Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index a23b675..3ca7de3 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -5,8 +5,8 @@
 	bool "Explicit Synchronization Framework"
 	default n
 	select DMA_SHARED_BUFFER
-	---help---
-	  The Sync File Framework adds explicit syncronization via
+	help
+	  The Sync File Framework adds explicit synchronization via
 	  userspace. It enables send/receive 'struct dma_fence' objects to/from
 	  userspace via Sync File fds for synchronization between drivers via
 	  userspace components. It has been ported from Android.
@@ -22,7 +22,7 @@
 	default n
 	depends on SYNC_FILE
 	depends on DEBUG_FS
-	---help---
+	help
 	  A sync object driver that uses a 32bit counter to coordinate
 	  synchronization.  Useful when there is no hardware primitive backing
 	  the synchronization.
@@ -39,9 +39,32 @@
 	  A driver to let userspace turn memfd regions into dma-bufs.
 	  Qemu can use this to create host dmabufs for guest framebuffers.
 
+config DMABUF_MOVE_NOTIFY
+	bool "Move notify between drivers (EXPERIMENTAL)"
+	default n
+	depends on DMA_SHARED_BUFFER
+	help
+	  Don't pin buffers if the dynamic DMA-buf interface is available on
+	  both the exporter as well as the importer. This fixes a security
+	  problem where userspace is able to pin unrestricted amounts of memory
+	  through DMA-buf.
+	  This is marked experimental because we don't yet have a consistent
+	  execution context and memory management between drivers.
+
 config DMABUF_SELFTESTS
 	tristate "Selftests for the dma-buf interfaces"
 	default n
 	depends on DMA_SHARED_BUFFER
 
+menuconfig DMABUF_HEAPS
+	bool "DMA-BUF Userland Memory Heaps"
+	select DMA_SHARED_BUFFER
+	help
+	  Choose this option to enable the DMA-BUF userland memory heaps.
+	  This options creates per heap chardevs in /dev/dma_heap/ which
+	  allows userspace to allocate dma-bufs that can be shared
+	  between drivers.
+
+source "drivers/dma-buf/heaps/Kconfig"
+
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 03479da..995e05f 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,12 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
 	 dma-resv.o seqno-fence.o
+obj-$(CONFIG_DMABUF_HEAPS)	+= dma-heap.o
+obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
 
 dmabuf_selftests-y := \
 	selftest.o \
-	st-dma-fence.o
+	st-dma-fence.o \
+	st-dma-fence-chain.o
 
 obj-$(CONFIG_DMABUF_SELFTESTS)	+= dmabuf_selftests.o
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 758de0e..93e9bf7 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -79,6 +79,7 @@
 	if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
 		dma_resv_fini(dmabuf->resv);
 
+	WARN_ON(!list_empty(&dmabuf->attachments));
 	module_put(dmabuf->owner);
 	kfree(dmabuf->name);
 	kfree(dmabuf);
@@ -172,11 +173,11 @@
 }
 
 /**
- * DOC: fence polling
+ * DOC: implicit fence polling
  *
  * To support cross-device and cross-driver synchronization of buffer access
- * implicit fences (represented internally in the kernel with &struct fence) can
- * be attached to a &dma_buf. The glue for that and a few related things are
+ * implicit fences (represented internally in the kernel with &struct dma_fence)
+ * can be attached to a &dma_buf. The glue for that and a few related things are
  * provided in the &dma_resv structure.
  *
  * Userspace can query the state of these implicitly tracked fences using poll()
@@ -330,9 +331,9 @@
  * name of the dma-buf if the same piece of memory is used for multiple
  * purpose between different devices.
  *
- * @dmabuf [in]     dmabuf buffer that will be renamed.
- * @buf:   [in]     A piece of userspace memory that contains the name of
- *                  the dma-buf.
+ * @dmabuf: [in]     dmabuf buffer that will be renamed.
+ * @buf:    [in]     A piece of userspace memory that contains the name of
+ *                   the dma-buf.
  *
  * Returns 0 on success. If the dma-buf buffer is already attached to
  * devices, return -EBUSY.
@@ -346,7 +347,7 @@
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
-	mutex_lock(&dmabuf->lock);
+	dma_resv_lock(dmabuf->resv, NULL);
 	if (!list_empty(&dmabuf->attachments)) {
 		ret = -EBUSY;
 		kfree(name);
@@ -358,7 +359,7 @@
 	spin_unlock(&dmabuf->name_lock);
 
 out_unlock:
-	mutex_unlock(&dmabuf->lock);
+	dma_resv_unlock(dmabuf->resv);
 	return ret;
 }
 
@@ -430,9 +431,7 @@
 	.llseek		= dma_buf_llseek,
 	.poll		= dma_buf_poll,
 	.unlocked_ioctl	= dma_buf_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= dma_buf_ioctl,
-#endif
+	.compat_ioctl	= compat_ptr_ioctl,
 	.show_fdinfo	= dma_buf_show_fdinfo,
 };
 
@@ -540,6 +539,13 @@
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
+		    (exp_info->ops->pin || exp_info->ops->unpin)))
+		return ERR_PTR(-EINVAL);
+
+	if (WARN_ON(!exp_info->ops->pin != !exp_info->ops->unpin))
+		return ERR_PTR(-EINVAL);
+
 	if (!try_module_get(exp_info->owner))
 		return ERR_PTR(-ENOENT);
 
@@ -661,10 +667,12 @@
 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().
@@ -678,8 +686,10 @@
  * 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;
@@ -687,30 +697,88 @@
 	if (WARN_ON(!dmabuf || !dev))
 		return ERR_PTR(-EINVAL);
 
+	if (WARN_ON(importer_ops && !importer_ops->move_notify))
+		return ERR_PTR(-EINVAL);
+
 	attach = kzalloc(sizeof(*attach), GFP_KERNEL);
 	if (!attach)
 		return ERR_PTR(-ENOMEM);
 
 	attach->dev = dev;
 	attach->dmabuf = dmabuf;
-
-	mutex_lock(&dmabuf->lock);
+	if (importer_ops)
+		attach->peer2peer = importer_ops->allow_peer2peer;
+	attach->importer_ops = importer_ops;
+	attach->importer_priv = importer_priv;
 
 	if (dmabuf->ops->attach) {
 		ret = dmabuf->ops->attach(dmabuf, attach);
 		if (ret)
 			goto err_attach;
 	}
+	dma_resv_lock(dmabuf->resv, NULL);
 	list_add(&attach->node, &dmabuf->attachments);
+	dma_resv_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)) {
+			dma_resv_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))
+			dma_resv_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))
+		dma_resv_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);
 
@@ -727,20 +795,67 @@
 	if (WARN_ON(!dmabuf || !attach))
 		return;
 
-	if (attach->sgt)
+	if (attach->sgt) {
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			dma_resv_lock(attach->dmabuf->resv, NULL);
+
 		dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir);
 
-	mutex_lock(&dmabuf->lock);
+		if (dma_buf_is_dynamic(attach->dmabuf)) {
+			dma_buf_unpin(attach);
+			dma_resv_unlock(attach->dmabuf->resv);
+		}
+	}
+
+	dma_resv_lock(dmabuf->resv, NULL);
 	list_del(&attach->node);
+	dma_resv_unlock(dmabuf->resv);
 	if (dmabuf->ops->detach)
 		dmabuf->ops->detach(dmabuf, attach);
 
-	mutex_unlock(&dmabuf->lock);
 	kfree(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;
+
+	dma_resv_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;
+
+	dma_resv_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
  * dma_buf_ops.
@@ -759,12 +874,16 @@
 					enum dma_data_direction direction)
 {
 	struct sg_table *sg_table;
+	int r;
 
 	might_sleep();
 
 	if (WARN_ON(!attach || !attach->dmabuf))
 		return ERR_PTR(-EINVAL);
 
+	if (dma_buf_attachment_is_dynamic(attach))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	if (attach->sgt) {
 		/*
 		 * Two mappings with different directions for the same
@@ -777,10 +896,23 @@
 		return attach->sgt;
 	}
 
+	if (dma_buf_is_dynamic(attach->dmabuf)) {
+		dma_resv_assert_held(attach->dmabuf->resv);
+		if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
+			r = dma_buf_pin(attach);
+			if (r)
+				return ERR_PTR(r);
+		}
+	}
+
 	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
 
+	if (IS_ERR(sg_table) && dma_buf_is_dynamic(attach->dmabuf) &&
+	     !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY))
+		dma_buf_unpin(attach);
+
 	if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) {
 		attach->sgt = sg_table;
 		attach->dir = direction;
@@ -809,14 +941,44 @@
 	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
 		return;
 
+	if (dma_buf_attachment_is_dynamic(attach))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	if (attach->sgt == sg_table)
 		return;
 
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
+
+	if (dma_buf_is_dynamic(attach->dmabuf) &&
+	    !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY))
+		dma_buf_unpin(attach);
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
 
