diff mbox series

[v3,7/7] drm/syncobj: Add a fast path to drm_syncobj_array_find

Message ID 20250328164621.59150-8-tvrtko.ursulin@igalia.com (mailing list archive)
State New
Headers show
Series few drm_syncobj optimisations | expand

Commit Message

Tvrtko Ursulin March 28, 2025, 4:46 p.m. UTC 
Running the Cyberpunk 2077 benchmark we can observe that the lookup helper
is relatively hot, but the 97% of the calls are for a single object. (~3%
for two points, and never more than three points. While a more trivial
workload like vkmark under Plasma is even more skewed to single point
lookups.)

Therefore lets add a fast path to bypass the kmalloc_array/kfree and use a
pre-allocated stack array for those cases.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
---
v2:
 * Added comments describing how the fast path arrays were sized.
 * Make container freeing criteria clearer by using a boolean.
---
 drivers/gpu/drm/drm_syncobj.c | 56 +++++++++++++++++++++++++++--------
 1 file changed, 44 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 34a6dc50ec31..d5b99bfea9a5 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1231,6 +1231,8 @@  EXPORT_SYMBOL(drm_timeout_abs_to_jiffies);
 static int drm_syncobj_array_find(struct drm_file *file_private,
 				  u32 __user *handles,
 				  uint32_t count,
+				  struct drm_syncobj **stack_syncobjs,
+				  u32 stack_count,
 				  struct drm_syncobj ***syncobjs_out)
 {
 	struct drm_syncobj **syncobjs;
@@ -1240,9 +1242,13 @@  static int drm_syncobj_array_find(struct drm_file *file_private,
 	if (!access_ok(handles, count * sizeof(*handles)))
 		return -EFAULT;
 
-	syncobjs = kmalloc_array(count, sizeof(*syncobjs), GFP_KERNEL);
-	if (!syncobjs)
-		return -ENOMEM;
+	if (count > stack_count) {
+		syncobjs = kmalloc_array(count, sizeof(*syncobjs), GFP_KERNEL);
+		if (!syncobjs)
+			return -ENOMEM;
+	} else {
+		syncobjs = stack_syncobjs;
+	}
 
 	for (i = 0; i < count; i++) {
 		u32 handle;
@@ -1264,25 +1270,31 @@  static int drm_syncobj_array_find(struct drm_file *file_private,
 err_put_syncobjs:
 	while (i-- > 0)
 		drm_syncobj_put(syncobjs[i]);
-	kfree(syncobjs);
+
+	if (syncobjs != stack_syncobjs)
+		kfree(syncobjs);
 
 	return ret;
 }
 
 static void drm_syncobj_array_free(struct drm_syncobj **syncobjs,
-				   uint32_t count)
+				   uint32_t count,
+				   bool free_container)
 {
 	uint32_t i;
 
 	for (i = 0; i < count; i++)
 		drm_syncobj_put(syncobjs[i]);
-	kfree(syncobjs);
+
+	if (free_container)
+		kfree(syncobjs);
 }
 
 int
 drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_wait *args = data;
 	ktime_t deadline, *pdeadline = NULL;
 	u32 count = args->count_handles;
@@ -1308,6 +1320,8 @@  drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     count,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1326,7 +1340,7 @@  drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 						 &first,
 						 pdeadline);
 
-	drm_syncobj_array_free(syncobjs, count);
+	drm_syncobj_array_free(syncobjs, count, syncobjs != stack_syncobjs);
 
 	if (timeout < 0)
 		return timeout;
@@ -1340,6 +1354,7 @@  int
 drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_timeline_wait *args = data;
 	ktime_t deadline, *pdeadline = NULL;
 	u32 count = args->count_handles;
@@ -1366,6 +1381,8 @@  drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     count,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1384,7 +1401,7 @@  drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
 						 &first,
 						 pdeadline);
 
-	drm_syncobj_array_free(syncobjs, count);
+	drm_syncobj_array_free(syncobjs, count, syncobjs != stack_syncobjs);
 
 	if (timeout < 0)
 		return timeout;
@@ -1501,6 +1518,7 @@  int
 drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_array *args = data;
 	struct drm_syncobj **syncobjs;
 	uint32_t i;
@@ -1518,6 +1536,8 @@  drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     args->count_handles,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1525,7 +1545,8 @@  drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 	for (i = 0; i < args->count_handles; i++)
 		drm_syncobj_replace_fence(syncobjs[i], NULL);
 
-	drm_syncobj_array_free(syncobjs, args->count_handles);
+	drm_syncobj_array_free(syncobjs, args->count_handles,
+			       syncobjs != stack_syncobjs);
 
 	return 0;
 }
@@ -1534,6 +1555,7 @@  int
 drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_array *args = data;
 	struct drm_syncobj **syncobjs;
 	uint32_t i;
@@ -1551,6 +1573,8 @@  drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     args->count_handles,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1561,7 +1585,8 @@  drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
 			break;
 	}
 
-	drm_syncobj_array_free(syncobjs, args->count_handles);
+	drm_syncobj_array_free(syncobjs, args->count_handles,
+			       syncobjs != stack_syncobjs);
 
 	return ret;
 }
@@ -1570,6 +1595,7 @@  int
 drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_timeline_array *args = data;
 	uint64_t __user *points = u64_to_user_ptr(args->points);
 	uint32_t i, j, count = args->count_handles;
@@ -1592,6 +1618,8 @@  drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     count,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1628,7 +1656,7 @@  drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 err_chains:
 	kfree(chains);
 out:
-	drm_syncobj_array_free(syncobjs, count);
+	drm_syncobj_array_free(syncobjs, count, syncobjs != stack_syncobjs);
 
 	return ret;
 }
@@ -1636,6 +1664,7 @@  drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_private)
 {
+	struct drm_syncobj *stack_syncobjs[DRM_SYNCOBJ_FAST_PATH_ENTRIES];
 	struct drm_syncobj_timeline_array *args = data;
 	struct drm_syncobj **syncobjs;
 	uint64_t __user *points = u64_to_user_ptr(args->points);
@@ -1657,6 +1686,8 @@  int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),
 				     args->count_handles,
+				     stack_syncobjs,
+				     ARRAY_SIZE(stack_syncobjs),
 				     &syncobjs);
 	if (ret < 0)
 		return ret;
@@ -1700,7 +1731,8 @@  int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
 			break;
 		}
 	}
-	drm_syncobj_array_free(syncobjs, args->count_handles);
+	drm_syncobj_array_free(syncobjs, args->count_handles,
+			       syncobjs != stack_syncobjs);
 
 	return ret;
 }