[PATCH] perf/bpf: Fix data race in __perf_event_overflow

[Deepanshu Kartikey]

perf_event_detach_bpf_prog() writes event->prog = NULL
under bpf_event_mutex, while __perf_event_overflow() reads
event->prog concurrently without any lock protection. This
causes a data race detected by KCSAN.

__perf_event_overflow() can be called from interrupt/NMI
context, so it cannot acquire bpf_event_mutex. Fix the race
by using WRITE_ONCE() in perf_event_detach_bpf_prog() and
READ_ONCE() in __perf_event_overflow(). Also store the result
of READ_ONCE() in a local variable to avoid reading event->prog
twice which could result in a NULL pointer dereference if the
pointer becomes NULL between the two reads.

Reported-by: syzbot+651d2774bd1d8395595f@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=651d2774bd1d8395595f
Fixes: f11f10bfa1ca ("perf/bpf: Call BPF handler directly, not through overflow machinery")
Signed-off-by: Deepanshu Kartikey <kartikey406@xxxxxxxxx>
---
 kernel/events/core.c     | 4 +++-
 kernel/trace/bpf_trace.c | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ba5bd6a78fe7..9d9c5477772e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10753,6 +10753,7 @@ static int __perf_event_overflow(struct perf_event *event,
 {
 	int events = atomic_read(&event->event_limit);
 	int ret = 0;
+	struct bpf_prog *prog;
 
 	/*
 	 * Non-sampling counters might still use the PMI to fold short
@@ -10766,7 +10767,8 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (event->attr.aux_pause)
 		perf_event_aux_pause(event->aux_event, true);
 
-	if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
+	prog = READ_ONCE(event->prog);
+	if (prog && prog->type == BPF_PROG_TYPE_PERF_EVENT &&
 	    !bpf_overflow_handler(event, data, regs))
 		goto out;
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 75495a5c3507..ee61dc760045 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2018,7 +2018,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 
 put:
 	prog = event->prog;
-	event->prog = NULL;
+	WRITE_ONCE(event->prog, NULL);
 
 unlock:
 	mutex_unlock(&bpf_event_mutex);
-- 
2.43.0