From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [RFC 05/10] drm/i915: Track runtime spent in unreachable intel_contexts
Date: Wed, 11 Mar 2020 18:26:13 +0000 [thread overview]
Message-ID: <20200311182618.21513-6-tvrtko.ursulin@linux.intel.com> (raw)
In-Reply-To: <20200311182618.21513-1-tvrtko.ursulin@linux.intel.com>
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
As contexts are abandoned we want to remember how much GPU time they used
(per class) so later we can used it for smarter purposes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++++++++++-
drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 5 +++++
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index c49cfec6d616..c521155a6474 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -257,7 +257,19 @@ static void free_engines_rcu(struct rcu_head *rcu)
{
struct i915_gem_engines *engines =
container_of(rcu, struct i915_gem_engines, rcu);
+ struct i915_gem_context *ctx = engines->ctx;
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+
+ /* Transfer accumulated runtime to the parent GEM context. */
+ for_each_gem_engine(ce, engines, it) {
+ 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]);
+ }
+
+ i915_gem_context_put(ctx);
i915_sw_fence_fini(&engines->fence);
free_engines(engines);
}
@@ -540,7 +552,6 @@ static int engines_notify(struct i915_sw_fence *fence,
list_del(&engines->link);
spin_unlock_irqrestore(&ctx->stale.lock, flags);
}
- i915_gem_context_put(engines->ctx);
break;
case FENCE_FREE:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index b0e03380c690..f0d7441aafc8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -177,6 +177,11 @@ struct i915_gem_context {
spinlock_t lock;
struct list_head engines;
} stale;
+
+ /**
+ * @past_runtime: Accumulation of freed intel_context pphwsp runtimes.
+ */
+ atomic64_t past_runtime[MAX_ENGINE_CLASS + 1];
};
#endif /* __I915_GEM_CONTEXT_TYPES_H__ */
--
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:[~2020-03-11 18:26 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-11 18:26 [Intel-gfx] [RFC 00/12] Per client engine busyness Tvrtko Ursulin
2020-03-11 18:26 ` [Intel-gfx] [RFC 01/10] drm/i915: Expose list of clients in sysfs Tvrtko Ursulin
2020-03-13 10:36 ` Chris Wilson
2020-03-11 18:26 ` [Intel-gfx] [RFC 02/10] drm/i915: Update client name on context create Tvrtko Ursulin
2020-03-13 10:41 ` Chris Wilson
2020-03-11 18:26 ` [Intel-gfx] [RFC 03/10] drm/i915: Make GEM contexts track DRM clients Tvrtko Ursulin
2020-03-13 11:00 ` Chris Wilson
2020-03-11 18:26 ` [Intel-gfx] [RFC 04/10] drm/i915: Use explicit flag to mark unreachable intel_context Tvrtko Ursulin
2020-03-13 11:03 ` Chris Wilson
2020-03-11 18:26 ` Tvrtko Ursulin [this message]
2020-03-11 18:26 ` [Intel-gfx] [RFC 06/10] drm/i915: Track runtime spent in closed GEM contexts Tvrtko Ursulin
2020-03-11 18:26 ` [Intel-gfx] [RFC 07/10] drm/i915: Track all user contexts per client Tvrtko Ursulin
2020-03-11 18:26 ` [Intel-gfx] [RFC 08/10] drm/i915: Expose per-engine client busyness Tvrtko Ursulin
2020-03-11 18:26 ` [Intel-gfx] [RFC 09/10] drm/i915: Track context current active time Tvrtko Ursulin
2020-03-11 18:26 ` [Intel-gfx] [RFC 10/10] drm/i915: Prefer software tracked context busyness Tvrtko Ursulin
2020-03-12 2:08 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Per client engine busyness (rev6) Patchwork
2020-03-12 2:14 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-03-12 2:33 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-03-13 10:28 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Per client engine busyness (rev7) Patchwork
2020-03-13 10:34 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-03-13 10:54 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-03-13 17:26 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
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=20200311182618.21513-6-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.