Merge drm-misc/drm-misc-next-fixes into drm-misc-fixes

There were a few patches left in drm-misc-next-fixes, let's bring them
into drm-misc-fixes.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

10 files changed, 540 insertions, 117 deletions

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 55006678394a..36a76cbe9095 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -185,6 +185,12 @@ DMA Fence Chain
 .. kernel-doc:: include/linux/dma-fence-chain.h
    :internal:
 
+DMA Fence unwrap
+~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/dma-fence-unwrap.h
+   :internal:
+
 DMA Fence uABI/Sync File
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 511805dbeb75..4c9eb53ba3f8 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -12,6 +12,7 @@ dmabuf_selftests-y := \
 	selftest.o \
 	st-dma-fence.o \
 	st-dma-fence-chain.o \
+	st-dma-fence-unwrap.o \
 	st-dma-resv.o
 
 obj-$(CONFIG_DMABUF_SELFTESTS)	+= dmabuf_selftests.o
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index cb1bacb5a42b..5c8a7084577b 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
 	struct dma_fence_array *array;
 	size_t size = sizeof(*array);
 
+	WARN_ON(!num_fences || !fences);
+
 	/* Allocate the callback structures behind the array. */
 	size += num_fences * sizeof(struct dma_fence_array_cb);
 	array = kzalloc(size, GFP_KERNEL);
@@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context)
 	return true;
 }
 EXPORT_SYMBOL(dma_fence_match_context);
+
+struct dma_fence *dma_fence_array_first(struct dma_fence *head)
+{
+	struct dma_fence_array *array;
+
+	if (!head)
+		return NULL;
+
+	array = to_dma_fence_array(head);
+	if (!array)
+		return head;
+
+	if (!array->num_fences)
+		return NULL;
+
+	return array->fences[0];
+}
+EXPORT_SYMBOL(dma_fence_array_first);
+
+struct dma_fence *dma_fence_array_next(struct dma_fence *head,
+				       unsigned int index)
+{
+	struct dma_fence_array *array = to_dma_fence_array(head);
+
+	if (!array || index >= array->num_fences)
+		return NULL;
+
+	return array->fences[index];
+}
+EXPORT_SYMBOL(dma_fence_array_next);
diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h
index 97d73aaa31da..851965867d9c 100644
--- a/drivers/dma-buf/selftests.h
+++ b/drivers/dma-buf/selftests.h
@@ -12,4 +12,5 @@
 selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */
 selftest(dma_fence, dma_fence)
 selftest(dma_fence_chain, dma_fence_chain)
+selftest(dma_fence_unwrap, dma_fence_unwrap)
 selftest(dma_resv, dma_resv)
diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c
new file mode 100644
index 000000000000..039f016b57be
--- /dev/null
+++ b/drivers/dma-buf/st-dma-fence-unwrap.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/dma-fence-unwrap.h>
+#if 0
+#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>
+#endif
+
+#include "selftest.h"
+
+#define CHAIN_SZ (4 << 10)
+
+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 const struct dma_fence_ops mock_ops = {
+	.get_driver_name = mock_name,
+	.get_timeline_name = mock_name,
+};
+
+static struct dma_fence *mock_fence(void)
+{
+	struct mock_fence *f;
+
+	f = kmalloc(sizeof(*f), 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 struct dma_fence *mock_array(unsigned int num_fences, ...)
+{
+	struct dma_fence_array *array;
+	struct dma_fence **fences;
+	va_list valist;
+	int i;
+
+	fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL);
+	if (!fences)
+		return NULL;
+
+	va_start(valist, num_fences);
+	for (i = 0; i < num_fences; ++i)
+		fences[i] = va_arg(valist, typeof(*fences));
+	va_end(valist);
+
+	array = dma_fence_array_create(num_fences, fences,
+				       dma_fence_context_alloc(1),
+				       1, false);
+	if (!array)
+		goto cleanup;
+	return &array->base;
+
+cleanup:
+	for (i = 0; i < num_fences; ++i)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+	return NULL;
+}
+
+static struct dma_fence *mock_chain(struct dma_fence *prev,
+				    struct dma_fence *fence)
+{
+	struct dma_fence_chain *f;
+
+	f = dma_fence_chain_alloc();
+	if (!f) {
+		dma_fence_put(prev);
+		dma_fence_put(fence);
+		return NULL;
+	}
+
+	dma_fence_chain_init(f, prev, fence, 1);
+	return &f->base;
+}
+
+static int sanitycheck(void *arg)
+{
+	struct dma_fence *f, *chain, *array;
+	int err = 0;
+
+	f = mock_fence();
+	if (!f)
+		return -ENOMEM;
+
+	array = mock_array(1, f);
+	if (!array)
+		return -ENOMEM;
+
+	chain = mock_chain(NULL, array);
+	if (!chain)
+		return -ENOMEM;
+
+	dma_fence_signal(f);
+	dma_fence_put(chain);
+	return err;
+}
+
+static int unwrap_array(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *array;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+
+	f1 = mock_fence();
+	if (!f1)
+		return -ENOMEM;
+
+	f2 = mock_fence();
+	if (!f2) {
+		dma_fence_put(f1);
+		return -ENOMEM;
+	}
+
+	array = mock_array(2, f1, f2);
+	if (!array)
+		return -ENOMEM;
+
+	dma_fence_unwrap_for_each(fence, &iter, array) {
+		if (fence == f1) {
+			f1 = NULL;
+		} else if (fence == f2) {
+			f2 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1 || f2) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_signal(f1);
+	dma_fence_signal(f2);
+	dma_fence_put(array);
+	return 0;
+}
+
+static int unwrap_chain(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *chain;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+
+	f1 = mock_fence();
+	if (!f1)
+		return -ENOMEM;
+
+	f2 = mock_fence();
+	if (!f2) {
+		dma_fence_put(f1);
+		return -ENOMEM;
+	}
+
+	chain = mock_chain(f1, f2);
+	if (!chain)
+		return -ENOMEM;
+
+	dma_fence_unwrap_for_each(fence, &iter, chain) {
+		if (fence == f1) {
+			f1 = NULL;
+		} else if (fence == f2) {
+			f2 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1 || f2) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_signal(f1);
+	dma_fence_signal(f2);
+	dma_fence_put(chain);
+	return 0;
+}
+
+static int unwrap_chain_array(void *arg)
+{
+	struct dma_fence *fence, *f1, *f2, *array, *chain;
+	struct dma_fence_unwrap iter;
+	int err = 0;
+
+	f1 = mock_fence();
+	if (!f1)
+		return -ENOMEM;
+
+	f2 = mock_fence();
+	if (!f2) {
+		dma_fence_put(f1);
+		return -ENOMEM;
+	}
+
+	array = mock_array(2, f1, f2);
+	if (!array)
+		return -ENOMEM;
+
+	chain = mock_chain(NULL, array);
+	if (!chain)
+		return -ENOMEM;
+
+	dma_fence_unwrap_for_each(fence, &iter, chain) {
+		if (fence == f1) {
+			f1 = NULL;
+		} else if (fence == f2) {
+			f2 = NULL;
+		} else {
+			pr_err("Unexpected fence!\n");
+			err = -EINVAL;
+		}
+	}
+
+	if (f1 || f2) {
+		pr_err("Not all fences seen!\n");
+		err = -EINVAL;
+	}
+
+	dma_fence_signal(f1);
+	dma_fence_signal(f2);
+	dma_fence_put(chain);
+	return 0;
+}
+
+int dma_fence_unwrap(void)
+{
+	static const struct subtest tests[] = {
+		SUBTEST(sanitycheck),
+		SUBTEST(unwrap_array),
+		SUBTEST(unwrap_chain),
+		SUBTEST(unwrap_chain_array),
+	};
+
+	return subtests(tests, NULL);
+}
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 394e6e1e9686..514d213261df 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2012 Google, Inc.
  */
 
+#include <linux/dma-fence-unwrap.h>
 #include <linux/export.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file,
 	return 0;
 }
 
-static struct dma_fence **get_fences(struct sync_file *sync_file,
-				     int *num_fences)
-{
-	if (dma_fence_is_array(sync_file->fence)) {
-		struct dma_fence_array *array = to_dma_fence_array(sync_file->fence);
-
-		*num_fences = array->num_fences;
-		return array->fences;
-	}
-
-	*num_fences = 1;
-	return &sync_file->fence;
-}
-
 static void add_fence(struct dma_fence **fences,
 		      int *i, struct dma_fence *fence)
 {
@@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences,
 static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
 					 struct sync_file *b)
 {
+	struct dma_fence *a_fence, *b_fence, **fences;
+	struct dma_fence_unwrap a_iter, b_iter;
+	unsigned int index, num_fences;
 	struct sync_file *sync_file;
-	struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences;
-	int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences;
 
 	sync_file = sync_file_alloc();
 	if (!sync_file)
 		return NULL;
 
-	a_fences = get_fences(a, &a_num_fences);
-	b_fences = get_fences(b, &b_num_fences);
-	if (a_num_fences > INT_MAX - b_num_fences)
-		goto err;
+	num_fences = 0;
+	dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence)
+		++num_fences;
+	dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence)
+		++num_fences;
 
-	num_fences = a_num_fences + b_num_fences;
+	if (num_fences > INT_MAX)
+		goto err_free_sync_file;
 
 	fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL);
 	if (!fences)
-		goto err;
+		goto err_free_sync_file;
 
 	/*
-	 * Assume sync_file a and b are both ordered and have no
-	 * duplicates with the same context.
+	 * We can't guarantee that fences in both a and b are ordered, but it is
+	 * still quite likely.
 	 *
-	 * If a sync_file can only be created with sync_file_merge
-	 * and sync_file_create, this is a reasonable assumption.
+	 * So attempt to order the fences as we pass over them and merge fences
+	 * with the same context.
 	 */
-	for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) {
-		struct dma_fence *pt_a = a_fences[i_a];
-		struct dma_fence *pt_b = b_fences[i_b];
 
-		if (pt_a->context < pt_b->context) {
-			add_fence(fences, &i, pt_a);
+	index = 0;
+	for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter),
+	     b_fence = dma_fence_unwrap_first(b->fence, &b_iter);
+	     a_fence || b_fence; ) {
+
+		if (!b_fence) {
+			add_fence(fences, &index, a_fence);
+			a_fence = dma_fence_unwrap_next(&a_iter);
+
+		} else if (!a_fence) {
+			add_fence(fences, &index, b_fence);
+			b_fence = dma_fence_unwrap_next(&b_iter);
+
+		} else if (a_fence->context < b_fence->context) {
+			add_fence(fences, &index, a_fence);
+			a_fence = dma_fence_unwrap_next(&a_iter);
 
-			i_a++;
-		} else if (pt_a->context > pt_b->context) {
-			add_fence(fences, &i, pt_b);
+		} else if (b_fence->context < a_fence->context) {
+			add_fence(fences, &index, b_fence);
+			b_fence = dma_fence_unwrap_next(&b_iter);
+
+		} else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno,
+						a_fence->ops)) {
+			add_fence(fences, &index, a_fence);
+			a_fence = dma_fence_unwrap_next(&a_iter);
+			b_fence = dma_fence_unwrap_next(&b_iter);
 
-			i_b++;
 		} else {
-			if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno,
-						 pt_a->ops))
-				add_fence(fences, &i, pt_a);
-			else
-				add_fence(fences, &i, pt_b);
-
-			i_a++;
-			i_b++;
+			add_fence(fences, &index, b_fence);
+			a_fence = dma_fence_unwrap_next(&a_iter);
+			b_fence = dma_fence_unwrap_next(&b_iter);
 		}
 	}
 
-	for (; i_a < a_num_fences; i_a++)
-		add_fence(fences, &i, a_fences[i_a]);
-
-	for (; i_b < b_num_fences; i_b++)
-		add_fence(fences, &i, b_fences[i_b]);
-
-	if (i == 0)
-		fences[i++] = dma_fence_get(a_fences[0]);
+	if (index == 0)
+		fences[index++] = dma_fence_get_stub();
 
-	if (num_fences > i) {
-		nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL);
-		if (!nfences)
-			goto err;
+	if (num_fences > index) {
+		struct dma_fence **tmp;
 
-		fences = nfences;
+		/* Keep going even when reducing the size failed */
+		tmp = krealloc_array(fences, index, sizeof(*fences),
+				     GFP_KERNEL);
+		if (tmp)
+			fences = tmp;
 	}
 
-	if (sync_file_set_fence(sync_file, fences, i) < 0)
-		goto err;
+	if (sync_file_set_fence(sync_file, fences, index) < 0)
+		goto err_put_fences;
 
 	strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name));
 	return sync_file;
 
-err:
-	while (i)
-		dma_fence_put(fences[--i]);
+err_put_fences:
+	while (index)
+		dma_fence_put(fences[--index]);
 	kfree(fences);
+
+err_free_sync_file:
 	fput(sync_file->file);
 	return NULL;
-
 }
 
 static int sync_file_release(struct inode *inode, struct file *file)
@@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence,
 static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
 				       unsigned long arg)
 {
-	struct sync_file_info info;
 	struct sync_fence_info *fence_info = NULL;
-	struct dma_fence **fences;
+	struct dma_fence_unwrap iter;
+	struct sync_file_info info;
+	unsigned int num_fences;
+	struct dma_fence *fence;
+	int ret;
 	__u32 size;
-	int num_fences, ret, i;
 
 	if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
 		return -EFAULT;
@@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
 	if (info.flags || info.pad)
 		return -EINVAL;
 
-	fences = get_fences(sync_file, &num_fences);
+	num_fences = 0;
+	dma_fence_unwrap_for_each(fence, &iter, sync_file->fence)
+		++num_fences;
 
 	/*
 	 * Passing num_fences = 0 means that userspace doesn't want to
@@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
 	if (!fence_info)
 		return -ENOMEM;
 
-	for (i = 0; i < num_fences; i++) {
-		int status = sync_fill_fence_info(fences[i], &fence_info[i]);
+	num_fences = 0;
+	dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) {
+		int status;
+
+		status = sync_fill_fence_info(fence, &fence_info[num_fences++]);
 		info.status = info.status <= 0 ? info.status : status;
 	}
 
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 026e4e29a0f3..f4df344509a8 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -214,6 +214,29 @@ int drm_of_encoder_active_endpoint(struct device_node *node,
 }
 EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint);
 
+static int find_panel_or_bridge(struct device_node *node,
+				struct drm_panel **panel,
+				struct drm_bridge **bridge)
+{
+	if (panel) {
+		*panel = of_drm_find_panel(node);
+		if (!IS_ERR(*panel))
+			return 0;
+
+		/* Clear the panel pointer in case of error. */
+		*panel = NULL;
+	}
+
+	/* No panel found yet, check for a bridge next. */
+	if (bridge) {
+		*bridge = of_drm_find_bridge(node);
+		if (*bridge)
+			return 0;
+	}
+
+	return -EPROBE_DEFER;
+}
+
 /**
  * drm_of_find_panel_or_bridge - return connected panel or bridge device
  * @np: device tree node containing encoder output ports
@@ -236,66 +259,44 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 				struct drm_panel **panel,
 				struct drm_bridge **bridge)
 {
-	int ret = -EPROBE_DEFER;
-	struct device_node *remote;
+	struct device_node *node;
+	int ret;
 
 	if (!panel && !bridge)
 		return -EINVAL;
+
 	if (panel)
 		*panel = NULL;
-
-	/**
-	 * Devices can also be child nodes when we also control that device
-	 * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device).
-	 *
-	 * Lookup for a child node of the given parent that isn't either port
-	 * or ports.
-	 */
-	for_each_available_child_of_node(np, remote) {
-		if (of_node_name_eq(remote, "port") ||
-		    of_node_name_eq(remote, "ports"))
-			continue;
-
-		goto of_find_panel_or_bridge;
+	if (bridge)
+		*bridge = NULL;
+
+	/* Check for a graph on the device node first. */
+	if (of_graph_is_present(np)) {
+		node = of_graph_get_remote_node(np, port, endpoint);
+		if (node) {
+			ret = find_panel_or_bridge(node, panel, bridge);
+			of_node_put(node);
+
+			if (!ret)
+				return 0;
+		}
 	}
 
-	/*
-	 * of_graph_get_remote_node() produces a noisy error message if port
-	 * node isn't found and the absence of the port is a legit case here,
-	 * so at first we silently check whether graph presents in the
-	 * device-tree node.
-	 */
-	if (!of_graph_is_present(np))
-		return -ENODEV;
-
-	remote = of_graph_get_remote_node(np, port, endpoint);
-
-of_find_panel_or_bridge:
-	if (!remote)
-		return -ENODEV;
+	/* Otherwise check for any child node other than port/ports. */
+	for_each_available_child_of_node(np, node) {
+		if (of_node_name_eq(node, "port") ||
+		    of_node_name_eq(node, "ports"))
+			continue;
 
-	if (panel) {
-		*panel = of_drm_find_panel(remote);
-		if (!IS_ERR(*panel))
-			ret = 0;
-		else
-			*panel = NULL;
-	}
-
-	/* No panel found yet, check for a bridge next. */
-	if (bridge) {
-		if (ret) {
-			*bridge = of_drm_find_bridge(remote);
-			if (*bridge)
-				ret = 0;
-		} else {
-			*bridge = NULL;
-		}
+		ret = find_panel_or_bridge(node, panel, bridge);
+		of_node_put(node);
 
+		/* Stop at the first found occurrence. */
+		if (!ret)
+			return 0;
 	}
 
-	of_node_put(remote);
-	return ret;
+	return -EPROBE_DEFER;
 }
 EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge);
 
diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h
index fec374f69e12..ec7f25def392 100644
--- a/include/linux/dma-fence-array.h
+++ b/include/linux/dma-fence-array.h
@@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence)
 	return container_of(fence, struct dma_fence_array, base);
 }
 
