From a6f0459aadf1b41a9b9fae02006b1db024d60856 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 28 Oct 2025 12:57:59 +0100 Subject: mptcp: fix subflow rcvbuf adjust The mptcp PM can add subflow to the conn_list before tcp_init_transfer(). Calling tcp_rcvbuf_grow() on such subflow is not correct as later init will overwrite the update. Fix the issue calling tcp_rcvbuf_grow() only after init buffer initialization. Fixes: e118cdc34dd1 ("mptcp: rcvbuf auto-tuning improvement") Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251028-net-tcp-recv-autotune-v3-1-74b43ba4c84c@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0292162a14ee..a8a3bdf95543 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2051,6 +2051,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) msk->rcvq_space.space = msk->rcvq_space.copied; if (mptcp_rcvbuf_grow(sk)) { + int copied = msk->rcvq_space.copied; /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to @@ -2063,8 +2064,11 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); - tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied; - tcp_rcvbuf_grow(ssk); + /* subflows can be added before tcp_init_transfer() */ + if (tcp_sk(ssk)->rcvq_space.space) { + tcp_sk(ssk)->rcvq_space.space = copied; + tcp_rcvbuf_grow(ssk); + } unlock_sock_fast(ssk, slow); } } -- cgit v1.2.3 From b1e014a1f3275a6f3d0f2b30b8117447fc3915f5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Oct 2025 12:58:01 +0100 Subject: tcp: add newval parameter to tcp_rcvbuf_grow() This patch has no functional change, and prepares the following one. tcp_rcvbuf_grow() will need to have access to tp->rcvq_space.space old and new values. Change mptcp_rcvbuf_grow() in a similar way. Signed-off-by: Eric Dumazet [ Moved 'oldval' declaration to the next patch to avoid warnings at build time. ] Signed-off-by: Matthieu Baerts (NGI0) Reviewed-by: Neal Cardwell Link: https://patch.msgid.link/20251028-net-tcp-recv-autotune-v3-3-74b43ba4c84c@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a8a3bdf95543..052a0c62023f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -194,17 +194,18 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, * - mptcp does not maintain a msk-level window clamp * - returns true when the receive buffer is actually updated */ -static bool mptcp_rcvbuf_grow(struct sock *sk) +static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) { struct mptcp_sock *msk = mptcp_sk(sk); const struct net *net = sock_net(sk); - int rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap; + msk->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return false; - rcvwin = msk->rcvq_space.space << 1; + rcvwin = newval << 1; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; @@ -334,7 +335,7 @@ end: skb_set_owner_r(skb, sk); /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) - mptcp_rcvbuf_grow(sk); + mptcp_rcvbuf_grow(sk, msk->rcvq_space.space); } static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, @@ -2049,10 +2050,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; - msk->rcvq_space.space = msk->rcvq_space.copied; - if (mptcp_rcvbuf_grow(sk)) { - int copied = msk->rcvq_space.copied; - + if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) { /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can @@ -2065,10 +2063,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); /* subflows can be added before tcp_init_transfer() */ - if (tcp_sk(ssk)->rcvq_space.space) { - tcp_sk(ssk)->rcvq_space.space = copied; - tcp_rcvbuf_grow(ssk); - } + if (tcp_sk(ssk)->rcvq_space.space) + tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied); unlock_sock_fast(ssk, slow); } } -- cgit v1.2.3 From aa251c84636c326471ca9d53723816ba8fffe2bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Oct 2025 12:58:02 +0100 Subject: tcp: fix too slow tcp_rcvbuf_grow() action While the blamed commits apparently avoided an overshoot, they also limited how fast a sender can increase BDP at each RTT. This is not exactly a revert, we do not add the 16 * tp->advmss cushion we had, and we are keeping the out_of_order_queue contribution. Do the same in mptcp_rcvbuf_grow(). Tested: emulated 50ms rtt (tcp_stream --tcp-tx-delay 50000), cubic 20 second flow. net.ipv4.tcp_rmem set to "4096 131072 