linux-next.git/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c, branch masterLinux kernel latest sourcehttp://mirrors.hust.edu.cn/git/linux-next.git/atom?h=master2026-06-17T20:22:02+00:00drm/amdgpu: Add gfx12.0.1 adev to queue reset support2026-06-17T20:22:02+00:00Amber LinAmber.Lin@amd.com2026-06-14T16:15:12+00:00urn:sha1:b54bf09ee083bdcf323321971d8d76d45701517c
This patch adds the inclusion of gfx12.0.1 by checking GC's major number
and minor number equal to 12.0.* with the same mes_sched version.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Expand MES queue/pipe reset support2026-06-17T19:51:36+00:00Amber LinAmber.Lin@amd.com2026-05-06T19:02:35+00:00urn:sha1:c847c557bba84edb3286549aee18cf3a34182e08
MES in newer versions on gfx11 and gfx12 can support queue/pipe reset via
MES.
v2: update the fw version check (Jesse)
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/gfx: add a common helper to handle MES compute resets2026-06-17T19:51:35+00:00Alex Deucheralexander.deucher@amd.com2026-05-07T16:03:47+00:00urn:sha1:e49044061b37cc4be99bfd17f6ccdd3509300469
Add helpers to handle MES compute queue resets when multiple queues
are affected. Can you be used by both KGD and KFD.
v2: sqaush in updates
v3: squash in userq updates
Co-developed-by: Jesse Zhang <jesse.zhang@amd.com>
Co-developed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Allocate enough space for hpd info on gfx112026-06-17T19:51:34+00:00Amber LinAmber.Lin@amd.com2026-05-06T19:02:35+00:00urn:sha1:fe5dfb55dd70eed75d5f8f50657334f03c71deef
MES in newer versions on gfx11 and gfx12 can support queue/pipe
reset via MES.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/mes: add a MMIO queue reset helper2026-06-17T19:51:34+00:00Alex Deucheralexander.deucher@amd.com2026-05-14T19:39:36+00:00urn:sha1:51fe463018a311083195f95b3e4067f4b3833065
Will be used by KFD for MMIO based resets.
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/mes: add userq reset helper2026-06-17T19:51:34+00:00Alex Deucheralexander.deucher@amd.com2026-04-30T16:00:26+00:00urn:sha1:b83490ad9845a7f9c1e91e9c076249bcfb745cfe
Implement a userq reset helper using the doorbell
index.
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: compare MES firmware version ucode for gfx112026-06-04T19:25:46+00:00Sunil Khatrisunil.khatri@amd.com2026-06-01T14:41:17+00:00urn:sha1:dd7bd8e0f0c47361a3a513d6aa8ea2b36dd70deb
MES firmware should report the same version whether read from
the register or from the firmware ucode binary. This is not
always the case, so add a log when they mismatch.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Support MES suspend_all_sdma_gangs2026-05-18T22:13:42+00:00Amber LinAmber.Lin@amd.com2026-03-23T18:19:04+00:00urn:sha1:36c063e72fc2a53c02a4d96e81a14fef433a3948
suspend_all_sdma_gangs is supported in new MES firmware for gfx 12.1
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michael Chen<michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Reset queue/pipe in MES2026-04-28T18:46:00+00:00Amber LinAmber.Lin@amd.com2026-03-13T10:08:40+00:00urn:sha1:eed95012c71ad887b3b524325c23dcbb1b6c16be
When removing queues fails, KFD calls amdgpu_mes to detect and reset
hung queues, then cleans up those hung queues in KFD.
Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Missing multi-XCC support in MES2026-04-28T18:42:36+00:00Amber LinAmber.Lin@amd.com2026-03-19T21:50:52+00:00urn:sha1:ef94439908c9ccb4d856c99a102fd2a0b1ea1662
In a multi-XCC GPU, pass the master XCC's ID to amdgpu_mes_suspend,
amdgpu_mes_resume, and detect_and_reset_hung_queues so the command will be
sent to the matching master MES when the compute partition mode is not
SPX.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>