| Message ID | 20230819024525.2056048-1-paul.gortmaker@windriver.com |
|---|---|
| Headers | show |
| Series | Backport i915 reset fix from v6.4-rt | expand |
On 2023-08-18 22:45:24 [-0400], paul.gortmaker@windriver.com wrote: > From: Paul Gortmaker <paul.gortmaker@windriver.com> Hi Paul, > However, the original regression was reported on v5.15-rt. This closes > the loop by backporting the v6.4-rt change to v5.15-rt/v6.1-rt -- as it > turns out, the same backport applies cleanly to both baselines. Thanks for the ping. I've sent a backport request https://lore.kernel.org/all/20230727105040.4V9DQ5pM@linutronix.de/ which includes the patch. It didn't go very so far but I am full of hope ;) Sebastian
On 8/23/23 09:39, Sebastian Andrzej Siewior wrote: > On 2023-08-18 22:45:24 [-0400], paul.gortmaker@windriver.com wrote: >> From: Paul Gortmaker <paul.gortmaker@windriver.com> > Hi Paul, > >> However, the original regression was reported on v5.15-rt. This closes >> the loop by backporting the v6.4-rt change to v5.15-rt/v6.1-rt -- as it >> turns out, the same backport applies cleanly to both baselines. > Thanks for the ping. I've sent a backport request > https://lore.kernel.org/all/20230727105040.4V9DQ5pM@linutronix.de/ > > which includes the patch. It didn't go very so far but I am full of hope > ;) > > Sebastian Hi Paul, I will put this on my list to backport to v5.15-rt stable. I usually wait until requested backports land in the next newer version, which is v6.1-rt, before I apply to v5.15-rt. Thanks, Joe
On 8/23/23 09:39, Sebastian Andrzej Siewior wrote: > On 2023-08-18 22:45:24 [-0400], paul.gortmaker@windriver.com wrote: >> From: Paul Gortmaker <paul.gortmaker@windriver.com> > Hi Paul, > >> However, the original regression was reported on v5.15-rt. This closes >> the loop by backporting the v6.4-rt change to v5.15-rt/v6.1-rt -- as it >> turns out, the same backport applies cleanly to both baselines. > Thanks for the ping. I've sent a backport request > https://lore.kernel.org/all/20230727105040.4V9DQ5pM@linutronix.de/ > > which includes the patch. It didn't go very so far but I am full of hope > ;) > > Sebastian Hi Paul, I just announced a release candidate that has this patch. The version is: v5.15.133-rt70-rc1. If there are no negative reports, this will be the next v5.15-rt release, which only contains the patches in the announcement. Thanks, Joe
From: Paul Gortmaker <paul.gortmaker@windriver.com> I'd originally reported an i915 regression caused by a linux-stable backport, and then later posted an RFC fix for it: https://lore.kernel.org/linux-rt-users/ZJTuDi1HNp9L2zxY@windriver.com/ That eventually led to further discussion and an eventual fix from Tvrtko that Sebastian put into the v6.4-rt queue, which is great. However, the original regression was reported on v5.15-rt. This closes the loop by backporting the v6.4-rt change to v5.15-rt/v6.1-rt -- as it turns out, the same backport applies cleanly to both baselines. The only small change required is to fix up the context a bit in the 5th and final chunk, because kernel versions before v6.4 dont have the commit b7d70b8b06ed ("drm/i915/gsc: implement wa 14015076503") Paul. -- Cc: Clark Williams <williams@redhat.com> [6.1-rt] Cc: Joseph Salisbury <joseph.salisbury@canonical.com> [5.15-rt] --- Tvrtko Ursulin (1): drm/i915: Do not disable preemption for resets drivers/gpu/drm/i915/gt/intel_reset.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)