[Intel-gfx] [PATCH v2] drm/i915: Include engine state on detecting a missed breadcrumb/seqno

[Chris Wilson]

Now that we have a common engine state pretty printer, we can use that
instead of the adhoc information printed when we miss a breadcrumb.

v2: Rearrange intel_engine_disarm_breadcrumbs() to avoid calling
intel_engine_dump() under the rb spinlock (Mika) and to pretty-print the
error state early so that we include the full list of waiters.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/intel_breadcrumbs.c | 24 +++++++++++++-----------
 drivers/gpu/drm/i915/intel_engine_cs.c   |  6 ++++++
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 43cf227a51c2..918641a7c3f3 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -64,12 +64,11 @@ static unsigned long wait_timeout(void)
 
 static noinline void missed_breadcrumb(struct intel_engine_cs *engine)
 {
-	DRM_DEBUG_DRIVER("%s missed breadcrumb at %pS, irq posted? %s, current seqno=%x, last=%x\n",
-			 engine->name, __builtin_return_address(0),
-			 yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-					&engine->irq_posted)),
-			 intel_engine_get_seqno(engine),
-			 intel_engine_last_submit(engine));
+	struct drm_printer p = drm_debug_printer(__func__);
+
+	DRM_DEBUG_DRIVER("%s missed breadcrumb at %pS\n",
+			 engine->name, __builtin_return_address(0));
+	intel_engine_dump(engine, &p);
 
 	set_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings);
 }
@@ -207,12 +206,16 @@ void intel_engine_unpin_breadcrumbs_irq(struct intel_engine_cs *engine)
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
-	struct intel_wait *wait, *n, *first;
+	struct intel_wait *wait, *n;
 
 	if (!b->irq_armed)
 		return;
 
-	/* We only disarm the irq when we are idle (all requests completed),
+	if (intel_engine_wakeup(engine) & ENGINE_WAKEUP_ASLEEP)
+		missed_breadcrumb(engine);
+
+	/*
+	 * We only disarm the irq when we are idle (all requests completed),
 	 * so if the bottom-half remains asleep, it missed the request
 	 * completion.
 	 */
@@ -220,15 +223,14 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	spin_lock_irq(&b->rb_lock);
 
 	spin_lock(&b->irq_lock);
-	first = fetch_and_zero(&b->irq_wait);
+	b->irq_wait = NULL;
 	if (b->irq_armed)
 		__intel_engine_disarm_breadcrumbs(engine);
 	spin_unlock(&b->irq_lock);
 
 	rbtree_postorder_for_each_entry_safe(wait, n, &b->waiters, node) {
 		RB_CLEAR_NODE(&wait->node);
-		if (wake_up_process(wait->tsk) && wait == first)
-			missed_breadcrumb(engine);
+		wake_up_process(wait->tsk);
 	}
 	b->waiters = RB_ROOT;
 
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 403cc4749008..1846c55afef5 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1878,6 +1878,12 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 	}
 	spin_unlock_irq(&b->rb_lock);
 
+	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+		   engine->irq_posted,
+		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
+				  &engine->irq_posted)),
+		   yesno(test_bit(ENGINE_IRQ_EXECLIST,
+				  &engine->irq_posted)));
 	drm_printf(m, "Idle? %s\n", yesno(intel_engine_is_idle(engine)));
 	drm_printf(m, "\n");
 }
-- 
2.15.0