intel-gfx.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: <daniel.vetter@ffwll.ch>
Subject: [Intel-gfx] [PATCH 19/22] drm/i915/guc: Proper xarray usage for contexts_lookup
Date: Mon, 16 Aug 2021 06:51:36 -0700	[thread overview]
Message-ID: <20210816135139.10060-20-matthew.brost@intel.com> (raw)
In-Reply-To: <20210816135139.10060-1-matthew.brost@intel.com>

Lock the xarray and take ref to the context if needed.

v2:
 (Checkpatch)
  - Add new line after declaration

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 84 ++++++++++++++++---
 1 file changed, 73 insertions(+), 11 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 ba19b99173fc..2ecb2f002bed 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -599,8 +599,18 @@ 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
@@ -616,7 +626,9 @@ 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) {
 			atomic_dec(&guc->outstanding_submission_g2h);
@@ -645,7 +657,12 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 
 			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
@@ -866,16 +883,26 @@ 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) {
+		intel_context_get(ce);
+		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);
 }
@@ -950,11 +977,21 @@ 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) {
+		intel_context_get(ce);
+		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 */
@@ -2848,21 +2885,26 @@ 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) {
+		intel_context_get(ce);
+		xa_unlock(&guc->context_lookup);
+
 		if (!intel_context_is_pinned(ce))
-			continue;
+			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) {
@@ -2872,9 +2914,17 @@ 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);
+
 	}
+done:
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
@@ -2890,23 +2940,32 @@ 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) {
+		intel_context_get(ce);
+		xa_unlock(&guc->context_lookup);
+
 		if (!intel_context_is_pinned(ce))
-			continue;
+			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);
 		intel_engine_dump_active_requests(&ce->guc_active.requests,
 						  hung_rq, m);
 		spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+
+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,
@@ -2960,7 +3019,9 @@ 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);
@@ -2979,6 +3040,7 @@ 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:[~2021-08-16 13:57 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-16 13:51 [Intel-gfx] [PATCH 00/22] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 01/22] drm/i915/guc: Fix blocked context accounting Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 02/22] drm/i915/guc: Fix outstanding G2H accounting Matthew Brost
2021-08-17  9:39   ` Daniel Vetter
2021-08-17 18:17     ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 03/22] drm/i915/guc: Unwind context requests in reverse order Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 04/22] drm/i915/guc: Don't drop ce->guc_active.lock when unwinding context Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 05/22] drm/i915/guc: Workaround reset G2H is received after schedule done G2H Matthew Brost
2021-08-17  9:32   ` Daniel Vetter
2021-08-17 15:03     ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 06/22] drm/i915/execlists: Do not propagate errors to dependent fences Matthew Brost
2021-08-17  9:21   ` Daniel Vetter
2021-08-17 15:08     ` Matthew Brost
2021-08-17 15:49       ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 07/22] drm/i915/selftests: Add a cancel request selftest that triggers a reset Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 08/22] drm/i915/guc: Don't enable scheduling on a banned context, guc_id invalid, not registered Matthew Brost
2021-08-17  9:47   ` Daniel Vetter
2021-08-17  9:57     ` Daniel Vetter
2021-08-17 16:44     ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 09/22] drm/i915/selftests: Fix memory corruption in live_lrc_isolation Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 10/22] drm/i915/selftests: Add initial GuC selftest for scrubbing lost G2H Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 11/22] drm/i915/guc: Take context ref when cancelling request Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 12/22] drm/i915/guc: Don't touch guc_state.sched_state without a lock Matthew Brost
2021-08-17  7:21   ` kernel test robot
2021-08-16 13:51 ` [Intel-gfx] [PATCH 13/22] drm/i915/guc: Reset LRC descriptor if register returns -ENODEV Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 14/22] drm/i915: Allocate error capture in atomic context Matthew Brost
2021-08-17 10:06   ` Daniel Vetter
2021-08-17 16:12     ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 15/22] drm/i915/guc: Flush G2H work queue during reset Matthew Brost
2021-08-17 10:06   ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 16/22] drm/i915/guc: Release submit fence from an IRQ Matthew Brost
2021-08-17 10:08   ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 17/22] drm/i915/guc: Move guc_blocked fence to struct guc_state Matthew Brost
2021-08-17 10:10   ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 18/22] drm/i915/guc: Rework and simplify locking Matthew Brost
2021-08-17 10:15   ` Daniel Vetter
2021-08-17 15:30     ` Matthew Brost
2021-08-16 13:51 ` Matthew Brost [this message]
2021-08-17 10:27   ` [Intel-gfx] [PATCH 19/22] drm/i915/guc: Proper xarray usage for contexts_lookup Daniel Vetter
2021-08-17 15:26     ` Matthew Brost
2021-08-17 17:13       ` Daniel Vetter
2021-08-17 17:13         ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 20/22] drm/i915/guc: Drop pin count check trick between sched_disable and re-pin Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 21/22] drm/i915/guc: Move GuC priority fields in context under guc_active Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 22/22] drm/i915/guc: Add GuC kernel doc Matthew Brost
2021-08-17 11:11   ` Daniel Vetter
2021-08-17 16:36     ` Matthew Brost
2021-08-17 17:20       ` Daniel Vetter
2021-08-17 17:27         ` Michal Wajdeczko
2021-08-17 17:34           ` Daniel Vetter
2021-08-17 20:41             ` Michal Wajdeczko
2021-08-17 21:49               ` Daniel Vetter
2021-08-17 12:49 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Clean up GuC CI failures, simplify locking, and kernel DOC (rev2) Patchwork
2021-08-17 12:51 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-08-17 13:22 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-08-17 14:39 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork

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=20210816135139.10060-20-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=daniel.vetter@ffwll.ch \
    --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).