67000000" perf record -a -e tcp:tcp_rcvbuf_grow sleep 20 perf script Before: We can see we fail to roughly double RWIN at each RTT. Sender is RWIN limited while CWND is ramping up (before getting tcp_wmem limited). tcp_stream 33793 [010] 825.717525: tcp:tcp_rcvbuf_grow: time=100869 rtt_us=50428 copied=49152 inq=0 space=40960 ooo=0 scaling_ratio=219 rcvbuf=131072 rcv_ssthresh=103970 window_clamp=112128 rcv_wnd=106496 tcp_stream 33793 [010] 825.768966: tcp:tcp_rcvbuf_grow: time=51447 rtt_us=50362 copied=86016 inq=0 space=49152 ooo=0 scaling_ratio=219 rcvbuf=131072 rcv_ssthresh=107474 window_clamp=112128 rcv_wnd=106496 tcp_stream 33793 [010] 825.821539: tcp:tcp_rcvbuf_grow: time=52577 rtt_us=50243 copied=114688 inq=0 space=86016 ooo=0 scaling_ratio=219 rcvbuf=201096 rcv_ssthresh=167377 window_clamp=172031 rcv_wnd=167936 tcp_stream 33793 [010] 825.871781: tcp:tcp_rcvbuf_grow: time=50248 rtt_us=50237 copied=167936 inq=0 space=114688 ooo=0 scaling_ratio=219 rcvbuf=268129 rcv_ssthresh=224722 window_clamp=229375 rcv_wnd=225280 tcp_stream 33793 [010] 825.922475: tcp:tcp_rcvbuf_grow: time=50698 rtt_us=50183 copied=241664 inq=0 space=167936 ooo=0 scaling_ratio=219 rcvbuf=392617 rcv_ssthresh=331217 window_clamp=335871 rcv_wnd=323584 tcp_stream 33793 [010] 825.973326: tcp:tcp_rcvbuf_grow: time=50855 rtt_us=50213 copied=339968 inq=0 space=241664 ooo=0 scaling_ratio=219 rcvbuf=564986 rcv_ssthresh=478674 window_clamp=483327 rcv_wnd=462848 tcp_stream 33793 [010] 826.023970: tcp:tcp_rcvbuf_grow: time=50647 rtt_us=50248 copied=491520 inq=0 space=339968 ooo=0 scaling_ratio=219 rcvbuf=794811 rcv_ssthresh=671778 window_clamp=679935 rcv_wnd=651264 tcp_stream 33793 [010] 826.074612: tcp:tcp_rcvbuf_grow: time=50648 rtt_us=50227 copied=700416 inq=0 space=491520 ooo=0 scaling_ratio=219 rcvbuf=1149124 rcv_ssthresh=974881 window_clamp=983039 rcv_wnd=942080 tcp_stream 33793 [010] 826.125452: tcp:tcp_rcvbuf_grow: time=50845 rtt_us=50225 copied=987136 inq=8192 space=700416 ooo=0 scaling_ratio=219 rcvbuf=1637502 rcv_ssthresh=1392674 window_clamp=1400831 rcv_wnd=1339392 tcp_stream 33793 [010] 826.175698: tcp:tcp_rcvbuf_grow: time=50250 rtt_us=50198 copied=1347584 inq=0 space=978944 ooo=0 scaling_ratio=219 rcvbuf=2288672 rcv_ssthresh=1949729 window_clamp=1957887 rcv_wnd=1945600 tcp_stream 33793 [010] 826.225947: tcp:tcp_rcvbuf_grow: time=50252 rtt_us=50240 copied=1945600 inq=0 space=1347584 ooo=0 scaling_ratio=219 rcvbuf=3150516 rcv_ssthresh=2687010 window_clamp=2695167 rcv_wnd=2691072 tcp_stream 33793 [010] 826.276175: tcp:tcp_rcvbuf_grow: time=50233 rtt_us=50224 copied=2691072 inq=0 space=1945600 ooo=0 scaling_ratio=219 rcvbuf=4548617 rcv_ssthresh=3883041 window_clamp=3891199 rcv_wnd=3887104 tcp_stream 33793 [010] 826.326403: tcp:tcp_rcvbuf_grow: time=50233 rtt_us=50229 copied=3887104 inq=0 space=2691072 ooo=0 scaling_ratio=219 rcvbuf=6291456 rcv_ssthresh=5370482 window_clamp=5382144 rcv_wnd=5373952 tcp_stream 33793 [010] 826.376723: tcp:tcp_rcvbuf_grow: time=50323 rtt_us=50218 copied=5373952 inq=0 space=3887104 ooo=0 scaling_ratio=219 rcvbuf=9087658 rcv_ssthresh=7755537 window_clamp=7774207 rcv_wnd=7757824 tcp_stream 33793 [010] 826.426991: tcp:tcp_rcvbuf_grow: time=50274 rtt_us=50196 copied=7757824 inq=180224 space=5373952 ooo=0 scaling_ratio=219 rcvbuf=12563759 rcv_ssthresh=10729233 window_clamp=10747903 rcv_wnd=10575872 tcp_stream 33793 [010] 826.477229: tcp:tcp_rcvbuf_grow: time=50241 rtt_us=50078 copied=10731520 inq=180224 space=7577600 ooo=0 scaling_ratio=219 rcvbuf=17715667 rcv_ssthresh=15136529 window_clamp=15155199 rcv_wnd=14983168 tcp_stream 33793 [010] 826.527482: tcp:tcp_rcvbuf_grow: time=50258 rtt_us=50153 copied=15138816 inq=360448 space=10551296 ooo=0 scaling_ratio=219 rcvbuf=24667870 rcv_ssthresh=21073410 window_clamp=21102591 rcv_wnd=20766720 tcp_stream 33793 [010] 826.577712: tcp:tcp_rcvbuf_grow: time=50234 rtt_us=50228 copied=21073920 inq=0 space=14778368 ooo=0 scaling_ratio=219 rcvbuf=34550339 rcv_ssthresh=29517041 window_clamp=29556735 rcv_wnd=29519872 tcp_stream 33793 [010] 826.627982: tcp:tcp_rcvbuf_grow: time=50275 rtt_us=50220 copied=29519872 inq=540672 space=21073920 ooo=0 scaling_ratio=219 rcvbuf=49268707 rcv_ssthresh=42090625 window_clamp=42147839 rcv_wnd=41627648 tcp_stream 33793 [010] 