From: Matthew Brost <matthew.brost@intel.com>
To: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
daniel.vetter@ffwll.ch
Subject: Re: [Intel-gfx] [PATCH 06/27] drm/i915/guc: Workaround reset G2H is received after schedule done G2H
Date: Tue, 24 Aug 2021 21:05:18 -0700 [thread overview]
Message-ID: <20210825040518.GA21209@jons-linux-dev-box> (raw)
In-Reply-To: <5015ca18-7237-b101-8afa-0cd17ef98aed@intel.com>
On Tue, Aug 24, 2021 at 04:31:21PM -0700, Daniele Ceraolo Spurio wrote:
>
>
> On 8/18/2021 11:16 PM, Matthew Brost wrote:
> > If the context is reset as a result of the request cancelation the
> > context reset G2H is received after schedule disable done G2H which is
> > likely the wrong order. The schedule disable done G2H release the
> > waiting request cancelation code which resubmits the context. This races
> > with the context reset G2H which also wants to resubmit the context but
> > in this case it really should be a NOP as request cancelation code owns
> > the resubmit. Use some clever tricks of checking the context state to
> > seal this race until if / when the GuC firmware is fixed.
>
> Did you raise this with the GuC team? If it's a GuC issue we definitely want
> a fix there ASAP so we can drop any i915-side WAs.
>
Yep, def an issue with the GuC firmware behavior. Will get fixed, just
not sure when.
> >
> > v2:
> > (Checkpatch)
> > - Fix typos
> >
> > Fixes: 62eaf0ae217d ("drm/i915/guc: Support request cancellation")
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > Cc: <stable@vger.kernel.org>
> > ---
> > .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 43 ++++++++++++++++---
> > 1 file changed, 37 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > index e4a099f8f820..8f7a11e65ef5 100644
> > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > @@ -832,17 +832,35 @@ __unwind_incomplete_requests(struct intel_context *ce)
> > static void __guc_reset_context(struct intel_context *ce, bool stalled)
> > {
> > struct i915_request *rq;
> > + unsigned long flags;
> > u32 head;
> > + bool skip = false;
> > intel_context_get(ce);
> > /*
> > - * GuC will implicitly mark the context as non-schedulable
> > - * when it sends the reset notification. Make sure our state
> > - * reflects this change. The context will be marked enabled
> > - * on resubmission.
> > + * GuC will implicitly mark the context as non-schedulable when it sends
> > + * the reset notification. Make sure our state reflects this change. The
> > + * context will be marked enabled on resubmission.
> > + *
> > + * XXX: If the context is reset as a result of the request cancellation
> > + * this G2H is received after the schedule disable complete G2H which is
> > + * likely wrong as this creates a race between the request cancellation
> > + * code re-submitting the context and this G2H handler. This likely
> > + * should be fixed in the GuC but until if / when that gets fixed we
> > + * need to workaround this. Convert this function to a NOP if a pending
> > + * enable is in flight as this indicates that a request cancellation has
> > + * occurred.
> > */
>
> IMO this comment sounds like we're not clear on expected behavior. Either
> the ordering is wrong, in which case we have a GuC bug and this is a
> temporary WA, or the ordering is allowed and we need to cope with it. The
> way the comment is written sounds like we're not sure.
>
Comments written prior to confirmation that GuC behavior was wrong, will
reword.
> Code changes look ok.
>
Ty. I'll think we have to carry this until we upgrade the GuC firmware
with a the proper behavior - until then without this workaround
canceling non-preemptable requests is 100% broken, hence why I added a
selftest. Will add a FIXME / XXX comment so we can remove this in the
future.
Matt
> Daniele
>
> > - clr_context_enabled(ce);
> > + spin_lock_irqsave(&ce->guc_state.lock, flags);
> > + if (likely(!context_pending_enable(ce))) {
> > + clr_context_enabled(ce);
> > + } else {
> > + skip = true;
> > + }
> > + spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> > + if (unlikely(skip))
> > + goto out_put;
> > rq = intel_context_find_active_request(ce);
> > if (!rq) {
> > @@ -861,6 +879,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
> > out_replay:
> > guc_reset_state(ce, head, stalled);
> > __unwind_incomplete_requests(ce);
> > +out_put:
> > intel_context_put(ce);
> > }
> > @@ -1605,6 +1624,13 @@ static void guc_context_cancel_request(struct intel_context *ce,
> > guc_reset_state(ce, intel_ring_wrap(ce->ring, rq->head),
> > true);
> > }
> > +
> > + /*
> > + * XXX: Racey if context is reset, see comment in
> > + * __guc_reset_context().
> > + */
> > + flush_work(&ce_to_guc(ce)->ct.requests.worker);
> > +
> > guc_context_unblock(ce);
> > }
> > }
> > @@ -2719,7 +2745,12 @@ static void guc_handle_context_reset(struct intel_guc *guc,
> > {
> > trace_intel_context_reset(ce);
> > - if (likely(!intel_context_is_banned(ce))) {
> > + /*
> > + * XXX: Racey if request cancellation has occurred, see comment in
> > + * __guc_reset_context().
> > + */
> > + if (likely(!intel_context_is_banned(ce) &&
> > + !context_blocked(ce))) {
> > capture_error_state(guc, ce);
> > guc_context_replay(ce);
> > }
>
next prev parent reply other threads:[~2021-08-25 4:10 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-19 6:16 [Intel-gfx] [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 01/27] drm/i915/guc: Fix blocked context accounting Matthew Brost
2021-08-24 23:24 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 02/27] drm/i915/guc: Fix outstanding G2H accounting Matthew Brost
2021-08-19 21:31 ` Daniele Ceraolo Spurio
2021-08-19 21:30 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 03/27] drm/i915/guc: Unwind context requests in reverse order Matthew Brost
2021-08-19 23:54 ` Daniele Ceraolo Spurio
2021-08-19 23:53 ` Matthew Brost
2021-08-20 0:03 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 04/27] drm/i915/guc: Don't drop ce->guc_active.lock when unwinding context Matthew Brost
2021-08-20 0:01 ` Daniele Ceraolo Spurio
2021-08-19 23:58 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 05/27] drm/i915/guc: Process all G2H message at once in work queue Matthew Brost
2021-08-20 0:06 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 06/27] drm/i915/guc: Workaround reset G2H is received after schedule done G2H Matthew Brost
2021-08-24 23:31 ` Daniele Ceraolo Spurio
2021-08-25 4:05 ` Matthew Brost [this message]
2021-08-19 6:16 ` [Intel-gfx] [PATCH 07/27] Revert "drm/i915/gt: Propagate change in error status to children on unhold" Matthew Brost
2021-08-20 19:47 ` Jason Ekstrand
2021-08-19 6:16 ` [Intel-gfx] [PATCH 08/27] drm/i915/selftests: Add a cancel request selftest that triggers a reset Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 09/27] drm/i915/guc: Kick tasklet after queuing a request Matthew Brost
2021-08-20 18:31 ` Daniele Ceraolo Spurio
2021-08-20 18:36 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 10/27] drm/i915/guc: Don't enable scheduling on a banned context, guc_id invalid, not registered Matthew Brost
2021-08-20 18:42 ` Daniele Ceraolo Spurio
2021-08-20 18:42 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 11/27] drm/i915/selftests: Fix memory corruption in live_lrc_isolation Matthew Brost
2021-08-25 0:07 ` Daniele Ceraolo Spurio
2021-08-25 20:03 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 12/27] drm/i915/selftests: Add initial GuC selftest for scrubbing lost G2H Matthew Brost
2021-08-25 0:58 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 13/27] drm/i915/guc: Take context ref when cancelling request Matthew Brost
2021-08-21 0:07 ` Daniele Ceraolo Spurio
2021-08-24 15:42 ` Matthew Brost
2021-08-25 1:21 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 14/27] drm/i915/guc: Don't touch guc_state.sched_state without a lock Matthew Brost
2021-08-25 1:20 ` Daniele Ceraolo Spurio
2021-08-25 1:44 ` Matthew Brost
2021-08-25 1:51 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 15/27] drm/i915/guc: Reset LRC descriptor if register returns -ENODEV Matthew Brost
2021-08-21 0:14 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 16/27] drm/i915: Allocate error capture in nowait context Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 17/27] drm/i915/guc: Flush G2H work queue during reset Matthew Brost
2021-08-21 0:25 ` Daniele Ceraolo Spurio
2021-08-24 15:44 ` Matthew Brost
2021-08-25 1:22 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 18/27] drm/i915/guc: Release submit fence from an irq_work Matthew Brost
2021-08-25 1:44 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 19/27] drm/i915/guc: Move guc_blocked fence to struct guc_state Matthew Brost
2021-08-21 0:30 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 20/27] drm/i915/guc: Rework and simplify locking Matthew Brost
2021-08-25 16:52 ` Daniele Ceraolo Spurio
2021-08-25 19:22 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup Matthew Brost
2021-08-26 0:44 ` Daniele Ceraolo Spurio
2021-08-26 0:41 ` Matthew Brost
2021-08-26 0:48 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 22/27] drm/i915/guc: Drop pin count check trick between sched_disable and re-pin Matthew Brost
2021-08-26 0:50 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 23/27] drm/i915/guc: Move GuC priority fields in context under guc_active Matthew Brost
2021-08-25 21:51 ` Daniele Ceraolo Spurio
2021-08-25 22:53 ` Matthew Brost
2021-08-25 23:04 ` Matthew Brost
2021-08-19 6:16 ` [Intel-gfx] [PATCH 24/27] drm/i915/guc: Move fields protected by guc->contexts_lock into sub structure Matthew Brost
2021-08-25 2:00 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 25/27] drm/i915/guc: Drop guc_active move everything into guc_state Matthew Brost
2021-08-26 0:54 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 26/27] drm/i915/guc: Add GuC kernel doc Matthew Brost
2021-08-26 1:03 ` Daniele Ceraolo Spurio
2021-08-19 6:16 ` [Intel-gfx] [PATCH 27/27] drm/i915/guc: Drop static inline functions intel_guc_submission.c Matthew Brost
2021-08-19 7:18 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Clean up GuC CI failures, simplify locking, and kernel DOC (rev3) Patchwork
2021-08-19 7:20 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-08-19 7:51 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-08-19 9:08 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2021-08-26 3:23 [Intel-gfx] [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-26 3:23 ` [Intel-gfx] [PATCH 06/27] drm/i915/guc: Workaround reset G2H is received after schedule done G2H Matthew Brost
2021-08-26 23:11 ` Daniele Ceraolo Spurio
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210825040518.GA21209@jons-linux-dev-box \
--to=matthew.brost@intel.com \
--cc=daniel.vetter@ffwll.ch \
--cc=daniele.ceraolospurio@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).