From: Tvrtko Ursulin <tursulin@ursulin.net>
To: Intel-gfx@lists.freedesktop.org
Subject: [PATCH 9/9] drm/i915/pmu: Add RC6 residency metrics
Date: Mon, 13 Nov 2017 08:57:26 +0000 [thread overview]
Message-ID: <20171113085726.26817-10-tvrtko.ursulin@linux.intel.com> (raw)
In-Reply-To: <20171113085726.26817-1-tvrtko.ursulin@linux.intel.com>
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
For clients like intel-gpu-overlay it is easier to read the
counters via the perf API than having to parse sysfs.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_pmu.c | 31 +++++++++++++++++++++++++++++++
include/uapi/drm/i915_drm.h | 6 +++++-
2 files changed, 36 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 9e257b42dcc4..ccf30e1ae4a6 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -361,6 +361,15 @@ static int i915_pmu_event_init(struct perf_event *event)
break;
case I915_PMU_INTERRUPTS:
break;
+ case I915_PMU_RC6_RESIDENCY:
+ if (!HAS_RC6(i915))
+ ret = -ENODEV;
+ break;
+ case I915_PMU_RC6p_RESIDENCY:
+ case I915_PMU_RC6pp_RESIDENCY:
+ if (!HAS_RC6p(i915))
+ ret = -ENODEV;
+ break;
default:
ret = -ENOENT;
break;
@@ -413,6 +422,24 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
case I915_PMU_INTERRUPTS:
val = count_interrupts(i915);
break;
+ case I915_PMU_RC6_RESIDENCY:
+ intel_runtime_pm_get(i915);
+ val = intel_rc6_residency_ns(i915,
+ IS_VALLEYVIEW(i915) ?
+ VLV_GT_RENDER_RC6 :
+ GEN6_GT_GFX_RC6);
+ intel_runtime_pm_put(i915);
+ break;
+ case I915_PMU_RC6p_RESIDENCY:
+ intel_runtime_pm_get(i915);
+ val = intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+ intel_runtime_pm_put(i915);
+ break;
+ case I915_PMU_RC6pp_RESIDENCY:
+ intel_runtime_pm_get(i915);
+ val = intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+ intel_runtime_pm_put(i915);
+ break;
}
}
@@ -677,6 +704,10 @@ static struct attribute *i915_pmu_events_attrs[] = {
I915_EVENT_ATTR(interrupts, I915_PMU_INTERRUPTS),
+ I915_EVENT(rc6-residency, I915_PMU_RC6_RESIDENCY, "ns"),
+ I915_EVENT(rc6p-residency, I915_PMU_RC6p_RESIDENCY, "ns"),
+ I915_EVENT(rc6pp-residency, I915_PMU_RC6pp_RESIDENCY, "ns"),
+
NULL,
};
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 5d0d4019e3f2..819effa3c8df 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -141,7 +141,11 @@ enum drm_i915_pmu_engine_sample {
#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2)
-#define I915_PMU_LAST I915_PMU_INTERRUPTS
+#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3)
+#define I915_PMU_RC6p_RESIDENCY __I915_PMU_OTHER(4)
+#define I915_PMU_RC6pp_RESIDENCY __I915_PMU_OTHER(5)
+
+#define I915_PMU_LAST I915_PMU_RC6pp_RESIDENCY
/* Each region is a minimum of 16k, and there are at most 255 of them.
*/
--
2.14.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2017-11-13 8:57 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-13 8:57 [PATCH v10 0/9] i915 PMU and engine busy stats Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 1/9] drm/i915: Extract intel_get_cagf Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 2/9] drm/i915/pmu: Expose a PMU interface for perf queries Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 3/9] drm/i915/pmu: Suspend sampling when GPU is idle Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 4/9] drm/i915: Wrap context schedule notification Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 5/9] drm/i915: Engine busy time tracking Tvrtko Ursulin
2017-11-15 14:27 ` Chris Wilson
2017-11-13 8:57 ` [PATCH 6/9] drm/i915/pmu: Wire up engine busy stats to PMU Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 7/9] drm/i915/pmu: Add interrupt count metric Tvrtko Ursulin
2017-11-13 8:57 ` [PATCH 8/9] drm/i915: Convert intel_rc6_residency_us to ns Tvrtko Ursulin
2017-11-13 8:57 ` Tvrtko Ursulin [this message]
2017-11-13 9:51 ` ✗ Fi.CI.BAT: warning for i915 PMU and engine busy stats (rev22) Patchwork
2017-11-14 13:00 ` ✓ Fi.CI.BAT: success " Patchwork
2017-11-14 14:20 ` ✓ Fi.CI.IGT: " Patchwork
2017-11-15 14:31 ` [PATCH v10 0/9] i915 PMU and engine busy stats Chris Wilson
-- strict thread matches above, loose matches on Subject: below --
2017-10-25 9:05 [PATCH v9 " Tvrtko Ursulin
2017-10-25 9:06 ` [PATCH 9/9] drm/i915/pmu: Add RC6 residency metrics Tvrtko Ursulin
2017-10-20 9:24 [PATCH v8 0/9] i915 PMU and engine busy stats Tvrtko Ursulin
2017-10-20 9:24 ` [PATCH 9/9] drm/i915/pmu: Add RC6 residency metrics Tvrtko Ursulin
2017-10-11 12:55 [PATCH v7 0/9] i915 PMU and engine busy stats Tvrtko Ursulin
2017-10-11 12:55 ` [PATCH 9/9] drm/i915/pmu: Add RC6 residency metrics Tvrtko Ursulin
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=20171113085726.26817-10-tvrtko.ursulin@linux.intel.com \
--to=tursulin@ursulin.net \
--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.