diff options
author | David S. Miller <davem@davemloft.net> | 2016-04-21 18:40:56 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-04-21 18:40:56 (GMT) |
commit | 5bec11cf446eafa4851649db2d53e4086119a36f (patch) | |
tree | 938326d0b6816e77fcfc232c7f5798dfc780d935 | |
parent | 3fa88c51c73a67e7eeda1fcafd809f9185790b31 (diff) | |
parent | cfea5a688eb37bcd1081255df9f9f777f4e61999 (diff) | |
download | linux-5bec11cf446eafa4851649db2d53e4086119a36f.tar.xz |
Merge branch 'tcp-coalesce-merge-timestamps'
Martin KaFai Lau says:
====================
tcp: Merge timestamp info when coalescing skbs
This series is separated from the RFC series related to
tcp_sendmsg(MSG_EOR) and it is targeting for the net branch.
This patchset is focusing on fixing cases where TCP
timestamp could be lost after coalescing skbs.
A BPF prog is used to kprobe to sock_queue_err_skb()
and print out the value of serr->ee.ee_data. The BPF
prog (run-able from bcc) is attached here:
BPF prog used for testing:
~~~~~
from __future__ import print_function
from bcc import BPF
bpf_text = """
int trace_err_skb(struct pt_regs *ctx)
{
struct sk_buff *skb = (struct sk_buff *)ctx->si;
struct sock *sk = (struct sock *)ctx->di;
struct sock_exterr_skb *serr;
u32 ee_data = 0;
if (!sk || !skb)
return 0;
serr = SKB_EXT_ERR(skb);
bpf_probe_read(&ee_data, sizeof(ee_data), &serr->ee.ee_data);
bpf_trace_printk("ee_data:%u\\n", ee_data);
return 0;
};
"""
b = BPF(text=bpf_text)
b.attach_kprobe(event="sock_queue_err_skb", fn_name="trace_err_skb")
print("Attached to kprobe")
b.trace_print()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | include/net/tcp.h | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 16 |
3 files changed, 19 insertions, 0 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index b91370f..6db1022 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 0edb071..c124c3c 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 7d2dc01..441ae9d 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; } +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); } |