11 files changed, 480 insertions, 280 deletions

diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index fee04fdb0822..b46eb8a552d7 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -36,7 +36,6 @@ config UDMABUF
 	depends on DMA_SHARED_BUFFER
 	depends on MEMFD_CREATE || COMPILE_TEST
 	depends on MMU
-	select VMAP_PFN
 	help
 	  A driver to let userspace turn memfd regions into dma-bufs.
 	  Qemu can use this to create host dmabufs for guest framebuffers.
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 5baa83b85515..2bcf9ceca997 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -19,7 +19,9 @@
 #include <linux/anon_inodes.h>
 #include <linux/export.h>
 #include <linux/debugfs.h>
+#include <linux/list.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/seq_file.h>
 #include <linux/sync_file.h>
 #include <linux/poll.h>
@@ -35,35 +37,91 @@
 
 static inline int is_dma_buf_file(struct file *);
 
-#if IS_ENABLED(CONFIG_DEBUG_FS)
-static DEFINE_MUTEX(debugfs_list_mutex);
-static LIST_HEAD(debugfs_list);
+static DEFINE_MUTEX(dmabuf_list_mutex);
+static LIST_HEAD(dmabuf_list);
 
-static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf)
+static void __dma_buf_list_add(struct dma_buf *dmabuf)
 {
-	mutex_lock(&debugfs_list_mutex);
-	list_add(&dmabuf->list_node, &debugfs_list);
-	mutex_unlock(&debugfs_list_mutex);
+	mutex_lock(&dmabuf_list_mutex);
+	list_add(&dmabuf->list_node, &dmabuf_list);
+	mutex_unlock(&dmabuf_list_mutex);
 }
 
-static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf)
+static void __dma_buf_list_del(struct dma_buf *dmabuf)
 {
 	if (!dmabuf)
 		return;
 
-	mutex_lock(&debugfs_list_mutex);
+	mutex_lock(&dmabuf_list_mutex);
 	list_del(&dmabuf->list_node);
-	mutex_unlock(&debugfs_list_mutex);
+	mutex_unlock(&dmabuf_list_mutex);
 }
-#else
-static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf)
+
+/**
+ * dma_buf_iter_begin - begin iteration through global list of all DMA buffers
+ *
+ * Returns the first buffer in the global list of DMA-bufs that's not in the
+ * process of being destroyed. Increments that buffer's reference count to
+ * prevent buffer destruction. Callers must release the reference, either by
+ * continuing iteration with dma_buf_iter_next(), or with dma_buf_put().
+ *
+ * Return:
+ * * First buffer from global list, with refcount elevated
+ * * NULL if no active buffers are present
+ */
+struct dma_buf *dma_buf_iter_begin(void)
 {
+	struct dma_buf *ret = NULL, *dmabuf;
+
+	/*
+	 * The list mutex does not protect a dmabuf's refcount, so it can be
+	 * zeroed while we are iterating. We cannot call get_dma_buf() since the
+	 * caller may not already own a reference to the buffer.
+	 */
+	mutex_lock(&dmabuf_list_mutex);
+	list_for_each_entry(dmabuf, &dmabuf_list, list_node) {
+		if (file_ref_get(&dmabuf->file->f_ref)) {
+			ret = dmabuf;
+			break;
+		}
+	}
+	mutex_unlock(&dmabuf_list_mutex);
+	return ret;
 }
 
-static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf)
+/**
+ * dma_buf_iter_next - continue iteration through global list of all DMA buffers
+ * @dmabuf:	[in]	pointer to dma_buf
+ *
+ * Decrements the reference count on the provided buffer. Returns the next
+ * buffer from the remainder of the global list of DMA-bufs with its reference
+ * count incremented. Callers must release the reference, either by continuing
+ * iteration with dma_buf_iter_next(), or with dma_buf_put().
+ *
+ * Return:
+ * * Next buffer from global list, with refcount elevated
+ * * NULL if no additional active buffers are present
+ */
+struct dma_buf *dma_buf_iter_next(struct dma_buf *dmabuf)
 {
+	struct dma_buf *ret = NULL;
+
+	/*
+	 * The list mutex does not protect a dmabuf's refcount, so it can be
+	 * zeroed while we are iterating. We cannot call get_dma_buf() since the
+	 * caller may not already own a reference to the buffer.
+	 */
+	mutex_lock(&dmabuf_list_mutex);
+	dma_buf_put(dmabuf);
+	list_for_each_entry_continue(dmabuf, &dmabuf_list, list_node) {
+		if (file_ref_get(&dmabuf->file->f_ref)) {
+			ret = dmabuf;
+			break;
+		}
+	}
+	mutex_unlock(&dmabuf_list_mutex);
+	return ret;
 }
-#endif
 
 static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen)
 {
@@ -115,7 +173,7 @@ static int dma_buf_file_release(struct inode *inode, struct file *file)
 	if (!is_dma_buf_file(file))
 		return -EINVAL;
 
-	__dma_buf_debugfs_list_del(file->private_data);
+	__dma_buf_list_del(file->private_data);
 
 	return 0;
 }
@@ -636,10 +694,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 		    || !exp_info->ops->release))
 		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);
 
@@ -689,7 +743,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	file->f_path.dentry->d_fsdata = dmabuf;
 	dmabuf->file = file;
 
-	__dma_buf_debugfs_list_add(dmabuf);
+	__dma_buf_list_add(dmabuf);
 
 	return dmabuf;
 
@@ -782,7 +836,7 @@ static void mangle_sg_table(struct sg_table *sg_table)
 
 	/* To catch abuse of the underlying struct page by importers mix
 	 * up the bits, but take care to preserve the low SG_ bits to
-	 * not corrupt the sgt. The mixing is undone in __unmap_dma_buf
+	 * not corrupt the sgt. The mixing is undone on unmap
 	 * before passing the sgt back to the exporter.
 	 */
 	for_each_sgtable_sg(sg_table, sg, i)
@@ -790,29 +844,19 @@ static void mangle_sg_table(struct sg_table *sg_table)
 #endif
 
 }
-static struct sg_table *__map_dma_buf(struct dma_buf_attachment *attach,
-				       enum dma_data_direction direction)
-{
-	struct sg_table *sg_table;
-	signed long ret;
 
-	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
-	if (IS_ERR_OR_NULL(sg_table))
-		return sg_table;
-
-	if (!dma_buf_attachment_is_dynamic(attach)) {
-		ret = dma_resv_wait_timeout(attach->dmabuf->resv,
-					    DMA_RESV_USAGE_KERNEL, true,
-					    MAX_SCHEDULE_TIMEOUT);
-		if (ret < 0) {
-			attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
-							   direction);
-			return ERR_PTR(ret);
-		}
-	}
+static inline bool
+dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach)
+{
+	return !!attach->importer_ops;
+}
 
-	mangle_sg_table(sg_table);
-	return sg_table;
+static bool
+dma_buf_pin_on_map(struct dma_buf_attachment *attach)
+{
+	return attach->dmabuf->ops->pin &&
+		(!dma_buf_attachment_is_dynamic(attach) ||
+		 !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY));
 }
 
 /**
@@ -935,48 +979,11 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
 	list_add(&attach->node, &dmabuf->attachments);
 	dma_resv_unlock(dmabuf->resv);
 
-	/* 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;
-
-		dma_resv_lock(attach->dmabuf->resv, NULL);
-		if (dma_buf_is_dynamic(attach->dmabuf)) {
-			ret = dmabuf->ops->pin(attach);
-			if (ret)
-				goto err_unlock;
-		}
-
-		sgt = __map_dma_buf(attach, DMA_BIDIRECTIONAL);
-		if (!sgt)
-			sgt = ERR_PTR(-ENOMEM);
-		if (IS_ERR(sgt)) {
-			ret = PTR_ERR(sgt);
-			goto err_unpin;
-		}
-		dma_resv_unlock(attach->dmabuf->resv);
-		attach->sgt = sgt;
-		attach->dir = DMA_BIDIRECTIONAL;
-	}
-
 	return attach;
 
 err_attach:
 	kfree(attach);
 	return ERR_PTR(ret);
-
-err_unpin:
-	if (dma_buf_is_dynamic(attach->dmabuf))
-		dmabuf->ops->unpin(attach);
-
-err_unlock:
-	dma_resv_unlock(attach->dmabuf->resv);
-
-	dma_buf_detach(dmabuf, attach);
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_dynamic_attach, "DMA_BUF");
 
@@ -995,16 +1002,6 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_attach, "DMA_BUF");
 
-static void __unmap_dma_buf(struct dma_buf_attachment *attach,
-			    struct sg_table *sg_table,
-			    enum dma_data_direction direction)
-{
-	/* uses XOR, hence this unmangles */
-	mangle_sg_table(sg_table);
-
-	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
-}
-
 /**
  * dma_buf_detach - Remove the given attachment from dmabuf's attachments list
  * @dmabuf:	[in]	buffer to detach from.
@@ -1020,16 +1017,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 		return;
 
 	dma_resv_lock(dmabuf->resv, NULL);
-
-	if (attach->sgt) {
-
-		__unmap_dma_buf(attach, attach->sgt, attach->dir);
-
-		if (dma_buf_is_dynamic(attach->dmabuf))
-			dmabuf->ops->unpin(attach);
-	}
 	list_del(&attach->node);
-
 	dma_resv_unlock(dmabuf->resv);
 
 	if (dmabuf->ops->detach)
@@ -1058,7 +1046,7 @@ int dma_buf_pin(struct dma_buf_attachment *attach)
 	struct dma_buf *dmabuf = attach->dmabuf;
 	int ret = 0;
 
