From: Pengcheng Yang yangpc@wangsu.com
mainline inclusion from mainline-v6.2-rc1 commit a351d6087bf7d3d8440d58d3bf244ec64b89394a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I65HYE CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
---------------------------
When redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag.
So we need to save the BPF_F_INGRESS flag in sk_psock and use it when redirection.
Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Pengcheng Yang yangpc@wangsu.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/1669718441-2654-3-git-send-email-yangpc@wangsu.c... Signed-off-by: Liu Jian liujian56@huawei.com
Conflicts: include/net/tcp.h --- include/linux/skmsg.h | 1 + include/net/tcp.h | 4 ++-- net/core/skmsg.c | 9 ++++++--- net/ipv4/tcp_bpf.c | 11 ++++++----- net/tls/tls_sw.c | 6 ++++-- 5 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index dda4e951aeba..9c14c5fbb8c0 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -94,6 +94,7 @@ struct sk_psock { u32 apply_bytes; u32 cork_bytes; u32 eval; + bool redir_ingress; /* undefined if sk_redir is null */ struct sk_msg *cork; struct sk_psock_progs progs; struct sk_psock_parser parser; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1b832683ccf8..36ab6cf44553 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2238,8 +2238,8 @@ static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) #endif /* CONFIG_BPF_STREAM_PARSER */
#ifdef CONFIG_NET_SOCK_MSG -int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, - int flags); +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 78cb3782326d..cc6570d71911 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -784,13 +784,16 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { - if (psock->sk_redir) + if (psock->sk_redir) { sock_put(psock->sk_redir); - psock->sk_redir = msg->sk_redir; - if (!psock->sk_redir) { + psock->sk_redir = NULL; + } + if (!msg->sk_redir) { ret = __SK_DROP; goto out; } + psock->redir_ingress = sk_msg_to_ingress(msg); + psock->sk_redir = msg->sk_redir; sock_hold(psock->sk_redir); } out: diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index e5a2aaa02f2a..8c2ea1aaef77 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -213,10 +213,9 @@ static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg, return ret; }
-int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, - u32 bytes, int flags) +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags) { - bool ingress = sk_msg_to_ingress(msg); struct sk_psock *psock = sk_psock_get(sk); int ret;
@@ -383,7 +382,7 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = sk_msg_full(msg); + bool cork = false, enospc = sk_msg_full(msg), redir_ingress; struct sock *sk_redir; u32 tosend, origsize, sent, delta = 0; u32 eval; @@ -429,6 +428,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, sk_msg_apply_bytes(psock, tosend); break; case __SK_REDIRECT: + redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); if (!psock->apply_bytes) { @@ -445,7 +445,8 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, release_sock(sk);
origsize = msg->sg.size; - ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + ret = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, + msg, tosend, flags); sent = origsize - msg->sg.size;
if (eval == __SK_REDIRECT) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 3ee8aa7ec04d..c8f8881032ed 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -807,7 +807,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, struct sk_psock *psock; struct sock *sk_redir; struct tls_rec *rec; - bool enospc, policy; + bool enospc, policy, redir_ingress; int err = 0, send; u32 delta = 0;
@@ -852,6 +852,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, } break; case __SK_REDIRECT: + redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; memcpy(&msg_redir, msg, sizeof(*msg)); if (msg->apply_bytes < send) @@ -861,7 +862,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, sk_msg_return_zero(sk, msg, send); msg->sg.size -= send; release_sock(sk); - err = tcp_bpf_sendmsg_redir(sk_redir, &msg_redir, send, flags); + err = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, + &msg_redir, send, flags); lock_sock(sk); if (err < 0) { *copied -= sk_msg_free_nocharge(sk, &msg_redir);