1 files changed, 84 insertions, 27 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 32e6aad..f56af0a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1146,23 +1146,74 @@ static bool missed_irq(struct drm_i915_private *dev_priv,
 	return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
 }
 
-static int __i915_spin_request(struct drm_i915_gem_request *req)
+static unsigned long local_clock_us(unsigned *cpu)
+{
+	unsigned long t;
+
+	/* Cheaply and approximately convert from nanoseconds to microseconds.
+	 * The result and subsequent calculations are also defined in the same
+	 * approximate microseconds units. The principal source of timing
+	 * error here is from the simple truncation.
+	 *
+	 * Note that local_clock() is only defined wrt to the current CPU;
+	 * the comparisons are no longer valid if we switch CPUs. Instead of
+	 * blocking preemption for the entire busywait, we can detect the CPU
+	 * switch and use that as indicator of system load and a reason to
+	 * stop busywaiting, see busywait_stop().
+	 */
+	*cpu = get_cpu();
+	t = local_clock() >> 10;
+	put_cpu();
+
+	return t;
+}
+
+static bool busywait_stop(unsigned long timeout, unsigned cpu)
+{
+	unsigned this_cpu;
+
+	if (time_after(local_clock_us(&this_cpu), timeout))
+		return true;
+
+	return this_cpu != cpu;
+}
+
+static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 {
 	unsigned long timeout;
+	unsigned cpu;
+
+	/* When waiting for high frequency requests, e.g. during synchronous
+	 * rendering split between the CPU and GPU, the finite amount of time
+	 * required to set up the irq and wait upon it limits the response
+	 * rate. By busywaiting on the request completion for a short while we
+	 * can service the high frequency waits as quick as possible. However,
+	 * if it is a slow request, we want to sleep as quickly as possible.
+	 * The tradeoff between waiting and sleeping is roughly the time it
+	 * takes to sleep on a request, on the order of a microsecond.
+	 */
 
-	if (i915_gem_request_get_ring(req)->irq_refcount)
+	if (req->ring->irq_refcount)
 		return -EBUSY;
 
-	timeout = jiffies + 1;
+	/* Only spin if we know the GPU is processing this request */
+	if (!i915_gem_request_started(req, true))
+		return -EAGAIN;
+
+	timeout = local_clock_us(&cpu) + 5;
 	while (!need_resched()) {
 		if (i915_gem_request_completed(req, true))
 			return 0;
 
-		if (time_after_eq(jiffies, timeout))
+		if (signal_pending_state(state, current))
+			break;
+
+		if (busywait_stop(timeout, cpu))
 			break;
 
 		cpu_relax_lowlatency();
 	}
+
 	if (i915_gem_request_completed(req, false))
 		return 0;
 
@@ -1197,6 +1248,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	const bool irq_test_in_progress =
 		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
+	int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
 	DEFINE_WAIT(wait);
 	unsigned long timeout_expire;
 	s64 before, now;
@@ -1229,7 +1281,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	before = ktime_get_raw_ns();
 
 	/* Optimistic spin for the next jiffie before touching IRQs */
-	ret = __i915_spin_request(req);
+	ret = __i915_spin_request(req, state);
 	if (ret == 0)
 		goto out;
 
@@ -1241,8 +1293,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	for (;;) {
 		struct timer_list timer;
 
-		prepare_to_wait(&ring->irq_queue, &wait,
-				interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&ring->irq_queue, &wait, state);
 
 		/* We need to check whether any gpu reset happened in between
 		 * the caller grabbing the seqno and now ... */
@@ -1260,7 +1311,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 			break;
 		}
 
-		if (interruptible && signal_pending(current)) {
+		if (signal_pending_state(state, current)) {
 			ret = -ERESTARTSYS;
 			break;
 		}
@@ -2554,6 +2605,7 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 	request->batch_obj = obj;
 
 	request->emitted_jiffies = jiffies;
+	request->previous_seqno = ring->last_submitted_seqno;
 	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 
@@ -4080,6 +4132,29 @@ i915_vma_misplaced(struct i915_vma *vma, uint32_t alignment, uint64_t flags)
 	return false;
 }
 
+void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	bool mappable, fenceable;
+	u32 fence_size, fence_alignment;
+
+	fence_size = i915_gem_get_gtt_size(obj->base.dev,
+					   obj->base.size,
+					   obj->tiling_mode);
+	fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
+						     obj->base.size,
+						     obj->tiling_mode,
+						     true);
+
+	fenceable = (vma->node.size == fence_size &&
+		     (vma->node.start & (fence_alignment - 1)) == 0);
+
+	mappable = (vma->node.start + fence_size <=
+		    to_i915(obj->base.dev)->gtt.mappable_end);
+
+	obj->map_and_fenceable = mappable && fenceable;
+}
+
 static int
 i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
 		       struct i915_address_space *vm,
@@ -4147,25 +4222,7 @@ i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
 
 	if (ggtt_view && ggtt_view->type == I915_GGTT_VIEW_NORMAL &&
 	    (bound ^ vma->bound) & GLOBAL_BIND) {
-		bool mappable, fenceable;
-		u32 fence_size, fence_alignment;
-
-		fence_size = i915_gem_get_gtt_size(obj->base.dev,
-						   obj->base.size,
-						   obj->tiling_mode);
-		fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
-							     obj->base.size,
-							     obj->tiling_mode,
-							     true);
-
-		fenceable = (vma->node.size == fence_size &&
-			     (vma->node.start & (fence_alignment - 1)) == 0);
-
-		mappable = (vma->node.start + fence_size <=
-			    dev_priv->gtt.mappable_end);
-
-		obj->map_and_fenceable = mappable && fenceable;
-
+		__i915_vma_set_map_and_fenceable(vma);
 		WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);
 	}