Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-30 Thread Daniel Vetter
On Tue, Sep 30, 2014 at 04:58:54PM +0100, Tvrtko Ursulin wrote: > > > On 09/30/2014 03:57 PM, Chris Wilson wrote: > >On Tue, Sep 30, 2014 at 03:08:02PM +0100, Tvrtko Ursulin wrote: > >>From: Tvrtko Ursulin > >> > >>Write and reads following the block changed use engine specific use counters > >>

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-30 Thread Tvrtko Ursulin
On 09/30/2014 03:57 PM, Chris Wilson wrote: On Tue, Sep 30, 2014 at 03:08:02PM +0100, Tvrtko Ursulin wrote: From: Tvrtko Ursulin Write and reads following the block changed use engine specific use counters and unless that is matched here force wake use counting goes bad. Same force wake is a

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-30 Thread Chris Wilson
On Tue, Sep 30, 2014 at 03:08:02PM +0100, Tvrtko Ursulin wrote: > From: Tvrtko Ursulin > > Write and reads following the block changed use engine specific use counters > and unless that is matched here force wake use counting goes bad. Same > force wake is attempted to be taken twice which leads

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-30 Thread Damien Lespiau
On Tue, Sep 30, 2014 at 03:08:02PM +0100, Tvrtko Ursulin wrote: > From: Tvrtko Ursulin > > Write and reads following the block changed use engine specific use counters > and unless that is matched here force wake use counting goes bad. Same > force wake is attempted to be taken twice which leads

[Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-30 Thread Tvrtko Ursulin
From: Tvrtko Ursulin Write and reads following the block changed use engine specific use counters and unless that is matched here force wake use counting goes bad. Same force wake is attempted to be taken twice which leads to at least time outs. NOTE: Depending on feedback from hardware designer

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-25 Thread Damien Lespiau
On Thu, Sep 25, 2014 at 01:43:31PM +0100, Tvrtko Ursulin wrote: > > On 09/25/2014 01:05 PM, Mika Kuoppala wrote: > >Damien Lespiau writes: > > > >>On Thu, Sep 25, 2014 at 11:17:00AM +0100, Tvrtko Ursulin wrote: > >>>From: Tvrtko Ursulin > >>> > >>>Write and reads following the block changed use

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-25 Thread Tvrtko Ursulin
On 09/25/2014 01:05 PM, Mika Kuoppala wrote: Damien Lespiau writes: On Thu, Sep 25, 2014 at 11:17:00AM +0100, Tvrtko Ursulin wrote: From: Tvrtko Ursulin Write and reads following the block changed use engine specific use counters and unless that is matched here force wake use counting goes

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-25 Thread Mika Kuoppala
Damien Lespiau writes: > On Thu, Sep 25, 2014 at 11:17:00AM +0100, Tvrtko Ursulin wrote: >> From: Tvrtko Ursulin >> >> Write and reads following the block changed use engine specific use counters >> and unless that is matched here force wake use counting goes bad. Same >> force wake is attempte

Re: [Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-25 Thread Damien Lespiau
On Thu, Sep 25, 2014 at 11:17:00AM +0100, Tvrtko Ursulin wrote: > From: Tvrtko Ursulin > > Write and reads following the block changed use engine specific use counters > and unless that is matched here force wake use counting goes bad. Same > force wake is attempted to be taken twice which leads

[Intel-gfx] [PATCH] drm/i915/skl: Use correct use counters for force wakes

2014-09-25 Thread Tvrtko Ursulin
From: Tvrtko Ursulin Write and reads following the block changed use engine specific use counters and unless that is matched here force wake use counting goes bad. Same force wake is attempted to be taken twice which leads to at least time outs. Signed-off-by: Tvrtko Ursulin --- drivers/gpu/dr