node = -1,
.socket = -1,
.die = -1,
- .core = -1
+ .core = -1,
+ .cpu = (struct perf_cpu){ .cpu = -1 },
};
return ret;
}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index a27eeaf..0d3c200 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -2,71 +2,135 @@
#ifndef __PERF_CPUMAP_H
#define __PERF_CPUMAP_H
+#include <stdbool.h>
#include <stdio.h>
#include <stdbool.h>
#include <internal/cpumap.h>
#include <perf/cpumap.h>
+/** Identify where counts are aggregated, -1 implies not to aggregate. */
struct aggr_cpu_id {
+ /** A value in the range 0 to number of threads. */
int thread;
+ /** The numa node X as read from /sys/devices/system/node/nodeX. */
int node;
+ /**
+ * The socket number as read from
+ * /sys/devices/system/cpu/cpuX/topology/physical_package_id.
+ */
int socket;
+ /** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */
int die;
+ /** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */
int core;
+ /** CPU aggregation, note there is one CPU for each SMT thread. */
+ struct perf_cpu cpu;
};
+/** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */
struct cpu_aggr_map {
refcount_t refcnt;
+ /** Number of valid entries. */
int nr;
+ /** The entries. */
struct aggr_cpu_id map[];
};
struct perf_record_cpu_map_data;
struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
-struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
-int cpu_map__get_socket_id(int cpu);
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_die_id(int cpu);
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_core_id(int cpu);
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_node_id(int cpu);
-struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp);
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep);
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep);
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep);
const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
-static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
-{
- if (!sock || s > sock->nr || s < 0)
- return 0;
- return sock->map[s];
-}
-
int cpu__setup_cpunode_map(void);
int cpu__max_node(void);
-int cpu__max_cpu(void);
-int cpu__max_present_cpu(void);
-int cpu__get_node(int cpu);
+struct perf_cpu cpu__max_cpu(void);
+struct perf_cpu cpu__max_present_cpu(void);
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
- struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
- void *data);
+/**
+ * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1.
+ */
+static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus)
+{
+ return cpus->nr == 1 && cpus->map[0].cpu == -1;
+}
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
+/**
+ * cpu__get_node - Returns the numa node X as read from
+ * /sys/devices/system/node/nodeX for the given CPU.
+ */
+int cpu__get_node(struct perf_cpu cpu);
+/**
+ * cpu__get_socket_id - Returns the socket number as read from
+ * /sys/devices/system/cpu/cpuX/topology/physical_package_id for the given CPU.
+ */
+int cpu__get_socket_id(struct perf_cpu cpu);
+/**
+ * cpu__get_die_id - Returns the die id as read from
+ * /sys/devices/system/cpu/cpuX/topology/die_id for the given CPU.
+ */
+int cpu__get_die_id(struct perf_cpu cpu);
+/**
+ * cpu__get_core_id - Returns the core id as read from
+ * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU.
+ */
+int cpu__get_core_id(struct perf_cpu cpu);
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b);
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a);
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void);
+/**
+ * cpu_aggr_map__empty_new - Create a cpu_aggr_map of size nr with every entry
+ * being empty.
+ */
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
+
+typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data);
+
+/**
+ * cpu_aggr_map__new - Create a cpu_aggr_map with an aggr_cpu_id for each cpu in
+ * cpus. The aggr_cpu_id is created with 'get_id' that may have a data value
+ * passed to it. The cpu_aggr_map is sorted with duplicate values removed.
+ */
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+ aggr_cpu_id_get_t get_id,
+ void *data);
+
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b);
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a);
+struct aggr_cpu_id aggr_cpu_id__empty(void);
+
+
+/**
+ * aggr_cpu_id__socket - Create an aggr_cpu_id with the socket populated with
+ * the socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__die - Create an aggr_cpu_id with the die and socket populated
+ * with the die and socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket
+ * populated with the core, die and socket for cpu. The function signature is
+ * compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the cpu, core, die and socket
+ * populated with the cpu, core, die and socket for cpu. The function signature
+ * is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__node - Create an aggr_cpu_id with the numa node populated for
+ * cpu. The function signature is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data);
#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 51b429c..e20b835 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -165,7 +165,8 @@ static bool has_die_topology(void)
if (uname(&uts) < 0)
return false;
- if (strncmp(uts.machine, "x86_64", 6))
+ if (strncmp(uts.machine, "x86_64", 6) &&
+ strncmp(uts.machine, "s390x", 5))
return false;
scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
@@ -187,7 +188,7 @@ struct cpu_topology *cpu_topology__new(void)
struct perf_cpu_map *map;
bool has_die = has_die_topology();
- ncpus = cpu__max_present_cpu();
+ ncpus = cpu__max_present_cpu().cpu;
/* build online CPU map */
map = perf_cpu_map__new(NULL);
@@ -218,7 +219,7 @@ struct cpu_topology *cpu_topology__new(void)
tp->core_cpus_list = addr;
for (i = 0; i < nr; i++) {
- if (!cpu_map__has(map, i))
+ if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i }))
continue;
ret = build_cpu_topology(tp, i);
@@ -333,7 +334,7 @@ struct numa_topology *numa_topology__new(void)
tp->nr = nr;
for (i = 0; i < nr; i++) {
- if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+ if (load_numa_node(&tp->nodes[i], node_map->map[i].cpu)) {
numa_topology__delete(tp);
tp = NULL;
break;
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 2c06abf..65e6c22 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -179,7 +179,7 @@ static int trace_event_printer(enum binary_printer_ops op,
break;
case BINARY_PRINT_CHAR_DATA:
printed += color_fprintf(fp, color, "%c",
- isprint(ch) ? ch : '.');
+ isprint(ch) && isascii(ch) ? ch : '.');
break;
case BINARY_PRINT_CHAR_PAD:
printed += color_fprintf(fp, color, " ");
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index b990489..579e44c 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -285,13 +285,13 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
int perf_env__read_cpu_topology_map(struct perf_env *env)
{
- int cpu, nr_cpus;
+ int idx, nr_cpus;
if (env->cpu != NULL)
return 0;
if (env->nr_cpus_avail == 0)
- env->nr_cpus_avail = cpu__max_present_cpu();
+ env->nr_cpus_avail = cpu__max_present_cpu().cpu;
nr_cpus = env->nr_cpus_avail;
if (nr_cpus == -1)
@@ -301,10 +301,12 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
if (env->cpu == NULL)
return -ENOMEM;
- for (cpu = 0; cpu < nr_cpus; ++cpu) {
- env->cpu[cpu].core_id = cpu_map__get_core_id(cpu);
- env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu);
- env->cpu[cpu].die_id = cpu_map__get_die_id(cpu);
+ for (idx = 0; idx < nr_cpus; ++idx) {
+ struct perf_cpu cpu = { .cpu = idx };
+
+ env->cpu[idx].core_id = cpu__get_core_id(cpu);
+ env->cpu[idx].socket_id = cpu__get_socket_id(cpu);
+ env->cpu[idx].die_id = cpu__get_die_id(cpu);
}
env->nr_cpus_avail = nr_cpus;
@@ -381,7 +383,7 @@ static int perf_env__read_arch(struct perf_env *env)
static int perf_env__read_nr_cpus_avail(struct perf_env *env)
{
if (env->nr_cpus_avail == 0)
- env->nr_cpus_avail = cpu__max_present_cpu();
+ env->nr_cpus_avail = cpu__max_present_cpu().cpu;
return env->nr_cpus_avail ? 0 : -ENOENT;
}
@@ -487,7 +489,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env)
return env->pmu_mappings;
}
-int perf_env__numa_node(struct perf_env *env, int cpu)
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
{
if (!env->nr_numa_map) {
struct numa_node *nn;
@@ -495,7 +497,7 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
for (i = 0; i < env->nr_numa_nodes; i++) {
nn = &env->numa_nodes[i];
- nr = max(nr, perf_cpu_map__max(nn->map));
+ nr = max(nr, perf_cpu_map__max(nn->map).cpu);
}
nr++;
@@ -514,13 +516,14 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
env->nr_numa_map = nr;
for (i = 0; i < env->nr_numa_nodes; i++) {
- int tmp, j;
+ struct perf_cpu tmp;
+ int j;
nn = &env->numa_nodes[i];
- perf_cpu_map__for_each_cpu(j, tmp, nn->map)
- env->numa_map[j] = i;
+ perf_cpu_map__for_each_cpu(tmp, j, nn->map)
+ env->numa_map[tmp.cpu] = i;
}
}
- return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1;
+ return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 163e5ec..a3541f9 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/rbtree.h>
+#include "cpumap.h"
#include "rwsem.h"
struct perf_cpu_map;
@@ -170,5 +171,5 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
-int perf_env__numa_node(struct perf_env *env, int cpu);
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
#endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5f92319..6e88d40 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -342,36 +342,65 @@ static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
return perf_thread_map__nr(evlist->core.threads);
}
-void evlist__cpu_iter_start(struct evlist *evlist)
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity)
{
- struct evsel *pos;
+ struct evlist_cpu_iterator itr = {
+ .container = evlist,
+ .evsel = evlist__first(evlist),
+ .cpu_map_idx = 0,
+ .evlist_cpu_map_idx = 0,
+ .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus),
+ .cpu = (struct perf_cpu){ .cpu = -1},
+ .affinity = affinity,
+ };
- /*
- * Reset the per evsel cpu_iter. This is needed because
- * each evsel's cpumap may have a different index space,
- * and some operations need the index to modify
- * the FD xyarray (e.g. open, close)
- */
- evlist__for_each_entry(evlist, pos)
- pos->cpu_iter = 0;
-}
-
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu)
-{
- if (ev->cpu_iter >= ev->core.cpus->nr)
- return true;
- if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu)
- return true;
- return false;
-}
-
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
-{
- if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) {
- ev->cpu_iter++;
- return false;
+ if (itr.affinity) {
+ itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0);
+ affinity__set(itr.affinity, itr.cpu.cpu);
+ itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu);
+ /*
+ * If this CPU isn't in the evsel's cpu map then advance through
+ * the list.
+ */
+ if (itr.cpu_map_idx == -1)
+ evlist_cpu_iterator__next(&itr);
}
- return true;
+ return itr;
+}
+
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr)
+{
+ while (evlist_cpu_itr->evsel != evlist__last(evlist_cpu_itr->container)) {
+ evlist_cpu_itr->evsel = evsel__next(evlist_cpu_itr->evsel);
+ evlist_cpu_itr->cpu_map_idx =
+ perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+ evlist_cpu_itr->cpu);
+ if (evlist_cpu_itr->cpu_map_idx != -1)
+ return;
+ }
+ evlist_cpu_itr->evlist_cpu_map_idx++;
+ if (evlist_cpu_itr->evlist_cpu_map_idx < evlist_cpu_itr->evlist_cpu_map_nr) {
+ evlist_cpu_itr->evsel = evlist__first(evlist_cpu_itr->container);
+ evlist_cpu_itr->cpu =
+ perf_cpu_map__cpu(evlist_cpu_itr->container->core.all_cpus,
+ evlist_cpu_itr->evlist_cpu_map_idx);
+ if (evlist_cpu_itr->affinity)
+ affinity__set(evlist_cpu_itr->affinity, evlist_cpu_itr->cpu.cpu);
+ evlist_cpu_itr->cpu_map_idx =
+ perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+ evlist_cpu_itr->cpu);
+ /*
+ * If this CPU isn't in the evsel's cpu map then advance through
+ * the list.
+ */
+ if (evlist_cpu_itr->cpu_map_idx == -1)
+ evlist_cpu_iterator__next(evlist_cpu_itr);
+ }
+}
+
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr)
+{
+ return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr;
}
static int evsel__strcmp(struct evsel *pos, char *evsel_name)
@@ -400,31 +429,26 @@ static int evlist__is_enabled(struct evlist *evlist)
static void __evlist__disable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
+ struct evlist_cpu_iterator evlist_cpu_itr;
struct affinity affinity;
- int cpu, i, imm = 0;
bool has_imm = false;
if (affinity__setup(&affinity) < 0)
return;
/* Disable 'immediate' events last */
- for (imm = 0; imm <= 1; imm++) {
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
-
- evlist__for_each_entry(evlist, pos) {
- if (evsel__strcmp(pos, evsel_name))
- continue;
- if (evsel__cpu_iter_skip(pos, cpu))
- continue;
- if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
- continue;
- if (pos->immediate)
- has_imm = true;
- if (pos->immediate != imm)
- continue;
- evsel__disable_cpu(pos, pos->cpu_iter - 1);
- }
+ for (int imm = 0; imm <= 1; imm++) {
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+ pos = evlist_cpu_itr.evsel;
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
+ if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ if (pos->immediate)
+ has_imm = true;
+ if (pos->immediate != imm)
+ continue;
+ evsel__disable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
}
if (!has_imm)
break;
@@ -462,24 +486,19 @@ void evlist__disable_evsel(struct evlist *evlist, char *evsel_name)
static void __evlist__enable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
+ struct evlist_cpu_iterator evlist_cpu_itr;
struct affinity affinity;
- int cpu, i;
if (affinity__setup(&affinity) < 0)
return;
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
-
- evlist__for_each_entry(evlist, pos) {
- if (evsel__strcmp(pos, evsel_name))
- continue;
- if (evsel__cpu_iter_skip(pos, cpu))
- continue;
- if (!evsel__is_group_leader(pos) || !pos->core.fd)
- continue;
- evsel__enable_cpu(pos, pos->cpu_iter - 1);
- }
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+ pos = evlist_cpu_itr.evsel;
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
}
affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
@@ -800,7 +819,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
static int
perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp,
- int output, int cpu)
+ int output, struct perf_cpu cpu)
{
struct mmap *map = container_of(_map, struct mmap, core);
struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
@@ -1264,14 +1283,14 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel)
void evlist__close(struct evlist *evlist)
{
struct evsel *evsel;
+ struct evlist_cpu_iterator evlist_cpu_itr;
struct affinity affinity;
- int cpu, i;
/*
* With perf record core.cpus is usually NULL.
* Use the old method to handle this for now.
*/
- if (!evlist->core.cpus) {
+ if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) {
evlist__for_each_entry_reverse(evlist, evsel)
evsel__close(evsel);
return;
@@ -1279,15 +1298,12 @@ void evlist__close(struct evlist *evlist)
if (affinity__setup(&affinity) < 0)
return;
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
- evlist__for_each_entry_reverse(evlist, evsel) {
- if (evsel__cpu_iter_skip(evsel, cpu))
- continue;
- perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
- }
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+ perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core,
+ evlist_cpu_itr.cpu_map_idx);
}
+
affinity__cleanup(&affinity);
evlist__for_each_entry_reverse(evlist, evsel) {
perf_evsel__free_fd(&evsel->core);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 97bfb8d..64cba56 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -64,6 +64,7 @@ struct evlist {
struct evsel *selected;
struct events_stats stats;
struct perf_env *env;
+ const char *hybrid_pmu_name;
void (*trace_event_sample_raw)(struct evlist *evlist,
union perf_event *event,
struct perf_sample *sample);
@@ -110,6 +111,7 @@ int __evlist__add_default_attrs(struct evlist *evlist,
__evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
int arch_evlist__add_default_attrs(struct evlist *evlist);
+struct evsel *arch_evlist__leader(struct list_head *list);
int evlist__add_dummy(struct evlist *evlist);
@@ -325,17 +327,53 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel);
#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
-#define evlist__for_each_cpu(evlist, index, cpu) \
- evlist__cpu_iter_start(evlist); \
- perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
+/** Iterator state for evlist__for_each_cpu */
+struct evlist_cpu_iterator {
+ /** The list being iterated through. */
+ struct evlist *container;
+ /** The current evsel of the iterator. */
+ struct evsel *evsel;
+ /** The CPU map index corresponding to the evsel->core.cpus for the current CPU. */
+ int cpu_map_idx;
+ /**
+ * The CPU map index corresponding to evlist->core.all_cpus for the
+ * current CPU. Distinct from cpu_map_idx as the evsel's cpu map may
+ * contain fewer entries.
+ */
+ int evlist_cpu_map_idx;
+ /** The number of CPU map entries in evlist->core.all_cpus. */
+ int evlist_cpu_map_nr;
+ /** The current CPU of the iterator. */
+ struct perf_cpu cpu;
+ /** If present, used to set the affinity when switching between CPUs. */
+ struct affinity *affinity;
+};
+
+/**
+ * evlist__for_each_cpu - without affinity, iterate over the evlist. With
+ * affinity, iterate over all CPUs and then the evlist
+ * for each evsel on that CPU. When switching between
+ * CPUs the affinity is set to the CPU to avoid IPIs
+ * during syscalls.
+ * @evlist_cpu_itr: the iterator instance.
+ * @evlist: evlist instance to iterate.
+ * @affinity: NULL or used to set the affinity to the current CPU.
+ */
+#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) \
+ for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity); \
+ !evlist_cpu_iterator__end(&evlist_cpu_itr); \
+ evlist_cpu_iterator__next(&evlist_cpu_itr))
+
+/** Returns an iterator set to the first CPU/evsel of evlist. */
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity);
+/** Move to next element in iterator, updating CPU, evsel and the affinity. */
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr);
+/** Returns true when iterator is at the end of the CPUs and evlist. */
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr);
struct evsel *evlist__get_tracking_event(struct evlist *evlist);
void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
-void evlist__cpu_iter_start(struct evlist *evlist);
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
-
struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f29d370..2f6b18a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1372,9 +1372,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
}
/* Caller has to clear disabled after going through all CPUs. */
-int evsel__enable_cpu(struct evsel *evsel, int cpu)
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__enable_cpu(&evsel->core, cpu);
+ return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx);
}
int evsel__enable(struct evsel *evsel)
@@ -1387,9 +1387,9 @@ int evsel__enable(struct evsel *evsel)
}
/* Caller has to set disabled after going through all CPUs. */
-int evsel__disable_cpu(struct evsel *evsel, int cpu)
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__disable_cpu(&evsel->core, cpu);
+ return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx);
}
int evsel__disable(struct evsel *evsel)
@@ -1455,7 +1455,7 @@ void evsel__delete(struct evsel *evsel)
free(evsel);
}
-void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values tmp;
@@ -1463,12 +1463,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
if (!evsel->prev_raw_counts)
return;
- if (cpu == -1) {
+ if (cpu_map_idx == -1) {
tmp = evsel->prev_raw_counts->aggr;
evsel->prev_raw_counts->aggr = *count;
} else {
- tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
- *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
+ tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+ *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
}
count->val = count->val - tmp.val;
@@ -1476,46 +1476,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
count->run = count->run - tmp.run;
}
-void perf_counts_values__scale(struct perf_counts_values *count,
- bool scale, s8 *pscaled)
+static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
{
- s8 scaled = 0;
+ struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread);
- if (scale) {
- if (count->run == 0) {
- scaled = -1;
- count->val = 0;
- } else if (count->run < count->ena) {
- scaled = 1;
- count->val = (u64)((double) count->val * count->ena / count->run);
- }
- }
-
- if (pscaled)
- *pscaled = scaled;
+ return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count);
}
-static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
-{
- struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
-
- return perf_evsel__read(&evsel->core, cpu, thread, count);
-}
-
-static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
+ u64 val, u64 ena, u64 run)
{
struct perf_counts_values *count;
- count = perf_counts(counter->counts, cpu, thread);
+ count = perf_counts(counter->counts, cpu_map_idx, thread);
count->val = val;
count->ena = ena;
count->run = run;
- perf_counts__set_loaded(counter->counts, cpu, thread, true);
+ perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
}
-static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data)
{
u64 read_format = leader->core.attr.read_format;
struct sample_read_value *v;
@@ -1534,7 +1516,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
v = (struct sample_read_value *) data;
- evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
+ evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
for (i = 1; i < nr; i++) {
struct evsel *counter;
@@ -1543,13 +1525,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
if (!counter)
return -EINVAL;
- evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
+ evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
}
return 0;
}
-static int evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread)
{
struct perf_stat_evsel *ps = leader->stats;
u64 read_format = leader->core.attr.read_format;
@@ -1570,67 +1552,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
ps->group_data = data;
}
- if (FD(leader, cpu, thread) < 0)
+ if (FD(leader, cpu_map_idx, thread) < 0)
return -EINVAL;
- if (readn(FD(leader, cpu, thread), data, size) <= 0)
+ if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0)
return -errno;
- return evsel__process_group_data(leader, cpu, thread, data);
+ return evsel__process_group_data(leader, cpu_map_idx, thread, data);
}
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
{
u64 read_format = evsel->core.attr.read_format;
if (read_format & PERF_FORMAT_GROUP)
- return evsel__read_group(evsel, cpu, thread);
+ return evsel__read_group(evsel, cpu_map_idx, thread);
- return evsel__read_one(evsel, cpu, thread);
+ return evsel__read_one(evsel, cpu_map_idx, thread);
}
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale)
{
struct perf_counts_values count;
size_t nv = scale ? 3 : 1;
- if (FD(evsel, cpu, thread) < 0)
+ if (FD(evsel, cpu_map_idx, thread) < 0)
return -EINVAL;
- if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
+ if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0)
return -ENOMEM;
- if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
+ if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
- evsel__compute_deltas(evsel, cpu, thread, &count);
+ evsel__compute_deltas(evsel, cpu_map_idx, thread, &count);
perf_counts_values__scale(&count, scale, NULL);
- *perf_counts(evsel->counts, cpu, thread) = count;
+ *perf_counts(evsel->counts, cpu_map_idx, thread) = count;
return 0;
}
static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other,
- int cpu)
+ int cpu_map_idx)
{
- int cpuid;
+ struct perf_cpu cpu;
- cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu);
- return perf_cpu_map__idx(other->core.cpus, cpuid);
+ cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
+ return perf_cpu_map__idx(other->core.cpus, cpu);
}
-static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu)
+static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx)
{
struct evsel *leader = evsel__leader(evsel);
if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) ||
(!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) {
- return evsel__match_other_cpu(evsel, leader, cpu);
+ return evsel__match_other_cpu(evsel, leader, cpu_map_idx);
}
- return cpu;
+ return cpu_map_idx;
}
-static int get_group_fd(struct evsel *evsel, int cpu, int thread)
+static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread)
{
struct evsel *leader = evsel__leader(evsel);
int fd;
@@ -1644,11 +1626,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
*/
BUG_ON(!leader->core.fd);
- cpu = evsel__hybrid_group_cpu(evsel, cpu);
- if (cpu == -1)
+ cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx);
+ if (cpu_map_idx == -1)
return -1;
- fd = FD(leader, cpu, thread);
+ fd = FD(leader, cpu_map_idx, thread);
BUG_ON(fd == -1);
return fd;
@@ -1662,16 +1644,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int
}
static int update_fds(struct evsel *evsel,
- int nr_cpus, int cpu_idx,
+ int nr_cpus, int cpu_map_idx,
int nr_threads, int thread_idx)
{
struct evsel *pos;
- if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+ if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads)
return -EINVAL;
evlist__for_each_entry(evsel->evlist, pos) {
- nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+ nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx;
evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
@@ -1685,10 +1667,10 @@ static int update_fds(struct evsel *evsel,
return 0;
}
-bool evsel__ignore_missing_thread(struct evsel *evsel,
- int nr_cpus, int cpu,
- struct perf_thread_map *threads,
- int thread, int err)
+static bool evsel__ignore_missing_thread(struct evsel *evsel,
+ int nr_cpus, int cpu_map_idx,
+ struct perf_thread_map *threads,
+ int thread, int err)
{
pid_t ignore_pid = perf_thread_map__pid(threads, thread);
@@ -1711,7 +1693,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel,
* We should remove fd for missing_thread first
* because thread_map__remove() will decrease threads->nr.
