Commit 1fe699e3 authored by Tvrtko Ursulin's avatar Tvrtko Ursulin

drm/i915/pmu: Fix sleep under atomic in RC6 readout

We are not allowed to call intel_runtime_pm_get from the PMU counter read
callback since the former can sleep, and the latter is running under IRQ
context.

To workaround this, we record the last known RC6 and while runtime
suspended estimate its increase by querying the runtime PM core
timestamps.

Downside of this approach is that we can temporarily lose a chunk of RC6
time, from the last PMU read-out to runtime suspend entry, but that will
eventually catch up, once device comes back online and in the presence of
PMU queries.

Also, we have to be careful not to overshoot the RC6 estimate, so once
resumed after a period of approximation, we only update the counter once
it catches up. With the observation that RC6 is increasing while the
device is suspended, this should not pose a problem and can only cause
slight inaccuracies due clock base differences.

v2: Simplify by estimating on top of PM core counters. (Imre)
Signed-off-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104943
Fixes: 6060b6ae ("drm/i915/pmu: Add RC6 residency metrics")
Testcase: igt/perf_pmu/rc6-runtime-pm
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: intel-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180206183311.17924-1-tvrtko.ursulin@linux.intel.com
parent 8177e112
...@@ -415,7 +415,81 @@ static int i915_pmu_event_init(struct perf_event *event) ...@@ -415,7 +415,81 @@ static int i915_pmu_event_init(struct perf_event *event)
return 0; return 0;
} }
static u64 __i915_pmu_event_read(struct perf_event *event) static u64 get_rc6(struct drm_i915_private *i915, bool locked)
{
unsigned long flags;
u64 val;
if (intel_runtime_pm_get_if_in_use(i915)) {
val = intel_rc6_residency_ns(i915, IS_VALLEYVIEW(i915) ?
VLV_GT_RENDER_RC6 :
GEN6_GT_GFX_RC6);
if (HAS_RC6p(i915))
val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
if (HAS_RC6pp(i915))
val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
intel_runtime_pm_put(i915);
/*
* If we are coming back from being runtime suspended we must
* be careful not to report a larger value than returned
* previously.
*/
if (!locked)
spin_lock_irqsave(&i915->pmu.lock, flags);
if (val >= i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0;
i915->pmu.sample[__I915_SAMPLE_RC6].cur = val;
} else {
val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
}
if (!locked)
spin_unlock_irqrestore(&i915->pmu.lock, flags);
} else {
struct pci_dev *pdev = i915->drm.pdev;
struct device *kdev = &pdev->dev;
unsigned long flags2;
/*
* We are runtime suspended.
*
* Report the delta from when the device was suspended to now,
* on top of the last known real value, as the approximated RC6
* counter value.
*/
if (!locked)
spin_lock_irqsave(&i915->pmu.lock, flags);
spin_lock_irqsave(&kdev->power.lock, flags2);
if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
i915->pmu.suspended_jiffies_last =
kdev->power.suspended_jiffies;
val = kdev->power.suspended_jiffies -
i915->pmu.suspended_jiffies_last;
val += jiffies - kdev->power.accounting_timestamp;
spin_unlock_irqrestore(&kdev->power.lock, flags2);
val = jiffies_to_nsecs(val);
val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
if (!locked)
spin_unlock_irqrestore(&i915->pmu.lock, flags);
}
return val;
}
static u64 __i915_pmu_event_read(struct perf_event *event, bool locked)
{ {
struct drm_i915_private *i915 = struct drm_i915_private *i915 =
container_of(event->pmu, typeof(*i915), pmu.base); container_of(event->pmu, typeof(*i915), pmu.base);
...@@ -453,18 +527,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event) ...@@ -453,18 +527,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
val = count_interrupts(i915); val = count_interrupts(i915);
break; break;
case I915_PMU_RC6_RESIDENCY: case I915_PMU_RC6_RESIDENCY:
intel_runtime_pm_get(i915); val = get_rc6(i915, locked);
val = intel_rc6_residency_ns(i915,
IS_VALLEYVIEW(i915) ?
VLV_GT_RENDER_RC6 :
GEN6_GT_GFX_RC6);
if (HAS_RC6p(i915))
val += intel_rc6_residency_ns(i915,
GEN6_GT_GFX_RC6p);
if (HAS_RC6pp(i915))
val += intel_rc6_residency_ns(i915,
GEN6_GT_GFX_RC6pp);
intel_runtime_pm_put(i915);
break; break;
} }
} }
...@@ -479,7 +542,7 @@ static void i915_pmu_event_read(struct perf_event *event) ...@@ -479,7 +542,7 @@ static void i915_pmu_event_read(struct perf_event *event)
again: again:
prev = local64_read(&hwc->prev_count); prev = local64_read(&hwc->prev_count);
new = __i915_pmu_event_read(event); new = __i915_pmu_event_read(event, false);
if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev) if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev)
goto again; goto again;
...@@ -534,7 +597,7 @@ static void i915_pmu_enable(struct perf_event *event) ...@@ -534,7 +597,7 @@ static void i915_pmu_enable(struct perf_event *event)
* for all listeners. Even when the event was already enabled and has * for all listeners. Even when the event was already enabled and has
* an existing non-zero value. * an existing non-zero value.
*/ */
local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); local64_set(&event->hw.prev_count, __i915_pmu_event_read(event, true));
spin_unlock_irqrestore(&i915->pmu.lock, flags); spin_unlock_irqrestore(&i915->pmu.lock, flags);
} }
......
...@@ -27,6 +27,8 @@ ...@@ -27,6 +27,8 @@
enum { enum {
__I915_SAMPLE_FREQ_ACT = 0, __I915_SAMPLE_FREQ_ACT = 0,
__I915_SAMPLE_FREQ_REQ, __I915_SAMPLE_FREQ_REQ,
__I915_SAMPLE_RC6,
__I915_SAMPLE_RC6_ESTIMATED,
__I915_NUM_PMU_SAMPLERS __I915_NUM_PMU_SAMPLERS
}; };
...@@ -94,6 +96,10 @@ struct i915_pmu { ...@@ -94,6 +96,10 @@ struct i915_pmu {
* struct intel_engine_cs. * struct intel_engine_cs.
*/ */
struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS]; struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
/**
* @suspended_jiffies_last: Cached suspend time from PM core.
*/
unsigned long suspended_jiffies_last;
/** /**
* @i915_attr: Memory block holding device attributes. * @i915_attr: Memory block holding device attributes.
*/ */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment