perf_counter: change event definition

Currently the definition of an event is slightly ambiguous. We have
wakeup events, for poll() and SIGIO, which are either generated
when a record crosses a page boundary (hw_events.wakeup_events == 0),
or every wakeup_events new records.

Now a record can be either a counter overflow record, or a number of
different things, like the mmap PROT_EXEC region notifications.

Then there is the PERF_COUNTER_IOC_REFRESH event limit, which only
considers counter overflows.

This patch changes then wakeup_events and SIGIO notification to only
consider overflow events. Furthermore it changes the SIGIO notification
to report SIGHUP when the event limit is reached and the counter will
be disabled.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090406094518.266679874@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

include/linux/perf_counter.h

@@ -439,6 +439,7 @@ struct perf_counter {
 
 	/* delayed work for NMIs and such */
 	int				pending_wakeup;
+	int				pending_kill;
 	int				pending_disable;
 	struct perf_pending_entry	pending;
 

kernel/perf_counter.c

@@ -1596,7 +1596,11 @@ void perf_counter_wakeup(struct perf_counter *counter)
 	rcu_read_unlock();
 
 	wake_up_all(&counter->waitq);
-	kill_fasync(&counter->fasync, SIGIO, POLL_IN);
+
+	if (counter->pending_kill) {
+		kill_fasync(&counter->fasync, SIGIO, counter->pending_kill);
+		counter->pending_kill = 0;
+	}
 }
 
 /*
@@ -1727,6 +1731,7 @@ struct perf_output_handle {
 	unsigned int		head;
 	int			wakeup;
 	int			nmi;
+	int			overflow;
 };
 
 static inline void __perf_output_wakeup(struct perf_output_handle *handle)
@@ -1741,7 +1746,7 @@ static inline void __perf_output_wakeup(struct perf_output_handle *handle)
 
 static int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_counter *counter, unsigned int size,
-			     int nmi)
+			     int nmi, int overflow)
 {
 	struct perf_mmap_data *data;
 	unsigned int offset, head;
@@ -1751,8 +1756,9 @@ static int perf_output_begin(struct perf_output_handle *handle,
 	if (!data)
 		goto out;
 
-	handle->counter	= counter;
-	handle->nmi	= nmi;
+	handle->counter	 = counter;
+	handle->nmi	 = nmi;
+	handle->overflow = overflow;
 
 	if (!data->nr_pages)
 		goto fail;
@@ -1816,7 +1822,7 @@ static void perf_output_end(struct perf_output_handle *handle)
 {
 	int wakeup_events = handle->counter->hw_event.wakeup_events;
 
-	if (wakeup_events) {
+	if (handle->overflow && wakeup_events) {
 		int events = atomic_inc_return(&handle->data->events);
 		if (events >= wakeup_events) {
 			atomic_sub(wakeup_events, &handle->data->events);
@@ -1891,7 +1897,7 @@ static void perf_counter_output(struct perf_counter *counter,
 		header.size += sizeof(u64);
 	}
 
-	ret = perf_output_begin(&handle, counter, header.size, nmi);
+	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
 	if (ret)
 		return;
 
@@ -1955,7 +1961,7 @@ static void perf_counter_mmap_output(struct perf_counter *counter,
 {
 	struct perf_output_handle handle;
 	int size = mmap_event->event.header.size;
-	int ret = perf_output_begin(&handle, counter, size, 0);
+	int ret = perf_output_begin(&handle, counter, size, 0, 0);
 
 	if (ret)
 		return;
@@ -2084,8 +2090,10 @@ int perf_counter_overflow(struct perf_counter *counter,
 	int events = atomic_read(&counter->event_limit);
 	int ret = 0;
 
+	counter->pending_kill = POLL_IN;
 	if (events && atomic_dec_and_test(&counter->event_limit)) {
 		ret = 1;
+		counter->pending_kill = POLL_HUP;
 		if (nmi) {
 			counter->pending_disable = 1;
 			perf_pending_queue(&counter->pending,