Re: [RFC PATCH v2 net-next 3/7] tcp: Merge tx_flags/tskey/txstamp_ack in tcp_shifted_skb

2016-04-18 Thread Soheil Hassas Yeganeh 
On Mon, Apr 18, 2016 at 6:46 PM, Martin KaFai Lau  wrote:
> After receiving sacks, tcp_shifted_skb() will collapse
> skbs if possible.  tx_flags/tskey/txstamp_ack also has
> to be merged in this case.
>
> This patch resues 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 setsockopt(4, SOL_SOCKET, 37, [2176], 4) = 0
>
> 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 

Acked-by: Soheil Hassas Yeganeh 

> Cc: Willem de Bruijn 
> Cc: Yuchung Cheng 
> ---
>  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 fd40f8c..c0ef054 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -557,6 +557,8 @@ 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 5e45a9c..75e8336 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 889ed96..d21a78f 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2443,8 +2443,8 @@ 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);
>

nice, thanks for the fix!

> --
> 2.5.1
>

[RFC PATCH v2 net-next 3/7] tcp: Merge tx_flags/tskey/txstamp_ack in tcp_shifted_skb

2016-04-18 Thread Martin KaFai Lau 
After receiving sacks, tcp_shifted_skb() will collapse
skbs if possible.  tx_flags/tskey/txstamp_ack also has
to be merged in this case.

This patch resues 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 setsockopt(4, SOL_SOCKET, 37, [2176], 4) = 0

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 
---
 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 fd40f8c..c0ef054 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -557,6 +557,8 @@ 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 5e45a9c..75e8336 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 889ed96..d21a78f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2443,8 +2443,8 @@ 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);
 
-- 
2.5.1