[PATCH] drm/i915: Use LRI to update the semaphore registers

[PATCH] drm/i915: Use LRI to update the semaphore registers

[Chris Wilson]

The bspec was recently updated to remove the ability to update the
semaphore using the MI_SEMAPHORE_BOX command, the ability to wait upon
the semaphore value remained. Instead the advice is to update the
register using the MI_LOAD_REGISTER_IMM command. In cursory testing,
semaphores continue to function - the question is whether this fixes
some of the deadlocks where the semaphore registers contained stale
values?

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel J Blueman <daniel@quora.org>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c |    7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ee4abc5..dd2e7db 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -554,12 +554,9 @@ update_mboxes(struct intel_ring_buffer *ring,
 	    u32 seqno,
 	    u32 mmio_offset)
 {
-	intel_ring_emit(ring, MI_SEMAPHORE_MBOX |
-			      MI_SEMAPHORE_GLOBAL_GTT |
-			      MI_SEMAPHORE_REGISTER |
-			      MI_SEMAPHORE_UPDATE);
-	intel_ring_emit(ring, seqno);
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
 	intel_ring_emit(ring, mmio_offset);
+	intel_ring_emit(ring, seqno);
 }
 
 /**
-- 
1.7.10.4

Re: [PATCH] drm/i915: Use LRI to update the semaphore registers

[Ben Widawsky]

On Wed, 14 Nov 2012 09:15:14 +0000
Chris Wilson <chris@chris-wilson.co.uk> wrote:

> The bspec was recently updated to remove the ability to update the
> semaphore using the MI_SEMAPHORE_BOX command, the ability to wait upon
> the semaphore value remained. Instead the advice is to update the
> register using the MI_LOAD_REGISTER_IMM command. In cursory testing,
> semaphores continue to function - the question is whether this fixes
> some of the deadlocks where the semaphore registers contained stale
> values?
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Daniel J Blueman <daniel@quora.org>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
> ---
>  drivers/gpu/drm/i915/intel_ringbuffer.c |    7 ++-----
>  1 file changed, 2 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index ee4abc5..dd2e7db 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -554,12 +554,9 @@ update_mboxes(struct intel_ring_buffer *ring,
>  	    u32 seqno,
>  	    u32 mmio_offset)
>  {
> -	intel_ring_emit(ring, MI_SEMAPHORE_MBOX |
> -			      MI_SEMAPHORE_GLOBAL_GTT |
> -			      MI_SEMAPHORE_REGISTER |
> -			      MI_SEMAPHORE_UPDATE);
> -	intel_ring_emit(ring, seqno);
> +	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
>  	intel_ring_emit(ring, mmio_offset);
> +	intel_ring_emit(ring, seqno);
>  }
>  
>  /**



-- 
Ben Widawsky, Intel Open Source Technology Center

Re: [PATCH] drm/i915: Use LRI to update the semaphore registers

[Ben Widawsky]

On Wed, 14 Nov 2012 11:06:42 -0800
Ben Widawsky <ben@bwidawsk.net> wrote:

> On Wed, 14 Nov 2012 09:15:14 +0000
> Chris Wilson <chris@chris-wilson.co.uk> wrote:
> 
> > The bspec was recently updated to remove the ability to update the
> > semaphore using the MI_SEMAPHORE_BOX command, the ability to wait upon
> > the semaphore value remained. Instead the advice is to update the
> > register using the MI_LOAD_REGISTER_IMM command. In cursory testing,
> > semaphores continue to function - the question is whether this fixes
> > some of the deadlocks where the semaphore registers contained stale
> > values?
> > 
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Daniel J Blueman <daniel@quora.org>
> Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Tested-by: Ben Widawsky <ben@bwidawsk.net>
 
> > ---
> >  drivers/gpu/drm/i915/intel_ringbuffer.c |    7 ++-----
> >  1 file changed, 2 insertions(+), 5 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > index ee4abc5..dd2e7db 100644
> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > @@ -554,12 +554,9 @@ update_mboxes(struct intel_ring_buffer *ring,
> >  	    u32 seqno,
> >  	    u32 mmio_offset)
> >  {
> > -	intel_ring_emit(ring, MI_SEMAPHORE_MBOX |
> > -			      MI_SEMAPHORE_GLOBAL_GTT |
> > -			      MI_SEMAPHORE_REGISTER |
> > -			      MI_SEMAPHORE_UPDATE);
> > -	intel_ring_emit(ring, seqno);
> > +	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
> >  	intel_ring_emit(ring, mmio_offset);
> > +	intel_ring_emit(ring, seqno);
> >  }
> >  
> >  /**
> 
> 
> 



-- 
Ben Widawsky, Intel Open Source Technology Center

Re: [PATCH] drm/i915: Use LRI to update the semaphore registers

[Daniel Vetter]

On Thu, Nov 15, 2012 at 09:14:48AM -0800, Ben Widawsky wrote:
> On Wed, 14 Nov 2012 11:06:42 -0800
> Ben Widawsky <ben@bwidawsk.net> wrote:
> 
> > On Wed, 14 Nov 2012 09:15:14 +0000
> > Chris Wilson <chris@chris-wilson.co.uk> wrote:
> > 
> > > The bspec was recently updated to remove the ability to update the
> > > semaphore using the MI_SEMAPHORE_BOX command, the ability to wait upon
> > > the semaphore value remained. Instead the advice is to update the
> > > register using the MI_LOAD_REGISTER_IMM command. In cursory testing,
> > > semaphores continue to function - the question is whether this fixes
> > > some of the deadlocks where the semaphore registers contained stale
> > > values?
> > > 
> > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > > Cc: Daniel J Blueman <daniel@quora.org>
> > Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
> Tested-by: Ben Widawsky <ben@bwidawsk.net>

I seem to have forgotten to mention that this is merged. Bad, bad me ...

Thanks for the patch & review.
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch