(no subject)

(no subject)

[Christian König]

Next try of prework for unpinned DMA-buf operation.

Only send to intel-gfx to trigger unit tests on the following patches.

Christian.

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/6] dma-buf: add caching of sg_table

[Christian König]

To allow a smooth transition from pinning buffer objects to dynamic
invalidation we first start to cache the sg_table for an attachment
unless the driver explicitly says to not do so.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-buf.c | 24 ++++++++++++++++++++++++
 include/linux/dma-buf.h   | 11 +++++++++++
 2 files changed, 35 insertions(+)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 13884474d158..0bea5eecf554 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -574,6 +574,20 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 	list_add(&attach->node, &dmabuf->attachments);
 
 	mutex_unlock(&dmabuf->lock);
+
+	if (!dmabuf->ops->no_sgt_cache) {
+		struct sg_table *sgt;
+
+		sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL);
+		if (!sgt)
+			sgt = ERR_PTR(-ENOMEM);
+		if (IS_ERR(sgt)) {
+			dma_buf_detach(dmabuf, attach);
+			return ERR_CAST(sgt);
+		}
+		attach->sgt = sgt;
+	}
+
 	return attach;
 
 err_attach:
@@ -596,6 +610,10 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 	if (WARN_ON(!dmabuf || !attach))
 		return;
 
+	if (attach->sgt)
+		dmabuf->ops->unmap_dma_buf(attach, attach->sgt,
+					   DMA_BIDIRECTIONAL);
+
 	mutex_lock(&dmabuf->lock);
 	list_del(&attach->node);
 	if (dmabuf->ops->detach)
@@ -631,6 +649,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf))
 		return ERR_PTR(-EINVAL);
 
+	if (attach->sgt)
+		return attach->sgt;
+
 	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
@@ -658,6 +679,9 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
 		return;
 
+	if (attach->sgt == sg_table)
+		return;
+
 	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
 						direction);
 }
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 58725f890b5b..6534a6769e17 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -51,6 +51,16 @@ struct dma_buf_attachment;
  * @vunmap: [optional] unmaps a vmap from the buffer
  */
 struct dma_buf_ops {
+	/**
+	 * @no_sgt_cache:
+	 *
+	 * Flag controlling the caching of the sg_table in the DMA-buf helpers.
+	 * If not set the sg_table is created during device attaching, if set
+	 * the sg_table is created dynamically when dma_buf_map_attachment() is
+	 * called.
+	 */
+	bool no_sgt_cache;
+
 	/**
 	 * @attach:
 	 *
@@ -323,6 +333,7 @@ struct dma_buf_attachment {
 	struct device *dev;
 	struct list_head node;
 	void *priv;
+	struct sg_table *sgt;
 };
 
 /**
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/6] drm: remove prime sg_table caching

[Christian König]

That is now done by the DMA-buf helpers instead.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/drm_prime.c | 78 +++++++++++----------------------------------
 1 file changed, 18 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 186db2e4c57a..f6bd37eb2a72 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -86,11 +86,6 @@ struct drm_prime_member {
 	struct rb_node handle_rb;
 };
 
-struct drm_prime_attachment {
-	struct sg_table *sgt;
-	enum dma_data_direction dir;
-};
-
 static int drm_prime_add_buf_handle(struct drm_prime_file_private *prime_fpriv,
 				    struct dma_buf *dma_buf, uint32_t handle)
 {
@@ -188,26 +183,17 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
  * @dma_buf: buffer to attach device to
  * @attach: buffer attachment data
  *
- * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for
- * device specific attachment. This can be used as the &dma_buf_ops.attach
- * callback.
+ * Calls &drm_driver.gem_prime_pin for device specific handling. This can be
+ * used as the &dma_buf_ops.attach callback.
  *
  * Returns 0 on success, negative error code on failure.
  */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach)
 {
-	struct drm_prime_attachment *prime_attach;
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
-	prime_attach = kzalloc(sizeof(*prime_attach), GFP_KERNEL);
-	if (!prime_attach)
-		return -ENOMEM;
-
-	prime_attach->dir = DMA_NONE;
-	attach->priv = prime_attach;
-
 	if (!dev->driver->gem_prime_pin)
 		return 0;
 
@@ -226,27 +212,9 @@ EXPORT_SYMBOL(drm_gem_map_attach);
 void drm_gem_map_detach(struct dma_buf *dma_buf,
 			struct dma_buf_attachment *attach)
 {
-	struct drm_prime_attachment *prime_attach = attach->priv;
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
-	if (prime_attach) {
-		struct sg_table *sgt = prime_attach->sgt;
-
-		if (sgt) {
-			if (prime_attach->dir != DMA_NONE)
-				dma_unmap_sg_attrs(attach->dev, sgt->sgl,
-						   sgt->nents,
-						   prime_attach->dir,
-						   DMA_ATTR_SKIP_CPU_SYNC);
-			sg_free_table(sgt);
-		}
-
-		kfree(sgt);
-		kfree(prime_attach);
-		attach->priv = NULL;
-	}
-
 	if (dev->driver->gem_prime_unpin)
 		dev->driver->gem_prime_unpin(obj);
 }
@@ -292,36 +260,21 @@ void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpr
 struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 				     enum dma_data_direction dir)
 {
-	struct drm_prime_attachment *prime_attach = attach->priv;
 	struct drm_gem_object *obj = attach->dmabuf->priv;
 	struct sg_table *sgt;
 
-	if (WARN_ON(dir == DMA_NONE || !prime_attach))
+	if (WARN_ON(dir == DMA_NONE))
 		return ERR_PTR(-EINVAL);
 
-	/* return the cached mapping when possible */
-	if (prime_attach->dir == dir)
-		return prime_attach->sgt;
-
-	/*
-	 * two mappings with different directions for the same attachment are
-	 * not allowed
-	 */
-	if (WARN_ON(prime_attach->dir != DMA_NONE))
-		return ERR_PTR(-EBUSY);
-
 	sgt = obj->dev->driver->gem_prime_get_sg_table(obj);
+	if (IS_ERR(sgt))
+		return sgt;
 
-	if (!IS_ERR(sgt)) {
-		if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
-				      DMA_ATTR_SKIP_CPU_SYNC)) {
-			sg_free_table(sgt);
-			kfree(sgt);
-			sgt = ERR_PTR(-ENOMEM);
-		} else {
-			prime_attach->sgt = sgt;
-			prime_attach->dir = dir;
-		}
+	if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+			      DMA_ATTR_SKIP_CPU_SYNC)) {
+		sg_free_table(sgt);
+		kfree(sgt);
+		sgt = ERR_PTR(-ENOMEM);
 	}
 
 	return sgt;
@@ -334,14 +287,19 @@ EXPORT_SYMBOL(drm_gem_map_dma_buf);
  * @sgt: scatterlist info of the buffer to unmap
  * @dir: direction of DMA transfer
  *
- * Not implemented. The unmap is done at drm_gem_map_detach().  This can be
- * used as the &dma_buf_ops.unmap_dma_buf callback.
+ * This can be used as the &dma_buf_ops.unmap_dma_buf callback.
  */
 void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 			   struct sg_table *sgt,
 			   enum dma_data_direction dir)
 {
-	/* nothing to be done here */
+	if (!sgt)
+		return;
+
+	dma_unmap_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+			   DMA_ATTR_SKIP_CPU_SYNC);
+	sg_free_table(sgt);
+	kfree(sgt);
 }
 EXPORT_SYMBOL(drm_gem_unmap_dma_buf);
 
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 3/6] dma-buf: add dma_buf_(un)map_attachment_locked variants v3

[Christian König]

Add function variants which can be called with the reservation lock
already held.

v2: reordered, add lockdep asserts, fix kerneldoc
v3: rebased on sgt caching

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-buf.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dma-buf.h   |  5 ++++
 2 files changed, 68 insertions(+)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 0bea5eecf554..e68322c953a9 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -624,6 +624,43 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 }
 EXPORT_SYMBOL_GPL(dma_buf_detach);
 
+/**
+ * dma_buf_map_attachment_locked - Maps the buffer into _device_ address space
+ * with the reservation lock held. Is a wrapper for map_dma_buf() of the
+ *
+ * Returns the scatterlist table of the attachment;
+ * dma_buf_ops.
+ * @attach:	[in]	attachment whose scatterlist is to be returned
+ * @direction:	[in]	direction of DMA transfer
+ *
+ * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
+ * on error. May return -EINTR if it is interrupted by a signal.
+ *
+ * A mapping must be unmapped by using dma_buf_unmap_attachment_locked(). Note
+ * that the underlying backing storage is pinned for as long as a mapping
+ * exists, therefore users/importers should not hold onto a mapping for undue
+ * amounts of time.
+ */
+struct sg_table *
+dma_buf_map_attachment_locked(struct dma_buf_attachment *attach,
+			      enum dma_data_direction direction)
+{
+	struct sg_table *sg_table;
+
+	might_sleep();
+	reservation_object_assert_held(attach->dmabuf->resv);
+
+	if (attach->sgt)
+		return attach->sgt;
+
+	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
+	if (!sg_table)
+		sg_table = ERR_PTR(-ENOMEM);
+
+	return sg_table;
+}
+EXPORT_SYMBOL_GPL(dma_buf_map_attachment_locked);
+
 /**
  * dma_buf_map_attachment - Returns the scatterlist table of the attachment;
  * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the
@@ -660,6 +697,32 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 }
 EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
 
+/**
+ * dma_buf_unmap_attachment_locked - unmaps the buffer with reservation lock
+ * held, should deallocate the associated scatterlist. Is a wrapper for
+ * unmap_dma_buf() of dma_buf_ops.
+ * @attach:	[in]	attachment to unmap buffer from
+ * @sg_table:	[in]	scatterlist info of the buffer to unmap
+ * @direction:  [in]    direction of DMA transfer
+ *
+ * This unmaps a DMA mapping for @attached obtained by
+ * dma_buf_map_attachment_locked().
+ */
+void dma_buf_unmap_attachment_locked(struct dma_buf_attachment *attach,
+				     struct sg_table *sg_table,
+				     enum dma_data_direction direction)
+{
+	might_sleep();
+	reservation_object_assert_held(attach->dmabuf->resv);
+
+	if (attach->sgt == sg_table)
+		return;
+
+	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
+						direction);
+}
+EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment_locked);
+
 /**
  * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might
  * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 6534a6769e17..a40f8f586a95 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -395,8 +395,13 @@ int dma_buf_fd(struct dma_buf *dmabuf, int flags);
 struct dma_buf *dma_buf_get(int fd);
 void dma_buf_put(struct dma_buf *dmabuf);
 
+struct sg_table *dma_buf_map_attachment_locked(struct dma_buf_attachment *,
+					       enum dma_data_direction);
 struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *,
 					enum dma_data_direction);
+void dma_buf_unmap_attachment_locked(struct dma_buf_attachment *,
+				     struct sg_table *,
+				     enum dma_data_direction);
 void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *,
 				enum dma_data_direction);
 int dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 4/6] dma-buf: lock the reservation object during (un)map_dma_buf v3

[Christian König]

First step towards unpinned DMA buf operation.

I've checked the DRM drivers to potential locking of the reservation
object, but essentially we need to audit all implementations of the
dma_buf _ops for this to work.

v2: reordered
v3: rebased on sgt caching

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-buf.c | 15 ++++++---------
 include/linux/dma-buf.h   |  6 ++++++
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e68322c953a9..21608306349d 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -686,10 +686,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf))
 		return ERR_PTR(-EINVAL);
 
-	if (attach->sgt)
-		return attach->sgt;
-
-	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
+	reservation_object_lock(attach->dmabuf->resv, NULL);
+	sg_table = dma_buf_map_attachment_locked(attach, direction);
+	reservation_object_unlock(attach->dmabuf->resv);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
 
@@ -742,11 +741,9 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
 		return;
 
-	if (attach->sgt == sg_table)
-		return;
-
-	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
-						direction);
+	reservation_object_lock(attach->dmabuf->resv, NULL);
+	dma_buf_unmap_attachment_locked(attach, sg_table, direction);
+	reservation_object_unlock(attach->dmabuf->resv);
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
 
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index a40f8f586a95..e964077a7e7e 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -128,6 +128,9 @@ struct dma_buf_ops {
 	 * any other kind of sharing that the exporter might wish to make
 	 * available to buffer-users.
 	 *
+	 * This is always called with the dmabuf->resv object locked when
+	 * no_sgt_cache is true.
+	 *
 	 * Returns:
 	 *
 	 * A &sg_table scatter list of or the backing storage of the DMA buffer,
@@ -148,6 +151,9 @@ struct dma_buf_ops {
 	 * It should also unpin the backing storage if this is the last mapping
 	 * of the DMA buffer, it the exporter supports backing storage
 	 * migration.
+	 *
+	 * This is always called with the dmabuf->resv object locked when
+	 * no_sgt_cache is true.
 	 */
 	void (*unmap_dma_buf)(struct dma_buf_attachment *,
 			      struct sg_table *,
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

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

[Christian König]

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 --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,
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 6/6] drm/amdgpu: add independent DMA-buf import v4

[Christian König]

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

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h       |  4 ----
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c   |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 38 +++++++++++++++++++------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c   | 34 +++++++++++++++++++++++----
 4 files changed, 52 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 269664fd00de..31c6edd77f2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -374,10 +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 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_device *dev,
 					struct drm_gem_object *gobj,
 					int flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 04ef967e128c..c632e14257d2 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_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,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 75c70ddbc080..13033ff48cb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -122,31 +122,28 @@ int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma
 }
 
 /**
- * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
- * implementation
+ * amdgpu_gem_prime_create_obj - create BO for DMA-buf import
+ *
  * @dev: DRM device
- * @attach: DMA-buf attachment
- * @sg: Scatter/gather table
+ * @dma_buf: DMA-buf
  *
- * Import shared DMA buffer memory exported by another device.
+ * Creates an empty SG BO for DMA-buf import.
  *
  * Returns:
  * A new GEM buffer object 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_gem_prime_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 {
-	struct reservation_object *resv = attach->dmabuf->resv;
+	struct reservation_object *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;
@@ -157,11 +154,9 @@ 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;
 
 	ww_mutex_unlock(&resv->lock);
@@ -377,6 +372,7 @@ struct dma_buf *amdgpu_gem_prime_export(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) {
@@ -391,5 +387,17 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 		}
 	}
 
-	return drm_gem_prime_import(dev, dma_buf);
+	obj = amdgpu_gem_prime_create_obj(dev, dma_buf);
+	if (IS_ERR(obj))
+		return obj;
+
+	attach = dma_buf_attach(dma_buf, dev->dev);
+	if (IS_ERR(attach)) {
+		drm_gem_object_put(obj);
+		return ERR_CAST(attach);
+	}
+
+	get_dma_buf(dma_buf);
+	obj->import_attach = attach;
+	return obj;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0e47f15b0f97..ee85e49e3b07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -43,6 +43,7 @@
 #include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include <linux/iommu.h>
+#include <linux/dma-buf.h>
 #include "amdgpu.h"
 #include "amdgpu_object.h"
 #include "amdgpu_trace.h"
@@ -798,6 +799,7 @@ struct amdgpu_ttm_gup_task_list {
 
 struct amdgpu_ttm_tt {
 	struct ttm_dma_tt	ttm;
+	struct drm_gem_object	*gobj;
 	u64			offset;
 	uint64_t		userptr;
 	struct task_struct	*usertask;
@@ -1222,6 +1224,7 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 		return NULL;
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
+	gtt->gobj = &ttm_to_amdgpu_bo(bo)->gem_base;
 
 	/* allocate space for the uninitialized page entries */
 	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags)) {
@@ -1242,7 +1245,6 @@ 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) {
@@ -1255,7 +1257,20 @@ 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_locked(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);
@@ -1282,9 +1297,8 @@ 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);
@@ -1293,7 +1307,17 @@ 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_locked(attach, ttm->sg,
+						DMA_BIDIRECTIONAL);
+		ttm->sg = NULL;
+		return;
+	}
+
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
 		return;
 
 	adev = amdgpu_ttm_adev(ttm->bdev);
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.BAT: failure for series starting with [1/6] dma-buf: add caching of sg_table

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: add caching of sg_table
URL   : https://patchwork.freedesktop.org/series/46080/
State : failure

== Summary ==

Applying: dma-buf: add caching of sg_table
Applying: drm: remove prime sg_table caching
Applying: dma-buf: add dma_buf_(un)map_attachment_locked variants v3
Applying: dma-buf: lock the reservation object during (un)map_dma_buf v3
Applying: drm/amdgpu: add independent DMA-buf export v3
error: sha1 information is lacking or useless (drivers/gpu/drm/amd/amdgpu/amdgpu.h).
error: could not build fake ancestor
Patch failed at 0005 drm/amdgpu: add independent DMA-buf export v3
Use 'git am --show-current-patch' to see the failed patch
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx