linux-stable.git/drivers/gpu/drm/amd/amdkfd, branch linux-5.15.y Linux kernel stable tree drm/amdkfd: Fix out-of-bounds write in kfd_event_page_set() 2026-03-04T12:20:34+00:00 Sunday Clement Sunday.Clement@amd.com 2026-02-02T17:41:39+00:00 de8d7a25cd2eb5875b1d8d4fbc7fe4b4138b781f [ Upstream commit 8a70a26c9f34baea6c3199a9862ddaff4554a96d ] The kfd_event_page_set() function writes KFD_SIGNAL_EVENT_LIMIT * 8 bytes via memset without checking the buffer size parameter. This allows unprivileged userspace to trigger an out-of bounds kernel memory write by passing a small buffer, leading to potential privilege escalation. Signed-off-by: Sunday Clement <Sunday.Clement@amd.com> Reviewed-by: Alexander Deucher <Alexander.Deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 8a70a26c9f34baea6c3199a9862ddaff4554a96d ]

The kfd_event_page_set() function writes KFD_SIGNAL_EVENT_LIMIT * 8
bytes via memset without checking the buffer size parameter. This allows
unprivileged userspace to trigger an out-of bounds kernel memory write
by passing a small buffer, leading to  potential privilege
escalation.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Reviewed-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix GART PTE for non-4K pagesize in svm_migrate_gart_map() 2026-03-04T12:20:04+00:00 Donet Tom donettom@linux.ibm.com 2026-01-12T14:06:56+00:00 f533cb04aed9e81b716470c4b462a219b08da59d [ Upstream commit 6c160001661b6c4e20f5c31909c722741e14c2d8 ] In svm_migrate_gart_map(), while migrating GART mapping, the number of bytes copied for the GART table only accounts for CPU pages. On non-4K systems, each CPU page can contain multiple GPU pages, and the GART requires one 8-byte PTE per GPU page. As a result, an incorrect size was passed to the DMA, causing only a partial update of the GART table. Fix this function to work correctly on non-4K page-size systems by accounting for the number of GPU pages per CPU page when calculating the number of bytes to be copied. Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com> Signed-off-by: Donet Tom <donettom@linux.ibm.com> Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 6c160001661b6c4e20f5c31909c722741e14c2d8 ]

In svm_migrate_gart_map(), while migrating GART mapping, the number of
bytes copied for the GART table only accounts for CPU pages. On non-4K
systems, each CPU page can contain multiple GPU pages, and the GART
requires one 8-byte PTE per GPU page. As a result, an incorrect size was
passed to the DMA, causing only a partial update of the GART table.

Fix this function to work correctly on non-4K page-size systems by
accounting for the number of GPU pages per CPU page when calculating the
number of bytes to be copied.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: fix a memory leak in device_queue_manager_init() 2026-02-06T15:42:05+00:00 Haoxiang Li lihaoxiang@isrc.iscas.ac.cn 2026-01-08T07:18:22+00:00 e11e8a29b304c76734efc3a267d75b23ba7bf0c0 commit 80614c509810fc051312d1a7ccac8d0012d6b8d0 upstream. If dqm->ops.initialize() fails, add deallocate_hiq_sdma_mqd() to release the memory allocated by allocate_hiq_sdma_mqd(). Move deallocate_hiq_sdma_mqd() up to ensure proper function visibility at the point of use. Fixes: 11614c36bc8f ("drm/amdkfd: Allocate MQD trunk for HIQ and SDMA") Signed-off-by: Haoxiang Li <lihaoxiang@isrc.iscas.ac.cn> Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit b7cccc8286bb9919a0952c812872da1dcfe9d390) Cc: stable@vger.kernel.org Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 80614c509810fc051312d1a7ccac8d0012d6b8d0 upstream.

