[Intel-gfx] [PATCH] drm/i915: Disable gpu relocations

Daniel Vetter daniel at ffwll.ch
Thu May 27 11:22:45 UTC 2021


On Thu, May 27, 2021 at 01:16:13PM +0200, Maarten Lankhorst wrote:
> Op 2021-05-26 om 18:37 schreef Daniel Vetter:
> > Media userspace was the last userspace to still use them, and they
> > converted now too:
> >
> > https://github.com/intel/media-driver/commit/144020c37770083974bedf59902b70b8f444c799
> >
> > This means no reason anymore to make relocations faster than they've
> > been for the first 9 years of gem. This code was added in
> >
> > commit 7dd4f6729f9243bd7046c6f04c107a456bda38eb
> > Author: Chris Wilson <chris at chris-wilson.co.uk>
> > Date:   Fri Jun 16 15:05:24 2017 +0100
> >
> >     drm/i915: Async GPU relocation processing
> >
> > Furthermore there's pretty strong indications it's buggy, since the
> > code to use it by default as the only option had to be reverted:
> >
> > commit ad5d95e4d538737ed3fa25493777decf264a3011
> > Author: Dave Airlie <airlied at redhat.com>
> > Date:   Tue Sep 8 15:41:17 2020 +1000
> >
> >     Revert "drm/i915/gem: Async GPU relocations only"
> >
> > This code just disables gpu relocations, leaving the garbage
> > collection for later patches and more importantly, much less confusing
> > diff. Also given how much headaches this code has caused in the past,
> > letting this soak for a bit seems justified.
> >
> > Cc: Jon Bloomfield <jon.bloomfield at intel.com>
> > Signed-off-by: Daniel Vetter <daniel.vetter at intel.com>
> > Cc: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
> > Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> > Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
> > Cc: "Thomas Hellström" <thomas.hellstrom at linux.intel.com>
> > Cc: Matthew Auld <matthew.auld at intel.com>
> > Cc: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
> > Cc: Dave Airlie <airlied at redhat.com>
> > Cc: Jason Ekstrand <jason at jlekstrand.net>
> > ---
> >  .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 43 ++++++++-----------
> >  1 file changed, 18 insertions(+), 25 deletions(-)
> 
> Reviewed-by: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
> 
> Note that a lot of complexity may be removed with gpu relocations gone.
> Some igt tests might also start to fail, as they expect relocations to
> complete asynchronously.

Yeah I have the kernel side patch for that, at least in the execbuf code +
selftests. For igt I'm wawiting on CI to tell me what I all need to look
at and decide what to do with it.

> Is it kept in case we need to revive it?

I don't want to revive it, but I want to split the huge code changes from
the functional changes at least.
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch


More information about the Intel-gfx mailing list