*/
- if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+ if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread))
return false;
if (thread_map__remove(threads, thread))
@@ -1993,9 +1975,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit)
static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads,
- int start_cpu, int end_cpu)
+ int start_cpu_map_idx, int end_cpu_map_idx)
{
- int cpu, thread, nthreads;
+ int idx, thread, nthreads;
int pid = -1, err, old_errno;
enum rlimit_action set_rlimit = NO_CHANGE;
@@ -2022,7 +2004,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
display_attr(&evsel->core.attr);
- for (cpu = start_cpu; cpu < end_cpu; cpu++) {
+ for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
for (thread = 0; thread < nthreads; thread++) {
int fd, group_fd;
@@ -2033,17 +2015,17 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
if (!evsel->cgrp && !evsel->core.system_wide)
pid = perf_thread_map__pid(threads, thread);
- group_fd = get_group_fd(evsel, cpu, thread);
+ group_fd = get_group_fd(evsel, idx, thread);
test_attr__ready();
pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
- pid, cpus->map[cpu], group_fd, evsel->open_flags);
+ pid, cpus->map[idx].cpu, group_fd, evsel->open_flags);
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu],
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[idx].cpu,
group_fd, evsel->open_flags);
- FD(evsel, cpu, thread) = fd;
+ FD(evsel, idx, thread) = fd;
if (fd < 0) {
err = -errno;
@@ -2053,10 +2035,10 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
goto try_fallback;
}
- bpf_counter__install_pe(evsel, cpu, fd);
+ bpf_counter__install_pe(evsel, idx, fd);
if (unlikely(test_attr__enabled)) {
- test_attr__open(&evsel->core.attr, pid, cpus->map[cpu],
+ test_attr__open(&evsel->core.attr, pid, cpus->map[idx],
fd, group_fd, evsel->open_flags);
}
@@ -2097,7 +2079,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
if (evsel__precise_ip_fallback(evsel))
goto retry_open;
- if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
+ if (evsel__ignore_missing_thread(evsel, cpus->nr, idx, threads, thread, err)) {
/* We just removed 1 thread, so lower the upper nthreads limit. */
nthreads--;
@@ -2112,7 +2094,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
goto retry_open;
- if (err != -EINVAL || cpu > 0 || thread > 0)
+ if (err != -EINVAL || idx > 0 || thread > 0)
goto out_close;
if (evsel__detect_missing_features(evsel))
@@ -2124,12 +2106,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
old_errno = errno;
do {
while (--thread >= 0) {
- if (FD(evsel, cpu, thread) >= 0)
- close(FD(evsel, cpu, thread));
- FD(evsel, cpu, thread) = -1;
+ if (FD(evsel, idx, thread) >= 0)
+ close(FD(evsel, idx, thread));
+ FD(evsel, idx, thread) = -1;
}
thread = nthreads;
- } while (--cpu >= 0);
+ } while (--idx >= 0);
errno = old_errno;
return err;
}
@@ -2146,13 +2128,13 @@ void evsel__close(struct evsel *evsel)
perf_evsel__free_id(&evsel->core);
}
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx)
{
- if (cpu == -1)
+ if (cpu_map_idx == -1)
return evsel__open_cpu(evsel, cpus, NULL, 0,
cpus ? cpus->nr : 1);
- return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
+ return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1);
}
int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
@@ -2952,6 +2934,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size, "wrong clockid (%d).", clockid);
if (perf_missing_features.aux_output)
return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
+ if (!target__has_cpu(target))
+ return scnprintf(msg, size,
+ "Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
+ evsel__name(evsel));
break;
case ENODATA:
return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. "
@@ -2975,15 +2961,15 @@ struct perf_env *evsel__env(struct evsel *evsel)
static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
{
- int cpu, thread;
+ int cpu_map_idx, thread;
- for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
+ for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
thread++) {
- int fd = FD(evsel, cpu, thread);
+ int fd = FD(evsel, cpu_map_idx, thread);
if (perf_evlist__id_add_fd(&evlist->core, &evsel->core,
- cpu, thread, fd) < 0)
+ cpu_map_idx, thread, fd) < 0)
return -1;
}
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 29d49a8..5720cee 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -121,7 +121,6 @@ struct evsel {
bool errored;
struct hashmap *per_pkg_mask;
int err;
- int cpu_iter;
struct {
evsel__sb_cb_t *cb;
void *data;
@@ -195,9 +194,6 @@ static inline int evsel__nr_cpus(struct evsel *evsel)
return evsel__cpus(evsel)->nr;
}
-void perf_counts_values__scale(struct perf_counts_values *count,
- bool scale, s8 *pscaled);
-
void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
@@ -288,12 +284,12 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
int evsel__set_filter(struct evsel *evsel, const char *filter);
int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
-int evsel__enable_cpu(struct evsel *evsel, int cpu);
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx);
int evsel__enable(struct evsel *evsel);
int evsel__disable(struct evsel *evsel);
-int evsel__disable_cpu(struct evsel *evsel, int cpu);
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx);
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu);
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx);
int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads);
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
@@ -305,10 +301,6 @@ bool evsel__detect_missing_features(struct evsel *evsel);
enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX };
bool evsel__increase_rlimit(enum rlimit_action *set_rlimit);
-bool evsel__ignore_missing_thread(struct evsel *evsel,
- int nr_cpus, int cpu,
- struct perf_thread_map *threads,
- int thread, int err);
bool evsel__precise_ip_fallback(struct evsel *evsel);
struct perf_sample;
@@ -337,32 +329,32 @@ static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
(e1->core.attr.config == e2->core.attr.config);
}
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread);
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread);
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale);
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale);
/**
* evsel__read_on_cpu - Read out the results on a CPU and thread
*
* @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
* @thread - thread of interest
*/
-static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread)
{
- return __evsel__read_on_cpu(evsel, cpu, thread, false);
+ return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, false);
}
/**
* evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
*
* @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
* @thread - thread of interest
*/
-static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu_map_idx, int thread)
{
- return __evsel__read_on_cpu(evsel, cpu, thread, true);
+ return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, true);
}
int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 666b59b..675f318 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -405,12 +405,17 @@ double expr_id_data__source_count(const struct expr_id_data *data)
double expr__get_literal(const char *literal)
{
static struct cpu_topology *topology;
+ double result = NAN;
- if (!strcmp("#smt_on", literal))
- return smt_on() > 0 ? 1.0 : 0.0;
+ if (!strcasecmp("#smt_on", literal)) {
+ result = smt_on() > 0 ? 1.0 : 0.0;
+ goto out;
+ }
- if (!strcmp("#num_cpus", literal))
- return cpu__max_present_cpu();
+ if (!strcmp("#num_cpus", literal)) {
+ result = cpu__max_present_cpu().cpu;
+ goto out;
+ }
/*
* Assume that topology strings are consistent, such as CPUs "0-1"
@@ -422,16 +427,24 @@ double expr__get_literal(const char *literal)
topology = cpu_topology__new();
if (!topology) {
pr_err("Error creating CPU topology");
- return NAN;
+ goto out;
}
}
- if (!strcmp("#num_packages", literal))
- return topology->package_cpus_lists;
- if (!strcmp("#num_dies", literal))
- return topology->die_cpus_lists;
- if (!strcmp("#num_cores", literal))
- return topology->core_cpus_lists;
+ if (!strcmp("#num_packages", literal)) {
+ result = topology->package_cpus_lists;
+ goto out;
+ }
+ if (!strcmp("#num_dies", literal)) {
+ result = topology->die_cpus_lists;
+ goto out;
+ }
+ if (!strcmp("#num_cores", literal)) {
+ result = topology->core_cpus_lists;
+ goto out;
+ }
pr_err("Unrecognized literal '%s'", literal);
- return NAN;
+out:
+ pr_debug2("literal: %s = %f\n", literal, result);
+ return result;
}
diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h
new file mode 100644
index 0000000..887f68a
--- /dev/null
+++ b/tools/perf/util/ftrace.h
@@ -0,0 +1,81 @@
+#ifndef __PERF_FTRACE_H__
+#define __PERF_FTRACE_H__
+
+#include <linux/list.h>
+
+#include "target.h"
+
+struct evlist;
+
+struct perf_ftrace {
+ struct evlist *evlist;
+ struct target target;
+ const char *tracer;
+ struct list_head filters;
+ struct list_head notrace;
+ struct list_head graph_funcs;
+ struct list_head nograph_funcs;
+ unsigned long percpu_buffer_size;
+ bool inherit;
+ int graph_depth;
+ int func_stack_trace;
+ int func_irq_info;
+ int graph_nosleep_time;
+ int graph_noirqs;
+ int graph_verbose;
+ int graph_thresh;
+ unsigned int initial_delay;
+};
+
+struct filter_entry {
+ struct list_head list;
+ char name[];
+};
+
+#define NUM_BUCKET 22 /* 20 + 2 (for outliers in both direction) */
+
+#ifdef HAVE_BPF_SKEL
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace,
+ int buckets[]);
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace);
+
+#else /* !HAVE_BPF_SKEL */
+
+static inline int
+perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+ int buckets[] __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+#endif /* HAVE_BPF_SKEL */
+
+#endif /* __PERF_FTRACE_H__ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e3c1a53..6da12e5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -472,7 +472,7 @@ static int write_nrcpus(struct feat_fd *ff,
u32 nrc, nra;
int ret;
- nrc = cpu__max_present_cpu();
+ nrc = cpu__max_present_cpu().cpu;
nr = sysconf(_SC_NPROCESSORS_ONLN);
if (nr < 0)
@@ -1163,7 +1163,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
u32 nr, cpu;
u16 level;
- nr = cpu__max_cpu();
+ nr = cpu__max_cpu().cpu;
for (cpu = 0; cpu < nr; cpu++) {
for (level = 0; level < MAX_CACHE_LVL; level++) {
@@ -1195,7 +1195,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
static int write_cache(struct feat_fd *ff,
struct evlist *evlist __maybe_unused)
{
- u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL;
+ u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL;
struct cpu_cache_level caches[max_caches];
u32 cnt = 0, i, version = 1;
int ret;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b776465..0a8033b 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
- hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
+ hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
+ hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
+
if (symbol_conf.nanosecs)
hists__new_col_len(hists, HISTC_TIME, 16);
else
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 621f35a..2a15e22 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -75,7 +75,8 @@ enum hist_column {
HISTC_MEM_BLOCKED,
HISTC_LOCAL_INS_LAT,
HISTC_GLOBAL_INS_LAT,
- HISTC_P_STAGE_CYC,
+ HISTC_LOCAL_P_STAGE_CYC,
+ HISTC_GLOBAL_P_STAGE_CYC,
HISTC_NR_COLS, /* Last entry */
};
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index c397be0..15f60fd 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -23,7 +23,9 @@
#include "unwind.h"
#include "libunwind-aarch64.h"
+#define perf_event_arm_regs perf_event_arm64_regs
#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
+#undef perf_event_arm_regs
#include "../../arch/arm64/util/unwind-libunwind.c"
/* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb8496d..3901440 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -34,6 +34,7 @@
#include "bpf-event.h"
#include <internal/lib.h> // page_size
#include "cgroup.h"
+#include "arm64-frame-pointer-unwind-support.h"
#include <linux/ctype.h>
#include <symbol/kallsyms.h>
@@ -2710,6 +2711,15 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
return err;
}
+static u64 get_leaf_frame_caller(struct perf_sample *sample,
+ struct thread *thread, int usr_idx)
+{
+ if (machine__normalized_is(thread->maps->machine, "arm64"))
+ return get_leaf_frame_caller_aarch64(sample, thread, usr_idx);
+ else
+ return 0;
+}
+
static int thread__resolve_callchain_sample(struct thread *thread,
struct callchain_cursor *cursor,
struct evsel *evsel,
@@ -2723,9 +2733,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
struct ip_callchain *chain = sample->callchain;
int chain_nr = 0;
u8 cpumode = PERF_RECORD_MISC_USER;
- int i, j, err, nr_entries;
+ int i, j, err, nr_entries, usr_idx;
int skip_idx = -1;
int first_call = 0;
+ u64 leaf_frame_caller;
if (chain)
chain_nr = chain->nr;
@@ -2850,6 +2861,34 @@ static int thread__resolve_callchain_sample(struct thread *thread,
continue;
}
+ /*
+ * PERF_CONTEXT_USER allows us to locate where the user stack ends.
+ * Depending on callchain_param.order and the position of PERF_CONTEXT_USER,
+ * the index will be different in order to add the missing frame
+ * at the right place.
+ */
+
+ usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1;
+
+ if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) {
+
+ leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx);
+
+ /*
+ * check if leaf_frame_Caller != ip to not add the same
+ * value twice.
+ */
+
+ if (leaf_frame_caller && leaf_frame_caller != ip) {
+
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, leaf_frame_caller,
+ false, NULL, NULL, 0);
+ if (err)
+ return (err < 0) ? err : 0;
+ }
+ }
+
err = add_callchain_ip(thread, cursor, parent,
root_al, &cpumode, ip,
false, NULL, NULL, 0);
@@ -3079,14 +3118,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
}
/*
- * Compares the raw arch string. N.B. see instead perf_env__arch() if a
- * normalized arch is needed.
+ * Compares the raw arch string. N.B. see instead perf_env__arch() or
+ * machine__normalized_is() if a normalized arch is needed.
*/
bool machine__is(struct machine *machine, const char *arch)
{
return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
}
+bool machine__normalized_is(struct machine *machine, const char *arch)
+{
+ return machine && !strcmp(perf_env__arch(machine->env), arch);
+}
+
int machine__nr_cpus_avail(struct machine *machine)
{
return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a143087..c5a45dc 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine)
}
bool machine__is(struct machine *machine, const char *arch);
+bool machine__normalized_is(struct machine *machine, const char *arch);
int machine__nr_cpus_avail(struct machine *machine);
struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 3167b46..ed0ab83 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -309,6 +309,9 @@ static const char * const mem_hops[] = {
* to be set with mem_hops field.
*/
"core, same node",
+ "node, same socket",
+ "socket, same board",
+ "board",
};
int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
@@ -316,7 +319,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
size_t i, l = 0;
u64 m = PERF_MEM_LVL_NA;
u64 hit, miss;
- int printed;
+ int printed = 0;
if (mem_info)
m = mem_info->data_src.mem_lvl;
@@ -335,18 +338,22 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
l += 7;
}
- if (mem_info && mem_info->data_src.mem_hops)
+ /*
+ * Incase mem_hops field is set, we can skip printing data source via
+ * PERF_MEM_LVL namespace.
+ */
+ if (mem_info && mem_info->data_src.mem_hops) {
l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]);
-
- printed = 0;
- for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
- if (!(m & 0x1))
- continue;
- if (printed++) {
- strcat(out, " or ");
- l += 4;
+ } else {
+ for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+ if (!(m & 0x1))
+ continue;
+ if (printed++) {
+ strcat(out, " or ");
+ l += 4;
+ }
+ l += scnprintf(out + l, sz - l, mem_lvl[i]);
}
- l += scnprintf(out + l, sz - l, mem_lvl[i]);
}
if (mem_info && mem_info->data_src.mem_lvl_num) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index fffe02a..d8492e3 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -209,8 +209,8 @@ static struct metric *metric__new(const struct pmu_event *pe,
m->metric_name = pe->metric_name;
m->modifier = modifier ? strdup(modifier) : NULL;
if (modifier && !m->modifier) {
- free(m);
expr__ctx_free(m->pctx);
+ free(m);
return NULL;
}
m->metric_expr = pe->metric_expr;
@@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids,
*/
metric_id = evsel__metric_id(ev);
evlist__for_each_entry_continue(metric_evlist, ev) {
- if (!strcmp(evsel__metric_id(metric_events[i]), metric_id))
+ if (!strcmp(evsel__metric_id(ev), metric_id))
ev->metric_leader = metric_events[i];
}
}
@@ -1115,13 +1115,27 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_event *pe,
return ret;
}
+/**
+ * metric_list_cmp - list_sort comparator that sorts metrics with more events to
+ * the front. duration_time is excluded from the count.
+ */
static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
const struct list_head *r)
{
const struct metric *left = container_of(l, struct metric, nd);
const struct metric *right = container_of(r, struct metric, nd);
+ struct expr_id_data *data;
+ int left_count, right_count;
- return hashmap__size(right->pctx->ids) - hashmap__size(left->pctx->ids);
+ left_count = hashmap__size(left->pctx->ids);
+ if (!expr__get_id(left->pctx, "duration_time", &data))
+ left_count--;
+
+ right_count = hashmap__size(right->pctx->ids);
+ if (!expr__get_id(right->pctx, "duration_time", &data))
+ right_count--;
+
+ return right_count - left_count;
}
/**
@@ -1299,14 +1313,16 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
/**
* parse_ids - Build the event string for the ids and parse them creating an
* evlist. The encoded metric_ids are decoded.
+ * @metric_no_merge: is metric sharing explicitly disabled.
* @fake_pmu: used when testing metrics not supported by the current CPU.
* @ids: the event identifiers parsed from a metric.
* @modifier: any modifiers added to the events.
* @has_constraint: false if events should be placed in a weak group.
* @out_evlist: the created list of events.
*/
-static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
- const char *modifier, bool has_constraint, struct evlist **out_evlist)
+static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
+ struct expr_parse_ctx *ids, const char *modifier,
+ bool has_constraint, struct evlist **out_evlist)
{
struct parse_events_error parse_error;
struct evlist *parsed_evlist;
@@ -1314,12 +1330,19 @@ static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
int ret;
*out_evlist = NULL;
- if (hashmap__size(ids->ids) == 0) {
+ if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
char *tmp;
/*
- * No ids/events in the expression parsing context. Events may
- * have been removed because of constant evaluation, e.g.:
- * event1 if #smt_on else 0
+ * We may fail to share events between metrics because
+ * duration_time isn't present in one metric. For example, a
+ * ratio of cache misses doesn't need duration_time but the same
+ * events may be used for a misses per second. Events without
+ * sharing implies multiplexing, that is best avoided, so place
+ * duration_time in every group.
+ *
+ * Also, there may be no ids/events in the expression parsing
+ * context because of constant evaluation, e.g.:
+ * event1 if #smt_on else 0
* Add a duration_time event to avoid a parse error on an empty
* string.
*/
@@ -1387,7 +1410,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
ret = build_combined_expr_ctx(&metric_list, &combined);
if (!ret && combined && hashmap__size(combined->ids)) {
- ret = parse_ids(fake_pmu, combined, /*modifier=*/NULL,
+ ret = parse_ids(metric_no_merge, fake_pmu, combined,
+ /*modifier=*/NULL,
/*has_constraint=*/true,
&combined_evlist);
}
@@ -1435,7 +1459,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
}
}
if (!metric_evlist) {
- ret = parse_ids(fake_pmu, m->pctx, m->modifier,
+ ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
m->has_constraint, &m->evlist);
if (ret)
goto out;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 23ecdba..12261ed 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -94,7 +94,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
}
}
-static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
+static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity)
{
void *data;
size_t mmap_len;
@@ -138,7 +138,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
}
static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused,
- int cpu __maybe_unused, int affinity __maybe_unused)
+ struct perf_cpu cpu __maybe_unused, int affinity __maybe_unused)
{
return 0;
}
@@ -240,7 +240,8 @@ void mmap__munmap(struct mmap *map)
static void build_node_mask(int node, struct mmap_cpu_mask *mask)
{
- int c, cpu, nr_cpus;
+ int idx, nr_cpus;
+ struct perf_cpu cpu;
const struct perf_cpu_map *cpu_map = NULL;
cpu_map = cpu_map__online();
@@ -248,16 +249,16 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask)
return;
nr_cpus = perf_cpu_map__nr(cpu_map);
- for (c = 0; c < nr_cpus; c++) {
- cpu = cpu_map->map[c]; /* map c index to online cpu index */
+ for (idx = 0; idx < nr_cpus; idx++) {
+ cpu = cpu_map->map[idx]; /* map c index to online cpu index */
if (cpu__get_node(cpu) == node)
- set_bit(cpu, mask->bits);
+ set_bit(cpu.cpu, mask->bits);
}
}
static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
{
- map->affinity_mask.nbits = cpu__max_cpu();
+ map->affinity_mask.nbits = cpu__max_cpu().cpu;
map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits);
if (!map->affinity_mask.bits)
return -1;
@@ -265,12 +266,12 @@ static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *
if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
else if (mp->affinity == PERF_AFFINITY_CPU)
- set_bit(map->core.cpu, map->affinity_mask.bits);
+ set_bit(map->core.cpu.cpu, map->affinity_mask.bits);
return 0;
}
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu)
{
if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 8e259b9..83f6bd4 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -7,6 +7,7 @@
#include <linux/types.h>
#include <linux/ring_buffer.h>
#include <linux/bitops.h>
+#include <perf/cpumap.h>
#include <stdbool.h>
#include <pthread.h> // for cpu_set_t
#ifdef HAVE_AIO_SUPPORT
@@ -52,7 +53,7 @@ struct mmap_params {
struct auxtrace_mmap_params auxtrace_mp;
};
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu);
void mmap__munmap(struct mmap *map);
union perf_event *perf_mmap__read_forward(struct mmap *map);
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 608b20c..48aa321 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -60,17 +60,49 @@ void namespaces__free(struct namespaces *namespaces)
free(namespaces);
}
+static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path)
+{
+ FILE *f = NULL;
+ char *statln = NULL;
+ size_t linesz = 0;
+ char *nspid;
+
+ f = fopen(path, "r");
+ if (f == NULL)
+ return -1;
+
+ while (getline(&statln, &linesz, f) != -1) {
+ /* Use tgid if CONFIG_PID_NS is not defined. */
+ if (strstr(statln, "Tgid:") != NULL) {
+ nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
+ NULL, 10);
+ nsi->nstgid = nsi->tgid;
+ }
+
+ if (strstr(statln, "NStgid:") != NULL) {
+ nspid = strrchr(statln, '\t');
+ nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
+ /*
+ * If innermost tgid is not the first, process is in a different
+ * PID namespace.
+ */
+ nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
+ break;
+ }
+ }
+
+ fclose(f);
+ free(statln);
+ return 0;
+}
+
int nsinfo__init(struct nsinfo *nsi)
{
char oldns[PATH_MAX];
char spath[PATH_MAX];
char *newns = NULL;
- char *statln = NULL;
- char *nspid;
struct stat old_stat;
struct stat new_stat;
- FILE *f = NULL;
- size_t linesz = 0;
int rv = -1;
if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
@@ -100,34 +132,9 @@ int nsinfo__init(struct nsinfo *nsi)
if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
goto out;
- f = fopen(spath, "r");
- if (f == NULL)
- goto out;
-
- while (getline(&statln, &linesz, f) != -1) {
- /* Use tgid if CONFIG_PID_NS is not defined. */
- if (strstr(statln, "Tgid:") != NULL) {
- nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
- NULL, 10);
- nsi->nstgid = nsi->tgid;
- }
-
- if (strstr(statln, "NStgid:") != NULL) {
- nspid = strrchr(statln, '\t');
- nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
- /* If innermost tgid is not the first, process is in a different
- * PID namespace.
- */
- nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
- break;
- }
- }
- rv = 0;
+ rv = nsinfo__get_nspid(nsi, spath);
out:
- if (f != NULL)
- (void) fclose(f);
- free(statln);
free(newns);
return rv;
}
@@ -299,3 +306,12 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi)
return ret;
}
+
+bool nsinfo__is_in_root_namespace(void)
+{
+ struct nsinfo nsi;
+
+ memset(&nsi, 0x0, sizeof(nsi));
+ nsinfo__get_nspid(&nsi, "/proc/self/status");
+ return !nsi.in_pidns;
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index ad9775d..9ceea96 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -59,6 +59,8 @@ void nsinfo__mountns_exit(struct nscookie *nc);
char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi);
+bool nsinfo__is_in_root_namespace(void);
+
static inline void __nsinfo__zput(struct nsinfo **nsip)
{
if (nsip) {
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 9fc8697..284f8ea 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -63,10 +63,13 @@ static int create_event_hybrid(__u32 config_type, int *idx,
static int pmu_cmp(struct parse_events_state *parse_state,
struct perf_pmu *pmu)
{
- if (!parse_state->hybrid_pmu_name)
- return 0;
+ if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name)
+ return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name);
- return strcmp(parse_state->hybrid_pmu_name, pmu->name);
+ if (parse_state->hybrid_pmu_name)
+ return strcmp(parse_state->hybrid_pmu_name, pmu->name);
+
+ return 0;
}
static int add_hw_hybrid(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index ba74fdf..acf20ce9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1824,6 +1824,11 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
return ret;
}
+__weak struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ return list_first_entry(list, struct evsel, core.node);
+}
+
void parse_events__set_leader(char *name, struct list_head *list,
struct parse_events_state *parse_state)
{
@@ -1837,9 +1842,10 @@ void parse_events__set_leader(char *name, struct list_head *list,
if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
return;
- __perf_evlist__set_leader(list);
- leader = list_entry(list->next, struct evsel, core.node);
+ leader = arch_evlist__leader(list);
+ __perf_evlist__set_leader(list, &leader->core);
leader->group_name = name ? strdup(name) : NULL;
+ list_move(&leader->core.node, list);
}
/* list_event is assumed to point to malloc'ed memory */
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index 0204116..734d006 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -11,7 +11,7 @@
typedef void (*setup_probe_fn_t)(struct evsel *evsel);
-static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str)
{
struct evlist *evlist;
struct evsel *evsel;
@@ -29,7 +29,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
evsel = evlist__first(evlist);
while (1) {
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
if (fd < 0) {
if (pid == -1 && errno == EACCES) {
pid = 0;
@@ -43,7 +43,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
fn(evsel);
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
if (fd < 0) {
if (errno == EINVAL)
err = -EINVAL;
@@ -61,7 +61,8 @@ static bool perf_probe_api(setup_probe_fn_t fn)
{
const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
struct perf_cpu_map *cpus;
- int cpu, ret, i = 0;
+ struct perf_cpu cpu;
+ int ret, i = 0;
cpus = perf_cpu_map__new(NULL);
if (!cpus)
@@ -136,15 +137,17 @@ bool perf_can_record_cpu_wide(void)
.exclude_kernel = 1,
};
struct perf_cpu_map *cpus;
- int cpu, fd;
+ struct perf_cpu cpu;
+ int fd;
cpus = perf_cpu_map__new(NULL);
if (!cpus)
return false;
+
cpu = cpus->map[0];
perf_cpu_map__put(cpus);
- fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+ fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0);
if (fd < 0)
return false;
close(fd);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 06a7461..a982e40 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
+#include <string.h>
#include "perf_regs.h"
#include "event.h"
@@ -20,6 +21,671 @@ uint64_t __weak arch__user_reg_mask(void)
}
#ifdef HAVE_PERF_REGS_SUPPORT
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+#include "../../arch/arm/include/uapi/asm/perf_regs.h"
+#include "../../arch/csky/include/uapi/asm/perf_regs.h"
+#include "../../arch/mips/include/uapi/asm/perf_regs.h"
+#include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
+#include "../../arch/riscv/include/uapi/asm/perf_regs.h"
+#include "../../arch/s390/include/uapi/asm/perf_regs.h"
+#include "../../arch/x86/include/uapi/asm/perf_regs.h"
+
+static const char *__perf_reg_name_arm64(int id)
+{
+ switch (id) {
+ case PERF_REG_ARM64_X0:
+ return "x0";
+ case PERF_REG_ARM64_X1:
+ return "x1";
+ case PERF_REG_ARM64_X2:
+ return "x2";
+ case PERF_REG_ARM64_X3:
+ return "x3";
+ case PERF_REG_ARM64_X4:
+ return "x4";
+ case PERF_REG_ARM64_X5:
+ return "x5";
+ case PERF_REG_ARM64_X6:
+ return "x6";
+ case PERF_REG_ARM64_X7:
+ return "x7";
+ case PERF_REG_ARM64_X8:
+ return "x8";
+ case PERF_REG_ARM64_X9:
+ return "x9";
+ case PERF_REG_ARM64_X10:
+ return "x10";
+ case PERF_REG_ARM64_X11:
+ return "x11";
+ case PERF_REG_ARM64_X12:
+ return "x12";
+ case PERF_REG_ARM64_X13:
+ return "x13";
+ case PERF_REG_ARM64_X14:
+ return "x14";
+ case PERF_REG_ARM64_X15:
+ return "x15";
+ case PERF_REG_ARM64_X16:
+ return "x16";
+ case PERF_REG_ARM64_X17:
+ return "x17";
+ case PERF_REG_ARM64_X18:
+ return "x18";
+ case PERF_REG_ARM64_X19:
+ return "x19";
+ case PERF_REG_ARM64_X20:
+ return "x20";
+ case PERF_REG_ARM64_X21:
+ return "x21";
+ case PERF_REG_ARM64_X22:
+ return "x22";
+ case PERF_REG_ARM64_X23:
+ return "x23";
+ case PERF_REG_ARM64_X24:
+ return "x24";
+ case PERF_REG_ARM64_X25:
+ return "x25";
+ case PERF_REG_ARM64_X26:
+ return "x26";
+ case PERF_REG_ARM64_X27:
+ return "x27";
+ case PERF_REG_ARM64_X28:
+ return "x28";
+ case PERF_REG_ARM64_X29:
+ return "x29";
+ case PERF_REG_ARM64_SP:
+ return "sp";
+ case PERF_REG_ARM64_LR:
+ return "lr";
+ case PERF_REG_ARM64_PC:
+ return "pc";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_arm(int id)
+{
+ switch (id) {
+ case PERF_REG_ARM_R0:
+ return "r0";
+ case PERF_REG_ARM_R1:
+ return "r1";
+ case PERF_REG_ARM_R2:
+ return "r2";
+ case PERF_REG_ARM_R3:
+ return "r3";
+ case PERF_REG_ARM_R4:
+ return "r4";
+ case PERF_REG_ARM_R5:
+ return "r5";
+ case PERF_REG_ARM_R6:
+ return "r6";
+ case PERF_REG_ARM_R7:
+ return "r7";
+ case PERF_REG_ARM_R8:
+ return "r8";
+ case PERF_REG_ARM_R9:
+ return "r9";
+ case PERF_REG_ARM_R10:
+ return "r10";
+ case PERF_REG_ARM_FP:
+ return "fp";
+ case PERF_REG_ARM_IP:
+ return "ip";
+ case PERF_REG_ARM_SP:
+ return "sp";
+ case PERF_REG_ARM_LR:
+ return "lr";
+ case PERF_REG_ARM_PC:
+ return "pc";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_csky(int id)
+{
+ switch (id) {
+ case PERF_REG_CSKY_A0:
+ return "a0";
+ case PERF_REG_CSKY_A1:
+ return "a1";
+ case PERF_REG_CSKY_A2:
+ return "a2";
+ case PERF_REG_CSKY_A3:
+ return "a3";
+ case PERF_REG_CSKY_REGS0:
+ return "regs0";
+ case PERF_REG_CSKY_REGS1:
+ return "regs1";
+ case PERF_REG_CSKY_REGS2:
+ return "regs2";
+ case PERF_REG_CSKY_REGS3:
+ return "regs3";
+ case PERF_REG_CSKY_REGS4:
+ return "regs4";
+ case PERF_REG_CSKY_REGS5:
+ return "regs5";
+ case PERF_REG_CSKY_REGS6:
+ return "regs6";
+ case PERF_REG_CSKY_REGS7:
+ return "regs7";
+ case PERF_REG_CSKY_REGS8:
+ return "regs8";
+ case PERF_REG_CSKY_REGS9:
+ return "regs9";
+ case PERF_REG_CSKY_SP:
+ return "sp";
+ case PERF_REG_CSKY_LR:
+ return "lr";
+ case PERF_REG_CSKY_PC:
+ return "pc";
+#if defined(__CSKYABIV2__)
+ case PERF_REG_CSKY_EXREGS0:
+ return "exregs0";
+ case PERF_REG_CSKY_EXREGS1:
+ return "exregs1";
+ case PERF_REG_CSKY_EXREGS2:
+ return "exregs2";
+ case PERF_REG_CSKY_EXREGS3:
+ return "exregs3";
+ case PERF_REG_CSKY_EXREGS4:
+ return "exregs4";
+ case PERF_REG_CSKY_EXREGS5:
+ return "exregs5";
+ case PERF_REG_CSKY_EXREGS6:
+ return "exregs6";
+ case PERF_REG_CSKY_EXREGS7:
+ return "exregs7";
+ case PERF_REG_CSKY_EXREGS8:
+ return "exregs8";
+ case PERF_REG_CSKY_EXREGS9:
+ return "exregs9";
+ case PERF_REG_CSKY_EXREGS10:
+ return "exregs10";
+ case PERF_REG_CSKY_EXREGS11:
+ return "exregs11";
+ case PERF_REG_CSKY_EXREGS12:
+ return "exregs12";
+ case PERF_REG_CSKY_EXREGS13:
+ return "exregs13";
+ case PERF_REG_CSKY_EXREGS14:
+ return "exregs14";
+ case PERF_REG_CSKY_TLS:
+ return "tls";
+ case PERF_REG_CSKY_HI:
+ return "hi";
+ case PERF_REG_CSKY_LO:
+ return "lo";
+#endif
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_mips(int id)
+{
+ switch (id) {
+ case PERF_REG_MIPS_PC:
+ return "PC";
+ case PERF_REG_MIPS_R1:
+ return "$1";
+ case PERF_REG_MIPS_R2:
+ return "$2";
+ case PERF_REG_MIPS_R3:
+ return "$3";
+ case PERF_REG_MIPS_R4:
+ return "$4";
+ case PERF_REG_MIPS_R5:
+ return "$5";
+ case PERF_REG_MIPS_R6:
+ return "$6";
+ case PERF_REG_MIPS_R7:
+ return "$7";
+ case PERF_REG_MIPS_R8:
+ return "$8";
+ case PERF_REG_MIPS_R9:
+ return "$9";
+ case PERF_REG_MIPS_R10:
+ return "$10";
+ case PERF_REG_MIPS_R11:
+ return "$11";
+ case PERF_REG_MIPS_R12:
+ return "$12";
+ case PERF_REG_MIPS_R13:
+ return "$13";
+ case PERF_REG_MIPS_R14:
+ return "$14";
+ case PERF_REG_MIPS_R15:
+ return "$15";
+ case PERF_REG_MIPS_R16:
+ return "$16";
+ case PERF_REG_MIPS_R17:
+ return "$17";
+ case PERF_REG_MIPS_R18:
+ return "$18";
+ case PERF_REG_MIPS_R19:
+ return "$19";
+ case PERF_REG_MIPS_R20:
+ return "$20";
+ case PERF_REG_MIPS_R21:
+ return "$21";
+ case PERF_REG_MIPS_R22:
+ return "$22";
+ case PERF_REG_MIPS_R23:
+ return "$23";
+ case PERF_REG_MIPS_R24:
+ return "$24";
+ case PERF_REG_MIPS_R25:
+ return "$25";
+ case PERF_REG_MIPS_R28:
+ return "$28";
+ case PERF_REG_MIPS_R29:
+ return "$29";
+ case PERF_REG_MIPS_R30:
+ return "$30";
+ case PERF_REG_MIPS_R31:
+ return "$31";
+ default:
+ break;
+ }
+ return NULL;
+}
+
+static const char *__perf_reg_name_powerpc(int id)
+{
+ switch (id) {
+ case PERF_REG_POWERPC_R0:
+ return "r0";
+ case PERF_REG_POWERPC_R1:
+ return "r1";
+ case PERF_REG_POWERPC_R2:
+ return "r2";
+ case PERF_REG_POWERPC_R3:
+ return "r3";
+ case PERF_REG_POWERPC_R4:
+ return "r4";
+ case PERF_REG_POWERPC_R5:
+ return "r5";
+ case PERF_REG_POWERPC_R6:
+ return "r6";
+ case PERF_REG_POWERPC_R7:
+ return "r7";
+ case PERF_REG_POWERPC_R8:
+ return "r8";
+ case PERF_REG_POWERPC_R9:
+ return "r9";
+ case PERF_REG_POWERPC_R10:
+ return "r10";
+ case PERF_REG_POWERPC_R11:
+ return "r11";
+ case PERF_REG_POWERPC_R12:
+ return "r12";
+ case PERF_REG_POWERPC_R13:
+ return "r13";
+ case PERF_REG_POWERPC_R14:
+ return "r14";
+ case PERF_REG_POWERPC_R15:
+ return "r15";
+ case PERF_REG_POWERPC_R16:
+ return "r16";
+ case PERF_REG_POWERPC_R17:
+ return "r17";
+ case PERF_REG_POWERPC_R18:
+ return "r18";
+ case PERF_REG_POWERPC_R19:
+ return "r19";
+ case PERF_REG_POWERPC_R20:
+ return "r20";
+ case PERF_REG_POWERPC_R21:
+ return "r21";
+ case PERF_REG_POWERPC_R22:
+ return "r22";
+ case PERF_REG_POWERPC_R23:
+ return "r23";
+ case PERF_REG_POWERPC_R24:
+ return "r24";
+ case PERF_REG_POWERPC_R25:
+ return "r25";
+ case PERF_REG_POWERPC_R26:
+ return "r26";
+ case PERF_REG_POWERPC_R27:
+ return "r27";
+ case PERF_REG_POWERPC_R28:
+ return "r28";
+ case PERF_REG_POWERPC_R29:
+ return "r29";
+ case PERF_REG_POWERPC_R30:
+ return "r30";
+ case PERF_REG_POWERPC_R31:
+ return "r31";
+ case PERF_REG_POWERPC_NIP:
+ return "nip";
+ case PERF_REG_POWERPC_MSR:
+ return "msr";
+ case PERF_REG_POWERPC_ORIG_R3:
+ return "orig_r3";
+ case PERF_REG_POWERPC_CTR:
+ return "ctr";
+ case PERF_REG_POWERPC_LINK:
+ return "link";
+ case PERF_REG_POWERPC_XER:
+ return "xer";
+ case PERF_REG_POWERPC_CCR:
+ return "ccr";
+ case PERF_REG_POWERPC_SOFTE:
+ return "softe";
+ case PERF_REG_POWERPC_TRAP:
+ return "trap";
+ case PERF_REG_POWERPC_DAR:
+ return "dar";
+ case PERF_REG_POWERPC_DSISR:
+ return "dsisr";
+ case PERF_REG_POWERPC_SIER:
+ return "sier";
+ case PERF_REG_POWERPC_MMCRA:
+ return "mmcra";
+ case PERF_REG_POWERPC_MMCR0:
+ return "mmcr0";
+ case PERF_REG_POWERPC_MMCR1:
+ return "mmcr1";
+ case PERF_REG_POWERPC_MMCR2:
+ return "mmcr2";
+ case PERF_REG_POWERPC_MMCR3:
+ return "mmcr3";
+ case PERF_REG_POWERPC_SIER2:
+ return "sier2";
+ case PERF_REG_POWERPC_SIER3:
+ return "sier3";
+ case PERF_REG_POWERPC_PMC1:
+ return "pmc1";
+ case PERF_REG_POWERPC_PMC2:
+ return "pmc2";
+ case PERF_REG_POWERPC_PMC3:
+ return "pmc3";
+ case PERF_REG_POWERPC_PMC4:
+ return "pmc4";
+ case PERF_REG_POWERPC_PMC5:
+ return "pmc5";
+ case PERF_REG_POWERPC_PMC6:
+ return "pmc6";
+ case PERF_REG_POWERPC_SDAR:
+ return "sdar";
+ case PERF_REG_POWERPC_SIAR:
+ return "siar";
+ default:
+ break;
+ }
+ return NULL;
+}
+
+static const char *__perf_reg_name_riscv(int id)
+{
+ switch (id) {
+ case PERF_REG_RISCV_PC:
+ return "pc";
+ case PERF_REG_RISCV_RA:
+ return "ra";
+ case PERF_REG_RISCV_SP:
+ return "sp";
+ case PERF_REG_RISCV_GP:
+ return "gp";
+ case PERF_REG_RISCV_TP:
+ return "tp";
+ case PERF_REG_RISCV_T0:
+ return "t0";
+ case PERF_REG_RISCV_T1:
+ return "t1";
+ case PERF_REG_RISCV_T2:
+ return "t2";
+ case PERF_REG_RISCV_S0:
+ return "s0";
+ case PERF_REG_RISCV_S1:
+ return "s1";
+ case PERF_REG_RISCV_A0:
+ return "a0";
+ case PERF_REG_RISCV_A1:
+ return "a1";
+ case PERF_REG_RISCV_A2:
+ return "a2";
+ case PERF_REG_RISCV_A3:
+ return "a3";
+ case PERF_REG_RISCV_A4:
+ return "a4";
+ case PERF_REG_RISCV_A5:
+ return "a5";
+ case PERF_REG_RISCV_A6:
+ return "a6";
+ case PERF_REG_RISCV_A7:
+ return "a7";
+ case PERF_REG_RISCV_S2:
+ return "s2";
+ case PERF_REG_RISCV_S3:
+ return "s3";
+ case PERF_REG_RISCV_S4:
+ return "s4";
+ case PERF_REG_RISCV_S5:
+ return "s5";
+ case PERF_REG_RISCV_S6:
+ return "s6";
+ case PERF_REG_RISCV_S7:
+ return "s7";
+ case PERF_REG_RISCV_S8:
+ return "s8";
+ case PERF_REG_RISCV_S9:
+ return "s9";
+ case PERF_REG_RISCV_S10:
+ return "s10";
+ case PERF_REG_RISCV_S11:
+ return "s11";
+ case PERF_REG_RISCV_T3:
+ return "t3";
+ case PERF_REG_RISCV_T4:
+ return "t4";
+ case PERF_REG_RISCV_T5:
+ return "t5";
+ case PERF_REG_RISCV_T6:
+ return "t6";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_s390(int id)
+{
+ switch (id) {
+ case PERF_REG_S390_R0:
+ return "R0";
+ case PERF_REG_S390_R1:
+ return "R1";
+ case PERF_REG_S390_R2:
+ return "R2";
+ case PERF_REG_S390_R3:
+ return "R3";
+ case PERF_REG_S390_R4:
+ return "R4";
+ case PERF_REG_S390_R5:
+ return "R5";
+ case PERF_REG_S390_R6:
+ return "R6";
+ case PERF_REG_S390_R7:
+ return "R7";
+ case PERF_REG_S390_R8:
+ return "R8";
+ case PERF_REG_S390_R9:
+ return "R9";
+ case PERF_REG_S390_R10:
+ return "R10";
+ case PERF_REG_S390_R11:
+ return "R11";
+ case PERF_REG_S390_R12:
+ return "R12";
+ case PERF_REG_S390_R13:
+ return "R13";
+ case PERF_REG_S390_R14:
+ return "R14";
+ case PERF_REG_S390_R15:
+ return "R15";
+ case PERF_REG_S390_FP0:
+ return "FP0";
+ case PERF_REG_S390_FP1:
+ return "FP1";
+ case PERF_REG_S390_FP2:
+ return "FP2";
+ case PERF_REG_S390_FP3:
+ return "FP3";
+ case PERF_REG_S390_FP4:
+ return "FP4";
+ case PERF_REG_S390_FP5:
+ return "FP5";
+ case PERF_REG_S390_FP6:
+ return "FP6";
+ case PERF_REG_S390_FP7:
+ return "FP7";
+ case PERF_REG_S390_FP8:
+ return "FP8";
+ case PERF_REG_S390_FP9:
+ return "FP9";
+ case PERF_REG_S390_FP10:
+ return "FP10";
+ case PERF_REG_S390_FP11:
+ return "FP11";
+ case PERF_REG_S390_FP12:
+ return "FP12";
+ case PERF_REG_S390_FP13:
+ return "FP13";
+ case PERF_REG_S390_FP14:
+ return "FP14";
+ case PERF_REG_S390_FP15:
+ return "FP15";
+ case PERF_REG_S390_MASK:
+ return "MASK";
+ case PERF_REG_S390_PC:
+ return "PC";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_x86(int id)
+{
+ switch (id) {
+ case PERF_REG_X86_AX:
+ return "AX";
+ case PERF_REG_X86_BX:
+ return "BX";
+ case PERF_REG_X86_CX:
+ return "CX";
+ case PERF_REG_X86_DX:
+ return "DX";
+ case PERF_REG_X86_SI:
+ return "SI";
+ case PERF_REG_X86_DI:
+ return "DI";
+ case PERF_REG_X86_BP:
+ return "BP";
+ case PERF_REG_X86_SP:
+ return "SP";
+ case PERF_REG_X86_IP:
+ return "IP";
+ case PERF_REG_X86_FLAGS:
+ return "FLAGS";
+ case PERF_REG_X86_CS:
+ return "CS";
+ case PERF_REG_X86_SS:
+ return "SS";
+ case PERF_REG_X86_DS:
+ return "DS";
+ case PERF_REG_X86_ES:
+ return "ES";
+ case PERF_REG_X86_FS:
+ return "FS";
+ case PERF_REG_X86_GS:
+ return "GS";
+ case PERF_REG_X86_R8:
+ return "R8";
+ case PERF_REG_X86_R9:
+ return "R9";
+ case PERF_REG_X86_R10:
+ return "R10";
+ case PERF_REG_X86_R11:
+ return "R11";
+ case PERF_REG_X86_R12:
+ return "R12";
+ case PERF_REG_X86_R13:
+ return "R13";
+ case PERF_REG_X86_R14:
+ return "R14";
+ case PERF_REG_X86_R15:
+ return "R15";
+
+#define XMM(x) \
+ case PERF_REG_X86_XMM ## x: \
+ case PERF_REG_X86_XMM ## x + 1: \
+ return "XMM" #x;
+ XMM(0)
+ XMM(1)
+ XMM(2)
+ XMM(3)
+ XMM(4)
+ XMM(5)
+ XMM(6)
+ XMM(7)
+ XMM(8)
+ XMM(9)
+ XMM(10)
+ XMM(11)
+ XMM(12)
+ XMM(13)
+ XMM(14)
+ XMM(15)
+#undef XMM
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+const char *perf_reg_name(int id, const char *arch)
+{
+ const char *reg_name = NULL;
+
+ if (!strcmp(arch, "csky"))
+ reg_name = __perf_reg_name_csky(id);
+ else if (!strcmp(arch, "mips"))
+ reg_name = __perf_reg_name_mips(id);
+ else if (!strcmp(arch, "powerpc"))
+ reg_name = __perf_reg_name_powerpc(id);
+ else if (!strcmp(arch, "riscv"))
+ reg_name = __perf_reg_name_riscv(id);
+ else if (!strcmp(arch, "s390"))
+ reg_name = __perf_reg_name_s390(id);
+ else if (!strcmp(arch, "x86"))
+ reg_name = __perf_reg_name_x86(id);
+ else if (!strcmp(arch, "arm"))
+ reg_name = __perf_reg_name_arm(id);
+ else if (!strcmp(arch, "arm64"))
+ reg_name = __perf_reg_name_arm64(id);
+
+ return reg_name ?: "unknown";
+}
+
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
{
int i, idx = 0;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index eeac181..ce1127a 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -11,8 +11,11 @@ struct sample_reg {
const char *name;
uint64_t mask;
};
-#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
-#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
+
+#define SMPL_REG_MASK(b) (1ULL << (b))
+#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) }
+#define SMPL_REG2_MASK(b) (3ULL << (b))
+#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) }
#define SMPL_REG_END { .name = NULL }
enum {
@@ -31,22 +34,16 @@ extern const struct sample_reg sample_reg_masks[];
#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
+const char *perf_reg_name(int id, const char *arch);
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
-static inline const char *perf_reg_name(int id)
-{
- const char *reg_name = __perf_reg_name(id);
-
- return reg_name ?: "unknown";
-}
-
#else
#define PERF_REGS_MASK 0
#define PERF_REGS_MAX 0
#define DWARF_MINIMAL_REGS PERF_REGS_MASK
-static inline const char *perf_reg_name(int id __maybe_unused)
+static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)
{
return "unknown";
}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 82c7f03..f3e5131 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1059,7 +1059,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu)
for (i = 0; i < evlist->core.nr_mmaps; i++) {
struct mmap *md = &evlist->mmap[i];
- if (md->core.cpu == cpu)
+ if (md->core.cpu.cpu == cpu)
return md;
}
@@ -1445,7 +1445,7 @@ PyMODINIT_FUNC PyInit_perf(void)
* Dummy, to avoid dragging all the test_attr infrastructure in the python
* binding.
*/
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
}
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index bff669b..20461f1 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call
if (opts->group)
evlist__set_leader(evlist);
- if (evlist->core.cpus->map[0] < 0)
+ if (evlist->core.cpus->map[0].cpu < 0)
opts->no_inherit = true;
use_comm_exec = perf_can_comm_exec();
@@ -229,7 +229,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
{
struct evlist *temp_evlist;
struct evsel *evsel;
- int err, fd, cpu;
+ int err, fd;
+ struct perf_cpu cpu = { .cpu = 0 };
bool ret = false;
pid_t pid = -1;
@@ -246,14 +247,16 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
- cpu = cpus ? cpus->map[0] : 0;
+ if (cpus)
+ cpu = cpus->map[0];
+
perf_cpu_map__put(cpus);
} else {
cpu = evlist->core.cpus->map[0];
}
while (1) {
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1,
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1,
perf_event_open_cloexec_flag());
if (fd < 0) {
if (pid == -1 && errno == EACCES) {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d1f1501..f5ad0e6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -36,6 +36,7 @@
#include "../debug.h"
#include "../dso.h"
#include "../callchain.h"
+#include "../env.h"
#include "../evsel.h"
#include "../event.h"
#include "../thread.h"
@@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict,
_PyUnicode_FromString(decode));
}
-static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
+static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size)
{
unsigned int i = 0, r;
int printed = 0;
@@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
printed += scnprintf(bf + printed, size - printed,
"%5s:0x%" PRIx64 " ",
- perf_reg_name(r), val);
+ perf_reg_name(r, arch), val);
}
}
@@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict,
struct evsel *evsel)
{
struct perf_event_attr *attr = &evsel->core.attr;
+ const char *arch = perf_env__arch(evsel__env(evsel));
/*
* Here value 28 is a constant size which can be used to print
@@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict,
int size = __sw_hweight64(attr->sample_regs_intr) * 28;
char bf[size];
- regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
+ regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf));
pydict_set_item_string_decref(dict, "iregs",
_PyUnicode_FromString(bf));
- regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf));
+ regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf));
pydict_set_item_string_decref(dict, "uregs",
_PyUnicode_FromString(bf));
@@ -1555,7 +1557,7 @@ static void get_handler_name(char *str, size_t size,
}
static void
-process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
+process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp,
struct perf_counts_values *count)
{
PyObject *handler, *t;
@@ -1575,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
return;
}
- PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu));
PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
tuple_set_u64(t, n++, tstamp);
@@ -1599,7 +1601,7 @@ static void python_process_stat(struct perf_stat_config *config,
int cpu, thread;
if (config->aggr_mode == AGGR_GLOBAL) {
- process_stat(counter, -1, -1, tstamp,
+ process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
&counter->counts->aggr);
return;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d8857d1..f19348d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
#include "map_symbol.h"
#include "branch.h"
#include "debug.h"
+#include "env.h"
#include "evlist.h"
#include "evsel.h"
#include "memswap.h"
@@ -1168,7 +1169,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
}
}
-static void regs_dump__printf(u64 mask, u64 *regs)
+static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
{
unsigned rid, i = 0;
@@ -1176,7 +1177,7 @@ static void regs_dump__printf(u64 mask, u64 *regs)
u64 val = regs[i++];
printf(".... %-5s 0x%016" PRIx64 "\n",
- perf_reg_name(rid), val);
+ perf_reg_name(rid, arch), val);
}
}
@@ -1194,7 +1195,7 @@ static inline const char *regs_dump_abi(struct regs_dump *d)
return regs_abi[d->abi];
}
-static void regs__printf(const char *type, struct regs_dump *regs)
+static void regs__printf(const char *type, struct regs_dump *regs, const char *arch)
{
u64 mask = regs->mask;
@@ -1203,23 +1204,23 @@ static void regs__printf(const char *type, struct regs_dump *regs)
mask,
regs_dump_abi(regs));
- regs_dump__printf(mask, regs->regs);
+ regs_dump__printf(mask, regs->regs, arch);
}
-static void regs_user__printf(struct perf_sample *sample)
+static void regs_user__printf(struct perf_sample *sample, const char *arch)
{
struct regs_dump *user_regs = &sample->user_regs;
if (user_regs->regs)
- regs__printf("user", user_regs);
+ regs__printf("user", user_regs, arch);
}
-static void regs_intr__printf(struct perf_sample *sample)
+static void regs_intr__printf(struct perf_sample *sample, const char *arch)
{
struct regs_dump *intr_regs = &sample->intr_regs;
if (intr_regs->regs)
- regs__printf("intr", intr_regs);
+ regs__printf("intr", intr_regs, arch);
}
static void stack_user__printf(struct stack_dump *dump)
@@ -1304,7 +1305,7 @@ char *get_page_size_name(u64 size, char *str)
}
static void dump_sample(struct evsel *evsel, union perf_event *event,
- struct perf_sample *sample)
+ struct perf_sample *sample, const char *arch)
{
u64 sample_type;
char str[PAGE_SIZE_NAME_LEN];
@@ -1325,10 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
if (sample_type & PERF_SAMPLE_REGS_USER)
- regs_user__printf(sample);
+ regs_user__printf(sample, arch);
if (sample_type & PERF_SAMPLE_REGS_INTR)
- regs_intr__printf(sample);
+ regs_intr__printf(sample, arch);
if (sample_type & PERF_SAMPLE_STACK_USER)
stack_user__printf(&sample->user_stack);
@@ -1502,7 +1503,7 @@ static int machines__deliver_event(struct machines *machines,
++evlist->stats.nr_unknown_id;
return 0;
}
- dump_sample(evsel, event, sample);
+ dump_sample(evsel, event, sample, perf_env__arch(machine->env));
if (machine == NULL) {
++evlist->stats.nr_unprocessable_samples;
return 0;
@@ -2537,15 +2538,15 @@ int perf_session__cpu_bitmap(struct perf_session *session,
}
for (i = 0; i < map->nr; i++) {
- int cpu = map->map[i];
+ struct perf_cpu cpu = map->map[i];
- if (cpu >= nr_cpus) {
+ if (cpu.cpu >= nr_cpus) {
pr_err("Requested CPU %d too large. "
- "Consider raising MAX_NR_CPUS\n", cpu);
+ "Consider raising MAX_NR_CPUS\n", cpu.cpu);
goto out_delete_map;
}
- set_bit(cpu, cpu_bitmap);
+ set_bit(cpu.cpu, cpu_bitmap);
}
err = 0;
@@ -2597,7 +2598,7 @@ int perf_event__process_id_index(struct perf_session *session,
if (!sid)
return -ENOENT;
sid->idx = e->idx;
- sid->cpu = e->cpu;
+ sid->cpu.cpu = e->cpu;
sid->tid = e->tid;
}
return 0;
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 34f1b1b..2b0a36e 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -5,6 +5,56 @@
#include "api/fs/fs.h"
#include "smt.h"
+/**
+ * hweight_str - Returns the number of bits set in str. Stops at first non-hex
+ * or ',' character.
