i915: Fix i915 suspend delay

During system suspend, the "wait for ring buffer to empty" loop would
always time out after three seconds, because the faster cached ring
buffer head read would always return zero.  Force the slow-and-careful
PIO read on all but the first iterations of the loop to fix it.

This also removes the unused (and useless) 'actual_head' variable that
tried to approximate doing this, but did it incorrectly.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Dave Airlie <airlied@linux.ie>
Cc: DRI mailing list <dri-devel@lists.freedesktop.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -928,6 +928,7 @@ static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
 
 int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
 {
+	int reread = 0;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long end;
@@ -940,9 +941,8 @@ int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
 		 * fallback to the slow and accurate path.
 		 */
 		head = intel_read_status_page(ring, 4);
-		if (head < ring->actual_head)
+		if (reread)
 			head = I915_READ_HEAD(ring);
-		ring->actual_head = head;
 		ring->head = head & HEAD_ADDR;
 		ring->space = ring->head - (ring->tail + 8);
 		if (ring->space < 0)
@@ -961,6 +961,7 @@ int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
 		msleep(1);
 		if (atomic_read(&dev_priv->mm.wedged))
 			return -EAGAIN;
+		reread = 1;
 	} while (!time_after(jiffies, end));
 	trace_i915_ring_wait_end (dev);
 	return -EBUSY;

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -47,7 +47,6 @@ struct  intel_ring_buffer {
 	struct		drm_device *dev;
 	struct		drm_i915_gem_object *obj;
 
-	u32		actual_head;
 	u32		head;
 	u32		tail;
 	int		space;