 /**
+ * dma_buf_move_notify - notify attachments that DMA-buf is moving
+ *
+ * @dmabuf:	[in]	buffer which is moving
+ *
+ * Informs all attachmenst that they need to destroy and recreated all their
+ * mappings.
+ */
+void dma_buf_move_notify(struct dma_buf *dmabuf)
+{
+	struct dma_buf_attachment *attach;
+
+	dma_resv_assert_held(dmabuf->resv);
+
+	list_for_each_entry(attach, &dmabuf->attachments, node)
+		if (attach->importer_ops)
+			attach->importer_ops->move_notify(attach);
+}
+EXPORT_SYMBOL_GPL(dma_buf_move_notify);
+
+/**
  * DOC: cpu access
  *
  * There are mutliple reasons for supporting CPU access to a dma buffer object:
@@ -827,29 +989,9 @@
  *   with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access()
  *   access.
  *
- *   To support dma_buf objects residing in highmem cpu access is page-based
- *   using an api similar to kmap. Accessing a dma_buf is done in aligned chunks
- *   of PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which
- *   returns a pointer in kernel virtual address space. Afterwards the chunk
- *   needs to be unmapped again. There is no limit on how often a given chunk
- *   can be mapped and unmapped, i.e. the importer does not need to call
- *   begin_cpu_access again before mapping the same chunk again.
- *
- *   Interfaces::
- *      void \*dma_buf_kmap(struct dma_buf \*, unsigned long);
- *      void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*);
- *
- *   Implementing the functions is optional for exporters and for importers all
- *   the restrictions of using kmap apply.
- *
- *   dma_buf kmap calls outside of the range specified in begin_cpu_access are
- *   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
- *   the partial chunks at the beginning and end but may return stale or bogus
- *   data outside of the range (in these partial chunks).
- *
- *   For some cases the overhead of kmap can be too high, a vmap interface
- *   is introduced. This interface should be used very carefully, as vmalloc
- *   space is a limited resources on many architectures.
+ *   Since for most kernel internal dma-buf accesses need the entire buffer, a
+ *   vmap interface is introduced. Note that on very old 32-bit architectures
+ *   vmalloc space might be limited and result in vmap calls failing.
  *
  *   Interfaces::
  *      void \*dma_buf_vmap(struct dma_buf \*dmabuf)
@@ -999,43 +1141,6 @@
 }
 EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
 
-/**
- * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
- * same restrictions as for kmap and friends apply.
- * @dmabuf:	[in]	buffer to map page from.
- * @page_num:	[in]	page in PAGE_SIZE units to map.
- *
- * This call must always succeed, any necessary preparations that might fail
- * need to be done in begin_cpu_access.
- */
-void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
-{
-	WARN_ON(!dmabuf);
-
-	if (!dmabuf->ops->map)
-		return NULL;
-	return dmabuf->ops->map(dmabuf, page_num);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kmap);
-
-/**
- * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap.
- * @dmabuf:	[in]	buffer to unmap page from.
- * @page_num:	[in]	page in PAGE_SIZE units to unmap.
- * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap.
- *
- * This call must always succeed.
- */
-void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num,
-		    void *vaddr)
-{
-	WARN_ON(!dmabuf);
-
-	if (dmabuf->ops->unmap)
-		dmabuf->ops->unmap(dmabuf, page_num, vaddr);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kunmap);
-
 
 /**
  * dma_buf_mmap - Setup up a userspace mmap with the given vma
@@ -1187,13 +1292,10 @@
 		   "size", "flags", "mode", "count", "ino");
 
 	list_for_each_entry(buf_obj, &db_list.head, list_node) {
-		ret = mutex_lock_interruptible(&buf_obj->lock);
 
-		if (ret) {
-			seq_puts(s,
-				 "\tERROR locking buffer object: skipping\n");
-			continue;
-		}
+		ret = dma_resv_lock_interruptible(buf_obj->resv, NULL);
+		if (ret)
+			goto error_unlock;
 
 		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n",
 				buf_obj->size,
@@ -1239,19 +1341,23 @@
 			seq_printf(s, "\t%s\n", dev_name(attach_obj->dev));
 			attach_count++;
 		}
+		dma_resv_unlock(buf_obj->resv);
 
 		seq_printf(s, "Total %d devices attached\n\n",
 				attach_count);
 
 		count++;
 		size += buf_obj->size;
-		mutex_unlock(&buf_obj->lock);
 	}
 
 	seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size);
 
 	mutex_unlock(&db_list.lock);
 	return 0;
+
+error_unlock:
+	mutex_unlock(&db_list.lock);
+	return ret;
 }
 
 DEFINE_SHOW_ATTRIBUTE(dma_buf_debug);
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index d3fbd95..3e07f96 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -104,7 +104,11 @@
 {
 	struct dma_fence_array *array = to_dma_fence_array(fence);
 
-	return atomic_read(&array->num_pending) <= 0;
+	if (atomic_read(&array->num_pending) > 0)
+		return false;
+
+	dma_fence_array_clear_pending_error(array);
+	return true;
 }
 
 static void dma_fence_array_release(struct dma_fence *fence)
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
index 44a7416..7d129e6 100644
--- a/drivers/dma-buf/dma-fence-chain.c
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -62,7 +62,8 @@
 			replacement = NULL;
 		}
 
-		tmp = cmpxchg((void **)&chain->prev, (void *)prev, (void *)replacement);
+		tmp = cmpxchg((struct dma_fence __force **)&chain->prev,
+			      prev, replacement);
 		if (tmp == prev)
 			dma_fence_put(tmp);
 		else
@@ -221,6 +222,7 @@
  * @chain: the chain node to initialize
  * @prev: the previous fence
  * @fence: the current fence
+ * @seqno: the sequence number to use for the fence chain
  *
  * Initialize a new chain node and either start a new chain or add the node to
  * the existing chain of the previous fence.
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 052a41e..7475e09 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -64,6 +64,52 @@
  *   &dma_buf.resv pointer.
  */
 
+/**
+ * DOC: fence cross-driver contract
+ *
+ * Since &dma_fence provide a cross driver contract, all drivers must follow the
+ * same rules:
+ *
+ * * Fences must complete in a reasonable time. Fences which represent kernels
+ *   and shaders submitted by userspace, which could run forever, must be backed
+ *   up by timeout and gpu hang recovery code. Minimally that code must prevent
+ *   further command submission and force complete all in-flight fences, e.g.
+ *   when the driver or hardware do not support gpu reset, or if the gpu reset
+ *   failed for some reason. Ideally the driver supports gpu recovery which only
+ *   affects the offending userspace context, and no other userspace
+ *   submissions.
+ *
+ * * Drivers may have different ideas of what completion within a reasonable
+ *   time means. Some hang recovery code uses a fixed timeout, others a mix
+ *   between observing forward progress and increasingly strict timeouts.
+ *   Drivers should not try to second guess timeout handling of fences from
+ *   other drivers.
+ *
+ * * To ensure there's no deadlocks of dma_fence_wait() against other locks
+ *   drivers should annotate all code required to reach dma_fence_signal(),
+ *   which completes the fences, with dma_fence_begin_signalling() and
+ *   dma_fence_end_signalling().
+ *
+ * * Drivers are allowed to call dma_fence_wait() while holding dma_resv_lock().
+ *   This means any code required for fence completion cannot acquire a
+ *   &dma_resv lock. Note that this also pulls in the entire established
+ *   locking hierarchy around dma_resv_lock() and dma_resv_unlock().
+ *
+ * * Drivers are allowed to call dma_fence_wait() from their &shrinker
+ *   callbacks. This means any code required for fence completion cannot
+ *   allocate memory with GFP_KERNEL.
+ *
+ * * Drivers are allowed to call dma_fence_wait() from their &mmu_notifier
+ *   respectively &mmu_interval_notifier callbacks. This means any code required
+ *   for fence completeion cannot allocate memory with GFP_NOFS or GFP_NOIO.
+ *   Only GFP_ATOMIC is permissible, which might fail.
+ *
+ * Note that only GPU drivers have a reasonable excuse for both requiring
+ * &mmu_interval_notifier and &shrinker callbacks at the same time as having to
+ * track asynchronous compute work using &dma_fence. No driver outside of
+ * drivers/gpu should ever call dma_fence_wait() in such contexts.
+ */
+
 static const char *dma_fence_stub_get_name(struct dma_fence *fence)
 {
         return "stub";
@@ -106,11 +152,166 @@
 u64 dma_fence_context_alloc(unsigned num)
 {
 	WARN_ON(!num);
-	return atomic64_add_return(num, &dma_fence_context_counter) - num;
+	return atomic64_fetch_add(num, &dma_fence_context_counter);
 }
 EXPORT_SYMBOL(dma_fence_context_alloc);
 
 /**
+ * DOC: fence signalling annotation
+ *
+ * Proving correctness of all the kernel code around &dma_fence through code
+ * review and testing is tricky for a few reasons:
+ *
+ * * It is a cross-driver contract, and therefore all drivers must follow the
+ *   same rules for lock nesting order, calling contexts for various functions
+ *   and anything else significant for in-kernel interfaces. But it is also
+ *   impossible to test all drivers in a single machine, hence brute-force N vs.
+ *   N testing of all combinations is impossible. Even just limiting to the
+ *   possible combinations is infeasible.
+ *
+ * * There is an enormous amount of driver code involved. For render drivers
+ *   there's the tail of command submission, after fences are published,
+ *   scheduler code, interrupt and workers to process job completion,
+ *   and timeout, gpu reset and gpu hang recovery code. Plus for integration
+ *   with core mm with have &mmu_notifier, respectively &mmu_interval_notifier,
+ *   and &shrinker. For modesetting drivers there's the commit tail functions
+ *   between when fences for an atomic modeset are published, and when the
+ *   corresponding vblank completes, including any interrupt processing and
+ *   related workers. Auditing all that code, across all drivers, is not
+ *   feasible.
+ *
+ * * Due to how many other subsystems are involved and the locking hierarchies
+ *   this pulls in there is extremely thin wiggle-room for driver-specific
+ *   differences. &dma_fence interacts with almost all of the core memory
+ *   handling through page fault handlers via &dma_resv, dma_resv_lock() and
+ *   dma_resv_unlock(). On the other side it also interacts through all
+ *   allocation sites through &mmu_notifier and &shrinker.
+ *
+ * Furthermore lockdep does not handle cross-release dependencies, which means
+ * any deadlocks between dma_fence_wait() and dma_fence_signal() can't be caught
+ * at runtime with some quick testing. The simplest example is one thread
+ * waiting on a &dma_fence while holding a lock::
+ *
+ *     lock(A);
+ *     dma_fence_wait(B);
+ *     unlock(A);
+ *
+ * while the other thread is stuck trying to acquire the same lock, which
+ * prevents it from signalling the fence the previous thread is stuck waiting
+ * on::
+ *
+ *     lock(A);
+ *     unlock(A);
+ *     dma_fence_signal(B);
+ *
+ * By manually annotating all code relevant to signalling a &dma_fence we can
+ * teach lockdep about these dependencies, which also helps with the validation
+ * headache since now lockdep can check all the rules for us::
+ *
+ *    cookie = dma_fence_begin_signalling();
+ *    lock(A);
+ *    unlock(A);
+ *    dma_fence_signal(B);
+ *    dma_fence_end_signalling(cookie);
+ *
+ * For using dma_fence_begin_signalling() and dma_fence_end_signalling() to
+ * annotate critical sections the following rules need to be observed:
+ *
+ * * All code necessary to complete a &dma_fence must be annotated, from the
+ *   point where a fence is accessible to other threads, to the point where
+ *   dma_fence_signal() is called. Un-annotated code can contain deadlock issues,
+ *   and due to the very strict rules and many corner cases it is infeasible to
+ *   catch these just with review or normal stress testing.
+ *
+ * * &struct dma_resv deserves a special note, since the readers are only
+ *   protected by rcu. This means the signalling critical section starts as soon
+ *   as the new fences are installed, even before dma_resv_unlock() is called.
+ *
+ * * The only exception are fast paths and opportunistic signalling code, which
+ *   calls dma_fence_signal() purely as an optimization, but is not required to
+ *   guarantee completion of a &dma_fence. The usual example is a wait IOCTL
+ *   which calls dma_fence_signal(), while the mandatory completion path goes
+ *   through a hardware interrupt and possible job completion worker.
+ *
+ * * To aid composability of code, the annotations can be freely nested, as long
+ *   as the overall locking hierarchy is consistent. The annotations also work
+ *   both in interrupt and process context. Due to implementation details this
+ *   requires that callers pass an opaque cookie from
+ *   dma_fence_begin_signalling() to dma_fence_end_signalling().
+ *
+ * * Validation against the cross driver contract is implemented by priming
+ *   lockdep with the relevant hierarchy at boot-up. This means even just
+ *   testing with a single device is enough to validate a driver, at least as
+ *   far as deadlocks with dma_fence_wait() against dma_fence_signal() are
+ *   concerned.
+ */
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map dma_fence_lockdep_map = {
+	.name = "dma_fence_map"
+};
+
+/**
+ * dma_fence_begin_signalling - begin a critical DMA fence signalling section
+ *
+ * Drivers should use this to annotate the beginning of any code section
+ * required to eventually complete &dma_fence by calling dma_fence_signal().
+ *
+ * The end of these critical sections are annotated with
+ * dma_fence_end_signalling().
+ *
+ * Returns:
+ *
+ * Opaque cookie needed by the implementation, which needs to be passed to
+ * dma_fence_end_signalling().
+ */
+bool dma_fence_begin_signalling(void)
+{
+	/* explicitly nesting ... */
+	if (lock_is_held_type(&dma_fence_lockdep_map, 1))
+		return true;
+
+	/* rely on might_sleep check for soft/hardirq locks */
+	if (in_atomic())
+		return true;
+
+	/* ... and non-recursive readlock */
+	lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _RET_IP_);
+
+	return false;
+}
+EXPORT_SYMBOL(dma_fence_begin_signalling);
+
+/**
+ * dma_fence_end_signalling - end a critical DMA fence signalling section
+ * @cookie: opaque cookie from dma_fence_begin_signalling()
+ *
+ * Closes a critical section annotation opened by dma_fence_begin_signalling().
+ */
+void dma_fence_end_signalling(bool cookie)
+{
+	if (cookie)
+		return;
+
+	lock_release(&dma_fence_lockdep_map, _RET_IP_);
+}
+EXPORT_SYMBOL(dma_fence_end_signalling);
+
+void __dma_fence_might_wait(void)
+{
+	bool tmp;
+
+	tmp = lock_is_held_type(&dma_fence_lockdep_map, 1);
+	if (tmp)
+		lock_release(&dma_fence_lockdep_map, _THIS_IP_);
+	lock_map_acquire(&dma_fence_lockdep_map);
+	lock_map_release(&dma_fence_lockdep_map);
+	if (tmp)
+		lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _THIS_IP_);
+}
+#endif
+
+
+/**
  * dma_fence_signal_locked - signal completion of a fence
  * @fence: the fence to signal
  *
@@ -170,14 +371,19 @@
 {
 	unsigned long flags;
 	int ret;
+	bool tmp;
 
 	if (!fence)
 		return -EINVAL;
 
+	tmp = dma_fence_begin_signalling();
+
 	spin_lock_irqsave(fence->lock, flags);
 	ret = dma_fence_signal_locked(fence);
 	spin_unlock_irqrestore(fence->lock, flags);
 
+	dma_fence_end_signalling(tmp);
+
 	return ret;
 }
 EXPORT_SYMBOL(dma_fence_signal);
@@ -208,6 +414,10 @@
 	if (WARN_ON(timeout < 0))
 		return -EINVAL;
 
+	might_sleep();
+
+	__dma_fence_might_wait();
+
 	trace_dma_fence_wait_start(fence);
 	if (fence->ops->wait)
 		ret = fence->ops->wait(fence, intr, timeout);
diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c
new file mode 100644
index 0000000..798f86f
--- /dev/null
+++ b/drivers/dma-buf/dma-heap.c
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Framework for userspace DMA-BUF allocations
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/cdev.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/xarray.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/dma-heap.h>
+#include <uapi/linux/dma-heap.h>
+
+#define DEVNAME "dma_heap"
+
+#define NUM_HEAP_MINORS 128
+
+/**
+ * struct dma_heap - represents a dmabuf heap in the system
+ * @name:		used for debugging/device-node name
+ * @ops:		ops struct for this heap
+ * @heap_devt		heap device node
+ * @list		list head connecting to list of heaps
+ * @heap_cdev		heap char device
+ *
+ * Represents a heap of memory from which buffers can be made.
+ */
+struct dma_heap {
+	const char *name;
+	const struct dma_heap_ops *ops;
+	void *priv;
+	dev_t heap_devt;
+	struct list_head list;
+	struct cdev heap_cdev;
+};
+
+static LIST_HEAD(heap_list);
+static DEFINE_MUTEX(heap_list_lock);
+static dev_t dma_heap_devt;
+static struct class *dma_heap_class;
+static DEFINE_XARRAY_ALLOC(dma_heap_minors);
+
+static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
+				 unsigned int fd_flags,
+				 unsigned int heap_flags)
+{
+	/*
+	 * Allocations from all heaps have to begin
+	 * and end on page boundaries.
+	 */
+	len = PAGE_ALIGN(len);
+	if (!len)
+		return -EINVAL;
+
+	return heap->ops->allocate(heap, len, fd_flags, heap_flags);
+}
+
+static int dma_heap_open(struct inode *inode, struct file *file)
+{
+	struct dma_heap *heap;
+
+	heap = xa_load(&dma_heap_minors, iminor(inode));
+	if (!heap) {
+		pr_err("dma_heap: minor %d unknown.\n", iminor(inode));
+		return -ENODEV;
+	}
+
+	/* instance data as context */
+	file->private_data = heap;
+	nonseekable_open(inode, file);
+
+	return 0;
+}
+
+static long dma_heap_ioctl_allocate(struct file *file, void *data)
+{
+	struct dma_heap_allocation_data *heap_allocation = data;
+	struct dma_heap *heap = file->private_data;
+	int fd;
+
+	if (heap_allocation->fd)
+		return -EINVAL;
+
+	if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS)
+		return -EINVAL;
+
+	if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS)
+		return -EINVAL;
+
+	fd = dma_heap_buffer_alloc(heap, heap_allocation->len,
+				   heap_allocation->fd_flags,
+				   heap_allocation->heap_flags);
+	if (fd < 0)
+		return fd;
+
+	heap_allocation->fd = fd;
+
+	return 0;
+}
+
+static unsigned int dma_heap_ioctl_cmds[] = {
+	DMA_HEAP_IOCTL_ALLOC,
+};
+
+static long dma_heap_ioctl(struct file *file, unsigned int ucmd,
+			   unsigned long arg)
+{
+	char stack_kdata[128];
+	char *kdata = stack_kdata;
+	unsigned int kcmd;
+	unsigned int in_size, out_size, drv_size, ksize;
+	int nr = _IOC_NR(ucmd);
+	int ret = 0;
+
+	if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds))
+		return -EINVAL;
+
+	nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds));
+	/* Get the kernel ioctl cmd that matches */
+	kcmd = dma_heap_ioctl_cmds[nr];
+
+	/* Figure out the delta between user cmd size and kernel cmd size */
+	drv_size = _IOC_SIZE(kcmd);
+	out_size = _IOC_SIZE(ucmd);
+	in_size = out_size;
+	if ((ucmd & kcmd & IOC_IN) == 0)
+		in_size = 0;
+	if ((ucmd & kcmd & IOC_OUT) == 0)
+		out_size = 0;
+	ksize = max(max(in_size, out_size), drv_size);
+
+	/* If necessary, allocate buffer for ioctl argument */
+	if (ksize > sizeof(stack_kdata)) {
+		kdata = kmalloc(ksize, GFP_KERNEL);
+		if (!kdata)
+			return -ENOMEM;
+	}
+
+	if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	/* zero out any difference between the kernel/user structure size */
+	if (ksize > in_size)
+		memset(kdata + in_size, 0, ksize - in_size);
+
+	switch (kcmd) {
+	case DMA_HEAP_IOCTL_ALLOC:
+		ret = dma_heap_ioctl_allocate(file, kdata);
+		break;
+	default:
+		ret = -ENOTTY;
+		goto err;
+	}
+
+	if (copy_to_user((void __user *)arg, kdata, out_size) != 0)
+		ret = -EFAULT;
+err:
+	if (kdata != stack_kdata)
+		kfree(kdata);
+	return ret;
+}
+
+static const struct file_operations dma_heap_fops = {
+	.owner          = THIS_MODULE,
+	.open		= dma_heap_open,
+	.unlocked_ioctl = dma_heap_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= dma_heap_ioctl,
+#endif
+};
+
+/**
+ * dma_heap_get_drvdata() - get per-subdriver data for the heap
+ * @heap: DMA-Heap to retrieve private data for
+ *
+ * Returns:
+ * The per-subdriver data for the heap.
+ */
+void *dma_heap_get_drvdata(struct dma_heap *heap)
+{
+	return heap->priv;
+}
+
+struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info)
+{
+	struct dma_heap *heap, *h, *err_ret;
+	struct device *dev_ret;
+	unsigned int minor;
+	int ret;
+
+	if (!exp_info->name || !strcmp(exp_info->name, "")) {
+		pr_err("dma_heap: Cannot add heap without a name\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!exp_info->ops || !exp_info->ops->allocate) {
+		pr_err("dma_heap: Cannot add heap with invalid ops struct\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* check the name is unique */
+	mutex_lock(&heap_list_lock);
+	list_for_each_entry(h, &heap_list, list) {
+		if (!strcmp(h->name, exp_info->name)) {
+			mutex_unlock(&heap_list_lock);
+			pr_err("dma_heap: Already registered heap named %s\n",
+			       exp_info->name);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+	mutex_unlock(&heap_list_lock);
+
+	heap = kzalloc(sizeof(*heap), GFP_KERNEL);
+	if (!heap)
+		return ERR_PTR(-ENOMEM);
+
+	heap->name = exp_info->name;
+	heap->ops = exp_info->ops;
+	heap->priv = exp_info->priv;
+
+	/* Find unused minor number */
+	ret = xa_alloc(&dma_heap_minors, &minor, heap,
+		       XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to get minor number for heap\n");
+		err_ret = ERR_PTR(ret);
+		goto err0;
+	}
+
+	/* Create device */
+	heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor);
+
+	cdev_init(&heap->heap_cdev, &dma_heap_fops);
+	ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to add char device\n");
+		err_ret = ERR_PTR(ret);
+		goto err1;
+	}
+
+	dev_ret = device_create(dma_heap_class,
+				NULL,
+				heap->heap_devt,
+				NULL,
+				heap->name);
+	if (IS_ERR(dev_ret)) {
+		pr_err("dma_heap: Unable to create device\n");
+		err_ret = ERR_CAST(dev_ret);
+		goto err2;
+	}
+	/* Add heap to the list */
+	mutex_lock(&heap_list_lock);
+	list_add(&heap->list, &heap_list);
+	mutex_unlock(&heap_list_lock);
+
+	return heap;
+
+err2:
+	cdev_del(&heap->heap_cdev);
+err1:
+	xa_erase(&dma_heap_minors, minor);
+err0:
+	kfree(heap);
+	return err_ret;
+}
+
+static char *dma_heap_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev));
+}
+
+static int dma_heap_init(void)
+{
+	int ret;
+
+	ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME);
+	if (ret)
+		return ret;
+
+	dma_heap_class = class_create(THIS_MODULE, DEVNAME);
+	if (IS_ERR(dma_heap_class)) {
+		unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS);
+		return PTR_ERR(dma_heap_class);
+	}
+	dma_heap_class->devnode = dma_heap_devnode;
+
+	return 0;
+}
+subsys_initcall(dma_heap_init);
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 242a9ec..1187e5e 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -34,6 +34,9 @@
 
 #include <linux/dma-resv.h>
 #include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/sched/mm.h>
+#include <linux/mmu_notifier.h>
 
 /**
  * DOC: Reservation Object Overview
@@ -49,12 +52,6 @@
 DEFINE_WD_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
-struct lock_class_key reservation_seqcount_class;
-EXPORT_SYMBOL(reservation_seqcount_class);
-
-const char reservation_seqcount_string[] = "reservation_seqcount";
-EXPORT_SYMBOL(reservation_seqcount_string);
-
 /**
  * dma_resv_list_alloc - allocate fence list
  * @shared_max: number of fences we need space for
@@ -95,6 +92,49 @@
 	kfree_rcu(list, rcu);
 }
 
+#if IS_ENABLED(CONFIG_LOCKDEP)
+static int __init dma_resv_lockdep(void)
+{
+	struct mm_struct *mm = mm_alloc();
+	struct ww_acquire_ctx ctx;
+	struct dma_resv obj;
+	struct address_space mapping;
+	int ret;
+
+	if (!mm)
+		return -ENOMEM;
+
+	dma_resv_init(&obj);
+	address_space_init_once(&mapping);
+
+	mmap_read_lock(mm);
+	ww_acquire_init(&ctx, &reservation_ww_class);
+	ret = dma_resv_lock(&obj, &ctx);
+	if (ret == -EDEADLK)
+		dma_resv_lock_slow(&obj, &ctx);
+	fs_reclaim_acquire(GFP_KERNEL);
+	/* for unmap_mapping_range on trylocked buffer objects in shrinkers */
+	i_mmap_lock_write(&mapping);
+	i_mmap_unlock_write(&mapping);
+#ifdef CONFIG_MMU_NOTIFIER
+	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
+	__dma_fence_might_wait();
+	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
+#else
+	__dma_fence_might_wait();
+#endif
+	fs_reclaim_release(GFP_KERNEL);
+	ww_mutex_unlock(&obj.lock);
+	ww_acquire_fini(&ctx);
+	mmap_read_unlock(mm);
+	
+	mmput(mm);
+
+	return 0;
+}
+subsys_initcall(dma_resv_lockdep);
+#endif
+
 /**
  * dma_resv_init - initialize a reservation object
  * @obj: the reservation object
@@ -102,9 +142,8 @@
 void dma_resv_init(struct dma_resv *obj)
 {
 	ww_mutex_init(&obj->lock, &reservation_ww_class);
+	seqcount_ww_mutex_init(&obj->seq, &obj->lock);
 
-	__seqcount_init(&obj->seq, reservation_seqcount_string,
-			&reservation_seqcount_class);
 	RCU_INIT_POINTER(obj->fence, NULL);
 	RCU_INIT_POINTER(obj->fence_excl, NULL);
 }
@@ -234,7 +273,6 @@
 	fobj = dma_resv_get_list(obj);
 	count = fobj->shared_count;
 
-	preempt_disable();
 	write_seqcount_begin(&obj->seq);
 
 	for (i = 0; i < count; ++i) {
@@ -256,7 +294,6 @@
 	smp_store_mb(fobj->shared_count, count);
 
 	write_seqcount_end(&obj->seq);
-	preempt_enable();
 	dma_fence_put(old);
 }
 EXPORT_SYMBOL(dma_resv_add_shared_fence);
@@ -283,14 +320,12 @@
 	if (fence)
 		dma_fence_get(fence);
 
-	preempt_disable();
 	write_seqcount_begin(&obj->seq);
 	/* write_seqcount_begin provides the necessary memory barrier */
 	RCU_INIT_POINTER(obj->fence_excl, fence);
 	if (old)
 		old->shared_count = 0;
 	write_seqcount_end(&obj->seq);
-	preempt_enable();
 
 	/* inplace update, no shared fences */
 	while (i--)
@@ -368,13 +403,11 @@
 	src_list = dma_resv_get_list(dst);
 	old = dma_resv_get_excl(dst);
 
-	preempt_disable();
 	write_seqcount_begin(&dst->seq);
 	/* write_seqcount_begin provides the necessary memory barrier */
 	RCU_INIT_POINTER(dst->fence_excl, new);
 	RCU_INIT_POINTER(dst->fence, dst_list);
 	write_seqcount_end(&dst->seq);
-	preempt_enable();
 
 	dma_resv_list_free(src_list);
 	dma_fence_put(old);
diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig
new file mode 100644
index 0000000..a5eef06
--- /dev/null
+++ b/drivers/dma-buf/heaps/Kconfig
@@ -0,0 +1,14 @@
+config DMABUF_HEAPS_SYSTEM
+	bool "DMA-BUF System Heap"
+	depends on DMABUF_HEAPS
+	help
+	  Choose this option to enable the system dmabuf heap. The system heap
+	  is backed by pages from the buddy allocator. If in doubt, say Y.
+
+config DMABUF_HEAPS_CMA
+	bool "DMA-BUF CMA Heap"
+	depends on DMABUF_HEAPS && DMA_CMA
+	help
+	  Choose this option to enable dma-buf CMA heap. This heap is backed
+	  by the Contiguous Memory Allocator (CMA). If your system has these
+	  regions, you should say Y here.
diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile
new file mode 100644
index 0000000..6e54cde
--- /dev/null
+++ b/drivers/dma-buf/heaps/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y					+= heap-helpers.o
+obj-$(CONFIG_DMABUF_HEAPS_SYSTEM)	+= system_heap.o
+obj-$(CONFIG_DMABUF_HEAPS_CMA)		+= cma_heap.o
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
new file mode 100644
index 0000000..e55384d
--- /dev/null
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF CMA heap exporter
+ *
+ * Copyright (C) 2012, 2019 Linaro Ltd.
+ * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson.
+ */
+
+#include <linux/cma.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/dma-map-ops.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/sched/signal.h>
+
+#include "heap-helpers.h"
+
+struct cma_heap {
+	struct dma_heap *heap;
+	struct cma *cma;
+};
+
+static void cma_heap_free(struct heap_helper_buffer *buffer)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(buffer->heap);
+	unsigned long nr_pages = buffer->pagecount;
+	struct page *cma_pages = buffer->priv_virt;
+
+	/* free page list */
+	kfree(buffer->pages);
+	/* release memory */
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+	kfree(buffer);
+}
+
+/* dmabuf heap CMA operations functions */
+static int cma_heap_allocate(struct dma_heap *heap,
+			     unsigned long len,
+			     unsigned long fd_flags,
+			     unsigned long heap_flags)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
+	struct heap_helper_buffer *helper_buffer;
+	struct page *cma_pages;
+	size_t size = PAGE_ALIGN(len);
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	unsigned long align = get_order(size);
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, cma_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	cma_pages = cma_alloc(cma_heap->cma, nr_pages, align, false);
+	if (!cma_pages)
+		goto free_buf;
+
+	if (PageHighMem(cma_pages)) {
+		unsigned long nr_clear_pages = nr_pages;
+		struct page *page = cma_pages;
+
+		while (nr_clear_pages > 0) {
+			void *vaddr = kmap_atomic(page);
+
+			memset(vaddr, 0, PAGE_SIZE);
+			kunmap_atomic(vaddr);
+			/*
+			 * Avoid wasting time zeroing memory if the process
+			 * has been killed by by SIGKILL
+			 */
+			if (fatal_signal_pending(current))
+				goto free_cma;
+
+			page++;
+			nr_clear_pages--;
+		}
+	} else {
+		memset(page_address(cma_pages), 0, size);
+	}
+
+	helper_buffer->pagecount = nr_pages;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto free_cma;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++)
+		helper_buffer->pages[pg] = &cma_pages[pg];
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto free_pages;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+	helper_buffer->priv_virt = cma_pages;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+free_pages:
+	kfree(helper_buffer->pages);
+free_cma:
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+free_buf:
+	kfree(helper_buffer);
+	return ret;
+}
+
+static const struct dma_heap_ops cma_heap_ops = {
+	.allocate = cma_heap_allocate,
+};
+
+static int __add_cma_heap(struct cma *cma, void *data)
+{
+	struct cma_heap *cma_heap;
+	struct dma_heap_export_info exp_info;
+
+	cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL);
+	if (!cma_heap)
+		return -ENOMEM;
+	cma_heap->cma = cma;
+
+	exp_info.name = cma_get_name(cma);
+	exp_info.ops = &cma_heap_ops;
+	exp_info.priv = cma_heap;
+
+	cma_heap->heap = dma_heap_add(&exp_info);
+	if (IS_ERR(cma_heap->heap)) {
+		int ret = PTR_ERR(cma_heap->heap);
+
+		kfree(cma_heap);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int add_default_cma_heap(void)
+{
+	struct cma *default_cma = dev_get_cma_area(NULL);
+	int ret = 0;
+
+	if (default_cma)
+		ret = __add_cma_heap(default_cma, NULL);
+
+	return ret;
+}
+module_init(add_default_cma_heap);
+MODULE_DESCRIPTION("DMA-BUF CMA Heap");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c
new file mode 100644
index 0000000..d0696cf
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.c
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <uapi/linux/dma-heap.h>
+
+#include "heap-helpers.h"
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *))
+{
+	buffer->priv_virt = NULL;
+	mutex_init(&buffer->lock);
+	buffer->vmap_cnt = 0;
+	buffer->vaddr = NULL;
+	buffer->pagecount = 0;
+	buffer->pages = NULL;
+	INIT_LIST_HEAD(&buffer->attachments);
+	buffer->free = free;
+}
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+	exp_info.ops = &heap_helper_ops;
+	exp_info.size = buffer->size;
+	exp_info.flags = fd_flags;
+	exp_info.priv = buffer;
+
+	return dma_buf_export(&exp_info);
+}
+
+static void *dma_heap_map_kernel(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL);
+	if (!vaddr)
+		return ERR_PTR(-ENOMEM);
+
+	return vaddr;
+}
+
+static void dma_heap_buffer_destroy(struct heap_helper_buffer *buffer)
+{
+	if (buffer->vmap_cnt > 0) {
+		WARN(1, "%s: buffer still mapped in the kernel\n", __func__);
+		vunmap(buffer->vaddr);
+	}
+
+	buffer->free(buffer);
+}
+
+static void *dma_heap_buffer_vmap_get(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	if (buffer->vmap_cnt) {
+		buffer->vmap_cnt++;
+		return buffer->vaddr;
+	}
+	vaddr = dma_heap_map_kernel(buffer);
+	if (IS_ERR(vaddr))
+		return vaddr;
+	buffer->vaddr = vaddr;
+	buffer->vmap_cnt++;
+	return vaddr;
+}
+
+static void dma_heap_buffer_vmap_put(struct heap_helper_buffer *buffer)
+{
+	if (!--buffer->vmap_cnt) {
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+}
+
+struct dma_heaps_attachment {
+	struct device *dev;
+	struct sg_table table;
+	struct list_head list;
+};
+
+static int dma_heap_attach(struct dma_buf *dmabuf,
+			   struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	int ret;
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a)
+		return -ENOMEM;
+
+	ret = sg_alloc_table_from_pages(&a->table, buffer->pages,
+					buffer->pagecount, 0,
+					buffer->pagecount << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret) {
+		kfree(a);
+		return ret;
+	}
+
+	a->dev = attachment->dev;
+	INIT_LIST_HEAD(&a->list);
+
+	attachment->priv = a;
+
+	mutex_lock(&buffer->lock);
+	list_add(&a->list, &buffer->attachments);
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void dma_heap_detach(struct dma_buf *dmabuf,
+			    struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	list_del(&a->list);
+	mutex_unlock(&buffer->lock);
+
+	sg_free_table(&a->table);
+	kfree(a);
+}
+
+static
+struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment,
+				      enum dma_data_direction direction)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct sg_table *table = &a->table;
+	int ret;
+
+	ret = dma_map_sgtable(attachment->dev, table, direction, 0);
+	if (ret)
+		table = ERR_PTR(ret);
+	return table;
+}
+
+static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
+				   struct sg_table *table,
+				   enum dma_data_direction direction)
+{
+	dma_unmap_sgtable(attachment->dev, table, direction, 0);
+}
+
+static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct heap_helper_buffer *buffer = vma->vm_private_data;
+
+	if (vmf->pgoff > buffer->pagecount)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = buffer->pages[vmf->pgoff];
+	get_page(vmf->page);
+
+	return 0;
+}
+
+static const struct vm_operations_struct dma_heap_vm_ops = {
+	.fault = dma_heap_vm_fault,
+};
+
+static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	vma->vm_ops = &dma_heap_vm_ops;
+	vma->vm_private_data = buffer;
+
+	return 0;
+}
+
+static void dma_heap_dma_buf_release(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	dma_heap_buffer_destroy(buffer);
+}
+
+static int dma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+					     enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+	int ret = 0;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		invalidate_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_cpu(a->dev, a->table.sgl, a->table.nents,
+				    direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return ret;
+}
+
+static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					   enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		flush_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_device(a->dev, a->table.sgl, a->table.nents,
+				       direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	void *vaddr;
+
+	mutex_lock(&buffer->lock);
+	vaddr = dma_heap_buffer_vmap_get(buffer);
+	mutex_unlock(&buffer->lock);
+
+	return vaddr;
+}
+
+static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	dma_heap_buffer_vmap_put(buffer);
+	mutex_unlock(&buffer->lock);
+}
+
+const struct dma_buf_ops heap_helper_ops = {
+	.map_dma_buf = dma_heap_map_dma_buf,
+	.unmap_dma_buf = dma_heap_unmap_dma_buf,
+	.mmap = dma_heap_mmap,
+	.release = dma_heap_dma_buf_release,
+	.attach = dma_heap_attach,
+	.detach = dma_heap_detach,
+	.begin_cpu_access = dma_heap_dma_buf_begin_cpu_access,
+	.end_cpu_access = dma_heap_dma_buf_end_cpu_access,
+	.vmap = dma_heap_dma_buf_vmap,
+	.vunmap = dma_heap_dma_buf_vunmap,
+};
diff --git a/drivers/dma-buf/heaps/heap-helpers.h b/drivers/dma-buf/heaps/heap-helpers.h
new file mode 100644
index 0000000..805d2df
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DMABUF Heaps helper code
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#ifndef _HEAP_HELPERS_H
+#define _HEAP_HELPERS_H
+
+#include <linux/dma-heap.h>
+#include <linux/list.h>
+
+/**
+ * struct heap_helper_buffer - helper buffer metadata
+ * @heap:		back pointer to the heap the buffer came from
+ * @dmabuf:		backing dma-buf for this buffer
+ * @size:		size of the buffer
+ * @priv_virt		pointer to heap specific private value
+ * @lock		mutext to protect the data in this structure
+ * @vmap_cnt		count of vmap references on the buffer
+ * @vaddr		vmap'ed virtual address
+ * @pagecount		number of pages in the buffer
+ * @pages		list of page pointers
+ * @attachments		list of device attachments
+ *
+ * @free		heap callback to free the buffer
+ */
+struct heap_helper_buffer {
+	struct dma_heap *heap;
+	struct dma_buf *dmabuf;
+	size_t size;
+
+	void *priv_virt;
+	struct mutex lock;
+	int vmap_cnt;
+	void *vaddr;
+	pgoff_t pagecount;
+	struct page **pages;
+	struct list_head attachments;
+
+	void (*free)(struct heap_helper_buffer *buffer);
+};
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *));
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags);
+
+extern const struct dma_buf_ops heap_helper_ops;
+#endif /* _HEAP_HELPERS_H */
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
new file mode 100644
index 0000000..0bf688e
--- /dev/null
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF System heap exporter
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-heap.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <asm/page.h>
+
+#include "heap-helpers.h"
+
+struct dma_heap *sys_heap;
+
+static void system_heap_free(struct heap_helper_buffer *buffer)
+{
+	pgoff_t pg;
+
+	for (pg = 0; pg < buffer->pagecount; pg++)
+		__free_page(buffer->pages[pg]);
+	kfree(buffer->pages);
+	kfree(buffer);
+}
+
+static int system_heap_allocate(struct dma_heap *heap,
+				unsigned long len,
+				unsigned long fd_flags,
+				unsigned long heap_flags)
+{
+	struct heap_helper_buffer *helper_buffer;
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, system_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	helper_buffer->pagecount = len / PAGE_SIZE;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto err0;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++) {
+		/*
+		 * Avoid trying to allocate memory if the process
+		 * has been killed by by SIGKILL
+		 */
+		if (fatal_signal_pending(current))
+			goto err1;
+
+		helper_buffer->pages[pg] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!helper_buffer->pages[pg])
+			goto err1;
+	}
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto err1;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+err1:
+	while (pg > 0)
+		__free_page(helper_buffer->pages[--pg]);
+	kfree(helper_buffer->pages);
+err0:
+	kfree(helper_buffer);
+
+	return ret;
+}
+
+static const struct dma_heap_ops system_heap_ops = {
+	.allocate = system_heap_allocate,
+};
+
+static int system_heap_create(void)
+{
+	struct dma_heap_export_info exp_info;
+	int ret = 0;
+
+	exp_info.name = "system";
+	exp_info.ops = &system_heap_ops;
+	exp_info.priv = NULL;
+
+	sys_heap = dma_heap_add(&exp_info);
+	if (IS_ERR(sys_heap))
+		ret = PTR_ERR(sys_heap);
+
+	return ret;
+}
+module_init(system_heap_create);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h
index 5320386..bc8cea6 100644
--- a/drivers/dma-buf/selftests.h
+++ b/drivers/dma-buf/selftests.h
@@ -5,9 +5,10 @@
  * a module parameter. It must be unique and legal for a C identifier.
  *
  * The function should be of type int function(void). It may be conditionally
- * compiled using #if IS_ENABLED(DRM_I915_SELFTEST).
+ * compiled using #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST).
  *
  * Tests are executed in order by igt/dmabuf_selftest
  */
 selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */
 selftest(dma_fence, dma_fence)
+selftest(dma_fence_chain, dma_fence_chain)
diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c
new file mode 100644
index 0000000..9525f7f
--- /dev/null
+++ b/drivers/dma-buf/st-dma-fence-chain.c
@@ -0,0 +1,714 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-fence.h>
+#include <linux/dma-fence-chain.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/random.h>
+
+#include "selftest.h"
+
+#define CHAIN_SZ (4 << 10)
+
+static struct kmem_cache *slab_fences;
+
+static inline struct mock_fence {
+	struct dma_fence base;
+	spinlock_t lock;
+} *to_mock_fence(struct dma_fence *f) {
+	return container_of(f, struct mock_fence, base);
+}
+
+static const char *mock_name(struct dma_fence *f)
+{
+	return "mock";
+}
+
+static void mock_fence_release(struct dma_fence *f)
+{
+	kmem_cache_free(slab_fences, to_mock_fence(f));
+}
+
+static const struct dma_fence_ops mock_ops = {
+	.get_driver_name = mock_name,
+	.get_timeline_name = mock_name,
+	.release = mock_fence_release,
+};
+
+static struct dma_fence *mock_fence(void)
+{
+	struct mock_fence *f;
+
+	f = kmem_cache_alloc(slab_fences, GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	spin_lock_init(&f->lock);
+	dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0);
+
+	return &f->base;
+}
+
+static inline struct mock_chain {
+	struct dma_fence_chain base;
+} *to_mock_chain(struct dma_fence *f) {
+	return container_of(f, struct mock_chain, base.base);
+}
+
+static struct dma_fence *mock_chain(struct dma_fence *prev,
+				    struct dma_fence *fence,
+				    u64 seqno)
+{
+	struct mock_chain *f;
+
+	f = kmalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	dma_fence_chain_init(&f->base,
+			     dma_fence_get(prev),
+			     dma_fence_get(fence),
+			     seqno);
+
+	return &f->base.base;
+}
+
+static int sanitycheck(void *arg)
+{
+	struct dma_fence *f, *chain;
+	int err = 0;
+
+	f = mock_fence();
+	if (!f)
+		return -ENOMEM;
+
+	chain = mock_chain(NULL, f, 1);
+	if (!chain)
+		err = -ENOMEM;
+
+	dma_fence_signal(f);
+	dma_fence_put(f);
+
+	dma_fence_put(chain);
+
+	return err;
+}
+
+struct fence_chains {
+	unsigned int chain_length;
+	struct dma_fence **fences;
+	struct dma_fence **chains;
+
+	struct dma_fence *tail;
+};
+
+static uint64_t seqno_inc(unsigned int i)
+{
+	return i + 1;
+}
+
+static int fence_chains_init(struct fence_chains *fc, unsigned int count,
+			     uint64_t (*seqno_fn)(unsigned int))
+{
+	unsigned int i;
+	int err = 0;
+
+	fc->chains = kvmalloc_array(count, sizeof(*fc->chains),
+				    GFP_KERNEL | __GFP_ZERO);
+	if (!fc->chains)
+		return -ENOMEM;
+
+	fc->fences = kvmalloc_array(count, sizeof(*fc->fences),
+				    GFP_KERNEL | __GFP_ZERO);
+	if (!fc->fences) {
+		err = -ENOMEM;
+		goto err_chains;
+	}
+
+	fc->tail = NULL;
+	for (i = 0; i < count; i++) {
+		fc->fences[i] = mock_fence();
+		if (!fc->fences[i]) {
+			err = -ENOMEM;
+			goto unwind;
+		}
+
+		fc->chains[i] = mock_chain(fc->tail,
+					   fc->fences[i],
+					   seqno_fn(i));
+		if (!fc->chains[i]) {
+			err = -ENOMEM;
+			goto unwind;
+		}
+
+		fc->tail = fc->chains[i];
+	}
+
+	fc->chain_length = i;
+	return 0;
+
+unwind:
+	for (i = 0; i < count; i++) {
+		dma_fence_put(fc->fences[i]);
+		dma_fence_put(fc->chains[i]);
+	}
+	kvfree(fc->fences);
+err_chains:
+	kvfree(fc->chains);
+	return err;
+}
+
+static void fence_chains_fini(struct fence_chains *fc)
+{
+	unsigned int i;
+
+	for (i = 0; i < fc->chain_length; i++) {
+		dma_fence_signal(fc->fences[i]);
+		dma_fence_put(fc->fences[i]);
+	}
+	kvfree(fc->fences);
+
+	for (i = 0; i < fc->chain_length; i++)
+		dma_fence_put(fc->chains[i]);
+	kvfree(fc->chains);
+}
+
+static int find_seqno(void *arg)
+{
+	struct fence_chains fc;
+	struct dma_fence *fence;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, 64, seqno_inc);
+	if (err)
+		return err;
+
+	fence = dma_fence_get(fc.tail);
+	err = dma_fence_chain_find_seqno(&fence, 0);
+	dma_fence_put(fence);
+	if (err) {
+		pr_err("Reported %d for find_seqno(0)!\n", err);
+		goto err;
+	}
+
+	for (i = 0; i < fc.chain_length; i++) {
+		fence = dma_fence_get(fc.tail);
+		err = dma_fence_chain_find_seqno(&fence, i + 1);
+		dma_fence_put(fence);
+		if (err) {
+			pr_err("Reported %d for find_seqno(%d:%d)!\n",
+			       err, fc.chain_length + 1, i + 1);
+			goto err;
+		}
+		if (fence != fc.chains[i]) {
+			pr_err("Incorrect fence reported by find_seqno(%d:%d)\n",
+			       fc.chain_length + 1, i + 1);
+			err = -EINVAL;
+			goto err;
+		}
+
+		dma_fence_get(fence);
+		err = dma_fence_chain_find_seqno(&fence, i + 1);
+		dma_fence_put(fence);
+		if (err) {
+			pr_err("Error reported for finding self\n");
+			goto err;
+		}
+		if (fence != fc.chains[i]) {
+			pr_err("Incorrect fence reported by find self\n");
+			err = -EINVAL;
+			goto err;
+		}
+
+		dma_fence_get(fence);
+		err = dma_fence_chain_find_seqno(&fence, i + 2);
+		dma_fence_put(fence);
+		if (!err) {
+			pr_err("Error not reported for future fence: find_seqno(%d:%d)!\n",
+			       i + 1, i + 2);
+			err = -EINVAL;
+			goto err;
+		}
+
+		dma_fence_get(fence);
+		err = dma_fence_chain_find_seqno(&fence, i);
+		dma_fence_put(fence);
+		if (err) {
+			pr_err("Error reported for previous fence!\n");
+			goto err;
+		}
+		if (i > 0 && fence != fc.chains[i - 1]) {
+			pr_err("Incorrect fence reported by find_seqno(%d:%d)\n",
+			       i + 1, i);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static int find_signaled(void *arg)
+{
+	struct fence_chains fc;
+	struct dma_fence *fence;
+	int err;
+
+	err = fence_chains_init(&fc, 2, seqno_inc);
+	if (err)
+		return err;
+
+	dma_fence_signal(fc.fences[0]);
+
+	fence = dma_fence_get(fc.tail);
+	err = dma_fence_chain_find_seqno(&fence, 1);
+	dma_fence_put(fence);
+	if (err) {
+		pr_err("Reported %d for find_seqno()!\n", err);
+		goto err;
+	}
+
+	if (fence && fence != fc.chains[0]) {
+		pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:1\n",
+		       fence->seqno);
+
+		dma_fence_get(fence);
+		err = dma_fence_chain_find_seqno(&fence, 1);
+		dma_fence_put(fence);
+		if (err)
+			pr_err("Reported %d for finding self!\n", err);
+
+		err = -EINVAL;
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static int find_out_of_order(void *arg)
+{
+	struct fence_chains fc;
+	struct dma_fence *fence;
+	int err;
+
+	err = fence_chains_init(&fc, 3, seqno_inc);
+	if (err)
+		return err;
+
+	dma_fence_signal(fc.fences[1]);
+
+	fence = dma_fence_get(fc.tail);
+	err = dma_fence_chain_find_seqno(&fence, 2);
+	dma_fence_put(fence);
+	if (err) {
+		pr_err("Reported %d for find_seqno()!\n", err);
+		goto err;
+	}
+
+	/*
+	 * We signaled the middle fence (2) of the 1-2-3 chain. The behavior
+	 * of the dma-fence-chain is to make us wait for all the fences up to
+	 * the point we want. Since fence 1 is still not signaled, this what
+	 * we should get as fence to wait upon (fence 2 being garbage
+	 * collected during the traversal of the chain).
+	 */
+	if (fence != fc.chains[0]) {
+		pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:2\n",
+		       fence ? fence->seqno : 0);
+
+		err = -EINVAL;
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static uint64_t seqno_inc2(unsigned int i)
+{
+	return 2 * i + 2;
+}
+
+static int find_gap(void *arg)
+{
+	struct fence_chains fc;
+	struct dma_fence *fence;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, 64, seqno_inc2);
+	if (err)
+		return err;
+
+	for (i = 0; i < fc.chain_length; i++) {
+		fence = dma_fence_get(fc.tail);
+		err = dma_fence_chain_find_seqno(&fence, 2 * i + 1);
+		dma_fence_put(fence);
+		if (err) {
+			pr_err("Reported %d for find_seqno(%d:%d)!\n",
+			       err, fc.chain_length + 1, 2 * i + 1);
+			goto err;
+		}
+		if (fence != fc.chains[i]) {
+			pr_err("Incorrect fence.seqno:%lld reported by find_seqno(%d:%d)\n",
+			       fence->seqno,
+			       fc.chain_length + 1,
+			       2 * i + 1);
+			err = -EINVAL;
+			goto err;
+		}
+
+		dma_fence_get(fence);
+		err = dma_fence_chain_find_seqno(&fence, 2 * i + 2);
+		dma_fence_put(fence);
+		if (err) {
+			pr_err("Error reported for finding self\n");
+			goto err;
+		}
+		if (fence != fc.chains[i]) {
+			pr_err("Incorrect fence reported by find self\n");
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+struct find_race {
+	struct fence_chains fc;
+	atomic_t children;
+};
+
+static int __find_race(void *arg)
+{
+	struct find_race *data = arg;
+	int err = 0;
+
+	while (!kthread_should_stop()) {
+		struct dma_fence *fence = dma_fence_get(data->fc.tail);
+		int seqno;
+
+		seqno = prandom_u32_max(data->fc.chain_length) + 1;
+
+		err = dma_fence_chain_find_seqno(&fence, seqno);
+		if (err) {
+			pr_err("Failed to find fence seqno:%d\n",
+			       seqno);
+			dma_fence_put(fence);
+			break;
+		}
+		if (!fence)
+			goto signal;
+
+		/*
+		 * We can only find ourselves if we are on fence we were
+		 * looking for.
+		 */
+		if (fence->seqno == seqno) {
+			err = dma_fence_chain_find_seqno(&fence, seqno);
+			if (err) {
+				pr_err("Reported an invalid fence for find-self:%d\n",
+				       seqno);
+				dma_fence_put(fence);
+				break;
+			}
+		}
+
+		dma_fence_put(fence);
+
+signal:
+		seqno = prandom_u32_max(data->fc.chain_length - 1);
+		dma_fence_signal(data->fc.fences[seqno]);
+		cond_resched();
+	}
+
+	if (atomic_dec_and_test(&data->children))
+		wake_up_var(&data->children);
+	return err;
+}
+
+static int find_race(void *arg)
+{
+	struct find_race data;
+	int ncpus = num_online_cpus();
+	struct task_struct **threads;
+	unsigned long count;
+	int err;
+	int i;
+
+	err = fence_chains_init(&data.fc, CHAIN_SZ, seqno_inc);
+	if (err)
+		return err;
+
+	threads = kmalloc_array(ncpus, sizeof(*threads), GFP_KERNEL);
+	if (!threads) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	atomic_set(&data.children, 0);
+	for (i = 0; i < ncpus; i++) {
+		threads[i] = kthread_run(__find_race, &data, "dmabuf/%d", i);
+		if (IS_ERR(threads[i])) {
+			ncpus = i;
+			break;
+		}
+		atomic_inc(&data.children);
+		get_task_struct(threads[i]);
+	}
+
+	wait_var_event_timeout(&data.children,
+			       !atomic_read(&data.children),
+			       5 * HZ);
+
+	for (i = 0; i < ncpus; i++) {
+		int ret;
+
+		ret = kthread_stop(threads[i]);
+		if (ret && !err)
+			err = ret;
+		put_task_struct(threads[i]);
+	}
+	kfree(threads);
+
+	count = 0;
+	for (i = 0; i < data.fc.chain_length; i++)
+		if (dma_fence_is_signaled(data.fc.fences[i]))
+			count++;
+	pr_info("Completed %lu cycles\n", count);
+
+err:
+	fence_chains_fini(&data.fc);
+	return err;
+}
+
+static int signal_forward(void *arg)
+{
+	struct fence_chains fc;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, 64, seqno_inc);
+	if (err)
+		return err;
+
+	for (i = 0; i < fc.chain_length; i++) {
+		dma_fence_signal(fc.fences[i]);
+
+		if (!dma_fence_is_signaled(fc.chains[i])) {
+			pr_err("chain[%d] not signaled!\n", i);
+			err = -EINVAL;
+			goto err;
+		}
+
+		if (i + 1 < fc.chain_length &&
+		    dma_fence_is_signaled(fc.chains[i + 1])) {
+			pr_err("chain[%d] is signaled!\n", i);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static int signal_backward(void *arg)
+{
+	struct fence_chains fc;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, 64, seqno_inc);
+	if (err)
+		return err;
+
+	for (i = fc.chain_length; i--; ) {
+		dma_fence_signal(fc.fences[i]);
+
+		if (i > 0 && dma_fence_is_signaled(fc.chains[i])) {
+			pr_err("chain[%d] is signaled!\n", i);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+	for (i = 0; i < fc.chain_length; i++) {
+		if (!dma_fence_is_signaled(fc.chains[i])) {
+			pr_err("chain[%d] was not signaled!\n", i);
+			err = -EINVAL;
+			goto err;
+		}
+	}
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static int __wait_fence_chains(void *arg)
+{
+	struct fence_chains *fc = arg;
+
+	if (dma_fence_wait(fc->tail, false))
+		return -EIO;
+
+	return 0;
+}
+
+static int wait_forward(void *arg)
+{
+	struct fence_chains fc;
+	struct task_struct *tsk;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc);
+	if (err)
+		return err;
+
+	tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		goto err;
+	}
+	get_task_struct(tsk);
+	yield_to(tsk, true);
+
+	for (i = 0; i < fc.chain_length; i++)
+		dma_fence_signal(fc.fences[i]);
+
+	err = kthread_stop(tsk);
+	put_task_struct(tsk);
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static int wait_backward(void *arg)
+{
+	struct fence_chains fc;
+	struct task_struct *tsk;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc);
+	if (err)
+		return err;
+
+	tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		goto err;
+	}
+	get_task_struct(tsk);
+	yield_to(tsk, true);
+
+	for (i = fc.chain_length; i--; )
+		dma_fence_signal(fc.fences[i]);
+
+	err = kthread_stop(tsk);
+	put_task_struct(tsk);
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+static void randomise_fences(struct fence_chains *fc)
+{
+	unsigned int count = fc->chain_length;
+
+	/* Fisher-Yates shuffle courtesy of Knuth */
+	while (--count) {
+		unsigned int swp;
+
+		swp = prandom_u32_max(count + 1);
+		if (swp == count)
+			continue;
+
+		swap(fc->fences[count], fc->fences[swp]);
+	}
+}
+
+static int wait_random(void *arg)
+{
+	struct fence_chains fc;
+	struct task_struct *tsk;
+	int err;
+	int i;
+
+	err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc);
+	if (err)
+		return err;
+
+	randomise_fences(&fc);
+
+	tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		goto err;
+	}
+	get_task_struct(tsk);
+	yield_to(tsk, true);
+
+	for (i = 0; i < fc.chain_length; i++)
+		dma_fence_signal(fc.fences[i]);
+
+	err = kthread_stop(tsk);
+	put_task_struct(tsk);
+
+err:
+	fence_chains_fini(&fc);
+	return err;
+}
+
+int dma_fence_chain(void)
+{
+	static const struct subtest tests[] = {
+		SUBTEST(sanitycheck),
+		SUBTEST(find_seqno),
+		SUBTEST(find_signaled),
+		SUBTEST(find_out_of_order),
+		SUBTEST(find_gap),
+		SUBTEST(find_race),
+		SUBTEST(signal_forward),
+		SUBTEST(signal_backward),
+		SUBTEST(wait_forward),
+		SUBTEST(wait_backward),
+		SUBTEST(wait_random),
+	};
+	int ret;
+
+	pr_info("sizeof(dma_fence_chain)=%zu\n",
+		sizeof(struct dma_fence_chain));
+
+	slab_fences = KMEM_CACHE(mock_fence,
+				 SLAB_TYPESAFE_BY_RCU |
+				 SLAB_HWCACHE_ALIGN);
+	if (!slab_fences)
+		return -ENOMEM;
+
+	ret = subtests(tests, NULL);
+
+	kmem_cache_destroy(slab_fences);
+	return ret;
+}
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 6713cfb..348b3a9 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -408,5 +408,5 @@
 	.open           = sw_sync_debugfs_open,
 	.release        = sw_sync_debugfs_release,
 	.unlocked_ioctl = sw_sync_ioctl,
-	.compat_ioctl	= sw_sync_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
 };
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 992c15c..f0c8229 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -481,5 +481,5 @@
 	.release = sync_file_release,
 	.poll = sync_file_poll,
 	.unlocked_ioctl = sync_file_ioctl,
-	.compat_ioctl = sync_file_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
 };
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 9635897..db732f7 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -18,6 +18,8 @@
 struct udmabuf {
 	pgoff_t pagecount;
 	struct page **pages;
+	struct sg_table *sg;
+	struct miscdevice *device;
 };
 
