From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [PATCH 8/9] drm/i915: Track context current active time
Date: Wed, 18 Mar 2020 11:01:45 +0000 [thread overview]
Message-ID: <20200318110146.22339-9-tvrtko.ursulin@linux.intel.com> (raw)
In-Reply-To: <20200318110146.22339-1-tvrtko.ursulin@linux.intel.com>
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Track context active (on hardware) status together with the start
timestamp.
This will be used to provide better granularity of context
runtime reporting in conjunction with already tracked pphwsp accumulated
runtime.
The latter is only updated on context save so does not give us visibility
to any currently executing work.
As part of the patch the existing runtime tracking data is moved under the
new ce->stats member and updated under the seqlock. This provides the
ability to atomically read out accumulated plus active runtime.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 +-
drivers/gpu/drm/i915/gt/intel_context.c | 18 +++++-
drivers/gpu/drm/i915/gt/intel_context.h | 6 +-
drivers/gpu/drm/i915/gt/intel_context_types.h | 24 +++++---
drivers/gpu/drm/i915/gt/intel_lrc.c | 55 +++++++++++++++----
drivers/gpu/drm/i915/gt/selftest_lrc.c | 10 ++--
drivers/gpu/drm/i915/i915_drm_client.c | 2 +-
drivers/gpu/drm/i915/i915_gpu_error.c | 4 +-
8 files changed, 90 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9654f0ab3f45..8c67a1269142 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -266,7 +266,8 @@ static void free_engines_rcu(struct rcu_head *rcu)
unsigned int class = ce->engine->uabi_class;
GEM_BUG_ON(class >= ARRAY_SIZE(ctx->past_runtime));
- atomic64_add(ce->runtime.total, &ctx->past_runtime[class]);
+ atomic64_add(ce->stats.runtime.total,
+ &ctx->past_runtime[class]);
}
i915_gem_context_put(ctx);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 01474d3a558b..1f371f8b202a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -288,7 +288,7 @@ intel_context_init(struct intel_context *ce,
ce->sseu = engine->sseu;
ce->ring = __intel_context_ring_size(SZ_4K);
- ewma_runtime_init(&ce->runtime.avg);
+ ewma_runtime_init(&ce->stats.runtime.avg);
ce->vm = i915_vm_get(engine->gt->vm);
@@ -296,6 +296,7 @@ intel_context_init(struct intel_context *ce,
INIT_LIST_HEAD(&ce->signals);
mutex_init(&ce->pin_mutex);
+ seqlock_init(&ce->stats.lock);
i915_active_init(&ce->active,
__intel_context_active, __intel_context_retire);
@@ -390,6 +391,21 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
return rq;
}
+ktime_t intel_context_get_active_time(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned int seq;
+ ktime_t total = 0;
+
+ do {
+ seq = read_seqbegin(&stats->lock);
+ if (stats->active)
+ total = ktime_sub(ktime_get(), stats->start);
+ } while (read_seqretry(&stats->lock, seq));
+
+ return total;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_context.c"
#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 18efad255124..1f8b6e0bbfaf 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -233,7 +233,7 @@ static inline u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
const u32 period =
RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
- return READ_ONCE(ce->runtime.total) * period;
+ return READ_ONCE(ce->stats.runtime.total) * period;
}
static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
@@ -241,7 +241,9 @@ static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
const u32 period =
RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
- return mul_u32_u32(ewma_runtime_read(&ce->runtime.avg), period);
+ return mul_u32_u32(ewma_runtime_read(&ce->stats.runtime.avg), period);
}
+ktime_t intel_context_get_active_time(struct intel_context *ce);
+
#endif /* __INTEL_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index d5925c25f109..fe85a3b0b7f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/types.h>
+#include <linux/seqlock.h>
#include "i915_active_types.h"
#include "i915_utils.h"
@@ -72,14 +73,21 @@ struct intel_context {
u64 lrc_desc;
u32 tag; /* cookie passed to HW to track this context on submission */
- /* Time on GPU as tracked by the hw. */
- struct {
- struct ewma_runtime avg;
- u64 total;
- u32 last;
- I915_SELFTEST_DECLARE(u32 num_underflow);
- I915_SELFTEST_DECLARE(u32 max_underflow);
- } runtime;
+ /** stats: Context GPU engine busyness tracking. */
+ struct intel_context_stats {
+ seqlock_t lock;
+ bool active;
+ ktime_t start;
+
+ /* Time on GPU as tracked by the hw. */
+ struct {
+ struct ewma_runtime avg;
+ u64 total;
+ u32 last;
+ I915_SELFTEST_DECLARE(u32 num_underflow);
+ I915_SELFTEST_DECLARE(u32 max_underflow);
+ } runtime;
+ } stats;
unsigned int active_count; /* protected by timeline->mutex */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 112531b29f59..6143c6a9dea4 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1206,35 +1206,61 @@ static u32 intel_context_get_runtime(const struct intel_context *ce)
return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
}
-static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
+static void
+st_update_runtime_underflow(struct intel_context_stats *stats, s32 dt)
{
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
- ce->runtime.num_underflow += dt < 0;
- ce->runtime.max_underflow = max_t(u32, ce->runtime.max_underflow, -dt);
+ stats->runtime.num_underflow += dt < 0;
+ stats->runtime.max_underflow =
+ max_t(u32, stats->runtime.max_underflow, -dt);
#endif
}
static void intel_context_update_runtime(struct intel_context *ce)
{
+ struct intel_context_stats *stats = &ce->stats;
u32 old;
s32 dt;
if (intel_context_is_barrier(ce))
return;
- old = ce->runtime.last;
- ce->runtime.last = intel_context_get_runtime(ce);
- dt = ce->runtime.last - old;
+ old = stats->runtime.last;
+ stats->runtime.last = intel_context_get_runtime(ce);
+ dt = stats->runtime.last - old;
if (unlikely(dt <= 0)) {
CE_TRACE(ce, "runtime underflow: last=%u, new=%u, delta=%d\n",
- old, ce->runtime.last, dt);
- st_update_runtime_underflow(ce, dt);
+ old, stats->runtime.last, dt);
+ st_update_runtime_underflow(stats, dt);
return;
}
- ewma_runtime_add(&ce->runtime.avg, dt);
- ce->runtime.total += dt;
+ ewma_runtime_add(&stats->runtime.avg, dt);
+ stats->runtime.total += dt;
+}
+
+static void intel_context_stats_start(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned long flags;
+
+ write_seqlock_irqsave(&stats->lock, flags);
+ stats->start = ktime_get();
+ stats->active = true;
+ write_sequnlock_irqrestore(&stats->lock, flags);
+}
+
+static void intel_context_stats_stop(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+ unsigned long flags;
+
+ write_seqlock_irqsave(&stats->lock, flags);
+ stats->active = false;
+ stats->start = 0;
+ intel_context_update_runtime(ce);
+ write_sequnlock_irqrestore(&stats->lock, flags);
}
static inline struct intel_engine_cs *
@@ -1304,7 +1330,7 @@ static inline void
__execlists_schedule_out(struct i915_request *rq,
struct intel_engine_cs * const engine)
{
- struct intel_context * const ce = rq->context;
+ struct intel_context *ce = rq->context;
/*
* NB process_csb() is not under the engine->active.lock and hence
@@ -1320,8 +1346,8 @@ __execlists_schedule_out(struct i915_request *rq,
i915_request_completed(rq))
intel_engine_add_retire(engine, ce->timeline);
- intel_context_update_runtime(ce);
intel_engine_context_out(engine);
+ intel_context_stats_stop(ce);
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
intel_gt_pm_put_async(engine->gt);
@@ -1790,6 +1816,11 @@ active_timeslice(const struct intel_engine_cs *engine)
static void set_timeslice(struct intel_engine_cs *engine)
{
+ struct intel_engine_execlists * const execlists = &engine->execlists;
+
+ if (*execlists->active)
+ intel_context_stats_start((*execlists->active)->context);
+
if (!intel_engine_has_timeslices(engine))
return;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 6f06ba750a0a..6a51e7fa03ca 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -5479,8 +5479,8 @@ static int __live_pphwsp_runtime(struct intel_engine_cs *engine)
if (IS_ERR(ce))
return PTR_ERR(ce);
- ce->runtime.num_underflow = 0;
- ce->runtime.max_underflow = 0;
+ ce->stats.runtime.num_underflow = 0;
+ ce->stats.runtime.max_underflow = 0;
do {
unsigned int loop = 1024;
@@ -5518,11 +5518,11 @@ static int __live_pphwsp_runtime(struct intel_engine_cs *engine)
intel_context_get_avg_runtime_ns(ce));
err = 0;
- if (ce->runtime.num_underflow) {
+ if (ce->stats.runtime.num_underflow) {
pr_err("%s: pphwsp underflow %u time(s), max %u cycles!\n",
engine->name,
- ce->runtime.num_underflow,
- ce->runtime.max_underflow);
+ ce->stats.runtime.num_underflow,
+ ce->stats.runtime.max_underflow);
GEM_TRACE_DUMP();
err = -EOVERFLOW;
}
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 0a2d933fe83c..485a2b75d3e1 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -67,7 +67,7 @@ pphwsp_busy_add(struct i915_gem_context *ctx, unsigned int class)
for_each_gem_engine(ce, engines, it) {
if (ce->engine->uabi_class == class)
- total += ce->runtime.total;
+ total += ce->stats.runtime.total;
}
return total;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 653e1bc5050e..ce752572c38f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1267,8 +1267,8 @@ static bool record_context(struct i915_gem_context_coredump *e,
e->guilty = atomic_read(&ctx->guilty_count);
e->active = atomic_read(&ctx->active_count);
- e->total_runtime = rq->context->runtime.total;
- e->avg_runtime = ewma_runtime_read(&rq->context->runtime.avg);
+ e->total_runtime = rq->context->stats.runtime.total;
+ e->avg_runtime = ewma_runtime_read(&rq->context->stats.runtime.avg);
simulated = i915_gem_context_no_error_capture(ctx);
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-03-18 11:02 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-18 11:01 [Intel-gfx] [PATCH 0/9] Per client engine busyness Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 1/9] drm/i915: Update client name on context create Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 2/9] drm/i915: Make GEM contexts track DRM clients Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 3/9] drm/i915: Use explicit flag to mark unreachable intel_context Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 4/9] drm/i915: Track runtime spent in unreachable intel_contexts Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 5/9] drm/i915: Track runtime spent in closed GEM contexts Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 6/9] drm/i915: Track all user contexts per client Tvrtko Ursulin
2020-03-18 11:01 ` [Intel-gfx] [PATCH 7/9] drm/i915: Expose per-engine client busyness Tvrtko Ursulin
2020-03-18 11:01 ` Tvrtko Ursulin [this message]
2020-03-18 11:01 ` [Intel-gfx] [PATCH 9/9] drm/i915: Prefer software tracked context busyness Tvrtko Ursulin
2020-03-18 11:49 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for Per client engine busyness (rev8) Patchwork
2020-03-18 12:16 ` [Intel-gfx] [PATCH 0/9] Per client engine busyness Tvrtko Ursulin
2020-04-15 10:11 Tvrtko Ursulin
2020-04-15 10:11 ` [Intel-gfx] [PATCH 8/9] drm/i915: Track context current active time Tvrtko Ursulin
2020-09-04 12:59 [Intel-gfx] [PATCH 0/9] Per client engine busyness Tvrtko Ursulin
2020-09-04 12:59 ` [Intel-gfx] [PATCH 8/9] drm/i915: Track context current active time Tvrtko Ursulin
2020-09-14 13:12 [Intel-gfx] [PATCH 0/9] Per client engine busyness Tvrtko Ursulin
2020-09-14 13:12 ` [Intel-gfx] [PATCH 8/9] drm/i915: Track context current active time Tvrtko Ursulin
2021-01-19 12:10 [Intel-gfx] [PATCH 1/9] drm/i915/gt: Show the per-engine runtime in sysfs Chris Wilson
2021-01-19 12:10 ` [Intel-gfx] [PATCH 8/9] drm/i915: Track context current active time Chris Wilson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200318110146.22339-9-tvrtko.ursulin@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=Intel-gfx@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.