[PATCH 1/6] dma-buf: add dynamic DMA-buf handling v9

[PATCH 1/6] dma-buf: add dynamic DMA-buf handling v9

[Christian König]

On the exporter side we add optional explicit pinning callbacks. If those
callbacks are implemented the framework no longer caches sg tables and the
map/unmap callbacks are always called with the lock of the reservation object
held.

On the importer side we add an optional invalidate callback. This callback is
used by the exporter to inform the importers that their mappings should be
destroyed as soon as possible.

This allows the exporter to provide the mappings without the need to pin
the backing store.

v2: don't try to invalidate mappings when the callback is NULL,
    lock the reservation obj while using the attachments,
    add helper to set the callback
v3: move flag for invalidation support into the DMA-buf,
    use new attach_info structure to set the callback
v4: use importer_priv field instead of mangling exporter priv.
v5: drop invalidation_supported flag
v6: squash together with pin/unpin changes
v7: pin/unpin takes an attachment now
v8: nuke dma_buf_attachment_(map|unmap)_locked,
    everything is now handled backward compatible
v9: always cache when export/importer don't agree on dynamic handling

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-buf.c | 188 ++++++++++++++++++++++++++++++++++++--
 include/linux/dma-buf.h   | 109 ++++++++++++++++++++--
 2 files changed, 283 insertions(+), 14 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index a2d34c6b80a5..f756870ba509 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -409,6 +409,9 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (WARN_ON(exp_info->ops->cache_sgt_mapping && exp_info->ops->pin))
+		return ERR_PTR(-EINVAL);
+
 	if (!try_module_get(exp_info->owner))
 		return ERR_PTR(-ENOENT);
 
@@ -530,10 +533,12 @@ void dma_buf_put(struct dma_buf *dmabuf)
 EXPORT_SYMBOL_GPL(dma_buf_put);
 
 /**
- * dma_buf_attach - Add the device to dma_buf's attachments list; optionally,
+ * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally,
  * calls attach() of dma_buf_ops to allow device-specific attach functionality
- * @dmabuf:	[in]	buffer to attach device to.
- * @dev:	[in]	device to be attached.
+ * @dmabuf:		[in]	buffer to attach device to.
+ * @dev:		[in]	device to be attached.
+ * @importer_ops	[in]	importer operations for the attachment
+ * @importer_priv	[in]	importer private pointer for the attachment
  *
  * Returns struct dma_buf_attachment pointer for this attachment. Attachments
  * must be cleaned up by calling dma_buf_detach().
@@ -547,8 +552,10 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
  * accessible to @dev, and cannot be moved to a more suitable place. This is
  * indicated with the error code -EBUSY.
  */
-struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
-					  struct device *dev)
+struct dma_buf_attachment *
+dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
+		       const struct dma_buf_attach_ops *importer_ops,
+		       void *importer_priv)
 {
 	struct dma_buf_attachment *attach;
 	int ret;
@@ -562,6 +569,8 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 
 	attach->dev = dev;
 	attach->dmabuf = dmabuf;
+	attach->importer_ops = importer_ops;
+	attach->importer_priv = importer_priv;
 
 	mutex_lock(&dmabuf->lock);
 
@@ -570,16 +579,72 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 		if (ret)
 			goto err_attach;
 	}
+	reservation_object_lock(dmabuf->resv, NULL);
 	list_add(&attach->node, &dmabuf->attachments);
+	reservation_object_unlock(dmabuf->resv);
 
 	mutex_unlock(&dmabuf->lock);
 
+	/* When either the importer or the exporter can't handle dynamic
+	 * mappings we cache the mapping here to avoid issues with the
+	 * reservation object lock.
+	 */
+	if (dma_buf_attachment_is_dynamic(attach) !=
+	    dma_buf_is_dynamic(dmabuf)) {
+		struct sg_table *sgt;
+
+		if (dma_buf_is_dynamic(attach->dmabuf)) {
+			reservation_object_lock(attach->dmabuf->resv, NULL);
+			ret = dma_buf_pin(attach);
+			if (ret)
+				goto err_unlock;
+		}
+
+		sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL);
+		if (!sgt)
+			sgt = ERR_PTR(-ENOMEM);
+		if (IS_ERR(sgt)) {
+			ret = PTR_ERR(sgt);
+			goto err_unpin;
+		}
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			reservation_object_unlock(attach->dmabuf->resv);
+		attach->sgt = sgt;
+		attach->dir = DMA_BIDIRECTIONAL;
+	}
+
 	return attach;
 
 err_attach:
 	kfree(attach);
 	mutex_unlock(&dmabuf->lock);
 	return ERR_PTR(ret);
+
+err_unpin:
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		dma_buf_unpin(attach);
+
+err_unlock:
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		reservation_object_unlock(attach->dmabuf->resv);
+
+	dma_buf_detach(dmabuf, attach);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach);
+
+/**
+ * dma_buf_attach - Wrapper for dma_buf_dynamic_attach
+ * @dmabuf:	[in]	buffer to attach device to.
+ * @dev:	[in]	device to be attached.
+ *
+ * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static
+ * mapping.
+ */
+struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
+					  struct device *dev)
+{
+	return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(dma_buf_attach);
 
@@ -596,11 +661,22 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 	if (WARN_ON(!dmabuf || !attach))
 		return;
 
-	if (attach->sgt)
+	if (attach->sgt) {
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			reservation_object_lock(attach->dmabuf->resv, NULL);
+
 		dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir);
 
+		if (dma_buf_is_dynamic(attach->dmabuf)) {
+			dma_buf_unpin(attach);
+			reservation_object_unlock(attach->dmabuf->resv);
+		}
+	}
+
 	mutex_lock(&dmabuf->lock);
+	reservation_object_lock(dmabuf->resv, NULL);
 	list_del(&attach->node);
+	reservation_object_unlock(dmabuf->resv);
 	if (dmabuf->ops->detach)
 		dmabuf->ops->detach(dmabuf, attach);
 
@@ -609,6 +685,44 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 }
 EXPORT_SYMBOL_GPL(dma_buf_detach);
 
+/**
+ * dma_buf_pin - Lock down the DMA-buf
+ *
+ * @attach:	[in]	attachment which should be pinned
+ *
+ * Returns:
+ * 0 on success, negative error code on failure.
+ */
+int dma_buf_pin(struct dma_buf_attachment *attach)
+{
+	struct dma_buf *dmabuf = attach->dmabuf;
+	int ret = 0;
+
+	reservation_object_assert_held(dmabuf->resv);
+
+	if (dmabuf->ops->pin)
+		ret = dmabuf->ops->pin(attach);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dma_buf_pin);
+
+/**
+ * dma_buf_unpin - Remove lock from DMA-buf
+ *
+ * @attach:	[in]	attachment which should be unpinned
+ */
+void dma_buf_unpin(struct dma_buf_attachment *attach)
+{
+	struct dma_buf *dmabuf = attach->dmabuf;
+
+	reservation_object_assert_held(dmabuf->resv);
+
+	if (dmabuf->ops->unpin)
+		dmabuf->ops->unpin(attach);
+}
+EXPORT_SYMBOL_GPL(dma_buf_unpin);
+
 /**
  * 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
@@ -628,6 +742,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 					enum dma_data_direction direction)
 {
 	struct sg_table *sg_table;
+	int r;
 
 	might_sleep();
 
@@ -646,10 +761,38 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		return attach->sgt;
 	}
 
+	if (dma_buf_attachment_is_dynamic(attach)) {
+		reservation_object_assert_held(attach->dmabuf->resv);
+
+		/*
+		 * Mapping a DMA-buf can trigger its invalidation, prevent
+		 * sending this event to the caller by temporary removing
+		 * this attachment from the list.
+		 */
+		list_del(&attach->node);
+
+	} else if (dma_buf_is_dynamic(attach->dmabuf)) {
+		reservation_object_lock(attach->dmabuf->resv, NULL);
+		r = dma_buf_pin(attach);
+		if (r) {
+			reservation_object_unlock(attach->dmabuf->resv);
+			return ERR_PTR(r);
+		}
+	}
+
 	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
 
+	if (dma_buf_attachment_is_dynamic(attach)) {
+		list_add(&attach->node, &attach->dmabuf->attachments);
+
+	} else if (dma_buf_is_dynamic(attach->dmabuf)) {
+		if (IS_ERR(sg_table))
+			dma_buf_unpin(attach);
+		reservation_object_unlock(attach->dmabuf->resv);
+	}
+
 	if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) {
 		attach->sgt = sg_table;
 		attach->dir = direction;
@@ -681,10 +824,41 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 	if (attach->sgt == sg_table)
 		return;
 
+	if (dma_buf_attachment_is_dynamic(attach))
+		reservation_object_assert_held(attach->dmabuf->resv);
+	else if (dma_buf_is_dynamic(attach->dmabuf))
+		reservation_object_lock(attach->dmabuf->resv, NULL);
+
 	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
+
+	if (dma_buf_is_dynamic(attach->dmabuf) &&
+	    !dma_buf_attachment_is_dynamic(attach)) {
+		dma_buf_unpin(attach);
+		reservation_object_unlock(attach->dmabuf->resv);
+	}
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
 
+/**
+ * dma_buf_invalidate_mappings - invalidate all mappings of this dma_buf
+ *
+ * @dmabuf:	[in]	buffer which mappings should be invalidated
+ *
+ * Informs all attachmenst that they need to destroy and recreated all their
+ * mappings.
+ */
+void dma_buf_invalidate_mappings(struct dma_buf *dmabuf)
+{
+	struct dma_buf_attachment *attach;
+
+	reservation_object_assert_held(dmabuf->resv);
+
+	list_for_each_entry(attach, &dmabuf->attachments, node)
+		if (attach->importer_ops && attach->importer_ops->invalidate)
+			attach->importer_ops->invalidate(attach);
+}
+EXPORT_SYMBOL_GPL(dma_buf_invalidate_mappings);
+
 /**
  * DOC: cpu access
  *
@@ -1097,10 +1271,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 		seq_puts(s, "\tAttached Devices:\n");
 		attach_count = 0;
 
+		reservation_object_lock(buf_obj->resv, NULL);
 		list_for_each_entry(attach_obj, &buf_obj->attachments, node) {
 			seq_printf(s, "\t%s\n", dev_name(attach_obj->dev));
 			attach_count++;
 		}
+		reservation_object_unlock(buf_obj->resv);
 
 		seq_printf(s, "Total %d devices attached\n\n",
 				attach_count);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 45b9767e67ec..5309f1ceaefe 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -99,14 +99,40 @@ struct dma_buf_ops {
 	 */
 	void (*detach)(struct dma_buf *, struct dma_buf_attachment *);
 
+	/**
+	 * @pin:
+	 *
+	 * This is called by dma_buf_pin and lets the exporter know that the
+	 * DMA-buf can't be moved any more.
+	 *
+	 * This is called with the dmabuf->resv object locked.
+	 *
+	 * This callback is optional.
+	 *
+	 * Returns:
+	 *
+	 * 0 on success, negative error code on failure.
+	 */
+	int (*pin)(struct dma_buf_attachment *);
+
+	/**
+	 * @unpin:
+	 *
+	 * This is called by dma_buf_unpin and lets the exporter know that the
+	 * DMA-buf can be moved again.
+	 *
+	 * This is called with the dmabuf->resv object locked.
+	 *
+	 * This callback is optional.
+	 */
+	void (*unpin)(struct dma_buf_attachment *);
+
 	/**
 	 * @map_dma_buf:
 	 *
 	 * This is called by dma_buf_map_attachment() and is used to map a
 	 * shared &dma_buf into device address space, and it is mandatory. It
-	 * can only be called if @attach has been called successfully. This
-	 * essentially pins the DMA buffer into place, and it cannot be moved
-	 * any more
+	 * can only be called if @attach has been called successfully.
 	 *
 	 * This call may sleep, e.g. when the backing storage first needs to be
 	 * allocated, or moved to a location suitable for all currently attached
@@ -127,6 +153,9 @@ 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
+	 * the pin/unpin callbacks are implemented.
+	 *
 	 * Returns:
 	 *
 	 * A &sg_table scatter list of or the backing storage of the DMA buffer,
@@ -144,9 +173,6 @@ struct dma_buf_ops {
 	 *
 	 * This is called by dma_buf_unmap_attachment() and should unmap and
 	 * release the &sg_table allocated in @map_dma_buf, and it is mandatory.
-	 * It should also unpin the backing storage if this is the last mapping
-	 * of the DMA buffer, it the exporter supports backing storage
-	 * migration.
 	 */
 	void (*unmap_dma_buf)(struct dma_buf_attachment *,
 			      struct sg_table *,
@@ -311,6 +337,35 @@ struct dma_buf {
 	} cb_excl, cb_shared;
 };
 
