dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: <intel-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: <daniele.ceraolospurio@intel.com>
Subject: [PATCH 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup
Date: Wed, 25 Aug 2021 20:23:21 -0700	[thread overview]
Message-ID: <20210826032327.18078-22-matthew.brost@intel.com> (raw)
In-Reply-To: <20210826032327.18078-1-matthew.brost@intel.com>

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
v3:
 (Checkpatch)
  - Extra new line

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 102 +++++++++++++++---
 1 file changed, 87 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 2aa25cc4ac4b..2c6a6453d332 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);
+		xa_lock(&guc->context_lookup);
 	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 static inline bool
@@ -871,16 +889,29 @@ 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);
 }
@@ -955,11 +986,24 @@ 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 */
@@ -2849,21 +2893,28 @@ 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) {
@@ -2873,9 +2924,16 @@ 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);
 	}
+done:
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
@@ -2891,23 +2949,34 @@ 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,
@@ -2961,7 +3030,9 @@ 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);
@@ -2980,6 +3051,7 @@ 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 *
-- 
2.32.0


  parent reply	other threads:[~2021-08-26  3:30 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-26  3:23 [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-26  3:23 ` [PATCH 01/27] drm/i915/guc: Fix blocked context accounting Matthew Brost
2021-08-26  3:23 ` [PATCH 02/27] drm/i915/guc: Fix outstanding G2H accounting Matthew Brost
2021-08-26 23:09   ` Daniele Ceraolo Spurio
2021-08-27  1:36     ` Matthew Brost
2021-08-26  3:23 ` [PATCH 03/27] drm/i915/guc: Unwind context requests in reverse order Matthew Brost
2021-08-26  3:23 ` [PATCH 04/27] drm/i915/guc: Don't drop ce->guc_active.lock when unwinding context Matthew Brost
2021-08-26  3:23 ` [PATCH 05/27] drm/i915/guc: Process all G2H message at once in work queue Matthew Brost
2021-08-26  3:23 ` [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
2021-08-26  3:23 ` [PATCH 07/27] Revert "drm/i915/gt: Propagate change in error status to children on unhold" Matthew Brost
2021-08-26  3:23 ` [PATCH 08/27] drm/i915/selftests: Add a cancel request selftest that triggers a reset Matthew Brost
2021-08-26  9:32   ` [Intel-gfx] " Tvrtko Ursulin
2021-08-26 14:00     ` Matthew Brost
2021-08-26  3:23 ` [PATCH 09/27] drm/i915/guc: Kick tasklet after queuing a request Matthew Brost
2021-08-26  3:23 ` [PATCH 10/27] drm/i915/guc: Don't enable scheduling on a banned context, guc_id invalid, not registered Matthew Brost
2021-08-26  3:23 ` [PATCH 11/27] drm/i915/guc: Copy whole golden context, set engine state size of subset Matthew Brost
2021-08-26 23:21   ` Daniele Ceraolo Spurio
2021-08-26 23:33   ` [Intel-gfx] " John Harrison
2021-08-26  3:23 ` [PATCH 12/27] drm/i915/selftests: Add initial GuC selftest for scrubbing lost G2H Matthew Brost
2021-08-26  3:23 ` [PATCH 13/27] drm/i915/guc: Take context ref when cancelling request Matthew Brost
2021-08-26  3:23 ` [PATCH 14/27] drm/i915/guc: Don't touch guc_state.sched_state without a lock Matthew Brost
2021-08-26  3:23 ` [PATCH 15/27] drm/i915/guc: Reset LRC descriptor if register returns -ENODEV Matthew Brost
2021-08-26  3:23 ` [PATCH 16/27] drm/i915: Allocate error capture in nowait context Matthew Brost
2021-08-26 16:18   ` [Intel-gfx] " Matthew Brost
2021-08-26 16:21   ` Daniel Vetter
2021-08-26  3:23 ` [PATCH 17/27] drm/i915/guc: Flush G2H work queue during reset Matthew Brost
2021-08-26  3:23 ` [PATCH 18/27] drm/i915/guc: Release submit fence from an irq_work Matthew Brost
2021-08-26  3:23 ` [PATCH 19/27] drm/i915/guc: Move guc_blocked fence to struct guc_state Matthew Brost
2021-08-26  3:23 ` [PATCH 20/27] drm/i915/guc: Rework and simplify locking Matthew Brost
2021-08-26  3:23 ` Matthew Brost [this message]
2021-08-26  3:23 ` [PATCH 22/27] drm/i915/guc: Drop pin count check trick between sched_disable and re-pin Matthew Brost
2021-08-26  3:23 ` [PATCH 23/27] drm/i915/guc: Move GuC priority fields in context under guc_active Matthew Brost
2021-08-26 23:26   ` Daniele Ceraolo Spurio
2021-08-26  3:23 ` [PATCH 24/27] drm/i915/guc: Move fields protected by guc->contexts_lock into sub structure Matthew Brost
2021-08-26  3:23 ` [PATCH 25/27] drm/i915/guc: Drop guc_active move everything into guc_state Matthew Brost
2021-08-26  3:23 ` [PATCH 26/27] drm/i915/guc: Add GuC kernel doc Matthew Brost
2021-08-31 19:04   ` [Intel-gfx] " John Harrison
2021-08-26  3:23 ` [PATCH 27/27] drm/i915/guc: Drop static inline functions intel_guc_submission.c Matthew Brost
2021-08-31 19:09   ` [Intel-gfx] " John Harrison
  -- strict thread matches above, loose matches on Subject: below --
2021-08-19  6:16 [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-19  6:16 ` [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=20210826032327.18078-22-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --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).