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 <[email protected]> --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 8 +++--- drivers/gpu/drm/i915/gt/intel_engine_stats.h | 28 +++++++------------- drivers/gpu/drm/i915/gt/intel_engine_types.h | 4 +-- 3 files changed, 15 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 39471674a40f..c378f1c4afff 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -338,7 +338,7 @@ 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); @@ -1606,7 +1606,7 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine) * If the engine is executing something at the moment * add it to the total. */ - if (atomic_read(&engine->stats.active)) + if (engine->stats.active) total = ktime_add(total, ktime_sub(ktime_get(), engine->stats.start)); @@ -1625,9 +1625,9 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine) ktime_t total; do { - seq = read_seqbegin(&engine->stats.lock); + seq = read_seqcount_begin(&engine->stats.lock); total = __intel_engine_get_busy_time(engine); - } while (read_seqretry(&engine->stats.lock, seq)); + } while (read_seqcount_retry(&engine->stats.lock, seq)); 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 58491eae3482..09e4aca8cff6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_stats.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_stats.h @@ -15,35 +15,25 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine) { - unsigned long flags; + raw_write_seqcount_begin(&engine->stats.lock); - if (atomic_add_unless(&engine->stats.active, 1, 0)) - return; - - write_seqlock_irqsave(&engine->stats.lock, flags); - if (!atomic_add_unless(&engine->stats.active, 1, 0)) { + if (!engine->stats.active++) engine->stats.start = ktime_get(); - atomic_inc(&engine->stats.active); - } - write_sequnlock_irqrestore(&engine->stats.lock, flags); + + raw_write_seqcount_end(&engine->stats.lock); } static inline void intel_engine_context_out(struct intel_engine_cs *engine) { - unsigned long flags; - - GEM_BUG_ON(!atomic_read(&engine->stats.active)); + raw_write_seqcount_begin(&engine->stats.lock); - if (atomic_add_unless(&engine->stats.active, -1, 1)) - return; - - write_seqlock_irqsave(&engine->stats.lock, flags); - if (atomic_dec_and_test(&engine->stats.active)) { + GEM_BUG_ON(!engine->stats.active); + if (!--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); + + raw_write_seqcount_end(&engine->stats.lock); } #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 ca124f229f65..50951a129db5 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -557,12 +557,12 @@ 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. -- 2.20.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
