From e4654059c2144b215b05f2b551ff11b83d2d0467 Mon Sep 17 00:00:00 2001 From: Shirish S Date: Wed, 30 Oct 2019 14:20:46 +0530 Subject: [PATCH] drm/amdgpu: dont schedule jobs while in reset MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit [Why] doing kthread_park()/unpark() from drm_sched_entity_fini while GPU reset is in progress defeats all the purpose of drm_sched_stop->kthread_park. If drm_sched_entity_fini->kthread_unpark() happens AFTER drm_sched_stop->kthread_park nothing prevents from another (third) thread to keep submitting job to HW which will be picked up by the unparked scheduler thread and try to submit to HW but fail because the HW ring is deactivated. [How] grab the reset lock before calling drm_sched_entity_fini() Signed-off-by: Shirish S Suggested-by: Christian König Reviewed-by: Christian König Reviewed-by: Andrey Grodzovsky Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 6614d8a6f4c8d..2cdaf3b2a7217 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) continue; } - for (i = 0; i < num_entities; i++) + for (i = 0; i < num_entities; i++) { + mutex_lock(&ctx->adev->lock_reset); drm_sched_entity_fini(&ctx->entities[0][i].entity); + mutex_unlock(&ctx->adev->lock_reset); + } } } -- 2.39.5