diff options
author | Jakub Kicinski <kuba@kernel.org> | 2023-10-19 09:10:02 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-10-19 09:10:02 -0700 |
commit | 1c1f14f92beca73555f9a23c3f37bae50d9ed323 (patch) | |
tree | 77379bce5ff8fe8deff715dc128ac6e141c6873d /net | |
parent | 389db4fd673e5b122393a69b2973dd294a125573 (diff) | |
parent | 2cfaa8b3b7aece3c7b13dd10db20dcea65875692 (diff) |
Merge branch 'mptcp-fixes-for-v6-6'
Mat Martineau says:
====================
mptcp: Fixes for v6.6
Patch 1 corrects the logic for MP_JOIN tests where 0 RSTs are expected.
Patch 2 ensures MPTCP packets are not incorrectly coalesced in the TCP
backlog queue.
Patch 3 avoids a zero-window probe and associated WARN_ON_ONCE() in an
expected MPTCP reinjection scenario.
Patches 4 & 5 allow an initial MPTCP subflow to be closed cleanly
instead of always sending RST. Associated selftest is updated.
====================
Link: https://lore.kernel.org/r/20231018-send-net-20231018-v1-0-17ecb002e41d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 1 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 36 |
2 files changed, 24 insertions, 13 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 27140e5cdc06..4167e8a48b60 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1869,6 +1869,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif + !mptcp_skb_can_collapse(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index d1902373c974..886ab689a8ae 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1298,7 +1298,7 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt) { + if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1306,11 +1306,6 @@ alloc_skb: zero_window_probe = true; data_seq = snd_una - 1; copy = 1; - - /* all mptcp-level data is acked, no skbs should be present into the - * ssk write queue - */ - WARN_ON_ONCE(reuse_skb); } copy = min_t(size_t, copy, info->limit - info->sent); @@ -1339,7 +1334,6 @@ alloc_skb: if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; - WARN_ON_ONCE(zero_window_probe); goto out; } @@ -2354,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) +/* be sure to send a reset only if the caller asked for it, also + * clean completely the subflow status when the subflow reaches + * TCP_CLOSE state + */ +static void __mptcp_subflow_disconnect(struct sock *ssk, + struct mptcp_subflow_context *subflow, + unsigned int flags) +{ + if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + (flags & MPTCP_CF_FASTCLOSE)) { + /* The MPTCP code never wait on the subflow sockets, TCP-level + * disconnect should never fail + */ + WARN_ON_ONCE(tcp_disconnect(ssk, 0)); + mptcp_subflow_ctx_reset(subflow); + } else { + tcp_shutdown(ssk, SEND_SHUTDOWN); + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2391,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_disconnect() path, + /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; @@ -2401,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - /* The MPTCP code never wait on the subflow sockets, TCP-level - * disconnect should never fail - */ - WARN_ON_ONCE(tcp_disconnect(ssk, 0)); - mptcp_subflow_ctx_reset(subflow); + __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; |