+ */
+static int hweight_str(char *str)
+{
+ int result = 0;
+
+ while (*str) {
+ switch (*str++) {
+ case '0':
+ case ',':
+ break;
+ case '1':
+ case '2':
+ case '4':
+ case '8':
+ result++;
+ break;
+ case '3':
+ case '5':
+ case '6':
+ case '9':
+ case 'a':
+ case 'A':
+ case 'c':
+ case 'C':
+ result += 2;
+ break;
+ case '7':
+ case 'b':
+ case 'B':
+ case 'd':
+ case 'D':
+ case 'e':
+ case 'E':
+ result += 3;
+ break;
+ case 'f':
+ case 'F':
+ result += 4;
+ break;
+ default:
+ goto done;
+ }
+ }
+done:
+ return result;
+}
+
int smt_on(void)
{
static bool cached;
@@ -15,9 +65,12 @@ int smt_on(void)
if (cached)
return cached_result;
- if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
- goto done;
+ if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) {
+ cached = true;
+ return cached_result;
+ }
+ cached_result = 0;
ncpu = sysconf(_SC_NPROCESSORS_CONF);
for (cpu = 0; cpu < ncpu; cpu++) {
unsigned long long siblings;
@@ -26,27 +79,21 @@ int smt_on(void)
char fn[256];
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+ "devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0) {
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/thread_siblings",
- cpu);
+ "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0)
continue;
}
/* Entry is hex, but does not have 0x, so need custom parser */
- siblings = strtoull(str, NULL, 16);
+ siblings = hweight_str(str);
free(str);
- if (hweight64(siblings) > 1) {
+ if (siblings > 1) {
cached_result = 1;
- cached = true;
break;
}
}
- if (!cached) {
- cached_result = 0;
-done:
- cached = true;
- }
+ cached = true;
return cached_result;
}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d9a106f..cfba8c3 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault";
const char *parent_pattern = default_parent_pattern;
const char *default_sort_order = "comm,dso,symbol";
const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
+const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
const char default_top_sort_order[] = "dso,symbol";
const char default_diff_sort_order[] = "dso,symbol";
const char default_tracepoint_sort_order[] = "trace";
@@ -46,8 +46,8 @@ const char *field_order;
regex_t ignore_callees_regex;
int have_ignore_callees = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
-const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
-const char *arch_specific_sort_keys[] = {"p_stage_cyc"};
+static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
+static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
/*
* Replaces all occurrences of a char used with the:
@@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
};
static int64_t
-sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->p_stage_cyc - right->p_stage_cyc;
}
+static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*u", width,
+ he->p_stage_cyc * he->stat.nr_events);
+}
+
+
static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
}
-struct sort_entry sort_p_stage_cyc = {
- .se_header = "Pipeline Stage Cycle",
- .se_cmp = sort__global_p_stage_cyc_cmp,
+struct sort_entry sort_local_p_stage_cyc = {
+ .se_header = "Local Pipeline Stage Cycle",
+ .se_cmp = sort__p_stage_cyc_cmp,
.se_snprintf = hist_entry__p_stage_cyc_snprintf,
- .se_width_idx = HISTC_P_STAGE_CYC,
+ .se_width_idx = HISTC_LOCAL_P_STAGE_CYC,
+};
+
+struct sort_entry sort_global_p_stage_cyc = {
+ .se_header = "Pipeline Stage Cycle",
+ .se_cmp = sort__p_stage_cyc_cmp,
+ .se_snprintf = hist_entry__global_p_stage_cyc_snprintf,
+ .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC,
};
struct sort_entry sort_mem_daddr_sym = {
@@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
- DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
+ DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
+ DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
};
#undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7b71455..f994261 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -235,7 +235,8 @@ enum sort_type {
SORT_CODE_PAGE_SIZE,
SORT_LOCAL_INS_LAT,
SORT_GLOBAL_INS_LAT,
- SORT_PIPELINE_STAGE_CYC,
+ SORT_LOCAL_PIPELINE_STAGE_CYC,
+ SORT_GLOBAL_PIPELINE_STAGE_CYC,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 5886010..5db83e5 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -4,6 +4,7 @@
#include <linux/string.h>
#include <linux/time64.h>
#include <math.h>
+#include <perf/cpumap.h>
#include "color.h"
#include "counts.h"
#include "evlist.h"
@@ -120,11 +121,10 @@ static void aggr_printout(struct perf_stat_config *config,
id.die,
config->csv_output ? 0 : -3,
id.core, config->csv_sep);
- } else if (id.core > -1) {
+ } else if (id.cpu.cpu > -1) {
fprintf(config->output, "CPU%*d%s",
config->csv_output ? 0 : -7,
- evsel__cpus(evsel)->map[id.core],
- config->csv_sep);
+ id.cpu.cpu, config->csv_sep);
}
break;
case AGGR_THREAD:
@@ -327,26 +327,24 @@ static void print_metric_header(struct perf_stat_config *config,
fprintf(os->fh, "%*s ", config->metric_only_len, unit);
}
-static int first_shadow_cpu(struct perf_stat_config *config,
- struct evsel *evsel, struct aggr_cpu_id id)
+static int first_shadow_cpu_map_idx(struct perf_stat_config *config,
+ struct evsel *evsel, const struct aggr_cpu_id *id)
{
- struct evlist *evlist = evsel->evlist;
- int i;
+ struct perf_cpu_map *cpus = evsel__cpus(evsel);
+ struct perf_cpu cpu;
+ int idx;
if (config->aggr_mode == AGGR_NONE)
- return id.core;
+ return perf_cpu_map__idx(cpus, id->cpu);
if (!config->aggr_get_id)
return 0;
- for (i = 0; i < evsel__nr_cpus(evsel); i++) {
- int cpu2 = evsel__cpus(evsel)->map[i];
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu);
- if (cpu_map__compare_aggr_cpu_id(
- config->aggr_get_id(config, evlist->core.cpus, cpu2),
- id)) {
- return cpu2;
- }
+ if (aggr_cpu_id__equal(&cpu_id, id))
+ return idx;
}
return 0;
}
@@ -505,7 +503,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
}
perf_stat__print_shadow_stats(config, counter, uval,
- first_shadow_cpu(config, counter, id),
+ first_shadow_cpu_map_idx(config, counter, &id),
&out, &config->metric_events, st);
if (!config->csv_output && !config->metric_only) {
print_noise(config, counter, noise);
@@ -516,23 +514,26 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
static void aggr_update_shadow(struct perf_stat_config *config,
struct evlist *evlist)
{
- int cpu, s;
+ int idx, s;
+ struct perf_cpu cpu;
struct aggr_cpu_id s2, id;
u64 val;
struct evsel *counter;
+ struct perf_cpu_map *cpus;
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
evlist__for_each_entry(evlist, counter) {
+ cpus = evsel__cpus(counter);
val = 0;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
- s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
- if (!cpu_map__compare_aggr_cpu_id(s2, id))
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ s2 = config->aggr_get_id(config, cpu);
+ if (!aggr_cpu_id__equal(&s2, &id))
continue;
- val += perf_counts(counter->counts, cpu, 0)->val;
+ val += perf_counts(counter->counts, idx, 0)->val;
}
perf_stat__update_shadow_stats(counter, val,
- first_shadow_cpu(config, counter, id),
+ first_shadow_cpu_map_idx(config, counter, &id),
&rt_stat);
}
}
@@ -627,25 +628,28 @@ struct aggr_data {
u64 ena, run, val;
struct aggr_cpu_id id;
int nr;
- int cpu;
+ int cpu_map_idx;
};
static void aggr_cb(struct perf_stat_config *config,
struct evsel *counter, void *data, bool first)
{
struct aggr_data *ad = data;
- int cpu;
+ int idx;
+ struct perf_cpu cpu;
+ struct perf_cpu_map *cpus;
struct aggr_cpu_id s2;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
+ cpus = evsel__cpus(counter);
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct perf_counts_values *counts;
- s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
- if (!cpu_map__compare_aggr_cpu_id(s2, ad->id))
+ s2 = config->aggr_get_id(config, cpu);
+ if (!aggr_cpu_id__equal(&s2, &ad->id))
continue;
if (first)
ad->nr++;
- counts = perf_counts(counter->counts, cpu, 0);
+ counts = perf_counts(counter->counts, idx, 0);
/*
* When any result is bad, make them all to give
* consistent output in interval mode.
@@ -665,7 +669,7 @@ static void aggr_cb(struct perf_stat_config *config,
static void print_counter_aggrdata(struct perf_stat_config *config,
struct evsel *counter, int s,
char *prefix, bool metric_only,
- bool *first, int cpu)
+ bool *first, struct perf_cpu cpu)
{
struct aggr_data ad;
FILE *output = config->output;
@@ -695,10 +699,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- if (cpu != -1) {
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
- }
+ if (cpu.cpu != -1)
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
+
printout(config, id, nr, counter, uval,
prefix, run, ena, 1.0, &rt_stat);
if (!metric_only)
@@ -731,8 +734,8 @@ static void print_aggr(struct perf_stat_config *config,
first = true;
evlist__for_each_entry(evlist, counter) {
print_counter_aggrdata(config, counter, s,
- prefix, metric_only,
- &first, -1);
+ prefix, metric_only,
+ &first, (struct perf_cpu){ .cpu = -1 });
}
if (metric_only)
fputc('\n', output);
@@ -778,7 +781,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
continue;
buf[i].counter = counter;
- buf[i].id = cpu_map__empty_aggr_cpu_id();
+ buf[i].id = aggr_cpu_id__empty();
buf[i].id.thread = thread;
buf[i].uval = uval;
buf[i].val = val;
@@ -866,7 +869,7 @@ static void print_counter_aggr(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
- printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running,
+ printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running,
cd.avg_enabled, cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
@@ -878,9 +881,9 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused,
{
struct aggr_data *ad = data;
- ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
- ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
- ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+ ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val;
+ ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena;
+ ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run;
}
/*
@@ -893,11 +896,12 @@ static void print_counter(struct perf_stat_config *config,
FILE *output = config->output;
u64 ena, run, val;
double uval;
- int cpu;
+ int idx;
+ struct perf_cpu cpu;
struct aggr_cpu_id id;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
- struct aggr_data ad = { .cpu = cpu };
+ perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
+ struct aggr_data ad = { .cpu_map_idx = idx };
if (!collect_data(config, counter, counter_cb, &ad))
return;
@@ -909,8 +913,7 @@ static void print_counter(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
@@ -922,29 +925,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
struct evlist *evlist,
char *prefix)
{
- int cpu;
- int nrcpus = 0;
- struct evsel *counter;
- u64 ena, run, val;
- double uval;
- struct aggr_cpu_id id;
+ int all_idx;
+ struct perf_cpu cpu;
- nrcpus = evlist->core.cpus->nr;
- for (cpu = 0; cpu < nrcpus; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) {
+ struct evsel *counter;
bool first = true;
if (prefix)
fputs(prefix, config->output);
evlist__for_each_entry(evlist, counter) {
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
+ u64 ena, run, val;
+ double uval;
+ struct aggr_cpu_id id;
+ int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
+
+ if (counter_idx < 0)
+ continue;
+
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
aggr_printout(config, counter, id, 0);
first = false;
}
- val = perf_counts(counter->counts, cpu, 0)->val;
- ena = perf_counts(counter->counts, cpu, 0)->ena;
- run = perf_counts(counter->counts, cpu, 0)->run;
+ val = perf_counts(counter->counts, counter_idx, 0)->val;
+ ena = perf_counts(counter->counts, counter_idx, 0)->ena;
+ run = perf_counts(counter->counts, counter_idx, 0)->run;
uval = val * counter->scale;
printout(config, id, 0, counter, uval, prefix,
@@ -1208,19 +1214,23 @@ static void print_percore_thread(struct perf_stat_config *config,
{
int s;
struct aggr_cpu_id s2, id;
+ struct perf_cpu_map *cpus;
bool first = true;
+ int idx;
+ struct perf_cpu cpu;
- for (int i = 0; i < evsel__nr_cpus(counter); i++) {
- s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+ cpus = evsel__cpus(counter);
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ s2 = config->aggr_get_id(config, cpu);
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
- if (cpu_map__compare_aggr_cpu_id(s2, id))
+ if (aggr_cpu_id__equal(&s2, &id))
break;
}
print_counter_aggrdata(config, counter, s,
prefix, false,
- &first, i);
+ &first, cpu);
}
}
@@ -1243,8 +1253,8 @@ static void print_percore(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
print_counter_aggrdata(config, counter, s,
- prefix, metric_only,
- &first, -1);
+ prefix, metric_only,
+ &first, (struct perf_cpu){ .cpu = -1 });
}
if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 5c7308e..10af780 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -32,7 +32,7 @@ struct saved_value {
struct evsel *evsel;
enum stat_type type;
int ctx;
- int cpu;
+ int cpu_map_idx;
struct cgroup *cgrp;
struct runtime_stat *stat;
struct stats stats;
@@ -47,8 +47,8 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
rb_node);
const struct saved_value *b = entry;
- if (a->cpu != b->cpu)
- return a->cpu - b->cpu;
+ if (a->cpu_map_idx != b->cpu_map_idx)
+ return a->cpu_map_idx - b->cpu_map_idx;
/*
* Previously the rbtree was used to link generic metrics.
@@ -105,7 +105,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused,
}
static struct saved_value *saved_value_lookup(struct evsel *evsel,
- int cpu,
+ int cpu_map_idx,
bool create,
enum stat_type type,
int ctx,
@@ -115,7 +115,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
struct rblist *rblist;
struct rb_node *nd;
struct saved_value dm = {
- .cpu = cpu,
+ .cpu_map_idx = cpu_map_idx,
.evsel = evsel,
.type = type,
.ctx = ctx,
@@ -213,10 +213,10 @@ struct runtime_stat_data {
static void update_runtime_stat(struct runtime_stat *st,
enum stat_type type,
- int cpu, u64 count,
+ int cpu_map_idx, u64 count,
struct runtime_stat_data *rsd)
{
- struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+ struct saved_value *v = saved_value_lookup(NULL, cpu_map_idx, true, type,
rsd->ctx, st, rsd->cgrp);
if (v)
@@ -229,7 +229,7 @@ static void update_runtime_stat(struct runtime_stat *st,
* instruction rates, etc:
*/
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
- int cpu, struct runtime_stat *st)
+ int cpu_map_idx, struct runtime_stat *st)
{
u64 count_ns = count;
struct saved_value *v;
@@ -241,88 +241,88 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
count *= counter->scale;
if (evsel__is_clock(counter))
- update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
+ update_runtime_stat(st, STAT_NSECS, cpu_map_idx, count_ns, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CYCLES, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_TRANSACTION, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_ELISION, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS))
update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT))
update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_BRANCHES, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CACHEREFS, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_L1_DCACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_L1_ICACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_LL_CACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_DTLB_CACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_ITLB_CACHE, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_SMI_NUM, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, APERF))
- update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_APERF, cpu_map_idx, count, &rsd);
if (counter->collect_stat) {
- v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+ v = saved_value_lookup(counter, cpu_map_idx, true, STAT_NONE, 0, st,
rsd.cgrp);
update_stats(&v->stats, count);
if (counter->metric_leader)
v->metric_total += count;
} else if (counter->metric_leader) {
v = saved_value_lookup(counter->metric_leader,
- cpu, true, STAT_NONE, 0, st, rsd.cgrp);
+ cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp);
v->metric_total += count;
v->metric_other++;
}
@@ -464,12 +464,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
}
static double runtime_stat_avg(struct runtime_stat *st,
- enum stat_type type, int cpu,
+ enum stat_type type, int cpu_map_idx,
struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+ v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -477,12 +477,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
}
static double runtime_stat_n(struct runtime_stat *st,
- enum stat_type type, int cpu,
+ enum stat_type type, int cpu_map_idx,
struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+ v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -490,7 +490,7 @@ static double runtime_stat_n(struct runtime_stat *st,
}
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -498,7 +498,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -513,7 +513,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
}
static void print_stalled_cycles_backend(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -521,7 +521,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -532,7 +532,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
}
static void print_branch_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -540,7 +540,7 @@ static void print_branch_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_BRANCHES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -551,7 +551,7 @@ static void print_branch_misses(struct perf_stat_config *config,
}
static void print_l1_dcache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -559,7 +559,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -570,7 +570,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
}
static void print_l1_icache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -578,7 +578,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -588,7 +588,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -596,7 +596,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -606,7 +606,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -614,7 +614,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -624,7 +624,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
}
static void print_ll_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -632,7 +632,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_LL_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -690,61 +690,61 @@ static double sanitize_val(double x)
return x;
}
-static double td_total_slots(int cpu, struct runtime_stat *st,
+static double td_total_slots(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
+ return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu_map_idx, rsd);
}
-static double td_bad_spec(int cpu, struct runtime_stat *st,
+static double td_bad_spec(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double bad_spec = 0;
double total_slots;
double total;
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu_map_idx, rsd) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu_map_idx, rsd) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu_map_idx, rsd);
- total_slots = td_total_slots(cpu, st, rsd);
+ total_slots = td_total_slots(cpu_map_idx, st, rsd);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int cpu, struct runtime_stat *st,
+static double td_retiring(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double retiring = 0;
- double total_slots = td_total_slots(cpu, st, rsd);
+ double total_slots = td_total_slots(cpu_map_idx, st, rsd);
double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- cpu, rsd);
+ cpu_map_idx, rsd);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int cpu, struct runtime_stat *st,
+static double td_fe_bound(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double fe_bound = 0;
- double total_slots = td_total_slots(cpu, st, rsd);
+ double total_slots = td_total_slots(cpu_map_idx, st, rsd);
double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- cpu, rsd);
+ cpu_map_idx, rsd);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int cpu, struct runtime_stat *st,
+static double td_be_bound(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
- double sum = (td_fe_bound(cpu, st, rsd) +
- td_bad_spec(cpu, st, rsd) +
- td_retiring(cpu, st, rsd));
+ double sum = (td_fe_bound(cpu_map_idx, st, rsd) +
+ td_bad_spec(cpu_map_idx, st, rsd) +
+ td_retiring(cpu_map_idx, st, rsd));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
@@ -755,15 +755,15 @@ static double td_be_bound(int cpu, struct runtime_stat *st,
* the ratios we need to recreate the sum.
*/
-static double td_metric_ratio(int cpu, enum stat_type type,
+static double td_metric_ratio(int cpu_map_idx, enum stat_type type,
struct runtime_stat *stat,
struct runtime_stat_data *rsd)
{
- double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
- double d = runtime_stat_avg(stat, type, cpu, rsd);
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd);
+ double d = runtime_stat_avg(stat, type, cpu_map_idx, rsd);
if (sum)
return d / sum;
@@ -775,23 +775,23 @@ static double td_metric_ratio(int cpu, enum stat_type type,
* We allow two missing.
