linux-stable.git/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c, branch linux-6.16.y Linux kernel stable tree Revert "drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini" 2025-08-15T14:38:44+00:00 Vitaly Prosyak vitaly.prosyak@amd.com 2025-06-24T16:05:10+00:00 585d65ce3c4de6ea6521d0eb4b285b3bb0f75380 [ Upstream commit a73345b866ff8bbd93135af667c973a8fb4b2c40 ] This reverts commit 5fb90421fa0fbe0a968274912101fe917bf1c47b. The original patch moved `amdgpu_userq_mgr_fini()` to the driver's `postclose` callback, which is called after `drm_gem_release()` in the DRM file cleanup sequence.If a user application crashes or aborts without cleaning up its user queues, 'drm_gem_release()` may free GEM objects that are still referenced by active user queues, leading to use-after-free. By reverting, we ensure that user queues are disabled and cleaned up before any GEM objects are released, preventing this class of bug. However, this reintroduces a race during PCI hot-unplug, where device removal can race with per-file cleanup, leading to use-after-free in suspend/unplug paths. This will be fixed in the next patch. Fixes: 5fb90421fa0f ("drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini+0x70c") Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit a73345b866ff8bbd93135af667c973a8fb4b2c40 ]

This reverts commit 5fb90421fa0fbe0a968274912101fe917bf1c47b.

The original patch moved `amdgpu_userq_mgr_fini()` to the driver's
`postclose` callback, which is called after `drm_gem_release()` in
the DRM file cleanup sequence.If a user application crashes or aborts
without cleaning up its user queues, 'drm_gem_release()` may free
GEM objects that are still referenced by active user queues, leading
to use-after-free. By reverting, we ensure that user queues are
disabled and cleaned up before any GEM objects are released,
preventing this class of bug. However, this reintroduces a race
during PCI hot-unplug, where device removal can race with per-file
cleanup, leading to use-after-free in suspend/unplug paths.
This will be fixed in the next patch.

Fixes: 5fb90421fa0f ("drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini+0x70c")
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-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/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini+0x70c 2025-08-15T14:38:40+00:00 Vitaly Prosyak vitaly.prosyak@amd.com 2025-06-18T23:35:21+00:00 f2997cef6d4056cb1b62190f1cf06e8dd19e228f [ Upstream commit 5fb90421fa0fbe0a968274912101fe917bf1c47b ] The issue was reproduced on NV10 using IGT pci_unplug test. It is expected that `amdgpu_driver_postclose_kms()` is called prior to `amdgpu_drm_release()`. However, the bug is that `amdgpu_fpriv` was freed in `amdgpu_driver_postclose_kms()`, and then later accessed in `amdgpu_drm_release()` via a call to `amdgpu_userq_mgr_fini()`. As a result, KASAN detected a use-after-free condition, as shown in the log below. The proposed fix is to move the calls to `amdgpu_eviction_fence_destroy()` and `amdgpu_userq_mgr_fini()` into `amdgpu_driver_postclose_kms()`, so they are invoked before `amdgpu_fpriv` is freed. This also ensures symmetry with the initialization path in `amdgpu_driver_open_kms()`, where the following components are initialized: - `amdgpu_userq_mgr_init()` - `amdgpu_eviction_fence_init()` - `amdgpu_ctx_mgr_init()` Correspondingly, in `amdgpu_driver_postclose_kms()` we should clean up using: - `amdgpu_userq_mgr_fini()` - `amdgpu_eviction_fence_destroy()` - `amdgpu_ctx_mgr_fini()` This change eliminates the use-after-free and improves consistency in resource management between open and close paths. [ +0.094367] ================================================================== [ +0.000026] BUG: KASAN: slab-use-after-free in amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu] [ +0.000866] Write of size 8 at addr ffff88811c068c60 by task amd_pci_unplug/1737 [ +0.000026] CPU: 3 UID: 0 PID: 1737 Comm: amd_pci_unplug Not tainted 6.14.0+ #2 [ +0.000008] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.000004] Call Trace: [ +0.000004] <TASK> [ +0.000003] dump_stack_lvl+0x76/0xa0 [ +0.000010] print_report+0xce/0x600 [ +0.000009] ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu] [ +0.000790] ? srso_return_thunk+0x5/0x5f [ +0.000007] ? kasan_complete_mode_report_info+0x76/0x200 [ +0.000008] ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu] [ +0.000684] kasan_report+0xbe/0x110 [ +0.000007] ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu] [ +0.000601] __asan_report_store8_noabort+0x17/0x30 [ +0.000007] amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu] [ +0.000801] ? __pfx_amdgpu_userq_mgr_fini+0x10/0x10 [amdgpu] [ +0.000819] ? srso_return_thunk+0x5/0x5f [ +0.000008] amdgpu_drm_release+0xa3/0xe0 [amdgpu] [ +0.000604] __fput+0x354/0xa90 [ +0.000010] __fput_sync+0x59/0x80 [ +0.000005] __x64_sys_close+0x7d/0xe0 [ +0.000006] x64_sys_call+0x2505/0x26f0 [ +0.000006] do_syscall_64+0x7c/0x170 [ +0.000004] ? kasan_record_aux_stack+0xae/0xd0 [ +0.000005] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? kmem_cache_free+0x398/0x580 [ +0.000006] ? __fput+0x543/0xa90 [ +0.000006] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? __fput+0x543/0xa90 [ +0.000004] ? __kasan_check_read+0x11/0x20 [ +0.000007] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? __kasan_check_read+0x11/0x20 [ +0.000003] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? fpregs_assert_state_consistent+0x21/0xb0 [ +0.000006] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? syscall_exit_to_user_mode+0x4e/0x240 [ +0.000005] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? do_syscall_64+0x88/0x170 [ +0.000003] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? do_syscall_64+0x88/0x170 [ +0.000004] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? irqentry_exit+0x43/0x50 [ +0.000004] ? srso_return_thunk+0x5/0x5f [ +0.000004] ? exc_page_fault+0x7c/0x110 [ +0.000006] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ +0.000005] RIP: 0033:0x7ffff7b14f67 [ +0.000005] Code: ff e8 0d 16 02 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 73 ba f7 ff [ +0.000004] RSP: 002b:00007fffffffe358 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 [ +0.000006] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffff7b14f67 [ +0.000003] RDX: 0000000000000000 RSI: 00007ffff7f5755a RDI: 0000000000000003 [ +0.000003] RBP: 00007fffffffe380 R08: 0000555555568170 R09: 0000000000000000 [ +0.000003] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffffffe5c8 [ +0.000003] R13: 00005555555552a9 R14: 0000555555557d48 R15: 00007ffff7ffd040 [ +0.000007] </TASK> [ +0.000286] Allocated by task 425 on cpu 11 at 29.751192s: [ +0.000013] kasan_save_stack+0x28/0x60 [ +0.000008] kasan_save_track+0x18/0x70 [ +0.000006] kasan_save_alloc_info+0x38/0x60 [ +0.000006] __kasan_kmalloc+0xc1/0xd0 [ +0.000005] __kmalloc_cache_noprof+0x1bd/0x430 [ +0.000006] amdgpu_driver_open_kms+0x172/0x760 [amdgpu] [ +0.000521] drm_file_alloc+0x569/0x9a0 [ +0.000008] drm_client_init+0x1b7/0x410 [ +0.000007] drm_fbdev_client_setup+0x174/0x470 [ +0.000007] drm_client_setup+0x8a/0xf0 [ +0.000006] amdgpu_pci_probe+0x50b/0x10d0 [amdgpu] [ +0.000482] local_pci_probe+0xe7/0x1b0 [ +0.000008] pci_device_probe+0x5bf/0x890 [ +0.000005] really_probe+0x1fd/0x950 [ +0.000007] __driver_probe_device+0x307/0x410 [ +0.000005] driver_probe_device+0x4e/0x150 [ +0.000006] __driver_attach+0x223/0x510 [ +0.000005] bus_for_each_dev+0x102/0x1a0 [ +0.000006] driver_attach+0x3d/0x60 [ +0.000005] bus_add_driver+0x309/0x650 [ +0.000005] driver_register+0x13d/0x490 [ +0.000006] __pci_register_driver+0x1ee/0x2b0 [ +0.000006] xfrm_ealg_get_byidx+0x43/0x50 [xfrm_algo] [ +0.000008] do_one_initcall+0x9c/0x3e0 [ +0.000007] do_init_module+0x29e/0x7f0 [ +0.000006] load_module+0x5c75/0x7c80 [ +0.000006] init_module_from_file+0x106/0x180 [ +0.000007] idempotent_init_module+0x377/0x740 [ +0.000006] __x64_sys_finit_module+0xd7/0x180 [ +0.000006] x64_sys_call+0x1f0b/0x26f0 [ +0.000006] do_syscall_64+0x7c/0x170 [ +0.000005] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ +0.000013] Freed by task 1737 on cpu 9 at 76.455063s: [ +0.000010] kasan_save_stack+0x28/0x60 [ +0.000006] kasan_save_track+0x18/0x70 [ +0.000005] kasan_save_free_info+0x3b/0x60 [ +0.000006] __kasan_slab_free+0x54/0x80 [ +0.000005] kfree+0x127/0x470 [ +0.000006] amdgpu_driver_postclose_kms+0x455/0x760 [amdgpu] [ +0.000485] drm_file_free.part.0+0x5b1/0xba0 [ +0.000007] drm_file_free+0x13/0x30 [ +0.000006] drm_client_release+0x1c4/0x2b0 [ +0.000006] drm_fbdev_ttm_fb_destroy+0xd2/0x120 [drm_ttm_helper] [ +0.000007] put_fb_info+0x97/0xe0 [ +0.000006] unregister_framebuffer+0x197/0x380 [ +0.000005] drm_fb_helper_unregister_info+0x94/0x100 [ +0.000005] drm_fbdev_client_unregister+0x3c/0x80 [ +0.000007] drm_client_dev_unregister+0x144/0x330 [ +0.000006] drm_dev_unregister+0x49/0x1b0 [ +0.000006] drm_dev_unplug+0x4c/0xd0 [ +0.000006] amdgpu_pci_remove+0x58/0x130 [amdgpu] [ +0.000482] pci_device_remove+0xae/0x1e0 [ +0.000006] device_remove+0xc7/0x180 [ +0.000006] device_release_driver_internal+0x3d4/0x5a0 [ +0.000007] device_release_driver+0x12/0x20 [ +0.000006] pci_stop_bus_device+0x104/0x150 [ +0.000006] pci_stop_and_remove_bus_device_locked+0x1b/0x40 [ +0.000005] remove_store+0xd7/0xf0 [ +0.000007] dev_attr_store+0x3f/0x80 [ +0.000006] sysfs_kf_write+0x125/0x1d0 [ +0.000005] kernfs_fop_write_iter+0x2ea/0x490 [ +0.000007] vfs_write+0x90d/0xe70 [ +0.000006] ksys_write+0x119/0x220 [ +0.000006] __x64_sys_write+0x72/0xc0 [ +0.000006] x64_sys_call+0x18ab/0x26f0 [ +0.000005] do_syscall_64+0x7c/0x170 [ +0.000005] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ +0.000013] The buggy address belongs to the object at ffff88811c068000 which belongs to the cache kmalloc-rnd-01-4k of size 4096 [ +0.000016] The buggy address is located 3168 bytes inside of freed 4096-byte region [ffff88811c068000, ffff88811c069000) [ +0.000022] The buggy address belongs to the physical page: [ +0.000010] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88811c06e000 pfn:0x11c068 [ +0.000006] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ +0.000006] flags: 0x17ffffc0000040(head|node=0|zone=2|lastcpupid=0x1fffff) [ +0.000007] page_type: f5(slab) [ +0.000007] raw: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000 [ +0.000005] raw: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000 [ +0.000006] head: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000 [ +0.000005] head: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000 [ +0.000006] head: 0017ffffc0000003 ffffea0004701a01 ffffffffffffffff 0000000000000000 [ +0.000005] head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000 [ +0.000004] page dumped because: kasan: bad access detected [ +0.000011] Memory state around the buggy address: [ +0.000009] ffff88811c068b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000012] ffff88811c068b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000011] >ffff88811c068c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000011] ^ [ +0.000010] ffff88811c068c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000011] ffff88811c068d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000011] ================================================================== Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Lijo Lazar <lijo.lazar@amd.com> Cc: Jesse Zhang <Jesse.Zhang@amd.com> Cc: Arvind Yadav <arvind.yadav@amd.com> v2: drop amdgpu_drm_release() and assign drm_release() as the callback directly.(Alex) Fixes: adba0929736a ("drm/amdgpu: Fix Illegal opcode in command stream Error") Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 5fb90421fa0fbe0a968274912101fe917bf1c47b ]

The issue was reproduced on NV10 using IGT pci_unplug test.
It is expected that `amdgpu_driver_postclose_kms()` is called prior to `amdgpu_drm_release()`.
However, the bug is that `amdgpu_fpriv` was freed in `amdgpu_driver_postclose_kms()`, and then
later accessed in `amdgpu_drm_release()` via a call to `amdgpu_userq_mgr_fini()`.
As a result, KASAN detected a use-after-free condition, as shown in the log below.
The proposed fix is to move the calls to `amdgpu_eviction_fence_destroy()` and
`amdgpu_userq_mgr_fini()` into `amdgpu_driver_postclose_kms()`, so they are invoked before
`amdgpu_fpriv` is freed.

This also ensures symmetry with the initialization path in `amdgpu_driver_open_kms()`,
where the following components are initialized:
- `amdgpu_userq_mgr_init()`
- `amdgpu_eviction_fence_init()`
- `amdgpu_ctx_mgr_init()`

Correspondingly, in `amdgpu_driver_postclose_kms()` we should clean up using:
- `amdgpu_userq_mgr_fini()`
- `amdgpu_eviction_fence_destroy()`
- `amdgpu_ctx_mgr_fini()`

This change eliminates the use-after-free and improves consistency in resource management between open and close paths.

[  +0.094367] ==================================================================
[  +0.000026] BUG: KASAN: slab-use-after-free in amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000866] Write of size 8 at addr ffff88811c068c60 by task amd_pci_unplug/1737
[  +0.000026] CPU: 3 UID: 0 PID: 1737 Comm: amd_pci_unplug Not tainted 6.14.0+ #2
[  +0.000008] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000003]  dump_stack_lvl+0x76/0xa0
[  +0.000010]  print_report+0xce/0x600
[  +0.000009]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000790]  ? srso_return_thunk+0x5/0x5f
[  +0.000007]  ? kasan_complete_mode_report_info+0x76/0x200
[  +0.000008]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000684]  kasan_report+0xbe/0x110
[  +0.000007]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000601]  __asan_report_store8_noabort+0x17/0x30
[  +0.000007]  amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000801]  ? __pfx_amdgpu_userq_mgr_fini+0x10/0x10 [amdgpu]
[  +0.000819]  ? srso_return_thunk+0x5/0x5f
[  +0.000008]  amdgpu_drm_release+0xa3/0xe0 [amdgpu]
[  +0.000604]  __fput+0x354/0xa90
[  +0.000010]  __fput_sync+0x59/0x80
[  +0.000005]  __x64_sys_close+0x7d/0xe0
[  +0.000006]  x64_sys_call+0x2505/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000004]  ? kasan_record_aux_stack+0xae/0xd0
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? kmem_cache_free+0x398/0x580
[  +0.000006]  ? __fput+0x543/0xa90
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __fput+0x543/0xa90
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000007]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? fpregs_assert_state_consistent+0x21/0xb0
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? syscall_exit_to_user_mode+0x4e/0x240
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? do_syscall_64+0x88/0x170
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? do_syscall_64+0x88/0x170
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? irqentry_exit+0x43/0x50
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? exc_page_fault+0x7c/0x110
[  +0.000006]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000005] RIP: 0033:0x7ffff7b14f67
[  +0.000005] Code: ff e8 0d 16 02 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 73 ba f7 ff
[  +0.000004] RSP: 002b:00007fffffffe358 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[  +0.000006] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffff7b14f67
[  +0.000003] RDX: 0000000000000000 RSI: 00007ffff7f5755a RDI: 0000000000000003
[  +0.000003] RBP: 00007fffffffe380 R08: 0000555555568170 R09: 0000000000000000
[  +0.000003] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffffffe5c8
[  +0.000003] R13: 00005555555552a9 R14: 0000555555557d48 R15: 00007ffff7ffd040
[  +0.000007]  </TASK>

[  +0.000286] Allocated by task 425 on cpu 11 at 29.751192s:
[  +0.000013]  kasan_save_stack+0x28/0x60
[  +0.000008]  kasan_save_track+0x18/0x70
[  +0.000006]  kasan_save_alloc_info+0x38/0x60
[  +0.000006]  __kasan_kmalloc+0xc1/0xd0
[  +0.000005]  __kmalloc_cache_noprof+0x1bd/0x430
[  +0.000006]  amdgpu_driver_open_kms+0x172/0x760 [amdgpu]
[  +0.000521]  drm_file_alloc+0x569/0x9a0
[  +0.000008]  drm_client_init+0x1b7/0x410
[  +0.000007]  drm_fbdev_client_setup+0x174/0x470
[  +0.000007]  drm_client_setup+0x8a/0xf0
[  +0.000006]  amdgpu_pci_probe+0x50b/0x10d0 [amdgpu]
[  +0.000482]  local_pci_probe+0xe7/0x1b0
[  +0.000008]  pci_device_probe+0x5bf/0x890
[  +0.000005]  really_probe+0x1fd/0x950
[  +0.000007]  __driver_probe_device+0x307/0x410
[  +0.000005]  driver_probe_device+0x4e/0x150
[  +0.000006]  __driver_attach+0x223/0x510
[  +0.000005]  bus_for_each_dev+0x102/0x1a0
[  +0.000006]  driver_attach+0x3d/0x60
[  +0.000005]  bus_add_driver+0x309/0x650
[  +0.000005]  driver_register+0x13d/0x490
[  +0.000006]  __pci_register_driver+0x1ee/0x2b0
[  +0.000006]  xfrm_ealg_get_byidx+0x43/0x50 [xfrm_algo]
[  +0.000008]  do_one_initcall+0x9c/0x3e0
[  +0.000007]  do_init_module+0x29e/0x7f0
[  +0.000006]  load_module+0x5c75/0x7c80
[  +0.000006]  init_module_from_file+0x106/0x180
[  +0.000007]  idempotent_init_module+0x377/0x740
[  +0.000006]  __x64_sys_finit_module+0xd7/0x180
[  +0.000006]  x64_sys_call+0x1f0b/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000005]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

[  +0.000013] Freed by task 1737 on cpu 9 at 76.455063s:
[  +0.000010]  kasan_save_stack+0x28/0x60
[  +0.000006]  kasan_save_track+0x18/0x70
[  +0.000005]  kasan_save_free_info+0x3b/0x60
[  +0.000006]  __kasan_slab_free+0x54/0x80
[  +0.000005]  kfree+0x127/0x470
[  +0.000006]  amdgpu_driver_postclose_kms+0x455/0x760 [amdgpu]
[  +0.000485]  drm_file_free.part.0+0x5b1/0xba0
[  +0.000007]  drm_file_free+0x13/0x30
[  +0.000006]  drm_client_release+0x1c4/0x2b0
[  +0.000006]  drm_fbdev_ttm_fb_destroy+0xd2/0x120 [drm_ttm_helper]
[  +0.000007]  put_fb_info+0x97/0xe0
[  +0.000006]  unregister_framebuffer+0x197/0x380
[  +0.000005]  drm_fb_helper_unregister_info+0x94/0x100
[  +0.000005]  drm_fbdev_client_unregister+0x3c/0x80
[  +0.000007]  drm_client_dev_unregister+0x144/0x330
[  +0.000006]  drm_dev_unregister+0x49/0x1b0
[  +0.000006]  drm_dev_unplug+0x4c/0xd0
[  +0.000006]  amdgpu_pci_remove+0x58/0x130 [amdgpu]
[  +0.000482]  pci_device_remove+0xae/0x1e0
[  +0.000006]  device_remove+0xc7/0x180
[  +0.000006]  device_release_driver_internal+0x3d4/0x5a0
[  +0.000007]  device_release_driver+0x12/0x20
[  +0.000006]  pci_stop_bus_device+0x104/0x150
[  +0.000006]  pci_stop_and_remove_bus_device_locked+0x1b/0x40
[  +0.000005]  remove_store+0xd7/0xf0
[  +0.000007]  dev_attr_store+0x3f/0x80
[  +0.000006]  sysfs_kf_write+0x125/0x1d0
[  +0.000005]  kernfs_fop_write_iter+0x2ea/0x490
[  +0.000007]  vfs_write+0x90d/0xe70
[  +0.000006]  ksys_write+0x119/0x220
[  +0.000006]  __x64_sys_write+0x72/0xc0
[  +0.000006]  x64_sys_call+0x18ab/0x26f0
[  +0.000005]  do_syscall_64+0x7c/0x170
[  +0.000005]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

[  +0.000013] The buggy address belongs to the object at ffff88811c068000
               which belongs to the cache kmalloc-rnd-01-4k of size 4096
[  +0.000016] The buggy address is located 3168 bytes inside of
               freed 4096-byte region [ffff88811c068000, ffff88811c069000)

[  +0.000022] The buggy address belongs to the physical page:
[  +0.000010] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88811c06e000 pfn:0x11c068
[  +0.000006] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  +0.000006] flags: 0x17ffffc0000040(head|node=0|zone=2|lastcpupid=0x1fffff)
[  +0.000007] page_type: f5(slab)
[  +0.000007] raw: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000
[  +0.000005] raw: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000
[  +0.000005] head: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000003 ffffea0004701a01 ffffffffffffffff 0000000000000000
[  +0.000005] head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000
[  +0.000004] page dumped because: kasan: bad access detected

[  +0.000011] Memory state around the buggy address:
[  +0.000009]  ffff88811c068b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000012]  ffff88811c068b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] >ffff88811c068c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]                                                        ^
[  +0.000010]  ffff88811c068c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]  ffff88811c068d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] ==================================================================

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Jesse Zhang <Jesse.Zhang@amd.com>
Cc: Arvind Yadav <arvind.yadav@amd.com>

v2: drop amdgpu_drm_release() and assign drm_release()
    as the callback directly.(Alex)

Fixes: adba0929736a ("drm/amdgpu: Fix Illegal opcode in command stream Error")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdgpu: Fix eviction fence worker race during fd close 2025-05-22T16:00:52+00:00 Jesse.Zhang Jesse.Zhang@amd.com 2025-05-15T07:02:13+00:00 0132ba7ff0f613915d332a30fcf14cf66e317f98 The current cleanup order during file descriptor close can lead to a race condition where the eviction fence worker attempts to access a destroyed mutex from the user queue manager: [ 517.294055] DEBUG_LOCKS_WARN_ON(lock->magic != lock) [ 517.294060] WARNING: CPU: 8 PID: 2030 at kernel/locking/mutex.c:564 [ 517.294094] Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu] The issue occurs because: 1. We destroy the user queue manager (including its mutex) first 2. Then try to destroy eviction fences which may have pending work 3. The eviction fence worker may try to access the already-destroyed mutex Fix this by reordering the cleanup to: 1. First mark the fd as closing and destroy eviction fences, which flushes any pending work 2. Then safely destroy the user queue manager after we're certain no more fence work will be executed The copy in amdgpu_driver_postclose_kms() needs to be removed (Christian) Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Arvind Yadav <Arvind.Yadav@amd.com> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The current cleanup order during file descriptor close can lead to
a race condition where the eviction fence worker attempts to access
a destroyed mutex from the user queue manager:

[  517.294055] DEBUG_LOCKS_WARN_ON(lock->magic != lock)
[  517.294060] WARNING: CPU: 8 PID: 2030 at kernel/locking/mutex.c:564
[  517.294094] Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu]

The issue occurs because:
1. We destroy the user queue manager (including its mutex) first
2. Then try to destroy eviction fences which may have pending work
3. The eviction fence worker may try to access the already-destroyed mutex

Fix this by reordering the cleanup to:
1. First mark the fd as closing and destroy eviction fences,
   which flushes any pending work
2. Then safely destroy the user queue manager after we're certain
   no more fence work will be executed

The copy in amdgpu_driver_postclose_kms() needs to be removed (Christian)

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Arvind Yadav <Arvind.Yadav@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add debug bit for userptr usage 2025-05-07T21:45:04+00:00 Shane Xiao shane.xiao@amd.com 2025-04-24T05:15:01+00:00 8e320f67d49d6bb28eba9c8bded66ad04b0acf0b In VM debug mode, it is desirable to notify the application to correct the freeing sequence by unmapping the memory before destroying the userptr in the old userptr path. Add a bitmask to decide whether to send gpu vm fault to the applition. Signed-off-by: Shane Xiao <shane.xiao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
In VM debug mode, it is desirable to notify the application
to correct the freeing sequence by unmapping the memory before
destroying the userptr in the old userptr path. Add a bitmask
to decide whether to send gpu vm fault to the applition.

Signed-off-by: Shane Xiao <shane.xiao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: fix pm notifier handling 2025-05-07T21:43:18+00:00 Alex Deucher alexander.deucher@amd.com 2025-05-01T17:46:46+00:00 06f2dcc241e7e5c681f81fbc46cacdf4bfd7d6d7 Set the s3/s0ix and s4 flags in the pm notifier so that we can skip the resource evictions properly in pm prepare based on whether we are suspending or hibernating. Drop the eviction as processes are not frozen at this time, we we can end up getting stuck trying to evict VRAM while applications continue to submit work which causes the buffers to get pulled back into VRAM. v2: Move suspend flags out of pm notifier (Mario) Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4178 Fixes: 2965e6355dcd ("drm/amd: Add Suspend/Hibernate notification callback support") Cc: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Set the s3/s0ix and s4 flags in the pm notifier so that we can skip
the resource evictions properly in pm prepare based on whether
we are suspending or hibernating.  Drop the eviction as processes
are not frozen at this time, we we can end up getting stuck trying
to evict VRAM while applications continue to submit work which
causes the buffers to get pulled back into VRAM.

v2: Move suspend flags out of pm notifier (Mario)

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4178
Fixes: 2965e6355dcd ("drm/amd: Add Suspend/Hibernate notification callback support")
Cc: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add Support for enforcing isolation without Cleaner Shader 2025-05-05T17:29:53+00:00 Srinivasan Shanmugam srinivasan.shanmugam@amd.com 2025-04-28T10:46:34+00:00 68071eb0ae64c076ed93897be644ebbd1c89a278 Adjusted the enforce isolation setting handling to include the ability to disable the cleaner shader without affecting isolation between tasks. v2: Updated enforce isolation documentation and parameters. (Alex) Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Adjusted the enforce isolation setting handling to include the ability
to disable the cleaner shader without affecting isolation between tasks.

v2: Updated enforce isolation documentation and parameters. (Alex)

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/userq: fix user_queue parameters list 2025-04-30T22:15:15+00:00 Bagas Sanjaya bagasdotme@gmail.com 2025-04-27T02:36:26+00:00 4e24c6bb5fab4d74205dde07c5c4e6c004f11938 Sphinx reports htmldocs warning: Documentation/gpu/amdgpu/module-parameters:7: drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c:1119: ERROR: Unexpected indentation. [docutils] Fix the warning by using reST bullet list syntax for user_queue parameter options, separated from preceding paragraph by a blank line. Fixes: fb20954c9717 ("drm/amdgpu/userq: rework driver parameter") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Closes: https://lore.kernel.org/linux-next/20250422202956.176fb590@canb.auug.org.au/ Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Sphinx reports htmldocs warning:

Documentation/gpu/amdgpu/module-parameters:7: drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c:1119: ERROR: Unexpected indentation. [docutils]

Fix the warning by using reST bullet list syntax for user_queue
parameter options, separated from preceding paragraph by a blank
line.

Fixes: fb20954c9717 ("drm/amdgpu/userq: rework driver parameter")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20250422202956.176fb590@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/userq: use consistent function naming 2025-04-22T12:51:46+00:00 Alex Deucher alexander.deucher@amd.com 2025-04-16T21:49:45+00:00 42a66677805d03df9e2600fab82d0cbe855500e1 s/userqueue/userq/ 1. remove the mix of amdgpu_userqueue and amdgpu_userq 2. to be consistent with other amdgpu_userq_fence.c 3. it's shorter Reviewed-by: Prike Liang <Prike.Liang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
s/userqueue/userq/

1. remove the mix of amdgpu_userqueue and amdgpu_userq
2. to be consistent with other amdgpu_userq_fence.c
3. it's shorter

Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/userq: rework driver parameter 2025-04-21T14:55:47+00:00 Alex Deucher alexander.deucher@amd.com 2025-04-14T18:18:03+00:00 fb20954c9717d1d07d8b8b8f34ac2a2755aec5ff Replace disable_kq parameter with user_queue parameter. The parameter has the following logic: -1 = auto (ASIC specific default) 0 = user queues disabled 1 = user queues enabled and kernel queues enabled (if supported) 2 = user queues enabled and kernel queues disabled The default behavior (-1) is currently the same as 0 for current ASICs. To enable user queues (in addition to kernel queues) set user_queue=1. To enable user queues and disable kernel queues (to make all resources available to user queues), set user_queue=2. Reviewed-by: Sunil Khatri <sunil.khatri@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Replace disable_kq parameter with user_queue parameter.
The parameter has the following logic:
 -1 = auto (ASIC specific default)
  0 = user queues disabled
  1 = user queues enabled and kernel queues enabled (if supported)
  2 = user queues enabled and kernel queues disabled

The default behavior (-1) is currently the same as 0 for current
ASICs.  To enable user queues (in addition to kernel queues) set
user_queue=1. To enable user queues and disable kernel queues
(to make all resources available to user queues), set user_queue=2.

Reviewed-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: adjust enforce_isolation handling 2025-04-11T20:58:15+00:00 Alex Deucher alexander.deucher@amd.com 2025-04-08T14:39:06+00:00 2e0454b730648e9349ca54eb4a8142d77e8e7008 Switch from a bool to an enum and allow more options for enforce isolation. There are now 3 modes of operation: - Disabled (0) - Enabled (serialization and cleaner shader) (1) - Enabled in legacy mode (no serialization or cleaner shader) (2) This provides better flexibility for more use cases. Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Switch from a bool to an enum and allow more options
for enforce isolation.  There are now 3 modes of operation:
- Disabled (0)
- Enabled (serialization and cleaner shader) (1)
- Enabled in legacy mode (no serialization or cleaner shader) (2)
This provides better flexibility for more use cases.

Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>