[Intel-gfx] [PATCH] drm/i915/perf: Do not clear pollin for small user read buffers

[Dixit, Ashutosh]

On Fri, 03 Apr 2020 09:17:14 -0700, Chris Wilson wrote:
>
> Quoting Ashutosh Dixit (2020-04-03 02:01:20)
> > It is wrong to block the user thread in the next poll when OA data is
> > already available which could not fit in the user buffer provided in
> > the previous read. In several cases the exact user buffer size is not
> > known. Blocking user space in poll can lead to data loss when the
> > buffer size used is smaller than the available data.
> >
> > This change fixes this issue and allows user space to read all OA data
> > even when using a buffer size smaller than the available data using
> > multiple non-blocking reads rather than staying blocked in poll till
> > the next timer interrupt.
> >
> > v2: Fix ret value for blocking reads (Umesh)
> > v3: Mistake during patch send (Ashutosh)
> > v4: Remove -EAGAIN from comment (Umesh)
> > v5: Improve condition for clearing pollin and return (Lionel)
> > v6: Improve blocking read loop and other cleanups (Lionel)
> > v7: Added Cc stable
> >
> > Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa at intel.com>
> > Cc: <stable at vger.kernel.org>
> > Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
> > Signed-off-by: Ashutosh Dixit <ashutosh.dixit at intel.com>
>
> Did you manage to devise a test case? It is nice (some might say
> important) to pair a patch for stable with its regression test.

Yes there is a test case here:

https://patchwork.freedesktop.org/series/75100/#rev3

Lionel verified that it is fails on stable kernels here:

https://patchwork.freedesktop.org/patch/358873/?series=75100&rev=1

Thanks!
--
Ashutosh