From d888b7af7c149c115dd6ac772cc11c375da3e17c Mon Sep 17 00:00:00 2001 From: Zijian Zhang Date: Tue, 10 Dec 2024 01:20:39 +0000 Subject: tcp_bpf: Add sk_rmem_alloc related logic for tcp_bpf ingress redirection When we do sk_psock_verdict_apply->sk_psock_skb_ingress, an sk_msg will be created out of the skb, and the rmem accounting of the sk_msg will be handled by the skb. For skmsgs in __SK_REDIRECT case of tcp_bpf_send_verdict, when redirecting to the ingress of a socket, although we sk_rmem_schedule and add sk_msg to the ingress_msg of sk_redir, we do not update sk_rmem_alloc. As a result, except for the global memory limit, the rmem of sk_redir is nearly unlimited. Thus, add sk_rmem_alloc related logic to limit the recv buffer. Since the function sk_msg_recvmsg and __sk_psock_purge_ingress_msg are used in these two paths. We use "msg->skb" to test whether the sk_msg is skb backed up. If it's not, we shall do the memory accounting explicitly. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Zijian Zhang Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Link: https://lore.kernel.org/bpf/20241210012039.1669389-3-zijianzhang@bytedance.com --- include/linux/skmsg.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux/skmsg.h') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) -- cgit