826.678274: tcp:tcp_rcvbuf_grow: time=50296 rtt_us=50185 copied=42053632 inq=761856 space=28979200 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57238168 window_clamp=57316406 rcv_wnd=56606720 tcp_stream 33793 [010] 826.728627: tcp:tcp_rcvbuf_grow: time=50357 rtt_us=50128 copied=43913216 inq=851968 space=41291776 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=56524800 tcp_stream 33793 [010] 827.131364: tcp:tcp_rcvbuf_grow: time=50239 rtt_us=50127 copied=43843584 inq=655360 space=43061248 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=56696832 tcp_stream 33793 [010] 827.181613: tcp:tcp_rcvbuf_grow: time=50254 rtt_us=50115 copied=43843584 inq=524288 space=43188224 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=56807424 tcp_stream 33793 [010] 828.339635: tcp:tcp_rcvbuf_grow: time=50283 rtt_us=50110 copied=43843584 inq=458752 space=43319296 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=56864768 tcp_stream 33793 [010] 828.440350: tcp:tcp_rcvbuf_grow: time=50404 rtt_us=50099 copied=43843584 inq=393216 space=43384832 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=56922112 tcp_stream 33793 [010] 829.195106: tcp:tcp_rcvbuf_grow: time=50154 rtt_us=50077 copied=43843584 inq=196608 space=43450368 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57290728 window_clamp=57316406 rcv_wnd=57090048 After: It takes few steps to increase RWIN. Sender is no longer RWIN limited. tcp_stream 50826 [010] 935.634212: tcp:tcp_rcvbuf_grow: time=100788 rtt_us=50315 copied=49152 inq=0 space=40960 ooo=0 scaling_ratio=219 rcvbuf=131072 rcv_ssthresh=103970 window_clamp=112128 rcv_wnd=106496 tcp_stream 50826 [010] 935.685642: tcp:tcp_rcvbuf_grow: time=51437 rtt_us=50361 copied=86016 inq=0 space=49152 ooo=0 scaling_ratio=219 rcvbuf=160875 rcv_ssthresh=132969 window_clamp=137623 rcv_wnd=131072 tcp_stream 50826 [010] 935.738299: tcp:tcp_rcvbuf_grow: time=52660 rtt_us=50256 copied=139264 inq=0 space=86016 ooo=0 scaling_ratio=219 rcvbuf=502741 rcv_ssthresh=411497 window_clamp=430079 rcv_wnd=413696 tcp_stream 50826 [010] 935.788544: tcp:tcp_rcvbuf_grow: time=50249 rtt_us=50233 copied=307200 inq=0 space=139264 ooo=0 scaling_ratio=219 rcvbuf=728690 rcv_ssthresh=618717 window_clamp=623371 rcv_wnd=618496 tcp_stream 50826 [010] 935.838796: tcp:tcp_rcvbuf_grow: time=50258 rtt_us=50202 copied=618496 inq=0 space=307200 ooo=0 scaling_ratio=219 rcvbuf=2450338 rcv_ssthresh=1855709 window_clamp=2096187 rcv_wnd=1859584 tcp_stream 50826 [010] 935.889140: tcp:tcp_rcvbuf_grow: time=50347 rtt_us=50166 copied=1261568 inq=0 space=618496 ooo=0 scaling_ratio=219 rcvbuf=4376503 rcv_ssthresh=3725291 window_clamp=3743961 rcv_wnd=3706880 tcp_stream 50826 [010] 935.939435: tcp:tcp_rcvbuf_grow: time=50300 rtt_us=50185 copied=2478080 inq=24576 space=1261568 ooo=0 scaling_ratio=219 rcvbuf=9082648 rcv_ssthresh=7733731 window_clamp=7769921 rcv_wnd=7692288 tcp_stream 50826 [010] 935.989681: tcp:tcp_rcvbuf_grow: time=50251 rtt_us=50221 copied=4915200 inq=114688 space=2453504 ooo=0 scaling_ratio=219 rcvbuf=16574936 rcv_ssthresh=14108110 window_clamp=14179339 rcv_wnd=14024704 tcp_stream 50826 [010] 936.039967: tcp:tcp_rcvbuf_grow: time=50289 rtt_us=50279 copied=9830400 inq=114688 space=4800512 ooo=0 scaling_ratio=219 rcvbuf=32695050 rcv_ssthresh=27896187 window_clamp=27969593 rcv_wnd=27815936 tcp_stream 50826 [010] 936.090172: tcp:tcp_rcvbuf_grow: time=50211 rtt_us=50200 copied=19841024 inq=114688 space=9715712 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57245176 window_clamp=57316406 rcv_wnd=57163776 tcp_stream 50826 [010] 936.140430: tcp:tcp_rcvbuf_grow: time=50262 rtt_us=50197 copied=39501824 inq=114688 space=19726336 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57245176 window_clamp=57316406 rcv_wnd=57163776 tcp_stream 50826 [010] 936.190527: tcp:tcp_rcvbuf_grow: time=50101 rtt_us=50071 copied=43655168 inq=262144 space=39387136 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57259192 window_clamp=57316406 rcv_wnd=57032704 tcp_stream 50826 [010] 936.240719: tcp:tcp_rcvbuf_grow: time=50197 rtt_us=50057 copied=43843584 inq=262144 space=43393024 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57259192 window_clamp=57316406 rcv_wnd=57032704 tcp_stream 50826 [010] 936.341271: tcp:tcp_rcvbuf_grow: time=50297 rtt_us=50123 copied=43843584 inq=131072 space=43581440 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57259192 window_clamp=57316406 rcv_wnd=57147392 tcp_stream 50826 [010] 936.642503: tcp:tcp_rcvbuf_grow: time=50131 rtt_us=50084 copied=43843584 inq=0 space=43712512 ooo=0 scaling_ratio=219 rcvbuf=67000000 rcv_ssthresh=57259192 window_clamp=57316406 rcv_wnd=57262080 Fixes: 65c5287892e9 ("tcp: fix sk_rcvbuf overshoot") Fixes: e118cdc34dd1 ("mptcp: rcvbuf auto-tuning improvement") Reported-by: Neal Cardwell Signed-off-by: Eric Dumazet Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/589 Signed-off-by: Matthieu Baerts (NGI0) Reviewed-by: Neal Cardwell Link: https://patch.msgid.link/20251028-net-tcp-recv-autotune-v3-4-74b43ba4c84c@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 052a0c62023f..875027b9319c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -198,15 +198,23 @@ static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) { struct mptcp_sock *msk = mptcp_sk(sk); const struct net *net = sock_net(sk); - u32 rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap, oldval; + u64 grow; + oldval = msk->rcvq_space.space; msk->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return false; + /* DRS is always one RTT late. */ rcvwin = newval << 1; + /* slow start: allow the sender to double its rate. */ + grow = (u64)rcvwin * (newval - oldval); + do_div(grow, oldval); + rcvwin += grow << 1; + if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; -- cgit v1.2.3 From 27b0e701d3872ba59c5b579a9e8a02ea49ad3d3b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 28 Oct 2025 09:16:52 +0100 Subject: mptcp: drop bogus optimization in __mptcp_check_push() Accessing the transmit queue without owning the msk socket lock is inherently racy, hence __mptcp_check_push() could actually quit early even when there is pending data. That in turn could cause unexpected tx lock and timeout. Dropping the early check avoids the race, implicitly relaying on later tests under the relevant lock. With such change, all the other mptcp_send_head() call sites are now under the msk socket lock and we can additionally drop the now unneeded annotation on the transmit head pointer accesses. Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Geliang Tang Tested-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-1-38ffff5a9ec8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 875027b9319c..655a2a45224f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1007,7 +1007,7 @@ static void __mptcp_clean_una(struct sock *sk) if (WARN_ON_ONCE(!msk->recovery)) break; - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); } dfrag_clear(sk, dfrag); @@ -1552,7 +1552,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, mptcp_update_post_push(msk, dfrag, ret); } - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || @@ -1912,7 +1912,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) - WRITE_ONCE(msk->first_pending, dfrag); + msk->first_pending = dfrag; } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, @@ -2882,7 +2882,7 @@ static void __mptcp_clear_xmit(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - WRITE_ONCE(msk->first_pending, NULL); + msk->first_pending = NULL; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } @@ -3422,9 +3422,6 @@ void __mptcp_data_acked(struct sock *sk) void __mptcp_check_push(struct sock *sk, struct sock *ssk) { - if (!mptcp_send_head(sk)) - return; - if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else -- cgit v1.2.3 From 8e04ce45a8db7a080220e86e249198fa676b83dc Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 28 Oct 2025 09:16:53 +0100 Subject: mptcp: fix MSG_PEEK stream corruption If a MSG_PEEK | MSG_WAITALL read operation consumes all the bytes in the receive queue and recvmsg() need to waits for more data - i.e. it's a blocking one - upon arrival of the next packet the MPTCP protocol will start again copying the oldest data present in the receive queue, corrupting the data stream. Address the issue explicitly tracking the peeked sequence number, restarting from the last peeked byte. Fixes: ca4fb892579f ("mptcp: add MSG_PEEK support") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Geliang Tang Tested-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-2-38ffff5a9ec8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 655a2a45224f..2535788569ab 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1945,22 +1945,36 @@ do_error: static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); -static int __mptcp_recvmsg_mskq(struct sock *sk, - struct msghdr *msg, - size_t len, int flags, +static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, + size_t len, int flags, int copied_total, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; + int total_data_len = 0; int copied = 0; skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { - u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 delta, offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; - u32 count = min_t(size_t, len - copied, data_len); + u32 count; int err; + if (flags & MSG_PEEK) { + /* skip already peeked skbs */ + if (total_data_len + data_len <= copied_total) { + total_data_len += data_len; + continue; + } + + /* skip the already peeked data in the current skb */ + delta = copied_total - total_data_len; + offset += delta; + data_len -= delta; + } + + count = min_t(size_t, len - copied, data_len); if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { @@ -1977,16 +1991,14 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, copied += count; - if (count < data_len) { - if (!(flags & MSG_PEEK)) { + if (!(flags & MSG_PEEK)) { + msk->bytes_consumed += count; + if (count < data_len) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; - msk->bytes_consumed += count; + break; } - break; - } - if (!(flags & MSG_PEEK)) { /* avoid the indirect call, we know the destructor is sock_rfree */ skb->destructor = NULL; skb->sk = NULL; @@ -1994,7 +2006,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); skb_attempt_defer_free(skb); - msk->bytes_consumed += count; } if (copied >= len) @@ -2191,7 +2202,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int err, bytes_read; - bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags); + bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, + copied, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; -- cgit v1.2.3 From a824084b98d8a1dbd6e85d0842a8eb5e73467f59 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 28 Oct 2025 09:16:54 +0100 Subject: mptcp: restore window probe Since commit 72377ab2d671 ("mptcp: more conservative check for zero probes") the MPTCP-level zero window probe check is always disabled, as the TCP-level write queue always contains at least the newly allocated skb. Refine the relevant check tacking in account that the above condition and that such skb can have zero length. Fixes: 72377ab2d671 ("mptcp: more conservative check for zero probes") Cc: stable@vger.kernel.org Reported-by: Geliang Tang Closes: https://lore.kernel.org/d0a814c364e744ca6b836ccd5b6e9146882e8d42.camel@kernel.org Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Tested-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-3-38ffff5a9ec8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2535788569ab..5d8714adae6c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1299,7 +1299,12 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { + /* No need for zero probe if there are any data pending + * either at the msk or ssk level; skb is the current write + * queue tail and can be empty at this point. + */ + if (snd_una != msk->snd_nxt || skb->len || + skb != tcp_send_head(ssk)) { tcp_remove_empty_skb(ssk); return 0; } -- cgit v1.2.3 From fe11dfa10919ce594682c76f5f648a0840d80a2b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 28 Oct 2025 09:16:55 +0100 Subject: mptcp: zero window probe mib Explicitly account for MPTCP-level zero windows probe, to catch hopefully earlier issues alike the one addressed by the previous patch. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Tested-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-4-38ffff5a9ec8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5d8714adae6c..2d6b8de35c44 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1355,6 +1355,7 @@ alloc_skb: mpext->dsn64); if (zero_window_probe) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_WINPROBE); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) -- cgit v1.2.3