perf_counter: unify and fix delayed counter wakeup

While going over the wakeup code I noticed delayed wakeups only work
for hardware counters but basically all software counters rely on
them.

This patch unifies and generalizes the delayed wakeup to fix this
issue.

Since we're dealing with NMI context bits here, use a cmpxchg() based
single link list implementation to track counters that have pending
wakeups.

[ This should really be generic code for delayed wakeups, but since we
  cannot use cmpxchg()/xchg() in generic code, I've let it live in the
  perf_counter code. -- Eric Dumazet could use it to aggregate the
  network wakeups. ]

Furthermore, the x86 method of using TIF flags was flawed in that its
quite possible to end up setting the bit on the idle task, loosing the
wakeup.

The powerpc method uses per-cpu storage and does appear to be
sufficient.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171023.153932974@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 5 insertions, 23 deletions

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index cb32d57..20a44d0 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -132,7 +132,7 @@ static inline int irqs_disabled_flags(unsigned long flags)
 struct irq_chip;
 
 #ifdef CONFIG_PERF_COUNTERS
-static inline unsigned long get_perf_counter_pending(void)
+static inline unsigned long test_perf_counter_pending(void)
 {
 	unsigned long x;
 
@@ -160,7 +160,7 @@ extern void perf_counter_do_pending(void);
 
 #else
 
-static inline unsigned long get_perf_counter_pending(void)
+static inline unsigned long test_perf_counter_pending(void)
 {
 	return 0;
 }
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 469e963..2cd471f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -135,7 +135,7 @@ notrace void raw_local_irq_restore(unsigned long en)
 			iseries_handle_interrupts();
 	}
 
-	if (get_perf_counter_pending()) {
+	if (test_perf_counter_pending()) {
 		clear_perf_counter_pending();
 		perf_counter_do_pending();
 	}
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index df007fe..cde720f 100644
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -650,24 +650,6 @@ hw_perf_counter_init(struct perf_counter *counter)
 }
 
 /*
- * Handle wakeups.
- */
-void perf_counter_do_pending(void)
-{
-	int i;
-	struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters);
-	struct perf_counter *counter;
-
-	for (i = 0; i < cpuhw->n_counters; ++i) {
-		counter = cpuhw->counter[i];
-		if (counter && counter->wakeup_pending) {
-			counter->wakeup_pending = 0;
-			wake_up(&counter->waitq);
-		}
-	}
-}
-
-/*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
  * here so there is no possibility of being interrupted.
@@ -720,7 +702,7 @@ static void perf_counter_interrupt(struct pt_regs *regs)
 	struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters);
 	struct perf_counter *counter;
 	long val;
-	int need_wakeup = 0, found = 0;
+	int found = 0;
 
 	for (i = 0; i < cpuhw->n_counters; ++i) {
 		counter = cpuhw->counter[i];
@@ -761,7 +743,7 @@ static void perf_counter_interrupt(struct pt_regs *regs)
 	 * immediately; otherwise we'll have do the wakeup when interrupts
 	 * get soft-enabled.
 	 */
-	if (get_perf_counter_pending() && regs->softe) {
+	if (test_perf_counter_pending() && regs->softe) {
 		irq_enter();
 		clear_perf_counter_pending();
 		perf_counter_do_pending();