Intel-GFX Archive on lore.kernel.org
 help / color / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 16/42] drm/i915/gt: Replace direct submit with direct call to tasklet
Date: Sun,  2 Aug 2020 17:43:46 +0100
Message-ID: <20200802164412.2738-17-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200802164412.2738-1-chris@chris-wilson.co.uk>

Rather than having special case code for opportunistically calling
process_csb() and performing a direct submit while holding the engine
spinlock for submitting the request, simply call the tasklet directly.
This allows us to retain the direct submission path, including the CS
draining to allow fast/immediate submissions, without requiring any
duplicated code paths.

The trickiest part here is to ensure that paired operations (such as
schedule_in/schedule_out) remain under consistent locking domains,
e.g. when pulled outside of the engine->active.lock

v2: Use bh kicking, see commit 3c53776e29f8 ("Mark HI and TASKLET
softirq synchronous").
v3: Update engine-reset to be tasklet aware

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c   |   4 +-
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |   2 +
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  35 +++--
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  |   3 +
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |   3 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c           | 126 ++++++------------
 drivers/gpu/drm/i915/gt/intel_reset.c         |  60 ++++++---
 drivers/gpu/drm/i915/gt/intel_reset.h         |   2 +
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  |   7 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |  27 ++--
 drivers/gpu/drm/i915/gt/selftest_reset.c      |   8 +-
 drivers/gpu/drm/i915/i915_request.c           |   2 +
 drivers/gpu/drm/i915/selftests/i915_request.c |   6 +-
 13 files changed, 144 insertions(+), 141 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 56700ddbed47..04d291a8d31d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -398,12 +398,14 @@ static bool __reset_engine(struct intel_engine_cs *engine)
 	if (!intel_has_reset_engine(gt))
 		return false;
 
+	local_bh_disable();
 	if (!test_and_set_bit(I915_RESET_ENGINE + engine->id,
 			      &gt->reset.flags)) {
-		success = intel_engine_reset(engine, NULL) == 0;
+		success = __intel_engine_reset_bh(engine, NULL) == 0;
 		clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
 				      &gt->reset.flags);
 	}
+	local_bh_enable();
 
 	return success;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 89c7b33dd99f..9f676df68fae 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2453,7 +2453,9 @@ static void eb_request_add(struct i915_execbuffer *eb)
 		__i915_request_skip(rq);
 	}
 
+	local_bh_disable();
 	__i915_request_queue(rq, &attr);
+	local_bh_enable();
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index ea4ba2afe9f9..26f2781e4a51 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1000,32 +1000,39 @@ static unsigned long stop_timeout(const struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.stop_timeout_ms);
 }
 
-int intel_engine_stop_cs(struct intel_engine_cs *engine)
+static int __intel_engine_stop_cs(struct intel_engine_cs *engine,
+				  int fast_timeout_us,
+				  int slow_timeout_ms)
 {
 	struct intel_uncore *uncore = engine->uncore;
-	const u32 base = engine->mmio_base;
-	const i915_reg_t mode = RING_MI_MODE(base);
+	const i915_reg_t mode = RING_MI_MODE(engine->mmio_base);
 	int err;
 
+	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
+	err = __intel_wait_for_register_fw(engine->uncore, mode,
+					   MODE_IDLE, MODE_IDLE,
+					   fast_timeout_us,
+					   slow_timeout_ms,
+					   NULL);
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	intel_uncore_posting_read_fw(uncore, mode);
+	return err;
+}
+
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+	int err = 0;
+
 	if (INTEL_GEN(engine->i915) < 3)
 		return -ENODEV;
 
 	ENGINE_TRACE(engine, "\n");
-
-	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
-
-	err = 0;
-	if (__intel_wait_for_register_fw(uncore,
-					 mode, MODE_IDLE, MODE_IDLE,
-					 1000, stop_timeout(engine),
-					 NULL)) {
+	if (__intel_engine_stop_cs(engine, 1000, stop_timeout(engine))) {
 		ENGINE_TRACE(engine, "timed out on STOP_RING -> IDLE\n");
 		err = -ETIMEDOUT;
 	}
 
-	/* A final mmio read to let GPU writes be hopefully flushed to memory */
-	intel_uncore_posting_read_fw(uncore, mode);
-
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index eb4393b2342e..5a0196dc5716 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -61,7 +61,10 @@ static void heartbeat_commit(struct i915_request *rq,
 	idle_pulse(rq->engine, rq);
 
 	__i915_request_commit(rq);
+
+	local_bh_disable();
 	__i915_request_queue(rq, attr);
+	local_bh_enable();
 }
 
 static void show_heartbeat(const struct i915_request *rq,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index c400aaa2287b..3ea1e59d2b85 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -183,7 +183,8 @@ struct intel_engine_execlists {
 	 * Reserve the upper 16b for tracking internal errors.
 	 */
 	u32 error_interrupt;
-#define ERROR_CSB BIT(31)
+#define ERROR_CSB	BIT(31)
+#define ERROR_PREEMPT	BIT(30)
 
 	/**
 	 * @reset_ccid: Active CCID [EXECLISTS_STATUS_HI] at the time of reset
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a870fd243e44..dcbd47e8a513 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1378,8 +1378,7 @@ __execlists_schedule_in(struct i915_request *rq)
 	return engine;
 }
 
-static inline struct i915_request *
-execlists_schedule_in(struct i915_request *rq, int idx)
+static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 {
 	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *old;
@@ -1396,7 +1395,6 @@ execlists_schedule_in(struct i915_request *rq, int idx)
 	} while (!try_cmpxchg(&ce->inflight, &old, ptr_inc(old)));
 
 	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
-	return i915_request_get(rq);
 }
 
 static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
@@ -2078,8 +2076,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
-	struct i915_request * const *active;
-	struct i915_request *last;
+	struct i915_request *last = *execlists->active;
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -2104,6 +2101,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * sequence of requests as being the most optimal (fewest wake ups
 	 * and context switches) submission.
 	 */
+	spin_lock_irq(&engine->active.lock);
 
 	for (rb = rb_first_cached(&execlists->virtual); rb; ) {
 		struct virtual_engine *ve =
@@ -2132,10 +2130,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * the active context to interject the preemption request,
 	 * i.e. we will retrigger preemption following the ack in case
 	 * of trouble.
-	 */
-	active = READ_ONCE(execlists->active);
-
-	/*
+	 *
 	 * In theory we can skip over completed contexts that have not
 	 * yet been processed by events (as those events are in flight):
 	 *
@@ -2147,7 +2142,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * completed and barf.
 	 */
 
-	if ((last = *active)) {
+	if (last) {
 		if (i915_request_completed(last)) {
 			goto check_secondary;
 		} else if (need_preempt(engine, last, rb)) {
@@ -2220,6 +2215,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
+				spin_unlock_irq(&engine->active.lock);
 				start_timeslice(engine, queue_prio(execlists));
 				return;
 			}
@@ -2255,6 +2251,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
+				spin_unlock_irq(&engine->active.lock);
 				start_timeslice(engine, rq_prio(rq));
 				return; /* leave this for another sibling */
 			}
@@ -2372,8 +2369,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (__i915_request_submit(rq)) {
 				if (!merge) {
-					*port = execlists_schedule_in(last, port - execlists->pending);
-					port++;
+					*port++ = i915_request_get(last);
 					last = NULL;
 				}
 
@@ -2392,8 +2388,9 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		rb_erase_cached(&p->node, &execlists->queue);
 		i915_priolist_free(p);
 	}
-
 done:
+	*port++ = i915_request_get(last);
+
 	/*
 	 * Here be a bit of magic! Or sleight-of-hand, whichever you prefer.
 	 *
@@ -2411,33 +2408,33 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * interrupt for secondary ports).
 	 */
 	execlists->queue_priority_hint = queue_prio(execlists);
+	spin_unlock_irq(&engine->active.lock);
 
