[Intel-gfx] [PATCH 00/13] Gen7 batch buffer command parser

Volkin, Bradley D bradley.d.volkin at intel.com
Wed Mar 5 17:59:56 CET 2014


On Wed, Mar 05, 2014 at 02:46:35AM -0800, Daniel Vetter wrote:
> On Tue, Feb 18, 2014 at 10:15:44AM -0800, bradley.d.volkin at intel.com wrote:
> > From: Brad Volkin <bradley.d.volkin at intel.com>
> > 3) Coherency. I've previously found a coherency issue on VLV when reading the
> >    batch buffer from the CPU during execbuffer2. Userspace writes the batch via
> >    pwrite fast path before calling execbuffer2. The parser reads stale data.
> >    This works fine on IVB and HSW, so I believe it's an LLC vs. non-LLC issue.
> >    It's possible that the shmem pread refactoring fixes this, I just have not
> >    been able to retest due to lack of a VLV system.
> 
> Is it still true that we need to test this on vlv? The shmem_pread path
> really should have fixed this ... Otherwise I think this looks ready to go
> in, I'll pester Jani for the review.

Yes, I still don't have a system to test on.

Brad

> 
> Thanks, Daniel
> 
> > 
> > v2:
> > - Significantly reorder series
> > - Scan secure batches (i.e. I915_EXEC_SECURE)
> > - Check that parser tables are sorted during init
> > - Fixed gem_cpu_reloc regression
> > - HAS_CMD_PARSER -> CMD_PARSER_VERSION getparam
> > - Additional tests
> > 
> > v3:
> > - Don't actually send batches as secure yet
> > - Improved documentation and commenting
> > - Many other small cleanups throughout
> > 
> > Brad Volkin (13):
> >   drm/i915: Refactor shmem pread setup
> >   drm/i915: Implement command buffer parsing logic
> >   drm/i915: Initial command parser table definitions
> >   drm/i915: Reject privileged commands
> >   drm/i915: Allow some privileged commands from master
> >   drm/i915: Add register whitelists for mesa
> >   drm/i915: Add register whitelist for DRM master
> >   drm/i915: Enable register whitelist checks
> >   drm/i915: Reject commands that explicitly generate interrupts
> >   drm/i915: Enable PPGTT command parser checks
> >   drm/i915: Reject commands that would store to global HWS page
> >   drm/i915: Add a CMD_PARSER_VERSION getparam
> >   drm/i915: Enable command parsing by default
> > 
> >  drivers/gpu/drm/i915/Makefile              |   1 +
> >  drivers/gpu/drm/i915/i915_cmd_parser.c     | 918 +++++++++++++++++++++++++++++
> >  drivers/gpu/drm/i915/i915_dma.c            |   3 +
> >  drivers/gpu/drm/i915/i915_drv.h            | 103 ++++
> >  drivers/gpu/drm/i915/i915_gem.c            |  51 +-
> >  drivers/gpu/drm/i915/i915_gem_execbuffer.c |  18 +
> >  drivers/gpu/drm/i915/i915_params.c         |   5 +
> >  drivers/gpu/drm/i915/i915_reg.h            |  96 +++
> >  drivers/gpu/drm/i915/intel_ringbuffer.c    |   2 +
> >  drivers/gpu/drm/i915/intel_ringbuffer.h    |  32 +
> >  include/uapi/drm/i915_drm.h                |   1 +
> >  11 files changed, 1216 insertions(+), 14 deletions(-)
> >  create mode 100644 drivers/gpu/drm/i915/i915_cmd_parser.c
> > 
> > -- 
> > 1.8.3.2
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx at lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
> 
> -- 
> Daniel Vetter
> Software Engineer, Intel Corporation
> +41 (0) 79 365 57 48 - http://blog.ffwll.ch



More information about the Intel-gfx mailing list