 static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -46,10 +48,10 @@
 	return 0;
 }
 
-static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
-				    enum dma_data_direction direction)
+static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
+				     enum dma_data_direction direction)
 {
-	struct udmabuf *ubuf = at->dmabuf->priv;
+	struct udmabuf *ubuf = buf->priv;
 	struct sg_table *sg;
 	int ret;
 
@@ -61,10 +63,9 @@
 					GFP_KERNEL);
 	if (ret < 0)
 		goto err;
-	if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) {
-		ret = -EINVAL;
+	ret = dma_map_sgtable(dev, sg, direction, 0);
+	if (ret < 0)
 		goto err;
-	}
 	return sg;
 
 err:
@@ -73,54 +74,89 @@
 	return ERR_PTR(ret);
 }
 
+static void put_sg_table(struct device *dev, struct sg_table *sg,
+			 enum dma_data_direction direction)
+{
+	dma_unmap_sgtable(dev, sg, direction, 0);
+	sg_free_table(sg);
+	kfree(sg);
+}
+
+static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
+				    enum dma_data_direction direction)
+{
+	return get_sg_table(at->dev, at->dmabuf, direction);
+}
+
 static void unmap_udmabuf(struct dma_buf_attachment *at,
 			  struct sg_table *sg,
 			  enum dma_data_direction direction)
 {
-	dma_unmap_sg(at->dev, sg->sgl, sg->nents, direction);
-	sg_free_table(sg);
-	kfree(sg);
+	return put_sg_table(at->dev, sg, direction);
 }
 
 static void release_udmabuf(struct dma_buf *buf)
 {
 	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
 	pgoff_t pg;
 
+	if (ubuf->sg)
+		put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
+
 	for (pg = 0; pg < ubuf->pagecount; pg++)
 		put_page(ubuf->pages[pg]);
 	kfree(ubuf->pages);
 	kfree(ubuf);
 }
 
-static void *kmap_udmabuf(struct dma_buf *buf, unsigned long page_num)
+static int begin_cpu_udmabuf(struct dma_buf *buf,
+			     enum dma_data_direction direction)
 {
 	struct udmabuf *ubuf = buf->priv;
-	struct page *page = ubuf->pages[page_num];
+	struct device *dev = ubuf->device->this_device;
 
-	return kmap(page);
+	if (!ubuf->sg) {
+		ubuf->sg = get_sg_table(dev, buf, direction);
+		if (IS_ERR(ubuf->sg))
+			return PTR_ERR(ubuf->sg);
+	} else {
+		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
+				    direction);
+	}
+
+	return 0;
 }
 
-static void kunmap_udmabuf(struct dma_buf *buf, unsigned long page_num,
-			   void *vaddr)
+static int end_cpu_udmabuf(struct dma_buf *buf,
+			   enum dma_data_direction direction)
 {
-	kunmap(vaddr);
+	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
+
+	if (!ubuf->sg)
+		return -EINVAL;
+
+	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	return 0;
 }
 
 static const struct dma_buf_ops udmabuf_ops = {
-	.map_dma_buf	  = map_udmabuf,
-	.unmap_dma_buf	  = unmap_udmabuf,
-	.release	  = release_udmabuf,
-	.map		  = kmap_udmabuf,
-	.unmap		  = kunmap_udmabuf,
-	.mmap		  = mmap_udmabuf,
+	.cache_sgt_mapping = true,
+	.map_dma_buf	   = map_udmabuf,
+	.unmap_dma_buf	   = unmap_udmabuf,
+	.release	   = release_udmabuf,
+	.mmap		   = mmap_udmabuf,
+	.begin_cpu_access  = begin_cpu_udmabuf,
+	.end_cpu_access    = end_cpu_udmabuf,
 };
 
 #define SEALS_WANTED (F_SEAL_SHRINK)
 #define SEALS_DENIED (F_SEAL_WRITE)
 
-static long udmabuf_create(const struct udmabuf_create_list *head,
-			   const struct udmabuf_create_item *list)
+static long udmabuf_create(struct miscdevice *device,
+			   struct udmabuf_create_list *head,
+			   struct udmabuf_create_item *list)
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
@@ -187,6 +223,7 @@
 	exp_info.priv = ubuf;
 	exp_info.flags = O_RDWR;
 
+	ubuf->device = device;
 	buf = dma_buf_export(&exp_info);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
@@ -224,7 +261,7 @@
 	list.offset = create.offset;
 	list.size   = create.size;
 
-	return udmabuf_create(&head, &list);
+	return udmabuf_create(filp->private_data, &head, &list);
 }
 
 static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
@@ -243,7 +280,7 @@
 	if (IS_ERR(list))
 		return PTR_ERR(list);
 
-	ret = udmabuf_create(&head, list);
+	ret = udmabuf_create(filp->private_data, &head, list);
 	kfree(list);
 	return ret;
 }
@@ -270,6 +307,9 @@
 static const struct file_operations udmabuf_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl = udmabuf_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = udmabuf_ioctl,
+#endif
 };
 
 static struct miscdevice udmabuf_misc = {