From 07c2c7a3b622e109ba4d2efd916da0477617ce81 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 24 Feb 2022 16:52:57 -0800 Subject: mptcp: accurate SIOCOUTQ for fallback socket The MPTCP SIOCOUTQ implementation is not very accurate in case of fallback: it only measures the data in the MPTCP-level write queue, but it does not take in account the subflow write queue utilization. In case of fallback the first can be empty, while the latter is not. The above produces sporadic self-tests issues and can foul legit user-space application. Fix the issue additionally querying the subflow in case of fallback. Fixes: 644807e3e462 ("mptcp: add SIOCINQ, OUTQ and OUTQNSD ioctls") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/260 Reported-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f60f01b14fac..12bb28c5007e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3294,6 +3294,17 @@ static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) return 0; delta = msk->write_seq - v; + if (__mptcp_check_fallback(msk) && msk->first) { + struct tcp_sock *tp = tcp_sk(msk->first); + + /* the first subflow is disconnected after close - see + * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq + * so ignore that status, too. + */ + if (!((1 << msk->first->sk_state) & + (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))) + delta += READ_ONCE(tp->write_seq) - tp->snd_una; + } if (delta > INT_MAX) delta = INT_MAX; -- cgit v1.2.3-70-g09d2 From 877d11f0332cd2160e19e3313e262754c321fa36 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Thu, 24 Feb 2022 16:52:59 -0800 Subject: mptcp: Correctly set DATA_FIN timeout when number of retransmits is large Syzkaller with UBSAN uncovered a scenario where a large number of DATA_FIN retransmits caused a shift-out-of-bounds in the DATA_FIN timeout calculation: ================================================================================ UBSAN: shift-out-of-bounds in net/mptcp/protocol.c:470:29 shift exponent 32 is too large for 32-bit type 'unsigned int' CPU: 1 PID: 13059 Comm: kworker/1:0 Not tainted 5.17.0-rc2-00630-g5fbf21c90c60 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: events mptcp_worker Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 ubsan_epilogue+0xb/0x5a lib/ubsan.c:151 __ubsan_handle_shift_out_of_bounds.cold+0xb2/0x20e lib/ubsan.c:330 mptcp_set_datafin_timeout net/mptcp/protocol.c:470 [inline] __mptcp_retrans.cold+0x72/0x77 net/mptcp/protocol.c:2445 mptcp_worker+0x58a/0xa70 net/mptcp/protocol.c:2528 process_one_work+0x9df/0x16d0 kernel/workqueue.c:2307 worker_thread+0x95/0xe10 kernel/workqueue.c:2454 kthread+0x2f4/0x3b0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 ================================================================================ This change limits the maximum timeout by limiting the size of the shift, which keeps all intermediate values in-bounds. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/259 Fixes: 6477dd39e62c ("mptcp: Retransmit DATA_FIN") Acked-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net/mptcp/protocol.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 12bb28c5007e..1c72f25f083e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -466,9 +466,12 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) static void mptcp_set_datafin_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + u32 retransmits; - mptcp_sk(sk)->timer_ival = min(TCP_RTO_MAX, - TCP_RTO_MIN << icsk->icsk_retransmits); + retransmits = min_t(u32, icsk->icsk_retransmits, + ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); + + mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) -- cgit v1.2.3-70-g09d2