summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorLiu Jian <liujian56@huawei.com>2021-10-12 13:20:19 +0800
committerAlexei Starovoitov <ast@kernel.org>2021-10-26 12:25:55 -0700
commitcd9733f5d75c94a32544d6ce5be47e14194cf137 (patch)
tree482cbaa3434e39675f0dfe9e30d8f8b8ac64184f /net/ipv4
parent04f8ef5643bcd8bcde25dfdebef998aea480b2ba (diff)
tcp_bpf: Fix one concurrency problem in the tcp_bpf_send_verdict function
With two Msgs, msgA and msgB and a user doing nonblocking sendmsg calls (or multiple cores) on a single socket 'sk' we could get the following flow. msgA, sk msgB, sk ----------- --------------- tcp_bpf_sendmsg() lock(sk) psock = sk->psock tcp_bpf_sendmsg() lock(sk) ... blocking tcp_bpf_send_verdict if (psock->eval == NONE) psock->eval = sk_psock_msg_verdict .. < handle SK_REDIRECT case > release_sock(sk) < lock dropped so grab here > ret = tcp_bpf_sendmsg_redir psock = sk->psock tcp_bpf_send_verdict lock_sock(sk) ... blocking on B if (psock->eval == NONE) <- boom. psock->eval will have msgA state The problem here is we dropped the lock on msgA and grabbed it with msgB. Now we have old state in psock and importantly psock->eval has not been cleared. So msgB will run whatever action was done on A and the verdict program may never see it. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211012052019.184398-1-liujian56@huawei.com
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_bpf.c12
1 files changed, 12 insertions, 0 deletions
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..9d068153c316 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -232,6 +232,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
u32 tosend, delta = 0;
+ u32 eval = __SK_NONE;
int ret;
more_data:
@@ -275,13 +276,24 @@ more_data:
case __SK_REDIRECT:
sk_redir = psock->sk_redir;
sk_msg_apply_bytes(psock, tosend);
+ if (!psock->apply_bytes) {
+ /* Clean up before releasing the sock lock. */
+ eval = psock->eval;
+ psock->eval = __SK_NONE;
+ psock->sk_redir = NULL;
+ }
if (psock->cork) {
cork = true;
psock->cork = NULL;
}
sk_msg_return(sk, msg, tosend);
release_sock(sk);
+
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+ if (eval == __SK_REDIRECT)
+ sock_put(sk_redir);
+
lock_sock(sk);
if (unlikely(ret < 0)) {
int free = sk_msg_free_nocharge(sk, msg);