<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/Documentation/accel, branch v6.18.21</title>
<subtitle>Clone of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git</subtitle>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/'/>
<entry>
<title>Documentation: accel: amdxdna: Update compiler information</title>
<updated>2025-08-21T15:25:31+00:00</updated>
<author>
<name>Lizhi Hou</name>
<email>lizhi.hou@amd.com</email>
</author>
<published>2025-08-20T23:38:17+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=3f13bcc886fc034113cb75cb32b8d9db1216b846'/>
<id>3f13bcc886fc034113cb75cb32b8d9db1216b846</id>
<content type='text'>
The compiler information is outdated. Update it to the latest.

Reviewed-by: Maciej Falkowski &lt;maciej.falkowski@linux.intel.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Lizhi Hou &lt;lizhi.hou@amd.com&gt;
Link: https://lore.kernel.org/r/20250820233817.4050006-1-lizhi.hou@amd.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The compiler information is outdated. Update it to the latest.

Reviewed-by: Maciej Falkowski &lt;maciej.falkowski@linux.intel.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Lizhi Hou &lt;lizhi.hou@amd.com&gt;
Link: https://lore.kernel.org/r/20250820233817.4050006-1-lizhi.hou@amd.com
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/rocket: Add a new driver for Rockchip's NPU</title>
<updated>2025-07-25T15:56:23+00:00</updated>
<author>
<name>Tomeu Vizoso</name>
<email>tomeu@tomeuvizoso.net</email>
</author>
<published>2025-07-21T09:17:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=ed98261b41687323ffa02ca20fef1e60b38fd1aa'/>
<id>ed98261b41687323ffa02ca20fef1e60b38fd1aa</id>
<content type='text'>
This initial version supports the NPU as shipped in the RK3588 SoC and
described in the first part of its TRM, in Chapter 36.

This NPU contains 3 independent cores that the driver can submit jobs
to.

This commit adds just hardware initialization and power management.

v2:
- Split cores and IOMMUs as independent devices (Sebastian Reichel)
- Add some documentation (Jeffrey Hugo)
- Be more explicit in the Kconfig documentation (Jeffrey Hugo)
- Remove resets, as these haven't been found useful so far (Zenghui Yu)
- Repack structs (Jeffrey Hugo)
- Use DEFINE_DRM_ACCEL_FOPS (Jeffrey Hugo)
- Use devm_drm_dev_alloc (Jeffrey Hugo)
- Use probe log helper (Jeffrey Hugo)
- Introduce UABI header in a later patch (Jeffrey Hugo)

v3:
- Adapt to a split of the register block in the DT bindings (Nicolas
  Frattaroli)
- Move registers header to its own commit (Thomas Zimmermann)
- Misc. cleanups (Thomas Zimmermann and Jeff Hugo)
- Make use of GPL-2.0-only for the copyright notice (Jeff Hugo)
- PM improvements (Nicolas Frattaroli)

v4:
- Use bulk clk API (Krzysztof Kozlowski)

v6:
- Remove mention to NVDLA, as the hardware is only incidentally related
  (Kever Yang)
- Use calloc instead of GFP_ZERO (Jeff Hugo)
- Explicitly include linux/container_of.h (Jeff Hugo)
- pclk and npu clocks are now needed by all cores (Rob Herring)

v7:
- Assign its own IOMMU domain to each client, for isolation (Daniel
  Stone and Robin Murphy)

v8:
- Kconfig: fix depends to be more explicit about Rockchip, and remove
  superfluous selects (Robin Murphy)
- Use reset lines to reset the cores (Robin Murphy)
- Reference count the module
- Set dma_set_max_seg_size
- Correctly acquire a reference to the IOMMU (Robin Murphy)
- Remove notion of top core (Robin Murphy)

Reviewed-by: Robert Foss &lt;rfoss@kernel.org&gt;
Tested-by: Heiko Stuebner &lt;heiko@sntech.de&gt;
Reviewed-by: Jeff Hugo &lt;jeff.hugo@oss.qualcomm.com&gt;
Signed-off-by: Tomeu Vizoso &lt;tomeu@tomeuvizoso.net&gt;
Signed-off-by: Jeff Hugo &lt;jeff.hugo@oss.qualcomm.com&gt;
Link: https://lore.kernel.org/r/20250721-6-10-rocket-v9-2-77ebd484941e@tomeuvizoso.net
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This initial version supports the NPU as shipped in the RK3588 SoC and
described in the first part of its TRM, in Chapter 36.

This NPU contains 3 independent cores that the driver can submit jobs
to.

This commit adds just hardware initialization and power management.

v2:
- Split cores and IOMMUs as independent devices (Sebastian Reichel)
- Add some documentation (Jeffrey Hugo)
- Be more explicit in the Kconfig documentation (Jeffrey Hugo)
- Remove resets, as these haven't been found useful so far (Zenghui Yu)
- Repack structs (Jeffrey Hugo)
- Use DEFINE_DRM_ACCEL_FOPS (Jeffrey Hugo)
- Use devm_drm_dev_alloc (Jeffrey Hugo)
- Use probe log helper (Jeffrey Hugo)
- Introduce UABI header in a later patch (Jeffrey Hugo)

v3:
- Adapt to a split of the register block in the DT bindings (Nicolas
  Frattaroli)
- Move registers header to its own commit (Thomas Zimmermann)
- Misc. cleanups (Thomas Zimmermann and Jeff Hugo)
- Make use of GPL-2.0-only for the copyright notice (Jeff Hugo)
- PM improvements (Nicolas Frattaroli)

v4:
- Use bulk clk API (Krzysztof Kozlowski)

v6:
- Remove mention to NVDLA, as the hardware is only incidentally related
  (Kever Yang)
- Use calloc instead of GFP_ZERO (Jeff Hugo)
- Explicitly include linux/container_of.h (Jeff Hugo)
- pclk and npu clocks are now needed by all cores (Rob Herring)

v7:
- Assign its own IOMMU domain to each client, for isolation (Daniel
  Stone and Robin Murphy)

v8:
- Kconfig: fix depends to be more explicit about Rockchip, and remove
  superfluous selects (Robin Murphy)
- Use reset lines to reset the cores (Robin Murphy)
- Reference count the module
- Set dma_set_max_seg_size
- Correctly acquire a reference to the IOMMU (Robin Murphy)
- Remove notion of top core (Robin Murphy)

Reviewed-by: Robert Foss &lt;rfoss@kernel.org&gt;
Tested-by: Heiko Stuebner &lt;heiko@sntech.de&gt;
Reviewed-by: Jeff Hugo &lt;jeff.hugo@oss.qualcomm.com&gt;
Signed-off-by: Tomeu Vizoso &lt;tomeu@tomeuvizoso.net&gt;
Signed-off-by: Jeff Hugo &lt;jeff.hugo@oss.qualcomm.com&gt;
Link: https://lore.kernel.org/r/20250721-6-10-rocket-v9-2-77ebd484941e@tomeuvizoso.net
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/amdxdna: Add documentation for AMD NPU accelerator driver</title>
<updated>2024-11-22T18:40:56+00:00</updated>
<author>
<name>Lizhi Hou</name>
<email>lizhi.hou@amd.com</email>
</author>
<published>2024-11-18T17:29:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=cafb2c9c27e3d0c63eae3be71b516e0d40ce2bb3'/>
<id>cafb2c9c27e3d0c63eae3be71b516e0d40ce2bb3</id>
<content type='text'>
AMD NPU (Neural Processing Unit) is a multi-user AI inference accelerator
integrated into AMD client APU. NPU enables efficient execution of Machine
Learning applications like CNN, LLM, etc. NPU is based on AMD XDNA
Architecture. NPU is managed by amdxdna driver.

Co-developed-by: Sonal Santan &lt;sonal.santan@amd.com&gt;
Signed-off-by: Sonal Santan &lt;sonal.santan@amd.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Lizhi Hou &lt;lizhi.hou@amd.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-2-lizhi.hou@amd.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
AMD NPU (Neural Processing Unit) is a multi-user AI inference accelerator
integrated into AMD client APU. NPU enables efficient execution of Machine
Learning applications like CNN, LLM, etc. NPU is based on AMD XDNA
Architecture. NPU is managed by amdxdna driver.

Co-developed-by: Sonal Santan &lt;sonal.santan@amd.com&gt;
Signed-off-by: Sonal Santan &lt;sonal.santan@amd.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Lizhi Hou &lt;lizhi.hou@amd.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-2-lizhi.hou@amd.com
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/qaic: Add AIC080 support</title>
<updated>2024-10-12T20:51:04+00:00</updated>
<author>
<name>Jeffrey Hugo</name>
<email>quic_jhugo@quicinc.com</email>
</author>
<published>2024-10-04T19:52:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=b8128f7815ff135f0333c1b46dcdf1543c41b860'/>
<id>b8128f7815ff135f0333c1b46dcdf1543c41b860</id>
<content type='text'>
Add basic support for the new AIC080 product. The PCIe Device ID is
0xa080. AIC080 is a lower cost, lower performance SKU variant of AIC100.
From the qaic perspective, it is the same as AIC100.

Reviewed-by: Troy Hanson &lt;quic_thanson@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241004195209.3910996-1-quic_jhugo@quicinc.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add basic support for the new AIC080 product. The PCIe Device ID is
0xa080. AIC080 is a lower cost, lower performance SKU variant of AIC100.
From the qaic perspective, it is the same as AIC100.

Reviewed-by: Troy Hanson &lt;quic_thanson@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241004195209.3910996-1-quic_jhugo@quicinc.com
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/qaic: Add ipc_router channel</title>
<updated>2024-10-12T20:49:47+00:00</updated>
<author>
<name>Jeffrey Hugo</name>
<email>quic_jhugo@quicinc.com</email>
</author>
<published>2024-10-04T16:40:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=2af5deb614e7bc9367aadf9105e37c8299120af4'/>
<id>2af5deb614e7bc9367aadf9105e37c8299120af4</id>
<content type='text'>
The ipc_router channel allows AF_QIPCRTR clients and services to
communicate with the AIC100 device. The ipc_router MHI transport layer
expects the channel to be named exactly "IPCR".

Reviewed-by: Carl Vanderlip &lt;quic_carlv@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241004164033.3825986-1-quic_jhugo@quicinc.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The ipc_router channel allows AF_QIPCRTR clients and services to
communicate with the AIC100 device. The ipc_router MHI transport layer
expects the channel to be named exactly "IPCR".

Reviewed-by: Carl Vanderlip &lt;quic_carlv@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241004164033.3825986-1-quic_jhugo@quicinc.com
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel</title>
<updated>2024-09-19T08:18:15+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2024-09-19T08:18:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=de848da12f752170c2ebe114804a985314fd5a6a'/>
<id>de848da12f752170c2ebe114804a985314fd5a6a</id>
<content type='text'>
Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR&lt;-&gt;non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo-&gt;ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR&lt;-&gt;non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo-&gt;ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/qaic: Fix a typo</title>
<updated>2024-09-06T19:01:37+00:00</updated>
<author>
<name>Andrew Kreimer</name>
<email>algonell@gmail.com</email>
</author>
<published>2024-09-06T08:00:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=d895eb31ae563152d398e2584c707d1efe7911ed'/>
<id>d895eb31ae563152d398e2584c707d1efe7911ed</id>
<content type='text'>
Fix a typo in documentation.

Signed-off-by: Andrew Kreimer &lt;algonell@gmail.com&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
Link: https://lore.kernel.org/r/20240906080136.4423-1-algonell@gmail.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix a typo in documentation.

Signed-off-by: Andrew Kreimer &lt;algonell@gmail.com&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
Link: https://lore.kernel.org/r/20240906080136.4423-1-algonell@gmail.com
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/qaic: Remove the description of DRM_IOCTL_QAIC_PART_DEV</title>
<updated>2024-07-26T15:15:42+00:00</updated>
<author>
<name>Zenghui Yu</name>
<email>yuzenghui@huawei.com</email>
</author>
<published>2024-07-16T07:30:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=a887d2c85a3f6af0d99ab0eafbd7a1a83f742cad'/>
<id>a887d2c85a3f6af0d99ab0eafbd7a1a83f742cad</id>
<content type='text'>
The partition device ioctl was removed during the development of the
initial version of qaic driver. Remove its description from the
documentation to avoid confusing readers.

Signed-off-by: Zenghui Yu &lt;yuzenghui@huawei.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240716073036.453-1-yuzenghui@huawei.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The partition device ioctl was removed during the development of the
initial version of qaic driver. Remove its description from the
documentation to avoid confusing readers.

Signed-off-by: Zenghui Yu &lt;yuzenghui@huawei.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240716073036.453-1-yuzenghui@huawei.com
</pre>
</div>
</content>
</entry>
<entry>
<title>docs/accel: correct links to mailing list archives</title>
<updated>2024-01-23T21:45:50+00:00</updated>
<author>
<name>Hu Haowen</name>
<email>2023002089@link.tyut.edu.cn</email>
</author>
<published>2024-01-18T09:01:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=3f0e4df37a1b505307f61fbfa7b1f9a2fa2c40bc'/>
<id>3f0e4df37a1b505307f61fbfa7b1f9a2fa2c40bc</id>
<content type='text'>
Since the mailing archive list lkml.org is obsolete, change the links into
lore.kernel.org's ones.

Signed-off-by: Hu Haowen &lt;2023002089@link.tyut.edu.cn&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
Link: https://lore.kernel.org/r/20240118090140.4868-1-2023002089@link.tyut.edu.cn
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Since the mailing archive list lkml.org is obsolete, change the links into
lore.kernel.org's ones.

Signed-off-by: Hu Haowen &lt;2023002089@link.tyut.edu.cn&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
Link: https://lore.kernel.org/r/20240118090140.4868-1-2023002089@link.tyut.edu.cn
</pre>
</div>
</content>
</entry>
<entry>
<title>accel/qaic: Expand DRM device lifecycle</title>
<updated>2023-12-01T17:37:06+00:00</updated>
<author>
<name>Carl Vanderlip</name>
<email>quic_carlv@quicinc.com</email>
</author>
<published>2023-11-17T17:43:37+00:00</published>
<link rel='alternate' type='text/html' href='https://git.exis.tech/linux.git/commit/?id=5f0a0ebca2b98eeda10715433c7d9418ef2e6d01'/>
<id>5f0a0ebca2b98eeda10715433c7d9418ef2e6d01</id>
<content type='text'>
Currently the QAIC DRM device registers itself when the MHI QAIC_CONTROL
channel becomes available. This is when the device is able to process
workloads. However, the DRM driver also provides the debugfs interface
bootlog for the device. If the device fails to boot to the QSM (which
brings up the MHI QAIC_CONTROL channel), the bootlog won't be available for
debugging why it failed to boot.

Change when the DRM device registers itself from when QAIC_CONTROL is
available to when the card is first probed on the PCI bus. Additionally,
make the DRM driver persist through reset/error cases so the driver
doesn't have to be reloaded to access the card again. Send
KOBJ_ONLINE/OFFLINE uevents so userspace can know when DRM device is
ready to handle requests.

Signed-off-by: Carl Vanderlip &lt;quic_carlv@quicinc.com&gt;
Reviewed-by: Pranjal Ramajor Asha Kanojiya &lt;quic_pkanojiy@quicinc.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20231117174337.20174-3-quic_jhugo@quicinc.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Currently the QAIC DRM device registers itself when the MHI QAIC_CONTROL
channel becomes available. This is when the device is able to process
workloads. However, the DRM driver also provides the debugfs interface
bootlog for the device. If the device fails to boot to the QSM (which
brings up the MHI QAIC_CONTROL channel), the bootlog won't be available for
debugging why it failed to boot.

Change when the DRM device registers itself from when QAIC_CONTROL is
available to when the card is first probed on the PCI bus. Additionally,
make the DRM driver persist through reset/error cases so the driver
doesn't have to be reloaded to access the card again. Send
KOBJ_ONLINE/OFFLINE uevents so userspace can know when DRM device is
ready to handle requests.

Signed-off-by: Carl Vanderlip &lt;quic_carlv@quicinc.com&gt;
Reviewed-by: Pranjal Ramajor Asha Kanojiya &lt;quic_pkanojiy@quicinc.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Signed-off-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20231117174337.20174-3-quic_jhugo@quicinc.com
</pre>
</div>
</content>
</entry>
</feed>
