Commit 5918045c authored by Christian König's avatar Christian König Committed by Alex Deucher
Browse files

drm/scheduler: rework job destruction 

We now destroy finished jobs from the worker thread to make sure that
we never destroy a job currently in timeout processing.
By this we avoid holding lock around ring mirror list in drm_sched_stop
which should solve a deadlock reported by a user.

v2: Remove unused variable.
v4: Move guilty job free into sched code.
v5:
Move sched->hw_rq_count to drm_sched_start to account for counter
decrement in drm_sched_stop even when we don't call resubmit jobs
if guily job did signal.
v6: remove unused variable

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109692



Acked-by: default avatarChunming Zhou <david1.zhou@amd.com>
Signed-off-by: default avatarChristian König <christian.koenig@amd.com>
Signed-off-by: default avatarAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1555599624-12285-3-git-send-email-andrey.grodzovsky@amd.com
parent b3198c38

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

+3 −6
Original line number Diff line number Diff line
@@ -3334,7 +3334,7 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, 
		if (!ring || !ring->sched.thread)

			continue;



		drm_sched_stop(&ring->sched);

		drm_sched_stop(&ring->sched, &job->base);



		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */

		amdgpu_fence_driver_force_completion(ring);
@@ -3343,8 +3343,6 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, 
	if(job)

		drm_sched_increase_karma(&job->base);







	if (!amdgpu_sriov_vf(adev)) {



		if (!need_full_reset)
@@ -3482,8 +3480,7 @@ end: 
	return r;

}



static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,

					  struct amdgpu_job *job)

static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev)

{

	int i;
@@ -3623,7 +3620,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ 


	/* Post ASIC reset for all devs .*/

	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {

		amdgpu_device_post_asic_reset(tmp_adev, tmp_adev == adev ? job : NULL);

		amdgpu_device_post_asic_reset(tmp_adev);



		if (r) {

			/* bad news, how to tell it to userspace ? */

drivers/gpu/drm/etnaviv/etnaviv_dump.c

+0 −5
Original line number Diff line number Diff line
@@ -118,7 +118,6 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) 
	unsigned int n_obj, n_bomap_pages;

	size_t file_size, mmu_size;

	__le64 *bomap, *bomap_start;

	unsigned long flags;



	/* Only catch the first event, or when manually re-armed */

	if (!etnaviv_dump_core)
@@ -135,13 +134,11 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) 
		    mmu_size + gpu->buffer.size;



	/* Add in the active command buffers */

	spin_lock_irqsave(&gpu->sched.job_list_lock, flags);

	list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {

		submit = to_etnaviv_submit(s_job);

		file_size += submit->cmdbuf.size;

		n_obj++;

	}

	spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);



	/* Add in the active buffer objects */

	list_for_each_entry(vram, &gpu->mmu->mappings, mmu_node) {
@@ -183,14 +180,12 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) 
			      gpu->buffer.size,

			      etnaviv_cmdbuf_get_va(&gpu->buffer));



	spin_lock_irqsave(&gpu->sched.job_list_lock, flags);

	list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {

		submit = to_etnaviv_submit(s_job);

		etnaviv_core_dump_mem(&iter, ETDUMP_BUF_CMD,

				      submit->cmdbuf.vaddr, submit->cmdbuf.size,

				      etnaviv_cmdbuf_get_va(&submit->cmdbuf));

	}

	spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);



	/* Reserve space for the bomap */

	if (n_bomap_pages) {

drivers/gpu/drm/etnaviv/etnaviv_sched.c

+1 −1
Original line number Diff line number Diff line
@@ -109,7 +109,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) 
	}



	/* block scheduler */

	drm_sched_stop(&gpu->sched);

	drm_sched_stop(&gpu->sched, sched_job);



	if(sched_job)

		drm_sched_increase_karma(sched_job);

drivers/gpu/drm/lima/lima_sched.c

+1 −1
Original line number Diff line number Diff line
@@ -258,7 +258,7 @@ static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job) 
static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,

					 struct lima_sched_task *task)

{

	drm_sched_stop(&pipe->base);

	drm_sched_stop(&pipe->base, &task->base);



	if (task)

		drm_sched_increase_karma(&task->base);

drivers/gpu/drm/panfrost/panfrost_job.c

+1 −1
Original line number Diff line number Diff line
@@ -387,7 +387,7 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) 
	mutex_lock(&pfdev->reset_lock);



	for (i = 0; i < NUM_JOB_SLOTS; i++)

		drm_sched_stop(&pfdev->js->queue[i].sched);

		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);



	if (sched_job)

		drm_sched_increase_karma(sched_job);

CRA Git | Maintained and supported by SUSTech CRA and CCSE