-	WARN_ON(!dma_buf_attachment_is_dynamic(attach));
+	WARN_ON(!attach->importer_ops);
 
 	dma_resv_assert_held(dmabuf->resv);
 
@@ -1081,7 +1069,7 @@ void dma_buf_unpin(struct dma_buf_attachment *attach)
 {
 	struct dma_buf *dmabuf = attach->dmabuf;
 
-	WARN_ON(!dma_buf_attachment_is_dynamic(attach));
+	WARN_ON(!attach->importer_ops);
 
 	dma_resv_assert_held(dmabuf->resv);
 
@@ -1115,7 +1103,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 					enum dma_data_direction direction)
 {
 	struct sg_table *sg_table;
-	int r;
+	signed long ret;
 
 	might_sleep();
 
@@ -1124,41 +1112,37 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 
 	dma_resv_assert_held(attach->dmabuf->resv);
 
-	if (attach->sgt) {
+	if (dma_buf_pin_on_map(attach)) {
+		ret = attach->dmabuf->ops->pin(attach);
 		/*
-		 * Two mappings with different directions for the same
-		 * attachment are not allowed.
+		 * Catch exporters making buffers inaccessible even when
+		 * attachments preventing that exist.
 		 */
-		if (attach->dir != direction &&
-		    attach->dir != DMA_BIDIRECTIONAL)
-			return ERR_PTR(-EBUSY);
-
-		return attach->sgt;
-	}
-
-	if (dma_buf_is_dynamic(attach->dmabuf)) {
-		if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
-			r = attach->dmabuf->ops->pin(attach);
-			if (r)
-				return ERR_PTR(r);
-		}
+		WARN_ON_ONCE(ret == -EBUSY);
+		if (ret)
+			return ERR_PTR(ret);
 	}
 
-	sg_table = __map_dma_buf(attach, direction);
+	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
+	if (IS_ERR(sg_table))
+		goto error_unpin;
 
-	if (IS_ERR(sg_table) && dma_buf_is_dynamic(attach->dmabuf) &&
-	     !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY))
-		attach->dmabuf->ops->unpin(attach);
-
-	if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) {
-		attach->sgt = sg_table;
-		attach->dir = direction;
+	/*
+	 * Importers with static attachments don't wait for fences.
+	 */
+	if (!dma_buf_attachment_is_dynamic(attach)) {
+		ret = dma_resv_wait_timeout(attach->dmabuf->resv,
+					    DMA_RESV_USAGE_KERNEL, true,
+					    MAX_SCHEDULE_TIMEOUT);
+		if (ret < 0)
+			goto error_unmap;
 	}
+	mangle_sg_table(sg_table);
 
 #ifdef CONFIG_DMA_API_DEBUG
-	if (!IS_ERR(sg_table)) {
+	{
 		struct scatterlist *sg;
 		u64 addr;
 		int len;
@@ -1175,6 +1159,16 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 	}
 #endif /* CONFIG_DMA_API_DEBUG */
 	return sg_table;
+
+error_unmap:
+	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
+	sg_table = ERR_PTR(ret);
+
+error_unpin:
+	if (dma_buf_pin_on_map(attach))
+		attach->dmabuf->ops->unpin(attach);
+
+	return sg_table;
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment, "DMA_BUF");
 
@@ -1227,14 +1221,11 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 
 	dma_resv_assert_held(attach->dmabuf->resv);
 
-	if (attach->sgt == sg_table)
-		return;
-
-	__unmap_dma_buf(attach, sg_table, direction);
+	mangle_sg_table(sg_table);
+	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);
+	if (dma_buf_pin_on_map(attach))
+		attach->dmabuf->ops->unpin(attach);
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment, "DMA_BUF");
 
@@ -1630,7 +1621,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 	size_t size = 0;
 	int ret;
 
-	ret = mutex_lock_interruptible(&debugfs_list_mutex);
+	ret = mutex_lock_interruptible(&dmabuf_list_mutex);
 
 	if (ret)
 		return ret;
@@ -1639,7 +1630,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 	seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\tname\n",
 		   "size", "flags", "mode", "count", "ino");
 
-	list_for_each_entry(buf_obj, &debugfs_list, list_node) {
+	list_for_each_entry(buf_obj, &dmabuf_list, list_node) {
 
 		ret = dma_resv_lock_interruptible(buf_obj->resv, NULL);
 		if (ret)
@@ -1676,11 +1667,11 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 
 	seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size);
 
-	mutex_unlock(&debugfs_list_mutex);
+	mutex_unlock(&dmabuf_list_mutex);
 	return 0;
 
 error_unlock:
-	mutex_unlock(&debugfs_list_mutex);
+	mutex_unlock(&dmabuf_list_mutex);
 	return ret;
 }
 
diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c
index 6345062731f1..a495d8a6c2e3 100644
--- a/drivers/dma-buf/dma-fence-unwrap.c
+++ b/drivers/dma-buf/dma-fence-unwrap.c
@@ -79,21 +79,58 @@ static int fence_cmp(const void *_a, const void *_b)
 	return 0;
 }
 
+/**
+ * dma_fence_dedup_array - Sort and deduplicate an array of dma_fence pointers
+ * @fences:     Array of dma_fence pointers to be deduplicated
+ * @num_fences: Number of entries in the @fences array
+ *
+ * Sorts the input array by context, then removes duplicate
+ * fences with the same context, keeping only the most recent one.
+ *
+ * The array is modified in-place and unreferenced duplicate fences are released
+ * via dma_fence_put(). The function returns the new number of fences after
+ * deduplication.
+ *
+ * Return: Number of unique fences remaining in the array.
+ */
+int dma_fence_dedup_array(struct dma_fence **fences, int num_fences)
+{
+	int i, j;
+
+	sort(fences, num_fences, sizeof(*fences), fence_cmp, NULL);
+
+	/*
+	 * Only keep the most recent fence for each context.
+	 */
+	j = 0;
+	for (i = 1; i < num_fences; i++) {
+		if (fences[i]->context == fences[j]->context)
+			dma_fence_put(fences[i]);
+		else
+			fences[++j] = fences[i];
+	}
+
+	return ++j;
+}
+EXPORT_SYMBOL_GPL(dma_fence_dedup_array);
+
 /* Implementation for the dma_fence_merge() marco, don't use directly */
 struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 					   struct dma_fence **fences,
 					   struct dma_fence_unwrap *iter)
 {
+	struct dma_fence *tmp, *unsignaled = NULL, **array;
 	struct dma_fence_array *result;
-	struct dma_fence *tmp, **array;
 	ktime_t timestamp;
-	int i, j, count;
+	int i, count;
 
 	count = 0;
 	timestamp = ns_to_ktime(0);
 	for (i = 0; i < num_fences; ++i) {
 		dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) {
 			if (!dma_fence_is_signaled(tmp)) {
+				dma_fence_put(unsignaled);
+				unsignaled = dma_fence_get(tmp);
 				++count;
 			} else {
 				ktime_t t = dma_fence_timestamp(tmp);
@@ -107,9 +144,16 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 	/*
 	 * If we couldn't find a pending fence just return a private signaled
 	 * fence with the timestamp of the last signaled one.
+	 *
+	 * Or if there was a single unsignaled fence left we can return it
+	 * directly and early since that is a major path on many workloads.
 	 */
 	if (count == 0)
 		return dma_fence_allocate_private_stub(timestamp);
+	else if (count == 1)
+		return unsignaled;
+
+	dma_fence_put(unsignaled);
 
 	array = kmalloc_array(count, sizeof(*array), GFP_KERNEL);
 	if (!array)
@@ -132,19 +176,7 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 	if (count == 0 || count == 1)
 		goto return_fastpath;
 
-	sort(array, count, sizeof(*array), fence_cmp, NULL);
-
-	/*
-	 * Only keep the most recent fence for each context.
-	 */
-	j = 0;
-	for (i = 1; i < count; i++) {
-		if (array[i]->context == array[j]->context)
-			dma_fence_put(array[i]);
-		else
-			array[++j] = array[i];
-	}
-	count = ++j;
+	count = dma_fence_dedup_array(array, count);
 
 	if (count > 1) {
 		result = dma_fence_array_create(count, array,
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 5f8d010516f0..bea3e9858aca 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 	count++;
 
 	dma_resv_list_set(fobj, i, fence, usage);
-	/* pointer update must be visible before we extend the num_fences */
-	smp_store_mb(fobj->num_fences, count);
+	/* fence update must be visible before we extend the num_fences */
+	smp_wmb();
+	fobj->num_fences = count;
 }
 EXPORT_SYMBOL(dma_resv_add_fence);
 
@@ -684,11 +685,13 @@ long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 	dma_resv_iter_begin(&cursor, obj, usage);
 	dma_resv_for_each_fence_unlocked(&cursor, fence) {
 
-		ret = dma_fence_wait_timeout(fence, intr, ret);
-		if (ret <= 0) {
-			dma_resv_iter_end(&cursor);
-			return ret;
-		}
+		ret = dma_fence_wait_timeout(fence, intr, timeout);
+		if (ret <= 0)
+			break;
+
+		/* Even for zero timeout the return value is 1 */
+		if (timeout)
+			timeout = ret;
 	}
 	dma_resv_iter_end(&cursor);
 
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index 26d5dc89ea16..82b1b714300d 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -21,8 +21,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
-static struct dma_heap *sys_heap;
-
 struct system_heap_buffer {
 	struct dma_heap *heap;
 	struct list_head attachments;
@@ -424,6 +422,7 @@ static const struct dma_heap_ops system_heap_ops = {
 static int __init system_heap_create(void)
 {
 	struct dma_heap_export_info exp_info;
+	struct dma_heap *sys_heap;
 
 	exp_info.name = "system";
 	exp_info.ops = &system_heap_ops;
diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c
index f0cee984b6c7..a3be888ae2e8 100644
--- a/drivers/dma-buf/st-dma-fence-unwrap.c
+++ b/drivers/dma-buf/st-dma-fence-unwrap.c
@@ -28,7 +28,7 @@ static const struct dma_fence_ops mock_ops = {
 	.get_timeline_name = mock_name,
 };
 
-static struct dma_fence *mock_fence(void)
+static struct dma_fence *__mock_fence(u64 context, u64 seqno)
 {
 	struct mock_fence *f;
 
@@ -37,12 +37,16 @@ static struct dma_fence *mock_fence(void)
 		return NULL;
 
 	spin_lock_init(&f->lock);
-	dma_fence_init(&f->base, &mock_ops, &f->lock,
-		       dma_fence_context_alloc(1), 1);
+	dma_fence_init(&f->base, &mock_ops, &f->lock, context, seqno);
 
 	return &f->base;
 }
 
+static struct dma_fence *mock_fence(void)
+{
+	return __mock_fence(dma_fence_context_alloc(1), 1);
+}
+
 static struct dma_fence *mock_array(unsigned int num_fences, ...)
 {
 	struct dma_fence_array *array;
@@ -304,6 +308,177 @@ error_put_f1:
 	return err;
 }
 
+static int unwrap_merge_duplicate(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+
+	f1 = mock_fence();
+	if (!f1)
+		return -ENOMEM;
+
+	dma_fence_enable_sw_signaling(f1);
+
+	f2 = dma_fence_unwrap_merge(f1, f1);
+	if (!f2) {
+		err = -ENOMEM;
+		goto error_put_f1;
+	}
+
+	dma_fence_unwrap_for_each(fence, &iter, f2) {
+		if (fence == f1) {
+			dma_fence_put(f1);
+			f1 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_put(f2);
+error_put_f1:
+	dma_fence_put(f1);
+	return err;
+}
+
+static int unwrap_merge_seqno(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *f3, *f4;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+	u64 ctx[2];
+
+	ctx[0] = dma_fence_context_alloc(1);
+	ctx[1] = dma_fence_context_alloc(1);
+
+	f1 = __mock_fence(ctx[1], 1);
+	if (!f1)
+		return -ENOMEM;
+
+	dma_fence_enable_sw_signaling(f1);
+
+	f2 = __mock_fence(ctx[1], 2);
+	if (!f2) {
+		err = -ENOMEM;
+		goto error_put_f1;
+	}
+
+	dma_fence_enable_sw_signaling(f2);
+
+	f3 = __mock_fence(ctx[0], 1);
+	if (!f3) {
+		err = -ENOMEM;
+		goto error_put_f2;
+	}
+
+	dma_fence_enable_sw_signaling(f3);
+
+	f4 = dma_fence_unwrap_merge(f1, f2, f3);
+	if (!f4) {
+		err = -ENOMEM;
+		goto error_put_f3;
+	}
+
+	dma_fence_unwrap_for_each(fence, &iter, f4) {
+		if (fence == f3 && f2) {
+			dma_fence_put(f3);
+			f3 = NULL;
+		} else if (fence == f2 && !f3) {
+			dma_fence_put(f2);
+			f2 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f2 || f3) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_put(f4);
+error_put_f3:
+	dma_fence_put(f3);
+error_put_f2:
+	dma_fence_put(f2);
+error_put_f1:
+	dma_fence_put(f1);
+	return err;
+}
+
+static int unwrap_merge_order(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *a1, *a2, *c1, *c2;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+
+	f1 = mock_fence();
+	if (!f1)
+		return -ENOMEM;
+
+	dma_fence_enable_sw_signaling(f1);
+
+	f2 = mock_fence();
+	if (!f2) {
+		dma_fence_put(f1);
+		return -ENOMEM;
+	}
+
+	dma_fence_enable_sw_signaling(f2);
+
+	a1 = mock_array(2, f1, f2);
+	if (!a1)
+		return -ENOMEM;
+
+	c1 = mock_chain(NULL, dma_fence_get(f1));
+	if (!c1)
+		goto error_put_a1;
+
+	c2 = mock_chain(c1, dma_fence_get(f2));
+	if (!c2)
+		goto error_put_a1;
+
+	/*
+	 * The fences in the chain are the same as in a1 but in oposite order,
+	 * the dma_fence_merge() function should be able to handle that.
+	 */
+	a2 = dma_fence_unwrap_merge(a1, c2);
+
+	dma_fence_unwrap_for_each(fence, &iter, a2) {
+		if (fence == f1) {
+			f1 = NULL;
+			if (!f2)
+				pr_err("Unexpected order!\n");
+		} else if (fence == f2) {
+			f2 = NULL;
+			if (f1)
+				pr_err("Unexpected order!\n");
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1 || f2) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_put(a2);
+	return err;
+
+error_put_a1:
+	dma_fence_put(a1);
+	return -ENOMEM;
+}
+
 static int unwrap_merge_complex(void *arg)
 {
 	struct dma_fence *fence, *f1, *f2, *f3, *f4, *f5;
@@ -327,7 +502,7 @@ static int unwrap_merge_complex(void *arg)
 		goto error_put_f2;
 
 	/* The resulting array has the fences in reverse */
-	f4 = dma_fence_unwrap_merge(f2, f1);
+	f4 = mock_array(2, dma_fence_get(f2), dma_fence_get(f1));
 	if (!f4)
 		goto error_put_f3;
 
@@ -367,6 +542,87 @@ error_put_f1:
 	return err;
 }
 
+static int unwrap_merge_complex_seqno(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *f3, *f4, *f5, *f6, *f7;
+	struct dma_fence_unwrap iter;
+	int err = -ENOMEM;
+	u64 ctx[2];
+
+	ctx[0] = dma_fence_context_alloc(1);
+	ctx[1] = dma_fence_context_alloc(1);
+
+	f1 = __mock_fence(ctx[0], 2);
+	if (!f1)
+		return -ENOMEM;
+
+	dma_fence_enable_sw_signaling(f1);
+
+	f2 = __mock_fence(ctx[1], 1);
+	if (!f2)
+		goto error_put_f1;
+
+	dma_fence_enable_sw_signaling(f2);
+
+	f3 = __mock_fence(ctx[0], 1);
+	if (!f3)
+		goto error_put_f2;
+
+	dma_fence_enable_sw_signaling(f3);
+
+	f4 = __mock_fence(ctx[1], 2);
+	if (!f4)
+		goto error_put_f3;
+
+	dma_fence_enable_sw_signaling(f4);
+
+	f5 = mock_array(2, dma_fence_get(f1), dma_fence_get(f2));
+	if (!f5)
+		goto error_put_f4;
+
+	f6 = mock_array(2, dma_fence_get(f3), dma_fence_get(f4));
+	if (!f6)
+		goto error_put_f5;
+
+	f7 = dma_fence_unwrap_merge(f5, f6);
+	if (!f7)
+		goto error_put_f6;
+
+	err = 0;
+	dma_fence_unwrap_for_each(fence, &iter, f7) {
+		if (fence == f1 && f4) {
+			dma_fence_put(f1);
+			f1 = NULL;
+		} else if (fence == f4 && !f1) {
+			dma_fence_put(f4);
+			f4 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1 || f4) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_put(f7);
+error_put_f6:
+	dma_fence_put(f6);
+error_put_f5:
+	dma_fence_put(f5);
+error_put_f4:
+	dma_fence_put(f4);
+error_put_f3:
+	dma_fence_put(f3);
+error_put_f2:
+	dma_fence_put(f2);
+error_put_f1:
+	dma_fence_put(f1);
+	return err;
+}
+
 int dma_fence_unwrap(void)
 {
 	static const struct subtest tests[] = {
@@ -375,7 +631,11 @@ int dma_fence_unwrap(void)
 		SUBTEST(unwrap_chain),
 		SUBTEST(unwrap_chain_array),
 		SUBTEST(unwrap_merge),
+		SUBTEST(unwrap_merge_duplicate),
+		SUBTEST(unwrap_merge_seqno),
+		SUBTEST(unwrap_merge_order),
 		SUBTEST(unwrap_merge_complex),
+		SUBTEST(unwrap_merge_complex_seqno),
 	};
 
 	return subtests(tests, NULL);
diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c
index cf2ce3744ce6..27a36045410b 100644
--- a/drivers/dma-buf/st-dma-fence.c
+++ b/drivers/dma-buf/st-dma-fence.c
@@ -375,7 +375,7 @@ struct wait_timer {
 
 static void wait_timer(struct timer_list *timer)
 {
-	struct wait_timer *wt = from_timer(wt, timer, timer);
+	struct wait_timer *wt = timer_container_of(wt, timer, timer);
 
 	dma_fence_signal(wt->f);
 }
@@ -412,8 +412,8 @@ static int test_wait_timeout(void *arg)
 
 	err = 0;
 err_free:
-	del_timer_sync(&wt.timer);
-	destroy_timer_on_stack(&wt.timer);
+	timer_delete_sync(&wt.timer);
+	timer_destroy_on_stack(&wt.timer);
 	dma_fence_signal(wt.f);
 	dma_fence_put(wt.f);
 	return err;
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index f5905d67dedb..4f27ee93a00c 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -173,20 +173,6 @@ static bool timeline_fence_signaled(struct dma_fence *fence)
 	return !__dma_fence_is_later(fence->seqno, parent->value, fence->ops);
 }
 
-static void timeline_fence_value_str(struct dma_fence *fence,
-				    char *str, int size)
-{
-	snprintf(str, size, "%lld", fence->seqno);
-}
-
-static void timeline_fence_timeline_value_str(struct dma_fence *fence,
-					     char *str, int size)
-{
-	struct sync_timeline *parent = dma_fence_parent(fence);
-
-	snprintf(str, size, "%d", parent->value);
-}
-
 static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
 {
 	struct sync_pt *pt = dma_fence_to_sync_pt(fence);
@@ -208,8 +194,6 @@ static const struct dma_fence_ops timeline_fence_ops = {
 	.get_timeline_name = timeline_fence_get_timeline_name,
 	.signaled = timeline_fence_signaled,
 	.release = timeline_fence_release,
-	.fence_value_str = timeline_fence_value_str,
-	.timeline_value_str = timeline_fence_timeline_value_str,
 	.set_deadline = timeline_fence_set_deadline,
 };
 
@@ -438,15 +422,17 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EINVAL;
 
 	pt = dma_fence_to_sync_pt(fence);
-	if (!pt)
-		return -EINVAL;
+	if (!pt) {
+		ret = -EINVAL;
+		goto put_fence;
+	}
 
 	spin_lock_irqsave(fence->lock, flags);
-	if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
-		data.deadline_ns = ktime_to_ns(pt->deadline);
-	} else {
+	if (!test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
 		ret = -ENOENT;
+		goto unlock;
 	}
+	data.deadline_ns = ktime_to_ns(pt->deadline);
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	dma_fence_put(fence);
@@ -458,6 +444,13 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EFAULT;
 
 	return 0;
+
+unlock:
+	spin_unlock_irqrestore(fence->lock, flags);
+put_fence:
+	dma_fence_put(fence);
+
+	return ret;
 }
 
 static long sw_sync_ioctl(struct file *file, unsigned int cmd,
diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c
index 237bce21d1e7..67cd69551e42 100644
--- a/drivers/dma-buf/sync_debug.c
+++ b/drivers/dma-buf/sync_debug.c
@@ -12,8 +12,6 @@ static struct dentry *dbgfs;
 
 static LIST_HEAD(sync_timeline_list_head);
 static DEFINE_SPINLOCK(sync_timeline_list_lock);
-static LIST_HEAD(sync_file_list_head);
-static DEFINE_SPINLOCK(sync_file_list_lock);
 
 void sync_timeline_debug_add(struct sync_timeline *obj)
 {
@@ -33,24 +31,6 @@ void sync_timeline_debug_remove(struct sync_timeline *obj)
 	spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
 }
 
-void sync_file_debug_add(struct sync_file *sync_file)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&sync_file_list_lock, flags);
-	list_add_tail(&sync_file->sync_file_list, &sync_file_list_head);
-	spin_unlock_irqrestore(&sync_file_list_lock, flags);
-}
-
-void sync_file_debug_remove(struct sync_file *sync_file)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&sync_file_list_lock, flags);
-	list_del(&sync_file->sync_file_list);
-	spin_unlock_irqrestore(&sync_file_list_lock, flags);
-}
-
 static const char *sync_status_str(int status)
 {
 	if (status < 0)
@@ -82,25 +62,8 @@ static void sync_print_fence(struct seq_file *s,
 		seq_printf(s, "@%lld.%09ld", (s64)ts64.tv_sec, ts64.tv_nsec);
 	}
 
-	if (fence->ops->timeline_value_str &&
-		fence->ops->fence_value_str) {
-		char value[64];
-		bool success;
-
-		fence->ops->fence_value_str(fence, value, sizeof(value));
-		success = strlen(value);
-
-		if (success) {
-			seq_printf(s, ": %s", value);
-
-			fence->ops->timeline_value_str(fence, value,
-						       sizeof(value));
-
-			if (strlen(value))
-				seq_printf(s, " / %s", value);
-		}
-	}
-
+	seq_printf(s, ": %lld", fence->seqno);
+	seq_printf(s, " / %d", parent->value);
 	seq_putc(s, '\n');
 }
 
