mirror of
https://github.com/torvalds/linux.git
synced 2024-12-01 16:41:39 +00:00
drm/i915/pmu: Add a name to the execlists stats
In preparation for GuC pmu stats, add a name to the execlists stats structure so that it can be differentiated from the GuC stats. Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20211027004821.66097-1-umesh.nerlige.ramappa@intel.com
This commit is contained in:
parent
64512a66b6
commit
344e694722
@ -363,7 +363,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
|
||||
DRIVER_CAPS(i915)->has_logical_contexts = true;
|
||||
|
||||
ewma__engine_latency_init(&engine->latency);
|
||||
seqcount_init(&engine->stats.lock);
|
||||
seqcount_init(&engine->stats.execlists.lock);
|
||||
|
||||
ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
|
||||
|
||||
@ -1918,15 +1918,16 @@ void intel_engine_dump(struct intel_engine_cs *engine,
|
||||
static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine,
|
||||
ktime_t *now)
|
||||
{
|
||||
ktime_t total = engine->stats.total;
|
||||
struct intel_engine_execlists_stats *stats = &engine->stats.execlists;
|
||||
ktime_t total = 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));
|
||||
if (READ_ONCE(stats->active))
|
||||
total = ktime_add(total, ktime_sub(*now, stats->start));
|
||||
|
||||
return total;
|
||||
}
|
||||
@ -1940,13 +1941,14 @@ 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)
|
||||
{
|
||||
struct intel_engine_execlists_stats *stats = &engine->stats.execlists;
|
||||
unsigned int seq;
|
||||
ktime_t total;
|
||||
|
||||
do {
|
||||
seq = read_seqcount_begin(&engine->stats.lock);
|
||||
seq = read_seqcount_begin(&stats->lock);
|
||||
total = __intel_engine_get_busy_time(engine, now);
|
||||
} while (read_seqcount_retry(&engine->stats.lock, seq));
|
||||
} while (read_seqcount_retry(&stats->lock, seq));
|
||||
|
||||
return total;
|
||||
}
|
||||
|
@ -15,45 +15,46 @@
|
||||
|
||||
static inline void intel_engine_context_in(struct intel_engine_cs *engine)
|
||||
{
|
||||
struct intel_engine_execlists_stats *stats = &engine->stats.execlists;
|
||||
unsigned long flags;
|
||||
|
||||
if (engine->stats.active) {
|
||||
engine->stats.active++;
|
||||
if (stats->active) {
|
||||
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);
|
||||
write_seqcount_begin(&stats->lock);
|
||||
|
||||
engine->stats.start = ktime_get();
|
||||
engine->stats.active++;
|
||||
stats->start = ktime_get();
|
||||
stats->active++;
|
||||
|
||||
write_seqcount_end(&engine->stats.lock);
|
||||
write_seqcount_end(&stats->lock);
|
||||
local_irq_restore(flags);
|
||||
|
||||
GEM_BUG_ON(!engine->stats.active);
|
||||
GEM_BUG_ON(!stats->active);
|
||||
}
|
||||
|
||||
static inline void intel_engine_context_out(struct intel_engine_cs *engine)
|
||||
{
|
||||
struct intel_engine_execlists_stats *stats = &engine->stats.execlists;
|
||||
unsigned long flags;
|
||||
|
||||
GEM_BUG_ON(!engine->stats.active);
|
||||
if (engine->stats.active > 1) {
|
||||
engine->stats.active--;
|
||||
GEM_BUG_ON(!stats->active);
|
||||
if (stats->active > 1) {
|
||||
stats->active--;
|
||||
return;
|
||||
}
|
||||
|
||||
local_irq_save(flags);
|
||||
write_seqcount_begin(&engine->stats.lock);
|
||||
write_seqcount_begin(&stats->lock);
|
||||
|
||||
engine->stats.active--;
|
||||
engine->stats.total =
|
||||
ktime_add(engine->stats.total,
|
||||
ktime_sub(ktime_get(), engine->stats.start));
|
||||
stats->active--;
|
||||
stats->total = ktime_add(stats->total,
|
||||
ktime_sub(ktime_get(), stats->start));
|
||||
|
||||
write_seqcount_end(&engine->stats.lock);
|
||||
write_seqcount_end(&stats->lock);
|
||||
local_irq_restore(flags);
|
||||
}
|
||||
|
||||
|
@ -257,6 +257,33 @@ struct intel_engine_execlists {
|
||||
|
||||
#define INTEL_ENGINE_CS_MAX_NAME 8
|
||||
|
||||
struct intel_engine_execlists_stats {
|
||||
/**
|
||||
* @active: Number of contexts currently scheduled in.
|
||||
*/
|
||||
unsigned int active;
|
||||
|
||||
/**
|
||||
* @lock: Lock protecting the below fields.
|
||||
*/
|
||||
seqcount_t lock;
|
||||
|
||||
/**
|
||||
* @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;
|
||||
|
||||
/**
|
||||
* @start: Timestamp of the last idle to active transition.
|
||||
*
|
||||
* Idle is defined as active == 0, active is active > 0.
|
||||
*/
|
||||
ktime_t start;
|
||||
};
|
||||
|
||||
struct intel_engine_cs {
|
||||
struct drm_i915_private *i915;
|
||||
struct intel_gt *gt;
|
||||
@ -488,30 +515,7 @@ struct intel_engine_cs {
|
||||
u32 (*get_cmd_length_mask)(u32 cmd_header);
|
||||
|
||||
struct {
|
||||
/**
|
||||
* @active: Number of contexts currently scheduled in.
|
||||
*/
|
||||
unsigned int active;
|
||||
|
||||
/**
|
||||
* @lock: Lock protecting the below fields.
|
||||
*/
|
||||
seqcount_t lock;
|
||||
|
||||
/**
|
||||
* @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;
|
||||
|
||||
/**
|
||||
* @start: Timestamp of the last idle to active transition.
|
||||
*
|
||||
* Idle is defined as active == 0, active is active > 0.
|
||||
*/
|
||||
ktime_t start;
|
||||
struct intel_engine_execlists_stats execlists;
|
||||
|
||||
/**
|
||||
* @rps: Utilisation at last RPS sampling.
|
||||
|
Loading…
Reference in New Issue
Block a user