+/**
+ * struct dma_buf_attach_ops - importer operations for an attachment
+ * @invalidate: [optional] invalidate all mappings made using this attachment.
+ *
+ * Attachment operations implemented by the importer.
+ */
+struct dma_buf_attach_ops {
+	/**
+	 * @invalidate:
+	 *
+	 * If the invalidate callback is provided the framework can avoid
+	 * pinning the backing store while mappings exists.
+	 *
+	 * This callback is called with the lock of the reservation object
+	 * associated with the dma_buf held and the mapping function must be
+	 * called with this lock held as well. This makes sure that no mapping
+	 * is created concurrently with an ongoing invalidation.
+	 *
+	 * After the callback all existing mappings are still valid until all
+	 * fences in the dma_bufs reservation object are signaled. After getting an
+	 * invalidation callback all mappings should be destroyed by the importer using
+	 * the normal dma_buf_unmap_attachment() function as soon as possible.
+	 *
+	 * New mappings can be created immediately, but can't be used before the
+	 * exclusive fence in the dma_bufs reservation object is signaled.
+	 */
+	void (*invalidate)(struct dma_buf_attachment *attach);
+};
+
 /**
  * struct dma_buf_attachment - holds device-buffer attachment data
  * @dmabuf: buffer for this attachment.
@@ -319,6 +374,8 @@ struct dma_buf {
  * @sgt: cached mapping.
  * @dir: direction of cached mapping.
  * @priv: exporter specific attachment data.
+ * @importer_ops: importer operations for this attachment.
+ * @importer_priv: importer specific attachment data.
  *
  * This structure holds the attachment information between the dma_buf buffer
  * and its user device(s). The list contains one attachment struct per device
@@ -336,6 +393,9 @@ struct dma_buf_attachment {
 	struct sg_table *sgt;
 	enum dma_data_direction dir;
 	void *priv;
+
+	const struct dma_buf_attach_ops *importer_ops;
+	void *importer_priv;
 };
 
 /**
@@ -386,10 +446,42 @@ static inline void get_dma_buf(struct dma_buf *dmabuf)
 	get_file(dmabuf->file);
 }
 
+/**
+ * dma_buf_is_dynamic - check if a DMA-buf uses dynamic mappings.
+ * @dmabuf: the DMA-buf to check
+ *
+ * Returns true if a DMA-buf exporter wants to create dynamic sg table mappings
+ * for each attachment. False if only a single static sg table should be used.
+ */
+static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf)
+{
+	return !!dmabuf->ops->pin;
+}
+
+/**
+ * dma_buf_attachment_is_dynamic - check if a DMA-buf attachment uses dynamic
+ * mappinsg
+ * @attach: the DMA-buf attachment to check
+ *
+ * Returns true if a DMA-buf importer wants to use dynamic sg table mappings and
+ * calls the map/unmap functions with the reservation object locked.
+ */
+static inline bool
+dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach)
+{
+	return attach->importer_ops && attach->importer_ops->invalidate;
+}
+
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
-							struct device *dev);
+					  struct device *dev);
+struct dma_buf_attachment *
+dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
+		       const struct dma_buf_attach_ops *importer_ops,
+		       void *importer_priv);
 void dma_buf_detach(struct dma_buf *dmabuf,
-				struct dma_buf_attachment *dmabuf_attach);
+		    struct dma_buf_attachment *attach);
+int dma_buf_pin(struct dma_buf_attachment *attach);
+void dma_buf_unpin(struct dma_buf_attachment *attach);
 
 struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info);
 
@@ -401,6 +493,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *,
 					enum dma_data_direction);
 void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *,
 				enum dma_data_direction);
+void dma_buf_invalidate_mappings(struct dma_buf *dma_buf);
 int dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 			     enum dma_data_direction dir);
 int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 2/6] drm/ttm: remove the backing store if no placement is given

[Christian König]

Pipeline removal of the BOs backing store when no placement is given
during validation.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c7de667d482a..682a1a035b35 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1240,6 +1240,18 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	uint32_t new_flags;
 
 	reservation_object_assert_held(bo->resv);
+
+	/*
+	 * Remove the backing store if no placement is given.
+	 */
+	if (!placement->num_placement && !placement->num_busy_placement) {
+		ret = ttm_bo_pipeline_gutting(bo);
+		if (ret)
+			return ret;
+
+		return ttm_tt_create(bo, false);
+	}
+
 	/*
 	 * Check whether we need to move buffer.
 	 */
-- 
2.17.1

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

[PATCH 3/6] drm/ttm: use the parent resv for ghost objects v2

[Christian König]

This way we can even pipeline imported BO evictions.

v2: Limit this to only cases when the parent object uses a separate reservation
    object as well. This fixes another OOM problem.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 895d77d799e4..95f47d685921 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -517,9 +517,11 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	kref_init(&fbo->base.kref);
 	fbo->base.destroy = &ttm_transfered_destroy;
 	fbo->base.acc_size = 0;
-	fbo->base.resv = &fbo->base.ttm_resv;
-	reservation_object_init(fbo->base.resv);
-	ret = reservation_object_trylock(fbo->base.resv);
+	if (bo->resv == &bo->ttm_resv)
+		fbo->base.resv = &fbo->base.ttm_resv;
+
+	reservation_object_init(&fbo->base.ttm_resv);
+	ret = reservation_object_trylock(&fbo->base.ttm_resv);
 	WARN_ON(!ret);
 
 	*new_obj = &fbo->base;
@@ -716,7 +718,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		reservation_object_add_excl_fence(ghost_obj->resv, fence);
+		reservation_object_add_excl_fence(&ghost_obj->ttm_resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object
@@ -729,7 +731,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		reservation_object_unlock(&ghost_obj->ttm_resv);
 		ttm_bo_put(ghost_obj);
 	}
 
@@ -772,7 +774,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		reservation_object_add_excl_fence(ghost_obj->resv, fence);
+		reservation_object_add_excl_fence(&ghost_obj->ttm_resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object
@@ -785,7 +787,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		reservation_object_unlock(&ghost_obj->ttm_resv);
 		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
@@ -841,7 +843,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	if (ret)
 		return ret;
 
-	ret = reservation_object_copy_fences(ghost->resv, bo->resv);
+	ret = reservation_object_copy_fences(&ghost->ttm_resv, bo->resv);
 	/* Last resort, wait for the BO to be idle when we are OOM */
 	if (ret)
 		ttm_bo_wait(bo, false, false);
@@ -850,7 +852,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->mem.mem_type = TTM_PL_SYSTEM;
 	bo->ttm = NULL;
 
-	ttm_bo_unreserve(ghost);
+	reservation_object_unlock(&ghost->ttm_resv);
 	ttm_bo_put(ghost);
 
 	return 0;
-- 
2.17.1

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

[PATCH 4/6] drm/amdgpu: use allowed_domains for exported DMA-bufs

[Christian König]

Avoid that we ping/pong the buffers when we stop to pin DMA-buf
exports by using the allowed domains for exported buffers.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 3e2da24cd17a..a59780654335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -26,6 +26,7 @@
  */
 #include <linux/pagemap.h>
 #include <linux/sync_file.h>
+#include <linux/dma-buf.h>
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_syncobj.h>
@@ -412,7 +413,9 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	/* Don't move this buffer if we have depleted our allowance
 	 * to move it. Don't move anything if the threshold is zero.
 	 */
-	if (p->bytes_moved < p->bytes_moved_threshold) {
+	if (p->bytes_moved < p->bytes_moved_threshold &&
+	    (!bo->gem_base.dma_buf ||
+	    list_empty(&bo->gem_base.dma_buf->attachments))) {
 		if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 		    (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) {
 			/* And don't move a CPU_ACCESS_REQUIRED BO to limited
-- 
2.17.1

_______________________________________________
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_dma_buf.c | 204 ++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h |   1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c     |   1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c  |   5 +
 4 files changed, 133 insertions(+), 78 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 4711cf1b5bd2..68a071060793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -40,22 +40,6 @@
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
 
-/**
- * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
- * implementation
- * @obj: GEM buffer object (BO)
- *
- * Returns:
- * A scatter/gather table for the pinned pages of the BO'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 BO
@@ -181,92 +165,158 @@ __reservation_object_make_exclusive(struct reservation_object *obj)
 }
 
 /**
- * amdgpu_dma_buf_map_attach - &dma_buf_ops.attach implementation
- * @dma_buf: Shared DMA buffer
+ * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
+ *
+ * @dmabuf: DMA-buf where we attach to
+ * @attach: attachment to add
+ *
+ * Add the attachment as user to the exported DMA-buf.
+ */
+static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
+				 struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	int r;
+
+	if (attach->dev->driver == adev->dev->driver)
+		return 0;
+
+	/*
+	 * We only create shared fences for internal use, but importers
+	 * of the dmabuf rely on exclusive fences for implicitly
+	 * tracking write hazards. As any of the current fences may
+	 * correspond to a write, we need to convert all existing
+	 * fences on the reservation object into a single exclusive
+	 * fence.
+	 */
+	r = __reservation_object_make_exclusive(bo->tbo.resv);
+	if (r)
+		return r;
+
+	bo->prime_shared_count++;
+	return 0;
+}
+
+/**
+ * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
+ *
+ * @dmabuf: DMA-buf where we remove the attachment from
+ * @attach: the attachment to remove
+ *
+ * Called when an attachment is removed from the DMA-buf.
+ */
+static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
+				  struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
+		bo->prime_shared_count--;
+}
+
+/**
+ * amdgpu_dma_buf_pin - &dma_buf_ops.pin implementation
+ *
+ * @attach: attachment to pin down
+ *
+ * Pin the BO which is backing the DMA-buf so that it can't move any more.
+ */
+static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = attach->dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	/* pin buffer into GTT */
+	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+}
+
+/**
+ * amdgpu_dma_buf_unpin - &dma_buf_ops.unpin implementation
+ *
+ * @attach: attachment to unpin
+ *
+ * Unpin a previously pinned BO to make it movable again.
+ */
+static void amdgpu_dma_buf_unpin(struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = attach->dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	amdgpu_bo_unpin(bo);
+}
+
+/**
+ * amdgpu_dma_buf_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 a negative error code on failure.
+ * sg_table filled with the DMA addresses to use or ERR_PRT with negative error
+ * code.
  */
-static int amdgpu_dma_buf_map_attach(struct dma_buf *dma_buf,
-				     struct dma_buf_attachment *attach)
+static struct sg_table *
+amdgpu_dma_buf_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;
+	if (!bo->pin_count) {
+		/* move buffer into GTT */
+		struct ttm_operation_ctx ctx = { false, false };
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (unlikely(r != 0))
-		goto error_detach;
-
-
-	if (attach->dev->driver != adev->dev->driver) {
-		/*
-		 * We only create shared fences for internal use, but importers
-		 * of the dmabuf rely on exclusive fences for implicitly
-		 * tracking write hazards. As any of the current fences may
-		 * correspond to a write, we need to convert all existing
-		 * fences on the reservation object into a single exclusive
-		 * fence.
-		 */
-		r = __reservation_object_make_exclusive(bo->tbo.resv);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (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;
+	sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);
+	if (IS_ERR(sgt))
+		return sgt;
 
