sock_map_sk_state_allowed() and sock_map_redirect_allowed() read af_unix socket sk_state locklessly. Use READ_ONCE(). Note that for sock_map_redirect_allowed() change affects not only af_unix, but all non-TCP sockets (UDP, af_vsock). Suggested-by: Kuniyuki Iwashima Suggested-by: Martin KaFai Lau Reviewed-by: Jiayuan Chen Reviewed-by: Kuniyuki Iwashima Signed-off-by: Michal Luczaj --- net/core/sock_map.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index b0e96337a269..02a68be3002a 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -530,7 +530,7 @@ static bool sock_map_redirect_allowed(const struct sock *sk) if (sk_is_tcp(sk)) return sk->sk_state != TCP_LISTEN; else - return sk->sk_state == TCP_ESTABLISHED; + return READ_ONCE(sk->sk_state) == TCP_ESTABLISHED; } static bool sock_map_sk_is_suitable(const struct sock *sk) @@ -543,7 +543,7 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) - return (1 << sk->sk_state) & TCPF_ESTABLISHED; + return (1 << READ_ONCE(sk->sk_state)) & TCPF_ESTABLISHED; if (sk_is_vsock(sk) && (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; -- 2.53.0 bpf_iter_unix_seq_show() may deadlock when lock_sock_fast() takes the fast path and the iter prog attempts to update a sockmap. Which ends up spinning at sock_map_update_elem()'s bh_lock_sock(): WARNING: possible recursive locking detected test_progs/1393 is trying to acquire lock: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: sock_map_update_elem+0xdb/0x1f0 but task is already holding lock: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: __lock_sock_fast+0x37/0xe0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(slock-AF_UNIX); lock(slock-AF_UNIX); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by test_progs/1393: #0: ffff88814b59c790 (&p->lock){+.+.}-{4:4}, at: bpf_seq_read+0x59/0x10d0 #1: ffff88811ec25fd8 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: bpf_seq_read+0x42c/0x10d0 #2: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: __lock_sock_fast+0x37/0xe0 #3: ffffffff85a6a7c0 (rcu_read_lock){....}-{1:3}, at: bpf_iter_run_prog+0x51d/0xb00 Call Trace: dump_stack_lvl+0x5d/0x80 print_deadlock_bug.cold+0xc0/0xce __lock_acquire+0x130f/0x2590 lock_acquire+0x14e/0x2b0 _raw_spin_lock+0x30/0x40 sock_map_update_elem+0xdb/0x1f0 bpf_prog_2d0075e5d9b721cd_dump_unix+0x55/0x4f4 bpf_iter_run_prog+0x5b9/0xb00 bpf_iter_unix_seq_show+0x1f7/0x2e0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0x6b/0x3a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Suggested-by: Kuniyuki Iwashima Suggested-by: Martin KaFai Lau Fixes: 2c860a43dd77 ("bpf: af_unix: Implement BPF iterator for UNIX domain socket.") Reviewed-by: Jiayuan Chen Reviewed-by: Kuniyuki Iwashima Signed-off-by: Michal Luczaj --- net/unix/af_unix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b23c33df8b46..590a30d3b2f7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3731,15 +3731,14 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) struct bpf_prog *prog; struct sock *sk = v; uid_t uid; - bool slow; int ret; if (v == SEQ_START_TOKEN) return 0; - slow = lock_sock_fast(sk); + lock_sock(sk); - if (unlikely(sk_unhashed(sk))) { + if (unlikely(sock_flag(sk, SOCK_DEAD))) { ret = SEQ_SKIP; goto unlock; } @@ -3749,7 +3748,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) prog = bpf_iter_get_info(&meta, false); ret = unix_prog_seq_show(prog, &meta, v, uid); unlock: - unlock_sock_fast(sk, slow); + release_sock(sk); return ret; } -- 2.53.0 Updating a sockmap from a unix iterator prog may lead to a deadlock. Piggyback on the original selftest. Reviewed-by: Jiayuan Chen Signed-off-by: Michal Luczaj --- tools/testing/selftests/bpf/progs/bpf_iter_unix.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index fea275df9e22..a2652c8c3616 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -7,6 +7,13 @@ char _license[] SEC("license") = "GPL"; +SEC(".maps") struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sockmap; + static long sock_i_ino(const struct sock *sk) { const struct socket *sk_socket = sk->sk_socket; @@ -76,5 +83,8 @@ int dump_unix(struct bpf_iter__unix *ctx) BPF_SEQ_PRINTF(seq, "\n"); + /* Test for deadlock. */ + bpf_map_update_elem(&sockmap, &(int){0}, sk, 0); + return 0; } -- 2.53.0 unix_stream_connect() sets sk_state (`WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED)`) _before_ it assigns a peer (`unix_peer(sk) = newsk`). sk_state == TCP_ESTABLISHED makes sock_map_sk_state_allowed() believe that socket is properly set up, which would include having a defined peer. IOW, there's a window when unix_stream_bpf_update_proto() can be called on socket which still has unix_peer(sk) == NULL. CPU0 bpf CPU1 connect -------- ------------ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED) sock_map_sk_state_allowed(sk) ... sk_pair = unix_peer(sk) sock_hold(sk_pair) sock_hold(newsk) smp_mb__after_atomic() unix_peer(sk) = newsk BUG: kernel NULL pointer dereference, address: 0000000000000080 RIP: 0010:unix_stream_bpf_update_proto+0xa0/0x1b0 Call Trace: sock_map_link+0x564/0x8b0 sock_map_update_common+0x6e/0x340 sock_map_update_elem_sys+0x17d/0x240 __sys_bpf+0x26db/0x3250 __x64_sys_bpf+0x21/0x30 do_syscall_64+0x6b/0x3a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Initial idea was to move peer assignment _before_ the sk_state update[1], but that involved an additional memory barrier, and changing the hot path was rejected. Then a NULL check during proto update in unix_stream_bpf_update_proto() was considered[2], but the follow-up discussion[3] focused on the root cause, i.e. sockmap update taking a wrong lock. Or, more specifically, missing unix_state_lock()[4]. In the end it was concluded that teaching sockmap about the af_unix locking would be unnecessarily complex[5]. Complexity aside, since BPF_PROG_TYPE_SCHED_CLS and BPF_PROG_TYPE_SCHED_ACT are allowed to update sockmaps, sock_map_update_elem() taking the unix lock, as it is currently implemented in unix_state_lock(): spin_lock(&unix_sk(s)->lock), would be problematic. unix_state_lock() taken in a process context, followed by a softirq-context TC BPF program attempting to take the same spinlock -- deadlock[6]. This way we circled back to the peer check idea[2]. [1]: https://lore.kernel.org/netdev/ba5c50aa-1df4-40c2-ab33-a72022c5a32e@rbox.co/ [2]: https://lore.kernel.org/netdev/20240610174906.32921-1-kuniyu@amazon.com/ [3]: https://lore.kernel.org/netdev/7603c0e6-cd5b-452b-b710-73b64bd9de26@linux.dev/ [4]: https://lore.kernel.org/netdev/CAAVpQUA+8GL_j63CaKb8hbxoL21izD58yr1NvhOhU=j+35+3og@mail.gmail.com/ [5]: https://lore.kernel.org/bpf/CAAVpQUAHijOMext28Gi10dSLuMzGYh+jK61Ujn+fZ-wvcODR2A@mail.gmail.com/ [6]: https://lore.kernel.org/bpf/dd043c69-4d03-46fe-8325-8f97101435cf@linux.dev/ Summary of scenarios where af_unix/stream connect() may race a sockmap update: 1. connect() vs. bpf(BPF_MAP_UPDATE_ELEM), i.e. sock_map_update_elem_sys() Implemented NULL check is sufficient. Once assigned, socket peer won't be released until socket fd is released. And that's not an issue because sock_map_update_elem_sys() bumps fd refcnf. 2. connect() vs BPF program doing update Update restricted per verifier.c:may_update_sockmap() to BPF_PROG_TYPE_TRACING/BPF_TRACE_ITER BPF_PROG_TYPE_SOCK_OPS (bpf_sock_map_update() only) BPF_PROG_TYPE_SOCKET_FILTER BPF_PROG_TYPE_SCHED_CLS BPF_PROG_TYPE_SCHED_ACT BPF_PROG_TYPE_XDP BPF_PROG_TYPE_SK_REUSEPORT BPF_PROG_TYPE_FLOW_DISSECTOR BPF_PROG_TYPE_SK_LOOKUP Plus one more race to consider: CPU0 bpf CPU1 connect -------- ------------ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED) sock_map_sk_state_allowed(sk) sock_hold(newsk) smp_mb__after_atomic() unix_peer(sk) = newsk sk_pair = unix_peer(sk) if (unlikely(!sk_pair)) return -EINVAL; CPU1 close ---------- skpair = unix_peer(sk); unix_peer(sk) = NULL; sock_put(skpair) // use after free? sock_hold(sk_pair) 2.1 BPF program invoking helper function bpf_sock_map_update() -> BPF_CALL_4(bpf_sock_map_update(), ...) Helper limited to BPF_PROG_TYPE_SOCK_OPS. Nevertheless, a unix sock might be accessible via bpf_map_lookup_elem(). Which implies sk already having psock, which in turn implies sk already having sk_pair. Since sk_psock_destroy() is queued as RCU work, sk_pair won't go away while BPF executes the update. 2.2 BPF program invoking helper function bpf_map_update_elem() -> sock_map_update_elem() 2.2.1 Unix sock accessible to BPF prog only via sockmap lookup in BPF_PROG_TYPE_SOCKET_FILTER, BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_SK_LOOKUP. Pretty much the same as case 2.1. 