dma-fence: Deadline awareness

index 0de0482cd36e..71b2e883f304 100644
@@ -912,6 +912,26 @@ dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
 }
 EXPORT_SYMBOL(dma_fence_wait_any_timeout);
 
+/**
+ * dma_fence_set_deadline - set desired fence-wait deadline hint
+ * @fence:    the fence that is to be waited on
+ * @deadline: the time by which the waiter hopes for the fence to be
+ *            signaled
+ *
+ * Give the fence signaler a hint about an upcoming deadline, such as
+ * vblank, by which point the waiter would prefer the fence to be
+ * signaled by.  This is intended to give feedback to the fence signaler
+ * to aid in power management decisions, such as boosting GPU frequency
+ * if a periodic vblank deadline is approaching but the fence is not
+ * yet signaled..
+ */
+void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
+{
+	if (fence->ops->set_deadline && !dma_fence_is_signaled(fence))
+		fence->ops->set_deadline(fence, deadline);
+}
+EXPORT_SYMBOL(dma_fence_set_deadline);
+
 /**
  * dma_fence_describe - Dump fence describtion into seq_file
  * @fence: the 6fence to describe

index 775cdc0b4f24..f334e37e52bc 100644
@@ -257,6 +257,23 @@ struct dma_fence_ops {
 	 */
 	void (*timeline_value_str)(struct dma_fence *fence,
 				   char *str, int size);
+
+	/**
+	 * @set_deadline:
+	 *
+	 * Callback to allow a fence waiter to inform the fence signaler of
+	 * an upcoming deadline, such as vblank, by which point the waiter
+	 * would prefer the fence to be signaled by.  This is intended to
+	 * give feedback to the fence signaler to aid in power management
+	 * decisions, such as boosting GPU frequency.
+	 *
+	 * This is called without &dma_fence.lock held, it can be called
+	 * multiple times and from any context.  Locking is up to the callee
+	 * if it has some state to manage.
+	 *
+	 * This callback is optional.
+	 */
+	void (*set_deadline)(struct dma_fence *fence, ktime_t deadline);
 };
 
 void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,

@@ -583,6 +600,8 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr)
 	return ret < 0 ? ret : 0;
 }
 
+void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline);
+
 struct dma_fence *dma_fence_get_stub(void);
 struct dma_fence *dma_fence_allocate_private_stub(void);
 u64 dma_fence_context_alloc(unsigned num);

index 5c8a7084577b..9b3ce8948351 100644
@@ -123,12 +123,23 @@ static void dma_fence_array_release(struct dma_fence *fence)
 	dma_fence_free(fence);
 }
 
+static void dma_fence_array_set_deadline(struct dma_fence *fence,
+					 ktime_t deadline)
+{
+	struct dma_fence_array *array = to_dma_fence_array(fence);
+	unsigned i;
+
+	for (i = 0; i < array->num_fences; ++i)
+		dma_fence_set_deadline(array->fences[i], deadline);
+}
+
 const struct dma_fence_ops dma_fence_array_ops = {
 	.get_driver_name = dma_fence_array_get_driver_name,
 	.get_timeline_name = dma_fence_array_get_timeline_name,
 	.enable_signaling = dma_fence_array_enable_signaling,
 	.signaled = dma_fence_array_signaled,
 	.release = dma_fence_array_release,
+	.set_deadline = dma_fence_array_set_deadline,
 };
 EXPORT_SYMBOL(dma_fence_array_ops);
 

index a0d920576ba6..9663ba1bb6ac 100644
@@ -206,6 +206,17 @@ static void dma_fence_chain_release(struct dma_fence *fence)
 	dma_fence_free(fence);
 }
 
+
+static void dma_fence_chain_set_deadline(struct dma_fence *fence,
+					 ktime_t deadline)
+{
+	dma_fence_chain_for_each(fence, fence) {
+		struct dma_fence *f = dma_fence_chain_contained(fence);
+
+		dma_fence_set_deadline(f, deadline);
+	}
+}
+
 const struct dma_fence_ops dma_fence_chain_ops = {
 	.use_64bit_seqno = true,
 	.get_driver_name = dma_fence_chain_get_driver_name,

@@ -213,6 +224,7 @@ const struct dma_fence_ops dma_fence_chain_ops = {
 	.enable_signaling = dma_fence_chain_enable_signaling,
 	.signaled = dma_fence_chain_signaled,
 	.release = dma_fence_chain_release,
+	.set_deadline = dma_fence_chain_set_deadline,
 };
 EXPORT_SYMBOL(dma_fence_chain_ops);
 

index 1c76aed8e262..2a594b754af1 100644
@@ -684,6 +684,28 @@ long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 }
 EXPORT_SYMBOL_GPL(dma_resv_wait_timeout);
 
+/**
+ * dma_resv_set_deadline - Set a deadline on reservation's objects fences
+ * @obj: the reservation object
+ * @usage: controls which fences to include, see enum dma_resv_usage.
+ * @deadline: the requested deadline (MONOTONIC)
+ *
+ * May be called without holding the dma_resv lock.  Sets @deadline on
+ * all fences filtered by @usage.
+ */
+void dma_resv_set_deadline(struct dma_resv *obj, enum dma_resv_usage usage,
+			   ktime_t deadline)
+{
+	struct dma_resv_iter cursor;
+	struct dma_fence *fence;
+
+	dma_resv_iter_begin(&cursor, obj, usage);
+	dma_resv_for_each_fence_unlocked(&cursor, fence) {
+		dma_fence_set_deadline(fence, deadline);
+	}
+	dma_resv_iter_end(&cursor);
+}
+EXPORT_SYMBOL_GPL(dma_resv_set_deadline);
 
 /**
  * dma_resv_test_signaled - Test if a reservation object's fences have been

index 0637659a702c..8d0e34dad446 100644
@@ -479,6 +479,8 @@ int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage,
 int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src);
 long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 			   bool intr, unsigned long timeout);
+void dma_resv_set_deadline(struct dma_resv *obj, enum dma_resv_usage usage,
+			   ktime_t deadline);
 bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage);
 void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq);
 

index af57799c86ce..418021cfb87c 100644
@@ -350,6 +350,22 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
 	return ret;
 }
 
+static int sync_file_ioctl_set_deadline(struct sync_file *sync_file,
+					unsigned long arg)
+{
+	struct sync_set_deadline ts;
+
+	if (copy_from_user(&ts, (void __user *)arg, sizeof(ts)))
+		return -EFAULT;
+
+	if (ts.pad)
+		return -EINVAL;
+
+	dma_fence_set_deadline(sync_file->fence, ns_to_ktime(ts.deadline_ns));
+
+	return 0;
+}
+
 static long sync_file_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {

@@ -362,6 +378,9 @@ static long sync_file_ioctl(struct file *file, unsigned int cmd,
 	case SYNC_IOC_FILE_INFO:
 		return sync_file_ioctl_fence_info(sync_file, arg);
 
+	case SYNC_IOC_SET_DEADLINE:
+		return sync_file_ioctl_set_deadline(sync_file, arg);
+
 	default:
 		return -ENOTTY;
 	}

index ee2dcfb3d660..49325cf6749b 100644
@@ -67,6 +67,21 @@ struct sync_file_info {
 	__u64	sync_fence_info;
 };
 
+/**
+ * struct sync_set_deadline - set a deadline hint on a fence
+ * @deadline_ns: absolute time of the deadline
+ * @pad:	must be zero
+ *
+ * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank)
+ */
+struct sync_set_deadline {
+	__u64	deadline_ns;
+	/* Not strictly needed for alignment but gives some possibility
+	 * for future extension:
+	 */
+	__u64	pad;
+};
+
 #define SYNC_IOC_MAGIC		'>'
 
 /**

@@ -95,4 +110,11 @@ struct sync_file_info {
  */
 #define SYNC_IOC_FILE_INFO	_IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info)
 
+/**
+ * DOC: SYNC_IOC_SET_DEADLINE - set a deadline on a fence
+ *
+ * Allows userspace to set a deadline on a fence, see dma_fence_set_deadline()
+ */
+#define SYNC_IOC_SET_DEADLINE	_IOW(SYNC_IOC_MAGIC, 5, struct sync_set_deadline)
+
 #endif /* _UAPI_LINUX_SYNC_H */

index 418021cfb87c..cbe96295373b 100644
@@ -192,6 +192,14 @@ static __poll_t sync_file_poll(struct file *file, poll_table *wait)
 {
 	struct sync_file *sync_file = file->private_data;
 
+	/*
+	 * The POLLPRI/EPOLLPRI flag can be used to signal that
+	 * userspace wants the fence to signal ASAP, express this
+	 * as an immediate deadline.
+	 */
+	if (poll_requested_events(wait) & EPOLLPRI)
+		dma_fence_set_deadline(sync_file->fence, ktime_get());
+
 	poll_wait(file, &sync_file->wq, wait);
 
 	if (list_empty(&sync_file->cb.node) &&

index 348b3a9170fa..3e2315ee955b 100644
@@ -52,12 +52,28 @@ struct sw_sync_create_fence_data {
 	__s32	fence; /* fd of new fence */
 };
 
+/**
+ * struct sw_sync_get_deadline - get the deadline hint of a sw_sync fence
+ * @deadline_ns: absolute time of the deadline
+ * @pad:	must be zero
+ * @fence_fd:	the sw_sync fence fd (in)
+ *
+ * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank)
+ */
+struct sw_sync_get_deadline {
+	__u64	deadline_ns;
+	__u32	pad;
+	__s32	fence_fd;
+};
+
 #define SW_SYNC_IOC_MAGIC	'W'
 
 #define SW_SYNC_IOC_CREATE_FENCE	_IOWR(SW_SYNC_IOC_MAGIC, 0,\
 		struct sw_sync_create_fence_data)
 
 #define SW_SYNC_IOC_INC			_IOW(SW_SYNC_IOC_MAGIC, 1, __u32)
+#define SW_SYNC_GET_DEADLINE		_IOWR(SW_SYNC_IOC_MAGIC, 2, \
+		struct sw_sync_get_deadline)
 
 static const struct dma_fence_ops timeline_fence_ops;
 

