drm/i915: Add ringbuffer wait reset to hangcheck

The GPU records whether it is currently waiting for a completion of a
WAIT_FOR_EVENT in the RB_WAIT bit in the ringbuffer control registers.
On third generation chipsets and later, a write of 1 to this bit breaks
the hang and returns the GPU to arbitration, i.e. the GPU should
continue executing the reminder of the batchbuffer and return to normal
operations.

By adding this to hangcheck we can avoid a full GPU reset under these
conditions.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

1 files changed, 16 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 29215b6d565..2f7f7cb0bf3 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1373,6 +1373,21 @@ void i915_hangcheck_elapsed(unsigned long data)
 	    dev_priv->last_instdone1 == instdone1) {
 		if (dev_priv->hangcheck_count++ > 1) {
 			DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
+
+			if (!IS_GEN2(dev)) {
+				/* Is the chip hanging on a WAIT_FOR_EVENT?
+				 * If so we can simply poke the RB_WAIT bit
+				 * and break the hang. This should work on
+				 * all but the second generation chipsets.
+				 */
+				u32 tmp = I915_READ(PRB0_CTL);
+				if (tmp & RING_WAIT) {
+					I915_WRITE(PRB0_CTL, tmp);
+					POSTING_READ(PRB0_CTL);
+					goto out;
+				}
+			}
+
 			i915_handle_error(dev, true);
 			return;
 		}
@@ -1384,6 +1399,7 @@ void i915_hangcheck_elapsed(unsigned long data)
 		dev_priv->last_instdone1 = instdone1;
 	}
 
+out:
 	/* Reset timer case chip hangs without another request being added */
 	mod_timer(&dev_priv->hangcheck_timer, jiffies + DRM_I915_HANGCHECK_PERIOD);
 }