drm/i915/gt: Convert stats.active to plain unsigned int

As context-in/out is now always serialised, we do not have to worry
about concurrent enabling/disable of the busy-stats and can reduce the
atomic_t active to a plain unsigned int, and the seqlock to a seqcount.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210115142331.24458-3-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -342,7 +342,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->schedule = NULL;
 
 	ewma__engine_latency_init(&engine->latency);
-	seqlock_init(&engine->stats.lock);
+	seqcount_init(&engine->stats.lock);
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
@@ -1754,7 +1754,7 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine,
 	 * add it to the total.
 	 */
 	*now = ktime_get();
-	if (atomic_read(&engine->stats.active))
+	if (READ_ONCE(engine->stats.active))
 		total = ktime_add(total, ktime_sub(*now, engine->stats.start));
 
 	return total;
@@ -1773,9 +1773,9 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 	ktime_t total;
 
 	do {
-		seq = read_seqbegin(&engine->stats.lock);
+		seq = read_seqcount_begin(&engine->stats.lock);
 		total = __intel_engine_get_busy_time(engine, now);
-	} while (read_seqretry(&engine->stats.lock, seq));
+	} while (read_seqcount_retry(&engine->stats.lock, seq));
 
 	return total;
 }

drivers/gpu/drm/i915/gt/intel_engine_stats.h

@@ -17,33 +17,44 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	if (atomic_add_unless(&engine->stats.active, 1, 0))
+	if (engine->stats.active) {
+		engine->stats.active++;
 		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (!atomic_add_unless(&engine->stats.active, 1, 0)) {
-		engine->stats.start = ktime_get();
-		atomic_inc(&engine->stats.active);
 	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+
+	/* The writer is serialised; but the pmu reader may be from hardirq */
+	local_irq_save(flags);
+	write_seqcount_begin(&engine->stats.lock);
+
+	engine->stats.start = ktime_get();
+	engine->stats.active++;
+
+	write_seqcount_end(&engine->stats.lock);
+	local_irq_restore(flags);
+
+	GEM_BUG_ON(!engine->stats.active);
 }
 
 static inline void intel_engine_context_out(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	GEM_BUG_ON(!atomic_read(&engine->stats.active));
+	GEM_BUG_ON(!engine->stats.active);
-
+	if (engine->stats.active > 1) {
-	if (atomic_add_unless(&engine->stats.active, -1, 1))
+		engine->stats.active--;
 		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (atomic_dec_and_test(&engine->stats.active)) {
-		engine->stats.total =
-			ktime_add(engine->stats.total,
-				  ktime_sub(ktime_get(), engine->stats.start));
 	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+
+	local_irq_save(flags);
+	write_seqcount_begin(&engine->stats.lock);
+
+	engine->stats.active--;
+	engine->stats.total =
+		ktime_add(engine->stats.total,
+			  ktime_sub(ktime_get(), engine->stats.start));
+
+	write_seqcount_end(&engine->stats.lock);
+	local_irq_restore(flags);
 }
 
 #endif /* __INTEL_ENGINE_STATS_H__ */

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -516,12 +516,12 @@ struct intel_engine_cs {
 		/**
 		 * @active: Number of contexts currently scheduled in.
 		 */
-		atomic_t active;
+		unsigned int active;
 
 		/**
 		 * @lock: Lock protecting the below fields.
 		 */
-		seqlock_t lock;
+		seqcount_t lock;
 
 		/**
 		 * @total: Total time this engine was busy.