@@ -171,6 +187,13 @@ static void timeline_fence_timeline_value_str(struct dma_fence *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);
+
+	pt->deadline = deadline;
+}
+
 static const struct dma_fence_ops timeline_fence_ops = {
 	.get_driver_name = timeline_fence_get_driver_name,
 	.get_timeline_name = timeline_fence_get_timeline_name,

@@ -179,6 +202,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
 	.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,
 };
 
 /**

@@ -387,6 +411,37 @@ static long sw_sync_ioctl_inc(struct sync_timeline *obj, unsigned long arg)
 	return 0;
 }
 
+static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long arg)
+{
+	struct sw_sync_get_deadline data;
+	struct dma_fence *fence;
+	struct sync_pt *pt;
+
+	if (copy_from_user(&data, (void __user *)arg, sizeof(data)))
+		return -EFAULT;
+
+	if (data.deadline_ns || data.pad)
+		return -EINVAL;
+
+	fence = sync_file_get_fence(data.fence_fd);
+	if (!fence)
+		return -EINVAL;
+
+	pt = dma_fence_to_sync_pt(fence);
+	if (!pt)
+		return -EINVAL;
+
+
+	data.deadline_ns = ktime_to_ns(pt->deadline);
+
+	dma_fence_put(fence);
+
+	if (copy_to_user((void __user *)arg, &data, sizeof(data)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static long sw_sync_ioctl(struct file *file, unsigned int cmd,
 			  unsigned long arg)
 {

@@ -399,6 +454,9 @@ static long sw_sync_ioctl(struct file *file, unsigned int cmd,
 	case SW_SYNC_IOC_INC:
 		return sw_sync_ioctl_inc(obj, arg);
 
+	case SW_SYNC_GET_DEADLINE:
+		return sw_sync_ioctl_get_deadline(obj, arg);
+
 	default:
 		return -ENOTTY;
 	}

index 6176e52ba2d7..2e0146d0bdbb 100644
@@ -55,11 +55,13 @@ static inline struct sync_timeline *dma_fence_parent(struct dma_fence *fence)
  * @base: base fence object
  * @link: link on the sync timeline's list
  * @node: node in the sync timeline's tree
+ * @deadline: the most recently set fence deadline
  */
 struct sync_pt {
 	struct dma_fence base;
 	struct list_head link;
 	struct rb_node node;
+	ktime_t deadline;
 };
 
 extern const struct file_operations sw_sync_debugfs_fops;

index 49325cf6749b..dc6645b2598b 100644
@@ -72,7 +72,11 @@ struct sync_file_info {
  * @deadline_ns: absolute time of the deadline
  * @pad:	must be zero
  *
- * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank)
+ * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank).  For
+ * example:
+ *
+ *     clock_gettime(CLOCK_MONOTONIC, &t);
+ *     deadline_ns = (t.tv_sec * 1000000000L) + t.tv_nsec + duration_ns
  */
 struct sync_set_deadline {
 	__u64	deadline_ns;

index 7fd869520ef2..fe9c6468e440 100644
@@ -123,6 +123,37 @@ static void drm_sched_fence_release_finished(struct dma_fence *f)
 	dma_fence_put(&fence->scheduled);
 }
 
+static void drm_sched_fence_set_deadline_finished(struct dma_fence *f,
+						  ktime_t deadline)
+{
+	struct drm_sched_fence *fence = to_drm_sched_fence(f);
+	struct dma_fence *parent;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fence->lock, flags);
+
+	/* If we already have an earlier deadline, keep it: */
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags) &&
+	    ktime_before(fence->deadline, deadline)) {
+		spin_unlock_irqrestore(&fence->lock, flags);
+		return;
+	}
+
+	fence->deadline = deadline;
+	set_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags);
+
+	spin_unlock_irqrestore(&fence->lock, flags);
+
+	/*
+	 * smp_load_aquire() to ensure that if we are racing another
+	 * thread calling drm_sched_fence_set_parent(), that we see
+	 * the parent set before it calls test_bit(HAS_DEADLINE_BIT)
+	 */
+	parent = smp_load_acquire(&fence->parent);
+	if (parent)
+		dma_fence_set_deadline(parent, deadline);
+}
+
 static const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,

@@ -133,6 +164,7 @@ static const struct dma_fence_ops drm_sched_fence_ops_finished = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
 	.release = drm_sched_fence_release_finished,
+	.set_deadline = drm_sched_fence_set_deadline_finished,
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)

@@ -147,6 +179,20 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
 }
 EXPORT_SYMBOL(to_drm_sched_fence);
 
