Since we can compute the elapsed time to add to the total, during the PMU sample we only need to have a consistent view of the (start, total, active) tuple to be able to locally determine the runtime. That can be arrange by a pair of memory bariiers and carefully sequencing of the writes and reads.
Signed-off-by: Chris Wilson <[email protected]> Reviewed-by: Andi Shyti <[email protected]> --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 34 +++++++------------- drivers/gpu/drm/i915/gt/intel_engine_stats.h | 24 +++----------- drivers/gpu/drm/i915/gt/intel_engine_types.h | 5 --- 3 files changed, 15 insertions(+), 48 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index fb1b1d096975..bd33f8a3e9b6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -342,7 +342,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) engine->schedule = NULL; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); @@ -1744,22 +1743,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, intel_engine_print_breadcrumbs(engine, m); } -static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine, - ktime_t *now) -{ - ktime_t total = engine->stats.total; - - /* - * If the engine is executing something at the moment - * add it to the total. - */ - *now = ktime_get(); - if (READ_ONCE(engine->stats.active)) - total = ktime_add(total, ktime_sub(*now, engine->stats.start)); - - return total; -} - /** * intel_engine_get_busy_time() - Return current accumulated engine busyness * @engine: engine to report on @@ -1769,13 +1752,18 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine, */ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) { - unsigned int seq; - ktime_t total; + ktime_t total = engine->stats.total; + ktime_t start = engine->stats.start; - do { - seq = read_seqcount_begin(&engine->stats.lock); - total = __intel_engine_get_busy_time(engine, now); - } while (read_seqcount_retry(&engine->stats.lock, seq)); + /* + * If the engine is executing something at the moment + * add it to the total. + */ + *now = ktime_get(); + if (READ_ONCE(engine->stats.active)) { + smp_rmb(); /* pairs with intel_engine_context_in/out */ + total = ktime_add(total, ktime_sub(*now, start)); + } return total; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_stats.h b/drivers/gpu/drm/i915/gt/intel_engine_stats.h index 24fbdd94351a..1d8314257ffa 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_stats.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_stats.h @@ -15,46 +15,30 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine) { - unsigned long flags; - if (engine->stats.active) { engine->stats.active++; return; } /* 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); + smp_wmb(); /* pairs with intel_engine_get_busy_time() */ + WRITE_ONCE(engine->stats.active, 1); } static inline void intel_engine_context_out(struct intel_engine_cs *engine) { - unsigned long flags; - GEM_BUG_ON(!engine->stats.active); if (engine->stats.active > 1) { engine->stats.active--; return; } - 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); + smp_wmb(); /* pairs with intel_engine_get_busy_time() */ + WRITE_ONCE(engine->stats.active, 0); } #endif /* __INTEL_ENGINE_STATS_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index d2346b425547..ed13012b9338 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -518,11 +518,6 @@ struct intel_engine_cs { */ unsigned int active; - /** - * @lock: Lock protecting the below fields. - */ - seqcount_t lock; - /** * @total: Total time this engine was busy. * -- 2.20.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