If dqm->ops.initialize() fails, add deallocate_hiq_sdma_mqd()
to release the memory allocated by allocate_hiq_sdma_mqd().
Move deallocate_hiq_sdma_mqd() up to ensure proper function
visibility at the point of use.

Fixes: 11614c36bc8f ("drm/amdkfd: Allocate MQD trunk for HIQ and SDMA")
Signed-off-by: Haoxiang Li <lihaoxiang@isrc.iscas.ac.cn>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b7cccc8286bb9919a0952c812872da1dcfe9d390)
Cc: stable@vger.kernel.org
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdkfd: Tie UNMAP_LATENCY to queue_preemption 2025-12-06T21:09:20+00:00 Amber Lin Amber.Lin@amd.com 2025-08-15T18:04:15+00:00 b751b7f87acb5e6155ed80472680aedfd184420a [ Upstream commit f3820e9d356132e18405cd7606e22dc87ccfa6d1 ] When KFD asks CP to preempt queues, other than preempt CP queues, CP also requests SDMA to preempt SDMA queues with UNMAP_LATENCY timeout. Currently queue_preemption_timeout_ms is 9000 ms by default but can be configured via module parameter. KFD_UNMAP_LATENCY_MS is hard coded as 4000 ms though. This patch ties KFD_UNMAP_LATENCY_MS to queue_preemption_timeout_ms so in a slow system such as emulator, both CP and SDMA slowness are taken into account. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit f3820e9d356132e18405cd7606e22dc87ccfa6d1 ]

When KFD asks CP to preempt queues, other than preempt CP queues, CP
also requests SDMA to preempt SDMA queues with UNMAP_LATENCY timeout.
Currently queue_preemption_timeout_ms is 9000 ms by default but can be
configured via module parameter. KFD_UNMAP_LATENCY_MS is hard coded as
4000 ms though. This patch ties KFD_UNMAP_LATENCY_MS to
queue_preemption_timeout_ms so in a slow system such as emulator, both
CP and SDMA slowness are taken into account.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: return -ENOTTY for unsupported IOCTLs 2025-12-06T21:09:18+00:00 Geoffrey McRae geoffrey.mcrae@amd.com 2025-07-08T03:53:40+00:00 556da285679893a37c5935a5cccc13c316d6ce2a [ Upstream commit 57af162bfc8c05332a28c4d458d246cc46d2746d ] Some kfd ioctls may not be available depending on the kernel version the user is running, as such we need to report -ENOTTY so userland can determine the cause of the ioctl failure. Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 57af162bfc8c05332a28c4d458d246cc46d2746d ]

Some kfd ioctls may not be available depending on the kernel version the
user is running, as such we need to report -ENOTTY so userland can
determine the cause of the ioctl failure.

Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix error code sign for EINVAL in svm_ioctl() 2025-10-19T14:21:33+00:00 Qianfeng Rong rongqianfeng@vivo.com 2025-09-04T12:36:46+00:00 650368aacbc78eb459a20ef9755ec5fe2115499d [ Upstream commit cbda64f3f58027f68211dda8ea94d52d7e493995 ] Use negative error code -EINVAL instead of positive EINVAL in the default case of svm_ioctl() to conform to Linux kernel error code conventions. Fixes: 42de677f7999 ("drm/amdkfd: register svm range") Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit cbda64f3f58027f68211dda8ea94d52d7e493995 ]

Use negative error code -EINVAL instead of positive EINVAL in the default
case of svm_ioctl() to conform to Linux kernel error code conventions.

Fixes: 42de677f7999 ("drm/amdkfd: register svm range")
Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix race in GWS queue scheduling 2025-07-10T13:57:40+00:00 Jay Cornwall jay.cornwall@amd.com 2025-06-11T14:52:14+00:00 105b0a0c7e651dd2c7bd334ca804780dc24683f1 commit cfb05257ae168a0496c7637e1d9e3ab8a25cbffe upstream. q->gws is not updated atomically with qpd->mapped_gws_queue. If a runlist is created between pqm_set_gws and update_queue it will contain a queue which uses GWS in a process with no GWS allocated. This will result in a scheduler hang. Use q->properties.is_gws which is changed while holding the DQM lock. Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit b98370220eb3110e82248e3354e16a489a492cfb) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit cfb05257ae168a0496c7637e1d9e3ab8a25cbffe upstream.

q->gws is not updated atomically with qpd->mapped_gws_queue. If a
runlist is created between pqm_set_gws and update_queue it will
contain a queue which uses GWS in a process with no GWS allocated.
This will result in a scheduler hang.

Use q->properties.is_gws which is changed while holding the DQM lock.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b98370220eb3110e82248e3354e16a489a492cfb)
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdkfd: Set SDMA_RLCx_IB_CNTL/SWITCH_INSIDE_IB 2025-06-27T10:05:30+00:00 Amber Lin Amber.Lin@amd.com 2025-04-22T19:54:19+00:00 ba5026e805cb7a7c37ad38d9e1c34ddd0a96787f [ Upstream commit ab9fcc6362e0699fc1150aa1d8503c40fce2c1e1 ] When submitting MQD to CP, set SDMA_RLCx_IB_CNTL/SWITCH_INSIDE_IB bit so it'll allow SDMA preemption if there is a massive command buffer of long-running SDMA commands. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit ab9fcc6362e0699fc1150aa1d8503c40fce2c1e1 ]

When submitting MQD to CP, set SDMA_RLCx_IB_CNTL/SWITCH_INSIDE_IB bit so
it'll allow SDMA preemption if there is a massive command buffer of
long-running SDMA commands.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: KFD release_work possible circular locking 2025-06-04T12:38:00+00:00 Philip Yang Philip.Yang@amd.com 2025-02-18T01:08:29+00:00 cfc5a07f9330b55972e5fbc06c2f9f126b8e1436 [ Upstream commit 1b9366c601039d60546794c63fbb83ce8e53b978 ] If waiting for gpu reset done in KFD release_work, thers is WARNING: possible circular locking dependency detected #2 kfd_create_process kfd_process_mutex flush kfd release work #1 kfd release work wait for amdgpu reset work #0 amdgpu_device_gpu_reset kgd2kfd_pre_reset kfd_process_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&p->release_work)); lock((wq_completion)kfd_process_wq); lock((work_completion)(&p->release_work)); lock((wq_completion)amdgpu-reset-dev); To fix this, KFD create process move flush release work outside kfd_process_mutex. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 1b9366c601039d60546794c63fbb83ce8e53b978 ]

If waiting for gpu reset done in KFD release_work, thers is WARNING:
possible circular locking dependency detected

  #2  kfd_create_process
        kfd_process_mutex
          flush kfd release work

  #1  kfd release work
        wait for amdgpu reset work

  #0  amdgpu_device_gpu_reset
        kgd2kfd_pre_reset
          kfd_process_mutex

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock((work_completion)(&p->release_work));
                  lock((wq_completion)kfd_process_wq);
                  lock((work_completion)(&p->release_work));
   lock((wq_completion)amdgpu-reset-dev);

To fix this, KFD create process move flush release work outside
kfd_process_mutex.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix pqm_destroy_queue race with GPU reset 2025-05-02T05:43:57+00:00 Philip Yang Philip.Yang@amd.com 2025-02-20T21:02:13+00:00 25c299517d58c803659f0af538136037fbfa48c0 [ Upstream commit 7919b4cad5545ed93778f11881ceee72e4dbed66 ] If GPU in reset, destroy_queue return -EIO, pqm_destroy_queue should delete the queue from process_queue_list and free the resource. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 7919b4cad5545ed93778f11881ceee72e4dbed66 ]

If GPU in reset, destroy_queue return -EIO, pqm_destroy_queue should
delete the queue from process_queue_list and free the resource.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>