drm/i915: Filter out spurious execlists context-switch interrupts

Back in commit a4b2b01523a8 ("drm/i915: Don't mark an execlists
context-switch when idle") we noticed the presence of late
context-switch interrupts. We were able to filter those out by looking
at whether the ELSP remained active, but in commit beecec901790
("drm/i915/execlists: Preemption!") that became problematic as we now
anticipate receiving a context-switch event for preemption while ELSP
may be empty. To restore the spurious interrupt suppression, add a
counter for the expected number of pending context-switches and skip if
we do not need to handle this interrupt to make forward progress.

v2: Don't forget to switch on for preempt.
v3: Reduce the counter to a on/off boolean tracker. Declare the HW as
active when we first submit, and idle after the final completion event
(with which we confirm the HW says it is idle), and track each source
of activity separately. With a finite number of sources, it should aide
us in debugging which gets stuck.

Fixes: beecec901790 ("drm/i915/execlists: Preemption!")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023213237.26536-3-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

1 files changed, 20 insertions, 7 deletions

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7f45dd7dc3e5..5b87d5284a84 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -575,7 +575,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * the state of the GPU is known (idle).
 			 */
 			inject_preempt_context(engine);
-			execlists->preempt = true;
+			execlists_set_active(execlists,
+					     EXECLISTS_ACTIVE_PREEMPT);
 			goto unlock;
 		} else {
 			/*
@@ -683,8 +684,10 @@ done:
 unlock:
 	spin_unlock_irq(&engine->timeline->lock);
 
-	if (submit)
+	if (submit) {
+		execlists_set_active(execlists, EXECLISTS_ACTIVE_USER);
 		execlists_submit_ports(engine);
+	}
 }
 
 static void
@@ -696,6 +699,7 @@ execlist_cancel_port_requests(struct intel_engine_execlists *execlists)
 	while (num_ports-- && port_isset(port)) {
 		struct drm_i915_gem_request *rq = port_request(port);
 
+		GEM_BUG_ON(!execlists->active);
 		execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_PREEMPTED);
 		i915_gem_request_put(rq);
 
@@ -861,15 +865,21 @@ static void intel_lrc_irq_handler(unsigned long data)
 				unwind_incomplete_requests(engine);
 				spin_unlock_irq(&engine->timeline->lock);
 
-				GEM_BUG_ON(!execlists->preempt);
-				execlists->preempt = false;
+				GEM_BUG_ON(!execlists_is_active(execlists,
+								EXECLISTS_ACTIVE_PREEMPT));
+				execlists_clear_active(execlists,
+						       EXECLISTS_ACTIVE_PREEMPT);
 				continue;
 			}
 
 			if (status & GEN8_CTX_STATUS_PREEMPTED &&
-			    execlists->preempt)
+			    execlists_is_active(execlists,
+						EXECLISTS_ACTIVE_PREEMPT))
 				continue;
 
+			GEM_BUG_ON(!execlists_is_active(execlists,
+							EXECLISTS_ACTIVE_USER));
+
 			/* Check the context/desc id for this event matches */
 			GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
 
@@ -892,6 +902,9 @@ static void intel_lrc_irq_handler(unsigned long data)
 			/* After the final element, the hw should be idle */
 			GEM_BUG_ON(port_count(port) == 0 &&
 				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
+			if (port_count(port) == 0)
+				execlists_clear_active(execlists,
+						       EXECLISTS_ACTIVE_USER);
 		}
 
 		if (head != execlists->csb_head) {
@@ -901,7 +914,7 @@ static void intel_lrc_irq_handler(unsigned long data)
 		}
 	}
 
-	if (!execlists->preempt)
+	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
 
 	intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
@@ -1460,7 +1473,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 		   GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
 	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 	execlists->csb_head = -1;
-	execlists->preempt = false;
+	execlists->active = 0;
 
 	/* After a GPU reset, we may have requests to replay */
 	if (!i915_modparams.enable_guc_submission && execlists->first)