+void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
+				struct dma_fence *fence)
+{
+	/*
+	 * smp_store_release() to ensure another thread racing us
+	 * in drm_sched_fence_set_deadline_finished() sees the
+	 * fence's parent set before test_bit()
+	 */
+	smp_store_release(&s_fence->parent, dma_fence_get(fence));
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT,
+		     &s_fence->finished.flags))
+		dma_fence_set_deadline(fence, s_fence->deadline);
+}
+
 struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
 					      void *owner)
 {

index 4e6ad6e122bc..007f98c48f8d 100644
@@ -1019,7 +1019,7 @@ static int drm_sched_main(void *param)
 		drm_sched_fence_scheduled(s_fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {
-			s_fence->parent = dma_fence_get(fence);
+			drm_sched_fence_set_parent(s_fence, fence);
 			/* Drop for original kref_init of the fence */
 			dma_fence_put(fence);
 

index 9db9e5e504ee..99584e457153 100644
@@ -41,6 +41,15 @@
  */
 #define DRM_SCHED_FENCE_DONT_PIPELINE	DMA_FENCE_FLAG_USER_BITS
 
+/**
+ * DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT - A fence deadline hint has been set
+ *
+ * Because we could have a deadline hint can be set before the backing hw
+ * fence is created, we need to keep track of whether a deadline has already
+ * been set.
+ */
+#define DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT	(DMA_FENCE_FLAG_USER_BITS + 1)
+
 enum dma_resv_usage;
 struct dma_resv;
 struct drm_gem_object;

@@ -280,6 +289,12 @@ struct drm_sched_fence {
          */
 	struct dma_fence		finished;
 
+	/**
+	 * @deadline: deadline set on &drm_sched_fence.finished which
+	 * potentially needs to be propagated to &drm_sched_fence.parent
+	 */
+	ktime_t				deadline;
+
         /**
          * @parent: the fence returned by &drm_sched_backend_ops.run_job
          * when scheduling the job on hardware. We signal the

@@ -568,6 +583,8 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
 				   enum drm_sched_priority priority);
 bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);
 
+void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
+				struct dma_fence *fence);
 struct drm_sched_fence *drm_sched_fence_alloc(
 	struct drm_sched_entity *s_entity, void *owner);
 void drm_sched_fence_init(struct drm_sched_fence *fence,

index 0c2be8360525..a85e9464f07b 100644
@@ -126,6 +126,11 @@
  * synchronize between the two.
  * This requirement is inherited from the Vulkan fence API.
  *
+ * If &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE is set, the ioctl will also set
+ * a fence deadline hint on the backing fences before waiting, to provide the
+ * fence signaler with an appropriate sense of urgency.  The deadline is
+ * specified as an absolute &CLOCK_MONOTONIC value in units of ns.
+ *
  * Similarly, &DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT takes an array of syncobj
  * handles as well as an array of u64 points and does a host-side wait on all
  * of syncobj fences at the given points simultaneously.

@@ -973,7 +978,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 						  uint32_t count,
 						  uint32_t flags,
 						  signed long timeout,
-						  uint32_t *idx)
+						  uint32_t *idx,
+						  ktime_t *deadline)
 {
 	struct syncobj_wait_entry *entries;
 	struct dma_fence *fence;

@@ -1053,6 +1059,15 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 			drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]);
 	}
 
+	if (deadline) {
+		for (i = 0; i < count; ++i) {
+			fence = entries[i].fence;
+			if (!fence)
+				continue;
+			dma_fence_set_deadline(fence, *deadline);
+		}
+	}
+
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 

@@ -1151,7 +1166,8 @@ static int drm_syncobj_array_wait(struct drm_device *dev,
 				  struct drm_file *file_private,
 				  struct drm_syncobj_wait *wait,
 				  struct drm_syncobj_timeline_wait *timeline_wait,
-				  struct drm_syncobj **syncobjs, bool timeline)
+				  struct drm_syncobj **syncobjs, bool timeline,
+				  ktime_t *deadline)
 {
 	signed long timeout = 0;
 	uint32_t first = ~0;

@@ -1162,7 +1178,8 @@ static int drm_syncobj_array_wait(struct drm_device *dev,
 							 NULL,
 							 wait->count_handles,
 							 wait->flags,
-							 timeout, &first);
+							 timeout, &first,
+							 deadline);
 		if (timeout < 0)
 			return timeout;
 		wait->first_signaled = first;

@@ -1172,7 +1189,8 @@ static int drm_syncobj_array_wait(struct drm_device *dev,
 							 u64_to_user_ptr(timeline_wait->points),
 							 timeline_wait->count_handles,
 							 timeline_wait->flags,
-							 timeout, &first);
+							 timeout, &first,
+							 deadline);
 		if (timeout < 0)
 			return timeout;
 		timeline_wait->first_signaled = first;

@@ -1243,17 +1261,22 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_syncobj_wait *args = data;
 	struct drm_syncobj **syncobjs;
+	unsigned possible_flags;
+	ktime_t t, *tp = NULL;
 	int ret = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ))
 		return -EOPNOTSUPP;
 
-	if (args->flags & ~(DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
-			    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT))
+	possible_flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
+			 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+			 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE;
+
+	if (args->flags & ~possible_flags)
 		return -EINVAL;
 
 	if (args->count_handles == 0)
-		return -EINVAL;
+		return 0;
 
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),

@@ -1262,8 +1285,13 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 	if (ret < 0)
 		return ret;
 
+	if (args->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE) {
+		t = ns_to_ktime(args->deadline_ns);
+		tp = &t;
+	}
+
 	ret = drm_syncobj_array_wait(dev, file_private,
-				     args, NULL, syncobjs, false);
+				     args, NULL, syncobjs, false, tp);
 
 	drm_syncobj_array_free(syncobjs, args->count_handles);
 

@@ -1276,18 +1304,23 @@ drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_syncobj_timeline_wait *args = data;
 	struct drm_syncobj **syncobjs;
+	unsigned possible_flags;
+	ktime_t t, *tp = NULL;
 	int ret = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE))
 		return -EOPNOTSUPP;
 
-	if (args->flags & ~(DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
-			    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
-			    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE))
+	possible_flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
+			 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+			 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE |
+			 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE;
+
+	if (args->flags & ~possible_flags)
 		return -EINVAL;
 
 	if (args->count_handles == 0)
-		return -EINVAL;
+		return -0;
 
 	ret = drm_syncobj_array_find(file_private,
 				     u64_to_user_ptr(args->handles),

@@ -1296,8 +1329,13 @@ drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
 	if (ret < 0)
 		return ret;
 
+	if (args->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE) {
+		t = ns_to_ktime(args->deadline_ns);
+		tp = &t;
+	}
+
 	ret = drm_syncobj_array_wait(dev, file_private,
-				     NULL, args, syncobjs, true);
+				     NULL, args, syncobjs, true, tp);
 
 	drm_syncobj_array_free(syncobjs, args->count_handles);
 

index 642808520d92..bff0509ac8b6 100644
@@ -887,6 +887,7 @@ struct drm_syncobj_transfer {
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline based to deadline_ns */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */

@@ -895,6 +896,14 @@ struct drm_syncobj_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_ns - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_ns;
 };
 
 struct drm_syncobj_timeline_wait {

@@ -907,6 +916,14 @@ struct drm_syncobj_timeline_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_ns - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_ns;
 };
 
 

index 2ff31717a3de..47e578128a9a 100644
@@ -844,10 +844,9 @@ bool drm_crtc_vblank_helper_get_vblank_timestamp(struct drm_crtc *crtc,
 EXPORT_SYMBOL(drm_crtc_vblank_helper_get_vblank_timestamp);
 
 /**
- * drm_get_last_vbltimestamp - retrieve raw timestamp for the most recent
- *                             vblank interval
- * @dev: DRM device
- * @pipe: index of CRTC whose vblank timestamp to retrieve
+ * drm_crtc_get_last_vbltimestamp - retrieve raw timestamp for the most
+ *                                  recent vblank interval
+ * @crtc: CRTC whose vblank timestamp to retrieve
  * @tvblank: Pointer to target time which should receive the timestamp
  * @in_vblank_irq:
  *     True when called from drm_crtc_handle_vblank().  Some drivers

@@ -865,10 +864,9 @@ EXPORT_SYMBOL(drm_crtc_vblank_helper_get_vblank_timestamp);
  * True if timestamp is considered to be very precise, false otherwise.
  */
 static bool
-drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe,
-			  ktime_t *tvblank, bool in_vblank_irq)
+drm_crtc_get_last_vbltimestamp(struct drm_crtc *crtc, ktime_t *tvblank,
+			       bool in_vblank_irq)
 {
-	struct drm_crtc *crtc = drm_crtc_from_index(dev, pipe);
 	bool ret = false;
 
 	/* Define requested maximum error on timestamps (nanoseconds). */

@@ -876,8 +874,6 @@ drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe,
 
 	/* Query driver if possible and precision timestamping enabled. */
 	if (crtc && crtc->funcs->get_vblank_timestamp && max_error > 0) {
-		struct drm_crtc *crtc = drm_crtc_from_index(dev, pipe);
-
 		ret = crtc->funcs->get_vblank_timestamp(crtc, &max_error,
 							tvblank, in_vblank_irq);
 	}

@@ -891,6 +887,15 @@ drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe,
 	return ret;
 }
 
+static bool
+drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe,
+			  ktime_t *tvblank, bool in_vblank_irq)
+{
+	struct drm_crtc *crtc = drm_crtc_from_index(dev, pipe);
+
+	return drm_crtc_get_last_vbltimestamp(crtc, tvblank, in_vblank_irq);
+}
+
 /**
  * drm_crtc_vblank_count - retrieve "cooked" vblank counter value
  * @crtc: which counter to retrieve

@@ -980,6 +985,35 @@ u64 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc,
 }
 EXPORT_SYMBOL(drm_crtc_vblank_count_and_time);
 
+/**
+ * drm_crtc_next_vblank_time - calculate the time of the next vblank
+ * @crtc: the crtc for which to calculate next vblank time
+ * @vblanktime: pointer to time to receive the next vblank timestamp.
+ *
+ * Calculate the expected time of the start of the next vblank period,
+ * based on time of previous vblank and frame duration
+ */
+int drm_crtc_next_vblank_start(struct drm_crtc *crtc, ktime_t *vblanktime)
+{
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[pipe];
+	struct drm_display_mode *mode = &vblank->hwmode;
+	u64 vblank_start;
+
+	if (!vblank->framedur_ns || !vblank->linedur_ns)
+		return -EINVAL;
+
+	if (!drm_crtc_get_last_vbltimestamp(crtc, vblanktime, false))
+		return -EINVAL;
+
+	vblank_start = (u64)vblank->framedur_ns * mode->crtc_vblank_start /
+			mode->crtc_vtotal;
+	*vblanktime  = ktime_add(*vblanktime, ns_to_ktime(vblank_start));
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_crtc_next_vblank_start);
+
 static void send_vblank_event(struct drm_device *dev,
 		struct drm_pending_vblank_event *e,
 		u64 seq, ktime_t now)

index 733a3e2d1d10..7f3957943dd1 100644
@@ -230,6 +230,7 @@ bool drm_dev_has_vblank(const struct drm_device *dev);
 u64 drm_crtc_vblank_count(struct drm_crtc *crtc);
 u64 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc,
 				   ktime_t *vblanktime);
+int drm_crtc_next_vblank_start(struct drm_crtc *crtc, ktime_t *vblanktime);
 void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
 			       struct drm_pending_vblank_event *e);
 void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,

index d579fd8f7cb8..d8ee98ce2fc5 100644
@@ -1511,6 +1511,40 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_enables);
 
+/*
+ * For atomic updates which touch just a single CRTC, calculate the time of the
+ * next vblank, and inform all the fences of the deadline.
+ */
+static void set_fence_deadline(struct drm_device *dev,
+			       struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc, *wait_crtc = NULL;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_plane *plane;
+	struct drm_plane_state *new_plane_state;
+	ktime_t vbltime;
+	int i;
+
+	for_each_new_crtc_in_state (state, crtc, new_crtc_state, i) {
+		if (wait_crtc)
+			return;
+		wait_crtc = crtc;
+	}
+
+	/* If no CRTCs updated, then nothing to do: */
+	if (!wait_crtc)
+		return;
+
+	if (drm_crtc_next_vblank_start(wait_crtc, &vbltime))
+		return;
+
+	for_each_new_plane_in_state (state, plane, new_plane_state, i) {
+		if (!new_plane_state->fence)
+			continue;
+		dma_fence_set_deadline(new_plane_state->fence, vbltime);
+	}
+}
+
 /**
  * drm_atomic_helper_wait_for_fences - wait for fences stashed in plane state
  * @dev: DRM device

@@ -1540,6 +1574,8 @@ int drm_atomic_helper_wait_for_fences(struct drm_device *dev,
 	struct drm_plane_state *new_plane_state;
 	int i, ret;
 
+	set_fence_deadline(dev, state);
+
 	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
 		if (!new_plane_state->fence)
 			continue;

index 56641408ea74..51b461f32103 100644
@@ -8,6 +8,35 @@
 
 #include "msm_drv.h"
 #include "msm_fence.h"
+#include "msm_gpu.h"
+
+static struct msm_gpu *fctx2gpu(struct msm_fence_context *fctx)
+{
+	struct msm_drm_private *priv = fctx->dev->dev_private;
+	return priv->gpu;
+}
+
+static enum hrtimer_restart deadline_timer(struct hrtimer *t)
+{
+	struct msm_fence_context *fctx = container_of(t,
+			struct msm_fence_context, deadline_timer);
+
+	kthread_queue_work(fctx2gpu(fctx)->worker, &fctx->deadline_work);
+
+	return HRTIMER_NORESTART;
+}
+
+static void deadline_work(struct kthread_work *work)
+{
+	struct msm_fence_context *fctx = container_of(work,
+			struct msm_fence_context, deadline_work);
+
+	/* If deadline fence has already passed, nothing to do: */
+	if (msm_fence_completed(fctx, fctx->next_deadline_fence))
+		return;
+
+	msm_devfreq_boost(fctx2gpu(fctx), 2);
+}
 
 
 struct msm_fence_context *

@@ -36,6 +65,13 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
 	fctx->completed_fence = fctx->last_fence;
 	*fctx->fenceptr = fctx->last_fence;
 
+	hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	fctx->deadline_timer.function = deadline_timer;
+
+	kthread_init_work(&fctx->deadline_work, deadline_work);
+
+	fctx->next_deadline = ktime_get();
+
 	return fctx;
 }
 

@@ -62,6 +98,8 @@ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 	spin_lock_irqsave(&fctx->spinlock, flags);
 	if (fence_after(fence, fctx->completed_fence))
 		fctx->completed_fence = fence;
+	if (msm_fence_completed(fctx, fctx->next_deadline_fence))
+		hrtimer_cancel(&fctx->deadline_timer);
 	spin_unlock_irqrestore(&fctx->spinlock, flags);
 }
 

@@ -92,10 +130,46 @@ static bool msm_fence_signaled(struct dma_fence *fence)
 	return msm_fence_completed(f->fctx, f->base.seqno);
 }
 
+static void msm_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
+{
+	struct msm_fence *f = to_msm_fence(fence);
+	struct msm_fence_context *fctx = f->fctx;
+	unsigned long flags;
+	ktime_t now;
+
+	spin_lock_irqsave(&fctx->spinlock, flags);
+	now = ktime_get();
+
+	if (ktime_after(now, fctx->next_deadline) ||
+			ktime_before(deadline, fctx->next_deadline)) {
+		fctx->next_deadline = deadline;
+		fctx->next_deadline_fence =
+			max(fctx->next_deadline_fence, (uint32_t)fence->seqno);
+
+		/*
+		 * Set timer to trigger boost 3ms before deadline, or
+		 * if we are already less than 3ms before the deadline
+		 * schedule boost work immediately.
+		 */
+		deadline = ktime_sub(deadline, ms_to_ktime(3));
+
+		if (ktime_after(now, deadline)) {
+			kthread_queue_work(fctx2gpu(fctx)->worker,
+					&fctx->deadline_work);
+		} else {
+			hrtimer_start(&fctx->deadline_timer, deadline,
+					HRTIMER_MODE_ABS);
+		}
+	}
+
+	spin_unlock_irqrestore(&fctx->spinlock, flags);
+}
+
 static const struct dma_fence_ops msm_fence_ops = {
 	.get_driver_name = msm_fence_get_driver_name,
 	.get_timeline_name = msm_fence_get_timeline_name,
 	.signaled = msm_fence_signaled,
+	.set_deadline = msm_fence_set_deadline,
 };
 
 struct dma_fence *

index 7f1798c54cd1..cdaebfb94f5c 100644
@@ -52,6 +52,26 @@ struct msm_fence_context {
 	volatile uint32_t *fenceptr;
 
 	spinlock_t spinlock;
+
+	/*
+	 * TODO this doesn't really deal with multiple deadlines, like
+	 * if userspace got multiple frames ahead.. OTOH atomic updates
+	 * don't queue, so maybe that is ok
+	 */
+
+	/** next_deadline: Time of next deadline */
+	ktime_t next_deadline;
+
+	/**
+	 * next_deadline_fence:
+	 *
+	 * Fence value for next pending deadline.  The deadline timer is
+	 * canceled when this fence is signaled.
+	 */
+	uint32_t next_deadline_fence;
+
+	struct hrtimer deadline_timer;
+	struct kthread_work deadline_work;
 };
 
 struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,

index aca48c868c14..f6764a86b2da 100644
@@ -46,6 +46,7 @@
  * - 1.8.0 - Add MSM_BO_CACHED_COHERENT for supported GPUs (a6xx)
  * - 1.9.0 - Add MSM_SUBMIT_FENCE_SN_IN
  * - 1.10.0 - Add MSM_SUBMIT_BO_NO_IMPLICIT
+ * - 1.11.0 - Add wait boost (MSM_WAIT_FENCE_BOOST, MSM_PREP_BOOST)
  */
 #define MSM_VERSION_MAJOR	1
 #define MSM_VERSION_MINOR	10

@@ -899,7 +900,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 }
 
 static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
-		      ktime_t timeout)
+		      ktime_t timeout, uint32_t flags)
 {
 	struct dma_fence *fence;
 	int ret;

@@ -929,6 +930,9 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
 	if (!fence)
 		return 0;
 
+	if (flags & MSM_WAIT_FENCE_BOOST)
+		dma_fence_set_deadline(fence, ktime_get());
+
 	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
 	if (ret == 0) {
 		ret = -ETIMEDOUT;

@@ -949,8 +953,8 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	struct msm_gpu_submitqueue *queue;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (args->flags & ~MSM_WAIT_FENCE_FLAGS) {
+		DRM_ERROR("invalid flags: %08x\n", args->flags);
 		return -EINVAL;
 	}
 

@@ -961,7 +965,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout), args->flags);
 
 	msm_submitqueue_put(queue);
 

index 1dee0d18abbb..dd4a0d773f6e 100644
@@ -846,6 +846,11 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
 		op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout);
 	long ret;
 
+	if (op & MSM_PREP_BOOST) {
+		dma_resv_set_deadline(obj->resv, dma_resv_usage_rw(write),
+				      ktime_get());
+	}
+
 	ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write),
 				    true,  remain);
 	if (ret == 0)

index 329100016e7c..dbf0d6f43fa9 100644
@@ -151,8 +151,13 @@ struct drm_msm_gem_info {
 #define MSM_PREP_READ        0x01
 #define MSM_PREP_WRITE       0x02
 #define MSM_PREP_NOSYNC      0x04
+#define MSM_PREP_BOOST       0x08
 
-#define MSM_PREP_FLAGS       (MSM_PREP_READ | MSM_PREP_WRITE | MSM_PREP_NOSYNC)
+#define MSM_PREP_FLAGS       (MSM_PREP_READ | \
+			      MSM_PREP_WRITE | \
+			      MSM_PREP_NOSYNC | \
+			      MSM_PREP_BOOST | \
+			      0)
 
 struct drm_msm_gem_cpu_prep {
 	__u32 handle;         /* in */

@@ -286,6 +291,11 @@ struct drm_msm_gem_submit {
 
 };
 
