From 9a1cddd6374fb1eb166f40f10d5411e3699066d4 Mon Sep 17 00:00:00 2001 From: jqdeng Date: Fri, 7 Aug 2020 17:31:19 +0800 Subject: [PATCH] drm/amdgpu: Fix repeatly flr issue Only for no job running test case need to do recover in flr notification. For having job in mirror list, then let guest driver to hit job timeout, and then do recover. Signed-off-by: jqdeng Acked-by: Nirmoy Das Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 28 ++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 2 +- drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 3 ++- 4 files changed, 32 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 08f80ca3b296..54666eea1863 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1133,6 +1133,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev); #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter)); /* Common functions */ +bool amdgpu_device_has_job_running(struct amdgpu_device *adev); bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev); int amdgpu_device_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 415e1a32b98c..6573e1112462 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3922,6 +3922,34 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, return r; } +/** + * amdgpu_device_has_job_running - check if there is any job in mirror list + * + * @adev: amdgpu device pointer + * + * check if there is any job in mirror list + */ +bool amdgpu_device_has_job_running(struct amdgpu_device *adev) +{ + int i; + struct drm_sched_job *job; + + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; + + if (!ring || !ring->sched.thread) + continue; + + spin_lock(&ring->sched.job_list_lock); + job = list_first_entry_or_null(&ring->sched.ring_mirror_list, + struct drm_sched_job, node); + spin_unlock(&ring->sched.job_list_lock); + if (job) + return true; + } + return false; +} + /** * amdgpu_device_should_recover_gpu - check if we should try GPU recovery * diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 5fd67e1cc2a0..475ff5df8c87 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) - && adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT) + && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)) amdgpu_device_gpu_recover(adev, NULL); } diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index ce2bf1fb79ed..9cf695c05db3 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -289,7 +289,8 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) - && (adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT || + && (amdgpu_device_has_job_running(adev) || + adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT || adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT || adev->compute_timeout == MAX_SCHEDULE_TIMEOUT || adev->video_timeout == MAX_SCHEDULE_TIMEOUT))