diff options
author | Florian Westphal <fw@strlen.de> | 2021-12-04 01:35:32 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2021-12-07 22:36:29 +0300 |
commit | 2c9e77659a0c8d7ce96af3e420914ace1e3f7d21 (patch) | |
tree | fbb3d3ae9ff493a1d6a76b13567f5b2993afb98a /net/mptcp/protocol.c | |
parent | c0e5e11af12b76d0dbed700c1088c6827cdcf56c (diff) | |
download | linux-2c9e77659a0c8d7ce96af3e420914ace1e3f7d21.tar.xz |
mptcp: add TCP_INQ cmsg support
Support the TCP_INQ setsockopt.
This is a boolean that tells recvmsg path to include the remaining
in-sequence bytes in the cmsg data.
v2: do not use CB(skb)->offset, increment map_seq instead (Paolo Abeni)
v3: adjust CB(skb)->map_seq when taking skb from ofo queue (Paolo Abeni)
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/224
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/mptcp/protocol.c')
-rw-r--r-- | net/mptcp/protocol.c | 36 |
1 files changed, 35 insertions, 1 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b100048e43fe..ffc8068aaad0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -46,6 +46,7 @@ struct mptcp_skb_cb { enum { MPTCP_CMSG_TS = BIT(0), + MPTCP_CMSG_INQ = BIT(1), }; static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; @@ -738,6 +739,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; + MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } msk->ack_seq = end_seq; @@ -1784,8 +1786,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, copied += count; if (count < data_len) { - if (!(flags & MSG_PEEK)) + if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; + MPTCP_SKB_CB(skb)->map_seq += count; + } break; } @@ -1965,6 +1969,27 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) return !skb_queue_empty(&msk->receive_queue); } +static unsigned int mptcp_inq_hint(const struct sock *sk) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + const struct sk_buff *skb; + + skb = skb_peek(&msk->receive_queue); + if (skb) { + u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; + + if (hint_val >= INT_MAX) + return INT_MAX; + + return (unsigned int)hint_val; + } + + if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) + return 1; + + return 0; +} + static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -1989,6 +2014,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + if (unlikely(msk->recvmsg_inq)) + cmsg_flags = MPTCP_CMSG_INQ; + while (copied < len) { int bytes_read; @@ -2062,6 +2090,12 @@ out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); + + if (cmsg_flags & MPTCP_CMSG_INQ) { + unsigned int inq = mptcp_inq_hint(sk); + + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + } } pr_debug("msk=%p rx queue empty=%d:%d copied=%d", |