[Intel-gfx] [PATCH 6/8] drm/i915: Engine busy time tracking
Tvrtko Ursulin
tvrtko.ursulin at linux.intel.com
Tue Sep 26 12:30:06 UTC 2017
On 25/09/2017 18:43, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2017-09-25 16:15:41)
>> From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
>>
>> Track total time requests have been executing on the hardware.
>>
>> We add new kernel API to allow software tracking of time GPU
>> engines are spending executing requests.
>>
>> Both per-engine and global API is added with the latter also
>> being exported for use by external users.
>>
>> v2:
>> * Squashed with the internal API.
>> * Dropped static key.
>> * Made per-engine.
>> * Store time in monotonic ktime.
>>
>> v3: Moved stats clearing to disable.
>>
>> v4:
>> * Comments.
>> * Don't export the API just yet.
>>
>> v5: Whitespace cleanup.
>>
>> v6:
>> * Rename ref to active.
>> * Drop engine aggregate stats for now.
>> * Account initial busy period after enabling stats.
>>
>> v7:
>> * Rebase.
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
>> ---
>> drivers/gpu/drm/i915/intel_engine_cs.c | 84 ++++++++++++++++++++++++++++++
>> drivers/gpu/drm/i915/intel_lrc.c | 2 +
>> drivers/gpu/drm/i915/intel_ringbuffer.h | 92 +++++++++++++++++++++++++++++++++
>> 3 files changed, 178 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
>> index 35c117c3fa0d..8db83f504d70 100644
>> --- a/drivers/gpu/drm/i915/intel_engine_cs.c
>> +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
>> @@ -234,6 +234,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
>> /* Nothing to do here, execute in order of dependencies */
>> engine->schedule = NULL;
>>
>> + spin_lock_init(&engine->stats.lock);
>> +
>> ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
>>
>> dev_priv->engine_class[info->class][info->instance] = engine;
>> @@ -1613,6 +1615,88 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
>> return i915->engine_class[class][instance];
>> }
>>
>> +/**
>> + * intel_enable_engine_stats() - Enable engine busy tracking on engine
>> + * @engine: engine to enable stats collection
>> + *
>> + * Start collecting the engine busyness data for @engine.
>> + *
>> + * Returns 0 on success or a negative error code.
>> + */
>> +int intel_enable_engine_stats(struct intel_engine_cs *engine)
>> +{
>> + unsigned long flags;
>> +
>> + if (!i915_modparams.enable_execlists)
>> + return -ENODEV;
>> +
>> + spin_lock_irqsave(&engine->stats.lock, flags);
>> + if (engine->stats.enabled == ~0)
>> + goto busy;
>
> This still makes me go wut? Why not just refcount_t for this?
Because I need the spinlock anyway (in context in/out) so refcount_t for
enable doesn't sound like a gain to me.
>> + if (engine->stats.enabled++ == 0)
>> + engine->stats.enabled_at = ktime_get();
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +
>> + return 0;
>> +
>> +busy:
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +
>> + return -EBUSY;
>> +}
>> +
>> +/**
>> + * intel_disable_engine_stats() - Disable engine busy tracking on engine
>> + * @engine: engine to disable stats collection
>> + *
>> + * Stops collecting the engine busyness data for @engine.
>> + */
>> +void intel_disable_engine_stats(struct intel_engine_cs *engine)
>> +{
>> + unsigned long flags;
>> +
>> + if (!i915_modparams.enable_execlists)
>> + return;
>> +
>> + spin_lock_irqsave(&engine->stats.lock, flags);
>> + WARN_ON_ONCE(engine->stats.enabled == 0);
>> + if (--engine->stats.enabled == 0) {
>> + engine->stats.enabled_at = 0;
>> + engine->stats.active = 0;
>> + engine->stats.start = 0;
>> + engine->stats.total = 0;
>> + }
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +}
>> +
>> +/**
>> + * intel_engine_get_busy_time() - Return current accumulated engine busyness
>> + * @engine: engine to report on
>> + *
>> + * Returns accumulated time @engine was busy since engine stats were enabled.
>> + */
>> +ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
>> +{
>> + ktime_t total;
>> + unsigned long flags;
>> +
>> + spin_lock_irqsave(&engine->stats.lock, flags);
>> +
>> + total = engine->stats.total;
>> +
>> + /*
>> + * If the engine is executing something at the moment
>> + * add it to the total.
