[PATCH v2] perf/bpf: Fix data races in BPF perf event handling

Fix multiple data races involving event->prog field:

1. __perf_event_overflow() reads event->prog twice without
   synchronization creating a TOCTOU race. Fix by using READ_ONCE()
   to capture prog into a local variable and pass it directly to
   bpf_overflow_handler() to avoid a second read inside that function.

2. perf_event_set_bpf_handler() and perf_event_free_bpf_handler()
   perform plain writes to event->prog without WRITE_ONCE(), failing
   to pair with the READ_ONCE() in __perf_event_overflow(). Fix by
   using WRITE_ONCE() in all write paths including
   perf_event_detach_bpf_prog().

3. perf_event_alloc() reads parent_event->prog locklessly during
   fork() which can race with a concurrent detach clearing and freeing
   the prog, potentially causing a NULL pointer dereference or
   use-after-free in bpf_prog_inc(). Fix by holding bpf_event_mutex
   when inheriting the BPF program. Make bpf_event_mutex non-static
   and declare it extern in perf_event.h so it is accessible from
   kernel/events/core.c.

Reported-by: [email protected]
Closes: https://syzkaller.appspot.com/bug?extid=651d2774bd1d8395595f
Link: https://lore.kernel.org/all/[email protected]/T/ [v1]
Signed-off-by: Deepanshu Kartikey <[email protected]>
---
v2:
- Pass validated prog pointer directly to bpf_overflow_handler()
  to avoid TOCTOU race from second READ_ONCE() inside the handler
- Add WRITE_ONCE() to perf_event_set_bpf_handler() and
  perf_event_free_bpf_handler() to pair with READ_ONCE() in overflow
- Fix lockless access in perf_event_alloc() during fork() by holding
  bpf_event_mutex to prevent concurrent detach UAF
- Make bpf_event_mutex non-static and export via perf_event.h
---
 include/linux/perf_event.h |  2 ++
 kernel/events/core.c       | 23 +++++++++++++----------
 kernel/trace/bpf_trace.c   |  4 ++--
 3 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 48d851fbd8ea..5c6dabb6dccb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -2136,4 +2136,6 @@ static inline void perf_lopwr_cb(bool mode)
 }
 #endif
 
+extern struct mutex bpf_event_mutex;
+
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ba5bd6a78fe7..6f8d3b57fa01 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10652,20 +10652,19 @@ static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *r
 #ifdef CONFIG_BPF_SYSCALL
 static int bpf_overflow_handler(struct perf_event *event,
 				struct perf_sample_data *data,
-				struct pt_regs *regs)
+				struct pt_regs *regs,
+				struct bpf_prog *prog)
 {
 	struct bpf_perf_event_data_kern ctx = {
 		.data = data,
 		.event = event,
 	};
-	struct bpf_prog *prog;
 	int ret = 0;
 
 	ctx.regs = perf_arch_bpf_user_pt_regs(regs);
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
 		goto out;
 	rcu_read_lock();
-	prog = READ_ONCE(event->prog);
 	if (prog) {
 		perf_prepare_sample(data, event, regs);
 		ret = bpf_prog_run(prog, &ctx);
@@ -10708,7 +10707,7 @@ static inline int perf_event_set_bpf_handler(struct perf_event *event,
 		return -EPROTO;
 	}
 
-	event->prog = prog;
+	WRITE_ONCE(event->prog, prog);
 	event->bpf_cookie = bpf_cookie;
 	return 0;
 }
@@ -10720,7 +10719,7 @@ static inline void perf_event_free_bpf_handler(struct perf_event *event)
 	if (!prog)
 		return;
 
-	event->prog = NULL;
+	WRITE_ONCE(event->prog, NULL);
 	bpf_prog_put(prog);
 }
 #else
@@ -10753,6 +10752,7 @@ 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
@@ -10766,8 +10766,9 @@ 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 &&
-	    !bpf_overflow_handler(event, data, regs))
+	prog = READ_ONCE(event->prog);
+	if (prog && prog->type == BPF_PROG_TYPE_PERF_EVENT &&
+	    !bpf_overflow_handler(event, data, regs, prog))
 		goto out;
 
 	/*
@@ -13433,12 +13434,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		overflow_handler = parent_event->overflow_handler;
 		context = parent_event->overflow_handler_context;
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING)
-		if (parent_event->prog) {
-			struct bpf_prog *prog = parent_event->prog;
-
+		struct bpf_prog *prog;
+
+		mutex_lock(&bpf_event_mutex);
+		prog = parent_event->prog;
+		if (prog) {
 			bpf_prog_inc(prog);
 			event->prog = prog;
 		}
+		mutex_unlock(&bpf_event_mutex);
 #endif
 	}
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 75495a5c3507..026b5c492115 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1944,7 +1944,7 @@ const struct bpf_verifier_ops perf_event_verifier_ops = {
 const struct bpf_prog_ops perf_event_prog_ops = {
 };
 
-static DEFINE_MUTEX(bpf_event_mutex);
+DEFINE_MUTEX(bpf_event_mutex);
 
 #define BPF_TRACE_MAX_PROGS 64
 
@@ -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