 	if (submit) {
-		*port = execlists_schedule_in(last, port - execlists->pending);
-		execlists->switch_priority_hint =
-			switch_prio(engine, *execlists->pending);
-
 		/*
 		 * Skip if we ended up with exactly the same set of requests,
 		 * e.g. trying to timeslice a pair of ordered contexts
 		 */
-		if (!memcmp(active, execlists->pending,
-			    (port - execlists->pending + 1) * sizeof(*port))) {
-			do
-				execlists_schedule_out(fetch_and_zero(port));
-			while (port-- != execlists->pending);
-
+		if (!memcmp(execlists->active,
+			    execlists->pending,
+			    (port - execlists->pending) * sizeof(*port)))
 			goto skip_submit;
-		}
-		clear_ports(port + 1, last_port - port);
+
+		*port = NULL;
+		while (port-- != execlists->pending)
+			execlists_schedule_in(*port, port - execlists->pending);
+
+		execlists->switch_priority_hint =
+			switch_prio(engine, *execlists->pending);
 
 		WRITE_ONCE(execlists->yield, -1);
-		set_preempt_timeout(engine, *active);
+		set_preempt_timeout(engine, *execlists->active);
 		execlists_submit_ports(engine);
 	} else {
 		start_timeslice(engine, execlists->queue_priority_hint);
 skip_submit:
 		ring_set_paused(engine, 0);
+		*execlists->pending = NULL;
 	}
 }
 
@@ -2717,16 +2714,6 @@ static void process_csb(struct intel_engine_cs *engine)
 	invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
 }
 
-static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
-{
-	lockdep_assert_held(&engine->active.lock);
-	if (!READ_ONCE(engine->execlists.pending[0])) {
-		rcu_read_lock(); /* protect peeking at execlists->active */
-		execlists_dequeue(engine);
-		rcu_read_unlock();
-	}
-}
-
 static void __execlists_hold(struct i915_request *rq)
 {
 	LIST_HEAD(list);
@@ -3113,7 +3100,7 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
 	if (!timer_expired(t))
 		return false;
 
-	return READ_ONCE(engine->execlists.pending[0]);
+	return engine->execlists.pending[0];
 }
 
 /*
@@ -3123,10 +3110,12 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
 static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
-	bool timeout = preempt_timeout(engine);
 
 	process_csb(engine);
 
+	if (unlikely(preempt_timeout(engine)))
+		engine->execlists.error_interrupt |= ERROR_PREEMPT;
+
 	if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) {
 		const char *msg;
 
@@ -3135,6 +3124,8 @@ static void execlists_submission_tasklet(unsigned long data)
 			msg = "CS error"; /* thrown by a user payload */
 		else if (engine->execlists.error_interrupt & ERROR_CSB)
 			msg = "invalid CSB event";
+		else if (engine->execlists.error_interrupt & ERROR_PREEMPT)
+			msg = "preemption time out";
 		else
 			msg = "internal error";
 
@@ -3142,17 +3133,8 @@ static void execlists_submission_tasklet(unsigned long data)
 		execlists_reset(engine, msg);
 	}
 
-	if (!READ_ONCE(engine->execlists.pending[0]) || timeout) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&engine->active.lock, flags);
-		__execlists_submission_tasklet(engine);
-		spin_unlock_irqrestore(&engine->active.lock, flags);
-
-		/* Recheck after serialising with direct-submission */
-		if (unlikely(timeout && preempt_timeout(engine)))
-			execlists_reset(engine, "preemption time out");
-	}
+	if (!engine->execlists.pending[0])
+		execlists_dequeue(engine);
 }
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
@@ -3183,26 +3165,16 @@ static void queue_request(struct intel_engine_cs *engine,
 	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
-static void __submit_queue_imm(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
-	if (reset_in_progress(execlists))
-		return; /* defer until we restart the engine following reset */
-
-	__execlists_submission_tasklet(engine);
-}
-
-static void submit_queue(struct intel_engine_cs *engine,
+static bool submit_queue(struct intel_engine_cs *engine,
 			 const struct i915_request *rq)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
 
 	if (rq_prio(rq) <= execlists->queue_priority_hint)
-		return;
+		return false;
 
 	execlists->queue_priority_hint = rq_prio(rq);
-	__submit_queue_imm(engine);
+	return true;
 }
 
 static bool ancestor_on_hold(const struct intel_engine_cs *engine,
@@ -3212,25 +3184,11 @@ static bool ancestor_on_hold(const struct intel_engine_cs *engine,
 	return !list_empty(&engine->active.hold) && hold_request(rq);
 }
 
