drm/radeon: remove r600 blit mutex v2

If we don't store local data into global variables
it isn't necessary to lock anything.

v2: rebased on new SA interface

Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>

5 files changed, 50 insertions, 75 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index 222acd2..30f0480 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -637,7 +637,6 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	if (rdev->r600_blit.shader_obj)
 		goto done;
 
-	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
 	if (rdev->family < CHIP_CAYMAN)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 478b51e..00b2238 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2363,20 +2363,15 @@ int r600_copy_blit(struct radeon_device *rdev,
 		   unsigned num_gpu_pages,
 		   struct radeon_fence *fence)
 {
+	struct radeon_sa_bo *vb = NULL;
 	int r;
 
-	mutex_lock(&rdev->r600_blit.mutex);
-	rdev->r600_blit.vb_ib = NULL;
-	r = r600_blit_prepare_copy(rdev, num_gpu_pages);
+	r = r600_blit_prepare_copy(rdev, num_gpu_pages, &vb);
 	if (r) {
-		if (rdev->r600_blit.vb_ib)
-			radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-		mutex_unlock(&rdev->r600_blit.mutex);
 		return r;
 	}
-	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages);
-	r600_blit_done_copy(rdev, fence);
-	mutex_unlock(&rdev->r600_blit.mutex);
+	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages, vb);
+	r600_blit_done_copy(rdev, fence, vb);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index db38f58..ef20822 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -513,7 +513,6 @@ int r600_blit_init(struct radeon_device *rdev)
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
 	rdev->r600_blit.ring_size_common = 40; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
 	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
 
@@ -528,7 +527,6 @@ int r600_blit_init(struct radeon_device *rdev)
 	if (rdev->r600_blit.shader_obj)
 		goto done;
 
-	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
 	if (rdev->family >= CHIP_RV770)
@@ -621,27 +619,6 @@ void r600_blit_fini(struct radeon_device *rdev)
 	radeon_bo_unref(&rdev->r600_blit.shader_obj);
 }
 
-static int r600_vb_ib_get(struct radeon_device *rdev, unsigned size)
-{
-	int r;
-	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX,
-			  &rdev->r600_blit.vb_ib, size);
-	if (r) {
-		DRM_ERROR("failed to get IB for vertex buffer\n");
-		return r;
-	}
-
-	rdev->r600_blit.vb_total = size;
-	rdev->r600_blit.vb_used = 0;
-	return 0;
-}
-
-static void r600_vb_ib_put(struct radeon_device *rdev)
-{
-	radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence);
-	radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-}
-
 static unsigned r600_blit_create_rect(unsigned num_gpu_pages,
 				      int *width, int *height, int max_dim)
 {
@@ -688,7 +665,8 @@ static unsigned r600_blit_create_rect(unsigned num_gpu_pages,
 }
 
 
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages)
+int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
+			   struct radeon_sa_bo **vb)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
@@ -705,46 +683,54 @@ int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages)
 	}
 
 	/* 48 bytes for vertex per loop */
-	r = r600_vb_ib_get(rdev, (num_loops*48)+256);
-	if (r)
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, vb,
+			     (num_loops*48)+256, 256, true);
+	if (r) {
 		return r;
+	}
 
 	/* calculate number of loops correctly */
 	ring_size = num_loops * dwords_per_loop;
 	ring_size += rdev->r600_blit.ring_size_common;
 	r = radeon_ring_lock(rdev, ring, ring_size);
-	if (r)
+	if (r) {
+		radeon_sa_bo_free(rdev, vb, NULL);
 		return r;
+	}
 
 	rdev->r600_blit.primitives.set_default_state(rdev);
 	rdev->r600_blit.primitives.set_shaders(rdev);
 	return 0;
 }
 
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence)
+void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence,
+			 struct radeon_sa_bo *vb)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
 
-	if (rdev->r600_blit.vb_ib)
-		r600_vb_ib_put(rdev);
-
-	if (fence)
-		r = radeon_fence_emit(rdev, fence);
+	r = radeon_fence_emit(rdev, fence);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return;
+	}
 
-	radeon_ring_unlock_commit(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_sa_bo_free(rdev, &vb, fence);
 }
 
 void r600_kms_blit_copy(struct radeon_device *rdev,
 			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages)
+			unsigned num_gpu_pages,
+			struct radeon_sa_bo *vb)
 {
 	u64 vb_gpu_addr;
-	u32 *vb;
+	u32 *vb_cpu_addr;
 
-	DRM_DEBUG("emitting copy %16llx %16llx %d %d\n",
-		  src_gpu_addr, dst_gpu_addr,
-		  num_gpu_pages, rdev->r600_blit.vb_used);
-	vb = (u32 *)(rdev->r600_blit.vb_ib->ptr + rdev->r600_blit.vb_used);
+	DRM_DEBUG("emitting copy %16llx %16llx %d\n",
+		  src_gpu_addr, dst_gpu_addr, num_gpu_pages);
+	vb_cpu_addr = (u32 *)radeon_sa_bo_cpu_addr(vb);
+	vb_gpu_addr = radeon_sa_bo_gpu_addr(vb);
 
 	while (num_gpu_pages) {
 		int w, h;
@@ -756,39 +742,34 @@ void r600_kms_blit_copy(struct radeon_device *rdev,
 		size_in_bytes = pages_per_loop * RADEON_GPU_PAGE_SIZE;
 		DRM_DEBUG("rectangle w=%d h=%d\n", w, h);
 
-		if ((rdev->r600_blit.vb_used + 48) > rdev->r600_blit.vb_total) {
-			WARN_ON(1);
-		}
-
-		vb[0] = 0;
-		vb[1] = 0;
-		vb[2] = 0;
-		vb[3] = 0;
+		vb_cpu_addr[0] = 0;
+		vb_cpu_addr[1] = 0;
+		vb_cpu_addr[2] = 0;
+		vb_cpu_addr[3] = 0;
 
-		vb[4] = 0;
-		vb[5] = i2f(h);
-		vb[6] = 0;
-		vb[7] = i2f(h);
+		vb_cpu_addr[4] = 0;
+		vb_cpu_addr[5] = i2f(h);
+		vb_cpu_addr[6] = 0;
+		vb_cpu_addr[7] = i2f(h);
 
-		vb[8] = i2f(w);
-		vb[9] = i2f(h);
-		vb[10] = i2f(w);
-		vb[11] = i2f(h);
+		vb_cpu_addr[8] = i2f(w);
+		vb_cpu_addr[9] = i2f(h);
+		vb_cpu_addr[10] = i2f(w);
+		vb_cpu_addr[11] = i2f(h);
 
 		rdev->r600_blit.primitives.set_tex_resource(rdev, FMT_8_8_8_8,
 							    w, h, w, src_gpu_addr, size_in_bytes);
 		rdev->r600_blit.primitives.set_render_target(rdev, COLOR_8_8_8_8,
 							     w, h, dst_gpu_addr);
 		rdev->r600_blit.primitives.set_scissors(rdev, 0, 0, w, h);
-		vb_gpu_addr = rdev->r600_blit.vb_ib->gpu_addr + rdev->r600_blit.vb_used;
 		rdev->r600_blit.primitives.set_vtx_resource(rdev, vb_gpu_addr);
 		rdev->r600_blit.primitives.draw_auto(rdev);
 		rdev->r600_blit.primitives.cp_set_surface_sync(rdev,
 				    PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA,
 				    size_in_bytes, dst_gpu_addr);
 
-		vb += 12;
-		rdev->r600_blit.vb_used += 4*12;
+		vb_cpu_addr += 12;
+		vb_gpu_addr += 4*12;
 		src_gpu_addr += size_in_bytes;
 		dst_gpu_addr += size_in_bytes;
 		num_gpu_pages -= pages_per_loop;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9507be0..659855a 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -743,7 +743,6 @@ struct r600_blit_cp_primitives {
 };
 
 struct r600_blit {
-	struct mutex		mutex;
 	struct radeon_bo	*shader_obj;
 	struct r600_blit_cp_primitives primitives;
 	int max_dim;
@@ -753,8 +752,6 @@ struct r600_blit {
 	u32 vs_offset, ps_offset;
 	u32 state_offset;
 	u32 state_len;
-	u32 vb_used, vb_total;
-	struct radeon_ib *vb_ib;
 };
 
 void r600_blit_suspend(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 7830931..05a4e15 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -368,11 +368,14 @@ void r600_hdmi_init(struct drm_encoder *encoder);
 int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
 /* r600 blit */
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages);
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
+int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
+			   struct radeon_sa_bo **vb);
+void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence,
+			 struct radeon_sa_bo *vb);
 void r600_kms_blit_copy(struct radeon_device *rdev,
 			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages);
+			unsigned num_gpu_pages,
+			struct radeon_sa_bo *vb);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
 
 /*