-	if (attach->dev->driver != adev->dev->driver)
-		bo->prime_shared_count++;
+	if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+			      DMA_ATTR_SKIP_CPU_SYNC))
+		goto error_free;
 
-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_dma_buf_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
  * another device. For now, simply unpins the buffer from GTT.
  */
-static void amdgpu_dma_buf_map_detach(struct dma_buf *dma_buf,
-				      struct dma_buf_attachment *attach)
+static void amdgpu_dma_buf_unmap_dma_buf(struct dma_buf_attachment *attach,
+					 struct sg_table *sgt,
+					 enum dma_data_direction dir)
 {
-	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);
+	if (!sgt)
+		return;
 
-error:
-	drm_gem_map_detach(dma_buf, attach);
+	dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+	sg_free_table(sgt);
+	kfree(sgt);
 }
 
 /**
@@ -324,10 +374,12 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 }
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
-	.attach = amdgpu_dma_buf_map_attach,
-	.detach = amdgpu_dma_buf_map_detach,
-	.map_dma_buf = drm_gem_map_dma_buf,
-	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.attach = amdgpu_dma_buf_attach,
+	.detach = amdgpu_dma_buf_detach,
+	.pin = amdgpu_dma_buf_pin,
+	.unpin = amdgpu_dma_buf_unpin,
+	.map_dma_buf = amdgpu_dma_buf_map_dma_buf,
+	.unmap_dma_buf = amdgpu_dma_buf_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
 	.mmap = drm_gem_dmabuf_mmap,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
index c7056cbe8685..f1522292814c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
@@ -25,7 +25,6 @@
 
 #include <drm/drm_gem.h>
 
-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 1f38d6fc1fe3..0e9fe121df90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1333,7 +1333,6 @@ 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_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 30493429851e..afde06947ff4 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>
@@ -1198,6 +1199,10 @@ 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);
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 6/6] drm/amdgpu: add independent DMA-buf import v6

[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
v5: rebased and cleanup on new DMA-buf interface
v6: squash with invalidation callback change,
    stop using _(map|unmap)_locked

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 65 ++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h |  4 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c     |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c  |  6 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c     | 32 ++++++++--
 5 files changed, 83 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 68a071060793..63dedc93c3d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -420,31 +420,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 }
 
 /**
- * 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 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;
@@ -455,11 +452,9 @@ 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);
@@ -470,6 +465,32 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	return ERR_PTR(ret);
 }
 
+/**
+ * amdgpu_gem_prime_invalidate_mappings - &attach.invalidate implementation
+ *
+ * @attach: the DMA-buf attachment
+ *
+ * Invalidate the DMA-buf attachment, making sure that the we re-create the
+ * mapping before the next use.
+ */
+static void
+amdgpu_gem_prime_invalidate_mappings(struct dma_buf_attachment *attach)
+{
+	struct ttm_operation_ctx ctx = { false, false };
+	struct drm_gem_object *obj = attach->importer_priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct ttm_placement placement = {};
+	int r;
+
+	r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
+	if (r)
+		DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
+}
+
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
+	.invalidate = amdgpu_gem_prime_invalidate_mappings
+};
+
 /**
  * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
  * @dev: DRM device
@@ -484,6 +505,7 @@ 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) {
@@ -498,5 +520,18 @@ 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,
+					&amdgpu_dma_buf_attach_ops, obj);
+	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_dma_buf.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
index f1522292814c..2765413770b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
+++ b/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_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 0e9fe121df90..9d6dd1853c3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1333,7 +1333,6 @@ 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_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index afde06947ff4..4bb1256dd980 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -854,6 +854,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return 0;
 	}
 
