drm/amdgpu: add independent DMA-buf import v9

Instead of relying on the DRM functions just implement our own import
functions. This prepares support for taking care of unpinned DMA-buf.

v2: enable for all exporters, not just amdgpu, fix invalidation
    handling, lock reservation object while setting callback
v3: change to new dma_buf attach interface
v4: split out from unpinned DMA-buf work
v5: rebased and cleanup on new DMA-buf interface
v6: squash with invalidation callback change,
    stop using _(map|unmap)_locked
v7: drop invalidations when the BO is already in system domain
v8: rebase on new DMA-buf patch and drop move notification
v9: cleanup comments
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/337948/

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

@@ -370,31 +370,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 }
 
 /**
- * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
- * implementation
+ * amdgpu_dma_buf_create_obj - create BO for DMA-buf import
+ *
  * @dev: DRM device
- * @attach: DMA-buf attachment
- * @sg: Scatter/gather table
+ * @dma_buf: DMA-buf
  *
- * Imports shared DMA buffer memory exported by another device.
+ * Creates an empty SG BO for DMA-buf import.
  *
  * Returns:
  * A new GEM BO of the given DRM device, representing the memory
  * described by the given DMA-buf attachment and scatter/gather table.
  */
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-				 struct dma_buf_attachment *attach,
-				 struct sg_table *sg)
+static struct drm_gem_object *
+amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 {
-	struct dma_resv *resv = attach->dmabuf->resv;
+	struct dma_resv *resv = dma_buf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_bo *bo;
 	struct amdgpu_bo_param bp;
 	int ret;
 
 	memset(&bp, 0, sizeof(bp));
-	bp.size = attach->dmabuf->size;
+	bp.size = dma_buf->size;
 	bp.byte_align = PAGE_SIZE;
 	bp.domain = AMDGPU_GEM_DOMAIN_CPU;
 	bp.flags = 0;
@@ -405,11 +402,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	if (ret)
 		goto error;
 
-	bo->tbo.sg = sg;
-	bo->tbo.ttm->sg = sg;
 	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
-	if (attach->dmabuf->ops != &amdgpu_dmabuf_ops)
+	if (dma_buf->ops != &amdgpu_dmabuf_ops)
 		bo->prime_shared_count = 1;
 
 	dma_resv_unlock(resv);
@@ -425,8 +420,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
  * @dev: DRM device
  * @dma_buf: Shared DMA buffer
  *
- * The main work is done by the &drm_gem_prime_import helper, which in turn
- * uses &amdgpu_gem_prime_import_sg_table.
+ * Import a dma_buf into a the driver and potentially create a new GEM object.
  *
  * Returns:
  * GEM BO representing the shared DMA buffer for the given device.
@@ -434,6 +428,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 					       struct dma_buf *dma_buf)
 {
+	struct dma_buf_attachment *attach;
 	struct drm_gem_object *obj;
 
 	if (dma_buf->ops == &amdgpu_dmabuf_ops) {
@@ -448,5 +443,17 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 		}
 	}
 
-	return drm_gem_prime_import(dev, dma_buf);
+	obj = amdgpu_dma_buf_create_obj(dev, dma_buf);
+	if (IS_ERR(obj))
+		return obj;
+
+	attach = dma_buf_dynamic_attach(dma_buf, dev->dev, true);
+	if (IS_ERR(attach)) {
+		drm_gem_object_put(obj);
+		return ERR_CAST(attach);
+	}
+
+	get_dma_buf(dma_buf);
+	obj->import_attach = attach;
+	return obj;
 }

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

@@ -25,10 +25,6 @@
 
 #include <drm/drm_gem.h>
 
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-				 struct dma_buf_attachment *attach,
-				 struct sg_table *sg);
 struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 					int flags);
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,

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

@@ -1445,7 +1445,6 @@ static struct drm_driver kms_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = amdgpu_gem_prime_export,
 	.gem_prime_import = amdgpu_gem_prime_import,
-	.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,
 	.gem_prime_mmap = amdgpu_gem_prime_mmap,

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

@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swiotlb.h>
+#include <linux/dma-buf.h>
 
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
@@ -763,6 +764,7 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
  */
 struct amdgpu_ttm_tt {
 	struct ttm_dma_tt	ttm;
+	struct drm_gem_object	*gobj;
 	u64			offset;
 	uint64_t		userptr;
 	struct task_struct	*usertask;
@@ -1227,6 +1229,7 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 		return NULL;
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
+	gtt->gobj = &bo->base;
 
 	/* allocate space for the uninitialized page entries */
 	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags)) {
@@ -1247,7 +1250,6 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
 	if (gtt && gtt->userptr) {
@@ -1260,7 +1262,19 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 		return 0;
 	}
 
-	if (slave && ttm->sg) {
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG) {
+		if (!ttm->sg) {
+			struct dma_buf_attachment *attach;
+			struct sg_table *sgt;
+
+			attach = gtt->gobj->import_attach;
+			sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+			if (IS_ERR(sgt))
+				return PTR_ERR(sgt);
+
+			ttm->sg = sgt;
+		}
+
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address,
 						 ttm->num_pages);
@@ -1287,9 +1301,8 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
  */
 static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 {
-	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
+	struct amdgpu_device *adev;
 
 	if (gtt && gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
@@ -1298,7 +1311,16 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 		return;
 	}
 
-	if (slave)
+	if (ttm->sg && gtt->gobj->import_attach) {
+		struct dma_buf_attachment *attach;
+
+		attach = gtt->gobj->import_attach;
+		dma_buf_unmap_attachment(attach, ttm->sg, DMA_BIDIRECTIONAL);
+		ttm->sg = NULL;
+		return;
+	}
+
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
 		return;
 
 	adev = amdgpu_ttm_adev(ttm->bdev);