-static void flush_csb(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists *el = &engine->execlists;
-
-	if (READ_ONCE(el->pending[0]) && tasklet_trylock(&el->tasklet)) {
-		if (!reset_in_progress(el))
-			process_csb(engine);
-		tasklet_unlock(&el->tasklet);
-	}
-}
-
 static void execlists_submit_request(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 	unsigned long flags;
 
-	/* Hopefully we clear execlists->pending[] to let us through */
-	flush_csb(engine);
-
 	/* Will be called from irq-context when using foreign fences. */
 	spin_lock_irqsave(&engine->active.lock, flags);
 
@@ -3244,7 +3202,8 @@ static void execlists_submit_request(struct i915_request *request)
 		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 		GEM_BUG_ON(list_empty(&request->sched.link));
 
-		submit_queue(engine, request);
+		if (submit_queue(engine, request))
+			__execlists_kick(&engine->execlists);
 	}
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
@@ -4132,7 +4091,6 @@ static int execlists_resume(struct intel_engine_cs *engine)
 static void execlists_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	unsigned long flags;
 
 	ENGINE_TRACE(engine, "depth<-%d\n",
 		     atomic_read(&execlists->tasklet.count));
@@ -4149,10 +4107,6 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	__tasklet_disable_sync_once(&execlists->tasklet);
 	GEM_BUG_ON(!reset_in_progress(execlists));
 
-	/* And flush any current direct submission. */
-	spin_lock_irqsave(&engine->active.lock, flags);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
-
 	/*
 	 * We stop engines, otherwise we might get failed reset and a
 	 * dead gpu (on elk). Also as modern gpu as kbl can suffer
@@ -4396,12 +4350,12 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	 * to sleep before we restart and reload a context.
 	 */
 	GEM_BUG_ON(!reset_in_progress(execlists));
-	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
-		execlists->tasklet.func(execlists->tasklet.data);
+	GEM_BUG_ON(engine->execlists.pending[0]);
 
+	/* And kick in case we missed a new request submission. */
 	if (__tasklet_enable(&execlists->tasklet))
-		/* And kick in case we missed a new request submission. */
-		tasklet_hi_schedule(&execlists->tasklet);
+		__execlists_kick(execlists);
+
 	ENGINE_TRACE(engine, "depth->%d\n",
 		     atomic_read(&execlists->tasklet.count));
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ac36b67fb46b..77f70a70082c 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -39,20 +39,19 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 	intel_uncore_rmw_fw(uncore, reg, clr, 0);
 }
 
-static void engine_skip_context(struct i915_request *rq)
+static void skip_context(struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = rq->engine;
 	struct intel_context *hung_ctx = rq->context;
 
-	if (!i915_request_is_active(rq))
-		return;
+	list_for_each_entry_from_rcu(rq, &hung_ctx->timeline->requests, link) {
+		if (!i915_request_is_active(rq))
+			return;
 
-	lockdep_assert_held(&engine->active.lock);
-	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->context == hung_ctx) {
 			i915_request_set_error_once(rq, -EIO);
 			__i915_request_skip(rq);
 		}
+	}
 }
 
 static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
@@ -159,7 +158,7 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		i915_request_set_error_once(rq, -EIO);
 		__i915_request_skip(rq);
 		if (mark_guilty(rq))
-			engine_skip_context(rq);
+			skip_context(rq);
 	} else {
 		i915_request_set_error_once(rq, -EAGAIN);
 		mark_innocent(rq);
@@ -753,8 +752,10 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 	if (err)
 		return err;
 
+	local_bh_disable();
 	for_each_engine(engine, gt, id)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
+	local_bh_enable();
 
 	intel_ggtt_restore_fences(gt->ggtt);
 
@@ -832,9 +833,11 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	set_bit(I915_WEDGED, &gt->reset.flags);
 
 	/* Mark all executing requests as skipped */
+	local_bh_disable();
 	for_each_engine(engine, gt, id)
 		if (engine->reset.cancel)
 			engine->reset.cancel(engine);
+	local_bh_enable();
 
 	reset_finish(gt, awake);
 
