summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2016-04-25 21:44:48 (GMT)
committerDavid S. Miller <davem@davemloft.net>2016-04-28 20:14:18 (GMT)
commitc134ecb87817ce70fd62b2dc48bb079c44fc08df (patch)
tree53328726428d98baa71257d393764ce7013be11b /include/net
parent2a9e8438a29c00432ae14eaceb088b965f8ac290 (diff)
downloadlinux-c134ecb87817ce70fd62b2dc48bb079c44fc08df.tar.xz
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 <mss 1460,sackOK,nop,nop,nop,wscale 7> 0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7> 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 <kafai@fb.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Soheil Hassas Yeganeh <soheil@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Yuchung Cheng <ycheng@google.com> Suggested-by: Eric Dumazet <edumazet@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net')
-rw-r--r--include/net/tcp.h8
1 files changed, 7 insertions, 1 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 992f317..24ec804 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 */