>> + */
>> + if (engine->stats.active)
>> + total = ktime_add(total,
>> + ktime_sub(ktime_get(), engine->stats.start));
>> +
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +
>> + return total;
>> +}
>> +
>> #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
>> #include "selftests/mock_engine.c"
>> #endif
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
>> index 7cd14b701ed7..1e743d3d16cb 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -366,12 +366,14 @@ execlists_context_status_change(struct drm_i915_gem_request *rq,
>> static inline void
>> execlists_context_schedule_in(struct drm_i915_gem_request *rq)
>> {
>> + intel_engine_context_in(rq->engine);
>> execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
>
> Symmetry: start accumulating after the notifier.
Ok.
>
>> }
>>
>> static inline void
>> execlists_context_schedule_out(struct drm_i915_gem_request *rq)
>> {
>> + intel_engine_context_out(rq->engine);
>> execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
>> }
>>
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> index 7a901e766d03..8db228ebdb28 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> @@ -538,6 +538,38 @@ struct intel_engine_cs {
>> * certain bits to encode the command length in the header).
>> */
>> u32 (*get_cmd_length_mask)(u32 cmd_header);
>> +
>> + struct {
>> + /**
>> + * @lock: Lock protecting the below fields.
>> + */
>> + spinlock_t lock;
>> + /**
>> + * @enabled: Reference count indicating number of listeners.
>> + */
>> + unsigned int enabled;
>> + /**
>> + * @active: Number of contexts currently scheduled in.
>> + */
>> + unsigned int active;
>> + /**
>> + * @enabled_at: Timestamp when busy stats were enabled.
>> + */
>> + ktime_t enabled_at;
>> + /**
>> + * @start: Timestamp of the last idle to active transition.
>> + *
>> + * Idle is defined as active == 0, active is active > 0.
>> + */
>> + ktime_t start;
>> + /**
>> + * @total: Total time this engine was busy.
>> + *
>> + * Accumulated time not counting the most recent block in cases
>> + * where engine is currently busy (active > 0).
>> + */
>> + ktime_t total;
>> + } stats;
>> };
>>
>> static inline unsigned int
>> @@ -859,4 +891,64 @@ bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
>> struct intel_engine_cs *
>> intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance);
>>
>> +static inline void intel_engine_context_in(struct intel_engine_cs *engine)
>> +{
>> + unsigned long flags;
>> +
>> + if (READ_ONCE(engine->stats.enabled) == 0)
>> + return;
>> +
>> + spin_lock_irqsave(&engine->stats.lock, flags);
>> +
>> + if (engine->stats.enabled > 0) {
>> + if (engine->stats.active++ == 0)
>> + engine->stats.start = ktime_get();
>> + GEM_BUG_ON(engine->stats.active == 0);
>> + }
>> +
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +}
>> +
>> +static inline void intel_engine_context_out(struct intel_engine_cs *engine)
>> +{
>> + unsigned long flags;
>> +
>> + if (READ_ONCE(engine->stats.enabled) == 0)
>> + return;
>> +
>> + spin_lock_irqsave(&engine->stats.lock, flags);
>> +
>> + if (engine->stats.enabled > 0) {
>> + ktime_t last, now = ktime_get();
>> +
>> + if (engine->stats.active && --engine->stats.active == 0) {
>> + /*
>> + * Decrement the active context count and in case GPU
>> + * is now idle add up to the running total.
>> + */
>> + last = ktime_sub(now, engine->stats.start);
>> +
>> + engine->stats.total = ktime_add(engine->stats.total,
>> + last);
>> + } else if (engine->stats.active == 0) {
>> + /*
>> + * After turning on engine stats, context out might be
>> + * the first event in which case we account from the
>> + * time stats gathering was turned on.
>> + */
>> + last = ktime_sub(now, engine->stats.enabled_at);
>> +
>> + engine->stats.total = ktime_add(engine->stats.total,
>> + last);
>> + }
>> + }
>> +
>> + spin_unlock_irqrestore(&engine->stats.lock, flags);
>> +}
>> +
>> +int intel_enable_engine_stats(struct intel_engine_cs *engine);
>> +void intel_disable_engine_stats(struct intel_engine_cs *engine);
>> +
>> +ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
>> +
>> #endif /* _INTEL_RINGBUFFER_H_ */
>> --
>> 2.9.5
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx at lists.freedesktop.org
>> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
Regards,
Tvrtko
More information about the Intel-gfx
mailing list