summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJohn Fastabend <john.fastabend@gmail.com>2023-11-28 17:25:56 -0800
committerDaniel Borkmann <daniel@iogearbox.net>2023-11-30 00:25:16 +0100
commit8866730aed5100f06d3d965c22f1c61f74942541 (patch)
tree66fd1fbd894a628549f2c42e841f43b89e4bce1e /net
parent0bad281d0ecdf8391b0f42678b663336e7c3ceb0 (diff)
bpf, sockmap: af_unix stream sockets need to hold ref for pair sock
AF_UNIX stream sockets are a paired socket. So sending on one of the pairs will lookup the paired socket as part of the send operation. It is possible however to put just one of the pairs in a BPF map. This currently increments the refcnt on the sock in the sockmap to ensure it is not free'd by the stack before sockmap cleans up its state and stops any skbs being sent/recv'd to that socket. But we missed a case. If the peer socket is closed it will be free'd by the stack. However, the paired socket can still be referenced from BPF sockmap side because we hold a reference there. Then if we are sending traffic through BPF sockmap to that socket it will try to dereference the free'd pair in its send logic creating a use after free. And following splat: [59.900375] BUG: KASAN: slab-use-after-free in sk_wake_async+0x31/0x1b0 [59.901211] Read of size 8 at addr ffff88811acbf060 by task kworker/1:2/954 [...] [59.905468] Call Trace: [59.905787] <TASK> [59.906066] dump_stack_lvl+0x130/0x1d0 [59.908877] print_report+0x16f/0x740 [59.910629] kasan_report+0x118/0x160 [59.912576] sk_wake_async+0x31/0x1b0 [59.913554] sock_def_readable+0x156/0x2a0 [59.914060] unix_stream_sendmsg+0x3f9/0x12a0 [59.916398] sock_sendmsg+0x20e/0x250 [59.916854] skb_send_sock+0x236/0xac0 [59.920527] sk_psock_backlog+0x287/0xaa0 To fix let BPF sockmap hold a refcnt on both the socket in the sockmap and its paired socket. It wasn't obvious how to contain the fix to bpf_unix logic. The primarily problem with keeping this logic in bpf_unix was: In the sock close() we could handle the deref by having a close handler. But, when we are destroying the psock through a map delete operation we wouldn't have gotten any signal thorugh the proto struct other than it being replaced. If we do the deref from the proto replace its too early because we need to deref the sk_pair after the backlog worker has been stopped. Given all this it seems best to just cache it at the end of the psock and eat 8B for the af_unix and vsock users. Notice dgram sockets are OK because they handle locking already. Fixes: 94531cfcbe79 ("af_unix: Add unix_stream_proto for sockmap") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20231129012557.95371-2-john.fastabend@gmail.com
Diffstat (limited to 'net')
-rw-r--r--net/core/skmsg.c2
-rw-r--r--net/unix/af_unix.c2
-rw-r--r--net/unix/unix_bpf.c5
3 files changed, 7 insertions, 2 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd777..93ecfceac1bc 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
if (psock->sk_redir)
sock_put(psock->sk_redir);
+ if (psock->sk_pair)
+ sock_put(psock->sk_pair);
sock_put(psock->sk);
kfree(psock);
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a357dc5f2404..ac1f2bc18fc9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
}
#endif /* CONFIG_SECURITY_NETWORK */
-#define unix_peer(sk) (unix_sk(sk)->peer)
-
static inline int unix_our_peer(struct sock *sk, struct sock *osk)
{
return unix_peer(osk) == sk;
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2f9d8271c6ec..7ea7c3a0d0d0 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
+ struct sock *sk_pair;
+
if (restore) {
sk->sk_write_space = psock->saved_write_space;
sock_replace_proto(sk, psock->sk_proto);
return 0;
}
+ sk_pair = unix_peer(sk);
+ sock_hold(sk_pair);
+ psock->sk_pair = sk_pair;
unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
sock_replace_proto(sk, &unix_stream_bpf_prot);
return 0;