Commit 75e83876 authored by Zhou Chengming's avatar Zhou Chengming Committed by Ingo Molnar
Browse files

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: default avatarZhou Chengming <zhouchengming1@huawei.com>
Reviewed-by: default avatarJiri Olsa <jolsa@kernel.org>
Acked-by: default avatarSteven 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: default avatarIngo Molnar <mingo@kernel.org>
parent f12f42ac

include/linux/perf_event.h

+1 −1
Original line number Diff line number Diff line
@@ -1201,7 +1201,7 @@ extern void perf_event_init(void); 
extern 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);

extern void perf_bp_event(struct perf_event *event, void *data);



#ifndef perf_misc_flags

include/linux/trace_events.h

+2 −2
Original line number Diff line number Diff line
@@ -508,9 +508,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, 
static inline void

perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,

		       u64 count, struct pt_regs *regs, void *head,

		       struct task_struct *task)

		       struct task_struct *task, struct perf_event *event)

{

	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task);

	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event);

}

#endif

kernel/events/core.c

+9 −4
Original line number Diff line number Diff line
@@ -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 = {
@@ -7929,10 +7928,16 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, 


	perf_trace_buf_update(record, event_type);



	/* 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);

		}

	}



	/*

	 * If we got specified a target task, also iterate its context and

kernel/trace/trace_event_perf.c

+3 −1
Original line number Diff line number Diff line
@@ -306,6 +306,7 @@ static void 
perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,

			  struct ftrace_ops *ops, struct pt_regs *pt_regs)

{

	struct perf_event *event;

	struct ftrace_entry *entry;

	struct hlist_head *head;

	struct pt_regs regs;
@@ -329,8 +330,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, 


	entry->ip = ip;

	entry->parent_ip = parent_ip;

	event = container_of(ops, struct perf_event, ftrace_ops);

	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,

			      1, &regs, head, NULL);

			      1, &regs, head, NULL, event);



#undef ENTRY_SIZE

}

kernel/trace/trace_kprobe.c

+2 −2
Original line number Diff line number Diff line
@@ -1200,7 +1200,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) 
	memset(&entry[1], 0, dsize);

	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);

	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,

			      head, NULL);

			      head, NULL, NULL);

}

NOKPROBE_SYMBOL(kprobe_perf_func);
@@ -1236,7 +1236,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, 
	entry->ret_ip = (unsigned long)ri->ret_addr;

	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);

	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,

			      head, NULL);

			      head, NULL, NULL);

}

NOKPROBE_SYMBOL(kretprobe_perf_func);

#endif	/* CONFIG_PERF_EVENTS */

CRA Git | Maintained and supported by SUSTech CRA and CCSE