*/
-static bool full_td(int cpu, struct runtime_stat *stat,
+static bool full_td(int cpu_map_idx, struct runtime_stat *stat,
struct runtime_stat_data *rsd)
{
int c = 0;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd) > 0)
c++;
return c >= 2;
}
-static void print_smi_cost(struct perf_stat_config *config, int cpu,
+static void print_smi_cost(struct perf_stat_config *config, int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -799,9 +799,9 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
double smi_num, aperf, cycles, cost = 0.0;
const char *color = NULL;
- smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
- aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
- cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu_map_idx, rsd);
+ aperf = runtime_stat_avg(st, STAT_APERF, cpu_map_idx, rsd);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if ((cycles == 0) || (aperf == 0))
return;
@@ -818,7 +818,7 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
static int prepare_metric(struct evsel **metric_events,
struct metric_ref *metric_refs,
struct expr_parse_ctx *pctx,
- int cpu,
+ int cpu_map_idx,
struct runtime_stat *st)
{
double scale;
@@ -836,7 +836,7 @@ static int prepare_metric(struct evsel **metric_events,
scale = 1e-9;
source_count = 1;
} else {
- v = saved_value_lookup(metric_events[i], cpu, false,
+ v = saved_value_lookup(metric_events[i], cpu_map_idx, false,
STAT_NONE, 0, st,
metric_events[i]->cgrp);
if (!v)
@@ -874,7 +874,7 @@ static void generic_metric(struct perf_stat_config *config,
const char *metric_name,
const char *metric_unit,
int runtime,
- int cpu,
+ int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
{
@@ -889,7 +889,7 @@ static void generic_metric(struct perf_stat_config *config,
return;
pctx->runtime = runtime;
- i = prepare_metric(metric_events, metric_refs, pctx, cpu, st);
+ i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st);
if (i < 0) {
expr__ctx_free(pctx);
return;
@@ -934,7 +934,7 @@ static void generic_metric(struct perf_stat_config *config,
expr__ctx_free(pctx);
}
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st)
{
struct expr_parse_ctx *pctx;
double ratio = 0.0;
@@ -943,7 +943,7 @@ double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_sta
if (!pctx)
return NAN;
- if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0)
+ if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu_map_idx, st) < 0)
goto out;
if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -956,7 +956,7 @@ double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_sta
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct evsel *evsel,
- double avg, int cpu,
+ double avg, int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
struct runtime_stat *st)
@@ -975,7 +975,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (config->iostat_run) {
iostat_print_metric(config, evsel, out);
} else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
if (total) {
ratio = avg / total;
@@ -985,11 +985,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu_map_idx, &rsd);
total = max(total, runtime_stat_avg(st,
STAT_STALLED_CYCLES_BACK,
- cpu, &rsd));
+ cpu_map_idx, &rsd));
if (total && avg) {
out->new_line(config, ctxp);
@@ -999,8 +999,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
ratio);
}
} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
- print_branch_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_BRANCHES, cpu_map_idx, &rsd) != 0)
+ print_branch_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -1009,8 +1009,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
- print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_L1_DCACHE, cpu_map_idx, &rsd) != 0)
+ print_l1_dcache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
@@ -1019,8 +1019,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
- print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_L1_ICACHE, cpu_map_idx, &rsd) != 0)
+ print_l1_icache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
@@ -1029,8 +1029,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
- print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu_map_idx, &rsd) != 0)
+ print_dtlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
@@ -1039,8 +1039,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
- print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu_map_idx, &rsd) != 0)
+ print_itlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
@@ -1049,27 +1049,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
- print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_LL_CACHE, cpu_map_idx, &rsd) != 0)
+ print_ll_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CACHEREFS, cpu_map_idx, &rsd);
if (total)
ratio = avg * 100 / total;
- if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
+ if (runtime_stat_n(st, STAT_CACHEREFS, cpu_map_idx, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
+ print_stalled_cycles_frontend(config, cpu_map_idx, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
+ print_stalled_cycles_backend(config, cpu_map_idx, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
if (total) {
ratio = avg / total;
@@ -1078,7 +1078,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
if (total)
print_metric(config, ctxp, NULL,
@@ -1088,8 +1088,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
- total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (total2 < avg)
total2 = avg;
@@ -1099,19 +1099,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (avg)
ratio = total / avg;
- if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
+ if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (avg)
ratio = total / avg;
@@ -1124,28 +1124,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(cpu, st, &rsd);
+ double fe_bound = td_fe_bound(cpu_map_idx, st, &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(cpu, st, &rsd);
+ double retiring = td_retiring(cpu_map_idx, st, &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(cpu, st, &rsd);
+ double bad_spec = td_bad_spec(cpu_map_idx, st, &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(cpu, st, &rsd);
+ double be_bound = td_be_bound(cpu_map_idx, st, &rsd);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -1158,14 +1158,14 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(cpu, st, &rsd) > 0)
+ if (td_total_slots(cpu_map_idx, st, &rsd) > 0)
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
- full_td(cpu, st, &rsd)) {
- double retiring = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double retiring = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_RETIRING, st,
&rsd);
if (retiring > 0.7)
@@ -1173,8 +1173,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
- full_td(cpu, st, &rsd)) {
- double fe_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double fe_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FE_BOUND, st,
&rsd);
if (fe_bound > 0.2)
@@ -1182,8 +1182,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
- full_td(cpu, st, &rsd)) {
- double be_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double be_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BE_BOUND, st,
&rsd);
if (be_bound > 0.2)
@@ -1191,8 +1191,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
- full_td(cpu, st, &rsd)) {
- double bad_spec = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double bad_spec = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BAD_SPEC, st,
&rsd);
if (bad_spec > 0.1)
@@ -1200,11 +1200,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double retiring = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double retiring = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_RETIRING, st,
&rsd);
- double heavy_ops = td_metric_ratio(cpu,
+ double heavy_ops = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_HEAVY_OPS, st,
&rsd);
double light_ops = retiring - heavy_ops;
@@ -1220,11 +1220,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "light operations",
light_ops * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double bad_spec = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double bad_spec = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BAD_SPEC, st,
&rsd);
- double br_mis = td_metric_ratio(cpu,
+ double br_mis = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BR_MISPREDICT, st,
&rsd);
double m_clears = bad_spec - br_mis;
@@ -1240,11 +1240,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
m_clears * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double fe_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double fe_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FE_BOUND, st,
&rsd);
- double fetch_lat = td_metric_ratio(cpu,
+ double fetch_lat = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FETCH_LAT, st,
&rsd);
double fetch_bw = fe_bound - fetch_lat;
@@ -1260,11 +1260,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
fetch_bw * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double be_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double be_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BE_BOUND, st,
&rsd);
- double mem_bound = td_metric_ratio(cpu,
+ double mem_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_MEM_BOUND, st,
&rsd);
double core_bound = be_bound - mem_bound;
@@ -1281,12 +1281,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
core_bound * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
- evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
- } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
+ evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st);
+ } else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) {
char unit = ' ';
char unit_buf[10] = "/sec";
- total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
if (total)
ratio = convert_unit_double(1000000000.0 * avg / total, &unit);
@@ -1294,7 +1294,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(config, cpu, out, st, &rsd);
+ print_smi_cost(config, cpu_map_idx, out, st, &rsd);
} else {
num = 0;
}
@@ -1307,7 +1307,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
out->new_line(config, ctxp);
generic_metric(config, mexp->metric_expr, mexp->metric_events,
mexp->metric_refs, evsel->name, mexp->metric_name,
- mexp->metric_unit, mexp->runtime, cpu, out, st);
+ mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st);
}
}
if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 09ea334..ee6f034 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel)
zfree(&evsel->stats);
}
-static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads)
+static int evsel__alloc_prev_raw_counts(struct evsel *evsel)
{
+ int cpu_map_nr = evsel__nr_cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
struct perf_counts *counts;
- counts = perf_counts__new(ncpus, nthreads);
+ counts = perf_counts__new(cpu_map_nr, nthreads);
if (counts)
evsel->prev_raw_counts = counts;
@@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel)
static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
- int ncpus = evsel__nr_cpus(evsel);
- int nthreads = perf_thread_map__nr(evsel->core.threads);
-
if (evsel__alloc_stat_priv(evsel) < 0 ||
- evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
- (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+ evsel__alloc_counts(evsel) < 0 ||
+ (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0))
return -ENOMEM;
return 0;
@@ -293,11 +292,12 @@ static bool pkg_id_equal(const void *__key1, const void *__key2,
return *key1 == *key2;
}
-static int check_per_pkg(struct evsel *counter,
- struct perf_counts_values *vals, int cpu, bool *skip)
+static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
+ int cpu_map_idx, bool *skip)
{
struct hashmap *mask = counter->per_pkg_mask;
struct perf_cpu_map *cpus = evsel__cpus(counter);
+ struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx);
int s, d, ret = 0;
uint64_t *key;
@@ -328,7 +328,7 @@ static int check_per_pkg(struct evsel *counter,
if (!(vals->run && vals->ena))
return 0;
- s = cpu_map__get_socket(cpus, cpu, NULL).socket;
+ s = cpu__get_socket_id(cpu);
if (s < 0)
return -1;
@@ -336,7 +336,7 @@ static int check_per_pkg(struct evsel *counter,
* On multi-die system, die_id > 0. On no-die system, die_id = 0.
* We use hashmap(socket, die) to check the used socket+die pair.
*/
- d = cpu_map__get_die(cpus, cpu, NULL).die;
+ d = cpu__get_die_id(cpu);
if (d < 0)
return -1;
@@ -345,9 +345,10 @@ static int check_per_pkg(struct evsel *counter,
return -ENOMEM;
*key = (uint64_t)d << 32 | s;
- if (hashmap__find(mask, (void *)key, NULL))
+ if (hashmap__find(mask, (void *)key, NULL)) {
*skip = true;
- else
+ free(key);
+ } else
ret = hashmap__add(mask, (void *)key, (void *)1);
return ret;
@@ -355,14 +356,14 @@ static int check_per_pkg(struct evsel *counter,
static int
process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
- int cpu, int thread,
+ int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values *aggr = &evsel->counts->aggr;
static struct perf_counts_values zero;
bool skip = false;
- if (check_per_pkg(evsel, count, cpu, &skip)) {
+ if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
@@ -378,11 +379,11 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
case AGGR_NODE:
case AGGR_NONE:
if (!evsel->snapshot)
- evsel__compute_deltas(evsel, cpu, thread, count);
+ evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
perf_stat__update_shadow_stats(evsel, count->val,
- cpu, &rt_stat);
+ cpu_map_idx, &rt_stat);
}
if (config->aggr_mode == AGGR_THREAD) {
@@ -411,15 +412,15 @@ static int process_counter_maps(struct perf_stat_config *config,
{
int nthreads = perf_thread_map__nr(counter->core.threads);
int ncpus = evsel__nr_cpus(counter);
- int cpu, thread;
+ int idx, thread;
if (counter->core.system_wide)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
- if (process_counter_values(config, counter, cpu, thread,
- perf_counts(counter->counts, cpu, thread)))
+ for (idx = 0; idx < ncpus; idx++) {
+ if (process_counter_values(config, counter, idx, thread,
+ perf_counts(counter->counts, idx, thread)))
return -1;
}
}
@@ -531,7 +532,7 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
struct target *target,
- int cpu)
+ int cpu_map_idx)
{
struct perf_event_attr *attr = &evsel->core.attr;
struct evsel *leader = evsel__leader(evsel);
@@ -585,7 +586,7 @@ int create_perf_stat_counter(struct evsel *evsel,
}
if (target__has_cpu(target) && !target__has_per_thread(target))
- return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+ return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx);
return evsel__open_per_thread(evsel, evsel->core.threads);
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 32c8527..335d19c 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -108,8 +108,7 @@ struct runtime_stat {
struct rblist value_list;
};
-typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config,
- struct perf_cpu_map *m, int cpu);
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
struct perf_stat_config {
enum aggr_mode aggr_mode;
@@ -209,7 +208,7 @@ void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
- int cpu, struct runtime_stat *st);
+ int cpu_map_idx, struct runtime_stat *st);
struct perf_stat_output_ctx {
void *ctx;
print_metric_t print_metric;
@@ -249,10 +248,10 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
struct target *target,
- int cpu);
+ int cpu_map_idx);
void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
struct target *_target, struct timespec *ts, int argc, const char **argv);
struct metric_expr;
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st);
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st);
#endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96f941e..4c9f211 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -728,7 +728,7 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
int i;
int ret = 0;
struct perf_cpu_map *m;
- int c;
+ struct perf_cpu c;
m = perf_cpu_map__new(s);
if (!m)
@@ -736,12 +736,12 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
for (i = 0; i < m->nr; i++) {
c = m->map[i];
- if (c >= nr_cpus) {
+ if (c.cpu >= nr_cpus) {
ret = -1;
break;
}
- set_bit(c, cpumask_bits(b));
+ set_bit(c.cpu, cpumask_bits(b));
}
perf_cpu_map__put(m);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 1989821..c9ba805 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1191,7 +1191,7 @@ static void synthesize_cpus(struct cpu_map_entries *cpus,
cpus->nr = map->nr;
for (i = 0; i < map->nr; i++)
- cpus->cpu[i] = map->map[i];
+ cpus->cpu[i] = map->map[i].cpu;
}
static void synthesize_mask(struct perf_record_record_cpu_map *mask,
@@ -1203,7 +1203,7 @@ static void synthesize_mask(struct perf_record_record_cpu_map *mask,
mask->long_size = sizeof(long);
for (i = 0; i < map->nr; i++)
- set_bit(map->map[i], mask->mask);
+ set_bit(map->map[i].cpu, mask->mask);
}
static size_t cpus_size(struct perf_cpu_map *map)
@@ -1219,7 +1219,7 @@ static size_t mask_size(struct perf_cpu_map *map, int *max)
for (i = 0; i < map->nr; i++) {
/* bit position of the cpu is + 1 */
- int bit = map->map[i] + 1;
+ int bit = map->map[i].cpu + 1;
if (bit > *max)
*max = bit;
@@ -1354,7 +1354,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool,
}
int perf_event__synthesize_stat(struct perf_tool *tool,
- u32 cpu, u32 thread, u64 id,
+ struct perf_cpu cpu, u32 thread, u64 id,
struct perf_counts_values *count,
perf_event__handler_t process,
struct machine *machine)
@@ -1366,7 +1366,7 @@ int perf_event__synthesize_stat(struct perf_tool *tool,
event.header.misc = 0;
event.id = id;
- event.cpu = cpu;
+ event.cpu = cpu.cpu;
event.thread = thread;
event.val = count->val;
event.ena = count->ena;
@@ -1763,7 +1763,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
}
e->idx = sid->idx;
- e->cpu = sid->cpu;
+ e->cpu = sid->cpu.cpu;
e->tid = sid->tid;
}
}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index c931433..78a0450 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -6,6 +6,7 @@
#include <sys/types.h> // pid_t
#include <linux/compiler.h>
#include <linux/types.h>
+#include <perf/cpumap.h>
struct auxtrace_record;
struct dso;
@@ -63,7 +64,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat(struct perf_tool *tool, struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data);
int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index df3c467..fb4f661 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -416,3 +416,18 @@ char *perf_exe(char *buf, int len)
}
return strcpy(buf, "perf");
}
+
+void perf_debuginfod_setup(struct perf_debuginfod *di)
+{
+ /*
+ * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod
+ * processing is not triggered, otherwise we set it to 'di->urls'
+ * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value.
+ */
+ if (!di->set)
+ setenv("DEBUGINFOD_URLS", "", 1);
+ else if (di->urls && strcmp(di->urls, "system"))
+ setenv("DEBUGINFOD_URLS", di->urls, 1);
+
+ pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9f0d36b..7b625cb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -11,6 +11,9 @@
#include <stddef.h>
#include <linux/compiler.h>
#include <sys/types.h>
+#ifndef __cplusplus
+#include <internal/cpumap.h>
+#endif
/* General helper functions */
void usage(const char *err) __noreturn;
@@ -66,6 +69,12 @@ extern bool test_attr__enabled;
void test_attr__ready(void);
void test_attr__init(void);
struct perf_event_attr;
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags);
+
+struct perf_debuginfod {
+ const char *urls;
+ bool set;
+};
+void perf_debuginfod_setup(struct perf_debuginfod *di);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/acpi/.gitignore b/tools/power/acpi/.gitignore
index 0b319fc..eada029 100644
--- a/tools/power/acpi/.gitignore
+++ b/tools/power/acpi/.gitignore
@@ -2,4 +2,5 @@
/acpidbg
/acpidump
/ec
+/pfrut
/include/
diff --git a/tools/power/acpi/Makefile b/tools/power/acpi/Makefile
index a249c50..5ff1d9c 100644
--- a/tools/power/acpi/Makefile
+++ b/tools/power/acpi/Makefile
@@ -9,18 +9,18 @@
.NOTPARALLEL:
-all: acpidbg acpidump ec
-clean: acpidbg_clean acpidump_clean ec_clean
-install: acpidbg_install acpidump_install ec_install
-uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall
+all: acpidbg acpidump ec pfrut
+clean: acpidbg_clean acpidump_clean ec_clean pfrut_clean
+install: acpidbg_install acpidump_install ec_install pfrut_install
+uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall
-acpidbg acpidump ec: FORCE
+acpidbg acpidump ec pfrut: FORCE
$(call descend,tools/$@,all)
-acpidbg_clean acpidump_clean ec_clean:
+acpidbg_clean acpidump_clean ec_clean pfrut_clean:
$(call descend,tools/$(@:_clean=),clean)
-acpidbg_install acpidump_install ec_install:
+acpidbg_install acpidump_install ec_install pfrut_install:
$(call descend,tools/$(@:_install=),install)
-acpidbg_uninstall acpidump_uninstall ec_uninstall:
+acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall:
$(call descend,tools/$(@:_uninstall=),uninstall)
.PHONY: FORCE
diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules
index 1d7616f..b71aada 100644
--- a/tools/power/acpi/Makefile.rules
+++ b/tools/power/acpi/Makefile.rules
@@ -9,7 +9,7 @@
toolobjs := $(addprefix $(objdir),$(TOOL_OBJS))
$(OUTPUT)$(TOOL): $(toolobjs) FORCE
$(ECHO) " LD " $(subst $(OUTPUT),,$@)
- $(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(toolobjs) -L$(OUTPUT) -o $@
+ $(QUIET) $(LD) $(CFLAGS) $(toolobjs) $(LDFLAGS) -L$(OUTPUT) -o $@
$(ECHO) " STRIP " $(subst $(OUTPUT),,$@)
$(QUIET) $(STRIPCMD) $@
diff --git a/tools/power/acpi/man/pfrut.8 b/tools/power/acpi/man/pfrut.8
new file mode 100644
index 0000000..3db57477
--- /dev/null
+++ b/tools/power/acpi/man/pfrut.8
@@ -0,0 +1,137 @@
+.TH "PFRUT" "8" "October 2021" "pfrut 1.0" ""
+.hy
+.SH Name
+.PP
+pfrut \- Platform Firmware Runtime Update and Telemetry tool
+.SH SYNOPSIS
+.PP
+\f[B]pfrut\f[R] [\f[I]Options\f[R]]
+.SH DESCRIPTION
+.PP
+The PFRUT(Platform Firmware Runtime Update and Telemetry) kernel interface is designed
+to
+.PD 0
+.P
+.PD
+interact with the platform firmware interface defined in the
+.PD 0
+.P
+.PD
+Management Mode Firmware Runtime
+Update (https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf)
+.PD 0
+.P
+.PD
+\f[B]pfrut\f[R] is the tool to interact with the kernel interface.
+.PD 0
+.P
+.PD
+.SH OPTIONS
+.TP
+.B \f[B]\-h\f[R], \f[B]\-\-help\f[R]
+Display helper information.
+.TP
+.B \f[B]\-l\f[R], \f[B]\-\-load\f[R]
+Load the capsule file into the system.
+To be more specific, the capsule file will be copied to the
+communication buffer.
+.TP
+.B \f[B]\-s\f[R], \f[B]\-\-stage\f[R]
+Stage the capsule image from communication buffer into Management Mode
+and perform authentication.
+.TP
+.B \f[B]\-a\f[R], \f[B]\-\-activate\f[R]
+Activate a previous staged capsule image.
+.TP
+.B \f[B]\-u\f[R], \f[B]\-\-update\f[R]
+Perform both stage and activation actions.
+.TP
+.B \f[B]\-q\f[R], \f[B]\-\-query\f[R]
+Query the update capability.
+.TP
+.B \f[B]\-d\f[R], \f[B]\-\-setrev\f[R]
+Set the revision ID of code injection/driver update.
+.TP
+.B \f[B]\-D\f[R], \f[B]\-\-setrevlog\f[R]
+Set the revision ID of telemetry.
+.TP
+.B \f[B]\-G\f[R], \f[B]\-\-getloginfo\f[R]
+Get telemetry log information and print it out.
+.TP
+.B \f[B]\-T\f[R], \f[B]\-\-type\f[R]
+Set the telemetry log data type.
+.TP
+.B \f[B]\-L\f[R], \f[B]\-\-level\f[R]
+Set the telemetry log level.
+.TP
+.B \f[B]\-R\f[R], \f[B]\-\-read\f[R]
+Read all the telemetry data and print it out.
+.SH EXAMPLES
+.PP
+\f[B]pfrut \-G\f[R]
+.PP
+log_level:4
+.PD 0
+.P
+.PD
+log_type:0
+.PD 0
+.P
+.PD
+log_revid:2
+.PD 0
+.P
+.PD
+max_data_size:65536
+.PD 0
+.P
+.PD
+chunk1_size:0
+.PD 0
+.P
+.PD
+chunk2_size:1401
+.PD 0
+.P
+.PD
+rollover_cnt:0
+.PD 0
+.P
+.PD
+reset_cnt:4
+.PP
+\f[B]pfru \-q\f[R]
+.PP
+code injection image type:794bf8b2\-6e7b\-454e\-885f\-3fb9bb185402
+.PD 0
+.P
+.PD
+fw_version:0
+.PD 0
+.P
+.PD
+code_rt_version:1
+.PD 0
+.P
+.PD
+driver update image type:0e5f0b14\-f849\-7945\-ad81\-bc7b6d2bb245
+.PD 0
+.P
+.PD
+drv_rt_version:0
+.PD 0
+.P
+.PD
+drv_svn:0
+.PD 0
+.P
+.PD
+platform id:39214663\-b1a8\-4eaa\-9024\-f2bb53ea4723
+.PD 0
+.P
+.PD
+oem id:a36db54f\-ea2a\-e14e\-b7c4\-b5780e51ba3d
+.PP
+\f[B]pfrut \-l yours.cap \-u \-T 1 \-L 4\f[R]
+.SH AUTHORS
+Chen Yu.
diff --git a/tools/power/acpi/tools/pfrut/Makefile b/tools/power/acpi/tools/pfrut/Makefile
new file mode 100644
index 0000000..61c1a96
--- /dev/null
+++ b/tools/power/acpi/tools/pfrut/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+include ../../Makefile.config
+
+TOOL = pfrut
+EXTRA_INSTALL = install-man
+EXTRA_UNINSTALL = uninstall-man
+
+CFLAGS += -Wall -O2
+CFLAGS += -DPFRUT_HEADER='"../../../../../include/uapi/linux/pfrut.h"'
+LDFLAGS += -luuid
+
+TOOL_OBJS = \
+ pfrut.o
+
+include ../../Makefile.rules
+
+install-man: $(srctree)/man/pfrut.8
+ $(ECHO) " INST " pfrut.8
+ $(QUIET) $(INSTALL_DATA) -D $< $(DESTDIR)$(mandir)/man8/pfrut.8
+uninstall-man:
+ $(ECHO) " UNINST " pfrut.8
+ $(QUIET) rm -f $(DESTDIR)$(mandir)/man8/pfrut.8
diff --git a/tools/power/acpi/tools/pfrut/pfrut.c b/tools/power/acpi/tools/pfrut/pfrut.c
new file mode 100644
index 0000000..d79c335
--- /dev/null
+++ b/tools/power/acpi/tools/pfrut/pfrut.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Platform Firmware Runtime Update tool to do Management
+ * Mode code injection/driver update and telemetry retrieval.
+ *
+ * This tool uses the interfaces provided by pfr_update and
+ * pfr_telemetry drivers. These interfaces are exposed via
+ * /dev/pfr_update and /dev/pfr_telemetry. Write operation
+ * on the /dev/pfr_update is to load the EFI capsule into
+ * kernel space. Mmap/read operations on /dev/pfr_telemetry
+ * could be used to read the telemetry data to user space.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <getopt.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <uuid/uuid.h>
+#include PFRUT_HEADER
+
+char *capsule_name;
+int action, query_cap, log_type, log_level, log_read, log_getinfo,
+ revid, log_revid;
+int set_log_level, set_log_type,
+ set_revid, set_log_revid;
+
+char *progname;
+
+#define LOG_ERR 0
+#define LOG_WARN 1
+#define LOG_INFO 2
+#define LOG_VERB 4
+#define LOG_EXEC_IDX 0
+#define LOG_HISTORY_IDX 1
+#define REVID_1 1
+#define REVID_2 2
+
+static int valid_log_level(int level)
+{
+ return level == LOG_ERR || level == LOG_WARN ||
+ level == LOG_INFO || level == LOG_VERB;
+}
+
+static int valid_log_type(int type)
+{
+ return type == LOG_EXEC_IDX || type == LOG_HISTORY_IDX;
+}
+
+static inline int valid_log_revid(int id)
+{
+ return id == REVID_1 || id == REVID_2;
+}
+
+static void help(void)
+{
+ fprintf(stderr,
+ "usage: %s [OPTIONS]\n"
+ " code injection:\n"
+ " -l, --load\n"
+ " -s, --stage\n"
+ " -a, --activate\n"
+ " -u, --update [stage and activate]\n"
+ " -q, --query\n"
+ " -d, --revid update\n"
+ " telemetry:\n"
+ " -G, --getloginfo\n"
+ " -T, --type(0:execution, 1:history)\n"
+ " -L, --level(0, 1, 2, 4)\n"
+ " -R, --read\n"
+ " -D, --revid log\n",
+ progname);
+}
+
+char *option_string = "l:sauqd:GT:L:RD:h";
+static struct option long_options[] = {
+ {"load", required_argument, 0, 'l'},
+ {"stage", no_argument, 0, 's'},
+ {"activate", no_argument, 0, 'a'},
+ {"update", no_argument, 0, 'u'},
+ {"query", no_argument, 0, 'q'},
+ {"getloginfo", no_argument, 0, 'G'},
+ {"type", required_argument, 0, 'T'},
+ {"level", required_argument, 0, 'L'},
+ {"read", no_argument, 0, 'R'},
+ {"setrev", required_argument, 0, 'd'},
+ {"setrevlog", required_argument, 0, 'D'},
+ {"help", no_argument, 0, 'h'},
+ {}
+};
+
+static void parse_options(int argc, char **argv)
+{
+ int option_index = 0;
+ char *pathname;
+ int opt;
+
+ pathname = strdup(argv[0]);
+ progname = basename(pathname);
+
+ while ((opt = getopt_long_only(argc, argv, option_string,
+ long_options, &option_index)) != -1) {
+ switch (opt) {
+ case 'l':
+ capsule_name = optarg;
+ break;
+ case 's':
+ action = 1;
+ break;
+ case 'a':
+ action = 2;
+ break;
+ case 'u':
+ action = 3;
+ break;
+ case 'q':
+ query_cap = 1;
+ break;
+ case 'G':
+ log_getinfo = 1;
+ break;
+ case 'T':
+ log_type = atoi(optarg);
+ set_log_type = 1;
+ break;
+ case 'L':
+ log_level = atoi(optarg);
+ set_log_level = 1;
+ break;
+ case 'R':
+ log_read = 1;
+ break;
+ case 'd':
+ revid = atoi(optarg);
+ set_revid = 1;
+ break;
+ case 'D':
+ log_revid = atoi(optarg);
+ set_log_revid = 1;
+ break;
+ case 'h':
+ help();
+ exit(0);
+ default:
+ break;
+ }
+ }
+}
+
+void print_cap(struct pfru_update_cap_info *cap)
+{
+ char *uuid;
+
+ uuid = malloc(37);
+ if (!uuid) {
+ perror("Can not allocate uuid buffer\n");
+ exit(1);
+ }
+
+ uuid_unparse(cap->code_type, uuid);
+ printf("code injection image type:%s\n", uuid);
+ printf("fw_version:%d\n", cap->fw_version);
+ printf("code_rt_version:%d\n", cap->code_rt_version);
+
+ uuid_unparse(cap->drv_type, uuid);
+ printf("driver update image type:%s\n", uuid);
+ printf("drv_rt_version:%d\n", cap->drv_rt_version);
+ printf("drv_svn:%d\n", cap->drv_svn);
+
+ uuid_unparse(cap->platform_id, uuid);
+ printf("platform id:%s\n", uuid);
+ uuid_unparse(cap->oem_id, uuid);
+ printf("oem id:%s\n", uuid);
+ printf("oem information length:%d\n", cap->oem_info_len);
+
+ free(uuid);
+}
+
+int main(int argc, char *argv[])
+{
+ int fd_update, fd_update_log, fd_capsule;
+ struct pfrt_log_data_info data_info;
+ struct pfrt_log_info info;
+ struct pfru_update_cap_info cap;
+ void *addr_map_capsule;
+ struct stat st;
+ char *log_buf;
+ int ret = 0;
+
+ if (getuid() != 0) {
+ printf("Please run the tool as root - Exiting.\n");
+ return 1;
+ }
+
+ parse_options(argc, argv);
+
+ fd_update = open("/dev/acpi_pfr_update0", O_RDWR);
+ if (fd_update < 0) {
+ printf("PFRU device not supported - Quit...\n");
+ return 1;
+ }
+
+ fd_update_log = open("/dev/acpi_pfr_telemetry0", O_RDWR);
+ if (fd_update_log < 0) {
+ printf("PFRT device not supported - Quit...\n");
+ return 1;
+ }
+
+ if (query_cap) {
+ ret = ioctl(fd_update, PFRU_IOC_QUERY_CAP, &cap);
+ if (ret)
+ perror("Query Update Capability info failed.");
+ else
+ print_cap(&cap);
+
+ close(fd_update);
+ close(fd_update_log);
+
+ return ret;
+ }
+
+ if (log_getinfo) {
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info);
+ if (ret) {
+ perror("Get telemetry data info failed.");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_INFO, &info);
+ if (ret) {
+ perror("Get telemetry info failed.");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ printf("log_level:%d\n", info.log_level);
+ printf("log_type:%d\n", info.log_type);
+ printf("log_revid:%d\n", info.log_revid);
+ printf("max_data_size:%d\n", data_info.max_data_size);
+ printf("chunk1_size:%d\n", data_info.chunk1_size);
+ printf("chunk2_size:%d\n", data_info.chunk2_size);
+ printf("rollover_cnt:%d\n", data_info.rollover_cnt);
+ printf("reset_cnt:%d\n", data_info.reset_cnt);
+
+ return 0;
+ }
+
+ info.log_level = -1;
+ info.log_type = -1;
+ info.log_revid = -1;
+
+ if (set_log_level) {
+ if (!valid_log_level(log_level)) {
+ printf("Invalid log level %d\n",
+ log_level);
+ } else {
+ info.log_level = log_level;
+ }
+ }
+
+ if (set_log_type) {
+ if (!valid_log_type(log_type)) {
+ printf("Invalid log type %d\n",
+ log_type);
+ } else {
+ info.log_type = log_type;
+ }
+ }
+
+ if (set_log_revid) {
+ if (!valid_log_revid(log_revid)) {
+ printf("Invalid log revid %d, unchanged.\n",
+ log_revid);
+ } else {
+ info.log_revid = log_revid;
+ }
+ }
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_SET_INFO, &info);
+ if (ret) {
+ perror("Log information set failed.(log_level, log_type, log_revid)");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ if (set_revid) {
+ ret = ioctl(fd_update, PFRU_IOC_SET_REV, &revid);
+ if (ret) {
+ perror("pfru update revid set failed");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ printf("pfru update revid set to %d\n", revid);
+ }
+
+ if (capsule_name) {
+ fd_capsule = open(capsule_name, O_RDONLY);
+ if (fd_capsule < 0) {
+ perror("Can not open capsule file...");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ if (fstat(fd_capsule, &st) < 0) {
+ perror("Can not fstat capsule file...");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ addr_map_capsule = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED,
+ fd_capsule, 0);
+ if (addr_map_capsule == MAP_FAILED) {
+ perror("Failed to mmap capsule file.");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ ret = write(fd_update, (char *)addr_map_capsule, st.st_size);
+ printf("Load %d bytes of capsule file into the system\n",
+ ret);
+
+ if (ret == -1) {
+ perror("Failed to load capsule file");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ munmap(addr_map_capsule, st.st_size);
+ close(fd_capsule);
+ printf("Load done.\n");
+ }
+
+ if (action) {
+ if (action == 1) {
+ ret = ioctl(fd_update, PFRU_IOC_STAGE, NULL);
+ } else if (action == 2) {
+ ret = ioctl(fd_update, PFRU_IOC_ACTIVATE, NULL);
+ } else if (action == 3) {
+ ret = ioctl(fd_update, PFRU_IOC_STAGE_ACTIVATE, NULL);
+ } else {
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+ printf("Update finished, return %d\n", ret);
+ }
+
+ close(fd_update);
+
+ if (log_read) {
+ void *p_mmap;
+ int max_data_sz;
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info);
+ if (ret) {
+ perror("Get telemetry data info failed.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ max_data_sz = data_info.max_data_size;
+ if (!max_data_sz) {
+ printf("No telemetry data available.\n");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ log_buf = malloc(max_data_sz + 1);
+ if (!log_buf) {
+ perror("log_buf allocate failed.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ p_mmap = mmap(NULL, max_data_sz, PROT_READ, MAP_SHARED, fd_update_log, 0);
+ if (p_mmap == MAP_FAILED) {
+ perror("mmap error.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ memcpy(log_buf, p_mmap, max_data_sz);
+ log_buf[max_data_sz] = '\0';
+ printf("%s\n", log_buf);
+ free(log_buf);
+
+ munmap(p_mmap, max_data_sz);
+ }
+
+ close(fd_update_log);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index 32fc5b3..911345c 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -10,6 +10,7 @@
#include "test_d_path.skel.h"
#include "test_d_path_check_rdonly_mem.skel.h"
+#include "test_d_path_check_types.skel.h"
static int duration;
@@ -167,6 +168,16 @@ static void test_d_path_check_rdonly_mem(void)
test_d_path_check_rdonly_mem__destroy(skel);
}
+static void test_d_path_check_types(void)
+{
+ struct test_d_path_check_types *skel;
+
+ skel = test_d_path_check_types__open_and_load();
+ ASSERT_ERR_PTR(skel, "unexpected_load_passing_wrong_type");
+
+ test_d_path_check_types__destroy(skel);
+}
+
void test_d_path(void)
{
if (test__start_subtest("basic"))
@@ -174,4 +185,7 @@ void test_d_path(void)
if (test__start_subtest("check_rdonly_mem"))
test_d_path_check_rdonly_mem();
+
+ if (test__start_subtest("check_alloc_mem"))
+ test_d_path_check_types();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 983ab0b..b2b357f 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -8,46 +8,47 @@
void serial_test_xdp_link(void)
{
- __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
struct test_xdp_link *skel1 = NULL, *skel2 = NULL;
+ __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2;
struct bpf_link_info link_info;
struct bpf_prog_info prog_info;
struct bpf_link *link;
+ int err;
__u32 link_info_len = sizeof(link_info);
__u32 prog_info_len = sizeof(prog_info);
skel1 = test_xdp_link__open_and_load();
- if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel1, "skel_load"))
goto cleanup;
prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler);
skel2 = test_xdp_link__open_and_load();
- if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel2, "skel_load"))
goto cleanup;
prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info1", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info1"))
goto cleanup;
id1 = prog_info.id;
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info2", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info2"))
goto cleanup;
id2 = prog_info.id;
/* set initial prog attachment */
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err))
+ if (!ASSERT_OK(err, "fd_attach"))
goto cleanup;
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err);
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
+ goto cleanup;
/* BPF link is not allowed to replace prog attachment */
link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
@@ -62,7 +63,7 @@ void serial_test_xdp_link(void)
/* detach BPF program */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "prog_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "prog_detach"))
goto cleanup;
/* now BPF link should attach successfully */
@@ -73,24 +74,23 @@ void serial_test_xdp_link(void)
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
goto cleanup;
/* BPF prog attach is not allowed to replace BPF link */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(!err, "prog_attach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_attach_fail"))
goto cleanup;
/* Can't force-update when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0);
- if (CHECK(!err, "prog_update_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_update_fail"))
goto cleanup;
/* Can't force-detach when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
- if (CHECK(!err, "prog_detach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_detach_fail"))
goto cleanup;
/* BPF link is not allowed to replace another BPF link */
@@ -110,40 +110,39 @@ void serial_test_xdp_link(void)
skel2->links.xdp_handler = link;
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id2, "id2_check",
- "loaded prog id %u != id2 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val"))
goto cleanup;
/* updating program under active BPF link works as expected */
err = bpf_link__update_program(link, skel1->progs.xdp_handler);
- if (CHECK(err, "link_upd", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_upd"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_info"))
goto cleanup;
- CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type",
- "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP);
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
- CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO);
+ ASSERT_EQ(link_info.type, BPF_LINK_TYPE_XDP, "link_type");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
+ ASSERT_EQ(link_info.xdp.ifindex, IFINDEX_LO, "link_ifindex");
+
+ /* updating program under active BPF link with different type fails */
+ err = bpf_link__update_program(link, skel1->progs.tc_handler);
+ if (!ASSERT_ERR(err, "link_upd_invalid"))
+ goto cleanup;
err = bpf_link__detach(link);
- if (CHECK(err, "link_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "link_detach"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
- goto cleanup;
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
+
+ ASSERT_OK(err, "link_info");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
/* ifindex should be zeroed out */
- CHECK(link_info.xdp.ifindex != 0, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, 0);
+ ASSERT_EQ(link_info.xdp.ifindex, 0, "link_ifindex");
cleanup:
test_xdp_link__destroy(skel1);
diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_types.c b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
new file mode 100644
index 0000000..7e02b73
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern const int bpf_prog_active __ksym;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+SEC("fentry/security_inode_getattr")
+int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat,
+ __u32 request_mask, unsigned int query_flags)
+{
+ void *active;
+ u32 cpu;
+
+ cpu = bpf_get_smp_processor_id();
+ active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+ if (active) {
+ /* FAIL here! 'active' points to 'regular' memory. It
+ * cannot be submitted to ring buffer.
+ */
+ bpf_ringbuf_submit(active, 0);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index a8233e7..728dbd3 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
@@ -41,11 +41,11 @@ struct {
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index ce69740..43bd7a2 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -1,17 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c
index ee7d6ac..64ff32e 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_link.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c
@@ -10,3 +10,9 @@ int xdp_handler(struct xdp_md *xdp)
{
return 0;
}
+
+SEC("tc")
+int tc_handler(struct __sk_buff *skb)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c
new file mode 100644
index 0000000..b64d33e
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/ringbuf.c
@@ -0,0 +1,95 @@
+{
+ "ringbuf: invalid reservation offset 1",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xcafe),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "dereference of modified alloc_mem ptr R1",
+},
+{
+ "ringbuf: invalid reservation offset 2",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 0xcafe),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "R7 min value is outside of the allowed memory range",
+},
+{
+ "ringbuf: check passing rb mem to helpers",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ /* pass allocated ring buffer memory to fib lookup */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_fib_lookup),
+ /* submit the ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 2 },
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 1a8eb96..8cfc534 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -84,7 +84,7 @@
},
.fixup_map_ringbuf = { 1 },
.result = REJECT,
- .errstr = "R0 pointer arithmetic on mem_or_null prohibited",
+ .errstr = "R0 pointer arithmetic on alloc_mem_or_null prohibited",
},
{
"check corrupted spill/fill",
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 8c12996..dce7de7 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -8,11 +8,12 @@
/s390x/memop
/s390x/resets
/s390x/sync_regs_test
+/x86_64/amx_test
+/x86_64/cpuid_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/emulator_error_test
-/x86_64/get_cpuid_test
/x86_64/get_msr_index_features
/x86_64/kvm_clock_test
/x86_64/kvm_pv_test
@@ -22,6 +23,7 @@
/x86_64/mmio_warning_test
/x86_64/mmu_role_test
/x86_64/platform_info_test
+/x86_64/pmu_event_filter_test
/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/sev_migrate_tests
@@ -36,6 +38,7 @@
/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
+/x86_64/vmx_exception_with_invalid_guest_state
/x86_64/vmx_invalid_nested_guest_state
/x86_64/vmx_preemption_timer_test
/x86_64/vmx_set_nested_state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ee8cf21..81ebf99 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -43,11 +43,11 @@
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
-TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
-TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
@@ -56,6 +56,7 @@
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/mmu_role_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
@@ -69,6 +70,7 @@
TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e94ba0f..423d8a6 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -364,6 +364,24 @@ static inline unsigned long get_xmm(int n)
}
bool is_intel_cpu(void);
+bool is_amd_cpu(void);
+
+static inline unsigned int x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+static inline unsigned int x86_model(unsigned int eax)
+{
+ return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
+}
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
@@ -375,6 +393,8 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index);
struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid);
void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_cpuid2 *cpuid);
@@ -419,6 +439,11 @@ void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
uint64_t pte);
/*
+ * get_cpuid() - find matching CPUID entry and return pointer to it.
+ */
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index);
+/*
* set_cpuid() - overwrites a matching cpuid entry with the provided value.
* matches based on ent->function && ent->index. returns true
* if a match was found and successfully overwritten.
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 4a645dc..8c53f96 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -393,10 +393,12 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
struct kvm_vm *vm;
int i;
+#ifdef __x86_64__
/*
* Permission needs to be requested before KVM_SET_CPUID2.
*/
vm_xsave_req_perm();
+#endif
/* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */
if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES)
@@ -497,9 +499,11 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
uint64_t first_page, uint32_t num_pages)
{
- struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
- .first_page = first_page,
- .num_pages = num_pages };
+ struct kvm_clear_dirty_log args = {
+ .dirty_bitmap = log, .slot = slot,
+ .first_page = first_page,
+ .num_pages = num_pages
+ };
int ret;
ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index babb0f2..5f9d7e9 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -886,6 +886,17 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
return entry;
}
+
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ return ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+}
+
/*
* VM VCPU CPUID Set
*
@@ -903,12 +914,9 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
void vcpu_set_cpuid(struct kvm_vm *vm,
uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int rc;
- TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-
- rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+ rc = __vcpu_set_cpuid(vm, vcpuid, cpuid);
TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
rc, errno);
@@ -1136,25 +1144,25 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
list->nmsrs = nmsrs;
r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+ r);
state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+ r);
r = vcpu_save_xsave_state(vm, vcpu, state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+ r);
if (kvm_check_cap(KVM_CAP_XCRS)) {
r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
@@ -1163,17 +1171,17 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
}
r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+ r);
if (nested_size) {
state->nested.size = sizeof(state->nested_);
r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
- r);
+ r);
TEST_ASSERT(state->nested.size <= nested_size,
- "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
- state->nested.size, nested_size);
+ "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+ state->nested.size, nested_size);
} else
state->nested.size = 0;
@@ -1181,12 +1189,12 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
for (i = 0; i < nmsrs; i++)
state->msrs.entries[i].index = list->indices[i];
r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
- TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
- r, r == nmsrs ? -1 : list->indices[r]);
+ TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
+ r, r == nmsrs ? -1 : list->indices[r]);
r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+ r);
free(list);
return state;
@@ -1199,7 +1207,7 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
- r);
+ r);
r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
TEST_ASSERT(r == state->msrs.nmsrs,
@@ -1214,28 +1222,28 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
- r);
+ r);
r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+ r);
if (state->nested.size) {
r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
- r);
+ r);
}
}
@@ -1245,10 +1253,10 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state)
free(state);
}
-bool is_intel_cpu(void)
+static bool cpu_vendor_string_is(const char *vendor)
{
+ const uint32_t *chunk = (const uint32_t *)vendor;
int eax, ebx, ecx, edx;
- const uint32_t *chunk;
const int leaf = 0;
__asm__ __volatile__(
@@ -1257,10 +1265,22 @@ bool is_intel_cpu(void)
"=c"(ecx), "=d"(edx)
: /* input */ "0"(leaf), "2"(0));
- chunk = (const uint32_t *)("GenuineIntel");
return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
}
+bool is_intel_cpu(void)
+{
+ return cpu_vendor_string_is("GenuineIntel");
+}
+
+/*
+ * Exclude early K5 samples with a vendor string of "AMDisbetter!"
+ */
+bool is_amd_cpu(void)
+{
+ return cpu_vendor_string_is("AuthenticAMD");
+}
+
uint32_t kvm_get_cpuid_max_basic(void)
{
return kvm_get_supported_cpuid_entry(0)->eax;
@@ -1384,6 +1404,23 @@ void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
}
}
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function == function && cur->index == index)
+ return cur;
+ }
+
+ TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index);
+
+ return NULL;
+}
+
bool set_cpuid(struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 *ent)
{
@@ -1479,22 +1516,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui
return cpuid;
}
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
-
-static inline unsigned x86_family(unsigned int eax)
-{
- unsigned int x86;
-
- x86 = (eax >> 8) & 0xf;
-
- if (x86 == 0xf)
- x86 += (eax >> 20) & 0xff;
-
- return x86;
-}
-
unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
{
const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
@@ -1504,11 +1525,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
/* Avoid reserved HyperTransport region on AMD processors. */
- eax = ecx = 0;
- cpuid(&eax, &ebx, &ecx, &edx);
- if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
- ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
- edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+ if (!is_amd_cpu())
return max_gfn;
/* On parts with <40 physical address bits, the area is fully hidden */
@@ -1518,6 +1535,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
/* Before family 17h, the HyperTransport area is just below 1T. */
ht_gfn = (1 << 28) - num_ht_pages;
eax = 1;
+ ecx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
if (x86_family(eax) < 0x17)
goto done;
diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
similarity index 83%
rename from tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
rename to tools/testing/selftests/kvm/x86_64/cpuid_test.c
index a711f83..16d2465 100644
--- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -154,6 +154,34 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct
return guest_cpuids;
}
+static void set_cpuid_after_run(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid)
+{
+ struct kvm_cpuid_entry2 *ent;
+ int rc;
+ u32 eax, ebx, x;
+
+ /* Setting unmodified CPUID is allowed */
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc);
+
+ /* Changing CPU features is forbidden */
+ ent = get_cpuid(cpuid, 0x7, 0);
+ ebx = ent->ebx;
+ ent->ebx--;
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing CPU features should fail");
+ ent->ebx = ebx;
+
+ /* Changing MAXPHYADDR is forbidden */
+ ent = get_cpuid(cpuid, 0x80000008, 0);
+ eax = ent->eax;
+ x = eax & 0xff;
+ ent->eax = (eax & ~0xffu) | (x - 1);
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing MAXPHYADDR should fail");
+ ent->eax = eax;
+}
+
int main(void)
{
struct kvm_cpuid2 *supp_cpuid, *cpuid2;
@@ -175,5 +203,7 @@ int main(void)
for (stage = 0; stage < 3; stage++)
run_vcpu(vm, VCPU_ID, stage);
+ set_cpuid_after_run(vm, cpuid2);
+
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
new file mode 100644
index 0000000..c715adc
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_SET_PMU_EVENT_FILTER.
+ *
+ * Copyright (C) 2022, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies the expected behavior of allow lists and deny lists for
+ * virtual PMU events.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+/*
+ * In lieu of copying perf_event.h into tools...
+ */
+#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
+
+union cpuid10_eax {
+ struct {
+ unsigned int version_id:8;
+ unsigned int num_counters:8;
+ unsigned int bit_width:8;
+ unsigned int mask_length:8;
+ } split;
+ unsigned int full;
+};
+
+union cpuid10_ebx {
+ struct {
+ unsigned int no_unhalted_core_cycles:1;
+ unsigned int no_instructions_retired:1;
+ unsigned int no_unhalted_reference_cycles:1;
+ unsigned int no_llc_reference:1;
+ unsigned int no_llc_misses:1;
+ unsigned int no_branch_instruction_retired:1;
+ unsigned int no_branch_misses_retired:1;
+ } split;
+ unsigned int full;
+};
+
+/* End of stuff taken from perf_event.h. */
+
+/* Oddly, this isn't in perf_event.h. */
+#define ARCH_PERFMON_BRANCHES_RETIRED 5
+
+#define VCPU_ID 0
+#define NUM_BRANCHES 42
+
+/*
+ * This is how the event selector and unit mask are stored in an AMD
+ * core performance event-select register. Intel's format is similar,
+ * but the event selector is only 8 bits.
+ */
+#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \
+ (umask & 0xff) << 8)
+
+/*
+ * "Branch instructions retired", from the Intel SDM, volume 3,
+ * "Pre-defined Architectural Performance Events."
+ */
+
+#define INTEL_BR_RETIRED EVENT(0xc4, 0)
+
+/*
+ * "Retired branch instructions", from Processor Programming Reference
+ * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors,
+ * Preliminary Processor Programming Reference (PPR) for AMD Family
+ * 17h Model 31h, Revision B0 Processors, and Preliminary Processor
+ * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision
+ * B1 Processors Volume 1 of 2.
+ */
+
+#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0)
+
+/*
+ * This event list comprises Intel's eight architectural events plus
+ * AMD's "retired branch instructions" for Zen[123] (and possibly
+ * other AMD CPUs).
+ */
+static const uint64_t event_list[] = {
+ EVENT(0x3c, 0),
+ EVENT(0xc0, 0),
+ EVENT(0x3c, 1),
+ EVENT(0x2e, 0x4f),
+ EVENT(0x2e, 0x41),
+ EVENT(0xc4, 0),
+ EVENT(0xc5, 0),
+ EVENT(0xa4, 1),
+ AMD_ZEN_BR_RETIRED,
+};
+
+/*
+ * If we encounter a #GP during the guest PMU sanity check, then the guest
+ * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0).
+ */
+static void guest_gp_handler(struct ex_regs *regs)
+{
+ GUEST_SYNC(0);
+}
+
+/*
+ * Check that we can write a new value to the given MSR and read it back.
+ * The caller should provide a non-empty set of bits that are safe to flip.
+ *
+ * Return on success. GUEST_SYNC(0) on error.
+ */
+static void check_msr(uint32_t msr, uint64_t bits_to_flip)
+{
+ uint64_t v = rdmsr(msr) ^ bits_to_flip;
+
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+
+ v ^= bits_to_flip;
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+}
+
+static void intel_guest_code(void)
+{
+ check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ check_msr(MSR_P6_EVNTSEL0, 0xffff);
+ check_msr(MSR_IA32_PMC0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED);
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ br0 = rdmsr(MSR_IA32_PMC0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_IA32_PMC0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * To avoid needing a check for CPUID.80000001:ECX.PerfCtrExtCore[bit 23],
+ * this code uses the always-available, legacy K7 PMU MSRs, which alias to
+ * the first four of the six extended core PMU MSRs.
+ */
+static void amd_guest_code(void)
+{
+ check_msr(MSR_K7_EVNTSEL0, 0xffff);
+ check_msr(MSR_K7_PERFCTR0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_K7_EVNTSEL0, 0);
+ wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED);
+ br0 = rdmsr(MSR_K7_PERFCTR0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_K7_PERFCTR0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * Run the VM to the next GUEST_SYNC(value), and return the value passed
+ * to the sync. Any other exit from the guest is fatal.
+ */
+static uint64_t run_vm_to_sync(struct kvm_vm *vm)
+{
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ get_ucall(vm, VCPU_ID, &uc);
+ TEST_ASSERT(uc.cmd == UCALL_SYNC,
+ "Received ucall other than UCALL_SYNC: %lu", uc.cmd);
+ return uc.args[1];
+}
+
+/*
+ * In a nested environment or if the vPMU is disabled, the guest PMU
+ * might not work as architected (accessing the PMU MSRs may raise
+ * #GP, or writes could simply be discarded). In those situations,
+ * there is no point in running these tests. The guest code will perform
+ * a sanity check and then GUEST_SYNC(success). In the case of failure,
+ * the behavior of the guest on resumption is undefined.
+ */
+static bool sanity_check_pmu(struct kvm_vm *vm)
+{
+ bool success;
+
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+ success = run_vm_to_sync(vm);
+ vm_install_exception_handler(vm, GP_VECTOR, NULL);
+
+ return success;
+}
+
+static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents)
+{
+ struct kvm_pmu_event_filter *f;
+ int size = sizeof(*f) + nevents * sizeof(f->events[0]);
+
+ f = malloc(size);
+ TEST_ASSERT(f, "Out of memory");
+ memset(f, 0, size);
+ f->nevents = nevents;
+ return f;
+}
+
+static struct kvm_pmu_event_filter *event_filter(uint32_t action)
+{
+ struct kvm_pmu_event_filter *f;
+ int i;
+
+ f = make_pmu_event_filter(ARRAY_SIZE(event_list));
+ f->action = action;
+ for (i = 0; i < ARRAY_SIZE(event_list); i++)
+ f->events[i] = event_list[i];
+
+ return f;
+}
+
+/*
+ * Remove the first occurrence of 'event' (if any) from the filter's
+ * event list.
+ */
+static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f,
+ uint64_t event)
+{
+ bool found = false;
+ int i;
+
+ for (i = 0; i < f->nevents; i++) {
+ if (found)
+ f->events[i - 1] = f->events[i];
+ else
+ found = f->events[i] == event;
+ }
+ if (found)
+ f->nevents--;
+ return f;
+}
+
+static void test_without_filter(struct kvm_vm *vm)
+{
+ uint64_t count = run_vm_to_sync(vm);
+
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static uint64_t test_with_filter(struct kvm_vm *vm,
+ struct kvm_pmu_event_filter *f)
+{
+ vm_ioctl(vm, KVM_SET_PMU_EVENT_FILTER, (void *)f);
+ return run_vm_to_sync(vm);
+}
+
+static void test_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+static void test_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+/*
+ * Check for a non-zero PMU version, at least one general-purpose
+ * counter per logical processor, an EBX bit vector of length greater
+ * than 5, and EBX[5] clear.
+ */
+static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry)
+{
+ union cpuid10_eax eax = { .full = entry->eax };
+ union cpuid10_ebx ebx = { .full = entry->ebx };
+
+ return eax.split.version_id && eax.split.num_counters > 0 &&
+ eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED &&
+ !ebx.split.no_branch_instruction_retired;
+}
+
+/*
+ * Note that CPUID leaf 0xa is Intel-specific. This leaf should be
+ * clear on AMD hardware.
+ */
+static bool use_intel_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(0xa, 0);
+ return is_intel_cpu() && entry && check_intel_pmu_leaf(entry);
+}
+
+static bool is_zen1(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f;
+}
+
+static bool is_zen2(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 &&
+ x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f;
+}
+
+static bool is_zen3(uint32_t eax)
+{
+ return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f;
+}
+
+/*
+ * Determining AMD support for a PMU event requires consulting the AMD
+ * PPR for the CPU or reference material derived therefrom. The AMD
+ * test code herein has been verified to work on Zen1, Zen2, and Zen3.
+ *
+ * Feel free to add more AMD CPUs that are documented to support event
+ * select 0xc2 umask 0 as "retired branch instructions."
+ */
+static bool use_amd_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(1, 0);
+ return is_amd_cpu() && entry &&
+ (is_zen1(entry->eax) ||
+ is_zen2(entry->eax) ||
+ is_zen3(entry->eax));
+}
+
+int main(int argc, char *argv[])
+{
+ void (*guest_code)(void) = NULL;
+ struct kvm_vm *vm;
+ int r;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ r = kvm_check_cap(KVM_CAP_PMU_EVENT_FILTER);
+ if (!r) {
+ print_skip("KVM_CAP_PMU_EVENT_FILTER not supported");
+ exit(KSFT_SKIP);
+ }
+
+ if (use_intel_pmu())
+ guest_code = intel_guest_code;
+ else if (use_amd_pmu())
+ guest_code = amd_guest_code;
+
+ if (!guest_code) {
+ print_skip("Don't know how to test this guest PMU");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ if (!sanity_check_pmu(vm)) {
+ print_skip("Guest PMU is not functional");
+ exit(KSFT_SKIP);
+ }
+
+ test_without_filter(vm);
+ test_member_deny_list(vm);
+ test_member_allow_list(vm);
+ test_not_member_deny_list(vm);
+ test_not_member_allow_list(vm);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index 5a6a662..a426078 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -77,8 +77,8 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage)
switch (get_ucall(vm, vcpuid, &uc)) {
case UCALL_SYNC:
TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
- uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
- stage + 1, (ulong)uc.args[1]);
+ uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
+ stage + 1, (ulong)uc.args[1]);
return;
case UCALL_DONE:
return;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 2835a17..edac883 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -30,8 +30,8 @@ static struct kvm_vm *vm;
static void l2_guest_code(void)
{
/* Exit to L0 */
- asm volatile("inb %%dx, %%al"
- : : [port] "d" (PORT_L0_EXIT) : "rax");
+ asm volatile("inb %%dx, %%al"
+ : : [port] "d" (PORT_L0_EXIT) : "rax");
}
static void l1_guest_code(struct vmx_pages *vmx_pages)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
new file mode 100644
index 0000000..27a850f
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#include <signal.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID 0
+
+static struct kvm_vm *vm;
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+ /* Loop on the ud2 until guest state is made invalid. */
+}
+
+static void guest_code(void)
+{
+ asm volatile("ud2");
+}
+
+static void __run_vcpu_with_invalid_state(void)
+{
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_run(vm, VCPU_ID);
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
+ "Expected emulation failure, got %d\n",
+ run->emulation_failure.suberror);
+}
+
+static void run_vcpu_with_invalid_state(void)
+{
+ /*
+ * Always run twice to verify KVM handles the case where _KVM_ queues
+ * an exception with invalid state and then exits to userspace, i.e.
+ * that KVM doesn't explode if userspace ignores the initial error.
+ */
+ __run_vcpu_with_invalid_state();
+ __run_vcpu_with_invalid_state();
+}
+
+static void set_timer(void)
+{
+ struct itimerval timer;
+
+ timer.it_value.tv_sec = 0;
+ timer.it_value.tv_usec = 200;
+ timer.it_interval = timer.it_value;
+ ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0);
+}
+
+static void set_or_clear_invalid_guest_state(bool set)
+{
+ static struct kvm_sregs sregs;
+
+ if (!sregs.cr0)
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ sregs.tr.unusable = !!set;
+ vcpu_sregs_set(vm, VCPU_ID, &sregs);
+}
+
+static void set_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(true);
+}
+
+static void clear_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(false);
+}
+
+static void sigalrm_handler(int sig)
+{
+ struct kvm_vcpu_events events;
+
+ TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig);
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ /*
+ * If an exception is pending, attempt KVM_RUN with invalid guest,
+ * otherwise rearm the timer and keep doing so until the timer fires
+ * between KVM queueing an exception and re-entering the guest.
+ */
+ if (events.exception.pending) {
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+ } else {
+ set_timer();
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ if (!is_intel_cpu() || vm_is_unrestricted_guest(NULL)) {
+ print_skip("Must be run with kvm_intel.unrestricted_guest=0");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, (void *)guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+ /*
+ * Stuff invalid guest state for L2 by making TR unusuable. The next
+ * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support
+ * emulating invalid guest state for L2.
+ */
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+
+ /*
+ * Verify KVM also handles the case where userspace gains control while
+ * an exception is pending and stuffs invalid state. Run with valid
+ * guest state and a timer firing every 200us, and attempt to enter the
+ * guest with invalid state when the handler interrupts KVM with an
+ * exception pending.
+ */
+ clear_invalid_guest_state();
+ TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR,
+ "Failed to register SIGALRM handler, errno = %d (%s)",
+ errno, strerror(errno));
+
+ set_timer();
+ run_vcpu_with_invalid_state();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 478e0ae..865e171 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -46,20 +46,20 @@ static struct kvm_vm *vm;
#define MIN_STEAL_TIME 50000
struct pvclock_vcpu_time_info {
- u32 version;
- u32 pad0;
- u64 tsc_timestamp;
- u64 system_time;
- u32 tsc_to_system_mul;
- s8 tsc_shift;
- u8 flags;
- u8 pad[2];
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
} __attribute__((__packed__)); /* 32 bytes */
struct pvclock_wall_clock {
- u32 version;
- u32 sec;
- u32 nsec;
+ u32 version;
+ u32 sec;
+ u32 nsec;
} __attribute__((__packed__));
struct vcpu_runstate_info {
@@ -74,11 +74,11 @@ struct arch_vcpu_info {
};
struct vcpu_info {
- uint8_t evtchn_upcall_pending;
- uint8_t evtchn_upcall_mask;
- unsigned long evtchn_pending_sel;
- struct arch_vcpu_info arch;
- struct pvclock_vcpu_time_info time;
+ uint8_t evtchn_upcall_pending;
+ uint8_t evtchn_upcall_mask;
+ unsigned long evtchn_pending_sel;
+ struct arch_vcpu_info arch;
+ struct pvclock_vcpu_time_info time;
}; /* 64 bytes (x86) */
struct shared_info {
@@ -493,7 +493,7 @@ int main(int argc, char *argv[])
vm_ts.tv_sec = wc->sec;
vm_ts.tv_nsec = wc->nsec;
- TEST_ASSERT(wc->version && !(wc->version & 1),
+ TEST_ASSERT(wc->version && !(wc->version & 1),
"Bad wallclock version %x", wc->version);
TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old");
TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new");
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 412d852..3f4c8cf 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4059,6 +4059,9 @@
-p Pause on fail
-P Pause after each test
-v Be verbose
+
+Tests:
+ $TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER
EOF
}
diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index 694d707..dfc27cd 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1 @@
-timeout=300
+timeout=1500
diff --git a/usr/Makefile b/usr/Makefile
index b1a81a4..cc0d282 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -3,11 +3,6 @@
# kbuild file for usr/ - including initramfs image
#
-# cmd_bzip2, cmd_lzma, cmd_lzo, cmd_lz4 from scripts/Makefile.lib appends the
-# size at the end of the compressed file, which unfortunately does not work
-# with unpack_to_rootfs(). Make size_append no-op.
-override size_append := :
-
compress-y := shipped
compress-$(CONFIG_INITRAMFS_COMPRESSION_GZIP) := gzip
compress-$(CONFIG_INITRAMFS_COMPRESSION_BZIP2) := bzip2
@@ -21,7 +16,7 @@
$(obj)/initramfs_data.o: $(obj)/initramfs_inc_data
-ramfs-input := $(strip $(shell echo $(CONFIG_INITRAMFS_SOURCE)))
+ramfs-input := $(CONFIG_INITRAMFS_SOURCE)
cpio-data :=
# If CONFIG_INITRAMFS_SOURCE is empty, generate a small initramfs with the
diff --git a/usr/include/Makefile b/usr/include/Makefile
index 1c2ae13..9440380 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -99,10 +99,12 @@
cmd_hdrtest = \
$(CC) $(c_flags) -S -o /dev/null -x c /dev/null \
$(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \
- $(PERL) $(srctree)/scripts/headers_check.pl $(obj) $(SRCARCH) $<; \
+ $(PERL) $(srctree)/$(src)/headers_check.pl $(obj) $(SRCARCH) $<; \
touch $@
$(obj)/%.hdrtest: $(obj)/%.h FORCE
$(call if_changed_dep,hdrtest)
-clean-files += $(filter-out Makefile, $(notdir $(wildcard $(obj)/*)))
+# Since GNU Make 4.3, $(patsubst $(obj)/%/,%,$(wildcard $(obj)/*/)) works.
+# To support older Make versions, use a somewhat tedious way.
+clean-files += $(filter-out Makefile headers_check.pl, $(notdir $(wildcard $(obj)/*)))
diff --git a/scripts/headers_check.pl b/usr/include/headers_check.pl
similarity index 100%
rename from scripts/headers_check.pl
rename to usr/include/headers_check.pl
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 504158f..9a20f22 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -427,9 +427,6 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
#endif
kvm_async_pf_vcpu_init(vcpu);
- vcpu->pre_pcpu = -1;
- INIT_LIST_HEAD(&vcpu->blocked_vcpu_list);
-
kvm_vcpu_set_in_spin_loop(vcpu, false);
kvm_vcpu_set_dy_eligible(vcpu, false);
vcpu->preempted = false;
@@ -3163,8 +3160,10 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING
if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
return;
+#endif
if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
unsigned long rel_gfn = gfn - memslot->base_gfn;