[PATCH 37/42] drm/amdgpu: split vm flush and vm flush emit logic

[Alex Deucher <alexander.deucher@amd.com>]

No intended functional change.  Split the logic into
two functions, one to set the state and one to use
the state to emit the ring contents.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c  |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c  | 92 ++++++++++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h  |  1 +
 4 files changed, 56 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index d2f03060d9d3a..54d7a975a74c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -213,6 +213,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,
 		amdgpu_ring_undo(ring);
 		return r;
 	}
+	amdgpu_vm_emit_flush(ring, job);
 
 	amdgpu_ring_ib_begin(ring);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index d53c13322a648..72d50602a8e52 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -108,6 +108,7 @@ struct amdgpu_job {
 	bool			vm_flush_needed;
 	bool			cleaner_shader_needed;
 	bool			pasid_mapping_needed;
+	bool			emit_vm_fence;
 
 	uint32_t		num_ibs;
 	struct amdgpu_ib	ibs[];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 374991520ad2c..6c84677daad4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -756,6 +756,57 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 	return false;
 }
 
+void amdgpu_vm_emit_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned int patch;
+
+	if (!job->vm_flush_needed && !job->gds_switch_needed && !job->need_pipe_sync &&
+	    !job->cleaner_shader_needed)
+		return;
+
+	amdgpu_ring_ib_begin(ring);
+	if (ring->funcs->init_cond_exec)
+		patch = amdgpu_ring_init_cond_exec(ring,
+						   ring->cond_exe_gpu_addr);
+
+	if (job->need_pipe_sync)
+		amdgpu_ring_emit_pipeline_sync(ring, job->pipe_sync_seq);
+
+	if (job->cleaner_shader_needed)
+		ring->funcs->emit_cleaner_shader(ring);
+
+	if (job->vm_flush_needed)
+		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
+
+	if (job->pasid_mapping_needed)
+		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);
+
+	if (job->spm_update_needed && adev->gfx.rlc.funcs->update_spm_vmid)
+		adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, job->vmid);
+
+	if (ring->funcs->emit_gds_switch &&
+	    job->gds_switch_needed) {
+		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
+					    job->gds_size, job->gws_base,
+					    job->gws_size, job->oa_base,
+					    job->oa_size);
+	}
+
+	if (job->emit_vm_fence)
+		amdgpu_fence_emit(ring, job->hw_vm_fence, 0);
+
+	amdgpu_ring_patch_cond_exec(ring, patch);
+
+	/* the double SWITCH_BUFFER here *cannot* be skipped by COND_EXEC */
+	if (ring->funcs->emit_switch_buffer) {
+		amdgpu_ring_emit_switch_buffer(ring);
+		amdgpu_ring_emit_switch_buffer(ring);
+	}
+
+	amdgpu_ring_ib_end(ring);
+}
+
 /**
  * amdgpu_vm_flush - hardware flush the vm
  *
@@ -775,7 +826,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 	struct amdgpu_vmid *id = &id_mgr->ids[job->vmid];
 	struct dma_fence *fence = NULL;
-	unsigned int patch;
 	int r;
 
 	job->gds_switch_needed = ring->funcs->emit_gds_switch &&
@@ -810,35 +860,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 	    !job->cleaner_shader_needed)
 		return 0;
 
-	amdgpu_ring_ib_begin(ring);
-	if (ring->funcs->init_cond_exec)
-		patch = amdgpu_ring_init_cond_exec(ring,
-						   ring->cond_exe_gpu_addr);
-
-	if (job->need_pipe_sync)
-		amdgpu_ring_emit_pipeline_sync(ring, job->pipe_sync_seq);
-
-	if (job->cleaner_shader_needed)
-		ring->funcs->emit_cleaner_shader(ring);
-
-	if (job->vm_flush_needed) {
+	if (job->vm_flush_needed)
 		trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr);
-		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
-	}
-
-	if (job->pasid_mapping_needed)
-		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);
-
-	if (job->spm_update_needed && adev->gfx.rlc.funcs->update_spm_vmid)
-		adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, job->vmid);
-
-	if (ring->funcs->emit_gds_switch &&
-	    job->gds_switch_needed) {
-		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
-					    job->gds_size, job->gws_base,
-					    job->gws_size, job->oa_base,
-					    job->oa_size);
-	}
 
 	if (job->vm_flush_needed ||
 	    job->pasid_mapping_needed ||
@@ -846,7 +869,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 		r = amdgpu_fence_init(ring, job->hw_vm_fence);
 		if (r)
 			return r;
-		amdgpu_fence_emit(ring, job->hw_vm_fence, 0);
+		job->emit_vm_fence = true;
 		fence = &job->hw_vm_fence->base;
 		/* get a ref for the job */
 		dma_fence_get(fence);
@@ -882,15 +905,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 	}
 	dma_fence_put(fence);
 
-	amdgpu_ring_patch_cond_exec(ring, patch);
-
-	/* the double SWITCH_BUFFER here *cannot* be skipped by COND_EXEC */
-	if (ring->funcs->emit_switch_buffer) {
-		amdgpu_ring_emit_switch_buffer(ring);
-		amdgpu_ring_emit_switch_buffer(ring);
-	}
-
-	amdgpu_ring_ib_end(ring);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 89b76639cb273..0ce37aab8b518 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -512,6 +512,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		       struct ww_acquire_ctx *ticket,
 		       int (*callback)(void *p, struct amdgpu_bo *bo),
 		       void *param);
+void amdgpu_vm_emit_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
 int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm, bool immediate);
-- 
2.52.0