@@ -1109,20 +1112,7 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 	return __intel_gt_reset(engine->gt, engine->mask);
 }
 
-/**
- * intel_engine_reset - reset GPU engine to recover from a hang
- * @engine: engine to reset
- * @msg: reason for GPU reset; or NULL for no drm_notice()
- *
- * Reset a specific GPU engine. Useful if a hang is detected.
- * Returns zero on successful reset or otherwise an error code.
- *
- * Procedure is:
- *  - identifies the request that caused the hang and it is dropped
- *  - reset engine (which will force the engine to idle)
- *  - re-init/configure engine
- */
-int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
+int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 {
 	struct intel_gt *gt = engine->gt;
 	bool uses_guc = intel_engine_in_guc_submission_mode(engine);
@@ -1173,6 +1163,30 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 	return ret;
 }
 
+/**
+ * intel_engine_reset - reset GPU engine to recover from a hang
+ * @engine: engine to reset
+ * @msg: reason for GPU reset; or NULL for no drm_notice()
+ *
+ * Reset a specific GPU engine. Useful if a hang is detected.
+ * Returns zero on successful reset or otherwise an error code.
+ *
+ * Procedure is:
+ *  - identifies the request that caused the hang and it is dropped
+ *  - reset engine (which will force the engine to idle)
+ *  - re-init/configure engine
+ */
+int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
+{
+	int err;
+
+	local_bh_disable();
+	err = __intel_engine_reset_bh(engine, msg);
+	local_bh_enable();
+
+	return err;
+}
+
 static void intel_gt_reset_global(struct intel_gt *gt,
 				  u32 engine_mask,
 				  const char *reason)
@@ -1259,18 +1273,20 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * single reset fails.
 	 */
 	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
+		local_bh_disable();
 		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					     &gt->reset.flags))
 				continue;
 
-			if (intel_engine_reset(engine, msg) == 0)
+			if (__intel_engine_reset_bh(engine, msg) == 0)
 				engine_mask &= ~engine->mask;
 
 			clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
 					      &gt->reset.flags);
 		}
+		local_bh_enable();
 	}
 
 	if (!engine_mask)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index a0eec7c11c0c..7dbf5cc8a333 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -34,6 +34,8 @@ void intel_gt_reset(struct intel_gt *gt,
 		    const char *reason);
 int intel_engine_reset(struct intel_engine_cs *engine,
 		       const char *reason);
+int __intel_engine_reset_bh(struct intel_engine_cs *engine,
+			    const char *reason);
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index fb5ebf930ab2..c28d1fcad673 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1576,12 +1576,17 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 		  engine->name, mode, p->name);
 
 	tasklet_disable(t);
+	if (strcmp(p->name, "softirq"))
+		local_bh_disable();
 	p->critical_section_begin();
 
-	err = intel_engine_reset(engine, NULL);
+	err = __intel_engine_reset_bh(engine, NULL);
 
 	p->critical_section_end();
+	if (strcmp(p->name, "softirq"))
+		local_bh_enable();
 	tasklet_enable(t);
+	tasklet_hi_schedule(t);
 
 	if (err)
 		pr_err("i915_reset_engine(%s:%s) failed under %s\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index f749071f54a7..3686ad3e32e6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -623,8 +623,10 @@ static int live_hold_reset(void *arg)
 
 		/* We have our request executing, now remove it and reset */
 
+		local_bh_disable();
 		if (test_and_set_bit(I915_RESET_ENGINE + id,
 				     &gt->reset.flags)) {
+			local_bh_enable();
 			intel_gt_set_wedged(gt);
 			err = -EBUSY;
 			goto out;
@@ -638,12 +640,13 @@ static int live_hold_reset(void *arg)
 		execlists_hold(engine, rq);
 		GEM_BUG_ON(!i915_request_on_hold(rq));
 
-		intel_engine_reset(engine, NULL);
+		__intel_engine_reset_bh(engine, NULL);
 		GEM_BUG_ON(rq->fence.error != -EIO);
 
 		tasklet_enable(&engine->execlists.tasklet);
 		clear_and_wake_up_bit(I915_RESET_ENGINE + id,
 				      &gt->reset.flags);
+		local_bh_enable();
 
