perf/ftrace: Fix double traces of perf on ftrace:function

When running perf on the ftrace:function tracepoint, there is a bug
which can be reproduced by:

  perf record -e ftrace:function -a sleep 20 &
  perf record -e ftrace:function ls
  perf script

              ls 10304 [005]   171.853235: ftrace:function:
  perf_output_begin
              ls 10304 [005]   171.853237: ftrace:function:
  perf_output_begin
              ls 10304 [005]   171.853239: ftrace:function:
  task_tgid_nr_ns
              ls 10304 [005]   171.853240: ftrace:function:
  task_tgid_nr_ns
              ls 10304 [005]   171.853242: ftrace:function:
  __task_pid_nr_ns
              ls 10304 [005]   171.853244: ftrace:function:
  __task_pid_nr_ns

We can see that all the function traces are doubled.

The problem is caused by the inconsistency of the register
function perf_ftrace_event_register() with the probe function
perf_ftrace_function_call(). The former registers one probe
for every perf_event. And the latter handles all perf_events
on the current cpu. So when two perf_events on the current cpu,
the traces of them will be doubled.

So this patch adds an extra parameter "event" for perf_tp_event,
only send sample data to this event when it's not NULL.

Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: alexander.shishkin@linux.intel.com
Cc: huawei.libin@huawei.com
Link: http://lkml.kernel.org/r/1503668977-12526-1-git-send-email-zhouchengming1@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 9 insertions, 4 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ce131d25622a..03ac9c8b02fb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7906,16 +7906,15 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
                 }
         }
         perf_tp_event(call->event.type, count, raw_data, size, regs, head,
-                      rctx, task);
+                      rctx, task, NULL);
 }
 EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit);
 
 void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
                    struct pt_regs *regs, struct hlist_head *head, int rctx,
-                   struct task_struct *task)
+                   struct task_struct *task, struct perf_event *event)
 {
         struct perf_sample_data data;
-        struct perf_event *event;
 
         struct perf_raw_record raw = {
                 .frag = {
@@ -7929,9 +7928,15 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 
         perf_trace_buf_update(record, event_type);
 
-        hlist_for_each_entry_rcu(event, head, hlist_entry) {
+        /* Use the given event instead of the hlist */
+        if (event) {
                 if (perf_tp_event_match(event, &data, regs))
                         perf_swevent_event(event, count, &data, regs);
+        } else {
+                hlist_for_each_entry_rcu(event, head, hlist_entry) {
+                        if (perf_tp_event_match(event, &data, regs))
+                                perf_swevent_event(event, count, &data, regs);
+                }
         }
 
         /*