+	if (bo->gem_base.import_attach)
+		dma_buf_pin(bo->gem_base.import_attach);
+
 	bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 	/* force to pin into visible video ram */
 	if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
@@ -937,6 +940,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 
 	amdgpu_bo_subtract_pin_size(bo);
 
+	if (bo->gem_base.import_attach)
+		dma_buf_unpin(bo->gem_base.import_attach);
+
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		bo->placements[i].lpfn = 0;
 		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 7138dc1dd1f4..f8d9f3779f76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -44,6 +44,7 @@
 #include <linux/debugfs.h>
 #include <linux/iommu.h>
 #include <linux/hmm.h>
+#include <linux/dma-buf.h>
 #include "amdgpu.h"
 #include "amdgpu_object.h"
 #include "amdgpu_trace.h"
@@ -706,6 +707,7 @@ 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;
@@ -1193,6 +1195,7 @@ 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)) {
@@ -1213,7 +1216,6 @@ 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) {
@@ -1226,7 +1228,19 @@ 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);
@@ -1253,9 +1267,8 @@ 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);
@@ -1264,7 +1277,16 @@ 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);
-- 
2.17.1

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

✗ Fi.CI.CHECKPATCH: warning for series starting with [1/6] dma-buf: add dynamic DMA-buf handling v9

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: add dynamic DMA-buf handling v9
URL   : https://patchwork.freedesktop.org/series/61774/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
a7793d675adb dma-buf: add dynamic DMA-buf handling v9
-:11: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#11: 
map/unmap callbacks are always called with the lock of the reservation object

-:354: WARNING:FUNCTION_ARGUMENTS: function definition argument 'struct dma_buf_attachment *' should also have an identifier name
#354: FILE: include/linux/dma-buf.h:109:
+	int (*pin)(struct dma_buf_attachment *);

-:366: WARNING:FUNCTION_ARGUMENTS: function definition argument 'struct dma_buf_attachment *' should also have an identifier name
#366: FILE: include/linux/dma-buf.h:121:
+	void (*unpin)(struct dma_buf_attachment *);

-:507: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 4 warnings, 0 checks, 445 lines checked
32a66b35fedc drm/ttm: remove the backing store if no placement is given
-:36: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 1 warnings, 0 checks, 18 lines checked
a682b7c716b4 drm/ttm: use the parent resv for ghost objects v2
-:11: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#11: 
v2: Limit this to only cases when the parent object uses a separate reservation

-:88: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 2 warnings, 0 checks, 62 lines checked
db69a0d6a285 drm/amdgpu: use allowed_domains for exported DMA-bufs
-:36: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 1 warnings, 0 checks, 17 lines checked
8ed696f9520a drm/amdgpu: add independent DMA-buf export v3
-:12: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#12: 
Start by providing a separate DMA-buf export implementation in amdgpu. This is

-:326: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 2 warnings, 0 checks, 283 lines checked
296641e96db1 drm/amdgpu: add independent DMA-buf import v6
-:276: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'Christian König <ckoenig.leichtzumerken@gmail.com>'

total: 0 errors, 1 warnings, 0 checks, 219 lines checked

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

✗ Fi.CI.SPARSE: warning for series starting with [1/6] dma-buf: add dynamic DMA-buf handling v9

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: add dynamic DMA-buf handling v9
URL   : https://patchwork.freedesktop.org/series/61774/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Sparse version: v0.5.2
Commit: dma-buf: add dynamic DMA-buf handling v9
Okay!

Commit: drm/ttm: remove the backing store if no placement is given
Okay!

Commit: drm/ttm: use the parent resv for ghost objects v2
Okay!

Commit: drm/amdgpu: use allowed_domains for exported DMA-bufs
Okay!

