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 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup
Date: Wed, 25 Aug 2021 17:41:36 -0700 [thread overview]
Message-ID: <20210826004136.GA7677@jons-linux-dev-box> (raw)
In-Reply-To: <b0a58b7b-25bc-c76c-8b6c-41ae81c3e629@intel.com>
On Wed, Aug 25, 2021 at 05:44:11PM -0700, Daniele Ceraolo Spurio wrote:
>
>
> On 8/18/2021 11:16 PM, Matthew Brost wrote:
> > Lock the xarray and take ref to the context if needed.
> >
> > v2:
> > (Checkpatch)
> > - Add new line after declaration
> > (Daniel Vetter)
> > - Correct put / get accounting in xa_for_loops
> >
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > ---
> > .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 103 +++++++++++++++---
> > 1 file changed, 88 insertions(+), 15 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 509b298e7cf3..5f77f25322ca 100644
> > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > @@ -606,8 +606,18 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
> > unsigned long index, flags;
> > bool pending_disable, pending_enable, deregister, destroyed, banned;
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > xa_for_each(&guc->context_lookup, index, ce) {
> > - spin_lock_irqsave(&ce->guc_state.lock, flags);
> > + /*
> > + * Corner case where the ref count on the object is zero but and
> > + * deregister G2H was lost. In this case we don't touch the ref
> > + * count and finish the destroy of the context.
> > + */
> > + bool do_put = kref_get_unless_zero(&ce->ref);
> > +
> > + xa_unlock(&guc->context_lookup);
> > +
> > + spin_lock(&ce->guc_state.lock);
> > /*
> > * Once we are at this point submission_disabled() is guaranteed
> > @@ -623,7 +633,9 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
> > banned = context_banned(ce);
> > init_sched_state(ce);
> > - spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> > + spin_unlock(&ce->guc_state.lock);
> > +
> > + GEM_BUG_ON(!do_put && !destroyed);
> > if (pending_enable || destroyed || deregister) {
> > decr_outstanding_submission_g2h(guc);
> > @@ -646,13 +658,19 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
> > }
> > intel_context_sched_disable_unpin(ce);
> > decr_outstanding_submission_g2h(guc);
> > - spin_lock_irqsave(&ce->guc_state.lock, flags);
> > +
> > + spin_lock(&ce->guc_state.lock);
> > guc_blocked_fence_complete(ce);
> > - spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> > + spin_unlock(&ce->guc_state.lock);
> > intel_context_put(ce);
> > }
> > +
> > + if (do_put)
> > + intel_context_put(ce);
>
> is it safe to do the put outside the xa_lock, in case the refcount goes to
> zero with this? I know it is unlikely because the refcount was > 0 if do_put
> is true, but it might've gone down between us checking earlier and now.
>
It is safe as xa_for_each indicates it is safe to destroy / delete
objects from the array while traversing it.
> > + xa_lock(&guc->context_lookup);
> > }
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > }
> > static inline bool
> > @@ -873,16 +891,29 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
> > {
> > struct intel_context *ce;
> > unsigned long index;
> > + unsigned long flags;
> > if (unlikely(!guc_submission_initialized(guc))) {
> > /* Reset called during driver load? GuC not yet initialised! */
> > return;
> > }
> > - xa_for_each(&guc->context_lookup, index, ce)
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > + xa_for_each(&guc->context_lookup, index, ce) {
> > + if (!kref_get_unless_zero(&ce->ref))
> > + continue;
> > +
> > + xa_unlock(&guc->context_lookup);
> > +
> > if (intel_context_is_pinned(ce))
> > __guc_reset_context(ce, stalled);
> > + intel_context_put(ce);
> > +
> > + xa_lock(&guc->context_lookup);
> > + }
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > +
> > /* GuC is blown away, drop all references to contexts */
> > xa_destroy(&guc->context_lookup);
> > }
> > @@ -957,11 +988,24 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
> > {
> > struct intel_context *ce;
> > unsigned long index;
> > + unsigned long flags;
> > +
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > + xa_for_each(&guc->context_lookup, index, ce) {
> > + if (!kref_get_unless_zero(&ce->ref))
> > + continue;
> > +
> > + xa_unlock(&guc->context_lookup);
> > - xa_for_each(&guc->context_lookup, index, ce)
> > if (intel_context_is_pinned(ce))
> > guc_cancel_context_requests(ce);
> > + intel_context_put(ce);
> > +
> > + xa_lock(&guc->context_lookup);
> > + }
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > +
> > guc_cancel_sched_engine_requests(guc->sched_engine);
> > /* GuC is blown away, drop all references to contexts */
> > @@ -2850,21 +2894,28 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
> > struct intel_context *ce;
> > struct i915_request *rq;
> > unsigned long index;
> > + unsigned long flags;
> > /* Reset called during driver load? GuC not yet initialised! */
> > if (unlikely(!guc_submission_initialized(guc)))
> > return;
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > xa_for_each(&guc->context_lookup, index, ce) {
> > - if (!intel_context_is_pinned(ce))
> > + if (!kref_get_unless_zero(&ce->ref))
> > continue;
> > + xa_unlock(&guc->context_lookup);
> > +
> > + if (!intel_context_is_pinned(ce))
> > + goto next;
> > +
> > if (intel_engine_is_virtual(ce->engine)) {
> > if (!(ce->engine->mask & engine->mask))
> > - continue;
> > + goto next;
> > } else {
> > if (ce->engine != engine)
> > - continue;
> > + goto next;
> > }
> > list_for_each_entry(rq, &ce->guc_active.requests, sched.link) {
> > @@ -2874,9 +2925,17 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
> > intel_engine_set_hung_context(engine, ce);
> > /* Can only cope with one hang at a time... */
> > - return;
> > + intel_context_put(ce);
> > + xa_lock(&guc->context_lookup);
> > + goto done;
> > }
> > +next:
> > + intel_context_put(ce);
> > + xa_lock(&guc->context_lookup);
> > +
>
> nit: extra newline
>
Checkpatch got that one too. Already fixed.
Matt
> Daniele
>
> > }
> > +done:
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > }
> > void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
> > @@ -2892,23 +2951,34 @@ void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
> > if (unlikely(!guc_submission_initialized(guc)))
> > return;
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > xa_for_each(&guc->context_lookup, index, ce) {
> > - if (!intel_context_is_pinned(ce))
> > + if (!kref_get_unless_zero(&ce->ref))
> > continue;
> > + xa_unlock(&guc->context_lookup);
> > +
> > + if (!intel_context_is_pinned(ce))
> > + goto next;
> > +
> > if (intel_engine_is_virtual(ce->engine)) {
> > if (!(ce->engine->mask & engine->mask))
> > - continue;
> > + goto next;
> > } else {
> > if (ce->engine != engine)
> > - continue;
> > + goto next;
> > }
> > - spin_lock_irqsave(&ce->guc_active.lock, flags);
> > + spin_lock(&ce->guc_active.lock);
> > intel_engine_dump_active_requests(&ce->guc_active.requests,
> > hung_rq, m);
> > - spin_unlock_irqrestore(&ce->guc_active.lock, flags);
> > + spin_unlock(&ce->guc_active.lock);
> > +
> > +next:
> > + intel_context_put(ce);
> > + xa_lock(&guc->context_lookup);
> > }
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > }
> > void intel_guc_submission_print_info(struct intel_guc *guc,
> > @@ -2962,7 +3032,9 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
> > {
> > struct intel_context *ce;
> > unsigned long index;
> > + unsigned long flags;
> > + xa_lock_irqsave(&guc->context_lookup, flags);
> > xa_for_each(&guc->context_lookup, index, ce) {
> > drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id);
> > drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
> > @@ -2981,6 +3053,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
> > guc_log_context_priority(p, ce);
> > }
> > + xa_unlock_irqrestore(&guc->context_lookup, flags);
> > }
> > static struct intel_context *
>
next prev parent reply other threads:[~2021-08-26 0:46 UTC|newest]
Thread overview: 76+ 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
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 [this message]
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 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup Matthew Brost
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=20210826004136.GA7677@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).