drm/i915: Change GEM throttling to be 20ms like the comment says.

keithp didn't like the original 20ms plan because a cooperative client could
be starved by an uncooperative client.  There may even have been problems
with cooperative clients versus cooperative clients.  So keithp changed
throttle to just wait for the second to last seqno emitted by that client.
It worked well, until we started getting more round-trips to the server
due to DRI2 -- the server throttles in BlockHandler, and so if you did more
than one round trip after finishing your frame, you'd end up unintentionally
syncing to the swap.

Fix this by keeping track of the client's requests, so the client can wait
when it has an outstanding request over 20ms old.  This should have
non-starving behavior, good behavior in the presence of restarts, and less
waiting.  Improves high-settings openarena performance on my GM45 by 50%.

Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>

1 files changed, 5 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fcaa5444daa0..e0fac5f62c69 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -498,13 +498,16 @@ struct drm_i915_gem_request {
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
+	/** global list entry for this request */
 	struct list_head list;
+
+	/** file_priv list entry for this request */
+	struct list_head client_list;
 };
 
 struct drm_i915_file_private {
 	struct {
-		uint32_t last_gem_seqno;
-		uint32_t last_gem_throttle_seqno;
+		struct list_head request_list;
 	} mm;
 };