[PATCH 1/1] Fix: trace sched switch start/stop racy updates

[Mathieu Desnoyers]

Reading the sched_cmdline_ref and sched_tgid_ref initial state within
tracing_start_sched_switch without holding the sched_register_mutex is
racy against concurrent updates, which can lead to tracepoint probes
being registered more than once (and thus trigger warnings within
tracepoint.c).

Also, write and read to/from those variables should be done with
WRITE_ONCE() and READ_ONCE(), given that those are read within tracing
probes without holding the sched_register_mutex.

[ Compile-tested only. I suspect it might fix the following syzbot
  report:

  syzbot+774fddf07b7ab29a1...@syzkaller.appspotmail.com ]

Signed-off-by: Mathieu Desnoyers <mathieu.desnoy...@efficios.com>
CC: Joel Fernandes (Google) <j...@joelfernandes.org>
CC: Peter Zijlstra <pet...@infradead.org>
CC: Steven Rostedt (VMware) <rost...@goodmis.org>
CC: Thomas Gleixner <t...@linutronix.de>
CC: Paul E. McKenney <paul...@linux.ibm.com>
---
 kernel/trace/trace_sched_switch.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_sched_switch.c 
b/kernel/trace/trace_sched_switch.c
index e288168661e1..902e8bf59aeb 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -26,8 +26,8 @@ probe_sched_switch(void *ignore, bool preempt,
 {
        int flags;
 
-       flags = (RECORD_TGID * !!sched_tgid_ref) +
-               (RECORD_CMDLINE * !!sched_cmdline_ref);
+       flags = (RECORD_TGID * !!READ_ONCE(sched_tgid_ref)) +
+               (RECORD_CMDLINE * !!READ_ONCE(sched_cmdline_ref));
 
        if (!flags)
                return;
@@ -39,8 +39,8 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 {
        int flags;
 
-       flags = (RECORD_TGID * !!sched_tgid_ref) +
-               (RECORD_CMDLINE * !!sched_cmdline_ref);
+       flags = (RECORD_TGID * !!READ_ONCE(sched_tgid_ref)) +
+               (RECORD_CMDLINE * !!READ_ONCE(sched_cmdline_ref));
 
        if (!flags)
                return;
@@ -89,21 +89,28 @@ static void tracing_sched_unregister(void)
 
 static void tracing_start_sched_switch(int ops)
 {
-       bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
+       bool sched_register;
+
        mutex_lock(&sched_register_mutex);
+       sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
 
        switch (ops) {
        case RECORD_CMDLINE:
-               sched_cmdline_ref++;
+               WRITE_ONCE(sched_cmdline_ref, sched_cmdline_ref + 1);
                break;
 
        case RECORD_TGID:
-               sched_tgid_ref++;
+               WRITE_ONCE(sched_tgid_ref, sched_tgid_ref + 1);
                break;
+
+       default:
+               WARN_ONCE(1, "Unsupported tracing op: %d", ops);
+               goto end;
        }
 
-       if (sched_register && (sched_cmdline_ref || sched_tgid_ref))
+       if (sched_register)
                tracing_sched_register();
+end:
        mutex_unlock(&sched_register_mutex);
 }
 
@@ -113,16 +120,21 @@ static void tracing_stop_sched_switch(int ops)
 
        switch (ops) {
        case RECORD_CMDLINE:
-               sched_cmdline_ref--;
+               WRITE_ONCE(sched_cmdline_ref, sched_cmdline_ref - 1);
                break;
 
        case RECORD_TGID:
-               sched_tgid_ref--;
+               WRITE_ONCE(sched_tgid_ref, sched_tgid_ref - 1);
                break;
+
+       default:
+               WARN_ONCE(1, "Unsupported tracing op: %d", ops);
+               goto end;
        }
 
        if (!sched_cmdline_ref && !sched_tgid_ref)
                tracing_sched_unregister();
+end:
        mutex_unlock(&sched_register_mutex);
 }
 
-- 
2.11.0