Re: [Intel-gfx] [PATCH v2] drm/i915: add register read IOCTL

2012-07-18 Thread Daniel Vetter
On Wed, Jul 18, 2012 at 10:22:01AM -0700, Ben Widawsky wrote: > On Wed, 18 Jul 2012 10:14:46 -0700 > Eric Anholt wrote: > > > Ben Widawsky writes: > > > > > The interface's immediate purpose is to do synchronous timestamp queries > > > as required by GL_TIMESTAMP. The GPU has a register for rea

Re: [Intel-gfx] [PATCH v2] drm/i915: add register read IOCTL

2012-07-18 Thread Ben Widawsky
On Wed, 18 Jul 2012 10:14:46 -0700 Eric Anholt wrote: > Ben Widawsky writes: > > > The interface's immediate purpose is to do synchronous timestamp queries > > as required by GL_TIMESTAMP. The GPU has a register for reading the > > timestamp but because that would normally require root access t

Re: [Intel-gfx] [PATCH v2] drm/i915: add register read IOCTL

2012-07-18 Thread Eric Anholt
Ben Widawsky writes: > The interface's immediate purpose is to do synchronous timestamp queries > as required by GL_TIMESTAMP. The GPU has a register for reading the > timestamp but because that would normally require root access through > libpciaccess, the IOCTL can provide this service instead.

[Intel-gfx] [PATCH v2] drm/i915: add register read IOCTL

2012-07-12 Thread Ben Widawsky
The interface's immediate purpose is to do synchronous timestamp queries as required by GL_TIMESTAMP. The GPU has a register for reading the timestamp but because that would normally require root access through libpciaccess, the IOCTL can provide this service instead. Currently the implementation