+/**
+ * dma_fence_array_for_each - iterate over all fences in array
+ * @fence: current fence
+ * @index: index into the array
+ * @head: potential dma_fence_array object
+ *
+ * Test if @array is a dma_fence_array object and if yes iterate over all fences
+ * in the array. If not just iterate over the fence in @array itself.
+ *
+ * For a deep dive iterator see dma_fence_unwrap_for_each().
+ */
+#define dma_fence_array_for_each(fence, index, head)			\
+	for (index = 0, fence = dma_fence_array_first(head); fence;	\
+	     ++(index), fence = dma_fence_array_next(head, index))
+
 struct dma_fence_array *dma_fence_array_create(int num_fences,
 					       struct dma_fence **fences,
 					       u64 context, unsigned seqno,
@@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
 
 bool dma_fence_match_context(struct dma_fence *fence, u64 context);
 
+struct dma_fence *dma_fence_array_first(struct dma_fence *head);
+struct dma_fence *dma_fence_array_next(struct dma_fence *head,
+				       unsigned int index);
+
 #endif /* __LINUX_DMA_FENCE_ARRAY_H */
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
index 10d51bcdf7b7..4bdf0b96da28 100644
--- a/include/linux/dma-fence-chain.h
+++ b/include/linux/dma-fence-chain.h
@@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain)
  *
  * Iterate over all fences in the chain. We keep a reference to the current
  * fence while inside the loop which must be dropped when breaking out.
+ *
+ * For a deep dive iterator see dma_fence_unwrap_for_each().
  */
 #define dma_fence_chain_for_each(iter, head)	\
 	for (iter = dma_fence_get(head); iter; \
diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h
new file mode 100644
index 000000000000..77e335a1bcac
--- /dev/null
+++ b/include/linux/dma-fence-unwrap.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ */
+
+#ifndef __LINUX_DMA_FENCE_UNWRAP_H
+#define __LINUX_DMA_FENCE_UNWRAP_H
+
+#include <linux/dma-fence-chain.h>
+#include <linux/dma-fence-array.h>
+
+/**
+ * struct dma_fence_unwrap - cursor into the container structure
+ *
+ * Should be used with dma_fence_unwrap_for_each() iterator macro.
+ */
+struct dma_fence_unwrap {
+	/**
+	 * @chain: potential dma_fence_chain, but can be other fence as well
+	 */
+	struct dma_fence *chain;
+	/**
+	 * @array: potential dma_fence_array, but can be other fence as well
+	 */
+	struct dma_fence *array;
+	/**
+	 * @index: last returned index if @array is really a dma_fence_array
+	 */
+	unsigned int index;
+};
+
+/* Internal helper to start new array iteration, don't use directly */
+static inline struct dma_fence *
+__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor)
+{
+	cursor->array = dma_fence_chain_contained(cursor->chain);
+	cursor->index = 0;
+	return dma_fence_array_first(cursor->array);
+}
+
+/**
+ * dma_fence_unwrap_first - return the first fence from fence containers
+ * @head: the entrypoint into the containers
+ * @cursor: current position inside the containers
+ *
+ * Unwraps potential dma_fence_chain/dma_fence_array containers and return the
+ * first fence.
+ */
+static inline struct dma_fence *
+dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor)
+{
+	cursor->chain = dma_fence_get(head);
+	return __dma_fence_unwrap_array(cursor);
+}
+
+/**
+ * dma_fence_unwrap_next - return the next fence from a fence containers
+ * @cursor: current position inside the containers
+ *
+ * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return
+ * the next fence from them.
+ */
+static inline struct dma_fence *
+dma_fence_unwrap_next(struct dma_fence_unwrap *cursor)
+{
+	struct dma_fence *tmp;
+
+	++cursor->index;
+	tmp = dma_fence_array_next(cursor->array, cursor->index);
+	if (tmp)
+		return tmp;
+
+	cursor->chain = dma_fence_chain_walk(cursor->chain);
+	return __dma_fence_unwrap_array(cursor);
+}
+
+/**
+ * dma_fence_unwrap_for_each - iterate over all fences in containers
+ * @fence: current fence
+ * @cursor: current position inside the containers
+ * @head: starting point for the iterator
+ *
+ * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all
+ * potential fences in them. If @head is just a normal fence only that one is
+ * returned.
+ */
+#define dma_fence_unwrap_for_each(fence, cursor, head)			\
+	for (fence = dma_fence_unwrap_first(head, cursor); fence;	\
+	     fence = dma_fence_unwrap_next(cursor))
+
+#endif