 		/* Check that we do not resubmit the held request */
 		if (!i915_request_wait(rq, 0, HZ / 5)) {
@@ -4569,8 +4572,10 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(engine == ve->engine);
 
 	/* Take ownership of the reset and tasklet */
+	local_bh_disable();
 	if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 			     &gt->reset.flags)) {
+		local_bh_enable();
 		intel_gt_set_wedged(gt);
 		err = -EBUSY;
 		goto out_heartbeat;
@@ -4590,12 +4595,13 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	execlists_hold(engine, rq);
 	GEM_BUG_ON(!i915_request_on_hold(rq));
 
-	intel_engine_reset(engine, NULL);
+	__intel_engine_reset_bh(engine, NULL);
 	GEM_BUG_ON(rq->fence.error != -EIO);
 
 	/* Release our grasp on the engine, letting CS flow again */
 	tasklet_enable(&engine->execlists.tasklet);
 	clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags);
+	local_bh_enable();
 
 	/* Check that we do not resubmit the held request */
 	i915_request_get(rq);
@@ -6233,16 +6239,17 @@ static void garbage_reset(struct intel_engine_cs *engine,
 	const unsigned int bit = I915_RESET_ENGINE + engine->id;
 	unsigned long *lock = &engine->gt->reset.flags;
 
-	if (test_and_set_bit(bit, lock))
-		return;
-
-	tasklet_disable(&engine->execlists.tasklet);
+	local_bh_disable();
+	if (!test_and_set_bit(bit, lock)) {
+		tasklet_disable(&engine->execlists.tasklet);
 
-	if (!rq->fence.error)
-		intel_engine_reset(engine, NULL);
+		if (!rq->fence.error)
+			__intel_engine_reset_bh(engine, NULL);
 
-	tasklet_enable(&engine->execlists.tasklet);
-	clear_and_wake_up_bit(bit, lock);
+		tasklet_enable(&engine->execlists.tasklet);
+		clear_and_wake_up_bit(bit, lock);
+	}
+	local_bh_enable();
 }
 
 static struct i915_request *garbage(struct intel_context *ce,
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 35406ecdf0b2..19dd0c347874 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -132,11 +132,16 @@ static int igt_atomic_engine_reset(void *arg)
 		for (p = igt_atomic_phases; p->name; p++) {
 			GEM_TRACE("intel_engine_reset(%s) under %s\n",
 				  engine->name, p->name);
+			if (strcmp(p->name, "softirq"))
+				local_bh_disable();
 
 			p->critical_section_begin();
-			err = intel_engine_reset(engine, NULL);
+			err = __intel_engine_reset_bh(engine, NULL);
 			p->critical_section_end();
 
+			if (strcmp(p->name, "softirq"))
+				local_bh_enable();
+
 			if (err) {
 				pr_err("intel_engine_reset(%s) failed under %s\n",
 				       engine->name, p->name);
@@ -146,6 +151,7 @@ static int igt_atomic_engine_reset(void *arg)
 
 		intel_engine_pm_put(engine);
 		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index ebfa195d6463..173b379c3021 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1621,7 +1621,9 @@ void i915_request_add(struct i915_request *rq)
 		attr = ctx->sched;
 	rcu_read_unlock();
 
+	local_bh_disable();
 	__i915_request_queue(rq, &attr);
+	local_bh_enable();
 
 	mutex_unlock(&tl->mutex);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index c1dcd4b91bda..528d07f9941b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -1926,9 +1926,7 @@ static int measure_inter_request(struct intel_context *ce)
 		intel_ring_advance(rq, cs);
 		i915_request_add(rq);
 	}
-	local_bh_disable();
 	i915_sw_fence_commit(submit);
-	local_bh_enable();
 	intel_engine_flush_submission(ce->engine);
 	heap_fence_put(submit);
 
@@ -2214,11 +2212,9 @@ static int measure_completion(struct intel_context *ce)
 		intel_ring_advance(rq, cs);
 
 		dma_fence_add_callback(&rq->fence, &cb.base, signal_cb);
-
-		local_bh_disable();
 		i915_request_add(rq);
-		local_bh_enable();
 
+		intel_engine_flush_submission(ce->engine);
 		if (wait_for(READ_ONCE(sema[i]) == -1, 50)) {
 			err = -EIO;
 			goto err;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply index

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-02 16:43 [Intel-gfx] Time, where did it go? Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 01/42] drm/i915: Fix wrong return value Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 02/42] drm/i915/gem: Don't drop the timeline lock during execbuf Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 03/42] drm/i915/gem: Reduce context termination list iteration guard to RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 04/42] drm/i915/gt: Protect context lifetime with RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 05/42] drm/i915/gt: Free stale request on destroying the virtual engine Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 06/42] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 07/42] drm/i915/gt: Split the breadcrumb spinlock between global and contexts Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 08/42] drm/i915: Drop i915_request.lock serialisation around await_start Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 09/42] drm/i915: Drop i915_request.lock requirement for intel_rps_boost() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 10/42] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 11/42] drm/i915/gem: Reduce ctx->engines_mutex for get_engines() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 12/42] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 13/42] drm/i915/gt: Decouple completed requests on unwind Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 14/42] drm/i915/gt: Check for a completed last request once Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 15/42] drm/i915/gt: Refactor heartbeat request construction and submission Chris Wilson
2020-08-02 16:43 ` Chris Wilson [this message]
2020-08-02 16:43 ` [Intel-gfx] [PATCH 17/42] drm/i915/gt: Use virtual_engine during execlists_dequeue Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 18/42] drm/i915/gt: Decouple inflight virtual engines Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 19/42] drm/i915/gt: Defer schedule_out until after the next dequeue Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 20/42] drm/i915/gt: Resubmit the virtual engine on schedule-out Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 21/42] drm/i915/gt: Simplify virtual engine handling for execlists_hold() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 22/42] drm/i915/gt: ce->inflight updates are now serialised Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 23/42] drm/i915/gt: Drop atomic for engine->fw_active tracking Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 24/42] drm/i915/gt: Extract busy-stats for ring-scheduler Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 25/42] drm/i915/gt: Convert stats.active to plain unsigned int Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 26/42] drm/i915: Lift waiter/signaler iterators Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 27/42] drm/i915: Strip out internal priorities Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 28/42] drm/i915: Remove I915_USER_PRIORITY_SHIFT Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 29/42] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 30/42] drm/i915: Prune empty priolists Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 31/42] drm/i915: Replace engine->schedule() with a known request operation Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 32/42] drm/i915/gt: Do not suspend bonded requests if one hangs Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 33/42] drm/i915: Teach the i915_dependency to use a double-lock Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 34/42] drm/i915: Restructure priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 35/42] drm/i915/selftests: Measure set-priority duration Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 36/42] drm/i915: Improve DFS for priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 37/42] drm/i915/gt: Remove timeslice suppression Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 38/42] drm/i915: Fair low-latency scheduling Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 39/42] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 40/42] drm/i915: Replace the priority boosting for the display with a deadline Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 41/42] drm/i915: Move saturated workload detection back to the context Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 42/42] drm/i915/gt: Another tweak for flushing the tasklets Chris Wilson
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/42] drm/i915: Fix wrong return value Patchwork
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-08-02 17:34 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-08-02 17:56 ` [Intel-gfx] Time, where did it go? Dave Airlie
2020-08-02 19:36   ` Chris Wilson
2020-08-04 21:45     ` Dave Airlie
2020-08-07  7:12       ` Chris Wilson
2020-08-09 20:01         ` Dave Airlie
2020-08-02 21:03 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [01/42] drm/i915: Fix wrong return value 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=20200802164412.2738-17-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --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

Intel-GFX Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/intel-gfx/0 intel-gfx/git/0.git
	git clone --mirror https://lore.kernel.org/intel-gfx/1 intel-gfx/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 intel-gfx intel-gfx/ https://lore.kernel.org/intel-gfx \
		intel-gfx@lists.freedesktop.org
	public-inbox-index intel-gfx

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.freedesktop.lists.intel-gfx


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git