[PATCH 11/12] drm/amdgpu: add DMA-buf pin/unpin implementation

[Christian König]

Pin and unpin the DMA-buf exported BOs only on demand and invalidate all
DMA-buf mappings when the underlying BO moves.

Signed-off-by: Christian König <christian.koenig at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c |  5 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c  | 73 ++++++++++++++++++++--
 2 files changed, 72 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ec9e45004bff..fdb98eb562db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -31,6 +31,7 @@
  */
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/dma-buf.h>
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_cache.h>
@@ -1192,6 +1193,10 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 
 	amdgpu_bo_kunmap(abo);
 
+	if (abo->gem_base.dma_buf && !abo->gem_base.import_attach &&
+	    bo->mem.mem_type != TTM_PL_SYSTEM)
+		dma_buf_invalidate_mappings(abo->gem_base.dma_buf);
+
 	/* remember the eviction */
 	if (evict)
 		atomic64_inc(&adev->num_evictions);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 56e2a606b9a1..40cd89271b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -209,6 +209,61 @@ __reservation_object_make_exclusive(struct reservation_object *obj)
 	return -ENOMEM;
 }
 
+/**
+ * amdgpu_gem_pin_dma_buf - &dma_buf_ops.pin_dma_buf implementation
+ *
+ * @dma_buf: DMA-buf to pin in memory
+ *
+ * Pin the BO which is backing the DMA-buf so that it can't move any more.
+ */
+static int amdgpu_gem_pin_dma_buf(struct dma_buf *dma_buf)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	/* pin buffer into GTT */
+	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+}
+
+/**
+ * amdgpu_gem_unpin_dma_buf - &dma_buf_ops.unpin_dma_buf implementation
+ *
+ * @dma_buf: DMA-buf to unpin
+ *
+ * Unpin a previously pinned BO to make it movable again.
+ */
+static void amdgpu_gem_unpin_dma_buf(struct dma_buf *dma_buf)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	amdgpu_bo_unpin(bo);
+}
+
+/**
+ * amdgpu_gem_dma_buf_attach - &dma_buf_ops.attach implementation
+ *
+ * @dma_buf: DMA-buf we attach to
+ * @attach: DMA-buf attachment
+ *
+ * Returns:
+ * Always zero for success.
+ */
+static int amdgpu_gem_dma_buf_attach(struct dma_buf *dma_buf,
+				     struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	/* Make sure the buffer is pinned when userspace didn't set GTT as
+	 * preferred domain. This avoid ping/pong situations with scan out BOs.
+	 */
+	if (!(bo->preferred_domains & AMDGPU_GEM_DOMAIN_GTT))
+		attach->invalidate = NULL;
+
+	return 0;
+}
+
 /**
  * amdgpu_gem_map_dma_buf - &dma_buf_ops.map_dma_buf implementation
  * @attach: DMA-buf attachment
@@ -247,10 +302,15 @@ amdgpu_gem_map_dma_buf(struct dma_buf_attachment *attach,
 			return ERR_PTR(r);
 	}
 
-	/* pin buffer into GTT */
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
-	if (r)
-		return ERR_PTR(r);
+	if (attach->invalidate) {
+		/* move buffer into GTT */
+		struct ttm_operation_ctx ctx = { false, false };
+
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+		if (r)
+			return ERR_PTR(r);
+	}
 
 	sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);
 	if (IS_ERR(sgt))
@@ -289,8 +349,6 @@ static void amdgpu_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	amdgpu_bo_unpin(bo);
-
 	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
 		bo->prime_shared_count--;
 
@@ -357,6 +415,9 @@ static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.dynamic_sgt_mapping = true,
+	.attach = amdgpu_gem_dma_buf_attach,
+	.pin = amdgpu_gem_pin_dma_buf,
+	.unpin = amdgpu_gem_unpin_dma_buf,
 	.map_dma_buf = amdgpu_gem_map_dma_buf,
 	.unmap_dma_buf = amdgpu_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
-- 
2.17.1