From c134ecb87817ce70fd62b2dc48bb079c44fc08df Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 25 Apr 2016 14:44:48 -0700 Subject: [PATCH 1/3] tcp: Make use of MSG_EOR in tcp_sendmsg This patch adds an eor bit to the TCP_SKB_CB. When MSG_EOR is passed to tcp_sendmsg, the eor bit will be set at the skb containing the last byte of the userland's msg. The eor bit will prevent data from appending to that skb in the future. The change in do_tcp_sendpages is to honor the eor set during the previous tcp_sendmsg(MSG_EOR) call. This patch handles the tcp_sendmsg case. The followup patches will handle other skb coalescing and fragment cases. One potential use case is to use MSG_EOR with SOF_TIMESTAMPING_TX_ACK to get a more accurate TCP ack timestamping on application protocol with multiple outgoing response messages (e.g. HTTP2). Packetdrill script for testing: ~~~~~~ +0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10` +0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1` +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 0.100 < S 0:0(0) win 32792 0.100 > S. 0:0(0) ack 1 0.200 < . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 0.200 write(4, ..., 14600) = 14600 0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730 0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730 0.200 > . 1:7301(7300) ack 1 0.200 > P. 7301:14601(7300) ack 1 0.300 < . 1:1(0) ack 14601 win 257 0.300 > P. 14601:15331(730) ack 1 0.300 > P. 15331:16061(730) ack 1 0.400 < . 1:1(0) ack 16061 win 257 0.400 close(4) = 0 0.400 > F. 16061:16061(0) ack 1 0.400 < F. 1:1(0) ack 16062 win 257 0.400 > . 16062:16062(0) ack 2 Signed-off-by: Martin KaFai Lau Cc: Eric Dumazet Cc: Neal Cardwell Cc: Soheil Hassas Yeganeh Cc: Willem de Bruijn Cc: Yuchung Cheng Suggested-by: Eric Dumazet Acked-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 8 +++++++- net/ipv4/tcp.c | 7 +++++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 992f317c1abe..24ec80483805 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -761,7 +761,8 @@ struct tcp_skb_cb { __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ - unused:7; + eor:1, /* Is skb MSG_EOR marked? */ + unused:6; __u32 ack_seq; /* Sequence number ACK'd */ union { struct inet_skb_parm h4; @@ -808,6 +809,11 @@ static inline int tcp_skb_mss(const struct sk_buff *skb) return TCP_SKB_CB(skb)->tcp_gso_size; } +static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) +{ + return likely(!TCP_SKB_CB(skb)->eor); +} + /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 91993782a947..cb4d1cabb42c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -909,7 +909,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, int copy, i; bool can_coalesce; - if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) { + if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 || + !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; @@ -1157,7 +1158,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = max - skb->len; } - if (copy <= 0) { + if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -1251,6 +1252,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copied += copy; if (!msg_data_left(msg)) { tcp_tx_timestamp(sk, sockc.tsflags, skb); + if (unlikely(flags & MSG_EOR)) + TCP_SKB_CB(skb)->eor = 1; goto out; } From a643b5d41c95164c14b111d19c05d6913bedb80b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 25 Apr 2016 14:44:49 -0700 Subject: [PATCH 2/3] tcp: Handle eor bit when coalescing skb This patch: 1. Prevent next_skb from coalescing to the prev_skb if TCP_SKB_CB(prev_skb)->eor is set 2. Update the TCP_SKB_CB(prev_skb)->eor if coalescing is allowed Packetdrill script for testing: ~~~~~~ +0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10` +0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1` +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 0.100 < S 0:0(0) win 32792 0.100 > S. 0:0(0) ack 1 0.200 < . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730 0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730 0.200 write(4, ..., 11680) = 11680 0.200 > P. 1:731(730) ack 1 0.200 > P. 731:1461(730) ack 1 0.200 > . 1461:8761(7300) ack 1 0.200 > P. 8761:13141(4380) ack 1 0.300 < . 1:1(0) ack 1 win 257 0.300 > P. 1:731(730) ack 1 0.300 > P. 731:1461(730) ack 1 0.400 < . 1:1(0) ack 13141 win 257 0.400 close(4) = 0 0.400 > F. 13141:13141(0) ack 1 0.500 < F. 1:1(0) ack 13142 win 257 0.500 > . 13142:13142(0) ack 2 Signed-off-by: Martin KaFai Lau Cc: Eric Dumazet Cc: Neal Cardwell Cc: Soheil Hassas Yeganeh Cc: Willem de Bruijn Cc: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++++ net/ipv4/tcp_output.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 70c370b93762..1fb19c91e091 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1303,6 +1303,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, } TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) TCP_SKB_CB(prev)->end_seq++; @@ -1368,6 +1369,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; + if (!tcp_skb_can_collapse_to(prev)) + goto fallback; + in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && !before(end_seq, TCP_SKB_CB(skb)->end_seq); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b3a31b4df57c..77c6cbb897e6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2499,6 +2499,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; + TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); @@ -2550,6 +2551,9 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!tcp_can_collapse(sk, skb)) break; + if (!tcp_skb_can_collapse_to(to)) + break; + space -= skb->len; if (first) { From a166140e810e74682f3ca248ef3879177b5c1315 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 25 Apr 2016 14:44:50 -0700 Subject: [PATCH 3/3] tcp: Handle eor bit when fragmenting a skb When fragmenting a skb, the next_skb should carry the eor from prev_skb. The eor of prev_skb should also be reset. Packetdrill script for testing: ~~~~~~ +0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10` +0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1` +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 0.100 < S 0:0(0) win 32792 0.100 > S. 0:0(0) ack 1 0.200 < . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 0.200 sendto(4, ..., 15330, MSG_EOR, ..., ...) = 15330 0.200 sendto(4, ..., 730, 0, ..., ...) = 730 0.200 > . 1:7301(7300) ack 1 0.200 > . 7301:14601(7300) ack 1 0.300 < . 1:1(0) ack 14601 win 257 0.300 > P. 14601:15331(730) ack 1 0.300 > P. 15331:16061(730) ack 1 0.400 < . 1:1(0) ack 16061 win 257 0.400 close(4) = 0 0.400 > F. 16061:16061(0) ack 1 0.400 < F. 1:1(0) ack 16062 win 257 0.400 > . 16062:16062(0) ack 2 Signed-off-by: Martin KaFai Lau Cc: Eric Dumazet Cc: Neal Cardwell Cc: Soheil Hassas Yeganeh Cc: Willem de Bruijn Cc: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 77c6cbb897e6..1a487ff95d4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1134,6 +1134,12 @@ static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) } } +static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) +{ + TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor; + TCP_SKB_CB(skb)->eor = 0; +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. @@ -1179,6 +1185,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; + tcp_skb_fragment_eor(skb, buff); if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { /* Copy and checksum data tail into the new buffer. */ @@ -1739,6 +1746,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; + tcp_skb_fragment_eor(skb, buff); + buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff);