Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-21 19:41:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm changes for 6.5-rc1:

Browse Source 
core:
 - replace strlcpy with strscpy
 - EDID changes to support further conversion to struct drm_edid
 - Move i915 DSC parameter code to common DRM helpers
 - Add Colorspace functionality
 
 aperture:
 - ignore framebuffers with non-primary devices
 
 fbdev:
 - use fbdev i/o helpers
 - add Kconfig options for fb_ops helpers
 - use new fb io helpers directly in drivers
 
 sysfs:
 - export DRM connector ID
 
 scheduler:
 - Avoid an infinite loop
 
 ttm:
 - store function table in .rodata
 - Add query for TTM mem limit
 - Add NUMA awareness to pools
 - Export ttm_pool_fini()
 
 bridge:
 - fsl-ldb: support i.MX6SX
 - lt9211, lt9611: remove blanking packets
 - tc358768: implement input bus formats, devm cleanups
 - ti-snd65dsi86: implement wait_hpd_asserted
 - analogix: fix endless probe loop
 - samsung-dsim: support swapped clock, fix enabling, support var clock
 - display-connector: Add support for external power supply
 - imx: Fix module linking
 - tc358762: Support reset GPIO
 
 panel:
 - nt36523: Support Lenovo J606F
 - st7703: Support Anbernic RG353V-V2
 - InnoLux G070ACE-L01 support
 - boe-tv101wum-nl6: Improve initialization
 - sharp-ls043t1le001: Mode fixes
 - simple: BOE EV121WXM-N10-1850, S6D7AA0
 - Ampire AM-800480L1TMQW-T00H
 - Rocktech RK043FN48H
 - Starry himax83102-j02
 - Starry ili9882t
 
 amdgpu:
 - add new ctx query flag to handle reset better
 - add new query/set shadow buffer for rdna3
 - DCN 3.2/3.1.x/3.0.x updates
 - Enable DC_FP on loongarch
 - PCIe fix for RDNA2
 - improve DC FAMS/SubVP support for better power management
 - partition support for lots of engines
 - Take NUMA into account when allocating memory
 - Add new DRM_AMDGPU_WERROR config parameter to help with CI
 - Initial SMU13 overdrive support
 - Add support for new colorspace KMS API
 - W=1 fixes
 
 amdkfd:
 - Query TTM mem limit rather than hardcoding it
 - GC 9.4.3 partition support
 - Handle NUMA for partitions
 - Add debugger interface for enabling gdb
 - Add KFD event age tracking
 
 radeon:
 - Fix possible UAF
 
 i915:
 - new getparam for PXP support
 - GSC/MEI proxy driver
 - Meteorlake display enablement
 - avoid clearing preallocated framebuffers with TTM
 - implement framebuffer mmap support
 - Disable sampler indirect state in bindless heap
 - Enable fdinfo for GuC backends
 - GuC loading and firmware table handling fixes
 - Various refactors for multi-tile enablement
 - Define MOCS and PAT tables for MTL
 - GSC/MEI support for Meteorlake
 - PMU multi-tile support
 - Large driver kernel doc cleanup
 - Allow VRR toggling and arbitrary refresh rates
 - Support async flips on linear buffers on display ver 12+
 - Expose CRTC CTM property on ILK/SNB/VLV
 - New debugfs for display clock frequencies
 - Hotplug refactoring
 - Display refactoring
 - I915_GEM_CREATE_EXT_SET_PAT for Mesa on Meteorlake
 - Use large rings for compute contexts
 - HuC loading for MTL
 - Allow user to set cache at BO creation
 - MTL powermanagement enhancements
 - Switch to dedicated workqueues to stop using flush_scheduled_work()
 - Move display runtime init under display/
 - Remove 10bit gamma on desktop gen3 parts, they don't support it
 
 habanalabs:
 - uapi: return 0 for user queries if there was a h/w or f/w error
 - Add pci health check when we lose connection with the firmware. This can be used to
   distinguish between pci link down and firmware getting stuck.
 - Add more info to the error print when TPC interrupt occur.
 - Firmware fixes
 
 msm:
 - Adreno A660 bindings
 - SM8350 MDSS bindings fix
 - Added support for DPU on sm6350 and sm6375 platforms
 - Implemented tearcheck support to support vsync on SM150 and newer platforms
 - Enabled missing features (DSPP, DSC, split display) on sc8180x, sc8280xp, sm8450
 - Added support for DSI and 28nm DSI PHY on MSM8226 platform
 - Added support for DSI on sm6350 and sm6375 platforms
 - Added support for display controller on MSM8226 platform
 - A690 GPU support
 - Move cmdstream dumping out of fence signaling path
 - a610 support
 - Support for a6xx devices without GMU
 
 nouveau:
 - NULL ptr before deref fixes
 
 armada:
 - implement fbdev emulation as client
 
 sun4i:
 - fix mipi-dsi dotclock
 - release clocks
 
 vc4:
 - rgb range toggle property
 - BT601 / BT2020 HDMI support
 
 vkms:
 - convert to drmm helpers
 - add reflection and rotation support
 - fix rgb565 conversion
 
 gma500:
 - fix iomem access
 
 shmobile:
 - support renesas soc platform
 - enable fbdev
 
 mxsfb:
 - Add support for i.MX93 LCDIF
 
 stm:
 - dsi: Use devm_ helper
 - ltdc: Fix potential invalid pointer deref
 
 renesas:
 - Group drivers in renesas subdirectory to prepare for new platform
 - Drop deprecated R-Car H3 ES1.x support
 
 meson:
 - Add support for MIPI DSI displays
 
 virtio:
 - add sync object support
 
 mediatek:
 - Add display binding document for MT6795
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEEKbZHaGwW9KfbeusDHTzWXnEhr4FAmSc3UwACgkQDHTzWXnE
 hr69fQ/+PF9L7FSB/qfjaoqJnk6wJyCehv7pDX2/UK7FUrW0e4EwNVx4KKIRqO/P
 pKSU9wRlC72ViGgqOYnw0pwzuh45630vWo1stbgxipU2cvM6Ywlq8FiQFdymFe+P
 tLYWe5MR55Y+E9Y+bCrKn2yvQ7v+f6EZ6ITIX7mrXL77Bpxhv58VzmZawkxmw5MV
 vwhSqJaaeeWNoyfSIDdN8Oj9fE6ScTyiA0YisOP6jnK/TiQofXQxFrMIdKctCcoA
 HjolfEEPVCDOSBipkV3hLiyN8lXmt47BmuHp9opSL/g1aASteVeD1/GrccTaA4xV
 ah+Jx1hBLcH5sm8CZzbCcHhNu3ILnPCFZFCx8gwflQqmDIOZvoMdL75j7lgqJZG8
 TePEiifG3kYO/ZiDc5TUBdeMfbgeehPOsxbvOlA3LxJrgyxe/5o9oejX2Uvvzhoq
 9fno1PLqeCILqYaMiCocJwyTw/2VKYCCH7Wiypd4o3h0nmAbbqPT3KeZgNOjoa2X
 GXpiIU9rTQ8LZgSmOXdCt2rc9Jb6q+eCiDgrZzAukbP8veQyOvO16Nx1+XzLhOYc
 BfjEOoA7nBJD+UPLWkwj42gKtoEWN7IOMTHgcK11d8jdpGISGupl/1nntGhYk0jO
 +3RRZXMB/Gjwe9ge4K9bFC81pbfuAE7ELQtPsgV9LapMmWHKccY=
 =FmUA
 -----END PGP SIGNATURE-----

Merge tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is one set of patches to misc for a i915 gsc/mei proxy driver.

  Otherwise it's mostly amdgpu/i915/msm, lots of hw enablement and lots
  of refactoring.

  core:
   - replace strlcpy with strscpy
   - EDID changes to support further conversion to struct drm_edid
   - Move i915 DSC parameter code to common DRM helpers
   - Add Colorspace functionality

  aperture:
   - ignore framebuffers with non-primary devices

  fbdev:
   - use fbdev i/o helpers
   - add Kconfig options for fb_ops helpers
   - use new fb io helpers directly in drivers

  sysfs:
   - export DRM connector ID

  scheduler:
   - Avoid an infinite loop

  ttm:
   - store function table in .rodata
   - Add query for TTM mem limit
   - Add NUMA awareness to pools
   - Export ttm_pool_fini()

  bridge:
   - fsl-ldb: support i.MX6SX
   - lt9211, lt9611: remove blanking packets
   - tc358768: implement input bus formats, devm cleanups
   - ti-snd65dsi86: implement wait_hpd_asserted
   - analogix: fix endless probe loop
   - samsung-dsim: support swapped clock, fix enabling, support var
     clock
   - display-connector: Add support for external power supply
   - imx: Fix module linking
   - tc358762: Support reset GPIO

  panel:
   - nt36523: Support Lenovo J606F
   - st7703: Support Anbernic RG353V-V2
   - InnoLux G070ACE-L01 support
   - boe-tv101wum-nl6: Improve initialization
   - sharp-ls043t1le001: Mode fixes
   - simple: BOE EV121WXM-N10-1850, S6D7AA0
   - Ampire AM-800480L1TMQW-T00H
   - Rocktech RK043FN48H
   - Starry himax83102-j02
   - Starry ili9882t

  amdgpu:
   - add new ctx query flag to handle reset better
   - add new query/set shadow buffer for rdna3
   - DCN 3.2/3.1.x/3.0.x updates
   - Enable DC_FP on loongarch
   - PCIe fix for RDNA2
   - improve DC FAMS/SubVP support for better power management
   - partition support for lots of engines
   - Take NUMA into account when allocating memory
   - Add new DRM_AMDGPU_WERROR config parameter to help with CI
   - Initial SMU13 overdrive support
   - Add support for new colorspace KMS API
   - W=1 fixes

  amdkfd:
   - Query TTM mem limit rather than hardcoding it
   - GC 9.4.3 partition support
   - Handle NUMA for partitions
   - Add debugger interface for enabling gdb
   - Add KFD event age tracking

  radeon:
   - Fix possible UAF

  i915:
   - new getparam for PXP support
   - GSC/MEI proxy driver
   - Meteorlake display enablement
   - avoid clearing preallocated framebuffers with TTM
   - implement framebuffer mmap support
   - Disable sampler indirect state in bindless heap
   - Enable fdinfo for GuC backends
   - GuC loading and firmware table handling fixes
   - Various refactors for multi-tile enablement
   - Define MOCS and PAT tables for MTL
   - GSC/MEI support for Meteorlake
   - PMU multi-tile support
   - Large driver kernel doc cleanup
   - Allow VRR toggling and arbitrary refresh rates
   - Support async flips on linear buffers on display ver 12+
   - Expose CRTC CTM property on ILK/SNB/VLV
   - New debugfs for display clock frequencies
   - Hotplug refactoring
   - Display refactoring
   - I915_GEM_CREATE_EXT_SET_PAT for Mesa on Meteorlake
   - Use large rings for compute contexts
   - HuC loading for MTL
   - Allow user to set cache at BO creation
   - MTL powermanagement enhancements
   - Switch to dedicated workqueues to stop using flush_scheduled_work()
   - Move display runtime init under display/
   - Remove 10bit gamma on desktop gen3 parts, they don't support it

  habanalabs:
   - uapi: return 0 for user queries if there was a h/w or f/w error
   - Add pci health check when we lose connection with the firmware.
     This can be used to distinguish between pci link down and firmware
     getting stuck.
   - Add more info to the error print when TPC interrupt occur.
   - Firmware fixes

  msm:
   - Adreno A660 bindings
   - SM8350 MDSS bindings fix
   - Added support for DPU on sm6350 and sm6375 platforms
   - Implemented tearcheck support to support vsync on SM150 and newer
     platforms
   - Enabled missing features (DSPP, DSC, split display) on sc8180x,
     sc8280xp, sm8450
   - Added support for DSI and 28nm DSI PHY on MSM8226 platform
   - Added support for DSI on sm6350 and sm6375 platforms
   - Added support for display controller on MSM8226 platform
   - A690 GPU support
   - Move cmdstream dumping out of fence signaling path
   - a610 support
   - Support for a6xx devices without GMU

  nouveau:
   - NULL ptr before deref fixes

  armada:
   - implement fbdev emulation as client

  sun4i:
   - fix mipi-dsi dotclock
   - release clocks

  vc4:
   - rgb range toggle property
   - BT601 / BT2020 HDMI support

  vkms:
   - convert to drmm helpers
   - add reflection and rotation support
   - fix rgb565 conversion

  gma500:
   - fix iomem access

  shmobile:
   - support renesas soc platform
   - enable fbdev

  mxsfb:
   - Add support for i.MX93 LCDIF

  stm:
   - dsi: Use devm_ helper
   - ltdc: Fix potential invalid pointer deref

  renesas:
   - Group drivers in renesas subdirectory to prepare for new platform
   - Drop deprecated R-Car H3 ES1.x support

  meson:
   - Add support for MIPI DSI displays

  virtio:
   - add sync object support

  mediatek:
   - Add display binding document for MT6795"

* tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm: (1791 commits)
  drm/i915: Fix a NULL vs IS_ERR() bug
  drm/i915: make i915_drm_client_fdinfo() reference conditional again
  drm/i915/huc: Fix missing error code in intel_huc_init()
  drm/i915/gsc: take a wakeref for the proxy-init-completion check
  drm/msm/a6xx: Add A610 speedbin support
  drm/msm/a6xx: Add A619_holi speedbin support
  drm/msm/a6xx: Use adreno_is_aXYZ macros in speedbin matching
  drm/msm/a6xx: Use "else if" in GPU speedbin rev matching
  drm/msm/a6xx: Fix some A619 tunables
  drm/msm/a6xx: Add A610 support
  drm/msm/a6xx: Add support for A619_holi
  drm/msm/adreno: Disable has_cached_coherent in GMU wrapper configurations
  drm/msm/a6xx: Introduce GMU wrapper support
  drm/msm/a6xx: Move CX GMU power counter enablement to hw_init
  drm/msm/a6xx: Extend and explain UBWC config
  drm/msm/a6xx: Remove both GBIF and RBBM GBIF halt on hw init
  drm/msm/a6xx: Add a helper for software-resetting the GPU
  drm/msm/a6xx: Improve a6xx_bus_clear_pending_transactions()
  drm/msm/a6xx: Move a6xx_bus_clear_pending_transactions to a6xx_gpu
  drm/msm/a6xx: Move force keepalive vote removal to a6xx_gmu_force_off()
  ...
This commit is contained in:
Linus Torvalds 2023-06-29 11:00:17 -07:00
commit 1b722407a1
1245 changed files with 80441 additions and 22850 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.mailmap
View File

@ -332,6 +332,7 @@ Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com>
Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com>
Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com>
Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@nvidia.com>
Maxime Ripard <mripard@kernel.org> <maxime@cerno.tech>
Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com>
Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com>
Mayuresh Janorkar <mayur@ti.com>

118
Documentation/devicetree/bindings/display/amlogic,meson-g12a-dw-mipi-dsi.yaml Normal file
View File

@ -0,0 +1,118 @@
# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
# Copyright 2020 BayLibre, SAS
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/amlogic,meson-g12a-dw-mipi-dsi.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Amlogic specific extensions to the Synopsys Designware MIPI DSI Host Controller
maintainers:
- Neil Armstrong <neil.armstrong@linaro.org>
description: |
The Amlogic Meson Synopsys Designware Integration is composed of
- A Synopsys DesignWare MIPI DSI Host Controller IP
- A TOP control block controlling the Clocks & Resets of the IP
allOf:
- $ref: dsi-controller.yaml#
properties:
compatible:
enum:
- amlogic,meson-g12a-dw-mipi-dsi
reg:
maxItems: 1
clocks:
minItems: 3
maxItems: 4
clock-names:
minItems: 3
items:
- const: pclk
- const: bit
- const: px
- const: meas
resets:
maxItems: 1
reset-names:
items:
- const: top
phys:
maxItems: 1
phy-names:
items:
- const: dphy
ports:
$ref: /schemas/graph.yaml#/properties/ports
properties:
port@0:
$ref: /schemas/graph.yaml#/properties/port
description: Input node to receive pixel data.
port@1:
$ref: /schemas/graph.yaml#/properties/port
description: DSI output node to panel.
required:
- port@0
- port@1
required:
- compatible
- reg
- clocks
- clock-names
- resets
- reset-names
- phys
- phy-names
- ports
unevaluatedProperties: false
examples:
- |
dsi@6000 {
compatible = "amlogic,meson-g12a-dw-mipi-dsi";
reg = <0x6000 0x400>;
resets = <&reset_top>;
reset-names = "top";
clocks = <&clk_pclk>, <&bit_clk>, <&clk_px>;
clock-names = "pclk", "bit", "px";
phys = <&mipi_dphy>;
phy-names = "dphy";
ports {
#address-cells = <1>;
#size-cells = <0>;
/* VPU VENC Input */
mipi_dsi_venc_port: port@0 {
reg = <0>;
mipi_dsi_in: endpoint {
remote-endpoint = <&dpi_out>;
};
};
/* DSI Output */
mipi_dsi_panel_port: port@1 {
reg = <1>;
mipi_out_panel: endpoint {
remote-endpoint = <&mipi_in_panel>;
};
};
};
};

5
Documentation/devicetree/bindings/display/amlogic,meson-vpu.yaml
View File

@ -96,6 +96,11 @@ properties:
description:
A port node pointing to the HDMI-TX port node.
port@2:
$ref: /schemas/graph.yaml#/properties/port
description:
A port node pointing to the DPI port node (e.g. DSI or LVDS transceiver).
"#address-cells":
const: 1

5
Documentation/devicetree/bindings/display/bridge/fsl,ldb.yaml
View File

@ -17,6 +17,7 @@ description: |
properties:
compatible:
enum:
- fsl,imx6sx-ldb
- fsl,imx8mp-ldb
- fsl,imx93-ldb
@ -64,7 +65,9 @@ allOf:
properties:
compatible:
contains:
const: fsl,imx93-ldb
enum:
- fsl,imx6sx-ldb
- fsl,imx93-ldb
then:
properties:
ports:

35
Documentation/devicetree/bindings/display/bridge/samsung,mipi-dsim.yaml
View File

@ -70,7 +70,9 @@ properties:
samsung,burst-clock-frequency:
$ref: /schemas/types.yaml#/definitions/uint32
description:
DSIM high speed burst mode frequency.
DSIM high speed burst mode frequency. If absent,
the pixel clock from the attached device or bridge
will be used instead.
samsung,esc-clock-frequency:
$ref: /schemas/types.yaml#/definitions/uint32
@ -80,7 +82,8 @@ properties:
samsung,pll-clock-frequency:
$ref: /schemas/types.yaml#/definitions/uint32
description:
DSIM oscillator clock frequency.
DSIM oscillator clock frequency. If absent, the clock frequency
of sclk_mipi will be used instead.
phys:
maxItems: 1
@ -100,20 +103,42 @@ properties:
specified.
port@1:
$ref: /schemas/graph.yaml#/properties/port
$ref: /schemas/graph.yaml#/$defs/port-base
unevaluatedProperties: false
description:
DSI output port node to the panel or the next bridge
in the chain.
properties:
endpoint:
$ref: /schemas/media/video-interfaces.yaml#
unevaluatedProperties: false
properties:
data-lanes:
minItems: 1
maxItems: 4
uniqueItems: true
items:
enum: [ 1, 2, 3, 4 ]
lane-polarities:
minItems: 1
maxItems: 5
description:
The Samsung MIPI DSI IP requires that all the data lanes have
the same polarity.
dependencies:
lane-polarities: [data-lanes]
required:
- clock-names
- clocks
- compatible
- interrupts
- reg
- samsung,burst-clock-frequency
- samsung,esc-clock-frequency
- samsung,pll-clock-frequency
allOf:
- $ref: ../dsi-controller.yaml#

3
Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml
View File

@ -21,6 +21,9 @@ properties:
maxItems: 1
description: virtual channel number of a DSI peripheral
reset-gpios:
maxItems: 1
vddc-supply:
description: Regulator for 1.2V internal core power.

14
Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml
View File

@ -4,16 +4,24 @@
$id: http://devicetree.org/schemas/display/bridge/toshiba,tc358767.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Toshiba TC358767 eDP bridge
title: Toshiba TC358767/TC358867/TC9595 DSI/DPI/eDP bridge
maintainers:
- Andrey Gusakov <andrey.gusakov@cogentembedded.com>
description: The TC358767 is bridge device which converts DSI/DPI to eDP/DP
description: |
The TC358767/TC358867/TC9595 is bridge device which
converts DSI/DPI to eDP/DP .
properties:
compatible:
const: toshiba,tc358767
oneOf:
- items:
- enum:
- toshiba,tc358867
- toshiba,tc9595
- const: toshiba,tc358767
- const: toshiba,tc358767
reg:
enum:

3
Documentation/devicetree/bindings/display/connector/hdmi-connector.yaml
View File

@ -36,6 +36,9 @@ properties:
description: GPIO signal to enable DDC bus
maxItems: 1
hdmi-pwr-supply:
description: Power supply for the HDMI +5V Power pin
port:
$ref: /schemas/graph.yaml#/properties/port
description: Connection to controller providing HDMI signals

7
Documentation/devicetree/bindings/display/fsl,lcdif.yaml
View File

@ -21,6 +21,7 @@ properties:
- fsl,imx28-lcdif
- fsl,imx6sx-lcdif
- fsl,imx8mp-lcdif
- fsl,imx93-lcdif
- items:
- enum:
- fsl,imx6sl-lcdif
@ -88,7 +89,9 @@ allOf:
properties:
compatible:
contains:
const: fsl,imx8mp-lcdif
enum:
- fsl,imx8mp-lcdif
- fsl,imx93-lcdif
then:
properties:
clocks:
@ -107,6 +110,7 @@ allOf:
enum:
- fsl,imx6sx-lcdif
- fsl,imx8mp-lcdif
- fsl,imx93-lcdif
then:
properties:
clocks:
@ -123,6 +127,7 @@ allOf:
- fsl,imx8mm-lcdif
- fsl,imx8mn-lcdif
- fsl,imx8mp-lcdif
- fsl,imx93-lcdif
then:
required:
- power-domains

1
Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml
View File

@ -27,6 +27,7 @@ properties:
- items:
- enum:
- mediatek,mt2712-disp-aal
- mediatek,mt6795-disp-aal
- const: mediatek,mt8173-disp-aal
- items:
- enum:

1
Documentation/devicetree/bindings/display/mediatek/mediatek,color.yaml
View File

@ -33,6 +33,7 @@ properties:
- const: mediatek,mt2701-disp-color
- items:
- enum:
- mediatek,mt6795-disp-color
- mediatek,mt8183-disp-color
- mediatek,mt8186-disp-color
- mediatek,mt8188-disp-color

23
Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml
View File

@ -17,15 +17,20 @@ description: |
properties:
compatible:
enum:
- mediatek,mt2701-dpi
- mediatek,mt7623-dpi
- mediatek,mt8173-dpi
- mediatek,mt8183-dpi
- mediatek,mt8186-dpi
- mediatek,mt8188-dp-intf
- mediatek,mt8192-dpi
- mediatek,mt8195-dp-intf
oneOf:
- enum:
- mediatek,mt2701-dpi
- mediatek,mt7623-dpi
- mediatek,mt8173-dpi
- mediatek,mt8183-dpi
- mediatek,mt8186-dpi
- mediatek,mt8188-dp-intf
- mediatek,mt8192-dpi
- mediatek,mt8195-dp-intf
- items:
- enum:
- mediatek,mt6795-dpi
- const: mediatek,mt8183-dpi
reg:
maxItems: 1

19
Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
View File

@ -22,13 +22,18 @@ allOf:
properties:
compatible:
enum:
- mediatek,mt2701-dsi
- mediatek,mt7623-dsi
- mediatek,mt8167-dsi
- mediatek,mt8173-dsi
- mediatek,mt8183-dsi
- mediatek,mt8186-dsi
oneOf:
- enum:
- mediatek,mt2701-dsi
- mediatek,mt7623-dsi
- mediatek,mt8167-dsi
- mediatek,mt8173-dsi
- mediatek,mt8183-dsi
- mediatek,mt8186-dsi
- items:
- enum:
- mediatek,mt6795-dsi
- const: mediatek,mt8173-dsi
reg:
maxItems: 1

4
Documentation/devicetree/bindings/display/mediatek/mediatek,gamma.yaml
View File

@ -24,6 +24,10 @@ properties:
- enum:
- mediatek,mt8173-disp-gamma
- mediatek,mt8183-disp-gamma
- items:
- enum:
- mediatek,mt6795-disp-gamma
- const: mediatek,mt8173-disp-gamma
- items:
- enum:
- mediatek,mt8186-disp-gamma

3
Documentation/devicetree/bindings/display/mediatek/mediatek,merge.yaml
View File

@ -24,6 +24,9 @@ properties:
- enum:
- mediatek,mt8173-disp-merge
- mediatek,mt8195-disp-merge
- items:
- const: mediatek,mt6795-disp-merge
- const: mediatek,mt8173-disp-merge
reg:
maxItems: 1

3
Documentation/devicetree/bindings/display/mediatek/mediatek,od.yaml
View File

@ -24,6 +24,9 @@ properties:
- enum:
- mediatek,mt2712-disp-od
- mediatek,mt8173-disp-od
- items:
- const: mediatek,mt6795-disp-od
- const: mediatek,mt8173-disp-od
reg:
maxItems: 1

4
Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml
View File

@ -31,6 +31,10 @@ properties:
- mediatek,mt7623-disp-ovl
- mediatek,mt2712-disp-ovl
- const: mediatek,mt2701-disp-ovl
- items:
- enum:
- mediatek,mt6795-disp-ovl
- const: mediatek,mt8173-disp-ovl
- items:
- enum:
- mediatek,mt8188-disp-ovl

4
Documentation/devicetree/bindings/display/mediatek/mediatek,rdma.yaml
View File

@ -37,6 +37,10 @@ properties:
- mediatek,mt7623-disp-rdma
- mediatek,mt2712-disp-rdma
- const: mediatek,mt2701-disp-rdma
- items:
- enum:
- mediatek,mt6795-disp-rdma
- const: mediatek,mt8173-disp-rdma
- items:
- enum:
- mediatek,mt8186-disp-rdma

3
Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml
View File

@ -23,6 +23,9 @@ properties:
oneOf:
- enum:
- mediatek,mt8173-disp-split
- items:
- const: mediatek,mt6795-disp-split
- const: mediatek,mt8173-disp-split
reg:
maxItems: 1

3
Documentation/devicetree/bindings/display/mediatek/mediatek,ufoe.yaml
View File

@ -24,6 +24,9 @@ properties:
oneOf:
- enum:
- mediatek,mt8173-disp-ufoe
- items:
- const: mediatek,mt6795-disp-ufoe
- const: mediatek,mt8173-disp-ufoe
reg:
maxItems: 1

3
Documentation/devicetree/bindings/display/mediatek/mediatek,wdma.yaml
View File

@ -23,6 +23,9 @@ properties:
oneOf:
- enum:
- mediatek,mt8173-disp-wdma
- items:
- const: mediatek,mt6795-disp-wdma
- const: mediatek,mt8173-disp-wdma
reg:
maxItems: 1

1
Documentation/devicetree/bindings/display/msm/dp-controller.yaml
View File

@ -29,6 +29,7 @@ properties:
- items:
- enum:
- qcom,sm8450-dp
- qcom,sm8550-dp
- const: qcom,sm8350-dp
reg:

6
Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
View File

@ -15,6 +15,7 @@ properties:
- items:
- enum:
- qcom,apq8064-dsi-ctrl
- qcom,msm8226-dsi-ctrl
- qcom,msm8916-dsi-ctrl
- qcom,msm8953-dsi-ctrl
- qcom,msm8974-dsi-ctrl
@ -26,6 +27,8 @@ properties:
- qcom,sdm660-dsi-ctrl
- qcom,sdm845-dsi-ctrl
- qcom,sm6115-dsi-ctrl
- qcom,sm6350-dsi-ctrl
- qcom,sm6375-dsi-ctrl
- qcom,sm8150-dsi-ctrl
- qcom,sm8250-dsi-ctrl
- qcom,sm8350-dsi-ctrl
@ -256,6 +259,7 @@ allOf:
compatible:
contains:
enum:
- qcom,msm8226-dsi-ctrl
- qcom,msm8974-dsi-ctrl
then:
properties:
@ -297,6 +301,7 @@ allOf:
contains:
enum:
- qcom,msm8998-dsi-ctrl
- qcom,sm6350-dsi-ctrl
then:
properties:
clocks:
@ -364,6 +369,7 @@ allOf:
enum:
- qcom,sdm845-dsi-ctrl
- qcom,sm6115-dsi-ctrl
- qcom,sm6375-dsi-ctrl
then:
properties:
clocks:

3
Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
View File

@ -15,10 +15,11 @@ allOf:
properties:
compatible:
enum:
- qcom,dsi-phy-28nm-8226
- qcom,dsi-phy-28nm-8960
- qcom,dsi-phy-28nm-hpm
- qcom,dsi-phy-28nm-hpm-fam-b
- qcom,dsi-phy-28nm-lp
- qcom,dsi-phy-28nm-8960
reg:
items:

51
Documentation/devicetree/bindings/display/msm/gmu.yaml
View File

@ -19,16 +19,18 @@ description: |
properties:
compatible:
items:
- pattern: '^qcom,adreno-gmu-6[0-9][0-9]\.[0-9]$'
- const: qcom,adreno-gmu
oneOf:
- items:
- pattern: '^qcom,adreno-gmu-6[0-9][0-9]\.[0-9]$'
- const: qcom,adreno-gmu
- const: qcom,adreno-gmu-wrapper
reg:
minItems: 3
minItems: 1
maxItems: 4
reg-names:
minItems: 3
minItems: 1
maxItems: 4
clocks:
@ -44,7 +46,6 @@ properties:
- description: GMU HFI interrupt
- description: GMU interrupt
interrupt-names:
items:
- const: hfi
@ -72,14 +73,8 @@ required:
- compatible
- reg
- reg-names
- clocks
- clock-names
- interrupts
- interrupt-names
- power-domains
- power-domain-names
- iommus
- operating-points-v2
additionalProperties: false
@ -122,6 +117,7 @@ allOf:
contains:
enum:
- qcom,adreno-gmu-635.0
- qcom,adreno-gmu-660.1
then:
properties:
reg:
@ -217,6 +213,28 @@ allOf:
- const: axi
- const: memnoc
- if:
properties:
compatible:
contains:
const: qcom,adreno-gmu-wrapper
then:
properties:
reg:
items:
- description: GMU wrapper register space
reg-names:
items:
- const: gmu
else:
required:
- clocks
- clock-names
- interrupts
- interrupt-names
- iommus
- operating-points-v2
examples:
- |
#include <dt-bindings/clock/qcom,gpucc-sdm845.h>
@ -249,3 +267,12 @@ examples:
iommus = <&adreno_smmu 5>;
operating-points-v2 = <&gmu_opp_table>;
};
gmu_wrapper: gmu@596a000 {
compatible = "qcom,adreno-gmu-wrapper";
reg = <0x0596a000 0x30000>;
reg-names = "gmu";
power-domains = <&gpucc GPU_CX_GDSC>,
<&gpucc GPU_GX_GDSC>;
power-domain-names = "cx", "gx";
};

61
Documentation/devicetree/bindings/display/msm/gpu.yaml
View File

@ -36,10 +36,7 @@ properties:
reg-names:
minItems: 1
items:
- const: kgsl_3d0_reg_memory
- const: cx_mem
- const: cx_dbgc
maxItems: 3
interrupts:
maxItems: 1
@ -157,16 +154,62 @@ allOf:
required:
- clocks
- clock-names
- if:
properties:
compatible:
contains:
pattern: '^qcom,adreno-6[0-9][0-9]\.[0-9]$'
then: # Since Adreno 6xx series clocks should be defined in GMU
enum:
- qcom,adreno-610.0
- qcom,adreno-619.1
then:
properties:
clocks: false
clock-names: false
clocks:
minItems: 6
maxItems: 6
clock-names:
items:
- const: core
description: GPU Core clock
- const: iface
description: GPU Interface clock
- const: mem_iface
description: GPU Memory Interface clock
- const: alt_mem_iface
description: GPU Alternative Memory Interface clock
- const: gmu
description: CX GMU clock
- const: xo
description: GPUCC clocksource clock
reg-names:
minItems: 1
items:
- const: kgsl_3d0_reg_memory
- const: cx_dbgc
required:
- clocks
- clock-names
else:
if:
properties:
compatible:
contains:
pattern: '^qcom,adreno-6[0-9][0-9]\.[0-9]$'
then: # Starting with A6xx, the clocks are usually defined in the GMU node
properties:
clocks: false
clock-names: false
reg-names:
minItems: 1
items:
- const: kgsl_3d0_reg_memory
- const: cx_mem
- const: cx_dbgc
examples:
- |

1
Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
View File

@ -22,6 +22,7 @@ properties:
- items:
- enum:
- qcom,apq8084-mdp5
- qcom,msm8226-mdp5
- qcom,msm8916-mdp5
- qcom,msm8917-mdp5
- qcom,msm8953-mdp5

1
Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml
View File

@ -125,6 +125,7 @@ patternProperties:
- qcom,dsi-phy-14nm-660
- qcom,dsi-phy-14nm-8953
- qcom,dsi-phy-20nm
- qcom,dsi-phy-28nm-8226
- qcom,dsi-phy-28nm-hpm
- qcom,dsi-phy-28nm-lp
- qcom,hdmi-phy-8084

23
Documentation/devicetree/bindings/display/msm/qcom,sc7180-dpu.yaml
View File

@ -13,7 +13,10 @@ $ref: /schemas/display/msm/dpu-common.yaml#
properties:
compatible:
const: qcom,sc7180-dpu
enum:
- qcom,sc7180-dpu
- qcom,sm6350-dpu
- qcom,sm6375-dpu
reg:
items:
@ -26,6 +29,7 @@ properties:
- const: vbif
clocks:
minItems: 6
items:
- description: Display hf axi clock
- description: Display ahb clock
@ -33,8 +37,10 @@ properties:
- description: Display lut clock
- description: Display core clock
- description: Display vsync clock
- description: Display core throttle clock
clock-names:
minItems: 6
items:
- const: bus
- const: iface
@ -42,6 +48,7 @@ properties:
- const: lut
- const: core
- const: vsync
- const: throttle
required:
- compatible
@ -52,6 +59,20 @@ required:
unevaluatedProperties: false
allOf:
- if:
properties:
compatible:
const: qcom,sm6375-dpu
then:
properties:
clocks:
minItems: 7
clock-names:
minItems: 7
examples:
- |
#include <dt-bindings/clock/qcom,dispcc-sc7180.h>

213
Documentation/devicetree/bindings/display/msm/qcom,sm6350-mdss.yaml Normal file
View File

@ -0,0 +1,213 @@
# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/msm/qcom,sm6350-mdss.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Qualcomm SM6350 Display MDSS
maintainers:
- Krishna Manikandan <quic_mkrishn@quicinc.com>
description:
SM6350 MSM Mobile Display Subsystem (MDSS), which encapsulates sub-blocks
like DPU display controller, DSI and DP interfaces etc.
$ref: /schemas/display/msm/mdss-common.yaml#
properties:
compatible:
const: qcom,sm6350-mdss
clocks:
items:
- description: Display AHB clock from gcc
- description: Display AXI clock from gcc
- description: Display core clock
clock-names:
items:
- const: iface
- const: bus
- const: core
iommus:
maxItems: 1
interconnects:
maxItems: 2
interconnect-names:
maxItems: 2
patternProperties:
"^display-controller@[0-9a-f]+$":
type: object
properties:
compatible:
const: qcom,sm6350-dpu
"^dsi@[0-9a-f]+$":
type: object
properties:
compatible:
items:
- const: qcom,sm6350-dsi-ctrl
- const: qcom,mdss-dsi-ctrl
"^phy@[0-9a-f]+$":
type: object
properties:
compatible:
const: qcom,dsi-phy-10nm
unevaluatedProperties: false
examples:
- |
#include <dt-bindings/clock/qcom,dispcc-sm6350.h>
#include <dt-bindings/clock/qcom,gcc-sm6350.h>
#include <dt-bindings/clock/qcom,rpmh.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/qcom-rpmpd.h>
display-subsystem@ae00000 {
compatible = "qcom,sm6350-mdss";
reg = <0x0ae00000 0x1000>;
reg-names = "mdss";
power-domains = <&dispcc MDSS_GDSC>;
clocks = <&gcc GCC_DISP_AHB_CLK>,
<&gcc GCC_DISP_AXI_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>;
clock-names = "iface", "bus", "core";
interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
interrupt-controller;
#interrupt-cells = <1>;
iommus = <&apps_smmu 0x800 0x2>;
#address-cells = <1>;
#size-cells = <1>;
ranges;
display-controller@ae01000 {
compatible = "qcom,sm6350-dpu";
reg = <0x0ae01000 0x8f000>,
<0x0aeb0000 0x2008>;
reg-names = "mdp", "vbif";
clocks = <&gcc GCC_DISP_AXI_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>,
<&dispcc DISP_CC_MDSS_ROT_CLK>,
<&dispcc DISP_CC_MDSS_MDP_LUT_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>,
<&dispcc DISP_CC_MDSS_VSYNC_CLK>;
clock-names = "bus", "iface", "rot", "lut", "core",
"vsync";
assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>,
<&dispcc DISP_CC_MDSS_VSYNC_CLK>,
<&dispcc DISP_CC_MDSS_ROT_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>;
assigned-clock-rates = <300000000>,
<19200000>,
<19200000>,
<19200000>;
interrupt-parent = <&mdss>;
interrupts = <0>;
operating-points-v2 = <&mdp_opp_table>;
power-domains = <&rpmhpd SM6350_CX>;
ports {
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
dpu_intf1_out: endpoint {
remote-endpoint = <&dsi0_in>;
};
};
port@1 {
reg = <1>;
dpu_intf2_out: endpoint {
remote-endpoint = <&dsi1_in>;
};
};
};
};
dsi@ae94000 {
compatible = "qcom,sm6350-dsi-ctrl", "qcom,mdss-dsi-ctrl";
reg = <0x0ae94000 0x400>;
reg-names = "dsi_ctrl";
interrupt-parent = <&mdss>;
interrupts = <4>;
clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>,
<&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>,
<&dispcc DISP_CC_MDSS_PCLK0_CLK>,
<&dispcc DISP_CC_MDSS_ESC0_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>,
<&gcc GCC_DISP_AXI_CLK>;
clock-names = "byte",
"byte_intf",
"pixel",
"core",
"iface",
"bus";
assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>,
<&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
assigned-clock-parents = <&dsi0_phy 0>, <&dsi0_phy 1>;
operating-points-v2 = <&dsi_opp_table>;
power-domains = <&rpmhpd SM6350_MX>;
phys = <&dsi0_phy>;
phy-names = "dsi";
#address-cells = <1>;
#size-cells = <0>;
ports {
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
dsi0_in: endpoint {
remote-endpoint = <&dpu_intf1_out>;
};
};
port@1 {
reg = <1>;
dsi0_out: endpoint {
};
};
};
};
dsi0_phy: phy@ae94400 {
compatible = "qcom,dsi-phy-10nm";
reg = <0x0ae94400 0x200>,
<0x0ae94600 0x280>,
<0x0ae94a00 0x1e0>;
reg-names = "dsi_phy",
"dsi_phy_lane",
"dsi_pll";
#clock-cells = <1>;
#phy-cells = <0>;
clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, <&rpmhcc RPMH_CXO_CLK>;
clock-names = "iface", "ref";
};
};
...

215
Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml Normal file
View File

@ -0,0 +1,215 @@
# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/msm/qcom,sm6375-mdss.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Qualcomm SM6375 Display MDSS
maintainers:
- Konrad Dybcio <konrad.dybcio@linaro.org>
description:
SM6375 MSM Mobile Display Subsystem (MDSS), which encapsulates sub-blocks
like DPU display controller, DSI and DP interfaces etc.
$ref: /schemas/display/msm/mdss-common.yaml#
properties:
compatible:
const: qcom,sm6375-mdss
clocks:
items:
- description: Display AHB clock from gcc
- description: Display AHB clock
- description: Display core clock
clock-names:
items:
- const: iface
- const: ahb
- const: core
iommus:
maxItems: 1
interconnects:
maxItems: 2
interconnect-names:
maxItems: 2
patternProperties:
"^display-controller@[0-9a-f]+$":
type: object
properties:
compatible:
const: qcom,sm6375-dpu
"^dsi@[0-9a-f]+$":
type: object
properties:
compatible:
items:
- const: qcom,sm6375-dsi-ctrl
- const: qcom,mdss-dsi-ctrl
"^phy@[0-9a-f]+$":
type: object
properties:
compatible:
const: qcom,sm6375-dsi-phy-7nm
unevaluatedProperties: false
examples:
- |
#include <dt-bindings/clock/qcom,rpmcc.h>
#include <dt-bindings/clock/qcom,sm6375-gcc.h>
#include <dt-bindings/clock/qcom,sm6375-dispcc.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/qcom-rpmpd.h>
display-subsystem@5e00000 {
compatible = "qcom,sm6375-mdss";
reg = <0x05e00000 0x1000>;
reg-names = "mdss";
power-domains = <&dispcc MDSS_GDSC>;
clocks = <&gcc GCC_DISP_AHB_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>;
clock-names = "iface", "ahb", "core";
interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
interrupt-controller;
#interrupt-cells = <1>;
iommus = <&apps_smmu 0x820 0x2>;
#address-cells = <1>;
#size-cells = <1>;
ranges;
display-controller@5e01000 {
compatible = "qcom,sm6375-dpu";
reg = <0x05e01000 0x8e030>,
<0x05eb0000 0x2008>;
reg-names = "mdp", "vbif";
clocks = <&gcc GCC_DISP_HF_AXI_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>,
<&dispcc DISP_CC_MDSS_ROT_CLK>,
<&dispcc DISP_CC_MDSS_MDP_LUT_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>,
<&dispcc DISP_CC_MDSS_VSYNC_CLK>,
<&gcc GCC_DISP_THROTTLE_CORE_CLK>;
clock-names = "bus",
"iface",
"rot",
"lut",
"core",
"vsync",
"throttle";
assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
assigned-clock-rates = <19200000>;
operating-points-v2 = <&mdp_opp_table>;
power-domains = <&rpmpd SM6375_VDDCX>;
interrupt-parent = <&mdss>;
interrupts = <0>;
ports {
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
dpu_intf1_out: endpoint {
remote-endpoint = <&dsi0_in>;
};
};
port@1 {
reg = <1>;
dpu_intf2_out: endpoint {
remote-endpoint = <&dsi1_in>;
};
};
};
};
dsi@5e94000 {
compatible = "qcom,sm6375-dsi-ctrl", "qcom,mdss-dsi-ctrl";
reg = <0x05e94000 0x400>;
reg-names = "dsi_ctrl";
interrupt-parent = <&mdss>;
interrupts = <4>;
clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>,
<&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>,
<&dispcc DISP_CC_MDSS_PCLK0_CLK>,
<&dispcc DISP_CC_MDSS_ESC0_CLK>,
<&dispcc DISP_CC_MDSS_AHB_CLK>,
<&gcc GCC_DISP_HF_AXI_CLK>;
clock-names = "byte",
"byte_intf",
"pixel",
"core",
"iface",
"bus";
assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>,
<&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
assigned-clock-parents = <&mdss_dsi0_phy 0>, <&mdss_dsi0_phy 1>;
operating-points-v2 = <&dsi_opp_table>;
power-domains = <&rpmpd SM6375_VDDMX>;
phys = <&mdss_dsi0_phy>;
phy-names = "dsi";
#address-cells = <1>;
#size-cells = <0>;
ports {
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
dsi0_in: endpoint {
remote-endpoint = <&dpu_intf1_out>;
};
};
port@1 {
reg = <1>;
dsi0_out: endpoint {
};
};
};
};
mdss_dsi0_phy: phy@5e94400 {
compatible = "qcom,sm6375-dsi-phy-7nm";
reg = <0x05e94400 0x200>,
<0x05e94600 0x280>,
<0x05e94900 0x264>;
reg-names = "dsi_phy",
"dsi_phy_lane",
"dsi_pll";
#clock-cells = <1>;
#phy-cells = <0>;
clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
<&rpmcc RPM_SMD_XO_CLK_SRC>;
clock-names = "iface", "ref";
};
};
...

2
Documentation/devicetree/bindings/display/msm/qcom,sm8350-mdss.yaml
View File

@ -64,7 +64,7 @@ patternProperties:
type: object
properties:
compatible:
const: qcom,dsi-phy-5nm-8350
const: qcom,sm8350-dsi-phy-5nm
unevaluatedProperties: false

4
Documentation/devicetree/bindings/display/panel/boe,tv101wum-nl6.yaml
View File

@ -32,6 +32,10 @@ properties:
- innolux,hj110iz-01a
# STARRY 2081101QFH032011-53G 10.1" WUXGA TFT LCD panel
- starry,2081101qfh032011-53g
# STARRY himax83102-j02 10.51" WUXGA TFT LCD panel
- starry,himax83102-j02
# STARRY ili9882t 10.51" WUXGA TFT LCD panel
- starry,ili9882t
reg:
description: the virtual channel number of a DSI peripheral

16
Documentation/devicetree/bindings/display/panel/novatek,nt36523.yaml
View File

@ -19,11 +19,16 @@ allOf:
properties:
compatible:
items:
- enum:
- xiaomi,elish-boe-nt36523
- xiaomi,elish-csot-nt36523
- const: novatek,nt36523
oneOf:
- items:
- enum:
- xiaomi,elish-boe-nt36523
- xiaomi,elish-csot-nt36523
- const: novatek,nt36523
- items:
- enum:
- lenovo,j606f-boe-nt36523w
- const: novatek,nt36523w
reset-gpios:
maxItems: 1
@ -34,6 +39,7 @@ properties:
reg: true
ports: true
rotation: true
backlight: true
required:

8
Documentation/devicetree/bindings/display/panel/panel-simple.yaml
View File

@ -33,6 +33,8 @@ properties:
- ampire,am-1280800n3tzqw-t00h
# Ampire AM-480272H3TMQW-T01H 4.3" WQVGA TFT LCD panel
- ampire,am-480272h3tmqw-t01h
# Ampire AM-800480L1TMQW-T00H 5" WVGA TFT LCD panel
- ampire,am-800480l1tmqw-t00h
# Ampire AM-800480R3TMQW-A1H 7.0" WVGA TFT LCD panel
- ampire,am800480r3tmqwa1h
# Ampire AM-800600P5TMQW-TB8H 8.0" SVGA TFT LCD panel
@ -77,6 +79,8 @@ properties:
- auo,t215hvn01
# Shanghai AVIC Optoelectronics 7" 1024x600 color TFT-LCD panel
- avic,tm070ddh03
# BOE EV121WXM-N10-1850 12.1" WXGA (1280x800) TFT LCD panel
- boe,ev121wxm-n10-1850
# BOE HV070WSA-100 7.01" WSVGA TFT LCD panel
- boe,hv070wsa-100
# BOE OPTOELECTRONICS TECHNOLOGY 10.1" WXGA TFT LCD panel
@ -174,6 +178,8 @@ properties:
- innolux,at043tn24
# Innolux AT070TN92 7.0" WQVGA TFT LCD panel
- innolux,at070tn92
# Innolux G070ACE-L01 7" WVGA (800x480) TFT LCD panel
- innolux,g070ace-l01
# Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD panel
- innolux,g070y2-l01
# Innolux G070Y2-T02 7" WVGA (800x480) TFT LCD TTL panel
@ -280,6 +286,8 @@ properties:
- rocktech,rk101ii01d-ct
# Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel
- rocktech,rk070er9427
# Rocktech Display Ltd. RK043FN48H 4.3" 480x272 LCD-TFT panel
- rocktech,rk043fn48h
# Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel
- samsung,atna33xc20
# Samsung 12.2" (2560x1600 pixels) TFT LCD panel

2
Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.yaml
View File

@ -20,6 +20,8 @@ allOf:
properties:
compatible:
enum:
# Anberic RG353V-V2 5.0" 640x480 TFT LCD panel
- anbernic,rg353v-panel-v2
# Rocktech JH057N00900 5.5" 720x1440 TFT LCD panel
- rocktech,jh057n00900
# Xingbangda XBD599 5.99" 720x1440 TFT LCD panel

70
Documentation/devicetree/bindings/display/panel/samsung,s6d7aa0.yaml Normal file
View File

@ -0,0 +1,70 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/panel/samsung,s6d7aa0.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Samsung S6D7AA0 MIPI-DSI LCD panel controller
maintainers:
- Artur Weber <aweber.kernel@gmail.com>
allOf:
- $ref: panel-common.yaml#
properties:
compatible:
items:
- enum:
# 1280x800 LSL080AL02 panel
- samsung,lsl080al02
# 1024x768 LSL080AL03 panel
- samsung,lsl080al03
# 1024x768 LTL101AT01 panel
- samsung,ltl101at01
- const: samsung,s6d7aa0
reg: true
backlight:
description:
Backlight to use for the panel. If this property is set on panels
that have DSI-based backlight control (LSL080AL03 and LTL101AT01),
it overrides the DSI-based backlight.
reset-gpios:
description: Reset GPIO pin, usually GPIO_ACTIVE_LOW.
power-supply:
description:
Main power supply for the panel; the exact voltage differs between
panels, and is usually somewhere around 3.3-5v.
vmipi-supply:
description: VMIPI supply, usually 1.8v.
required:
- compatible
- reg
- reset-gpios
additionalProperties: false
examples:
- |
#include <dt-bindings/gpio/gpio.h>
dsi {
#address-cells = <1>;
#size-cells = <0>;
panel@0 {
compatible = "samsung,lsl080al02", "samsung,s6d7aa0";
reg = <0>;
power-supply = <&display_3v3_supply>;
reset-gpios = <&gpf0 4 GPIO_ACTIVE_LOW>;
backlight = <&backlight>;
};
};
...

4
Documentation/gpu/amdgpu/apu-asic-info-table.csv
View File

@ -5,6 +5,8 @@ Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2, 11.0.3
Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1, 10.0.1
SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0
Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1
Ryzen 6000 series / Ryzen 7x35 series, YELLOW CARP / Rembrandt / Rembrandt+, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
Ryzen 7x45 series (FL1), / Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8
Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
1 Product Name Code Reference DCN/DCE version GC version VCE/UVD/VCN version SDMA version MP0 version
5 Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx RAVEN2 DCN 1.0 9.2.2 VCN 1.0.1 4.1.1 10.0.1
6 SteamDeck VANGOGH DCN 3.0.1 10.3.1 VCN 3.1.0 5.2.1 11.5.0
7 Ryzen 5000 series / Ryzen 7x30 series GREEN SARDINE / Cezanne / Barcelo / Barcelo-R DCN 2.1 9.3 VCN 2.2 4.1.1 12.0.1
8 Ryzen 6000 series / Ryzen 7x35 series Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series YELLOW CARP / Rembrandt / Rembrandt+ YELLOW CARP / Rembrandt / Rembrandt-R 3.1.2 10.3.3 VCN 3.1.1 5.2.3 13.0.3
9 Ryzen 7000 series (AM5) Raphael 3.1.5 10.3.6 3.1.2 5.2.6 13.0.5
10 Ryzen 7x45 series (FL1) / Dragon Range 3.1.5 10.3.6 3.1.2 5.2.6 13.0.5
11 Ryzen 7x20 series Mendocino 3.1.6 10.3.7 3.1.1 5.2.7 13.0.8
12 Ryzen 7x40 series Phoenix 3.1.4 11.0.1 / 11.0.4 4.0.2 6.0.1 13.0.4 / 13.0.11

91
Documentation/gpu/drm-usage-stats.rst
View File

@ -24,7 +24,7 @@ File format specification
- All keys shall be prefixed with `drm-`.
- Whitespace between the delimiter and first non-whitespace character shall be
ignored when parsing.
- Neither keys or values are allowed to contain whitespace characters.
- Keys are not allowed to contain whitespace characters.
- Numerical key value pairs can end with optional unit string.
- Data type of the value is fixed as defined in the specification.
@ -39,12 +39,13 @@ Data types
----------
- <uint> - Unsigned integer without defining the maximum value.
- <str> - String excluding any above defined reserved characters or whitespace.
- <keystr> - String excluding any above defined reserved characters or whitespace.
- <valstr> - String.
Mandatory fully standardised keys
---------------------------------
- drm-driver: <str>
- drm-driver: <valstr>
String shall contain the name this driver registered as via the respective
`struct drm_driver` data structure.
@ -52,6 +53,9 @@ String shall contain the name this driver registered as via the respective
Optional fully standardised keys
--------------------------------
Identification
^^^^^^^^^^^^^^
- drm-pdev: <aaaa:bb.cc.d>
For PCI devices this should contain the PCI slot address of the device in
@ -69,10 +73,13 @@ scope of each device, in which case `drm-pdev` shall be present as well.
Userspace should make sure to not double account any usage statistics by using
the above described criteria in order to associate data to individual clients.
- drm-engine-<str>: <uint> ns
Utilization
^^^^^^^^^^^
- drm-engine-<keystr>: <uint> ns
GPUs usually contain multiple execution engines. Each shall be given a stable
and unique name (str), with possible values documented in the driver specific
and unique name (keystr), with possible values documented in the driver specific
documentation.
Value shall be in specified time units which the respective GPU engine spent
@ -84,31 +91,19 @@ larger value within a reasonable period. Upon observing a value lower than what
was previously read, userspace is expected to stay with that larger previous
value until a monotonic update is seen.
- drm-engine-capacity-<str>: <uint>
- drm-engine-capacity-<keystr>: <uint>
Engine identifier string must be the same as the one specified in the
drm-engine-<str> tag and shall contain a greater than zero number in case the
drm-engine-<keystr> tag and shall contain a greater than zero number in case the
exported engine corresponds to a group of identical hardware engines.
In the absence of this tag parser shall assume capacity of one. Zero capacity
is not allowed.
- drm-memory-<str>: <uint> [KiB|MiB]
Each possible memory type which can be used to store buffer objects by the
GPU in question shall be given a stable and unique name to be returned as the
string here.
Value shall reflect the amount of storage currently consumed by the buffer
object belong to this client, in the respective memory region.
Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
indicating kibi- or mebi-bytes.
- drm-cycles-<str> <uint>
- drm-cycles-<keystr>: <uint>
Engine identifier string must be the same as the one specified in the
drm-engine-<str> tag and shall contain the number of busy cycles for the given
drm-engine-<keystr> tag and shall contain the number of busy cycles for the given
engine.
Values are not required to be constantly monotonic if it makes the driver
@ -117,16 +112,60 @@ larger value within a reasonable period. Upon observing a value lower than what
was previously read, userspace is expected to stay with that larger previous
value until a monotonic update is seen.
- drm-maxfreq-<str> <uint> [Hz|MHz|KHz]
- drm-maxfreq-<keystr>: <uint> [Hz|MHz|KHz]
Engine identifier string must be the same as the one specified in the
drm-engine-<str> tag and shall contain the maximum frequency for the given
engine. Taken together with drm-cycles-<str>, this can be used to calculate
percentage utilization of the engine, whereas drm-engine-<str> only reflects
drm-engine-<keystr> tag and shall contain the maximum frequency for the given
engine. Taken together with drm-cycles-<keystr>, this can be used to calculate
percentage utilization of the engine, whereas drm-engine-<keystr> only reflects
time active without considering what frequency the engine is operating as a
percentage of it's maximum frequency.
Memory
^^^^^^
- drm-memory-<region>: <uint> [KiB|MiB]
Each possible memory type which can be used to store buffer objects by the
GPU in question shall be given a stable and unique name to be returned as the
string here. The name "memory" is reserved to refer to normal system memory.
Value shall reflect the amount of storage currently consumed by the buffer
objects belong to this client, in the respective memory region.
Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
indicating kibi- or mebi-bytes.
- drm-shared-<region>: <uint> [KiB|MiB]
The total size of buffers that are shared with another file (ie. have more
than a single handle).
- drm-total-<region>: <uint> [KiB|MiB]
The total size of buffers that including shared and private memory.
- drm-resident-<region>: <uint> [KiB|MiB]
The total size of buffers that are resident in the specified region.
- drm-purgeable-<region>: <uint> [KiB|MiB]
The total size of buffers that are purgeable.
- drm-active-<region>: <uint> [KiB|MiB]
The total size of buffers that are active on one or more engines.
Implementation Details
======================
Drivers should use drm_show_fdinfo() in their `struct file_operations`, and
implement &drm_driver.show_fdinfo if they wish to provide any stats which
are not provided by drm_show_fdinfo(). But even driver specific stats should
be documented above and where possible, aligned with other drivers.
Driver specific implementations
===============================
-------------------------------
:ref:`i915-usage-stats`

