1 files changed, 94 insertions, 66 deletions

diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c
index 628af51c81af..a495d8a6c2e3 100644
--- a/drivers/dma-buf/dma-fence-unwrap.c
+++ b/drivers/dma-buf/dma-fence-unwrap.c
@@ -12,6 +12,7 @@
 #include <linux/dma-fence-chain.h>
 #include <linux/dma-fence-unwrap.h>
 #include <linux/slab.h>
+#include <linux/sort.h>
 
 /* Internal helper to start new array iteration, don't use directly */
 static struct dma_fence *
@@ -59,22 +60,77 @@ struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor)
 }
 EXPORT_SYMBOL_GPL(dma_fence_unwrap_next);
 
+
+static int fence_cmp(const void *_a, const void *_b)
+{
+	struct dma_fence *a = *(struct dma_fence **)_a;
+	struct dma_fence *b = *(struct dma_fence **)_b;
+
+	if (a->context < b->context)
+		return -1;
+	else if (a->context > b->context)
+		return 1;
+
+	if (dma_fence_is_later(b, a))
+		return 1;
+	else if (dma_fence_is_later(a, b))
+		return -1;
+
+	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;
-	unsigned int i;
-	size_t 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);
@@ -88,86 +144,58 @@ 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)
 		return NULL;
 
-	/*
-	 * This trashes the input fence array and uses it as position for the
-	 * following merge loop. This works because the dma_fence_merge()
-	 * wrapper macro is creating this temporary array on the stack together
-	 * with the iterators.
-	 */
-	for (i = 0; i < num_fences; ++i)
-		fences[i] = dma_fence_unwrap_first(fences[i], &iter[i]);
-
 	count = 0;
-	do {
-		unsigned int sel;
-
-restart:
-		tmp = NULL;
-		for (i = 0; i < num_fences; ++i) {
-			struct dma_fence *next;
-
-			while (fences[i] && dma_fence_is_signaled(fences[i]))
-				fences[i] = dma_fence_unwrap_next(&iter[i]);
-
-			next = fences[i];
-			if (!next)
-				continue;
-
-			/*
-			 * We can't guarantee that inpute fences are ordered by
-			 * context, but it is still quite likely when this
-			 * function is used multiple times. So attempt to order
-			 * the fences by context as we pass over them and merge
-			 * fences with the same context.
-			 */
-			if (!tmp || tmp->context > next->context) {
-				tmp = next;
-				sel = i;
-
-			} else if (tmp->context < next->context) {
-				continue;
-
-			} else if (dma_fence_is_later(tmp, next)) {
-				fences[i] = dma_fence_unwrap_next(&iter[i]);
-				goto restart;
+	for (i = 0; i < num_fences; ++i) {
+		dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) {
+			if (!dma_fence_is_signaled(tmp)) {
+				array[count++] = dma_fence_get(tmp);
 			} else {
-				fences[sel] = dma_fence_unwrap_next(&iter[sel]);
-				goto restart;
+				ktime_t t = dma_fence_timestamp(tmp);
+
+				if (ktime_after(t, timestamp))
+					timestamp = t;
 			}
 		}
+	}
 
-		if (tmp) {
-			array[count++] = dma_fence_get(tmp);
-			fences[sel] = dma_fence_unwrap_next(&iter[sel]);
-		}
-	} while (tmp);
+	if (count == 0 || count == 1)
+		goto return_fastpath;
 
-	if (count == 0) {
-		tmp = dma_fence_allocate_private_stub(ktime_get());
-		goto return_tmp;
-	}
+	count = dma_fence_dedup_array(array, count);
 
-	if (count == 1) {
-		tmp = array[0];
-		goto return_tmp;
+	if (count > 1) {
+		result = dma_fence_array_create(count, array,
+						dma_fence_context_alloc(1),
+						1, false);
+		if (!result) {
+			for (i = 0; i < count; i++)
+				dma_fence_put(array[i]);
+			tmp = NULL;
+			goto return_tmp;
+		}
+		return &result->base;
 	}
 
-	result = dma_fence_array_create(count, array,
-					dma_fence_context_alloc(1),
-					1, false);
-	if (!result) {
-		tmp = NULL;
-		goto return_tmp;
-	}
-	return &result->base;
+return_fastpath:
+	if (count == 0)
+		tmp = dma_fence_allocate_private_stub(timestamp);
+	else
+		tmp = array[0];
 
 return_tmp:
 	kfree(array);