[PATCH v2 11/11] perf/x86: Simplify put_exclusive_constraints

From: Peter Zijlstra
Date: Fri May 22 2015 - 09:35:40 EST


Don't bother with taking locks if we're not actually going to do
anything. Also, drop the _irqsave(), this is very much only called
from IRQ-disabled context.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
arch/x86/kernel/cpu/perf_event_intel.c | 29 +++++++++++++++--------------
1 file changed, 15 insertions(+), 14 deletions(-)

--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2130,7 +2130,6 @@ static void intel_put_excl_constraints(s
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
int tid = cpuc->excl_thread_id;
struct intel_excl_states *xl;
- unsigned long flags = 0; /* keep compiler happy */

/*
* nothing needed if in group validation mode
@@ -2141,7 +2140,6 @@ static void intel_put_excl_constraints(s
if (WARN_ON_ONCE(!excl_cntrs))
return;

- xl = &excl_cntrs->states[tid];
if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
if (!--cpuc->n_excl)
@@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(s
}

/*
- * put_constraint may be called from x86_schedule_events()
- * which already has the lock held so here make locking
- * conditional
+ * If event was actually assigned, then mark the counter state as
+ * unused now.
*/
- if (!xl->sched_started)
- raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+ if (hwc->idx >= 0) {
+ xl = &excl_cntrs->states[tid];
+
+ /*
+ * put_constraint may be called from x86_schedule_events()
+ * which already has the lock held so here make locking
+ * conditional.
+ */
+ if (!xl->sched_started)
+ raw_spin_lock(&excl_cntrs->lock);

- /*
- * if event was actually assigned, then mark the
- * counter state as unused now
- */
- if (hwc->idx >= 0)
xl->state[hwc->idx] = INTEL_EXCL_UNUSED;

- if (!xl->sched_started)
- raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+ if (!xl->sched_started)
+ raw_spin_unlock(&excl_cntrs->lock);
+ }
}

static void


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/