Re: [Intel-gfx] [PATCH 4/5] drm/i915: detect hang using per ring hangcheck_score

2013-05-27 Thread Mika Kuoppala
Ben Widawsky writes: > On Mon, May 13, 2013 at 04:32:12PM +0300, Mika Kuoppala wrote: >> Keep track of ring seqno progress and if there are no >> progress detected, declare hang. Use actual head (acthd) >> to distinguish between ring stuck and batchbuffer looping >> situation. Stuck ring will be

Re: [Intel-gfx] [PATCH 4/5] drm/i915: detect hang using per ring hangcheck_score

2013-05-26 Thread Ben Widawsky
On Mon, May 13, 2013 at 04:32:12PM +0300, Mika Kuoppala wrote: > Keep track of ring seqno progress and if there are no > progress detected, declare hang. Use actual head (acthd) > to distinguish between ring stuck and batchbuffer looping > situation. Stuck ring will be kicked to trigger progress. >

[Intel-gfx] [PATCH 4/5] drm/i915: detect hang using per ring hangcheck_score

2013-05-13 Thread Mika Kuoppala
Keep track of ring seqno progress and if there are no progress detected, declare hang. Use actual head (acthd) to distinguish between ring stuck and batchbuffer looping situation. Stuck ring will be kicked to trigger progress. v2: use atchd to detect stuck ring from loop (Ben Widawsky) v3: Use ac