[PATCH 3/5] ftrace perf: Use ftrace_ops::private to store event pointer

[Jiri Olsa]

Having following commands running concurrently:

  # perf record -e ftrace:function -a -o krava.data sleep 10
  # perf record -e ftrace:function --filter 'ip == SyS_read' ls

will end up in the latter one to fail on the filter rules
and store all functions (in perf.data) as instructed by the
first perf record instead of just SyS_read records.

The reason for this is, that tracepoint code by default
triggers all events that registered for the tracepoint.

While ftrace:function is special because ftrace_ops
itself carries a filter and only the event that owns
ftrace_ops is eligible to be triggered.

Fixing this by using ftrace_ops::private value to keep
the perf_event pointer. This way we don't need to search
for triggered event (as tracepoint handler does) and
directly store sample.

Suggested-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
 include/linux/perf_event.h      |  3 +++
 kernel/events/core.c            | 22 ++++++++++++++++++++++
 kernel/trace/trace_event_perf.c | 10 +++-------
 3 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a9d8cab18b00..a330dc06d90d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1008,6 +1008,9 @@ extern void perf_tp_event(u64 addr, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
 			  struct hlist_head *head, int rctx,
 			  struct task_struct *task);
+void perf_function_event(struct perf_event *event,
+			 void *record, int entry_size,
+			 struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ca68fdcf47ce..18da90859c17 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7063,6 +7063,28 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	}
 }
 
+#ifdef CONFIG_FUNCTION_TRACER
+void perf_function_event(struct perf_event *event,
+			 void *record, int entry_size,
+			 struct pt_regs *regs)
+
+{
+	struct perf_sample_data data;
+	struct perf_raw_record raw = {
+		.size = entry_size,
+		.data = record,
+	};
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	perf_sample_data_init(&data, 0, 0);
+	data.raw = &raw;
+
+	perf_swevent_event(event, 1, &data, regs);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
 #else
 
 static inline void perf_tp_register(void)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0a3779bd18a1..087c811db04c 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -328,14 +328,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
 {
 	struct ftrace_entry *entry;
-	struct hlist_head *head;
 	struct pt_regs regs;
 	int rctx;
 
-	head = this_cpu_ptr(event_function.perf_events);
-	if (hlist_empty(head))
-		return;
-
 #define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
 		    sizeof(u64)) - sizeof(u32))
 
@@ -349,8 +344,8 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 
 	entry->ip = ip;
 	entry->parent_ip = parent_ip;
-	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
-			      1, &regs, head, NULL);
+	perf_function_event(ops->private, entry, ENTRY_SIZE, &regs);
+	perf_swevent_put_recursion_context(rctx);
 
 #undef ENTRY_SIZE
 }
@@ -359,6 +354,7 @@ static int perf_ftrace_function_register(struct perf_event *event)
 {
 	struct ftrace_ops *ops = &event->ftrace_ops;
 
+	ops->private = event;
 	ops->flags |= FTRACE_OPS_FL_PER_CPU | FTRACE_OPS_FL_RCU;
 	ops->func = perf_ftrace_function_call;
 	return register_ftrace_function(ops);
-- 
2.4.3