perf/core: Add return value for perf_event_read()

When we implement the ability to read several counters at once (using
the PERF_PMU_TXN_READ transaction interface), perf_event_read() can
fail when the 'group' parameter is true (eg: trying to read too many
events at once).

For now, have perf_event_read() return an integer. Ignore the return
value when the 'group' parameter is false.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1441336073-22750-8-git-send-email-sukadev@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd2a0b8..ade04df 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3187,6 +3187,7 @@ void perf_event_exec(void)
 struct perf_read_data {
        struct perf_event *event;
        bool group;
+       int ret;
 };
 
 /*
@@ -3227,6 +3228,7 @@ static void __perf_event_read(void *info)
                if (sub->state == PERF_EVENT_STATE_ACTIVE)
                        sub->pmu->read(sub);
        }
+       data->ret = 0;
 
 unlock:
        raw_spin_unlock(&ctx->lock);
@@ -3293,8 +3295,10 @@ u64 perf_event_read_local(struct perf_event *event)
        return val;
 }
 
-static void perf_event_read(struct perf_event *event, bool group)
+static int perf_event_read(struct perf_event *event, bool group)
 {
+       int ret = 0;
+
        /*
         * If event is enabled and currently active on a CPU, update the
         * value in the event structure:
@@ -3303,9 +3307,11 @@ static void perf_event_read(struct perf_event *event, bool group)
                struct perf_read_data data = {
                        .event = event,
                        .group = group,
+                       .ret = 0,
                };
                smp_call_function_single(event->oncpu,
                                         __perf_event_read, &data, 1);
+               ret = data.ret;
        } else if (event->state == PERF_EVENT_STATE_INACTIVE) {
                struct perf_event_context *ctx = event->ctx;
                unsigned long flags;
@@ -3326,6 +3332,8 @@ static void perf_event_read(struct perf_event *event, bool group)
                        update_event_times(event);
                raw_spin_unlock_irqrestore(&ctx->lock, flags);
        }
+
+       return ret;
 }
 
 /*
@@ -3842,7 +3850,7 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 
        mutex_lock(&event->child_mutex);
 
-       perf_event_read(event, false);
+       (void)perf_event_read(event, false);
        total += perf_event_count(event);
 
        *enabled += event->total_time_enabled +
@@ -3851,7 +3859,7 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
                        atomic64_read(&event->child_total_time_running);
 
        list_for_each_entry(child, &event->child_list, child_list) {
-               perf_event_read(child, false);
+               (void)perf_event_read(child, false);
                total += perf_event_count(child);
                *enabled += child->total_time_enabled;
                *running += child->total_time_running;
@@ -3862,13 +3870,16 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 }
 EXPORT_SYMBOL_GPL(perf_event_read_value);
 
-static void __perf_read_group_add(struct perf_event *leader,
+static int __perf_read_group_add(struct perf_event *leader,
                                        u64 read_format, u64 *values)
 {
        struct perf_event *sub;
        int n = 1; /* skip @nr */
+       int ret;
 
-       perf_event_read(leader, true);
+       ret = perf_event_read(leader, true);
+       if (ret)
+               return ret;
 
        /*
         * Since we co-schedule groups, {enabled,running} times of siblings
@@ -3897,6 +3908,8 @@ static void __perf_read_group_add(struct perf_event *leader,
                if (read_format & PERF_FORMAT_ID)
                        values[n++] = primary_event_id(sub);
        }
+
+       return 0;
 }
 
 static int perf_read_group(struct perf_event *event,
@@ -3904,7 +3917,7 @@ static int perf_read_group(struct perf_event *event,
 {
        struct perf_event *leader = event->group_leader, *child;
        struct perf_event_context *ctx = leader->ctx;
-       int ret = event->read_size;
+       int ret;
        u64 *values;
 
        lockdep_assert_held(&ctx->mutex);
@@ -3921,17 +3934,27 @@ static int perf_read_group(struct perf_event *event,
         */
        mutex_lock(&leader->child_mutex);
 
-       __perf_read_group_add(leader, read_format, values);
-       list_for_each_entry(child, &leader->child_list, child_list)
-               __perf_read_group_add(child, read_format, values);
+       ret = __perf_read_group_add(leader, read_format, values);
+       if (ret)
+               goto unlock;
+
+       list_for_each_entry(child, &leader->child_list, child_list) {
+               ret = __perf_read_group_add(child, read_format, values);
+               if (ret)
+                       goto unlock;
+       }
 
        mutex_unlock(&leader->child_mutex);
 
+       ret = event->read_size;
        if (copy_to_user(buf, values, event->read_size))
                ret = -EFAULT;
+       goto out;
 
+unlock:
+       mutex_unlock(&leader->child_mutex);
+out:
        kfree(values);
-
        return ret;
 }
 
@@ -4037,7 +4060,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 
 static void _perf_event_reset(struct perf_event *event)
 {
-       perf_event_read(event, false);
+       (void)perf_event_read(event, false);
        local64_set(&event->count, 0);
        perf_event_update_userpage(event);
 }