+#define MSM_WAIT_FENCE_BOOST	0x00000001
+#define MSM_WAIT_FENCE_FLAGS	( \
+		MSM_WAIT_FENCE_BOOST | \
+		0)
+
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
  * a buffer if you need to access it from the CPU (other cmdstream
  * submission from same or other contexts, PAGE_FLIP ioctl, etc, all

@@ -295,7 +305,7 @@ struct drm_msm_gem_submit {
  */
 struct drm_msm_wait_fence {
 	__u32 fence;          /* in */
-	__u32 pad;
+	__u32 flags;          /* in, bitmask of MSM_WAIT_FENCE_x */
 	struct drm_msm_timespec timeout;   /* in */
 	__u32 queueid;         /* in, submitqueue id */
 };

index a683bd9b5a04..43996aecaf8c 100644
@@ -411,20 +411,6 @@ static void dpu_kms_disable_commit(struct msm_kms *kms)
 	pm_runtime_put_sync(&dpu_kms->pdev->dev);
 }
 
-static ktime_t dpu_kms_vsync_time(struct msm_kms *kms, struct drm_crtc *crtc)
-{
-	struct drm_encoder *encoder;
-
-	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) {
-		ktime_t vsync_time;
-
-		if (dpu_encoder_vsync_time(encoder, &vsync_time) == 0)
-			return vsync_time;
-	}
-
-	return ktime_get();
-}
-
 static void dpu_kms_prepare_commit(struct msm_kms *kms,
 		struct drm_atomic_state *state)
 {

@@ -953,7 +939,6 @@ static const struct msm_kms_funcs kms_funcs = {
 	.irq             = dpu_core_irq,
 	.enable_commit   = dpu_kms_enable_commit,
 	.disable_commit  = dpu_kms_disable_commit,
-	.vsync_time      = dpu_kms_vsync_time,
 	.prepare_commit  = dpu_kms_prepare_commit,
 	.flush_commit    = dpu_kms_flush_commit,
 	.wait_flush      = dpu_kms_wait_flush,

index 1686fbb611fd..de7ce17489cc 100644
@@ -186,8 +186,7 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 	struct msm_kms *kms = priv->kms;
 	struct drm_crtc *async_crtc = NULL;
 	unsigned crtc_mask = get_crtc_mask(state);
-	bool async = kms->funcs->vsync_time &&
-			can_do_async(state, &async_crtc);
+	bool async = can_do_async(state, &async_crtc);
 
 	trace_msm_atomic_commit_tail_start(async, crtc_mask);
 

@@ -231,7 +230,9 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 
 			kms->pending_crtc_mask |= crtc_mask;
 
-			vsync_time = kms->funcs->vsync_time(kms, async_crtc);
+			if (!drm_crtc_next_vblank_start(async_crtc, &vsync_time))
+				goto fallback;
+
 			wakeup_time = ktime_sub(vsync_time, ms_to_ktime(1));
 
 			msm_hrtimer_queue_work(&timer->work, wakeup_time,

@@ -253,6 +254,7 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 		return;
 	}
 
+fallback:
 	/*
 	 * If there is any async flush pending on updated crtcs, fold
 	 * them into the current flush.

index f8ed7588928c..086a3f1ff956 100644
@@ -59,14 +59,6 @@ struct msm_kms_funcs {
 	void (*enable_commit)(struct msm_kms *kms);
 	void (*disable_commit)(struct msm_kms *kms);
 
-	/**
-	 * If the kms backend supports async commit, it should implement
-	 * this method to return the time of the next vsync.  This is
-	 * used to determine a time slightly before vsync, for the async
-	 * commit timer to run and complete an async commit.
-	 */
-	ktime_t (*vsync_time)(struct msm_kms *kms, struct drm_crtc *crtc);
-
 	/**
 	 * Prepare for atomic commit.  This is called after any previous
 	 * (async or otherwise) commit has completed.

index 7503dcb9043b..44491e7e214c 100644
@@ -97,6 +97,25 @@ static bool i915_fence_enable_signaling(struct dma_fence *fence)
 	return i915_request_enable_breadcrumb(to_request(fence));
 }
 
+static void i915_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
+{
+	struct i915_request *rq = to_request(fence);
+
+	if (i915_request_completed(rq))
+		return;
+
+	if (i915_request_started(rq))
+		return;
+
+	/*
+	 * TODO something more clever for deadlines that are in the
+	 * future.  I think probably track the nearest deadline in
+	 * rq->timeline and set timer to trigger boost accordingly?
+	 */
+
+	intel_rps_boost(rq);
+}
+
 static signed long i915_fence_wait(struct dma_fence *fence,
 				   bool interruptible,
 				   signed long timeout)

@@ -182,6 +201,7 @@ const struct dma_fence_ops i915_fence_ops = {
 	.signaled = i915_fence_signaled,
 	.wait = i915_fence_wait,
 	.release = i915_fence_release,
+	.set_deadline = i915_fence_set_deadline,
 };
 
 static void irq_execute_cb(struct irq_work *wrk)