4
Documentation/gpu/rfc/index.rst
View File

@ -31,3 +31,7 @@ host such documentation:
.. toctree::
i915_vm_bind.rst
.. toctree::
xe.rst

235
Documentation/gpu/rfc/xe.rst Normal file
View File

@ -0,0 +1,235 @@
==========================
Xe – Merge Acceptance Plan
==========================
Xe is a new driver for Intel GPUs that supports both integrated and
discrete platforms starting with Tiger Lake (first Intel Xe Architecture).
This document aims to establish a merge plan for the Xe, by writing down clear
pre-merge goals, in order to avoid unnecessary delays.
Xe – Overview
=============
The main motivation of Xe is to have a fresh base to work from that is
unencumbered by older platforms, whilst also taking the opportunity to
rearchitect our driver to increase sharing across the drm subsystem, both
leveraging and allowing us to contribute more towards other shared components
like TTM and drm/scheduler.
This is also an opportunity to start from the beginning with a clean uAPI that is
extensible by design and already aligned with the modern userspace needs. For
this reason, the memory model is solely based on GPU Virtual Address space
bind/unbind (‘VM_BIND’) of GEM buffer objects (BOs) and execution only supporting
explicit synchronization. With persistent mapping across the execution, the
userspace does not need to provide a list of all required mappings during each
submission.
The new driver leverages a lot from i915. As for display, the intent is to share
the display code with the i915 driver so that there is maximum reuse there.
As for the power management area, the goal is to have a much-simplified support
for the system suspend states (S-states), PCI device suspend states (D-states),
GPU/Render suspend states (R-states) and frequency management. It should leverage
as much as possible all the existent PCI-subsystem infrastructure (pm and
runtime_pm) and underlying firmware components such PCODE and GuC for the power
states and frequency decisions.
Repository:
https://gitlab.freedesktop.org/drm/xe/kernel (branch drm-xe-next)
Xe – Platforms
==============
Currently, Xe is already functional and has experimental support for multiple
platforms starting from Tiger Lake, with initial support in userspace implemented
in Mesa (for Iris and Anv, our OpenGL and Vulkan drivers), as well as in NEO
(for OpenCL and Level0).
During a transition period, platforms will be supported by both Xe and i915.
However, the force_probe mechanism existent in both drivers will allow only one
official and by-default probe at a given time.
For instance, in order to probe a DG2 which PCI ID is 0x5690 by Xe instead of
i915, the following set of parameters need to be used:
```
i915.force_probe=!5690 xe.force_probe=5690
```
In both drivers, the ‘.require_force_probe’ protection forces the user to use the
force_probe parameter while the driver is under development. This protection is
only removed when the support for the platform and the uAPI are stable. Stability
which needs to be demonstrated by CI results.
In order to avoid user space regressions, i915 will continue to support all the
current platforms that are already out of this protection. Xe support will be
forever experimental and dependent on the usage of force_probe for these
platforms.
When the time comes for Xe, the protection will be lifted on Xe and kept in i915.
Xe driver will be protected with both STAGING Kconfig and force_probe. Changes in
the uAPI are expected while the driver is behind these protections. STAGING will
be removed when the driver uAPI gets to a mature state where we can guarantee the
‘no regression’ rule. Then force_probe will be lifted only for future platforms
that will be productized with Xe driver, but not with i915.
Xe – Pre-Merge Goals
====================
Drm_scheduler
-------------
Xe primarily uses Firmware based scheduling (GuC FW). However, it will use
drm_scheduler as the scheduler ‘frontend’ for userspace submission in order to
resolve syncobj and dma-buf implicit sync dependencies. However, drm_scheduler is
not yet prepared to handle the 1-to-1 relationship between drm_gpu_scheduler and
drm_sched_entity.
Deeper changes to drm_scheduler should *not* be required to get Xe accepted, but
some consensus needs to be reached between Xe and other community drivers that
could also benefit from this work, for coupling FW based/assisted submission such
as the ARM’s new Mali GPU driver, and others.
As a key measurable result, the patch series introducing Xe itself shall not
depend on any other patch touching drm_scheduler itself that was not yet merged
through drm-misc. This, by itself, already includes the reach of an agreement for
uniform 1 to 1 relationship implementation / usage across drivers.
GPU VA
------
Two main goals of Xe are meeting together here:
1) Have an uAPI that aligns with modern UMD needs.
2) Early upstream engagement.
RedHat engineers working on Nouveau proposed a new DRM feature to handle keeping
track of GPU virtual address mappings. This is still not merged upstream, but
this aligns very well with our goals and with our VM_BIND. The engagement with
upstream and the port of Xe towards GPUVA is already ongoing.
As a key measurable result, Xe needs to be aligned with the GPU VA and working in
our tree. Missing Nouveau patches should *not* block Xe and any needed GPUVA
related patch should be independent and present on dri-devel or acked by
maintainers to go along with the first Xe pull request towards drm-next.
DRM_VM_BIND
-----------
Nouveau, and Xe are all implementing ‘VM_BIND’ and new ‘Exec’ uAPIs in order to
fulfill the needs of the modern uAPI. Xe merge should *not* be blocked on the
development of a common new drm_infrastructure. However, the Xe team needs to
engage with the community to explore the options of a common API.
As a key measurable result, the DRM_VM_BIND needs to be documented in this file
below, or this entire block deleted if the consensus is for independent drivers
vm_bind ioctls.
Although having a common DRM level IOCTL for VM_BIND is not a requirement to get
Xe merged, it is mandatory to enforce the overall locking scheme for all major
structs and list (so vm and vma). So, a consensus is needed, and possibly some
common helpers. If helpers are needed, they should be also documented in this
document.
ASYNC VM_BIND
-------------
Although having a common DRM level IOCTL for VM_BIND is not a requirement to get
Xe merged, it is mandatory to have a consensus with other drivers and Mesa.
It needs to be clear how to handle async VM_BIND and interactions with userspace
memory fences. Ideally with helper support so people don't get it wrong in all
possible ways.
As a key measurable result, the benefits of ASYNC VM_BIND and a discussion of
various flavors, error handling and a sample API should be documented here or in
a separate document pointed to by this document.
Userptr integration and vm_bind
-------------------------------
Different drivers implement different ways of dealing with execution of userptr.
With multiple drivers currently introducing support to VM_BIND, the goal is to
aim for a DRM consensus on what’s the best way to have that support. To some
extent this is already getting addressed itself with the GPUVA where likely the
userptr will be a GPUVA with a NULL GEM call VM bind directly on the userptr.
However, there are more aspects around the rules for that and the usage of
mmu_notifiers, locking and other aspects.
This task here has the goal of introducing a documentation of the basic rules.
The documentation *needs* to first live in this document (API session below) and
then moved to another more specific document or at Xe level or at DRM level.
Documentation should include:
* The userptr part of the VM_BIND api.
* Locking, including the page-faulting case.
* O(1) complexity under VM_BIND.
Some parts of userptr like mmu_notifiers should become GPUVA or DRM helpers when
the second driver supporting VM_BIND+userptr appears. Details to be defined when
the time comes.
Long running compute: minimal data structure/scaffolding
--------------------------------------------------------
The generic scheduler code needs to include the handling of endless compute
contexts, with the minimal scaffolding for preempt-ctx fences (probably on the
drm_sched_entity) and making sure drm_scheduler can cope with the lack of job
completion fence.
The goal is to achieve a consensus ahead of Xe initial pull-request, ideally with
this minimal drm/scheduler work, if needed, merged to drm-misc in a way that any
drm driver, including Xe, could re-use and add their own individual needs on top
in a next stage. However, this should not block the initial merge.
This is a non-blocker item since the driver without the support for the long
running compute enabled is not a showstopper.
Display integration with i915
-----------------------------
In order to share the display code with the i915 driver so that there is maximum
reuse, the i915/display/ code is built twice, once for i915.ko and then for
xe.ko. Currently, the i915/display code in Xe tree is polluted with many 'ifdefs'
depending on the build target. The goal is to refactor both Xe and i915/display
code simultaneously in order to get a clean result before they land upstream, so
that display can already be part of the initial pull request towards drm-next.
However, display code should not gate the acceptance of Xe in upstream. Xe
patches will be refactored in a way that display code can be removed, if needed,
from the first pull request of Xe towards drm-next. The expectation is that when
both drivers are part of the drm-tip, the introduction of cleaner patches will be
easier and speed up.
Drm_exec
--------
Helper to make dma_resv locking for a big number of buffers is getting removed in
the drm_exec series proposed in https://patchwork.freedesktop.org/patch/524376/
If that happens, Xe needs to change and incorporate the changes in the driver.
The goal is to engage with the Community to understand if the best approach is to
move that to the drivers that are using it or if we should keep the helpers in
place waiting for Xe to get merged.
This item ties into the GPUVA, VM_BIND, and even long-running compute support.
As a key measurable result, we need to have a community consensus documented in
this document and the Xe driver prepared for the changes, if necessary.
Dev_coredump
------------
Xe needs to align with other drivers on the way that the error states are
dumped, avoiding a Xe only error_state solution. The goal is to use devcoredump
infrastructure to report error states, since it produces a standardized way
by exposing a virtual and temporary /sys/class/devcoredump device.
As the key measurable result, Xe driver needs to provide GPU snapshots captured
at hang time through devcoredump, but without depending on any core modification
of devcoredump infrastructure itself.
Later, when we are in-tree, the goal is to collaborate with devcoredump
infrastructure with overall possible improvements, like multiple file support
for better organization of the dumps, snapshot support, dmesg extra print,
and whatever may make sense and help the overall infrastructure.
Xe – uAPI high level overview
=============================
...Warning: To be done in follow up patches after/when/where the main consensus in various items are individually reached.

7
Documentation/gpu/todo.rst
View File

@ -276,11 +276,8 @@ Various hold-ups:
- Need to switch to drm_fbdev_generic_setup(), otherwise a lot of the custom fb
setup code can't be deleted.
- Many drivers wrap drm_gem_fb_create() only to check for valid formats. For
atomic drivers we could check for valid formats by calling
drm_plane_check_pixel_format() against all planes, and pass if any plane
supports the format. For non-atomic that's not possible since like the format
list for the primary plane is fake and we'd therefor reject valid formats.
- Need to switch to drm_gem_fb_create(), as now drm_gem_fb_create() checks for
valid formats for atomic drivers.
- Many drivers subclass drm_framebuffer, we'd need a embedding compatible
version of the varios drm_gem_fb_create functions. Maybe called

7
Documentation/gpu/vkms.rst
View File

@ -118,14 +118,9 @@ Add Plane Features
There's lots of plane features we could add support for:
- ARGB format on primary plane: blend the primary plane into background with
translucent alpha.
- Add background color KMS property[Good to get started].
- Full alpha blending on all planes.
- Rotation, scaling.
- Scaling.
- Additional buffer formats, especially YUV formats for video like NV12.
Low/high bpp RGB formats would also be interesting.

14
MAINTAINERS
View File

@ -6604,6 +6604,7 @@ M: Rob Clark <robdclark@gmail.com>
M: Abhinav Kumar <quic_abhinavk@quicinc.com>
M: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
R: Sean Paul <sean@poorly.run>
R: Marijn Suijten <marijn.suijten@somainline.org>
L: linux-arm-msm@vger.kernel.org
L: dri-devel@lists.freedesktop.org
L: freedreno@lists.freedesktop.org
@ -6724,6 +6725,12 @@ S: Maintained
F: Documentation/devicetree/bindings/display/panel/samsung,s6d27a1.yaml
F: drivers/gpu/drm/panel/panel-samsung-s6d27a1.c
DRM DRIVER FOR SAMSUNG S6D7AA0 PANELS
M: Artur Weber <aweber.kernel@gmail.com>
S: Maintained
F: Documentation/devicetree/bindings/display/panel/samsung,s6d7aa0.yaml
F: drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
DRM DRIVER FOR SITRONIX ST7586 PANELS
M: David Lechner <david@lechnology.com>
S: Maintained
@ -6796,6 +6803,7 @@ F: drivers/gpu/drm/udl/
DRM DRIVER FOR VIRTUAL KERNEL MODESETTING (VKMS)
M: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
M: Melissa Wen <melissa.srw@gmail.com>
M: Maíra Canal <mairacanal@riseup.net>
R: Haneen Mohammed <hamohammed.sa@gmail.com>
R: Daniel Vetter <daniel@ffwll.ch>
L: dri-devel@lists.freedesktop.org
@ -6898,6 +6906,7 @@ S: Maintained
T: git git://anongit.freedesktop.org/drm/drm-misc
F: Documentation/devicetree/bindings/display/bridge/
F: drivers/gpu/drm/bridge/
F: drivers/gpu/drm/drm_bridge.c
F: include/drm/drm_bridge.h
DRM DRIVERS FOR EXYNOS
@ -7006,8 +7015,7 @@ F: Documentation/devicetree/bindings/display/bridge/renesas,dsi-csi2-tx.yaml
F: Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.yaml
F: Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml
F: Documentation/devicetree/bindings/display/renesas,du.yaml
F: drivers/gpu/drm/rcar-du/
F: drivers/gpu/drm/shmobile/
F: drivers/gpu/drm/renesas/
F: include/linux/platform_data/shmob_drm.h
DRM DRIVERS FOR ROCKCHIP
@ -17486,6 +17494,8 @@ F: include/dt-bindings/clock/qcom,*
QUALCOMM CLOUD AI (QAIC) DRIVER
M: Jeffrey Hugo <quic_jhugo@quicinc.com>
R: Carl Vanderlip <quic_carlv@quicinc.com>
R: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
L: linux-arm-msm@vger.kernel.org
L: dri-devel@lists.freedesktop.org
S: Supported

16
arch/arc/include/asm/fb.h
View File

@ -1,20 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
}
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

15
arch/arm/include/asm/fb.h
View File

@ -1,19 +1,6 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
}
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

15
arch/arm64/include/asm/fb.h
View File

@ -5,19 +5,6 @@
#ifndef __ASM_FB_H_
#define __ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
}
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#include <asm-generic/fb.h>
#endif /* __ASM_FB_H_ */

27
arch/ia64/include/asm/fb.h
View File

@ -2,11 +2,14 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <linux/compiler.h>
#include <linux/efi.h>
#include <linux/string.h>
#include <asm/page.h>
struct file;
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
@ -15,10 +18,26 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
else
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
}
#define fb_pgprotect fb_pgprotect
static inline int fb_is_primary_device(struct fb_info *info)
static inline void fb_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
{
return 0;
memcpy(to, (void __force *)from, n);
}
#define fb_memcpy_fromio fb_memcpy_fromio
static inline void fb_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
{
memcpy((void __force *)to, from, n);
}
#define fb_memcpy_toio fb_memcpy_toio
static inline void fb_memset_io(volatile void __iomem *addr, int c, size_t n)
{
memset((void __force *)addr, c, n);
}
#define fb_memset fb_memset_io
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

24
arch/loongarch/include/asm/fb.h
View File

@ -5,19 +5,27 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
#include <linux/compiler.h>
#include <linux/string.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
static inline void fb_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
memcpy(to, (void __force *)from, n);
}
#define fb_memcpy_fromio fb_memcpy_fromio
static inline int fb_is_primary_device(struct fb_info *info)
static inline void fb_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
{
return 0;
memcpy((void __force *)to, from, n);
}
#define fb_memcpy_toio fb_memcpy_toio
static inline void fb_memset_io(volatile void __iomem *addr, int c, size_t n)
{
memset((void __force *)addr, c, n);
}
#define fb_memset fb_memset_io
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

24
arch/m68k/include/asm/fb.h
View File

@ -2,22 +2,18 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
#include <asm/setup.h>
struct file;
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
#ifdef CONFIG_MMU
#ifdef CONFIG_SUN3
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
pgprot_val(vma->vm_page_prot) |= SUN3_PAGE_NOCACHE;
}
#else
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
if (CPU_IS_020_OR_030)
pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE030;
if (CPU_IS_040_OR_060) {
@ -25,15 +21,11 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
/* Use no-cache mode, serialized */
pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE_S;
}
}
#endif /* CONFIG_SUN3 */
#else
#define fb_pgprotect(...) do {} while (0)
#endif /* CONFIG_MMU */
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#define fb_pgprotect fb_pgprotect
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

28
arch/mips/include/asm/fb.h
View File

@ -1,19 +1,39 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
struct file;
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
}
#define fb_pgprotect fb_pgprotect
static inline int fb_is_primary_device(struct fb_info *info)
/*
* MIPS doesn't define __raw_ I/O macros, so the helpers
* in <asm-generic/fb.h> don't generate fb_readq() and
* fb_write(). We have to provide them here.
*
* TODO: Convert MIPS to generic I/O. The helpers below can
* then be removed.
*/
#ifdef CONFIG_64BIT
static inline u64 fb_readq(const volatile void __iomem *addr)
{
return 0;
return __raw_readq(addr);
}
#define fb_readq fb_readq
static inline void fb_writeq(u64 b, volatile void __iomem *addr)
{
__raw_writeq(b, addr);
}
#define fb_writeq fb_writeq
#endif
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

4
arch/parisc/Makefile
View File

@ -11,7 +11,7 @@
# Copyright (C) 1994 by Linus Torvalds
# Portions Copyright (C) 1999 The Puffin Group
#
# Modified for PA-RISC Linux by Paul Lahaie, Alex deVries,
# Modified for PA-RISC Linux by Paul Lahaie, Alex deVries,
# Mike Shaver, Helge Deller and Martin K. Petersen
#
@ -119,6 +119,8 @@ export LIBGCC
libs-y += arch/parisc/lib/ $(LIBGCC)
drivers-y += arch/parisc/video/
boot := arch/parisc/boot
PALO := $(shell if (which palo 2>&1); then : ; \

20
arch/parisc/include/asm/fb.h
View File

@ -2,23 +2,13 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
struct fb_info;
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE;
}
#if defined(CONFIG_FB_STI)
#if defined(CONFIG_STI_CORE)
int fb_is_primary_device(struct fb_info *info);
#else
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#define fb_is_primary_device fb_is_primary_device
#endif
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

3
arch/parisc/video/Makefile Normal file
View File

@ -0,0 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_STI_CORE) += fbdev.o

26
arch/parisc/video/fbdev.c Normal file
View File

@ -0,0 +1,26 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
* Copyright (C) 2001-2020 Helge Deller <deller@gmx.de>
* Copyright (C) 2001-2002 Thomas Bogendoerfer <tsbogend@alpha.franken.de>
*/
#include <linux/fb.h>
#include <linux/module.h>
#include <video/sticore.h>
int fb_is_primary_device(struct fb_info *info)
{
struct sti_struct *sti;
sti = sti_get_rom(0);
/* if no built-in graphics card found, allow any fb driver as default */
if (!sti)
return true;
/* return true if it's the default built-in framebuffer driver */
return (sti->info == info);
}
EXPORT_SYMBOL(fb_is_primary_device);

8
arch/powerpc/include/asm/fb.h
View File

@ -2,8 +2,8 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
@ -13,10 +13,8 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
#define fb_pgprotect fb_pgprotect
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

15
arch/sh/include/asm/fb.h
View File

@ -2,19 +2,6 @@
#ifndef _ASM_FB_H_
#define _ASM_FB_H_
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
}
static inline int fb_is_primary_device(struct fb_info *info)
{
return 0;
}
#include <asm-generic/fb.h>
#endif /* _ASM_FB_H_ */

1
arch/sparc/Makefile
View File

@ -60,6 +60,7 @@ libs-y += arch/sparc/prom/
libs-y += arch/sparc/lib/
drivers-$(CONFIG_PM) += arch/sparc/power/
drivers-$(CONFIG_FB) += arch/sparc/video/
boot := arch/sparc/boot

51
arch/sparc/include/asm/fb.h
View File

@ -1,34 +1,41 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _SPARC_FB_H_
#define _SPARC_FB_H_
#include <linux/console.h>
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
#include <asm/prom.h>
#include <linux/io.h>
struct fb_info;
struct file;
struct vm_area_struct;
#ifdef CONFIG_SPARC32
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
#ifdef CONFIG_SPARC64
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
{ }
#define fb_pgprotect fb_pgprotect
#endif
}
static inline int fb_is_primary_device(struct fb_info *info)
int fb_is_primary_device(struct fb_info *info);
#define fb_is_primary_device fb_is_primary_device
static inline void fb_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
{
struct device *dev = info->device;
struct device_node *node;
if (console_set_on_cmdline)
return 0;
node = dev->of_node;
if (node &&
node == of_console_device)
return 1;
return 0;
sbus_memcpy_fromio(to, from, n);
}
#define fb_memcpy_fromio fb_memcpy_fromio
static inline void fb_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
{
sbus_memcpy_toio(to, from, n);
}
#define fb_memcpy_toio fb_memcpy_toio
static inline void fb_memset_io(volatile void __iomem *addr, int c, size_t n)
{
sbus_memset_io(addr, c, n);
}
#define fb_memset fb_memset_io
#include <asm-generic/fb.h>
#endif /* _SPARC_FB_H_ */

3
arch/sparc/video/Makefile Normal file
View File

@ -0,0 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_FB) += fbdev.o

23
arch/sparc/video/fbdev.c Normal file
View File

@ -0,0 +1,23 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/console.h>
#include <linux/fb.h>
#include <linux/module.h>
#include <asm/prom.h>
int fb_is_primary_device(struct fb_info *info)
{
struct device *dev = info->device;
struct device_node *node;
if (console_set_on_cmdline)
return 0;
node = dev->of_node;
if (node && node == of_console_device)
return 1;
return 0;
}
EXPORT_SYMBOL(fb_is_primary_device);

21
arch/x86/include/asm/fb.h
View File

@ -2,21 +2,16 @@
#ifndef _ASM_X86_FB_H
#define _ASM_X86_FB_H
#include <linux/fb.h>
#include <linux/fs.h>
#include <asm/page.h>
struct fb_info;
struct file;
struct vm_area_struct;
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
unsigned long prot;
void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off);
#define fb_pgprotect fb_pgprotect
prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK;
if (boot_cpu_data.x86 > 3)
pgprot_val(vma->vm_page_prot) =
prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
}
int fb_is_primary_device(struct fb_info *info);
#define fb_is_primary_device fb_is_primary_device
extern int fb_is_primary_device(struct fb_info *info);
#include <asm-generic/fb.h>
#endif /* _ASM_X86_FB_H */

28
arch/x86/video/fbdev.c
View File

@ -6,36 +6,38 @@
* for more details.
*
*/
#include <linux/fb.h>
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/vgaarb.h>
#include <asm/fb.h>
void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off)
{
unsigned long prot;
prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK;
if (boot_cpu_data.x86 > 3)
pgprot_val(vma->vm_page_prot) =
prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
}
EXPORT_SYMBOL(fb_pgprotect);
int fb_is_primary_device(struct fb_info *info)
{
struct device *device = info->device;
struct pci_dev *default_device = vga_default_device();
struct pci_dev *pci_dev;
struct resource *res;
if (!device || !dev_is_pci(device))
return 0;
pci_dev = to_pci_dev(device);
if (default_device) {
if (pci_dev == default_device)
return 1;
return 0;
}
res = pci_dev->resource + PCI_ROM_RESOURCE;
if (res->flags & IORESOURCE_ROM_SHADOW)
if (pci_dev == vga_default_device())
return 1;
return 0;
}
EXPORT_SYMBOL(fb_is_primary_device);
MODULE_LICENSE("GPL");

6
drivers/accel/habanalabs/common/command_buffer.c
View File

@ -27,12 +27,6 @@ static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
return -EINVAL;
}
if (!hdev->mmu_enable) {
dev_err_ratelimited(hdev->dev,
"Cannot map CB because MMU is disabled\n");
return -EINVAL;
}
if (cb->is_mmu_mapped)
return 0;

61
drivers/accel/habanalabs/common/command_submission.c
View File

@ -280,14 +280,8 @@ bool cs_needs_timeout(struct hl_cs *cs)
static bool is_cb_patched(struct hl_device *hdev, struct hl_cs_job *job)
{
/*
* Patched CB is created for external queues jobs, and for H/W queues
* jobs if the user CB was allocated by driver and MMU is disabled.
*/
return (job->queue_type == QUEUE_TYPE_EXT ||
(job->queue_type == QUEUE_TYPE_HW &&
job->is_kernel_allocated_cb &&
!hdev->mmu_enable));
/* Patched CB is created for external queues jobs */
return (job->queue_type == QUEUE_TYPE_EXT);
}
/*
@ -363,14 +357,13 @@ static void hl_complete_job(struct hl_device *hdev, struct hl_cs_job *job)
}
}
/* For H/W queue jobs, if a user CB was allocated by driver and MMU is
* enabled, the user CB isn't released in cs_parser() and thus should be
/* For H/W queue jobs, if a user CB was allocated by driver,
* the user CB isn't released in cs_parser() and thus should be
* released here. This is also true for INT queues jobs which were
* allocated by driver.
*/
if ((job->is_kernel_allocated_cb &&
((job->queue_type == QUEUE_TYPE_HW && hdev->mmu_enable) ||
job->queue_type == QUEUE_TYPE_INT))) {
if (job->is_kernel_allocated_cb &&
(job->queue_type == QUEUE_TYPE_HW || job->queue_type == QUEUE_TYPE_INT)) {
atomic_dec(&job->user_cb->cs_cnt);
hl_cb_put(job->user_cb);
}
@ -804,12 +797,14 @@ out:
static void cs_timedout(struct work_struct *work)
{
struct hl_cs *cs = container_of(work, struct hl_cs, work_tdr.work);
bool skip_reset_on_timeout, device_reset = false;
struct hl_device *hdev;
u64 event_mask = 0x0;
uint timeout_sec;
int rc;
struct hl_cs *cs = container_of(work, struct hl_cs,
work_tdr.work);
bool skip_reset_on_timeout = cs->skip_reset_on_timeout, device_reset = false;
skip_reset_on_timeout = cs->skip_reset_on_timeout;
rc = cs_get_unless_zero(cs);
if (!rc)
@ -840,29 +835,31 @@ static void cs_timedout(struct work_struct *work)
event_mask |= HL_NOTIFIER_EVENT_CS_TIMEOUT;
}
timeout_sec = jiffies_to_msecs(hdev->timeout_jiffies) / 1000;
switch (cs->type) {
case CS_TYPE_SIGNAL:
dev_err(hdev->dev,
"Signal command submission %llu has not finished in time!\n",
cs->sequence);
"Signal command submission %llu has not finished in %u seconds!\n",
cs->sequence, timeout_sec);
break;
case CS_TYPE_WAIT:
dev_err(hdev->dev,
"Wait command submission %llu has not finished in time!\n",
cs->sequence);
"Wait command submission %llu has not finished in %u seconds!\n",
cs->sequence, timeout_sec);
break;
case CS_TYPE_COLLECTIVE_WAIT:
dev_err(hdev->dev,
"Collective Wait command submission %llu has not finished in time!\n",
cs->sequence);
"Collective Wait command submission %llu has not finished in %u seconds!\n",
cs->sequence, timeout_sec);
break;
default:
dev_err(hdev->dev,
"Command submission %llu has not finished in time!\n",
cs->sequence);
"Command submission %llu has not finished in %u seconds!\n",
cs->sequence, timeout_sec);
break;
}
@ -1139,11 +1136,10 @@ static void force_complete_cs(struct hl_device *hdev)
spin_unlock(&hdev->cs_mirror_lock);
}
void hl_abort_waitings_for_completion(struct hl_device *hdev)
void hl_abort_waiting_for_cs_completions(struct hl_device *hdev)
{
force_complete_cs(hdev);
force_complete_multi_cs(hdev);
hl_release_pending_user_interrupts(hdev);
}
static void job_wq_completion(struct work_struct *work)
@ -1948,8 +1944,7 @@ static int cs_ioctl_signal_wait_create_jobs(struct hl_device *hdev,
else
cb_size = hdev->asic_funcs->get_signal_cb_size(hdev);
cb = hl_cb_kernel_create(hdev, cb_size,
q_type == QUEUE_TYPE_HW && hdev->mmu_enable);
cb = hl_cb_kernel_create(hdev, cb_size, q_type == QUEUE_TYPE_HW);
if (!cb) {
atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
atomic64_inc(&cntr->out_of_mem_drop_cnt);
@ -2152,7 +2147,7 @@ static int cs_ioctl_unreserve_signals(struct hl_fpriv *hpriv, u32 handle_id)
hdev->asic_funcs->hw_queues_unlock(hdev);
rc = -EINVAL;
goto out;
goto out_unlock;
}
/*
@ -2167,15 +2162,21 @@ static int cs_ioctl_unreserve_signals(struct hl_fpriv *hpriv, u32 handle_id)
/* Release the id and free allocated memory of the handle */
idr_remove(&mgr->handles, handle_id);
/* unlock before calling ctx_put, where we might sleep */
spin_unlock(&mgr->lock);
hl_ctx_put(encaps_sig_hdl->ctx);
kfree(encaps_sig_hdl);
goto out;
} else {
rc = -EINVAL;
dev_err(hdev->dev, "failed to unreserve signals, cannot find handler\n");
}
out:
out_unlock:
spin_unlock(&mgr->lock);
out:
return rc;
}

60
drivers/accel/habanalabs/common/debugfs.c
View File

@ -255,9 +255,6 @@ static int vm_show(struct seq_file *s, void *data)
u64 j;
int i;
if (!dev_entry->hdev->mmu_enable)
return 0;
mutex_lock(&dev_entry->ctx_mem_hash_mutex);
list_for_each_entry(ctx, &dev_entry->ctx_mem_hash_list, debugfs_list) {
@ -436,9 +433,6 @@ static int mmu_show(struct seq_file *s, void *data)
u64 virt_addr = dev_entry->mmu_addr, phys_addr;
int i;
if (!hdev->mmu_enable)
return 0;
if (dev_entry->mmu_asid == HL_KERNEL_ASID_ID)
ctx = hdev->kernel_ctx;
else
@ -496,9 +490,6 @@ static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf,
char *c;
ssize_t rc;
if (!hdev->mmu_enable)
return count;
if (count > sizeof(kbuf) - 1)
goto err;
if (copy_from_user(kbuf, buf, count))
@ -535,9 +526,6 @@ static int mmu_ack_error(struct seq_file *s, void *data)
struct hl_device *hdev = dev_entry->hdev;
int rc;
if (!hdev->mmu_enable)
return 0;
if (!dev_entry->mmu_cap_mask) {
dev_err(hdev->dev, "mmu_cap_mask is not set\n");
goto err;
@ -563,9 +551,6 @@ static ssize_t mmu_ack_error_value_write(struct file *file,
char kbuf[MMU_KBUF_SIZE];
ssize_t rc;
if (!hdev->mmu_enable)
return count;
if (count > sizeof(kbuf) - 1)
goto err;
@ -661,9 +646,6 @@ static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
if (!hdev->mmu_enable)
goto out;
if (prop->dram_supports_virtual_memory &&
(addr >= prop->dmmu.start_addr && addr < prop->dmmu.end_addr))
return true;
@ -675,7 +657,7 @@ static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
if (addr >= prop->pmmu_huge.start_addr &&
addr < prop->pmmu_huge.end_addr)
return true;
out:
return false;
}
@ -685,9 +667,6 @@ static bool hl_is_device_internal_memory_va(struct hl_device *hdev, u64 addr,
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 dram_start_addr, dram_end_addr;
if (!hdev->mmu_enable)
return false;
if (prop->dram_supports_virtual_memory) {
dram_start_addr = prop->dmmu.start_addr;
dram_end_addr = prop->dmmu.end_addr;
@ -1756,17 +1735,15 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
}
}
void hl_debugfs_add_device(struct hl_device *hdev)
int hl_debugfs_device_init(struct hl_device *hdev)
{
struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
int count = ARRAY_SIZE(hl_debugfs_list);
dev_entry->hdev = hdev;
dev_entry->entry_arr = kmalloc_array(count,
sizeof(struct hl_debugfs_entry),
GFP_KERNEL);
dev_entry->entry_arr = kmalloc_array(count, sizeof(struct hl_debugfs_entry), GFP_KERNEL);
if (!dev_entry->entry_arr)
return;
return -ENOMEM;
dev_entry->data_dma_blob_desc.size = 0;
dev_entry->data_dma_blob_desc.data = NULL;
@ -1787,21 +1764,14 @@ void hl_debugfs_add_device(struct hl_device *hdev)
spin_lock_init(&dev_entry->userptr_spinlock);
mutex_init(&dev_entry->ctx_mem_hash_mutex);
dev_entry->root = debugfs_create_dir(dev_name(hdev->dev),
hl_debug_root);
add_files_to_device(hdev, dev_entry, dev_entry->root);
if (!hdev->asic_prop.fw_security_enabled)
add_secured_nodes(dev_entry, dev_entry->root);
return 0;
}
void hl_debugfs_remove_device(struct hl_device *hdev)
void hl_debugfs_device_fini(struct hl_device *hdev)
{
struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
int i;
debugfs_remove_recursive(entry->root);
mutex_destroy(&entry->ctx_mem_hash_mutex);
mutex_destroy(&entry->file_mutex);
@ -1814,6 +1784,24 @@ void hl_debugfs_remove_device(struct hl_device *hdev)
kfree(entry->entry_arr);
}
void hl_debugfs_add_device(struct hl_device *hdev)
{
struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
dev_entry->root = debugfs_create_dir(dev_name(hdev->dev), hl_debug_root);
add_files_to_device(hdev, dev_entry, dev_entry->root);
if (!hdev->asic_prop.fw_security_enabled)
add_secured_nodes(dev_entry, dev_entry->root);
}
void hl_debugfs_remove_device(struct hl_device *hdev)
{
struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
debugfs_remove_recursive(entry->root);
}
void hl_debugfs_add_file(struct hl_fpriv *hpriv)
{
struct hl_dbg_device_entry *dev_entry = &hpriv->hdev->hl_debugfs;

112
drivers/accel/habanalabs/common/device.c
View File

@ -674,7 +674,7 @@ static int device_init_cdev(struct hl_device *hdev, struct class *class,
return 0;
}
static int device_cdev_sysfs_add(struct hl_device *hdev)
static int cdev_sysfs_debugfs_add(struct hl_device *hdev)
{
int rc;
@ -699,7 +699,9 @@ static int device_cdev_sysfs_add(struct hl_device *hdev)
goto delete_ctrl_cdev_device;
}
hdev->cdev_sysfs_created = true;
hl_debugfs_add_device(hdev);
hdev->cdev_sysfs_debugfs_created = true;
return 0;
@ -710,11 +712,12 @@ delete_cdev_device:
return rc;
}
static void device_cdev_sysfs_del(struct hl_device *hdev)
static void cdev_sysfs_debugfs_remove(struct hl_device *hdev)
{
if (!hdev->cdev_sysfs_created)
if (!hdev->cdev_sysfs_debugfs_created)
goto put_devices;
hl_debugfs_remove_device(hdev);
hl_sysfs_fini(hdev);
cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
cdev_device_del(&hdev->cdev, hdev->dev);
@ -981,6 +984,18 @@ static void device_early_fini(struct hl_device *hdev)
hdev->asic_funcs->early_fini(hdev);
}
static bool is_pci_link_healthy(struct hl_device *hdev)
{
u16 vendor_id;
if (!hdev->pdev)
return false;
pci_read_config_word(hdev->pdev, PCI_VENDOR_ID, &vendor_id);
return (vendor_id == PCI_VENDOR_ID_HABANALABS);
}
static void hl_device_heartbeat(struct work_struct *work)
{
struct hl_device *hdev = container_of(work, struct hl_device,
@ -995,7 +1010,8 @@ static void hl_device_heartbeat(struct work_struct *work)
goto reschedule;
if (hl_device_operational(hdev, NULL))
dev_err(hdev->dev, "Device heartbeat failed!\n");
dev_err(hdev->dev, "Device heartbeat failed! PCI link is %s\n",
is_pci_link_healthy(hdev) ? "healthy" : "broken");
info.err_type = HL_INFO_FW_HEARTBEAT_ERR;
info.event_mask = &event_mask;
@ -1157,6 +1173,16 @@ static void take_release_locks(struct hl_device *hdev)
mutex_unlock(&hdev->fpriv_ctrl_list_lock);
}
static void hl_abort_waiting_for_completions(struct hl_device *hdev)
{
hl_abort_waiting_for_cs_completions(hdev);
/* Release all pending user interrupts, each pending user interrupt
* holds a reference to a user context.
*/
hl_release_pending_user_interrupts(hdev);
}
static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset,
bool skip_wq_flush)
{
@ -1176,10 +1202,7 @@ static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_r
/* flush the MMU prefetch workqueue */
flush_workqueue(hdev->prefetch_wq);
/* Release all pending user interrupts, each pending user interrupt
* holds a reference to user context
*/
hl_release_pending_user_interrupts(hdev);
hl_abort_waiting_for_completions(hdev);
}
/*
@ -1921,7 +1944,7 @@ out:
hl_ctx_put(ctx);
hl_abort_waitings_for_completion(hdev);
hl_abort_waiting_for_completions(hdev);
return 0;
@ -2034,7 +2057,7 @@ out_err:
int hl_device_init(struct hl_device *hdev)
{
int i, rc, cq_cnt, user_interrupt_cnt, cq_ready_cnt;
bool add_cdev_sysfs_on_err = false;
bool expose_interfaces_on_err = false;
rc = create_cdev(hdev);
if (rc)
@ -2150,16 +2173,22 @@ int hl_device_init(struct hl_device *hdev)
hdev->device_release_watchdog_timeout_sec = HL_DEVICE_RELEASE_WATCHDOG_TIMEOUT_SEC;
hdev->memory_scrub_val = MEM_SCRUB_DEFAULT_VAL;
hl_debugfs_add_device(hdev);
/* debugfs nodes are created in hl_ctx_init so it must be called after
* hl_debugfs_add_device.
rc = hl_debugfs_device_init(hdev);
if (rc) {
dev_err(hdev->dev, "failed to initialize debugfs entry structure\n");
kfree(hdev->kernel_ctx);
goto mmu_fini;
}
/* The debugfs entry structure is accessed in hl_ctx_init(), so it must be called after
* hl_debugfs_device_init().
*/
rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
if (rc) {
dev_err(hdev->dev, "failed to initialize kernel context\n");
kfree(hdev->kernel_ctx);
goto remove_device_from_debugfs;
goto debugfs_device_fini;
}
rc = hl_cb_pool_init(hdev);
@ -2175,11 +2204,10 @@ int hl_device_init(struct hl_device *hdev)
}
/*
* From this point, override rc (=0) in case of an error to allow
* debugging (by adding char devices and create sysfs nodes as part of
* the error flow).
* From this point, override rc (=0) in case of an error to allow debugging
* (by adding char devices and creating sysfs/debugfs files as part of the error flow).
*/
add_cdev_sysfs_on_err = true;
expose_interfaces_on_err = true;
/* Device is now enabled as part of the initialization requires
* communication with the device firmware to get information that
@ -2221,15 +2249,13 @@ int hl_device_init(struct hl_device *hdev)
}
/*
* Expose devices and sysfs nodes to user.
* From here there is no need to add char devices and create sysfs nodes
* in case of an error.
* Expose devices and sysfs/debugfs files to user.
* From here there is no need to expose them in case of an error.
*/
add_cdev_sysfs_on_err = false;
rc = device_cdev_sysfs_add(hdev);
expose_interfaces_on_err = false;
rc = cdev_sysfs_debugfs_add(hdev);
if (rc) {
dev_err(hdev->dev,
"Failed to add char devices and sysfs nodes\n");
dev_err(hdev->dev, "Failed to add char devices and sysfs/debugfs files\n");
rc = 0;
goto out_disabled;
}
@ -2275,8 +2301,8 @@ release_ctx:
if (hl_ctx_put(hdev->kernel_ctx) != 1)
dev_err(hdev->dev,
"kernel ctx is still alive on initialization failure\n");
remove_device_from_debugfs:
hl_debugfs_remove_device(hdev);
debugfs_device_fini:
hl_debugfs_device_fini(hdev);
mmu_fini:
hl_mmu_fini(hdev);
eq_fini:
@ -2300,15 +2326,11 @@ free_dev:
put_device(hdev->dev);
out_disabled:
hdev->disabled = true;
if (add_cdev_sysfs_on_err)
device_cdev_sysfs_add(hdev);
if (hdev->pdev)
dev_err(&hdev->pdev->dev,
"Failed to initialize hl%d. Device %s is NOT usable !\n",
hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));
else
pr_err("Failed to initialize hl%d. Device %s is NOT usable !\n",
hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));
if (expose_interfaces_on_err)
cdev_sysfs_debugfs_add(hdev);
dev_err(&hdev->pdev->dev,
"Failed to initialize hl%d. Device %s is NOT usable !\n",
hdev->cdev_idx, dev_name(&hdev->pdev->dev));
return rc;
}
@ -2427,8 +2449,6 @@ void hl_device_fini(struct hl_device *hdev)
if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
dev_err(hdev->dev, "kernel ctx is still alive\n");
hl_debugfs_remove_device(hdev);
hl_dec_fini(hdev);
hl_vm_fini(hdev);
@ -2453,8 +2473,10 @@ void hl_device_fini(struct hl_device *hdev)
device_early_fini(hdev);
/* Hide devices and sysfs nodes from user */
device_cdev_sysfs_del(hdev);
/* Hide devices and sysfs/debugfs files from user */
cdev_sysfs_debugfs_remove(hdev);
hl_debugfs_device_fini(hdev);
pr_info("removed device successfully\n");
}
@ -2667,3 +2689,11 @@ void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info)
if (info->event_mask)
*info->event_mask |= HL_NOTIFIER_EVENT_CRITICL_FW_ERR;
}
void hl_enable_err_info_capture(struct hl_error_info *captured_err_info)
{
vfree(captured_err_info->page_fault_info.user_mappings);
memset(captured_err_info, 0, sizeof(struct hl_error_info));
atomic_set(&captured_err_info->cs_timeout.write_enable, 1);
captured_err_info->undef_opcode.write_enable = true;
}

218
drivers/accel/habanalabs/common/firmware_if.c
View File

@ -71,38 +71,124 @@ free_fw_ver:
return NULL;
}
/**
* extract_u32_until_given_char() - given a string of the format "<u32><char>*", extract the u32.
* @str: the given string
* @ver_num: the pointer to the extracted u32 to be returned to the caller.
* @given_char: the given char at the end of the u32 in the string
*
* Return: Upon success, return a pointer to the given_char in the string. Upon failure, return NULL
*/
static char *extract_u32_until_given_char(char *str, u32 *ver_num, char given_char)
{
char num_str[8] = {}, *ch;
ch = strchrnul(str, given_char);
if (*ch == '\0' || ch == str || ch - str >= sizeof(num_str))
return NULL;
memcpy(num_str, str, ch - str);
if (kstrtou32(num_str, 10, ver_num))
return NULL;
return ch;
}
/**
* hl_get_sw_major_minor_subminor() - extract the FW's SW version major, minor, sub-minor
* from the version string
* @hdev: pointer to the hl_device
* @fw_str: the FW's version string
*
* The extracted version is set in the hdev fields: fw_sw_{major/minor/sub_minor}_ver.
*
* fw_str is expected to have one of two possible formats, examples:
* 1) 'Preboot version hl-gaudi2-1.9.0-fw-42.0.1-sec-3'
* 2) 'Preboot version hl-gaudi2-1.9.0-rc-fw-42.0.1-sec-3'
* In those examples, the SW major,minor,subminor are correspondingly: 1,9,0.
*
* Return: 0 for success or a negative error code for failure.
*/
static int hl_get_sw_major_minor_subminor(struct hl_device *hdev, const char *fw_str)
{
char *end, *start;
end = strnstr(fw_str, "-rc-", VERSION_MAX_LEN);
if (end == fw_str)
return -EINVAL;
if (!end)
end = strnstr(fw_str, "-fw-", VERSION_MAX_LEN);
if (end == fw_str)
return -EINVAL;
if (!end)
return -EINVAL;
for (start = end - 1; start != fw_str; start--) {
if (*start == '-')
break;
}
if (start == fw_str)
return -EINVAL;
/* start/end point each to the starting and ending hyphen of the sw version e.g. -1.9.0- */
start++;
start = extract_u32_until_given_char(start, &hdev->fw_sw_major_ver, '.');
if (!start)
goto err_zero_ver;
start++;
start = extract_u32_until_given_char(start, &hdev->fw_sw_minor_ver, '.');
if (!start)
goto err_zero_ver;
start++;
start = extract_u32_until_given_char(start, &hdev->fw_sw_sub_minor_ver, '-');
if (!start)
goto err_zero_ver;
return 0;
err_zero_ver:
hdev->fw_sw_major_ver = 0;
hdev->fw_sw_minor_ver = 0;
hdev->fw_sw_sub_minor_ver = 0;
return -EINVAL;
}
/**
* hl_get_preboot_major_minor() - extract the FW's version major, minor from the version string.
* @hdev: pointer to the hl_device
* @preboot_ver: the FW's version string
*
* preboot_ver is expected to be the format of <major>.<minor>.<sub minor>*, e.g: 42.0.1-sec-3
* The extracted version is set in the hdev fields: fw_inner_{major/minor}_ver.
*
* Return: 0 on success, negative error code for failure.
*/
static int hl_get_preboot_major_minor(struct hl_device *hdev, char *preboot_ver)
{
char major[8], minor[8], *first_dot, *second_dot;
int rc;
first_dot = strnstr(preboot_ver, ".", 10);
if (first_dot) {
strscpy(major, preboot_ver, first_dot - preboot_ver + 1);
rc = kstrtou32(major, 10, &hdev->fw_major_version);
} else {
rc = -EINVAL;
preboot_ver = extract_u32_until_given_char(preboot_ver, &hdev->fw_inner_major_ver, '.');
if (!preboot_ver) {
dev_err(hdev->dev, "Error parsing preboot major version\n");
goto err_zero_ver;
}
if (rc) {
dev_err(hdev->dev, "Error %d parsing preboot major version\n", rc);
return rc;
preboot_ver++;
preboot_ver = extract_u32_until_given_char(preboot_ver, &hdev->fw_inner_minor_ver, '.');
if (!preboot_ver) {
dev_err(hdev->dev, "Error parsing preboot minor version\n");
goto err_zero_ver;
}
return 0;
/* skip the first dot */
first_dot++;
second_dot = strnstr(first_dot, ".", 10);
if (second_dot) {
strscpy(minor, first_dot, second_dot - first_dot + 1);
rc = kstrtou32(minor, 10, &hdev->fw_minor_version);
} else {
rc = -EINVAL;
}
if (rc)
dev_err(hdev->dev, "Error %d parsing preboot minor version\n", rc);
return rc;
err_zero_ver:
hdev->fw_inner_major_ver = 0;
hdev->fw_inner_minor_ver = 0;
return -EINVAL;
}
static int hl_request_fw(struct hl_device *hdev,
@ -505,6 +591,20 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
size);
}
int hl_fw_send_soft_reset(struct hl_device *hdev)
{
struct cpucp_packet pkt;
int rc;
memset(&pkt, 0, sizeof(pkt));
pkt.ctl = cpu_to_le32(CPUCP_PACKET_SOFT_RESET << CPUCP_PKT_CTL_OPCODE_SHIFT);
rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
if (rc)
dev_err(hdev->dev, "failed to send soft-reset msg (err = %d)\n", rc);
return rc;
}
int hl_fw_send_device_activity(struct hl_device *hdev, bool open)
{
struct cpucp_packet pkt;
@ -1268,8 +1368,10 @@ void hl_fw_ask_hard_reset_without_linux(struct hl_device *hdev)
void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
{
struct static_fw_load_mgr *static_loader =
&hdev->fw_loader.static_loader;
struct fw_load_mgr *fw_loader = &hdev->fw_loader;
u32 status, cpu_boot_status_reg, cpu_timeout;
struct static_fw_load_mgr *static_loader;
struct pre_fw_load_props *pre_fw_load;
int rc;
if (hdev->device_cpu_is_halted)
@ -1277,12 +1379,28 @@ void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
/* Stop device CPU to make sure nothing bad happens */
if (hdev->asic_prop.dynamic_fw_load) {
pre_fw_load = &fw_loader->pre_fw_load;
cpu_timeout = fw_loader->cpu_timeout;
cpu_boot_status_reg = pre_fw_load->cpu_boot_status_reg;
rc = hl_fw_dynamic_send_protocol_cmd(hdev, &hdev->fw_loader,
COMMS_GOTO_WFE, 0, false,
hdev->fw_loader.cpu_timeout);
if (rc)
COMMS_GOTO_WFE, 0, false, cpu_timeout);
if (rc) {
dev_err(hdev->dev, "Failed sending COMMS_GOTO_WFE\n");
} else {
rc = hl_poll_timeout(
hdev,
cpu_boot_status_reg,
status,
status == CPU_BOOT_STATUS_IN_WFE,
hdev->fw_poll_interval_usec,
cpu_timeout);
if (rc)
dev_err(hdev->dev, "Current status=%u. Timed-out updating to WFE\n",
status);
}
} else {
static_loader = &hdev->fw_loader.static_loader;
WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_GOTO_WFE);
msleep(static_loader->cpu_reset_wait_msec);
@ -2151,6 +2269,7 @@ static int hl_fw_dynamic_read_device_fw_version(struct hl_device *hdev,
struct asic_fixed_properties *prop = &hdev->asic_prop;
char *preboot_ver, *boot_ver;
char btl_ver[32];
int rc;
switch (fwc) {
case FW_COMP_BOOT_FIT:
@ -2164,20 +2283,20 @@ static int hl_fw_dynamic_read_device_fw_version(struct hl_device *hdev,
break;
case FW_COMP_PREBOOT:
strscpy(prop->preboot_ver, fw_version, VERSION_MAX_LEN);
preboot_ver = strnstr(prop->preboot_ver, "Preboot",
VERSION_MAX_LEN);
preboot_ver = strnstr(prop->preboot_ver, "Preboot", VERSION_MAX_LEN);
dev_info(hdev->dev, "preboot full version: '%s'\n", preboot_ver);
if (preboot_ver && preboot_ver != prop->preboot_ver) {
strscpy(btl_ver, prop->preboot_ver,
min((int) (preboot_ver - prop->preboot_ver), 31));
dev_info(hdev->dev, "%s\n", btl_ver);
}
rc = hl_get_sw_major_minor_subminor(hdev, preboot_ver);
if (rc)
return rc;
preboot_ver = extract_fw_ver_from_str(prop->preboot_ver);
if (preboot_ver) {
int rc;
dev_info(hdev->dev, "preboot version %s\n", preboot_ver);
rc = hl_get_preboot_major_minor(hdev, preboot_ver);
kfree(preboot_ver);
if (rc)
@ -2367,16 +2486,6 @@ static int hl_fw_dynamic_load_image(struct hl_device *hdev,
if (rc)
goto release_fw;
/* update state according to boot stage */
if (cur_fwc == FW_COMP_BOOT_FIT) {
struct cpu_dyn_regs *dyn_regs;
dyn_regs = &fw_loader->dynamic_loader.comm_desc.cpu_dyn_regs;
hl_fw_boot_fit_update_state(hdev,
le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
}
/* copy boot fit to space allocated by FW */
rc = hl_fw_dynamic_copy_image(hdev, fw, fw_loader);
if (rc)
@ -2679,6 +2788,14 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
goto protocol_err;
}
rc = hl_fw_dynamic_wait_for_boot_fit_active(hdev, fw_loader);
if (rc)
goto protocol_err;
hl_fw_boot_fit_update_state(hdev,
le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
/*
* when testing FW load (without Linux) on PLDM we don't want to
* wait until boot fit is active as it may take several hours.
@ -2688,10 +2805,6 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
if (hdev->pldm && !(hdev->fw_components & FW_TYPE_LINUX))
return 0;
rc = hl_fw_dynamic_wait_for_boot_fit_active(hdev, fw_loader);
if (rc)
goto protocol_err;
/* Enable DRAM scrambling before Linux boot and after successful
* UBoot
*/
@ -2725,7 +2838,8 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
if (rc)
goto protocol_err;
hl_fw_linux_update_state(hdev, le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
hl_fw_linux_update_state(hdev,
le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
hl_fw_dynamic_update_linux_interrupt_if(hdev);

77
drivers/accel/habanalabs/common/habanalabs.h
View File

@ -36,6 +36,8 @@
struct hl_device;
struct hl_fpriv;
#define PCI_VENDOR_ID_HABANALABS 0x1da3
/* Use upper bits of mmap offset to store habana driver specific information.
* bits[63:59] - Encode mmap type
* bits[45:0] - mmap offset value
@ -113,18 +115,6 @@ enum hl_mmu_page_table_location {
MMU_NUM_PGT_LOCATIONS /* num of PGT locations */
};
/**
* enum hl_mmu_enablement - what mmu modules to enable
* @MMU_EN_NONE: mmu disabled.
* @MMU_EN_ALL: enable all.
* @MMU_EN_PMMU_ONLY: Enable only the PMMU leaving the DMMU disabled.
*/
enum hl_mmu_enablement {
MMU_EN_NONE = 0,
MMU_EN_ALL = 1,
MMU_EN_PMMU_ONLY = 3, /* N/A for Goya/Gaudi */
};
/*
* HL_RSVD_SOBS 'sync stream' reserved sync objects per QMAN stream
* HL_RSVD_MONS 'sync stream' reserved monitors per QMAN stream
@ -2568,12 +2558,7 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
ktime_t __timeout; \
u32 __elbi_read; \
int __rc = 0; \
if (hdev->pdev) \
__timeout = ktime_add_us(ktime_get(), timeout_us); \
else \
__timeout = ktime_add_us(ktime_get(),\
min((u64)(timeout_us * 10), \
(u64) HL_SIM_MAX_TIMEOUT_US)); \
__timeout = ktime_add_us(ktime_get(), timeout_us); \
might_sleep_if(sleep_us); \
for (;;) { \
if (elbi) { \
@ -2625,13 +2610,7 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
u8 __arr_idx; \
int __rc = 0; \
\
if (hdev->pdev) \
__timeout = ktime_add_us(ktime_get(), timeout_us); \
else \
__timeout = ktime_add_us(ktime_get(),\
min(((u64)timeout_us * 10), \
(u64) HL_SIM_MAX_TIMEOUT_US)); \
\
__timeout = ktime_add_us(ktime_get(), timeout_us); \
might_sleep_if(sleep_us); \
if (arr_size >= 64) \
__rc = -EINVAL; \
@ -2689,12 +2668,8 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
mem_written_by_device) \
({ \
ktime_t __timeout; \
if (hdev->pdev) \
__timeout = ktime_add_us(ktime_get(), timeout_us); \
else \
__timeout = ktime_add_us(ktime_get(),\
min((u64)(timeout_us * 100), \
(u64) HL_SIM_MAX_TIMEOUT_US)); \
\
__timeout = ktime_add_us(ktime_get(), timeout_us); \
might_sleep_if(sleep_us); \
for (;;) { \
/* Verify we read updates done by other cores or by device */ \
@ -3225,8 +3200,11 @@ struct hl_reset_info {
* @captured_err_info: holds information about errors.
* @reset_info: holds current device reset information.
* @stream_master_qid_arr: pointer to array with QIDs of master streams.
* @fw_major_version: major version of current loaded preboot.
* @fw_minor_version: minor version of current loaded preboot.
* @fw_inner_major_ver: the major of current loaded preboot inner version.
* @fw_inner_minor_ver: the minor of current loaded preboot inner version.
* @fw_sw_major_ver: the major of current loaded preboot SW version.
* @fw_sw_minor_ver: the minor of current loaded preboot SW version.
* @fw_sw_sub_minor_ver: the sub-minor of current loaded preboot SW version.
* @dram_used_mem: current DRAM memory consumption.
* @memory_scrub_val: the value to which the dram will be scrubbed to using cb scrub_device_dram
* @timeout_jiffies: device CS timeout value.
@ -3287,7 +3265,7 @@ struct hl_reset_info {
* @in_debug: whether the device is in a state where the profiling/tracing infrastructure
* can be used. This indication is needed because in some ASICs we need to do
* specific operations to enable that infrastructure.
* @cdev_sysfs_created: were char devices and sysfs nodes created.
* @cdev_sysfs_debugfs_created: were char devices and sysfs/debugfs files created.
* @stop_on_err: true if engines should stop on error.
* @supports_sync_stream: is sync stream supported.
* @sync_stream_queue_idx: helper index for sync stream queues initialization.
@ -3314,7 +3292,7 @@ struct hl_reset_info {
* @nic_ports_mask: Controls which NIC ports are enabled. Used only for testing.
* @fw_components: Controls which f/w components to load to the device. There are multiple f/w
* stages and sometimes we want to stop at a certain stage. Used only for testing.
* @mmu_enable: Whether to enable or disable the device MMU(s). Used only for testing.
* @mmu_disable: Disable the device MMU(s). Used only for testing.
* @cpu_queues_enable: Whether to enable queues communication vs. the f/w. Used only for testing.
* @pldm: Whether we are running in Palladium environment. Used only for testing.
* @hard_reset_on_fw_events: Whether to do device hard-reset when a fatal event is received from
@ -3412,8 +3390,11 @@ struct hl_device {
struct hl_reset_info reset_info;
u32 *stream_master_qid_arr;
u32 fw_major_version;
u32 fw_minor_version;
u32 fw_inner_major_ver;
u32 fw_inner_minor_ver;
u32 fw_sw_major_ver;
u32 fw_sw_minor_ver;
u32 fw_sw_sub_minor_ver;
atomic64_t dram_used_mem;
u64 memory_scrub_val;
u64 timeout_jiffies;
@ -3451,7 +3432,7 @@ struct hl_device {
u8 init_done;
u8 device_cpu_disabled;
u8 in_debug;
u8 cdev_sysfs_created;
u8 cdev_sysfs_debugfs_created;
u8 stop_on_err;
u8 supports_sync_stream;
u8 sync_stream_queue_idx;
@ -3474,7 +3455,7 @@ struct hl_device {
/* Parameters for bring-up to be upstreamed */
u64 nic_ports_mask;
u64 fw_components;
u8 mmu_enable;
u8 mmu_disable;
u8 cpu_queues_enable;
u8 pldm;
u8 hard_reset_on_fw_events;
@ -3547,9 +3528,15 @@ struct hl_ioctl_desc {
hl_ioctl_t *func;
};
static inline bool hl_is_fw_ver_below_1_9(struct hl_device *hdev)
static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major, u32 fw_sw_minor)
{
return (hdev->fw_major_version < 42);
if (hdev->fw_sw_major_ver < fw_sw_major)
return true;
if (hdev->fw_sw_major_ver > fw_sw_major)
return false;
if (hdev->fw_sw_minor_ver < fw_sw_minor)
return true;
return false;
}
/*
@ -3813,8 +3800,6 @@ struct pgt_info *hl_mmu_hr_get_alloc_next_hop(struct hl_ctx *ctx,
u64 curr_pte, bool *is_new_hop);
int hl_mmu_hr_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_info *hops,
struct hl_hr_mmu_funcs *hr_func);
void hl_mmu_swap_out(struct hl_ctx *ctx);
void hl_mmu_swap_in(struct hl_ctx *ctx);
int hl_mmu_if_set_funcs(struct hl_device *hdev);
void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
void hl_mmu_v2_hr_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
@ -3872,6 +3857,7 @@ int hl_fw_dram_replaced_row_get(struct hl_device *hdev,
int hl_fw_dram_pending_row_get(struct hl_device *hdev, u32 *pend_rows_num);
int hl_fw_cpucp_engine_core_asid_set(struct hl_device *hdev, u32 asid);
int hl_fw_send_device_activity(struct hl_device *hdev, bool open);
int hl_fw_send_soft_reset(struct hl_device *hdev);
int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3],
bool is_wc[3]);
int hl_pci_elbi_read(struct hl_device *hdev, u64 addr, u32 *data);
@ -3921,7 +3907,7 @@ void hl_dec_fini(struct hl_device *hdev);
void hl_dec_ctx_fini(struct hl_ctx *ctx);
void hl_release_pending_user_interrupts(struct hl_device *hdev);
void hl_abort_waitings_for_completion(struct hl_device *hdev);
void hl_abort_waiting_for_cs_completions(struct hl_device *hdev);
int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
struct hl_hw_sob **hw_sob, u32 count, bool encaps_sig);
@ -3958,11 +3944,14 @@ void hl_handle_page_fault(struct hl_device *hdev, u64 addr, u16 eng_id, bool is_
u64 *event_mask);
void hl_handle_critical_hw_err(struct hl_device *hdev, u16 event_id, u64 *event_mask);
void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info);
void hl_enable_err_info_capture(struct hl_error_info *captured_err_info);
#ifdef CONFIG_DEBUG_FS
void hl_debugfs_init(void);
void hl_debugfs_fini(void);
int hl_debugfs_device_init(struct hl_device *hdev);
void hl_debugfs_device_fini(struct hl_device *hdev);
void hl_debugfs_add_device(struct hl_device *hdev);
void hl_debugfs_remove_device(struct hl_device *hdev);
void hl_debugfs_add_file(struct hl_fpriv *hpriv);

9
drivers/accel/habanalabs/common/habanalabs_drv.c
View File

@ -13,6 +13,7 @@
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#define CREATE_TRACE_POINTS
#include <trace/events/habanalabs.h>
@ -54,8 +55,6 @@ module_param(boot_error_status_mask, ulong, 0444);
MODULE_PARM_DESC(boot_error_status_mask,
"Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)");
#define PCI_VENDOR_ID_HABANALABS 0x1da3
#define PCI_IDS_GOYA 0x0001
#define PCI_IDS_GAUDI 0x1000
#define PCI_IDS_GAUDI_SEC 0x1010
@ -220,9 +219,7 @@ int hl_device_open(struct inode *inode, struct file *filp)
hl_debugfs_add_file(hpriv);
memset(&hdev->captured_err_info, 0, sizeof(hdev->captured_err_info));
atomic_set(&hdev->captured_err_info.cs_timeout.write_enable, 1);
hdev->captured_err_info.undef_opcode.write_enable = true;
hl_enable_err_info_capture(&hdev->captured_err_info);
hdev->open_counter++;
hdev->last_successful_open_jif = jiffies;
@ -307,7 +304,6 @@ static void set_driver_behavior_per_device(struct hl_device *hdev)
{
hdev->nic_ports_mask = 0;
hdev->fw_components = FW_TYPE_ALL_TYPES;
hdev->mmu_enable = MMU_EN_ALL;
hdev->cpu_queues_enable = 1;
hdev->pldm = 0;
hdev->hard_reset_on_fw_events = 1;
@ -382,7 +378,6 @@ static int fixup_device_params(struct hl_device *hdev)
/* If CPU queues not enabled, no way to do heartbeat */
if (!hdev->cpu_queues_enable)
hdev->heartbeat = 0;
fixup_device_params_per_asic(hdev, tmp_timeout);
return 0;

35
drivers/accel/habanalabs/common/habanalabs_ioctl.c
View File

@ -62,7 +62,7 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
hw_ip.device_id = hdev->asic_funcs->get_pci_id(hdev);
hw_ip.sram_base_address = prop->sram_user_base_address;
hw_ip.dram_base_address =
hdev->mmu_enable && prop->dram_supports_virtual_memory ?
prop->dram_supports_virtual_memory ?
prop->dmmu.start_addr : prop->dram_user_base_address;
hw_ip.tpc_enabled_mask = prop->tpc_enabled_mask & 0xFF;
hw_ip.tpc_enabled_mask_ext = prop->tpc_enabled_mask;
@ -71,11 +71,8 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
dram_available_size = prop->dram_size - dram_kmd_size;
if (hdev->mmu_enable == MMU_EN_ALL)
hw_ip.dram_size = DIV_ROUND_DOWN_ULL(dram_available_size,
prop->dram_page_size) * prop->dram_page_size;
else
hw_ip.dram_size = dram_available_size;
hw_ip.dram_size = DIV_ROUND_DOWN_ULL(dram_available_size, prop->dram_page_size) *
prop->dram_page_size;
if (hw_ip.dram_size > PAGE_SIZE)
hw_ip.dram_enabled = 1;
@ -842,15 +839,15 @@ static int hw_err_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
struct hw_err_info *info;
int rc;
if ((!user_buf_size) || (!user_buf))
if (!user_buf)
return -EINVAL;
if (user_buf_size < sizeof(struct hl_info_hw_err_event))
return -ENOMEM;
info = &hdev->captured_err_info.hw_err;
if (!info->event_info_available)
return -ENOENT;
return 0;
if (user_buf_size < sizeof(struct hl_info_hw_err_event))
return -ENOMEM;
rc = copy_to_user(user_buf, &info->event, sizeof(struct hl_info_hw_err_event));
return rc ? -EFAULT : 0;
@ -864,15 +861,15 @@ static int fw_err_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
struct fw_err_info *info;
int rc;
if ((!user_buf_size) || (!user_buf))
if (!user_buf)
return -EINVAL;
if (user_buf_size < sizeof(struct hl_info_fw_err_event))
return -ENOMEM;
info = &hdev->captured_err_info.fw_err;
if (!info->event_info_available)
return -ENOENT;
return 0;
if (user_buf_size < sizeof(struct hl_info_fw_err_event))
return -ENOMEM;
rc = copy_to_user(user_buf, &info->event, sizeof(struct hl_info_fw_err_event));
return rc ? -EFAULT : 0;
@ -1198,7 +1195,7 @@ static long _hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg,
out_err:
if (retcode)
dev_dbg(dev, "error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
dev_dbg_ratelimited(dev, "error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
task_pid_nr(current), cmd, nr);
if (kdata != stack_kdata)
@ -1222,7 +1219,7 @@ long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
ioctl = &hl_ioctls[nr];
} else {
dev_err(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
dev_dbg_ratelimited(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
task_pid_nr(current), nr);
return -ENOTTY;
}
@ -1245,7 +1242,7 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
if (nr == _IOC_NR(HL_IOCTL_INFO)) {
ioctl = &hl_ioctls_control[nr];
} else {
dev_err(hdev->dev_ctrl, "invalid ioctl: pid=%d, nr=0x%02x\n",
dev_dbg_ratelimited(hdev->dev_ctrl, "invalid ioctl: pid=%d, nr=0x%02x\n",
task_pid_nr(current), nr);
return -ENOTTY;
}

2
drivers/accel/habanalabs/common/irq.c
View File

@ -430,7 +430,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg)
cur_eqe_index = FIELD_GET(EQ_CTL_INDEX_MASK, cur_eqe);
if ((hdev->event_queue.check_eqe_index) &&
(((eq->prev_eqe_index + 1) & EQ_CTL_INDEX_MASK) != cur_eqe_index)) {
dev_dbg(hdev->dev,
dev_err(hdev->dev,
"EQE %#x in queue is ready but index does not match %d!=%d",
cur_eqe,
((eq->prev_eqe_index + 1) & EQ_CTL_INDEX_MASK),

104
drivers/accel/habanalabs/common/memory.c
View File

@ -1034,30 +1034,6 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
}
}
static int get_paddr_from_handle(struct hl_ctx *ctx, struct hl_mem_in *args,
u64 *paddr)
{
struct hl_device *hdev = ctx->hdev;
struct hl_vm *vm = &hdev->vm;
struct hl_vm_phys_pg_pack *phys_pg_pack;
u32 handle;
handle = lower_32_bits(args->map_device.handle);
spin_lock(&vm->idr_lock);
phys_pg_pack = idr_find(&vm->phys_pg_pack_handles, handle);
if (!phys_pg_pack) {
spin_unlock(&vm->idr_lock);
dev_err(hdev->dev, "no match for handle %u\n", handle);
return -EINVAL;
}
*paddr = phys_pg_pack->pages[0];
spin_unlock(&vm->idr_lock);
return 0;
}
/**
* map_device_va() - map the given memory.
* @ctx: pointer to the context structure.
@ -2094,76 +2070,6 @@ err_free_dmabuf_wrapper:
return rc;
}
static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
{
struct hl_device *hdev = hpriv->hdev;
u64 block_handle, device_addr = 0;
struct hl_ctx *ctx = hpriv->ctx;
u32 handle = 0, block_size;
int rc;
switch (args->in.op) {
case HL_MEM_OP_ALLOC:
if (args->in.alloc.mem_size == 0) {
dev_err(hdev->dev, "alloc size must be larger than 0\n");
rc = -EINVAL;
goto out;
}
/* Force contiguous as there are no real MMU
* translations to overcome physical memory gaps
*/
args->in.flags |= HL_MEM_CONTIGUOUS;
rc = alloc_device_memory(ctx, &args->in, &handle);
memset(args, 0, sizeof(*args));
args->out.handle = (__u64) handle;
break;
case HL_MEM_OP_FREE:
rc = free_device_memory(ctx, &args->in);
break;
case HL_MEM_OP_MAP:
if (args->in.flags & HL_MEM_USERPTR) {
dev_err(hdev->dev, "Failed to map host memory when MMU is disabled\n");
rc = -EPERM;
} else {
rc = get_paddr_from_handle(ctx, &args->in, &device_addr);
memset(args, 0, sizeof(*args));
args->out.device_virt_addr = device_addr;
}
break;
case HL_MEM_OP_UNMAP:
rc = 0;
break;
case HL_MEM_OP_MAP_BLOCK:
rc = map_block(hdev, args->in.map_block.block_addr, &block_handle, &block_size);
args->out.block_handle = block_handle;
args->out.block_size = block_size;
break;
case HL_MEM_OP_EXPORT_DMABUF_FD:
dev_err(hdev->dev, "Failed to export dma-buf object when MMU is disabled\n");
rc = -EPERM;
break;
case HL_MEM_OP_TS_ALLOC:
rc = allocate_timestamps_buffers(hpriv, &args->in, &args->out.handle);
break;
default:
dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
rc = -EINVAL;
break;
}
out:
return rc;
}
static void ts_buff_release(struct hl_mmap_mem_buf *buf)
{
struct hl_ts_buff *ts_buff = buf->private;
@ -2282,9 +2188,6 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
return -EBUSY;
}
if (!hdev->mmu_enable)
return mem_ioctl_no_mmu(hpriv, args);
switch (args->in.op) {
case HL_MEM_OP_ALLOC:
if (args->in.alloc.mem_size == 0) {
@ -2779,13 +2682,10 @@ int hl_vm_ctx_init(struct hl_ctx *ctx)
atomic64_set(&ctx->dram_phys_mem, 0);
/*
* - If MMU is enabled, init the ranges as usual.
* - If MMU is disabled, in case of host mapping, the returned address
* is the given one.
* In case of DRAM mapping, the returned address is the physical
* address of the memory related to the given handle.
*/
if (!ctx->hdev->mmu_enable)
if (ctx->hdev->mmu_disable)
return 0;
dram_range_start = prop->dmmu.start_addr;
@ -2835,7 +2735,7 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
struct hl_mem_in args;
int i;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return;
hl_debugfs_remove_ctx_mem_hash(hdev, ctx);

56
drivers/accel/habanalabs/common/mmu/mmu.c
View File

@ -44,7 +44,7 @@ int hl_mmu_init(struct hl_device *hdev)
{
int rc = -EOPNOTSUPP;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return 0;
mutex_init(&hdev->mmu_lock);
@ -82,7 +82,7 @@ fini_dr_mmu:
*/
void hl_mmu_fini(struct hl_device *hdev)
{
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return;
if (hdev->mmu_func[MMU_DR_PGT].fini != NULL)
@ -107,7 +107,7 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx)
struct hl_device *hdev = ctx->hdev;
int rc = -EOPNOTSUPP;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return 0;
if (hdev->mmu_func[MMU_DR_PGT].ctx_init != NULL) {
@ -145,7 +145,7 @@ void hl_mmu_ctx_fini(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return;
if (hdev->mmu_func[MMU_DR_PGT].ctx_fini != NULL)
@ -233,7 +233,7 @@ int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, bool flu
u64 real_virt_addr;
bool is_dram_addr;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return 0;
is_dram_addr = hl_is_dram_va(hdev, virt_addr);
@ -301,7 +301,7 @@ int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_s
bool is_dram_addr;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return 0;
is_dram_addr = hl_is_dram_va(hdev, virt_addr);
@ -472,46 +472,6 @@ int hl_mmu_unmap_contiguous(struct hl_ctx *ctx, u64 virt_addr, u32 size)
return rc;
}
/*
* hl_mmu_swap_out - marks all mapping of the given ctx as swapped out
*
* @ctx: pointer to the context structure
*
*/
void hl_mmu_swap_out(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
if (!hdev->mmu_enable)
return;
if (hdev->mmu_func[MMU_DR_PGT].swap_out != NULL)
hdev->mmu_func[MMU_DR_PGT].swap_out(ctx);
if (hdev->mmu_func[MMU_HR_PGT].swap_out != NULL)
hdev->mmu_func[MMU_HR_PGT].swap_out(ctx);
}
/*
* hl_mmu_swap_in - marks all mapping of the given ctx as swapped in
*
* @ctx: pointer to the context structure
*
*/
void hl_mmu_swap_in(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
if (!hdev->mmu_enable)
return;
if (hdev->mmu_func[MMU_DR_PGT].swap_in != NULL)
hdev->mmu_func[MMU_DR_PGT].swap_in(ctx);
if (hdev->mmu_func[MMU_HR_PGT].swap_in != NULL)
hdev->mmu_func[MMU_HR_PGT].swap_in(ctx);
}
static void hl_mmu_pa_page_with_offset(struct hl_ctx *ctx, u64 virt_addr,
struct hl_mmu_hop_info *hops,
u64 *phys_addr)
@ -594,7 +554,7 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
int pgt_residency, rc;
bool is_dram_addr;
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return -EOPNOTSUPP;
prop = &hdev->asic_prop;
@ -625,7 +585,7 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
int hl_mmu_if_set_funcs(struct hl_device *hdev)
{
if (!hdev->mmu_enable)
if (hdev->mmu_disable)
return 0;
switch (hdev->asic_type) {

57
drivers/accel/habanalabs/common/security.c
View File

@ -284,14 +284,14 @@ void hl_secure_block(struct hl_device *hdev,
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_array: register array
* @regs_array_size: register array size
* @user_regs_array: unsecured register array
* @user_regs_array_size: unsecured register array size
* @mask: enabled instances mask: 1- enabled, 0- disabled
*/
int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
u32 dcore_offset, u32 num_instances, u32 instance_offset,
const u32 pb_blocks[], u32 blocks_array_size,
const u32 *regs_array, u32 regs_array_size, u64 mask)
const u32 *user_regs_array, u32 user_regs_array_size, u64 mask)
{
int i, j;
struct hl_block_glbl_sec *glbl_sec;
@ -303,8 +303,8 @@ int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
return -ENOMEM;
hl_secure_block(hdev, glbl_sec, blocks_array_size);
hl_unsecure_registers(hdev, regs_array, regs_array_size, 0, pb_blocks,
glbl_sec, blocks_array_size);
hl_unsecure_registers(hdev, user_regs_array, user_regs_array_size, 0,
pb_blocks, glbl_sec, blocks_array_size);
/* Fill all blocks with the same configuration */
for (i = 0 ; i < num_dcores ; i++) {
@ -336,19 +336,19 @@ int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_array: register array
* @regs_array_size: register array size
* @user_regs_array: unsecured register array
* @user_regs_array_size: unsecured register array size
*
*/
int hl_init_pb(struct hl_device *hdev, u32 num_dcores, u32 dcore_offset,
u32 num_instances, u32 instance_offset,
const u32 pb_blocks[], u32 blocks_array_size,
const u32 *regs_array, u32 regs_array_size)
const u32 *user_regs_array, u32 user_regs_array_size)
{
return hl_init_pb_with_mask(hdev, num_dcores, dcore_offset,
num_instances, instance_offset, pb_blocks,
blocks_array_size, regs_array, regs_array_size,
ULLONG_MAX);
blocks_array_size, user_regs_array,
user_regs_array_size, ULLONG_MAX);
}
/**
@ -364,15 +364,15 @@ int hl_init_pb(struct hl_device *hdev, u32 num_dcores, u32 dcore_offset,
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_range_array: register range array
* @regs_range_array_size: register range array size
* @user_regs_range_array: unsecured register range array
* @user_regs_range_array_size: unsecured register range array size
* @mask: enabled instances mask: 1- enabled, 0- disabled
*/
int hl_init_pb_ranges_with_mask(struct hl_device *hdev, u32 num_dcores,
u32 dcore_offset, u32 num_instances, u32 instance_offset,
const u32 pb_blocks[], u32 blocks_array_size,
const struct range *regs_range_array, u32 regs_range_array_size,
u64 mask)
const struct range *user_regs_range_array,
u32 user_regs_range_array_size, u64 mask)
{
int i, j, rc = 0;
struct hl_block_glbl_sec *glbl_sec;
@ -384,8 +384,8 @@ int hl_init_pb_ranges_with_mask(struct hl_device *hdev, u32 num_dcores,
return -ENOMEM;
hl_secure_block(hdev, glbl_sec, blocks_array_size);
rc = hl_unsecure_registers_range(hdev, regs_range_array,
regs_range_array_size, 0, pb_blocks, glbl_sec,
rc = hl_unsecure_registers_range(hdev, user_regs_range_array,
user_regs_range_array_size, 0, pb_blocks, glbl_sec,
blocks_array_size);
if (rc)
goto free_glbl_sec;
@ -422,19 +422,20 @@ free_glbl_sec:
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_range_array: register range array
* @regs_range_array_size: register range array size
* @user_regs_range_array: unsecured register range array
* @user_regs_range_array_size: unsecured register range array size
*
*/
int hl_init_pb_ranges(struct hl_device *hdev, u32 num_dcores,
u32 dcore_offset, u32 num_instances, u32 instance_offset,
const u32 pb_blocks[], u32 blocks_array_size,
const struct range *regs_range_array, u32 regs_range_array_size)
const struct range *user_regs_range_array,
u32 user_regs_range_array_size)
{
return hl_init_pb_ranges_with_mask(hdev, num_dcores, dcore_offset,
num_instances, instance_offset, pb_blocks,
blocks_array_size, regs_range_array,
regs_range_array_size, ULLONG_MAX);
blocks_array_size, user_regs_range_array,
user_regs_range_array_size, ULLONG_MAX);
}
/**
@ -447,14 +448,14 @@ int hl_init_pb_ranges(struct hl_device *hdev, u32 num_dcores,
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_array: register array
* @regs_array_size: register array size
* @user_regs_array: unsecured register array
* @user_regs_array_size: unsecured register array size
*
*/
int hl_init_pb_single_dcore(struct hl_device *hdev, u32 dcore_offset,
u32 num_instances, u32 instance_offset,
const u32 pb_blocks[], u32 blocks_array_size,
const u32 *regs_array, u32 regs_array_size)
const u32 *user_regs_array, u32 user_regs_array_size)
{
int i, rc = 0;
struct hl_block_glbl_sec *glbl_sec;
@ -466,8 +467,8 @@ int hl_init_pb_single_dcore(struct hl_device *hdev, u32 dcore_offset,
return -ENOMEM;
hl_secure_block(hdev, glbl_sec, blocks_array_size);
rc = hl_unsecure_registers(hdev, regs_array, regs_array_size, 0,
pb_blocks, glbl_sec, blocks_array_size);
rc = hl_unsecure_registers(hdev, user_regs_array, user_regs_array_size,
0, pb_blocks, glbl_sec, blocks_array_size);
if (rc)
goto free_glbl_sec;
@ -495,8 +496,8 @@ free_glbl_sec:
* @instance_offset: offset between instances
* @pb_blocks: blocks array
* @blocks_array_size: blocks array size
* @regs_range_array: register range array
* @regs_range_array_size: register range array size
* @user_regs_range_array: unsecured register range array
* @user_regs_range_array_size: unsecured register range array size
*
*/
int hl_init_pb_ranges_single_dcore(struct hl_device *hdev, u32 dcore_offset,

13
drivers/accel/habanalabs/gaudi/gaudi.c
View File

@ -114,13 +114,6 @@ static u32 gaudi_stream_master[GAUDI_STREAM_MASTER_ARR_SIZE] = {
GAUDI_QUEUE_ID_DMA_1_3
};
static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
"gaudi cq 5_0", "gaudi cq 5_1", "gaudi cq 5_2", "gaudi cq 5_3",
"gaudi cpu eq"
};
static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = {
[GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0,
[GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1,
@ -1476,8 +1469,7 @@ static int gaudi_collective_wait_create_job(struct hl_device *hdev,
}
/* Allocate internal mapped CB for non patched CBs */
cb = hl_cb_kernel_create(hdev, cb_size,
hdev->mmu_enable && !patched_cb);
cb = hl_cb_kernel_create(hdev, cb_size, !patched_cb);
if (!cb) {
atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
atomic64_inc(&cntr->out_of_mem_drop_cnt);
@ -3651,9 +3643,6 @@ static int gaudi_mmu_init(struct hl_device *hdev)
u64 hop0_addr;
int rc, i;
if (!hdev->mmu_enable)
return 0;
if (gaudi->hw_cap_initialized & HW_CAP_MMU)
return 0;

334
drivers/accel/habanalabs/gaudi2/gaudi2.c
View File

@ -57,13 +57,13 @@
#define GAUDI2_NA_EVENT_CAUSE 0xFF
#define GAUDI2_NUM_OF_QM_ERR_CAUSE 18
#define GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE 25
#define GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE 25
#define GAUDI2_NUM_OF_QM_ARB_ERR_CAUSE 3
#define GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE 14
#define GAUDI2_NUM_OF_CPU_SEI_ERR_CAUSE 3
#define GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE 2
#define GAUDI2_NUM_OF_ROT_ERR_CAUSE 22
#define GAUDI2_NUM_OF_TPC_INTR_CAUSE 30
#define GAUDI2_NUM_OF_TPC_INTR_CAUSE 31
#define GAUDI2_NUM_OF_DEC_ERR_CAUSE 25
#define GAUDI2_NUM_OF_MME_ERR_CAUSE 16
#define GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE 5
@ -162,6 +162,9 @@
#define PSOC_RAZWI_ENG_STR_SIZE 128
#define PSOC_RAZWI_MAX_ENG_PER_RTR 5
/* HW scrambles only bits 0-25 */
#define HW_UNSCRAMBLED_BITS_MASK GENMASK_ULL(63, 26)
struct gaudi2_razwi_info {
u32 axuser_xy;
u32 rtr_ctrl;
@ -801,7 +804,7 @@ static const char * const gaudi2_qman_error_cause[GAUDI2_NUM_OF_QM_ERR_CAUSE] =
"PQC L2H error"
};
static const char * const gaudi2_qman_lower_cp_error_cause[GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE] = {
static const char * const gaudi2_lower_qman_error_cause[GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE] = {
"RSVD0",
"CQ AXI HBW error",
"CP AXI HBW error",
@ -891,6 +894,7 @@ static const char * const gaudi2_tpc_interrupts_cause[GAUDI2_NUM_OF_TPC_INTR_CAU
"invalid_lock_access",
"LD_L protection violation",
"ST_L protection violation",
"D$ L0CS mismatch",
};
static const char * const guadi2_mme_error_cause[GAUDI2_NUM_OF_MME_ERR_CAUSE] = {
@ -3615,6 +3619,12 @@ static int gaudi2_sw_init(struct hl_device *hdev)
prop->supports_compute_reset = true;
/* Event queue sanity check added in FW version 1.11 */
if (hl_is_fw_sw_ver_below(hdev, 1, 11))
hdev->event_queue.check_eqe_index = false;
else
hdev->event_queue.check_eqe_index = true;
hdev->asic_funcs->set_pci_memory_regions(hdev);
rc = gaudi2_special_blocks_iterator_config(hdev);
@ -3630,8 +3640,8 @@ static int gaudi2_sw_init(struct hl_device *hdev)
special_blocks_free:
gaudi2_special_blocks_iterator_free(hdev);
free_scratchpad_mem:
hl_asic_dma_pool_free(hdev, gaudi2->scratchpad_kernel_address,
gaudi2->scratchpad_bus_address);
hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
gaudi2->scratchpad_bus_address);
free_virt_msix_db_mem:
hl_cpu_accessible_dma_pool_free(hdev, prop->pmmu.page_size, gaudi2->virt_msix_db_cpu_addr);
free_cpu_accessible_dma_pool:
@ -4526,7 +4536,7 @@ static int gaudi2_set_tpc_engine_mode(struct hl_device *hdev, u32 engine_id, u32
reg_base = gaudi2_tpc_cfg_blocks_bases[tpc_id];
reg_addr = reg_base + TPC_CFG_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_TPC0_CFG_TPC_STALL_V_MASK,
!!(engine_command == HL_ENGINE_STALL));
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
if (engine_command == HL_ENGINE_RESUME) {
@ -4550,7 +4560,7 @@ static int gaudi2_set_mme_engine_mode(struct hl_device *hdev, u32 engine_id, u32
reg_base = gaudi2_mme_ctrl_lo_blocks_bases[mme_id];
reg_addr = reg_base + MME_CTRL_LO_QM_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_MME_CTRL_LO_QM_STALL_V_MASK,
!!(engine_command == HL_ENGINE_STALL));
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
return 0;
@ -4571,7 +4581,7 @@ static int gaudi2_set_edma_engine_mode(struct hl_device *hdev, u32 engine_id, u3
reg_base = gaudi2_dma_core_blocks_bases[edma_id];
reg_addr = reg_base + EDMA_CORE_CFG_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_EDMA0_CORE_CFG_1_HALT_MASK,
!!(engine_command == HL_ENGINE_STALL));
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
if (engine_command == HL_ENGINE_STALL) {
@ -6148,18 +6158,24 @@ static int gaudi2_execute_soft_reset(struct hl_device *hdev, bool driver_perform
u32 poll_timeout_us)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
int rc = 0;
if (!driver_performs_reset) {
/* set SP to indicate reset request sent to FW */
if (dyn_regs->cpu_rst_status)
WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
else
WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
if (hl_is_fw_sw_ver_below(hdev, 1, 10)) {
/* set SP to indicate reset request sent to FW */
if (dyn_regs->cpu_rst_status)
WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
else
WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
return gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
/* wait for f/w response */
rc = gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
} else {
rc = hl_fw_send_soft_reset(hdev);
}
return rc;
}
/* Block access to engines, QMANs and SM during reset, these
@ -7231,7 +7247,7 @@ static bool gaudi2_get_tpc_idle_status(struct hl_device *hdev, u64 *mask_arr, u8
gaudi2_iterate_tpcs(hdev, &tpc_iter);
return tpc_idle_data.is_idle;
return *tpc_idle_data.is_idle;
}
static bool gaudi2_get_decoder_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
@ -7737,137 +7753,28 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
return !!ecc_data->is_critical;
}
/*
* gaudi2_queue_idx_dec - decrement queue index (pi/ci) and handle wrap
*
* @idx: the current pi/ci value
* @q_len: the queue length (power of 2)
*
* @return the cyclically decremented index
*/
static inline u32 gaudi2_queue_idx_dec(u32 idx, u32 q_len)
static void print_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base)
{
u32 mask = q_len - 1;
u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
u64 cq_ptr, arc_cq_ptr, cp_current_inst;
/*
* modular decrement is equivalent to adding (queue_size -1)
* later we take LSBs to make sure the value is in the
* range [0, queue_len - 1]
*/
return (idx + q_len - 1) & mask;
}
lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
cq_ptr = ((u64) hi) << 32 | lo;
cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
/**
* gaudi2_print_sw_config_stream_data - print SW config stream data
*
* @hdev: pointer to the habanalabs device structure
* @stream: the QMAN's stream
* @qman_base: base address of QMAN registers block
*/
static void gaudi2_print_sw_config_stream_data(struct hl_device *hdev,
u32 stream, u64 qman_base)
{
u64 cq_ptr_lo, cq_ptr_hi, cq_tsize, cq_ptr;
u32 cq_ptr_lo_off, size;
lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
arc_cq_ptr = ((u64) hi) << 32 | lo;
arc_cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
cq_ptr_lo_off = mmDCORE0_TPC0_QM_CQ_PTR_LO_1 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0;
lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
hi = RREG32(qman_base + QM_CP_CURRENT_INST_HI_4_OFFSET);
cp_current_inst = ((u64) hi) << 32 | lo;
cq_ptr_lo = qman_base + (mmDCORE0_TPC0_QM_CQ_PTR_LO_0 - mmDCORE0_TPC0_QM_BASE) +
stream * cq_ptr_lo_off;
cq_ptr_hi = cq_ptr_lo + (mmDCORE0_TPC0_QM_CQ_PTR_HI_0 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0);
cq_tsize = cq_ptr_lo + (mmDCORE0_TPC0_QM_CQ_TSIZE_0 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0);
cq_ptr = (((u64) RREG32(cq_ptr_hi)) << 32) | RREG32(cq_ptr_lo);
size = RREG32(cq_tsize);
dev_info(hdev->dev, "stop on err: stream: %u, addr: %#llx, size: %x\n",
stream, cq_ptr, size);
}
/**
* gaudi2_print_last_pqes_on_err - print last PQEs on error
*
* @hdev: pointer to the habanalabs device structure
* @qid_base: first QID of the QMAN (out of 4 streams)
* @stream: the QMAN's stream
* @qman_base: base address of QMAN registers block
* @pr_sw_conf: if true print the SW config stream data (CQ PTR and SIZE)
*/
static void gaudi2_print_last_pqes_on_err(struct hl_device *hdev, u32 qid_base, u32 stream,
u64 qman_base, bool pr_sw_conf)
{
u32 ci, qm_ci_stream_off;
struct hl_hw_queue *q;
u64 pq_ci;
int i;
q = &hdev->kernel_queues[qid_base + stream];
qm_ci_stream_off = mmDCORE0_TPC0_QM_PQ_CI_1 - mmDCORE0_TPC0_QM_PQ_CI_0;
pq_ci = qman_base + (mmDCORE0_TPC0_QM_PQ_CI_0 - mmDCORE0_TPC0_QM_BASE) +
stream * qm_ci_stream_off;
hdev->asic_funcs->hw_queues_lock(hdev);
if (pr_sw_conf)
gaudi2_print_sw_config_stream_data(hdev, stream, qman_base);
ci = RREG32(pq_ci);
/* we should start printing form ci -1 */
ci = gaudi2_queue_idx_dec(ci, HL_QUEUE_LENGTH);
for (i = 0; i < PQ_FETCHER_CACHE_SIZE; i++) {
struct hl_bd *bd;
u64 addr;
u32 len;
bd = q->kernel_address;
bd += ci;
len = le32_to_cpu(bd->len);
/* len 0 means uninitialized entry- break */
if (!len)
break;
addr = le64_to_cpu(bd->ptr);
dev_info(hdev->dev, "stop on err PQE(stream %u): ci: %u, addr: %#llx, size: %x\n",
stream, ci, addr, len);
/* get previous ci, wrap if needed */
ci = gaudi2_queue_idx_dec(ci, HL_QUEUE_LENGTH);
}
hdev->asic_funcs->hw_queues_unlock(hdev);
}
/**
* print_qman_data_on_err - extract QMAN data on error
*
* @hdev: pointer to the habanalabs device structure
* @qid_base: first QID of the QMAN (out of 4 streams)
* @stream: the QMAN's stream
* @qman_base: base address of QMAN registers block
*
* This function attempt to extract as much data as possible on QMAN error.
* On upper CP print the SW config stream data and last 8 PQEs.
* On lower CP print SW config data and last PQEs of ALL 4 upper CPs
*/
static void print_qman_data_on_err(struct hl_device *hdev, u32 qid_base, u32 stream, u64 qman_base)
{
u32 i;
if (stream != QMAN_STREAMS) {
gaudi2_print_last_pqes_on_err(hdev, qid_base, stream, qman_base, true);
return;
}
gaudi2_print_sw_config_stream_data(hdev, stream, qman_base);
for (i = 0 ; i < QMAN_STREAMS ; i++)
gaudi2_print_last_pqes_on_err(hdev, qid_base, i, qman_base, false);
dev_info(hdev->dev,
"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
}
static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type,
@ -7888,8 +7795,8 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
continue;
if (i == QMAN_STREAMS) {
snprintf(reg_desc, ARRAY_SIZE(reg_desc), "LowerCP");
num_error_causes = GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE;
snprintf(reg_desc, ARRAY_SIZE(reg_desc), "LowerQM");
num_error_causes = GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE;
} else {
snprintf(reg_desc, ARRAY_SIZE(reg_desc), "stream%u", i);
num_error_causes = GAUDI2_NUM_OF_QM_ERR_CAUSE;
@ -7900,12 +7807,13 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
gaudi2_print_event(hdev, event_type, true,
"%s. err cause: %s", reg_desc,
i == QMAN_STREAMS ?
gaudi2_qman_lower_cp_error_cause[j] :
gaudi2_lower_qman_error_cause[j] :
gaudi2_qman_error_cause[j]);
error_count++;
}
print_qman_data_on_err(hdev, qid_base, i, qman_base);
if (i == QMAN_STREAMS)
print_lower_qman_data_on_err(hdev, qman_base);
}
arb_err_val = RREG32(arb_err_addr);
@ -8033,7 +7941,7 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
u8 module_sub_idx, u64 *event_mask)
{
bool via_sft = false;
u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id;
u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id, binned_idx;
u64 hbw_rtr_mstr_if_base_addr, lbw_rtr_mstr_if_base_addr;
u32 hbw_shrd_aw = 0, hbw_shrd_ar = 0;
u32 lbw_shrd_aw = 0, lbw_shrd_ar = 0;
@ -8041,15 +7949,21 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
switch (module) {
case RAZWI_TPC:
sprintf(initiator_name, "TPC_%u", module_idx);
if (hdev->tpc_binning) {
binned_idx = __ffs(hdev->tpc_binning);
if (binned_idx == module_idx)
module_idx = TPC_ID_DCORE0_TPC6;
}
hbw_rtr_id = gaudi2_tpc_initiator_hbw_rtr_id[module_idx];
if (hl_is_fw_ver_below_1_9(hdev) &&
if (hl_is_fw_sw_ver_below(hdev, 1, 9) &&
!hdev->asic_prop.fw_security_enabled &&
((module_idx == 0) || (module_idx == 1)))
lbw_rtr_id = DCORE0_RTR0;
else
lbw_rtr_id = gaudi2_tpc_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "TPC_%u", module_idx);
break;
case RAZWI_MME:
sprintf(initiator_name, "MME_%u", module_idx);
@ -8108,9 +8022,14 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
sprintf(initiator_name, "NIC_%u", module_idx);
break;
case RAZWI_DEC:
sprintf(initiator_name, "DEC_%u", module_idx);
if (hdev->decoder_binning) {
binned_idx = __ffs(hdev->decoder_binning);
if (binned_idx == module_idx)
module_idx = DEC_ID_PCIE_VDEC1;
}
hbw_rtr_id = gaudi2_dec_initiator_hbw_rtr_id[module_idx];
lbw_rtr_id = gaudi2_dec_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "DEC_%u", module_idx);
break;
case RAZWI_ROT:
hbw_rtr_id = gaudi2_rot_initiator_hbw_rtr_id[module_idx];
@ -8251,6 +8170,7 @@ static bool gaudi2_handle_psoc_razwi_happened(struct hl_device *hdev, u32 razwi_
u16 num_of_eng, eng_id[PSOC_RAZWI_MAX_ENG_PER_RTR];
char eng_name_str[PSOC_RAZWI_ENG_STR_SIZE];
bool razwi_happened = false;
u64 addr;
int i;
num_of_eng = gaudi2_psoc_razwi_get_engines(common_razwi_info, ARRAY_SIZE(common_razwi_info),
@ -8269,43 +8189,53 @@ static bool gaudi2_handle_psoc_razwi_happened(struct hl_device *hdev, u32 razwi_
if (RREG32(base[i] + DEC_RAZWI_HBW_AW_SET)) {
addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_HI);
addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_LO);
dev_err(hdev->dev,
addr = ((u64)addr_hi << 32) + addr_lo;
if (addr) {
dev_err(hdev->dev,
"PSOC HBW AW RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
eng_name_str, ((u64)addr_hi << 32) + addr_lo);
hl_handle_razwi(hdev, ((u64)addr_hi << 32) + addr_lo, &eng_id[0],
eng_name_str, addr);
hl_handle_razwi(hdev, addr, &eng_id[0],
num_of_eng, HL_RAZWI_HBW | HL_RAZWI_WRITE, event_mask);
razwi_happened = true;
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_HBW_AR_SET)) {
addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_HI);
addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_LO);
dev_err(hdev->dev,
addr = ((u64)addr_hi << 32) + addr_lo;
if (addr) {
dev_err(hdev->dev,
"PSOC HBW AR RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
eng_name_str, ((u64)addr_hi << 32) + addr_lo);
hl_handle_razwi(hdev, ((u64)addr_hi << 32) + addr_lo, &eng_id[0],
eng_name_str, addr);
hl_handle_razwi(hdev, addr, &eng_id[0],
num_of_eng, HL_RAZWI_HBW | HL_RAZWI_READ, event_mask);
razwi_happened = true;
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_LBW_AW_SET)) {
addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AW_ADDR);
dev_err(hdev->dev,
if (addr_lo) {
dev_err(hdev->dev,
"PSOC LBW AW RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
eng_name_str, addr_lo);
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
num_of_eng, HL_RAZWI_LBW | HL_RAZWI_WRITE, event_mask);
razwi_happened = true;
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_LBW_AR_SET)) {
addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AR_ADDR);
dev_err(hdev->dev,
"PSOC LBW AR RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
eng_name_str, addr_lo);
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
if (addr_lo) {
dev_err(hdev->dev,
"PSOC LBW AR RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
eng_name_str, addr_lo);
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
num_of_eng, HL_RAZWI_LBW | HL_RAZWI_READ, event_mask);
razwi_happened = true;
razwi_happened = true;
}
}
/* In common case the loop will break, when there is only one engine id, or
* several engines with the same router. The exceptional case is with psoc razwi
@ -8789,13 +8719,13 @@ static int gaudi2_handle_kdma_core_event(struct hl_device *hdev, u16 event_type,
return error_count;
}
static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type, int sts_addr)
static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type, u64 intr_cause)
{
u32 error_count = 0, sts_val = RREG32(sts_addr);
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE ; i++)
if (sts_val & BIT(i)) {
if (intr_cause & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_dma_core_interrupts_cause[i]);
error_count++;
@ -8806,27 +8736,6 @@ static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type,
return error_count;
}
static int gaudi2_handle_pdma_core_event(struct hl_device *hdev, u16 event_type, int pdma_idx)
{
u32 sts_addr;
sts_addr = mmPDMA0_CORE_ERR_CAUSE + pdma_idx * PDMA_OFFSET;
return gaudi2_handle_dma_core_event(hdev, event_type, sts_addr);
}
static int gaudi2_handle_edma_core_event(struct hl_device *hdev, u16 event_type, int edma_idx)
{
static const int edma_event_index_map[] = {2, 3, 0, 1, 6, 7, 4, 5};
u32 sts_addr, index;
index = edma_event_index_map[edma_idx];
sts_addr = mmDCORE0_EDMA0_CORE_ERR_CAUSE +
DCORE_OFFSET * (index / NUM_OF_EDMA_PER_DCORE) +
DCORE_EDMA_OFFSET * (index % NUM_OF_EDMA_PER_DCORE);
return gaudi2_handle_dma_core_event(hdev, event_type, sts_addr);
}
static void gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(struct hl_device *hdev, u64 *event_mask)
{
u32 mstr_if_base_addr = mmPCIE_MSTR_RR_MSTR_IF_RR_SHRD_HBW_BASE, razwi_happened_addr;
@ -8866,6 +8775,9 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
u32 error_count = 0;
int i;
gaudi2_print_event(hdev, event_type, true,
"intr_cause_data: %#llx", intr_cause_data);
for (i = 0 ; i < GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE ; i++) {
if (!(intr_cause_data & BIT_ULL(i)))
continue;
@ -8874,16 +8786,15 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
"err cause: %s", gaudi2_pcie_addr_dec_error_cause[i]);
error_count++;
switch (intr_cause_data & BIT_ULL(i)) {
case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_AXI_LBW_ERR_INTR_MASK:
hl_check_for_glbl_errors(hdev);
break;
case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_BAD_ACCESS_INTR_MASK:
gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
break;
}
/*
* Always check for LBW and HBW additional info as the indication itself is
* sometimes missing
*/
}
hl_check_for_glbl_errors(hdev);
gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
return error_count;
}
@ -8937,11 +8848,16 @@ static void gaudi2_handle_page_error(struct hl_device *hdev, u64 mmu_base, bool
addr <<= 32;
addr |= RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE_VA));
if (!is_pmmu)
addr = gaudi2_mmu_descramble_addr(hdev, addr);
if (is_pmmu) {
dev_err_ratelimited(hdev->dev, "PMMU page fault on va 0x%llx\n", addr);
} else {
addr = gaudi2_mmu_descramble_addr(hdev, addr);
addr &= HW_UNSCRAMBLED_BITS_MASK;
dev_err_ratelimited(hdev->dev, "HMMU page fault on va range 0x%llx - 0x%llx\n",
addr, addr + ~HW_UNSCRAMBLED_BITS_MASK);
}
dev_err_ratelimited(hdev->dev, "%s page fault on va 0x%llx\n",
is_pmmu ? "PMMU" : "HMMU", addr);
hl_handle_page_fault(hdev, addr, 0, is_pmmu, event_mask);
WREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID), 0);
@ -9709,19 +9625,19 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
case GAUDI2_EVENT_KDMA_CH0_AXI_ERR_RSP:
case GAUDI2_EVENT_KDMA0_CORE:
error_count = gaudi2_handle_kdma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_HDMA2_CORE ... GAUDI2_EVENT_HDMA5_CORE:
index = event_type - GAUDI2_EVENT_HDMA2_CORE;
error_count = gaudi2_handle_edma_core_event(hdev, event_type, index);
error_count = gaudi2_handle_dma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_PDMA0_CORE ... GAUDI2_EVENT_PDMA1_CORE:
index = event_type - GAUDI2_EVENT_PDMA0_CORE;
error_count = gaudi2_handle_pdma_core_event(hdev, event_type, index);
error_count = gaudi2_handle_dma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;

2
drivers/accel/habanalabs/gaudi2/gaudi2P.h
View File

@ -98,7 +98,7 @@
#define GAUDI2_DEFAULT_CARD_NAME "HL225"
#define QMAN_STREAMS 4
#define PQ_FETCHER_CACHE_SIZE 8
#define NUM_OF_MME_SBTE_PORTS 5
#define NUM_OF_MME_WB_PORTS 2

15
drivers/accel/habanalabs/gaudi2/gaudi2_security.c
View File

@ -479,6 +479,7 @@ static const u32 gaudi2_pb_dcr0_edma0_unsecured_regs[] = {
mmDCORE0_EDMA0_CORE_CTX_TE_NUMROWS,
mmDCORE0_EDMA0_CORE_CTX_IDX,
mmDCORE0_EDMA0_CORE_CTX_IDX_INC,
mmDCORE0_EDMA0_CORE_RD_LBW_RATE_LIM_CFG,
mmDCORE0_EDMA0_QM_CQ_CFG0_0,
mmDCORE0_EDMA0_QM_CQ_CFG0_1,
mmDCORE0_EDMA0_QM_CQ_CFG0_2,
@ -1533,6 +1534,10 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = {
mmDCORE0_TPC0_CFG_QM_KERNEL_CONFIG,
mmDCORE0_TPC0_CFG_QM_KERNEL_ID,
mmDCORE0_TPC0_CFG_QM_POWER_LOOP,
mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_0,
mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_1,
mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_2,
mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_3,
mmDCORE0_TPC0_CFG_LUT_FUNC32_BASE2_ADDR_LO,
mmDCORE0_TPC0_CFG_LUT_FUNC32_BASE2_ADDR_HI,
mmDCORE0_TPC0_CFG_LUT_FUNC64_BASE2_ADDR_LO,
@ -1541,6 +1546,7 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = {
mmDCORE0_TPC0_CFG_LUT_FUNC128_BASE2_ADDR_HI,
mmDCORE0_TPC0_CFG_LUT_FUNC256_BASE2_ADDR_LO,
mmDCORE0_TPC0_CFG_LUT_FUNC256_BASE2_ADDR_HI,
mmDCORE0_TPC0_CFG_FP8_143_BIAS,
mmDCORE0_TPC0_CFG_ROUND_CSR,
mmDCORE0_TPC0_CFG_CONV_ROUND_CSR,
mmDCORE0_TPC0_CFG_SEMAPHORE,
@ -3442,15 +3448,6 @@ static int gaudi2_init_protection_bits(struct hl_device *hdev)
ARRAY_SIZE(gaudi2_pb_thermal_sensor0), NULL, HL_PB_NA);
}
/* HBM */
/* Temporarily skip until SW-63348 is solved
* instance_offset = mmHBM1_MC0_BASE - mmHBM0_MC0_BASE;
* rc |= hl_init_pb_with_mask(hdev, HL_PB_SHARED, HL_PB_NA, GAUDI2_HBM_NUM,
* instance_offset, gaudi2_pb_hbm,
* ARRAY_SIZE(gaudi2_pb_hbm), NULL, HL_PB_NA,
* prop->dram_enabled_mask);
*/
/* Scheduler ARCs */
instance_offset = mmARC_FARM_ARC1_AUX_BASE - mmARC_FARM_ARC0_AUX_BASE;
rc |= hl_init_pb_ranges(hdev, HL_PB_SHARED, HL_PB_NA,

3
drivers/accel/habanalabs/goya/goya.c
View File

@ -2671,9 +2671,6 @@ int goya_mmu_init(struct hl_device *hdev)
u64 hop0_addr;
int rc, i;
if (!hdev->mmu_enable)
return 0;
if (goya->hw_cap_initialized & HW_CAP_MMU)
return 0;

9
drivers/accel/habanalabs/goya/goya_coresight.c
View File

@ -371,13 +371,8 @@ static int goya_etr_validate_address(struct hl_device *hdev, u64 addr,
return false;
}
if (hdev->mmu_enable) {
range_start = prop->dmmu.start_addr;
range_end = prop->dmmu.end_addr;
} else {
range_start = prop->dram_user_base_address;
range_end = prop->dram_end_address;
}
range_start = prop->dmmu.start_addr;
range_end = prop->dmmu.end_addr;
return hl_mem_area_inside_range(addr, size, range_start, range_end);
}

22
drivers/accel/habanalabs/include/common/cpucp_if.h
View File

@ -359,7 +359,7 @@ struct hl_eq_entry {
union {
__le64 data_placeholder;
struct hl_eq_ecc_data ecc_data;
struct hl_eq_hbm_ecc_data hbm_ecc_data; /* Gaudi1 HBM */
struct hl_eq_hbm_ecc_data hbm_ecc_data; /* Obsolete */
struct hl_eq_sm_sei_data sm_sei_data;
struct cpucp_pkt_sync_err pkt_sync_err;
struct hl_eq_fw_alive fw_alive;
@ -653,7 +653,7 @@ enum pq_init_status {
* which address is passed via the CpuCp packet. In addition, the host's driver
* passes the max size it allows the CpuCP to write to the structure, to prevent
* data corruption in case of mismatched driver/FW versions.
* Relevant only to Gaudi.
* Obsolete.
*
* CPUCP_PACKET_GENERIC_PASSTHROUGH -
* Generic opcode for all firmware info that is only passed to host
@ -665,6 +665,9 @@ enum pq_init_status {
*
* CPUCP_PACKET_REGISTER_INTERRUPTS -
* Packet to register interrupts indicating LKD is ready to receive events from FW.
*
* CPUCP_PACKET_SOFT_RESET -
* Packet to perform soft-reset.
*/
enum cpucp_packet_id {
@ -731,6 +734,7 @@ enum cpucp_packet_id {
CPUCP_PACKET_RESERVED11, /* not used */
CPUCP_PACKET_RESERVED12, /* internal */
CPUCP_PACKET_REGISTER_INTERRUPTS, /* internal */
CPUCP_PACKET_SOFT_RESET, /* internal */
CPUCP_PACKET_ID_MAX /* must be last */
};
@ -864,19 +868,19 @@ struct cpucp_array_data_packet {
enum cpucp_led_index {
CPUCP_LED0_INDEX = 0,
CPUCP_LED1_INDEX,
CPUCP_LED2_INDEX
CPUCP_LED2_INDEX,
CPUCP_LED_MAX_INDEX = CPUCP_LED2_INDEX
};
/*
* enum cpucp_packet_rc - Error return code
* @cpucp_packet_success -> in case of success.
* @cpucp_packet_invalid -> this is to support Goya and Gaudi platform.
* @cpucp_packet_invalid -> this is to support first generation platforms.
* @cpucp_packet_fault -> in case of processing error like failing to
* get device binding or semaphore etc.
* @cpucp_packet_invalid_pkt -> when cpucp packet is un-supported. This is
* supported Greco onwards.
* @cpucp_packet_invalid_pkt -> when cpucp packet is un-supported.
* @cpucp_packet_invalid_params -> when checking parameter like length of buffer
* or attribute value etc. Supported Greco onwards.
* or attribute value etc.
* @cpucp_packet_rc_max -> It indicates size of enum so should be at last.
*/
enum cpucp_packet_rc {
@ -1361,7 +1365,7 @@ struct cpucp_dev_info_signed {
#define DCORE_MON_REGS_SZ 512
/*
* struct dcore_monitor_regs_data - DCORE monitor regs data.
* the structure follows sync manager block layout. relevant only to Gaudi.
* the structure follows sync manager block layout. Obsolete.
* @mon_pay_addrl: array of payload address low bits.
* @mon_pay_addrh: array of payload address high bits.
* @mon_pay_data: array of payload data.
@ -1376,7 +1380,7 @@ struct dcore_monitor_regs_data {
__le32 mon_status[DCORE_MON_REGS_SZ];
};
/* contains SM data for each SYNC_MNGR (relevant only to Gaudi) */
/* contains SM data for each SYNC_MNGR (Obsolete) */
struct cpucp_monitor_dump {
struct dcore_monitor_regs_data sync_mngr_w_s;
struct dcore_monitor_regs_data sync_mngr_e_s;

41
drivers/accel/habanalabs/include/common/hl_boot_if.h
View File

@ -35,6 +35,7 @@ enum cpu_boot_err {
CPU_BOOT_ERR_TPM_FAIL = 20,
CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
CPU_BOOT_ERR_EEPROM_FAIL = 22,
CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL = 23,
CPU_BOOT_ERR_ENABLED = 31,
CPU_BOOT_ERR_SCND_EN = 63,
CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
@ -51,6 +52,7 @@ enum cpu_boot_err {
(1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL) | \
(1 << CPU_BOOT_ERR_BINNING_FAIL) | \
(1 << CPU_BOOT_ERR_DRAM_SKIPPED) | \
(1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) | \
(1 << CPU_BOOT_ERR_EEPROM_FAIL))
/*
@ -132,6 +134,9 @@ enum cpu_boot_err {
* CPU_BOOT_ERR_EEPROM_FAIL Failed reading EEPROM data. Defaults
* are used.
*
* CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL Failed scrubbing the Engines/ARCFarm
* memories. Boot disabled until reset.
*
* CPU_BOOT_ERR0_ENABLED Error registers enabled.
* This is a main indication that the
* running FW populates the error
@ -157,6 +162,7 @@ enum cpu_boot_err {
#define CPU_BOOT_ERR0_TPM_FAIL (1 << CPU_BOOT_ERR_TPM_FAIL)
#define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL (1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
#define CPU_BOOT_ERR0_EEPROM_FAIL (1 << CPU_BOOT_ERR_EEPROM_FAIL)
#define CPU_BOOT_ERR0_ENG_ARC_MEM_SCRUB_FAIL (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
#define CPU_BOOT_ERR0_ENABLED (1 << CPU_BOOT_ERR_ENABLED)
#define CPU_BOOT_ERR1_ENABLED (1 << CPU_BOOT_ERR_ENABLED)
@ -744,36 +750,6 @@ struct comms_status {
};
};
/**
* HL_MODULES_MAX_NUM is determined by the size of modules_mask in struct
* hl_component_versions
*/
enum hl_modules {
HL_MODULES_BOOT_INFO = 0,
HL_MODULES_EEPROM,
HL_MODULES_FDT,
HL_MODULES_I2C,
HL_MODULES_LZ4,
HL_MODULES_MBEDTLS,
HL_MODULES_MAX_NUM = 16
};
/**
* HL_COMPONENTS_MAX_NUM is determined by the size of components_mask in
* struct cpucp_versions
*/
enum hl_components {
HL_COMPONENTS_PID = 0,
HL_COMPONENTS_MGMT,
HL_COMPONENTS_PREBOOT,
HL_COMPONENTS_PPBOOT,
HL_COMPONENTS_ARMCP,
HL_COMPONENTS_CPLD,
HL_COMPONENTS_UBOOT,
HL_COMPONENTS_FUSE,
HL_COMPONENTS_MAX_NUM = 16
};
#define NAME_MAX_LEN 32 /* bytes */
struct hl_module_data {
__u8 name[NAME_MAX_LEN];
@ -787,8 +763,6 @@ struct hl_module_data {
* @component: version of the component itself.
* @fw_os: Firmware OS Version.
* @comp_name: Name of the component.
* @modules_mask: i'th bit (from LSB) is a flag - on if module i in enum
* hl_modules is used.
* @modules_counter: number of set bits in modules_mask.
* @reserved: reserved for future use.
* @modules: versions of the component's modules. Elborated explanation in
@ -800,9 +774,8 @@ struct hl_component_versions {
__u8 component[VERSION_MAX_LEN];
__u8 fw_os[VERSION_MAX_LEN];
__u8 comp_name[NAME_MAX_LEN];
__le16 modules_mask;
__u8 modules_counter;
__u8 reserved[1];
__u8 reserved[3];
struct hl_module_data modules[];
};

11
drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
View File

@ -242,6 +242,17 @@
#define QM_FENCE2_OFFSET (mmPDMA0_QM_CP_FENCE2_RDATA_0 - mmPDMA0_QM_BASE)
#define QM_SEI_STATUS_OFFSET (mmPDMA0_QM_SEI_STATUS - mmPDMA0_QM_BASE)
#define QM_CQ_PTR_LO_4_OFFSET (mmPDMA0_QM_CQ_PTR_LO_4 - mmPDMA0_QM_BASE)
#define QM_CQ_PTR_HI_4_OFFSET (mmPDMA0_QM_CQ_PTR_HI_4 - mmPDMA0_QM_BASE)
#define QM_CQ_TSIZE_4_OFFSET (mmPDMA0_QM_CQ_TSIZE_4 - mmPDMA0_QM_BASE)
#define QM_ARC_CQ_PTR_LO_OFFSET (mmPDMA0_QM_ARC_CQ_PTR_LO - mmPDMA0_QM_BASE)
#define QM_ARC_CQ_PTR_HI_OFFSET (mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
#define QM_ARC_CQ_TSIZE_OFFSET (mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
#define QM_CP_CURRENT_INST_LO_4_OFFSET (mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)
#define QM_CP_CURRENT_INST_HI_4_OFFSET (mmPDMA0_QM_CP_CURRENT_INST_HI_4 - mmPDMA0_QM_BASE)
#define SFT_OFFSET (mmSFT1_HBW_RTR_IF0_RTR_H3_BASE - mmSFT0_HBW_RTR_IF0_RTR_H3_BASE)
#define SFT_IF_RTR_OFFSET (mmSFT0_HBW_RTR_IF1_RTR_H3_BASE - mmSFT0_HBW_RTR_IF0_RTR_H3_BASE)

2
drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
View File

@ -62,7 +62,7 @@ struct gaudi2_cold_rst_data {
u32 fake_security_enable : 1;
u32 fake_sig_validation_en : 1;
u32 bist_skip_enable : 1;
u32 bist_need_iatu_config : 1;
u32 reserved1 : 1;
u32 fake_bis_compliant : 1;
u32 wd_rst_cause_arm : 1;
u32 wd_rst_cause_arcpid : 1;

2
drivers/auxdisplay/cfag12864bfb.c
View File

@ -72,7 +72,7 @@ static int cfag12864bfb_probe(struct platform_device *device)
if (!info)
goto none;
info->screen_base = (char __iomem *) cfag12864b_buffer;
info->screen_buffer = cfag12864b_buffer;
info->screen_size = CFAG12864B_SIZE;
info->fbops = &cfag12864bfb_ops;
info->fix = cfag12864bfb_fix;

2
drivers/auxdisplay/ht16k33.c
View File

@ -640,7 +640,7 @@ static int ht16k33_fbdev_probe(struct device *dev, struct ht16k33_priv *priv,
INIT_DELAYED_WORK(&priv->work, ht16k33_fb_update);
fbdev->info->fbops = &ht16k33_fb_ops;
fbdev->info->screen_base = (char __iomem *) fbdev->buffer;
fbdev->info->screen_buffer = fbdev->buffer;
fbdev->info->screen_size = HT16K33_FB_SIZE;
fbdev->info->fix = ht16k33_fb_fix;
fbdev->info->var = ht16k33_fb_var;

2
drivers/dma-buf/dma-resv.c
View File

@ -660,7 +660,7 @@ EXPORT_SYMBOL_GPL(dma_resv_get_singleton);
* dma_resv_lock() already
* RETURNS
* Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or
* greater than zer on success.
* greater than zero on success.
*/
long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
bool intr, unsigned long timeout)

2
drivers/dma-buf/sw_sync.c
View File

@ -85,7 +85,7 @@ static struct sync_timeline *sync_timeline_create(const char *name)
kref_init(&obj->kref);
obj->context = dma_fence_context_alloc(1);
strlcpy(obj->name, name, sizeof(obj->name));
strscpy(obj->name, name, sizeof(obj->name));
obj->pt_tree = RB_ROOT;
INIT_LIST_HEAD(&obj->pt_list);

2
drivers/firmware/sysfb.c
View File

@ -128,4 +128,4 @@ unlock_mutex:
}
/* must execute after PCI subsystem for EFI quirks */
device_initcall(sysfb_init);
subsys_initcall_sync(sysfb_init);

14
drivers/gpu/drm/Kconfig
View File

@ -95,6 +95,7 @@ config DRM_KUNIT_TEST
config DRM_KMS_HELPER
tristate
depends on DRM
select FB_SYS_HELPERS_DEFERRED if DRM_FBDEV_EMULATION
help
CRTC helpers for KMS drivers.
@ -132,14 +133,6 @@ config DRM_FBDEV_EMULATION
bool "Enable legacy fbdev support for your modesetting driver"
depends on DRM_KMS_HELPER
depends on FB=y || FB=DRM_KMS_HELPER
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
select FB_DEFERRED_IO
select FB_SYS_FOPS
select FB_SYS_FILLRECT
select FB_SYS_COPYAREA
select FB_SYS_IMAGEBLIT
select FRAMEBUFFER_CONSOLE if !EXPERT
select FRAMEBUFFER_CONSOLE_DETECT_PRIMARY if FRAMEBUFFER_CONSOLE
default y
@ -223,6 +216,7 @@ config DRM_TTM_HELPER
config DRM_GEM_DMA_HELPER
tristate
depends on DRM
select FB_SYS_HELPERS if DRM_FBDEV_EMULATION
help
Choose this if you need the GEM DMA helper functions
@ -295,9 +289,7 @@ source "drivers/gpu/drm/armada/Kconfig"
source "drivers/gpu/drm/atmel-hlcdc/Kconfig"
source "drivers/gpu/drm/rcar-du/Kconfig"
source "drivers/gpu/drm/shmobile/Kconfig"
source "drivers/gpu/drm/renesas/Kconfig"
source "drivers/gpu/drm/sun4i/Kconfig"

4
drivers/gpu/drm/Makefile
View File

@ -140,6 +140,7 @@ obj-$(CONFIG_DRM_TTM) += ttm/
obj-$(CONFIG_DRM_SCHED) += scheduler/
obj-$(CONFIG_DRM_RADEON)+= radeon/
obj-$(CONFIG_DRM_AMDGPU)+= amd/amdgpu/
obj-$(CONFIG_DRM_AMDGPU)+= amd/amdxcp/
obj-$(CONFIG_DRM_I915) += i915/
obj-$(CONFIG_DRM_KMB_DISPLAY) += kmb/
obj-$(CONFIG_DRM_MGAG200) += mgag200/
@ -156,8 +157,7 @@ obj-$(CONFIG_DRM_UDL) += udl/
obj-$(CONFIG_DRM_AST) += ast/
obj-$(CONFIG_DRM_ARMADA) += armada/
obj-$(CONFIG_DRM_ATMEL_HLCDC) += atmel-hlcdc/
obj-y += rcar-du/
obj-$(CONFIG_DRM_SHMOBILE) +=shmobile/
obj-y += renesas/
obj-y += omapdrm/
obj-$(CONFIG_DRM_SUN4I) += sun4i/
obj-y += tilcdc/

10
drivers/gpu/drm/amd/amdgpu/Kconfig
View File

@ -69,6 +69,16 @@ config DRM_AMDGPU_USERPTR
This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it
isn't already selected to enabled full userptr support.
config DRM_AMDGPU_WERROR
bool "Force the compiler to throw an error instead of a warning when compiling"
depends on DRM_AMDGPU
depends on EXPERT
depends on !COMPILE_TEST
default n
help
Add -Werror to the build flags for amdgpu.ko.
Only enable this if you are warning code for amdgpu.ko.
source "drivers/gpu/drm/amd/acp/Kconfig"
source "drivers/gpu/drm/amd/display/Kconfig"
source "drivers/gpu/drm/amd/amdkfd/Kconfig"

30
drivers/gpu/drm/amd/amdgpu/Makefile
View File

@ -39,6 +39,26 @@ ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \
-I$(FULL_AMD_DISPLAY_PATH)/amdgpu_dm \
-I$(FULL_AMD_PATH)/amdkfd
subdir-ccflags-y := -Wextra
subdir-ccflags-y += -Wunused
subdir-ccflags-y += -Wmissing-prototypes
subdir-ccflags-y += -Wmissing-declarations
subdir-ccflags-y += -Wmissing-include-dirs
subdir-ccflags-y += -Wold-style-definition
subdir-ccflags-y += -Wmissing-format-attribute
# Need this to avoid recursive variable evaluation issues
cond-flags := $(call cc-option, -Wunused-but-set-variable) \
$(call cc-option, -Wunused-const-variable) \
$(call cc-option, -Wstringop-truncation) \
$(call cc-option, -Wpacked-not-aligned)
subdir-ccflags-y += $(cond-flags)
subdir-ccflags-y += -Wno-unused-parameter
subdir-ccflags-y += -Wno-type-limits
subdir-ccflags-y += -Wno-sign-compare
subdir-ccflags-y += -Wno-missing-field-initializers
subdir-ccflags-y += -Wno-override-init
subdir-ccflags-$(CONFIG_DRM_AMDGPU_WERROR) += -Werror
amdgpu-y := amdgpu_drv.o
# add KMS driver
@ -60,7 +80,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
amdgpu_fw_attestation.o amdgpu_securedisplay.o \
amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o \
amdgpu_ring_mux.o
amdgpu_ring_mux.o amdgpu_xcp.o
amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
@ -78,7 +98,7 @@ amdgpu-y += \
vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \
nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o \
sienna_cichlid.o smu_v13_0_10.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o \
nbio_v7_9.o
nbio_v7_9.o aqua_vanjaram_reg_init.o
# add DF block
amdgpu-y += \
@ -183,12 +203,14 @@ amdgpu-y += \
vcn_v2_5.o \
vcn_v3_0.o \
vcn_v4_0.o \
vcn_v4_0_3.o \
amdgpu_jpeg.o \
jpeg_v1_0.o \
jpeg_v2_0.o \
jpeg_v2_5.o \
jpeg_v3_0.o \
jpeg_v4_0.o
jpeg_v4_0.o \
jpeg_v4_0_3.o
# add ATHUB block
amdgpu-y += \
@ -203,6 +225,7 @@ amdgpu-y += \
smuio_v11_0.o \
smuio_v11_0_6.o \
smuio_v13_0.o \
smuio_v13_0_3.o \
smuio_v13_0_6.o
# add reset block
@ -228,6 +251,7 @@ amdgpu-y += \
amdgpu_amdkfd_gfx_v9.o \
amdgpu_amdkfd_arcturus.o \
amdgpu_amdkfd_aldebaran.o \
amdgpu_amdkfd_gc_9_4_3.o \
amdgpu_amdkfd_gfx_v10.o \
amdgpu_amdkfd_gfx_v10_3.o \
amdgpu_amdkfd_gfx_v11.o

79
drivers/gpu/drm/amd/amdgpu/amdgpu.h
View File

@ -107,8 +107,9 @@
#include "amdgpu_fdinfo.h"
#include "amdgpu_mca.h"
#include "amdgpu_ras.h"
#include "amdgpu_xcp.h"
#define MAX_GPU_INSTANCE 16
#define MAX_GPU_INSTANCE 64
struct amdgpu_gpu_instance
{
@ -212,6 +213,8 @@ extern int amdgpu_noretry;
extern int amdgpu_force_asic_type;
extern int amdgpu_smartshift_bias;
extern int amdgpu_use_xgmi_p2p;
extern int amdgpu_mtype_local;
extern bool enforce_isolation;
#ifdef CONFIG_HSA_AMD
extern int sched_policy;
extern bool debug_evictions;
@ -242,9 +245,10 @@ extern int amdgpu_num_kcq;
extern int amdgpu_vcnfw_log;
extern int amdgpu_sg_display;
extern int amdgpu_user_partt_mode;
#define AMDGPU_VM_MAX_NUM_CTX 4096
#define AMDGPU_SG_THRESHOLD (256*1024*1024)
#define AMDGPU_DEFAULT_GTT_SIZE_MB 3072ULL /* 3GB by default */
#define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000
#define AMDGPU_MAX_USEC_TIMEOUT 100000 /* 100 ms */
#define AMDGPU_FENCE_JIFFIES_TIMEOUT (HZ / 2)
@ -282,6 +286,7 @@ extern int amdgpu_sg_display;
#define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
#define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
struct amdgpu_xcp_mgr;
struct amdgpu_device;
struct amdgpu_irq_src;
struct amdgpu_fpriv;
@ -463,6 +468,8 @@ struct amdgpu_fpriv {
struct mutex bo_list_lock;
struct idr bo_list_handles;
struct amdgpu_ctx_mgr ctx_mgr;
/** GPU partition selection */
uint32_t xcp_id;
};
int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv);
@ -573,6 +580,8 @@ struct amdgpu_asic_funcs {
/* query video codecs */
int (*query_video_codecs)(struct amdgpu_device *adev, bool encode,
const struct amdgpu_video_codecs **codecs);
/* encode "> 32bits" smn addressing */
u64 (*encode_ext_smn_addressing)(int ext_id);
};
/*
@ -607,6 +616,9 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
typedef uint32_t (*amdgpu_rreg_t)(struct amdgpu_device*, uint32_t);
typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
typedef uint32_t (*amdgpu_rreg_ext_t)(struct amdgpu_device*, uint64_t);
typedef void (*amdgpu_wreg_ext_t)(struct amdgpu_device*, uint64_t, uint32_t);
typedef uint64_t (*amdgpu_rreg64_t)(struct amdgpu_device*, uint32_t);
typedef void (*amdgpu_wreg64_t)(struct amdgpu_device*, uint32_t, uint64_t);
@ -657,7 +669,7 @@ enum amd_hw_ip_block_type {
MAX_HWIP
};
#define HWIP_MAX_INSTANCE 28
#define HWIP_MAX_INSTANCE 44
#define HW_ID_MAX 300
#define IP_VERSION(mj, mn, rv) (((mj) << 16) | ((mn) << 8) | (rv))
@ -665,6 +677,17 @@ enum amd_hw_ip_block_type {
#define IP_VERSION_MIN(ver) (((ver) >> 8) & 0xFF)
#define IP_VERSION_REV(ver) ((ver) & 0xFF)
struct amdgpu_ip_map_info {
/* Map of logical to actual dev instances/mask */
uint32_t dev_inst[MAX_HWIP][HWIP_MAX_INSTANCE];
int8_t (*logical_to_dev_inst)(struct amdgpu_device *adev,
enum amd_hw_ip_block_type block,
int8_t inst);
uint32_t (*logical_to_dev_mask)(struct amdgpu_device *adev,
enum amd_hw_ip_block_type block,
uint32_t mask);
};
struct amd_powerplay {
void *pp_handle;
const struct amd_pm_funcs *pp_funcs;
@ -750,6 +773,7 @@ struct amdgpu_device {
struct amdgpu_acp acp;
#endif
struct amdgpu_hive_info *hive;
struct amdgpu_xcp_mgr *xcp_mgr;
/* ASIC */
enum amd_asic_type asic_type;
uint32_t family;
@ -797,6 +821,8 @@ struct amdgpu_device {
amdgpu_wreg_t pcie_wreg;
amdgpu_rreg_t pciep_rreg;
amdgpu_wreg_t pciep_wreg;
amdgpu_rreg_ext_t pcie_rreg_ext;
amdgpu_wreg_ext_t pcie_wreg_ext;
amdgpu_rreg64_t pcie_rreg64;
amdgpu_wreg64_t pcie_wreg64;
/* protects concurrent UVD register access */
@ -830,7 +856,7 @@ struct amdgpu_device {
dma_addr_t dummy_page_addr;
struct amdgpu_vm_manager vm_manager;
struct amdgpu_vmhub vmhub[AMDGPU_MAX_VMHUBS];
unsigned num_vmhubs;
DECLARE_BITMAP(vmhubs_mask, AMDGPU_MAX_VMHUBS);
/* memory management */
struct amdgpu_mman mman;
@ -962,6 +988,7 @@ struct amdgpu_device {
/* soc15 register offset based on ip, instance and segment */
uint32_t *reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
struct amdgpu_ip_map_info ip_map;
/* delayed work_func for deferring clockgating during resume */
struct delayed_work delayed_init_work;
@ -1020,6 +1047,9 @@ struct amdgpu_device {
struct pci_saved_state *pci_state;
pci_channel_state_t pci_channel_state;
/* Track auto wait count on s_barrier settings */
bool barrier_has_auto_waitcnt;
struct amdgpu_reset_control *reset_cntl;
uint32_t ip_versions[MAX_HWIP][HWIP_MAX_INSTANCE];
@ -1050,6 +1080,8 @@ struct amdgpu_device {
bool job_hang;
bool dc_enabled;
/* Mask of active clusters */
uint32_t aid_mask;
};
static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
@ -1081,11 +1113,18 @@ size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
void *buf, size_t size, bool write);
uint32_t amdgpu_device_wait_on_rreg(struct amdgpu_device *adev,
uint32_t inst, uint32_t reg_addr, char reg_name[],
uint32_t expected_value, uint32_t mask);
uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
uint32_t reg, uint32_t acc_flags);
u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev,
u64 reg_addr);
void amdgpu_device_wreg(struct amdgpu_device *adev,
uint32_t reg, uint32_t v,
uint32_t acc_flags);
void amdgpu_device_indirect_wreg_ext(struct amdgpu_device *adev,
u64 reg_addr, u32 reg_data);
void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
uint32_t reg, uint32_t v);
void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
@ -1137,6 +1176,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
#define WREG32_PCIE(reg, v) adev->pcie_wreg(adev, (reg), (v))
#define RREG32_PCIE_PORT(reg) adev->pciep_rreg(adev, (reg))
#define WREG32_PCIE_PORT(reg, v) adev->pciep_wreg(adev, (reg), (v))
#define RREG32_PCIE_EXT(reg) adev->pcie_rreg_ext(adev, (reg))
#define WREG32_PCIE_EXT(reg, v) adev->pcie_wreg_ext(adev, (reg), (v))
#define RREG64_PCIE(reg) adev->pcie_rreg64(adev, (reg))
#define WREG64_PCIE(reg, v) adev->pcie_wreg64(adev, (reg), (v))
#define RREG32_SMC(reg) adev->smc_rreg(adev, (reg))
@ -1204,7 +1245,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
/*
* ASICs macro.
*/
#define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
#define amdgpu_asic_set_vga_state(adev, state) \
((adev)->asic_funcs->set_vga_state ? (adev)->asic_funcs->set_vga_state((adev), (state)) : 0)
#define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
#define amdgpu_asic_reset_method(adev) (adev)->asic_funcs->reset_method((adev))
#define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
@ -1235,6 +1277,10 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
#define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
#define for_each_inst(i, inst_mask) \
for (i = ffs(inst_mask) - 1; inst_mask; \
inst_mask &= ~(1U << i), i = ffs(inst_mask) - 1)
#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
/* Common functions */
@ -1348,6 +1394,12 @@ struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock);
/* amdgpu_acpi.c */
struct amdgpu_numa_info {
uint64_t size;
int pxm;
int nid;
};
/* ATCS Device/Driver State */
#define AMDGPU_ATCS_PSC_DEV_STATE_D0 0
#define AMDGPU_ATCS_PSC_DEV_STATE_D3_HOT 3
@ -1365,15 +1417,32 @@ int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
u8 dev_state, bool drv_state);
int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_state);
int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
int amdgpu_acpi_get_tmr_info(struct amdgpu_device *adev, u64 *tmr_offset,
u64 *tmr_size);
int amdgpu_acpi_get_mem_info(struct amdgpu_device *adev, int xcc_id,
struct amdgpu_numa_info *numa_info);
void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps);
bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev);
void amdgpu_acpi_detect(void);
void amdgpu_acpi_release(void);
#else
static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
static inline int amdgpu_acpi_get_tmr_info(struct amdgpu_device *adev,
u64 *tmr_offset, u64 *tmr_size)
{
return -EINVAL;
}
static inline int amdgpu_acpi_get_mem_info(struct amdgpu_device *adev,
int xcc_id,
struct amdgpu_numa_info *numa_info)
{
return -EINVAL;
}
static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; }
static inline void amdgpu_acpi_detect(void) { }
static inline void amdgpu_acpi_release(void) { }
static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; }
static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
u8 dev_state, bool drv_state) { return 0; }

407
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
View File

@ -26,6 +26,7 @@
#include <linux/acpi.h>
#include <linux/backlight.h>
#include <linux/slab.h>
#include <linux/xarray.h>
#include <linux/power_supply.h>
#include <linux/pm_runtime.h>
#include <linux/suspend.h>
@ -38,6 +39,45 @@
#include "amd_acpi.h"
#include "atom.h"
/* Declare GUID for AMD _DSM method for XCCs */
static const guid_t amd_xcc_dsm_guid = GUID_INIT(0x8267f5d5, 0xa556, 0x44f2,
0xb8, 0xb4, 0x45, 0x56, 0x2e,
0x8c, 0x5b, 0xec);
#define AMD_XCC_HID_START 3000
#define AMD_XCC_DSM_GET_NUM_FUNCS 0
#define AMD_XCC_DSM_GET_SUPP_MODE 1
#define AMD_XCC_DSM_GET_XCP_MODE 2
#define AMD_XCC_DSM_GET_VF_XCC_MAPPING 4
#define AMD_XCC_DSM_GET_TMR_INFO 5
#define AMD_XCC_DSM_NUM_FUNCS 5
#define AMD_XCC_MAX_HID 24
struct xarray numa_info_xa;
/* Encapsulates the XCD acpi object information */
struct amdgpu_acpi_xcc_info {
struct list_head list;
struct amdgpu_numa_info *numa_info;
uint8_t xcp_node;
uint8_t phy_id;
acpi_handle handle;
};
struct amdgpu_acpi_dev_info {
struct list_head list;
struct list_head xcc_list;
uint16_t bdf;
uint16_t supp_xcp_mode;
uint16_t xcp_mode;
uint16_t mem_mode;
uint64_t tmr_base;
uint64_t tmr_size;
};
struct list_head amdgpu_acpi_dev_list;
struct amdgpu_atif_notification_cfg {
bool enabled;
int command_code;
@ -801,6 +841,343 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta
return r;
}
#ifdef CONFIG_ACPI_NUMA
static inline uint64_t amdgpu_acpi_get_numa_size(int nid)
{
/* This is directly using si_meminfo_node implementation as the
* function is not exported.
*/
int zone_type;
uint64_t managed_pages = 0;
pg_data_t *pgdat = NODE_DATA(nid);
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
managed_pages +=
zone_managed_pages(&pgdat->node_zones[zone_type]);
return managed_pages * PAGE_SIZE;
}
static struct amdgpu_numa_info *amdgpu_acpi_get_numa_info(uint32_t pxm)
{
struct amdgpu_numa_info *numa_info;
int nid;
numa_info = xa_load(&numa_info_xa, pxm);
if (!numa_info) {
struct sysinfo info;
numa_info = kzalloc(sizeof *numa_info, GFP_KERNEL);
if (!numa_info)
return NULL;
nid = pxm_to_node(pxm);
numa_info->pxm = pxm;
numa_info->nid = nid;
if (numa_info->nid == NUMA_NO_NODE) {
si_meminfo(&info);
numa_info->size = info.totalram * info.mem_unit;
} else {
numa_info->size = amdgpu_acpi_get_numa_size(nid);
}
xa_store(&numa_info_xa, numa_info->pxm, numa_info, GFP_KERNEL);
}
return numa_info;
}
#endif
/**
* amdgpu_acpi_get_node_id - obtain the NUMA node id for corresponding amdgpu
* acpi device handle
*
* @handle: acpi handle
* @numa_info: amdgpu_numa_info structure holding numa information
*
* Queries the ACPI interface to fetch the corresponding NUMA Node ID for a
* given amdgpu acpi device.
*
* Returns ACPI STATUS OK with Node ID on success or the corresponding failure reason
*/
static acpi_status amdgpu_acpi_get_node_id(acpi_handle handle,
struct amdgpu_numa_info **numa_info)
{
#ifdef CONFIG_ACPI_NUMA
u64 pxm;
acpi_status status;
if (!numa_info)
return_ACPI_STATUS(AE_ERROR);
status = acpi_evaluate_integer(handle, "_PXM", NULL, &pxm);
if (ACPI_FAILURE(status))
return status;
*numa_info = amdgpu_acpi_get_numa_info(pxm);
if (!*numa_info)
return_ACPI_STATUS(AE_ERROR);
return_ACPI_STATUS(AE_OK);
#else
return_ACPI_STATUS(AE_NOT_EXIST);
#endif
}
static struct amdgpu_acpi_dev_info *amdgpu_acpi_get_dev(u16 bdf)
{
struct amdgpu_acpi_dev_info *acpi_dev;
if (list_empty(&amdgpu_acpi_dev_list))
return NULL;
list_for_each_entry(acpi_dev, &amdgpu_acpi_dev_list, list)
if (acpi_dev->bdf == bdf)
return acpi_dev;
return NULL;
}
static int amdgpu_acpi_dev_init(struct amdgpu_acpi_dev_info **dev_info,
struct amdgpu_acpi_xcc_info *xcc_info, u16 bdf)
{
struct amdgpu_acpi_dev_info *tmp;
union acpi_object *obj;
int ret = -ENOENT;
*dev_info = NULL;
tmp = kzalloc(sizeof(struct amdgpu_acpi_dev_info), GFP_KERNEL);
if (!tmp)
return -ENOMEM;
INIT_LIST_HEAD(&tmp->xcc_list);
INIT_LIST_HEAD(&tmp->list);
tmp->bdf = bdf;
obj = acpi_evaluate_dsm_typed(xcc_info->handle, &amd_xcc_dsm_guid, 0,
AMD_XCC_DSM_GET_SUPP_MODE, NULL,
ACPI_TYPE_INTEGER);
if (!obj) {
acpi_handle_debug(xcc_info->handle,
"_DSM function %d evaluation failed",
AMD_XCC_DSM_GET_SUPP_MODE);
ret = -ENOENT;
goto out;
}
tmp->supp_xcp_mode = obj->integer.value & 0xFFFF;
ACPI_FREE(obj);
obj = acpi_evaluate_dsm_typed(xcc_info->handle, &amd_xcc_dsm_guid, 0,
AMD_XCC_DSM_GET_XCP_MODE, NULL,
ACPI_TYPE_INTEGER);
if (!obj) {
acpi_handle_debug(xcc_info->handle,
"_DSM function %d evaluation failed",
AMD_XCC_DSM_GET_XCP_MODE);
ret = -ENOENT;
goto out;
}
tmp->xcp_mode = obj->integer.value & 0xFFFF;
tmp->mem_mode = (obj->integer.value >> 32) & 0xFFFF;
ACPI_FREE(obj);
/* Evaluate DSMs and fill XCC information */
obj = acpi_evaluate_dsm_typed(xcc_info->handle, &amd_xcc_dsm_guid, 0,
AMD_XCC_DSM_GET_TMR_INFO, NULL,
ACPI_TYPE_PACKAGE);
if (!obj || obj->package.count < 2) {
acpi_handle_debug(xcc_info->handle,
"_DSM function %d evaluation failed",
AMD_XCC_DSM_GET_TMR_INFO);
ret = -ENOENT;
goto out;
}
tmp->tmr_base = obj->package.elements[0].integer.value;
tmp->tmr_size = obj->package.elements[1].integer.value;
ACPI_FREE(obj);
DRM_DEBUG_DRIVER(
"New dev(%x): Supported xcp mode: %x curr xcp_mode : %x mem mode : %x, tmr base: %llx tmr size: %llx ",
tmp->bdf, tmp->supp_xcp_mode, tmp->xcp_mode, tmp->mem_mode,
tmp->tmr_base, tmp->tmr_size);
list_add_tail(&tmp->list, &amdgpu_acpi_dev_list);
*dev_info = tmp;
return 0;
out:
if (obj)
ACPI_FREE(obj);
kfree(tmp);
return ret;
}
static int amdgpu_acpi_get_xcc_info(struct amdgpu_acpi_xcc_info *xcc_info,
u16 *bdf)
{
union acpi_object *obj;
acpi_status status;
int ret = -ENOENT;
obj = acpi_evaluate_dsm_typed(xcc_info->handle, &amd_xcc_dsm_guid, 0,
AMD_XCC_DSM_GET_NUM_FUNCS, NULL,
ACPI_TYPE_INTEGER);
if (!obj || obj->integer.value != AMD_XCC_DSM_NUM_FUNCS)
goto out;
ACPI_FREE(obj);
/* Evaluate DSMs and fill XCC information */
obj = acpi_evaluate_dsm_typed(xcc_info->handle, &amd_xcc_dsm_guid, 0,
AMD_XCC_DSM_GET_VF_XCC_MAPPING, NULL,
ACPI_TYPE_INTEGER);
if (!obj) {
acpi_handle_debug(xcc_info->handle,
"_DSM function %d evaluation failed",
AMD_XCC_DSM_GET_VF_XCC_MAPPING);
ret = -EINVAL;
goto out;
}
/* PF xcc id [39:32] */
xcc_info->phy_id = (obj->integer.value >> 32) & 0xFF;
/* xcp node of this xcc [47:40] */
xcc_info->xcp_node = (obj->integer.value >> 40) & 0xFF;
/* PF bus/dev/fn of this xcc [63:48] */
*bdf = (obj->integer.value >> 48) & 0xFFFF;
ACPI_FREE(obj);
obj = NULL;
status =
amdgpu_acpi_get_node_id(xcc_info->handle, &xcc_info->numa_info);
/* TODO: check if this check is required */
if (ACPI_SUCCESS(status))
ret = 0;
out:
if (obj)
ACPI_FREE(obj);
return ret;
}
static int amdgpu_acpi_enumerate_xcc(void)
{
struct amdgpu_acpi_dev_info *dev_info = NULL;
struct amdgpu_acpi_xcc_info *xcc_info;
struct acpi_device *acpi_dev;
char hid[ACPI_ID_LEN];
int ret, id;
u16 bdf;
INIT_LIST_HEAD(&amdgpu_acpi_dev_list);
xa_init(&numa_info_xa);
for (id = 0; id < AMD_XCC_MAX_HID; id++) {
sprintf(hid, "%s%d", "AMD", AMD_XCC_HID_START + id);
acpi_dev = acpi_dev_get_first_match_dev(hid, NULL, -1);
/* These ACPI objects are expected to be in sequential order. If
* one is not found, no need to check the rest.
*/
if (!acpi_dev) {
DRM_DEBUG_DRIVER("No matching acpi device found for %s",
hid);
break;
}
xcc_info = kzalloc(sizeof(struct amdgpu_acpi_xcc_info),
GFP_KERNEL);
if (!xcc_info) {
DRM_ERROR("Failed to allocate memory for xcc info\n");
return -ENOMEM;
}
INIT_LIST_HEAD(&xcc_info->list);
xcc_info->handle = acpi_device_handle(acpi_dev);
acpi_dev_put(acpi_dev);
ret = amdgpu_acpi_get_xcc_info(xcc_info, &bdf);
if (ret) {
kfree(xcc_info);
continue;
}
dev_info = amdgpu_acpi_get_dev(bdf);
if (!dev_info)
ret = amdgpu_acpi_dev_init(&dev_info, xcc_info, bdf);
if (ret == -ENOMEM)
return ret;
if (!dev_info) {
kfree(xcc_info);
continue;
}
list_add_tail(&xcc_info->list, &dev_info->xcc_list);
}
return 0;
}
int amdgpu_acpi_get_tmr_info(struct amdgpu_device *adev, u64 *tmr_offset,
u64 *tmr_size)
{
struct amdgpu_acpi_dev_info *dev_info;
u16 bdf;
if (!tmr_offset || !tmr_size)
return -EINVAL;
bdf = (adev->pdev->bus->number << 8) | adev->pdev->devfn;
dev_info = amdgpu_acpi_get_dev(bdf);
if (!dev_info)
return -ENOENT;
*tmr_offset = dev_info->tmr_base;
*tmr_size = dev_info->tmr_size;
return 0;
}
int amdgpu_acpi_get_mem_info(struct amdgpu_device *adev, int xcc_id,
struct amdgpu_numa_info *numa_info)
{
struct amdgpu_acpi_dev_info *dev_info;
struct amdgpu_acpi_xcc_info *xcc_info;
u16 bdf;
if (!numa_info)
return -EINVAL;
bdf = (adev->pdev->bus->number << 8) | adev->pdev->devfn;
dev_info = amdgpu_acpi_get_dev(bdf);
if (!dev_info)
return -ENOENT;
list_for_each_entry(xcc_info, &dev_info->xcc_list, list) {
if (xcc_info->phy_id == xcc_id) {
memcpy(numa_info, xcc_info->numa_info,
sizeof(*numa_info));
return 0;
}
}
return -ENOENT;
}
/**
* amdgpu_acpi_event - handle notify events
*
@ -1054,6 +1431,36 @@ void amdgpu_acpi_detect(void)
} else {
atif->backlight_caps.caps_valid = false;
}
amdgpu_acpi_enumerate_xcc();
}
void amdgpu_acpi_release(void)
{
struct amdgpu_acpi_dev_info *dev_info, *dev_tmp;
struct amdgpu_acpi_xcc_info *xcc_info, *xcc_tmp;
struct amdgpu_numa_info *numa_info;
unsigned long index;
xa_for_each(&numa_info_xa, index, numa_info) {
kfree(numa_info);
xa_erase(&numa_info_xa, index);
}
if (list_empty(&amdgpu_acpi_dev_list))
return;
list_for_each_entry_safe(dev_info, dev_tmp, &amdgpu_acpi_dev_list,
list) {
list_for_each_entry_safe(xcc_info, xcc_tmp, &dev_info->xcc_list,
list) {
list_del(&xcc_info->list);
kfree(xcc_info);
}
list_del(&dev_info->list);
kfree(dev_info);
}
}
#if IS_ENABLED(CONFIG_SUSPEND)

82
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
View File

@ -53,7 +53,6 @@ int amdgpu_amdkfd_init(void)
amdgpu_amdkfd_total_mem_size *= si.mem_unit;
ret = kgd2kfd_init();
amdgpu_amdkfd_gpuvm_init_mem_limits();
kfd_initialized = !ret;
return ret;
@ -143,6 +142,8 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
int i;
int last_valid_bit;
amdgpu_amdkfd_gpuvm_init_mem_limits();
if (adev->kfd.dev) {
struct kgd2kfd_shared_resources gpu_resources = {
.compute_vmid_bitmap =
@ -162,7 +163,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
* clear
*/
bitmap_complement(gpu_resources.cp_queue_bitmap,
adev->gfx.mec.queue_bitmap,
adev->gfx.mec_bitmap[0].queue_bitmap,
KGD_MAX_QUEUES);
/* According to linux/bitmap.h we shouldn't use bitmap_clear if
@ -427,14 +428,23 @@ uint32_t amdgpu_amdkfd_get_fw_version(struct amdgpu_device *adev,
}
void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev,
struct kfd_local_mem_info *mem_info)
struct kfd_local_mem_info *mem_info,
struct amdgpu_xcp *xcp)
{
memset(mem_info, 0, sizeof(*mem_info));
mem_info->local_mem_size_public = adev->gmc.visible_vram_size;
mem_info->local_mem_size_private = adev->gmc.real_vram_size -
if (xcp) {
if (adev->gmc.real_vram_size == adev->gmc.visible_vram_size)
mem_info->local_mem_size_public =
KFD_XCP_MEMORY_SIZE(adev, xcp->id);
else
mem_info->local_mem_size_private =
KFD_XCP_MEMORY_SIZE(adev, xcp->id);
} else {
mem_info->local_mem_size_public = adev->gmc.visible_vram_size;
mem_info->local_mem_size_private = adev->gmc.real_vram_size -
adev->gmc.visible_vram_size;
}
mem_info->vram_width = adev->gmc.vram_width;
pr_debug("Address base: %pap public 0x%llx private 0x%llx\n",
@ -497,7 +507,7 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd,
struct amdgpu_device **dmabuf_adev,
uint64_t *bo_size, void *metadata_buffer,
size_t buffer_size, uint32_t *metadata_size,
uint32_t *flags)
uint32_t *flags, int8_t *xcp_id)
{
struct dma_buf *dma_buf;
struct drm_gem_object *obj;
@ -541,6 +551,8 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd,
if (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
*flags |= KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC;
}
if (xcp_id)
*xcp_id = bo->xcp_id;
out_put:
dma_buf_put(dma_buf);
@ -732,17 +744,19 @@ int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct amdgpu_device *adev,
if (adev->family == AMDGPU_FAMILY_AI) {
int i;
for (i = 0; i < adev->num_vmhubs; i++)
for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS)
amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
} else {
amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB(0), 0);
}
return 0;
}
int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
uint16_t pasid, enum TLB_FLUSH_TYPE flush_type)
uint16_t pasid,
enum TLB_FLUSH_TYPE flush_type,
uint32_t inst)
{
bool all_hub = false;
@ -750,7 +764,7 @@ int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
adev->family == AMDGPU_FAMILY_RV)
all_hub = true;
return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub);
return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub, inst);
}
bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev)
@ -758,11 +772,32 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev)
return adev->have_atomics_support;
}
void amdgpu_amdkfd_debug_mem_fence(struct amdgpu_device *adev)
{
amdgpu_device_flush_hdp(adev, NULL);
}
void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, bool reset)
{
amdgpu_umc_poison_handler(adev, reset);
}
int amdgpu_amdkfd_send_close_event_drain_irq(struct amdgpu_device *adev,
uint32_t *payload)
{
int ret;
/* Device or IH ring is not ready so bail. */
ret = amdgpu_ih_wait_on_checkpoint_process_ts(adev, &adev->irq.ih);
if (ret)
return ret;
/* Send payload to fence KFD interrupts */
amdgpu_amdkfd_interrupt(adev, payload);
return 0;
}
bool amdgpu_amdkfd_ras_query_utcl2_poison_status(struct amdgpu_device *adev)
{
if (adev->gfx.ras && adev->gfx.ras->query_utcl2_poison_status)
@ -770,3 +805,28 @@ bool amdgpu_amdkfd_ras_query_utcl2_poison_status(struct amdgpu_device *adev)
else
return false;
}
int amdgpu_amdkfd_check_and_lock_kfd(struct amdgpu_device *adev)
{
return kgd2kfd_check_and_lock_kfd();
}
void amdgpu_amdkfd_unlock_kfd(struct amdgpu_device *adev)
{
kgd2kfd_unlock_kfd();
}
u64 amdgpu_amdkfd_xcp_memory_size(struct amdgpu_device *adev, int xcp_id)
{
u64 tmp;
s8 mem_id = KFD_XCP_MEM_ID(adev, xcp_id);
if (adev->gmc.num_mem_partitions && xcp_id >= 0 && mem_id >= 0) {
tmp = adev->gmc.mem_partitions[mem_id].size;
do_div(tmp, adev->xcp_mgr->num_xcp_per_mem_partition);
return ALIGN_DOWN(tmp, PAGE_SIZE);
} else {
return adev->gmc.real_vram_size;
}
}

60
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
View File

@ -30,10 +30,12 @@
#include <linux/kthread.h>
#include <linux/workqueue.h>
#include <linux/mmu_notifier.h>
#include <linux/memremap.h>
#include <kgd_kfd_interface.h>
#include <drm/ttm/ttm_execbuf_util.h>
#include "amdgpu_sync.h"
#include "amdgpu_vm.h"
#include "amdgpu_xcp.h"
extern uint64_t amdgpu_amdkfd_total_mem_size;
@ -97,10 +99,13 @@ struct amdgpu_amdkfd_fence {
struct amdgpu_kfd_dev {
struct kfd_dev *dev;
int64_t vram_used;
uint64_t vram_used_aligned;
int64_t vram_used[MAX_XCP];
uint64_t vram_used_aligned[MAX_XCP];
bool init_complete;
struct work_struct reset_work;
/* HMM page migration MEMORY_DEVICE_PRIVATE mapping */
struct dev_pagemap pgmap;
};
enum kgd_engine_type {
@ -151,6 +156,8 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev);
int amdgpu_amdkfd_check_and_lock_kfd(struct amdgpu_device *adev);
void amdgpu_amdkfd_unlock_kfd(struct amdgpu_device *adev);
int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev,
enum kgd_engine_type engine,
uint32_t vmid, uint64_t gpu_addr,
@ -160,7 +167,8 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct amdgpu_device *adev,
uint16_t vmid);
int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
uint16_t pasid, enum TLB_FLUSH_TYPE flush_type);
uint16_t pasid, enum TLB_FLUSH_TYPE flush_type,
uint32_t inst);
bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
@ -224,7 +232,8 @@ int amdgpu_amdkfd_remove_gws_from_process(void *info, void *mem);
uint32_t amdgpu_amdkfd_get_fw_version(struct amdgpu_device *adev,
enum kgd_engine_type type);
void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev,
struct kfd_local_mem_info *mem_info);
struct kfd_local_mem_info *mem_info,
struct amdgpu_xcp *xcp);
uint64_t amdgpu_amdkfd_get_gpu_clock_counter(struct amdgpu_device *adev);
uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct amdgpu_device *adev);
@ -234,13 +243,15 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd,
struct amdgpu_device **dmabuf_adev,
uint64_t *bo_size, void *metadata_buffer,
size_t buffer_size, uint32_t *metadata_size,
uint32_t *flags);
uint32_t *flags, int8_t *xcp_id);
uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst,
struct amdgpu_device *src);
int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
struct amdgpu_device *src,
bool is_min);
int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min);
int amdgpu_amdkfd_send_close_event_drain_irq(struct amdgpu_device *adev,
uint32_t *payload);
/* Read user wptr from a specified user address space with page fault
* disabled. The memory must be pinned and mapped to the hardware when
@ -279,7 +290,8 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev,
void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev,
void *drm_priv);
uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv);
size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev);
size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
uint8_t xcp_id);
int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
struct amdgpu_device *adev, uint64_t va, uint64_t size,
void *drm_priv, struct kgd_mem **mem,
@ -310,6 +322,7 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
uint64_t *mmap_offset);
int amdgpu_amdkfd_gpuvm_export_dmabuf(struct kgd_mem *mem,
struct dma_buf **dmabuf);
void amdgpu_amdkfd_debug_mem_fence(struct amdgpu_device *adev);
int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev,
struct tile_config *config);
void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev,
@ -319,9 +332,18 @@ void amdgpu_amdkfd_block_mmu_notifications(void *p);
int amdgpu_amdkfd_criu_resume(void *p);
bool amdgpu_amdkfd_ras_query_utcl2_poison_status(struct amdgpu_device *adev);
int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
uint64_t size, u32 alloc_flag);
uint64_t size, u32 alloc_flag, int8_t xcp_id);
void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
uint64_t size, u32 alloc_flag);
uint64_t size, u32 alloc_flag, int8_t xcp_id);
u64 amdgpu_amdkfd_xcp_memory_size(struct amdgpu_device *adev, int xcp_id);
#define KFD_XCP_MEM_ID(adev, xcp_id) \
((adev)->xcp_mgr && (xcp_id) >= 0 ?\
(adev)->xcp_mgr->xcp[(xcp_id)].mem_id : -1)
#define KFD_XCP_MEMORY_SIZE(adev, xcp_id) amdgpu_amdkfd_xcp_memory_size((adev), (xcp_id))
#if IS_ENABLED(CONFIG_HSA_AMD)
void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
@ -352,6 +374,17 @@ void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
{
}
#endif
#if IS_ENABLED(CONFIG_HSA_AMD_SVM)
int kgd2kfd_init_zone_device(struct amdgpu_device *adev);
#else
static inline
int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
{
return 0;
}
#endif
/* KGD2KFD callbacks */
int kgd2kfd_quiesce_mm(struct mm_struct *mm, uint32_t trigger);
int kgd2kfd_resume_mm(struct mm_struct *mm);
@ -372,6 +405,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd);
void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask);
int kgd2kfd_check_and_lock_kfd(void);
void kgd2kfd_unlock_kfd(void);
#else
static inline int kgd2kfd_init(void)
{
@ -437,5 +472,14 @@ static inline
void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask)
{
}
static inline int kgd2kfd_check_and_lock_kfd(void)
{
return 0;
}
static inline void kgd2kfd_unlock_kfd(void)
{
}
#endif
#endif /* AMDGPU_AMDKFD_H_INCLUDED */

154
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
View File

@ -23,6 +23,149 @@
#include "amdgpu_amdkfd.h"
#include "amdgpu_amdkfd_arcturus.h"
#include "amdgpu_amdkfd_gfx_v9.h"
#include "gc/gc_9_4_2_offset.h"
#include "gc/gc_9_4_2_sh_mask.h"
#include <uapi/linux/kfd_ioctl.h>
/*
* Returns TRAP_EN, EXCP_EN and EXCP_REPLACE.
*
* restore_dbg_registers is ignored here but is a general interface requirement
* for devices that support GFXOFF and where the RLC save/restore list
* does not support hw registers for debugging i.e. the driver has to manually
* initialize the debug mode registers after it has disabled GFX off during the
* debug session.
*/
static uint32_t kgd_aldebaran_enable_debug_trap(struct amdgpu_device *adev,
bool restore_dbg_registers,
uint32_t vmid)
{
uint32_t data = 0;
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, 0);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, 0);
return data;
}
/* returns TRAP_EN, EXCP_EN and EXCP_REPLACE. */
static uint32_t kgd_aldebaran_disable_debug_trap(struct amdgpu_device *adev,
bool keep_trap_enabled,
uint32_t vmid)
{
uint32_t data = 0;
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, keep_trap_enabled);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, 0);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, 0);
return data;
}
static int kgd_aldebaran_validate_trap_override_request(struct amdgpu_device *adev,
uint32_t trap_override,
uint32_t *trap_mask_supported)
{
*trap_mask_supported &= KFD_DBG_TRAP_MASK_FP_INVALID |
KFD_DBG_TRAP_MASK_FP_INPUT_DENORMAL |
KFD_DBG_TRAP_MASK_FP_DIVIDE_BY_ZERO |
KFD_DBG_TRAP_MASK_FP_OVERFLOW |
KFD_DBG_TRAP_MASK_FP_UNDERFLOW |
KFD_DBG_TRAP_MASK_FP_INEXACT |
KFD_DBG_TRAP_MASK_INT_DIVIDE_BY_ZERO |
KFD_DBG_TRAP_MASK_DBG_ADDRESS_WATCH |
KFD_DBG_TRAP_MASK_DBG_MEMORY_VIOLATION;
if (trap_override != KFD_DBG_TRAP_OVERRIDE_OR &&
trap_override != KFD_DBG_TRAP_OVERRIDE_REPLACE)
return -EPERM;
return 0;
}
/* returns TRAP_EN, EXCP_EN and EXCP_RPLACE. */
static uint32_t kgd_aldebaran_set_wave_launch_trap_override(struct amdgpu_device *adev,
uint32_t vmid,
uint32_t trap_override,
uint32_t trap_mask_bits,
uint32_t trap_mask_request,
uint32_t *trap_mask_prev,
uint32_t kfd_dbg_trap_cntl_prev)
{
uint32_t data = 0;
*trap_mask_prev = REG_GET_FIELD(kfd_dbg_trap_cntl_prev, SPI_GDBG_PER_VMID_CNTL, EXCP_EN);
trap_mask_bits = (trap_mask_bits & trap_mask_request) |
(*trap_mask_prev & ~trap_mask_request);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, trap_mask_bits);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, trap_override);
return data;
}
static uint32_t kgd_aldebaran_set_wave_launch_mode(struct amdgpu_device *adev,
uint8_t wave_launch_mode,
uint32_t vmid)
{
uint32_t data = 0;
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, LAUNCH_MODE, wave_launch_mode);
return data;
}
#define TCP_WATCH_STRIDE (regTCP_WATCH1_ADDR_H - regTCP_WATCH0_ADDR_H)
static uint32_t kgd_gfx_aldebaran_set_address_watch(
struct amdgpu_device *adev,
uint64_t watch_address,
uint32_t watch_address_mask,
uint32_t watch_id,
uint32_t watch_mode,
uint32_t debug_vmid)
{
uint32_t watch_address_high;
uint32_t watch_address_low;
uint32_t watch_address_cntl;
watch_address_cntl = 0;
watch_address_low = lower_32_bits(watch_address);
watch_address_high = upper_32_bits(watch_address) & 0xffff;
watch_address_cntl = REG_SET_FIELD(watch_address_cntl,
TCP_WATCH0_CNTL,
MODE,
watch_mode);
watch_address_cntl = REG_SET_FIELD(watch_address_cntl,
TCP_WATCH0_CNTL,
MASK,
watch_address_mask >> 6);
watch_address_cntl = REG_SET_FIELD(watch_address_cntl,
TCP_WATCH0_CNTL,
VALID,
1);
WREG32_RLC((SOC15_REG_OFFSET(GC, 0, regTCP_WATCH0_ADDR_H) +
(watch_id * TCP_WATCH_STRIDE)),
watch_address_high);
WREG32_RLC((SOC15_REG_OFFSET(GC, 0, regTCP_WATCH0_ADDR_L) +
(watch_id * TCP_WATCH_STRIDE)),
watch_address_low);
return watch_address_cntl;
}
static uint32_t kgd_gfx_aldebaran_clear_address_watch(struct amdgpu_device *adev,
uint32_t watch_id)
{
return 0;
}
const struct kfd2kgd_calls aldebaran_kfd2kgd = {
.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
@ -42,5 +185,14 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
.enable_debug_trap = kgd_aldebaran_enable_debug_trap,
.disable_debug_trap = kgd_aldebaran_disable_debug_trap,
.validate_trap_override_request = kgd_aldebaran_validate_trap_override_request,
.set_wave_launch_trap_override = kgd_aldebaran_set_wave_launch_trap_override,
.set_wave_launch_mode = kgd_aldebaran_set_wave_launch_mode,
.set_address_watch = kgd_gfx_aldebaran_set_address_watch,
.clear_address_watch = kgd_gfx_aldebaran_clear_address_watch,
.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
.build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info,
.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
};

123
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
View File

@ -26,6 +26,7 @@
#include "amdgpu.h"
#include "amdgpu_amdkfd.h"
#include "amdgpu_amdkfd_arcturus.h"
#include "amdgpu_reset.h"
#include "sdma0/sdma0_4_2_2_offset.h"
#include "sdma0/sdma0_4_2_2_sh_mask.h"
#include "sdma1/sdma1_4_2_2_offset.h"
@ -48,6 +49,8 @@
#include "amdgpu_amdkfd_gfx_v9.h"
#include "gfxhub_v1_0.h"
#include "mmhub_v9_4.h"
#include "gc/gc_9_0_offset.h"
#include "gc/gc_9_0_sh_mask.h"
#define HQD_N_REGS 56
#define DUMP_REG(addr) do { \
@ -276,6 +279,117 @@ int kgd_arcturus_hqd_sdma_destroy(struct amdgpu_device *adev, void *mqd,
return 0;
}
/*
* Helper used to suspend/resume gfx pipe for image post process work to set
* barrier behaviour.
*/
static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool suspend)
{
int i, r = 0;
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
if (!(ring && ring->sched.thread))
continue;
/* stop secheduler and drain ring. */
if (suspend) {
drm_sched_stop(&ring->sched, NULL);
r = amdgpu_fence_wait_empty(ring);
if (r)
goto out;
} else {
drm_sched_start(&ring->sched, false);
}
}
out:
/* return on resume or failure to drain rings. */
if (!suspend || r)
return r;
return amdgpu_device_ip_wait_for_idle(adev, AMD_IP_BLOCK_TYPE_GFX);
}
static void set_barrier_auto_waitcnt(struct amdgpu_device *adev, bool enable_waitcnt)
{
uint32_t data;
WRITE_ONCE(adev->barrier_has_auto_waitcnt, enable_waitcnt);
if (!down_read_trylock(&adev->reset_domain->sem))
return;
amdgpu_amdkfd_suspend(adev, false);
if (suspend_resume_compute_scheduler(adev, true))
goto out;
data = RREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CONFIG));
data = REG_SET_FIELD(data, SQ_CONFIG, DISABLE_BARRIER_WAITCNT,
!enable_waitcnt);
WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CONFIG), data);
out:
suspend_resume_compute_scheduler(adev, false);
amdgpu_amdkfd_resume(adev, false);
up_read(&adev->reset_domain->sem);
}
/*
* restore_dbg_registers is ignored here but is a general interface requirement
* for devices that support GFXOFF and where the RLC save/restore list
* does not support hw registers for debugging i.e. the driver has to manually
* initialize the debug mode registers after it has disabled GFX off during the
* debug session.
*/
static uint32_t kgd_arcturus_enable_debug_trap(struct amdgpu_device *adev,
bool restore_dbg_registers,
uint32_t vmid)
{
mutex_lock(&adev->grbm_idx_mutex);
kgd_gfx_v9_set_wave_launch_stall(adev, vmid, true);
set_barrier_auto_waitcnt(adev, true);
WREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_GDBG_TRAP_MASK), 0);
kgd_gfx_v9_set_wave_launch_stall(adev, vmid, false);
mutex_unlock(&adev->grbm_idx_mutex);
return 0;
}
/*
* keep_trap_enabled is ignored here but is a general interface requirement
* for devices that support multi-process debugging where the performance
* overhead from trap temporary setup needs to be bypassed when the debug
* session has ended.
*/
static uint32_t kgd_arcturus_disable_debug_trap(struct amdgpu_device *adev,
bool keep_trap_enabled,
uint32_t vmid)
{
mutex_lock(&adev->grbm_idx_mutex);
kgd_gfx_v9_set_wave_launch_stall(adev, vmid, true);
set_barrier_auto_waitcnt(adev, false);
WREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_GDBG_TRAP_MASK), 0);
kgd_gfx_v9_set_wave_launch_stall(adev, vmid, false);
mutex_unlock(&adev->grbm_idx_mutex);
return 0;
}
const struct kfd2kgd_calls arcturus_kfd2kgd = {
.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
@ -294,6 +408,15 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
.set_vm_context_page_table_base =
kgd_gfx_v9_set_vm_context_page_table_base,
.enable_debug_trap = kgd_arcturus_enable_debug_trap,
.disable_debug_trap = kgd_arcturus_disable_debug_trap,
.validate_trap_override_request = kgd_gfx_v9_validate_trap_override_request,
.set_wave_launch_trap_override = kgd_gfx_v9_set_wave_launch_trap_override,
.set_wave_launch_mode = kgd_gfx_v9_set_wave_launch_mode,
.set_address_watch = kgd_gfx_v9_set_address_watch,
.clear_address_watch = kgd_gfx_v9_clear_address_watch,
.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
.build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info,
.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
};

Some files were not shown because too many files have changed in this diff Show More