2.2.2 Unix sock accessible to BPF program directly: BPF_PROG_TYPE_TRACING, narrowed down to BPF_TRACE_ITER. Sockmap iterator (sock_map_seq_ops) is safe: unix sock residing in a sockmap means that the sock already went through the proto update step. Unix sock iterator (bpf_iter_unix_seq_ops), on the other hand, gives access to socks that may still be unconnected. Which means iterator prog can race sockmap/proto update against connect(). BUG: KASAN: null-ptr-deref in unix_stream_bpf_update_proto+0x253/0x4d0 Write of size 4 at addr 0000000000000080 by task test_progs/3140 Call Trace: dump_stack_lvl+0x5d/0x80 kasan_report+0xe4/0x1c0 kasan_check_range+0x125/0x200 unix_stream_bpf_update_proto+0x253/0x4d0 sock_map_link+0x71c/0xec0 sock_map_update_common+0xbc/0x600 sock_map_update_elem+0x19a/0x1f0 bpf_prog_bbbf56096cdd4f01_selective_dump_unix+0x20c/0x217 bpf_iter_run_prog+0x21e/0xae0 bpf_iter_unix_seq_show+0x1e0/0x2a0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e While the introduced NULL check prevents null-ptr-deref in the BPF program path as well, it is insufficient to guard against a poorly timed close() leading to a use-after-free. This will be addressed in a subsequent patch. Reported-by: Michal Luczaj Closes: https://lore.kernel.org/netdev/ba5c50aa-1df4-40c2-ab33-a72022c5a32e@rbox.co/ Reported-by: 钱一铭 Suggested-by: Kuniyuki Iwashima Suggested-by: Martin KaFai Lau Fixes: c63829182c37 ("af_unix: Implement ->psock_update_sk_prot()") Signed-off-by: Michal Luczaj --- net/unix/unix_bpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index e0d30d6d22ac..57f3124c9d8d 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -185,6 +185,9 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r */ if (!psock->sk_pair) { sk_pair = unix_peer(sk); + if (unlikely(!sk_pair)) + return -EINVAL; + sock_hold(sk_pair); psock->sk_pair = sk_pair; } -- 2.53.0 When a BPF iterator program updates a sockmap, there is a race condition in unix_stream_bpf_update_proto() where the `peer` pointer can become stale[1] during a state transition TCP_ESTABLISHED -> TCP_CLOSE. CPU0 bpf CPU1 close -------- ---------- // unix_stream_bpf_update_proto() sk_pair = unix_peer(sk) if (unlikely(!sk_pair)) return -EINVAL; // unix_release_sock() skpair = unix_peer(sk); unix_peer(sk) = NULL; sock_put(skpair) sock_hold(sk_pair) // UaF More practically, this fix guarantees that the iterator program is consistently provided with a unix socket that remains stable during iterator execution. [1]: BUG: KASAN: slab-use-after-free in unix_stream_bpf_update_proto+0x155/0x490 Write of size 4 at addr ffff8881178c9a00 by task test_progs/2231 Call Trace: dump_stack_lvl+0x5d/0x80 print_report+0x170/0x4f3 kasan_report+0xe4/0x1c0 kasan_check_range+0x125/0x200 unix_stream_bpf_update_proto+0x155/0x490 sock_map_link+0x71c/0xec0 sock_map_update_common+0xbc/0x600 sock_map_update_elem+0x19a/0x1f0 bpf_prog_bbbf56096cdd4f01_selective_dump_unix+0x20c/0x217 bpf_iter_run_prog+0x21e/0xae0 bpf_iter_unix_seq_show+0x1e0/0x2a0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 2236: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_slab_alloc+0x63/0x80 kmem_cache_alloc_noprof+0x1d5/0x680 sk_prot_alloc+0x59/0x210 sk_alloc+0x34/0x470 unix_create1+0x86/0x8a0 unix_stream_connect+0x318/0x15b0 __sys_connect+0xfd/0x130 __x64_sys_connect+0x72/0xd0 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 2236: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x70 __kasan_slab_free+0x47/0x70 kmem_cache_free+0x11c/0x590 __sk_destruct+0x432/0x6e0 unix_release_sock+0x9b3/0xf60 unix_release+0x8a/0xf0 __sock_release+0xb0/0x270 sock_close+0x18/0x20 __fput+0x36e/0xac0 fput_close_sync+0xe5/0x1a0 __x64_sys_close+0x7d/0xd0 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Suggested-by: Kuniyuki Iwashima Fixes: 2c860a43dd77 ("bpf: af_unix: Implement BPF iterator for UNIX domain socket.") Signed-off-by: Michal Luczaj --- net/unix/af_unix.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 590a30d3b2f7..15b48cc6e9b0 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3737,6 +3737,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) return 0; lock_sock(sk); + unix_state_lock(sk); if (unlikely(sock_flag(sk, SOCK_DEAD))) { ret = SEQ_SKIP; @@ -3748,6 +3749,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) prog = bpf_iter_get_info(&meta, false); ret = unix_prog_seq_show(prog, &meta, v, uid); unlock: + unix_state_unlock(sk); release_sock(sk); return ret; } -- 2.53.0