@@ -118,26 +81,6 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj)
 	spin_unlock(&obj->lock);
 }
 
-static void sync_print_sync_file(struct seq_file *s,
-				  struct sync_file *sync_file)
-{
-	char buf[128];
-	int i;
-
-	seq_printf(s, "[%p] %s: %s\n", sync_file,
-		   sync_file_get_name(sync_file, buf, sizeof(buf)),
-		   sync_status_str(dma_fence_get_status(sync_file->fence)));
-
-	if (dma_fence_is_array(sync_file->fence)) {
-		struct dma_fence_array *array = to_dma_fence_array(sync_file->fence);
-
-		for (i = 0; i < array->num_fences; ++i)
-			sync_print_fence(s, array->fences[i], true);
-	} else {
-		sync_print_fence(s, sync_file->fence, true);
-	}
-}
-
 static int sync_info_debugfs_show(struct seq_file *s, void *unused)
 {
 	struct list_head *pos;
@@ -157,15 +100,6 @@ static int sync_info_debugfs_show(struct seq_file *s, void *unused)
 
 	seq_puts(s, "fences:\n--------------\n");
 
-	spin_lock_irq(&sync_file_list_lock);
-	list_for_each(pos, &sync_file_list_head) {
-		struct sync_file *sync_file =
-			container_of(pos, struct sync_file, sync_file_list);
-
-		sync_print_sync_file(s, sync_file);
-		seq_putc(s, '\n');
-	}
-	spin_unlock_irq(&sync_file_list_lock);
 	return 0;
 }
 
diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h
index a1bdd62efccd..02af347293d0 100644
--- a/drivers/dma-buf/sync_debug.h
+++ b/drivers/dma-buf/sync_debug.h
@@ -68,7 +68,5 @@ extern const struct file_operations sw_sync_debugfs_fops;
 
 void sync_timeline_debug_add(struct sync_timeline *obj);
 void sync_timeline_debug_remove(struct sync_timeline *obj);
-void sync_file_debug_add(struct sync_file *fence);
-void sync_file_debug_remove(struct sync_file *fence);
 
 #endif /* _LINUX_SYNC_H */
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index cc7398cc17d6..40399c26e6be 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -109,29 +109,22 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
 {
 	struct udmabuf *ubuf = buf->priv;
-	unsigned long *pfns;
+	struct page **pages;
 	void *vaddr;
 	pgoff_t pg;
 
 	dma_resv_assert_held(buf->resv);
 
-	/**
-	 * HVO may free tail pages, so just use pfn to map each folio
-	 * into vmalloc area.
-	 */
-	pfns = kvmalloc_array(ubuf->pagecount, sizeof(*pfns), GFP_KERNEL);
-	if (!pfns)
+	pages = kvmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
 		return -ENOMEM;
 
-	for (pg = 0; pg < ubuf->pagecount; pg++) {
-		unsigned long pfn = folio_pfn(ubuf->folios[pg]);
-
-		pfn += ubuf->offsets[pg] >> PAGE_SHIFT;
-		pfns[pg] = pfn;
-	}
+	for (pg = 0; pg < ubuf->pagecount; pg++)
+		pages[pg] = folio_page(ubuf->folios[pg],
+				       ubuf->offsets[pg] >> PAGE_SHIFT);
 
-	vaddr = vmap_pfn(pfns, ubuf->pagecount, PAGE_KERNEL);
-	kvfree(pfns);
+	vaddr = vm_map_ram(pages, ubuf->pagecount, -1);
+	kvfree(pages);
 	if (!vaddr)
 		return -EINVAL;
 
@@ -264,8 +257,7 @@ static int begin_cpu_udmabuf(struct dma_buf *buf,
 			ubuf->sg = NULL;
 		}
 	} else {
-		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
-				    direction);
+		dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction);
 	}
 
 	return ret;
@@ -280,12 +272,11 @@ static int end_cpu_udmabuf(struct dma_buf *buf,
 	if (!ubuf->sg)
 		return -EINVAL;
 
-	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	dma_sync_sgtable_for_device(dev, ubuf->sg, direction);
 	return 0;
 }
 
 static const struct dma_buf_ops udmabuf_ops = {
-	.cache_sgt_mapping = true,
 	.map_dma_buf	   = map_udmabuf,
 	.unmap_dma_buf	   = unmap_udmabuf,
 	.release	   = release_udmabuf,
@@ -393,7 +384,7 @@ static long udmabuf_create(struct miscdevice *device,
 	if (!ubuf)
 		return -ENOMEM;
 
-	pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
+	pglimit = ((u64)size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
 	for (i = 0; i < head->count; i++) {
 		pgoff_t subpgcnt;