From 082ac2d51d9f19ec1c29bdaaaf7fb49889e4fade Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 19 Apr 2016 22:39:28 -0700 Subject: [PATCH 1/2] tcp: Merge tx_flags and tskey in tcp_collapse_retrans If two skbs are merged/collapsed during retransmission, the current logic does not merge the tx_flags and tskey. The end result is the SCM_TSTAMP_ACK timestamp could be missing for a packet. The patch: 1. Merge the tx_flags 2. Overwrite the prev_skb's tskey with the next_skb's tskey BPF Output Before: ~~~~~~ BPF Output After: ~~~~~~ packetdrill-2092 [001] d.s. 453.998486: : ee_data:1459 Packetdrill Script: ~~~~~~ +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, ..., 730) = 730 +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0 0.200 write(4, ..., 730) = 730 +0 setsockopt(4, SOL_SOCKET, 37, [2176], 4) = 0 0.200 write(4, ..., 11680) = 11680 +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0 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 < . 1:1(0) ack 1 win 257 0.300 < . 1:1(0) ack 1 win 257 0.300 > P. 1:1461(1460) 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: Soheil Hassas Yeganeh Tested-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7d2dc015cd19..5bc3c3062672 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2441,6 +2441,20 @@ u32 __tcp_select_window(struct sock *sk) return window; } +static void tcp_skb_collapse_tstamp(struct sk_buff *skb, + const struct sk_buff *next_skb) +{ + const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); + u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP; + + if (unlikely(tsflags)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + + shinfo->tx_flags |= tsflags; + shinfo->tskey = next_shinfo->tskey; + } +} + /* Collapses two adjacent SKB's during retransmission. */ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { @@ -2484,6 +2498,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); + tcp_skb_collapse_tstamp(skb, next_skb); + sk_wmem_free_skb(sk, next_skb); } From cfea5a688eb37bcd1081255df9f9f777f4e61999 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 19 Apr 2016 22:39:29 -0700 Subject: [PATCH 2/2] tcp: Merge tx_flags and tskey in tcp_shifted_skb After receiving sacks, tcp_shifted_skb() will collapse skbs if possible. tx_flags and tskey also have to be merged. This patch reuses the tcp_skb_collapse_tstamp() to handle them. BPF Output Before: ~~~~~ BPF Output After: ~~~~~ <...>-2024 [007] d.s. 88.644374: : ee_data:14599 Packetdrill Script: ~~~~~ +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, ..., 1460) = 1460 +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0 0.200 write(4, ..., 13140) = 13140 0.200 > P. 1:1461(1460) ack 1 0.200 > . 1461:8761(7300) ack 1 0.200 > P. 8761:14601(5840) ack 1 0.300 < . 1:1(0) ack 1 win 257 0.300 > P. 1:1461(1460) ack 1 0.400 < . 1:1(0) ack 14601 win 257 0.400 close(4) = 0 0.400 > F. 14601:14601(0) ack 1 0.500 < F. 1:1(0) ack 14602 win 257 0.500 > . 14602:14602(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: Soheil Hassas Yeganeh Tested-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_output.c | 4 ++-- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index b91370f61be6..6db10228113f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -552,6 +552,8 @@ void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk); +void tcp_skb_collapse_tstamp(struct sk_buff *skb, + const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_resume_early_retransmit(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0edb07185c25..c124c3c12f7c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1309,6 +1309,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); + tcp_skb_collapse_tstamp(prev, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5bc3c3062672..441ae9da3a23 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2441,8 +2441,8 @@ u32 __tcp_select_window(struct sock *sk) return window; } -static void tcp_skb_collapse_tstamp(struct sk_buff *skb, - const struct sk_buff *next_skb) +void tcp_skb_collapse_tstamp(struct sk_buff *skb, + const struct sk_buff *next_skb) { const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;