user/sven/linux.git/drivers/gpu/drm/amd/amdkfd, branch v6.11.8Linux Kernel
https://git.stealer.net/cgit.cgi/user/sven/linux.git/atom?h=v6.11.82024-10-17T13:26:56Zdrm/amdkfd: Fix an eviction fence leak2024-10-17T13:26:56ZLang Yulang.yu@amd.com2024-09-27T10:27:46Zurn:sha1:ef1f315a1ed50a29d13e9c6ff295596a990c3b90
commit d7d7b947a4fa6d0a82ff2bf0db413edc63738e3a upstream.
Only creating a new reference for each process instead of each VM.
Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs")
Suggested-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Lang Yu <lang.yu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5fa436289483ae56427b0896c31f72361223c758)
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdkfd: Check int source id for utcl2 poison event2024-10-10T10:03:37ZHawking ZhangHawking.Zhang@amd.com2024-08-20T05:56:32Zurn:sha1:d2bf81c38d79bdd82a1be513e22a314c6ac16f0a
[ Upstream commit db6341a9168d2a24ded526277eeab29724d76e9d ]
Traditional utcl2 fault_status polling does not
work in SRIOV environment. The polling of fault
status register from guest side will be dropped
by hardware.
Driver should switch to check utcl2 interrupt
source id to identify utcl2 poison event. It is
set to 1 when poisoned data interrupts are
signaled.
v2: drop the unused local variable (Tao)
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix resource leak in criu restore queue2024-10-10T10:03:30ZJesse Zhangjesse.zhang@amd.com2024-09-06T03:29:55Zurn:sha1:a5370f339c64aa88dfee43e7e8d85a0a40aeb350
[ Upstream commit aa47fe8d3595365a935921a90d00bc33ee374728 ]
To avoid memory leaks, release q_extra_data when exiting the restore queue.
v2: Correct the proto (Alex)
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Tim Huang <tim.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: amdkfd_free_gtt_mem clear the correct pointer2024-10-10T10:03:24ZPhilip YangPhilip.Yang@amd.com2024-07-14T15:11:05Zurn:sha1:6c9289806591807e4e3be9a23df8ee2069180055
[ Upstream commit c86ad39140bbcb9dc75a10046c2221f657e8083b ]
Pass pointer reference to amdgpu_bo_unref to clear the correct pointer,
otherwise amdgpu_bo_unref clear the local variable, the original pointer
not set to NULL, this could cause use-after-free bug.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Add SDMA queue quantum support for GFX122024-10-04T14:38:34ZSreekant Somasekharansreekant.somasekharan@amd.com2024-09-20T05:53:17Zurn:sha1:5a76fd0410881fa6d4d410664a0273b1fbbc7ea8
commit d52ac79053a2f3eba04c1e7b56334df84d1d289f upstream.
program SDMAx_QUEUEx_SCHEDULE_CNTL for context switch due to
quantum in KFD for GFX12.
Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.11.x
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdkfd: Add cache line size info2024-09-10T20:15:16ZDavid Belangerdavid.belanger@amd.com2024-08-23T17:50:03Zurn:sha1:02c132166993c8f8ca1b319665181f72f22ebc6b
Populate cache line size info in topology based on information from IP
discovery table.
Signed-off-by: David Belanger <david.belanger@amd.com>
Reviewed-by: Sreekant Somasekharan <Sreekant.Somasekharan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4e9fadacddca96a2e6fcee9cc9488b78eb7a6953)
drm/amdgpu/gfx12: set UNORD_DISPATCH in compute MQDs2024-08-28T14:04:53ZAlex Deucheralexander.deucher@amd.com2024-08-20T17:11:22Zurn:sha1:959fc102ff4c39f5ab021da311c2cfd1d5602a0c
This needs to be set to 1 to avoid a potential deadlock in
the GC 10.x and newer. On GC 9.x and older, this needs
to be set to 0. This can lead to hangs in some mixed
graphics and compute workloads.
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3575
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 40318a2406bd426c6f4591269669c04e8eda571d)
drm/amdgpu: set CP_HQD_PQ_DOORBELL_CONTROL.DOORBELL_MODE to 12024-07-08T20:56:27ZZhigang LuoZhigang.Luo@amd.com2024-06-25T17:53:56Zurn:sha1:ee98fb71baa8728156b4d75740f82cb0cfe6d923
to avoid reading wrong WPTR from doorbell in sriov vf, set
CP_HQD_PQ_DOORBELL_CONTROL.DOORBELL_MODE to 1 to read WPTR from MQD.
Signed-off-by: Zhigang Luo <Zhigang.Luo@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: add ras POSION_CONSUMPTION event id support2024-07-08T20:55:37ZYang Wangkevinyang.wang@amd.com2024-06-28T08:24:39Zurn:sha1:12b435a40cb5b05378ca244a9d524b125b0c1f6d
add amdgpu ras POSION_CONSUMPTION event id support.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Use mode1 reset for GFX v9.4.42024-07-08T20:55:26ZStanley.YangStanley.Yang@amd.com2024-07-03T07:34:35Zurn:sha1:91ba536ead3ad86952979b1944cf3b612a7f944a
GFX v9.4.4 uses mode1 reset to handle poison consumption.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>