Commit: drm/amdgpu: add independent DMA-buf export v3
-drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:90:5: warning: symbol 'amdgpu_gem_prime_mmap' was not declared. Should it be static?
-O:drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:326:26: warning: symbol 'amdgpu_dmabuf_ops' was not declared. Should it be static?
+drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:376:26: warning: symbol 'amdgpu_dmabuf_ops' was not declared. Should it be static?
-O:drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:51:17: warning: symbol 'amdgpu_gem_prime_get_sg_table' was not declared. Should it be static?
+drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:90:5: warning: symbol 'amdgpu_gem_prime_mmap' was not declared. Should it be static?
-./include/linux/reservation.h:220:20: warning: dereference of noderef expression
-./include/linux/reservation.h:220:20: warning: dereference of noderef expression
-./include/linux/reservation.h:220:45: warning: dereference of noderef expression
-./include/linux/reservation.h:220:45: warning: dereference of noderef expression

Commit: drm/amdgpu: add independent DMA-buf import v6
-O:drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:435:23: warning: symbol 'amdgpu_gem_prime_import_sg_table' was not declared. Should it be static?
-O:drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:484:23: warning: symbol 'amdgpu_gem_prime_import' was not declared. Should it be static?
+drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c:505:23: warning: symbol 'amdgpu_gem_prime_import' was not declared. Should it be static?

_______________________________________________
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 dynamic DMA-buf handling v9

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: add dynamic DMA-buf handling v9
URL   : https://patchwork.freedesktop.org/series/61774/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_6221 -> Patchwork_13207
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_13207 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_13207, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_13207:

### IGT changes ###

#### Possible regressions ####

  * igt@amdgpu/amd_prime@amd-to-i915:
    - fi-kbl-8809g:       [PASS][1] -> [DMESG-WARN][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6221/fi-kbl-8809g/igt@amdgpu/amd_prime@amd-to-i915.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-kbl-8809g/igt@amdgpu/amd_prime@amd-to-i915.html

  * igt@runner@aborted:
    - fi-kbl-8809g:       NOTRUN -> [FAIL][3]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-kbl-8809g/igt@runner@aborted.html

  
Known issues
------------

  Here are the changes found in Patchwork_13207 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_exec_suspend@basic-s4-devices:
    - fi-blb-e6850:       [PASS][4] -> [INCOMPLETE][5] ([fdo#107718])
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6221/fi-blb-e6850/igt@gem_exec_suspend@basic-s4-devices.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-blb-e6850/igt@gem_exec_suspend@basic-s4-devices.html

  
#### Possible fixes ####

  * igt@gem_ctx_switch@basic-default:
    - {fi-icl-guc}:       [INCOMPLETE][6] ([fdo#107713] / [fdo#108569]) -> [PASS][7]
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6221/fi-icl-guc/igt@gem_ctx_switch@basic-default.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-icl-guc/igt@gem_ctx_switch@basic-default.html

  * {igt@i915_selftest@live_blt}:
    - fi-skl-iommu:       [INCOMPLETE][8] ([fdo#108602]) -> [PASS][9]
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6221/fi-skl-iommu/igt@i915_selftest@live_blt.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-skl-iommu/igt@i915_selftest@live_blt.html

  * igt@kms_cursor_legacy@basic-flip-before-cursor-varying-size:
    - fi-icl-u3:          [DMESG-WARN][10] ([fdo#107724]) -> [PASS][11] +1 similar issue
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6221/fi-icl-u3/igt@kms_cursor_legacy@basic-flip-before-cursor-varying-size.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/fi-icl-u3/igt@kms_cursor_legacy@basic-flip-before-cursor-varying-size.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#107713]: https://bugs.freedesktop.org/show_bug.cgi?id=107713
  [fdo#107718]: https://bugs.freedesktop.org/show_bug.cgi?id=107718
  [fdo#107724]: https://bugs.freedesktop.org/show_bug.cgi?id=107724
  [fdo#108044]: https://bugs.freedesktop.org/show_bug.cgi?id=108044
  [fdo#108569]: https://bugs.freedesktop.org/show_bug.cgi?id=108569
  [fdo#108602]: https://bugs.freedesktop.org/show_bug.cgi?id=108602
  [fdo#108744]: https://bugs.freedesktop.org/show_bug.cgi?id=108744


Participating hosts (54 -> 48)
------------------------------

  Missing    (6): fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-byt-clapper fi-bdw-samus 


Build changes
-------------

  * Linux: CI_DRM_6221 -> Patchwork_13207

  CI_DRM_6221: 3f71d971d89a60348dbb11c40459aeb9d69c18f9 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5048: 1a34b94f1ce07ac5978fe7893a17e8732d467868 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_13207: 296641e96db103b7ce9b37902f58b8241243d9d4 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

296641e96db1 drm/amdgpu: add independent DMA-buf import v6
8ed696f9520a drm/amdgpu: add independent DMA-buf export v3
db69a0d6a285 drm/amdgpu: use allowed_domains for exported DMA-bufs
a682b7c716b4 drm/ttm: use the parent resv for ghost objects v2
32a66b35fedc drm/ttm: remove the backing store if no placement is given
a7793d675adb dma-buf: add dynamic DMA-buf handling v9

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13207/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx