[Bug 214029] [NAVI] Several memory leaks in amdgpu and ttm

[bugzilla-daemon at bugzilla.kernel.org]

https://bugzilla.kernel.org/show_bug.cgi?id=214029

Erhard F. (erhard_f at mailbox.org) changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
 Attachment #298267|0                           |1
        is obsolete|                            |

--- Comment #5 from Erhard F. (erhard_f at mailbox.org) ---
Created attachment 298529
  --> https://bugzilla.kernel.org/attachment.cgi?id=298529&action=edit
output of kmemleak (kernel 5.14, AMD FX-8370)

[...]
unreferenced object 0xffff8881dd96f0c0 (size 216):
  comm "lxdm-greeter-gt", pid 619, jiffies 4294888177 (age 3729.577s)
  hex dump (first 32 bytes):
    50 f1 96 dd 81 88 ff ff 20 8b 72 c0 ff ff ff ff  P....... .r.....
    c0 3a 59 da 08 00 00 00 58 fd a6 08 00 c9 ff ff  .:Y.....X.......
  backtrace:
    [<ffffffffc072514f>] drm_sched_fence_create+0x1f/0x1d0 [gpu_sched]
    [<ffffffffc07204de>] drm_sched_job_init+0x10e/0x240 [gpu_sched]
    [<ffffffffc159e317>] amdgpu_job_submit+0x27/0x2d0 [amdgpu]
    [<ffffffffc118ae6e>] amdgpu_copy_buffer+0x49e/0x700 [amdgpu]
    [<ffffffffc118b6ca>] amdgpu_ttm_copy_mem_to_mem+0x5fa/0xf00 [amdgpu]
    [<ffffffffc118ce06>] amdgpu_bo_move+0x356/0x2180 [amdgpu]
    [<ffffffffc0887897>] ttm_bo_handle_move_mem+0x1c7/0x620 [ttm]
    [<ffffffffc088b297>] ttm_bo_validate+0x2c7/0x450 [ttm]
    [<ffffffffc1193444>] amdgpu_bo_fault_reserve_notify+0x2a4/0x640 [amdgpu]
    [<ffffffffc11a3323>] amdgpu_gem_fault+0x123/0x2d0 [amdgpu]
    [<ffffffffb255c853>] __do_fault+0xf3/0x3e0
    [<ffffffffb256ea4b>] __handle_mm_fault+0x1bcb/0x2ac0
    [<ffffffffb256fa6a>] handle_mm_fault+0x12a/0x490
    [<ffffffffb2090909>] do_user_addr_fault+0x259/0xb70
    [<ffffffffb37ad665>] exc_page_fault+0x55/0xb0
    [<ffffffffb3800acb>] asm_exc_page_fault+0x1b/0x20
unreferenced object 0xffff888120f77100 (size 72):
  comm "sdma0", pid 344, jiffies 4294888177 (age 3729.577s)
  hex dump (first 32 bytes):
    30 f4 ec 3a 81 88 ff ff 20 8a f0 c1 ff ff ff ff  0..:.... .......
    a3 49 5d da 08 00 00 00 58 84 a3 0c 82 88 ff ff  .I].....X.......
  backtrace:
    [<ffffffffc1180521>] amdgpu_fence_emit+0x91/0x790 [amdgpu]
    [<ffffffffc11ed4cb>] amdgpu_ib_schedule+0x8cb/0x12f0 [amdgpu]
    [<ffffffffc159d67e>] amdgpu_job_run+0x35e/0x790 [amdgpu]
    [<ffffffffc072392e>] drm_sched_main+0x64e/0xc60 [gpu_sched]
    [<ffffffffb212fdf2>] kthread+0x342/0x410
    [<ffffffffb20030d2>] ret_from_fork+0x22/0x30
unreferenced object 0xffff888246342640 (size 216):
  comm "mate-session-ch", pid 718, jiffies 4294890392 (age 3722.200s)
  hex dump (first 32 bytes):
    d0 26 34 46 82 88 ff ff 20 8b 72 c0 ff ff ff ff  .&4F.... .r.....
    03 71 65 92 0a 00 00 00 58 fd a6 08 00 c9 ff ff  .qe.....X.......
  backtrace:
    [<ffffffffc072514f>] drm_sched_fence_create+0x1f/0x1d0 [gpu_sched]
    [<ffffffffc07204de>] drm_sched_job_init+0x10e/0x240 [gpu_sched]
    [<ffffffffc159e317>] amdgpu_job_submit+0x27/0x2d0 [amdgpu]
    [<ffffffffc118ae6e>] amdgpu_copy_buffer+0x49e/0x700 [amdgpu]
    [<ffffffffc118b6ca>] amdgpu_ttm_copy_mem_to_mem+0x5fa/0xf00 [amdgpu]
    [<ffffffffc118ce06>] amdgpu_bo_move+0x356/0x2180 [amdgpu]
    [<ffffffffc0887897>] ttm_bo_handle_move_mem+0x1c7/0x620 [ttm]
    [<ffffffffc088b297>] ttm_bo_validate+0x2c7/0x450 [ttm]
    [<ffffffffc1193444>] amdgpu_bo_fault_reserve_notify+0x2a4/0x640 [amdgpu]
    [<ffffffffc11a3323>] amdgpu_gem_fault+0x123/0x2d0 [amdgpu]
    [<ffffffffb255c853>] __do_fault+0xf3/0x3e0
    [<ffffffffb256ea4b>] __handle_mm_fault+0x1bcb/0x2ac0
    [<ffffffffb256fa6a>] handle_mm_fault+0x12a/0x490
    [<ffffffffb2090909>] do_user_addr_fault+0x259/0xb70
    [<ffffffffb37ad665>] exc_page_fault+0x55/0xb0
    [<ffffffffb3800acb>] asm_exc_page_fault+0x1b/0x20
[...]

-- 
You may reply to this email to add a comment.

You are receiving this mail because:
You are watching the assignee of the bug.