From ea66758c1795cef81dc59cd5240e9d0f5c5207cf Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 4 May 2022 14:54:06 -0700 Subject: [PATCH] tcp: allow MPTCP to update the announced window The MPTCP RFC requires that the MPTCP-level receive window's right edge never moves backward. Currently the MPTCP code enforces such constraint while tracking the right edge, but it does not reflects it on the wire, as MPTCP lacks a suitable hook to update accordingly the TCP header. This change modifies the existing mptcp_write_options() hook, providing the current packet's TCP header to the MPTCP protocol, so that the next patch could implement the above mentioned constraint. No functional changes intended. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 2 +- net/ipv4/tcp_output.c | 14 ++++++++------ net/mptcp/options.c | 2 +- 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..d4ec894ce67b 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -125,7 +125,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts); bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts); void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5f91a9536e00..b092228e4342 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -445,12 +445,13 @@ struct tcp_out_options { struct mptcp_out_options mptcp; }; -static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp, +static void mptcp_options_write(struct tcphdr *th, __be32 *ptr, + struct tcp_sock *tp, struct tcp_out_options *opts) { #if IS_ENABLED(CONFIG_MPTCP) if (unlikely(OPTION_MPTCP & opts->options)) - mptcp_write_options(ptr, tp, &opts->mptcp); + mptcp_write_options(th, ptr, tp, &opts->mptcp); #endif } @@ -606,9 +607,10 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ -static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, +static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, struct tcp_out_options *opts) { + __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ if (unlikely(OPTION_MD5 & options)) { @@ -702,7 +704,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, smc_options_write(ptr, &options); - mptcp_options_write(ptr, tp, opts); + mptcp_options_write(th, ptr, tp, opts); } static void smc_set_option(const struct tcp_sock *tp, @@ -1355,7 +1357,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, th->window = htons(min(tp->rcv_wnd, 65535U)); } - tcp_options_write((__be32 *)(th + 1), tp, &opts); + tcp_options_write(th, tp, &opts); #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ @@ -3591,7 +3593,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); - tcp_options_write((__be32 *)(th + 1), NULL, &opts); + tcp_options_write(th, NULL, &opts); th->doff = (tcp_header_size >> 2); __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index e05d9458a025..2570911735ab 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1265,7 +1265,7 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) ~csum_unfold(mpext->csum)); } -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts) { const struct sock *ssk = (const struct sock *)tp;