net: Fix suspicious RCU usage in bpf_sk_reuseport_detach()

bpf_sk_reuseport_detach() calls __rcu_dereference_sk_user_data_with_flags()
to obtain the value of sk->sk_user_data, but that function is only usable
if the RCU read lock is held, and neither that function nor any of its
callers hold it.

Fix this by adding a new helper, __locked_read_sk_user_data_with_flags()
that checks to see if sk->sk_callback_lock() is held and use that here
instead.

Alternatively, making __rcu_dereference_sk_user_data_with_flags() use
rcu_dereference_checked() might suffice.

Without this, the following warning can be occasionally observed:

=============================
WARNING: suspicious RCU usage
6.0.0-rc1-build2+ torvalds#563 Not tainted
-----------------------------
include/net/sock.h:592 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
5 locks held by locktest/29873:
 #0: ffff88812734b550 (&sb->s_type->i_mutex_key#9){+.+.}-{3:3}, at: __sock_release+0x77/0x121
 #1: ffff88812f5621b0 (sk_lock-AF_INET){+.+.}-{0:0}, at: tcp_close+0x1c/0x70
 #2: ffff88810312f5c8 (&h->lhash2[i].lock){+.+.}-{2:2}, at: inet_unhash+0x76/0x1c0
 #3: ffffffff83768bb8 (reuseport_lock){+...}-{2:2}, at: reuseport_detach_sock+0x18/0xdd
 #4: ffff88812f562438 (clock-AF_INET){++..}-{2:2}, at: bpf_sk_reuseport_detach+0x24/0xa4

stack backtrace:
CPU: 1 PID: 29873 Comm: locktest Not tainted 6.0.0-rc1-build2+ torvalds#563
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x4c/0x5f
 bpf_sk_reuseport_detach+0x6d/0xa4
 reuseport_detach_sock+0x75/0xdd
 inet_unhash+0xa5/0x1c0
 tcp_set_state+0x169/0x20f
 ? lockdep_sock_is_held+0x3a/0x3a
 ? __lock_release.isra.0+0x13e/0x220
 ? reacquire_held_locks+0x1bb/0x1bb
 ? hlock_class+0x31/0x96
 ? mark_lock+0x9e/0x1af
 __tcp_close+0x50/0x4b6
 tcp_close+0x28/0x70
 inet_release+0x8e/0xa7
 __sock_release+0x95/0x121
 sock_close+0x14/0x17
 __fput+0x20f/0x36a
 task_work_run+0xa3/0xcc
 exit_to_user_mode_prepare+0x9c/0x14d
 syscall_exit_to_user_mode+0x18/0x44
 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Fixes: cf8c1e9 ("net: refactor bpf_sk_reuseport_detach()")
Signed-off-by: David Howells <[email protected]>
cc: Hawkins Jiawei <[email protected]>
Link: https://lore.kernel.org/r/166064248071.3502205.10036394558814861778.stgit@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <[email protected]>

Author: dhowells

include/net/sock.h

@@ -577,6 +577,31 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk)
 
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
+/**
+ * __locked_read_sk_user_data_with_flags - return the pointer
+ * only if argument flags all has been set in sk_user_data. Otherwise
+ * return NULL
+ *
+ * @sk: socket
+ * @flags: flag bits
+ *
+ * The caller must be holding sk->sk_callback_lock.
+ */
+static inline void *
+__locked_read_sk_user_data_with_flags(const struct sock *sk,
+				      uintptr_t flags)
+{
+	uintptr_t sk_user_data =
+		(uintptr_t)rcu_dereference_check(__sk_user_data(sk),
+						 lockdep_is_held(&sk->sk_callback_lock));
+
+	WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK);
+
+	if ((sk_user_data & flags) == flags)
+		return (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+	return NULL;
+}
+
 /**
  * __rcu_dereference_sk_user_data_with_flags - return the pointer
  * only if argument flags all has been set in sk_user_data. Otherwise

kernel/bpf/reuseport_array.c

@@ -24,7 +24,7 @@ void bpf_sk_reuseport_detach(struct sock *sk)
 	struct sock __rcu **socks;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	socks = __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
+	socks = __locked_read_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
 	if (socks) {
 		WRITE_ONCE(sk->sk_user_data, NULL);
 		/*