eprobes: Remove redundant event type information

Currently, the event probes save the type of the event they are attached
to when recording the event. For example:

  # echo 'e:switch sched/sched_switch prev_state=$prev_state prev_prio=$prev_prio next_pid=$next_pid next_prio=$next_prio' > dynamic_events
  # cat events/eprobes/switch/format

 name: switch
 ID: 1717
 format:
        field:unsigned short common_type;       offset:0;       size:2; signed:0;
        field:unsigned char common_flags;       offset:2;       size:1; signed:0;
        field:unsigned char common_preempt_count;       offset:3;       size:1; signed:0;
        field:int common_pid;   offset:4;       size:4; signed:1;

        field:unsigned int __probe_type;        offset:8;       size:4; signed:0;
        field:u64 prev_state;   offset:12;      size:8; signed:0;
        field:u64 prev_prio;    offset:20;      size:8; signed:0;
        field:u64 next_pid;     offset:28;      size:8; signed:0;
        field:u64 next_prio;    offset:36;      size:8; signed:0;

 print fmt: "(%u) prev_state=0x%Lx prev_prio=0x%Lx next_pid=0x%Lx next_prio=0x%Lx", REC->__probe_type, REC->prev_state, REC->prev_prio, REC->next_pid, REC->next_prio

The __probe_type adds 4 bytes to every event.

One of the reasons for creating eprobes is to limit what is traced in an
event to be able to limit what is written into the ring buffer. Having
this redundant 4 bytes to every event takes away from this.

The event that is recorded can be retrieved from the event probe itself,
that is available when the trace is happening. For user space tools, it
could simply read the dynamic_event file to find the event they are for.
So there is really no reason to write this information into the ring
buffer for every event.

Link: https://lkml.kernel.org/r/20220218190057.2f5a19a8@gandalf.local.home

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 7 insertions, 9 deletions

diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 191db32dec46..541aa13581b9 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -242,7 +242,6 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
 {
-	int ret;
 	struct eprobe_trace_entry_head field;
 	struct trace_probe *tp;
 
@@ -250,8 +249,6 @@ static int eprobe_event_define_fields(struct trace_event_call *event_call)
 	if (WARN_ON_ONCE(!tp))
 		return -ENOENT;
 
-	DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0);
-
 	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
 }
 
@@ -270,7 +267,9 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	struct trace_event_call *pevent;
 	struct trace_event *probed_event;
 	struct trace_seq *s = &iter->seq;
+	struct trace_eprobe *ep;
 	struct trace_probe *tp;
+	unsigned int type;
 
 	field = (struct eprobe_trace_entry_head *)iter->ent;
 	tp = trace_probe_primary_from_call(
@@ -278,15 +277,18 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	if (WARN_ON_ONCE(!tp))
 		goto out;
 
+	ep = container_of(tp, struct trace_eprobe, tp);
+	type = ep->event->event.type;
+
 	trace_seq_printf(s, "%s: (", trace_probe_name(tp));
 
-	probed_event = ftrace_find_event(field->type);
+	probed_event = ftrace_find_event(type);
 	if (probed_event) {
 		pevent = container_of(probed_event, struct trace_event_call, event);
 		trace_seq_printf(s, "%s.%s", pevent->class->system,
 				 trace_event_name(pevent));
 	} else {
-		trace_seq_printf(s, "%u", field->type);
+		trace_seq_printf(s, "%u", type);
 	}
 
 	trace_seq_putc(s, ')');
@@ -498,10 +500,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
-	if (edata->ep->event)
-		entry->type = edata->ep->event->event.type;
-	else
-		entry->type = 0;
 	store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);