diff mbox

[5/6] drm/amdgpu: add independent DMA-buf export v3

Message ID 20180706144216.14731-6-christian.koenig@amd.com (mailing list archive)
State New, archived
Headers show

Commit Message

Christian König July 6, 2018, 2:42 p.m. UTC
The caching of SGT's is actually quite harmful and should probably removed
altogether when all drivers are audited.

Start by providing a separate DMA-buf export implementation in amdgpu. This is
also a prerequisite of unpinned DMA-buf handling.

v2: fix unintended recursion, remove debugging leftovers
v3: split out from unpinned DMA-buf work
v4: rebase on top of new no_sgt_cache flag

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h       |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c   |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 94 +++++++++++++------------------
 3 files changed, 40 insertions(+), 56 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8eaba0f4db10..269664fd00de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -374,7 +374,6 @@  int amdgpu_gem_object_open(struct drm_gem_object *obj,
 void amdgpu_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 unsigned long amdgpu_gem_timeout(uint64_t timeout_ns);
-struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *
 amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 				 struct dma_buf_attachment *attach,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 06aede194bf8..04ef967e128c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1138,7 +1138,6 @@  static struct drm_driver kms_driver = {
 	.gem_prime_export = amdgpu_gem_prime_export,
 	.gem_prime_import = amdgpu_gem_prime_import,
 	.gem_prime_res_obj = amdgpu_gem_prime_res_obj,
-	.gem_prime_get_sg_table = amdgpu_gem_prime_get_sg_table,
 	.gem_prime_import_sg_table = amdgpu_gem_prime_import_sg_table,
 	.gem_prime_vmap = amdgpu_gem_prime_vmap,
 	.gem_prime_vunmap = amdgpu_gem_prime_vunmap,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 3ed02f472003..75c70ddbc080 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -40,22 +40,6 @@ 
 
 static const struct dma_buf_ops amdgpu_dmabuf_ops;
 
-/**
- * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
- * implementation
- * @obj: GEM buffer object
- *
- * Returns:
- * A scatter/gather table for the pinned pages of the buffer object's memory.
- */
-struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
-{
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	int npages = bo->tbo.num_pages;
-
-	return drm_prime_pages_to_sg(bo->tbo.ttm->pages, npages);
-}
-
 /**
  * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
  * @obj: GEM buffer object
@@ -189,34 +173,29 @@  amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 }
 
 /**
- * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
- * @dma_buf: shared DMA buffer
+ * amdgpu_gem_map_dma_buf - &dma_buf_ops.map_dma_buf implementation
  * @attach: DMA-buf attachment
+ * @dir: DMA direction
  *
  * Makes sure that the shared DMA buffer can be accessed by the target device.
  * For now, simply pins it to the GTT domain, where it should be accessible by
  * all DMA devices.
  *
  * Returns:
- * 0 on success or negative error code.
+ * sg_table filled with the DMA addresses to use or ERR_PRT with negative error
+ * code.
  */
-static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
-				 struct dma_buf_attachment *attach)
+static struct sg_table *
+amdgpu_gem_map_dma_buf(struct dma_buf_attachment *attach,
+		       enum dma_data_direction dir)
 {
+	struct dma_buf *dma_buf = attach->dmabuf;
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct sg_table *sgt;
 	long r;
 
-	r = drm_gem_map_attach(dma_buf, attach);
-	if (r)
-		return r;
-
-	r = amdgpu_bo_reserve(bo, false);
-	if (unlikely(r != 0))
-		goto error_detach;
-
-
 	if (attach->dev->driver != adev->dev->driver) {
 		/*
 		 * Wait for all shared fences to complete before we switch to future
@@ -227,54 +206,62 @@  static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 							MAX_SCHEDULE_TIMEOUT);
 		if (unlikely(r < 0)) {
 			DRM_DEBUG_PRIME("Fence wait failed: %li\n", r);
-			goto error_unreserve;
+			return ERR_PTR(r);
 		}
 	}
 
 	/* pin buffer into GTT */
 	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r)
-		goto error_unreserve;
+		return ERR_PTR(r);
+
+	sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);
+	if (IS_ERR(sgt))
+		return sgt;
+
+	if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+			      DMA_ATTR_SKIP_CPU_SYNC))
+		goto error_free;
 
 	if (attach->dev->driver != adev->dev->driver)
 		bo->prime_shared_count++;
 
-error_unreserve:
-	amdgpu_bo_unreserve(bo);
+	return sgt;
 
-error_detach:
-	if (r)
-		drm_gem_map_detach(dma_buf, attach);
-	return r;
+error_free:
+	sg_free_table(sgt);
+	kfree(sgt);
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
- * amdgpu_gem_map_detach - &dma_buf_ops.detach implementation
- * @dma_buf: shared DMA buffer
+ * amdgpu_gem_unmap_dma_buf - &dma_buf_ops.unmap_dma_buf implementation
  * @attach: DMA-buf attachment
+ * @sgt: sg_table to unmap
+ * @dir: DMA direction
  *
  * This is called when a shared DMA buffer no longer needs to be accessible by
  * the other device. For now, simply unpins the buffer from GTT.
  */
-static void amdgpu_gem_map_detach(struct dma_buf *dma_buf,
-				  struct dma_buf_attachment *attach)
+static void amdgpu_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
+				     struct sg_table *sgt,
+				     enum dma_data_direction dir)
 {
+	struct dma_buf *dma_buf = attach->dmabuf;
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	int ret = 0;
-
-	ret = amdgpu_bo_reserve(bo, true);
-	if (unlikely(ret != 0))
-		goto error;
 
 	amdgpu_bo_unpin(bo);
+
 	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
 		bo->prime_shared_count--;
-	amdgpu_bo_unreserve(bo);
 
-error:
-	drm_gem_map_detach(dma_buf, attach);
+	if (sgt) {
+		dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+		sg_free_table(sgt);
+		kfree(sgt);
+	}
 }
 
 /**
@@ -332,10 +319,9 @@  static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 }
 
 static const struct dma_buf_ops amdgpu_dmabuf_ops = {
-	.attach = amdgpu_gem_map_attach,
-	.detach = amdgpu_gem_map_detach,
-	.map_dma_buf = drm_gem_map_dma_buf,
-	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.no_sgt_cache = true,
+	.map_dma_buf = amdgpu_gem_map_dma_buf,
+	.unmap_dma_buf = amdgpu_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_gem_begin_cpu_access,
 	.map = drm_gem_dmabuf_kmap,