drm/amdgpu: make pipeline sync be in same place v2

v2: directly return for 'if' case.
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1132,7 +1132,6 @@ struct amdgpu_job {
 	void			*owner;
 	uint64_t		fence_ctx; /* the fence_context this job uses */
 	bool                    vm_needs_flush;
-	bool			need_pipeline_sync;
 	unsigned		vm_id;
 	uint64_t		vm_pd_addr;
 	uint32_t		gds_base, gds_size;

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

@@ -121,7 +121,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib *ib = &ibs[0];
-	struct dma_fence *tmp;
+	struct dma_fence *tmp = NULL;
 	bool skip_preamble, need_ctx_switch;
 	unsigned patch_offset = ~0;
 	struct amdgpu_vm *vm;
@@ -163,8 +163,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	}
 
 	if (ring->funcs->emit_pipeline_sync && job &&
-	    (tmp = amdgpu_sync_get_fence(&job->sched_sync))) {
-		job->need_pipeline_sync = true;
+	    ((tmp = amdgpu_sync_get_fence(&job->sched_sync)) ||
+	     amdgpu_vm_need_pipeline_sync(ring, job))) {
 		amdgpu_ring_emit_pipeline_sync(ring);
 		dma_fence_put(tmp);
 	}

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

@@ -57,7 +57,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
-	(*job)->need_pipeline_sync = false;
 
 	amdgpu_sync_create(&(*job)->sync);
 	amdgpu_sync_create(&(*job)->sched_sync);

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

@@ -694,6 +694,35 @@ static u64 amdgpu_vm_adjust_mc_addr(struct amdgpu_device *adev, u64 mc_addr)
 	return addr;
 }
 
+bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
+				  struct amdgpu_job *job)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vm_id *id;
+	bool gds_switch_needed;
+	bool vm_flush_needed = job->vm_needs_flush ||
+		amdgpu_vm_ring_has_compute_vm_bug(ring);
+
+	if (job->vm_id == 0)
+		return false;
+	id = &id_mgr->ids[job->vm_id];
+	gds_switch_needed = ring->funcs->emit_gds_switch && (
+		id->gds_base != job->gds_base ||
+		id->gds_size != job->gds_size ||
+		id->gws_base != job->gws_base ||
+		id->gws_size != job->gws_size ||
+		id->oa_base != job->oa_base ||
+		id->oa_size != job->oa_size);
+
+	if (amdgpu_vm_had_gpu_reset(adev, id))
+		return true;
+	if (!vm_flush_needed && !gds_switch_needed)
+		return false;
+	return true;
+}
+
 /**
  * amdgpu_vm_flush - hardware flush the vm
  *
@@ -732,9 +761,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 	if (ring->funcs->init_cond_exec)
 		patch_offset = amdgpu_ring_init_cond_exec(ring);
 
-	if (ring->funcs->emit_pipeline_sync && !job->need_pipeline_sync)
-		amdgpu_ring_emit_pipeline_sync(ring);
-
 	if (ring->funcs->emit_vm_flush && vm_flush_needed) {
 		u64 pd_addr = amdgpu_vm_adjust_mc_addr(adev, job->vm_pd_addr);
 		struct dma_fence *fence;

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h

@@ -245,5 +245,7 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
 void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size);
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
+				  struct amdgpu_job *job);
 
 #endif