kernel/linux.git/drivers/gpu/drm/amd/amdkfd, branch v6.6.132

drm/amdkfd: Fix out-of-bounds write in kfd_event_page_set()

2026-03-04T12:21:15+00:00

[ 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 Reviewed-by: Alexander Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin

drm/amdkfd: Fix GART PTE for non-4K pagesize in svm_migrate_gart_map()

2026-03-04T12:20:40+00:00

[ 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 Reviewed-by: Philip Yang Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Donet Tom Signed-off-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Fix watch_id bounds checking in debug address watch v2

2026-03-04T12:20:26+00:00

[ Upstream commit 5a19302cab5cec7ae7f1a60c619951e6c17d8742 ] The address watch clear code receives watch_id as an unsigned value (u32), but some helper functions were using a signed int and checked bits by shifting with watch_id. If a very large watch_id is passed from userspace, it can be converted to a negative value. This can cause invalid shifts and may access memory outside the watch_points array. drm/amdkfd: Fix watch_id bounds checking in debug address watch v2 Fix this by checking that watch_id is within MAX_WATCH_ADDRESSES before using it. Also use BIT(watch_id) to test and clear bits safely. This keeps the behavior unchanged for valid watch IDs and avoids undefined behavior for invalid ones. Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_debug.c:448 kfd_dbg_trap_clear_dev_address_watch() error: buffer overflow 'pdd->watch_points' 4 <= u32max user_rl='0-3,2147483648-u32max' uncapped drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_debug.c 433 int kfd_dbg_trap_clear_dev_address_watch(struct kfd_process_device *pdd, 434 uint32_t watch_id) 435 { 436 int r; 437 438 if (!kfd_dbg_owns_dev_watch_id(pdd, watch_id)) kfd_dbg_owns_dev_watch_id() doesn't check for negative values so if watch_id is larger than INT_MAX it leads to a buffer overflow. (Negative shifts are undefined). 439 return -EINVAL; 440 441 if (!pdd->dev->kfd->shared_resources.enable_mes) { 442 r = debug_lock_and_unmap(pdd->dev->dqm); 443 if (r) 444 return r; 445 } 446 447 amdgpu_gfx_off_ctrl(pdd->dev->adev, false); --> 448 pdd->watch_points[watch_id] = pdd->dev->kfd2kgd->clear_address_watch( 449 pdd->dev->adev, 450 watch_id); v2: (as per, Jonathan Kim) - Add early watch_id >= MAX_WATCH_ADDRESSES validation in the set path to match the clear path. - Drop the redundant bounds check in kfd_dbg_owns_dev_watch_id(). Fixes: e0f85f4690d0 ("drm/amdkfd: add debug set and clear address watch points operation") Reported-by: Dan Carpenter Cc: Jonathan Kim Cc: Felix Kuehling Cc: Alex Deucher Cc: Christian König Signed-off-by: Srinivasan Shanmugam Reviewed-by: Jonathan Kim Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix debug watchpoints for logical devices

2026-03-04T12:20:26+00:00

[ Upstream commit b41a382932263b2951bc9e83a22168d579a94865 ] The number of watchpoints should be set and constrained per logical partition device, not by the socket device. Signed-off-by: Jonathan Kim Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher Stable-dep-of: 5a19302cab5c ("drm/amdkfd: Fix watch_id bounds checking in debug address watch v2") Signed-off-by: Sasha Levin

drm/amdkfd: fix a memory leak in device_queue_manager_init()

2026-01-30T09:27:29+00:00

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 Signed-off-by: Felix Kuehling Reviewed-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher (cherry picked from commit b7cccc8286bb9919a0952c812872da1dcfe9d390) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

amd/amdkfd: resolve a race in amdgpu_amdkfd_device_fini_sw

2025-11-24T09:29:44+00:00

[ Upstream commit 99d7181bca34e96fbf61bdb6844918bdd4df2814 ] There is race in amdgpu_amdkfd_device_fini_sw and interrupt. if amdgpu_amdkfd_device_fini_sw run in b/w kfd_cleanup_nodes and kfree(kfd), and KGD interrupt generated. kernel panic log: BUG: kernel NULL pointer dereference, address: 0000000000000098 amdgpu 0000:c8:00.0: amdgpu: Requesting 4 partitions through PSP PGD d78c68067 P4D d78c68067 kfd kfd: amdgpu: Allocated 3969056 bytes on gart PUD 1465b8067 PMD @ Oops: @002 [#1] SMP NOPTI kfd kfd: amdgpu: Total number of KFD nodes to be created: 4 CPU: 115 PID: @ Comm: swapper/115 Kdump: loaded Tainted: G S W OE K RIP: 0010:_raw_spin_lock_irqsave+0x12/0x40 Code: 89 e@ 41 5c c3 cc cc cc cc 66 66 2e Of 1f 84 00 00 00 00 00 OF 1f 40 00 Of 1f 44% 00 00 41 54 9c 41 5c fa 31 cO ba 01 00 00 00 OF b1 17 75 Ba 4c 89 e@ 41 Sc 89 c6 e8 07 38 5d RSP: 0018: ffffc90@1a6b0e28 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000018 0000000000000001 RSI: ffff8883bb623e00 RDI: 0000000000000098 ffff8883bb000000 RO8: ffff888100055020 ROO: ffff888100055020 0000000000000000 R11: 0000000000000000 R12: 0900000000000002 ffff888F2b97da0@ R14: @000000000000098 R15: ffff8883babdfo00 CS: 010 DS: 0000 ES: 0000 CRO: 0000000080050033 CR2: 0000000000000098 CR3: 0000000e7cae2006 CR4: 0000000002770ce0 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 0000000000000000 DR6: 00000000fffeO7FO DR7: 0000000000000400 PKRU: 55555554 Call Trace: kgd2kfd_interrupt+@x6b/0x1f@ [amdgpu] ? amdgpu_fence_process+0xa4/0x150 [amdgpu] kfd kfd: amdgpu: Node: 0, interrupt_bitmap: 3 YcpxFl Rant tErace amdgpu_irq_dispatch+0x165/0x210 [amdgpu] amdgpu_ih_process+0x80/0x100 [amdgpu] amdgpu: Virtual CRAT table created for GPU amdgpu_irq_handler+0x1f/@x60 [amdgpu] __handle_irq_event_percpu+0x3d/0x170 amdgpu: Topology: Add dGPU node [0x74a2:0x1002] handle_irq_event+0x5a/@xcO handle_edge_irq+0x93/0x240 kfd kfd: amdgpu: KFD node 1 partition @ size 49148M asm_call_irq_on_stack+0xf/@x20 common_interrupt+0xb3/0x130 asm_common_interrupt+0x1le/0x40 5.10.134-010.a1i5000.a18.x86_64 #1 Signed-off-by: Yifan Zhang Reviewed-by: Philip Yang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdgpu: Allow kfd CRIU with no buffer objects

2025-11-24T09:29:32+00:00

[ Upstream commit 85705b18ae7674347f8675f64b2b3115fb1d5629 ] The kfd CRIU checkpoint ioctl would return an error if trying to checkpoint a process with no kfd buffer objects. This is a normal case and should not be an error. Reviewed-by: Felix Kuehling Signed-off-by: David Francis Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Tie UNMAP_LATENCY to queue_preemption

2025-11-24T09:29:30+00:00

[ 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 Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix vram allocation failure for a special case

2025-11-24T09:29:30+00:00

[ Upstream commit 93aa919ca05bec544b17ee9a1bfe394ce6c94bd8 ] When it only allocates vram without va, which is 0, and a SVM range allocated stays in this range, the vram allocation returns failure. It should be skipped for this case from SVM usage check. Signed-off-by: Eric Huang Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Handle lack of READ permissions in SVM mapping

2025-11-24T09:29:28+00:00

[ Upstream commit 0ed704d058cec7643a716a21888d58c7d03f2c3e ] HMM assumes that pages have READ permissions by default. Inside svm_range_validate_and_map, we add READ permissions then add WRITE permissions if the VMA isn't read-only. This will conflict with regions that only have PROT_WRITE or have PROT_NONE. When that happens, svm_range_restore_work will continue to retry, silently, giving the impression of a hang if pr_debug isn't enabled to show the retries.. If pages don't have READ permissions, simply unmap them and continue. If they weren't mapped in the first place, this would be a no-op. Since x86 doesn't support write-only, and PROT_NONE doesn't allow reads or writes anyways, this will allow the svm range validation to continue without getting stuck in a loop forever on mappings we can't use with HMM. Signed-off-by: Kent Russell Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin