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>

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b14095b..c00cd4b 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -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

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 536c80f..5012b52 100644 (file)
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -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
 

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ce131d2..03ac9c8 100644 (file)
--- 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);
+               }
        }
 
        /*

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 562fa69..13ba2d3 100644 (file)
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -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
 }

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9b5aa1..8a907e1 100644 (file)
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -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 */

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e10395..74d9a86 100644 (file)
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -596,7 +596,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
                               (unsigned long *)&rec->args);
        perf_trace_buf_submit(rec, size, rctx,
                              sys_data->enter_event->event.type, 1, regs,
-                             head, NULL);
+                             head, NULL, NULL);
 }
 
 static int perf_sysenter_enable(struct trace_event_call *call)
@@ -667,7 +667,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
        rec->nr = syscall_nr;
        rec->ret = syscall_get_return_value(current, regs);
        perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
-                             1, regs, head, NULL);
+                             1, regs, head, NULL, NULL);
 }
 
 static int perf_sysexit_enable(struct trace_event_call *call)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index a7581fe..4525e02 100644 (file)
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1156,7 +1156,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
        }
 
        perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-                             head, NULL);
+                             head, NULL, NULL);
  out:
        preempt_enable();
 }