found recover_vram_from_shadow sometimes get executed in paralle with SDMA scheduler, should stop all schedulers before doing gpu reset/recover
Change-Id: Ibaef3e3c015f3cf88f84b2eaf95cda95ae1a64e3 Signed-off-by: Monk Liu <monk....@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 40 +++++++++++------------------- 1 file changed, 15 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 75d1733..e9d81a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2649,22 +2649,23 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); + /* store modesetting */ if (amdgpu_device_has_dc_support(adev)) state = drm_atomic_helper_suspend(adev->ddev); - /* block scheduler */ + /* block all schedulers and reset given job's ring */ for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; if (!ring || !ring->sched.thread) continue; - /* only focus on the ring hit timeout if &job not NULL */ + kthread_park(ring->sched.thread); + if (job && job->ring->idx != i) continue; - kthread_park(ring->sched.thread); drm_sched_hw_job_reset(&ring->sched, &job->base); /* after all hw jobs are reset, hw fence is meaningless, so force_completion */ @@ -2707,33 +2708,22 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, } dma_fence_put(fence); } + } - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { - struct amdgpu_ring *ring = adev->rings[i]; - - if (!ring || !ring->sched.thread) - continue; + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; - /* only focus on the ring hit timeout if &job not NULL */ - if (job && job->ring->idx != i) - continue; + if (!ring || !ring->sched.thread) + continue; + /* only need recovery sched of the given job's ring + * or all rings (in the case @job is NULL) + * after above amdgpu_reset accomplished + */ + if ((!job || job->ring->idx == i) && !r) drm_sched_job_recovery(&ring->sched); - kthread_unpark(ring->sched.thread); - } - } else { - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { - struct amdgpu_ring *ring = adev->rings[i]; - if (!ring || !ring->sched.thread) - continue; - - /* only focus on the ring hit timeout if &job not NULL */ - if (job && job->ring->idx != i) - continue; - - kthread_unpark(adev->rings[i]->sched.thread); - } + kthread_unpark(ring->sched.thread); } if (amdgpu_device_has_dc_support(adev)) { -- 2.7.4 _______________________________________________ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx