tcp: use TCP_SKB_CB(skb)->tcp_flags in input path

Input path of TCP do not currently uses TCP_SKB_CB(skb)->tcp_flags,
which is only used in output path.

tcp_recvmsg(), looks at tcp_hdr(skb)->syn for every skb found in receive queue,
and its unfortunate because this bit is located in a cache line right before
the payload.

We can simplify TCP by copying tcp flags into TCP_SKB_CB(skb)->tcp_flags.

This patch does so, and avoids the cache line miss in tcp_recvmsg()

Following patches will
- allow a segment with FIN being coalesced in tcp_try_coalesce()
- simplify tcp_collapse() by not copying the headers.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 541f26a67ba28861c882f819369baf2ad2cd4724..070aeff1b13166d78df3bf84fc20438afd8a6e04 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1510,9 +1510,9 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 
        while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
                offset = seq - TCP_SKB_CB(skb)->seq;
-               if (tcp_hdr(skb)->syn)
+               if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
                        offset--;
-               if (offset < skb->len || tcp_hdr(skb)->fin) {
+               if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
                        *off = offset;
                        return skb;
                }
@@ -1585,7 +1585,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
                        if (offset + 1 != skb->len)
                                continue;
                }
-               if (tcp_hdr(skb)->fin) {
+               if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
                        sk_eat_skb(sk, skb, false);
                        ++seq;
                        break;
@@ -1722,11 +1722,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                                break;
 
                        offset = *seq - TCP_SKB_CB(skb)->seq;
-                       if (tcp_hdr(skb)->syn)
+                       if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
                                offset--;
                        if (offset < skb->len)
                                goto found_ok_skb;
-                       if (tcp_hdr(skb)->fin)
+                       if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                                goto found_fin_ok;
                        WARN(!(flags & MSG_PEEK),
                             "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
@@ -1959,7 +1959,7 @@ skip_copy:
                if (used + offset < skb->len)
                        continue;
 
-               if (tcp_hdr(skb)->fin)
+               if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                        goto found_fin_ok;
                if (!(flags & MSG_PEEK)) {
                        sk_eat_skb(sk, skb, copied_early);
@@ -2160,8 +2160,10 @@ void tcp_close(struct sock *sk, long timeout)
         *  reader process may not have drained the data yet!
         */
        while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-               u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
-                         tcp_hdr(skb)->fin;
+               u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
+
+               if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+                       len--;
                data_was_unread += len;
                __kfree_skb(skb);
        }

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f97003ad0af55998df0be629f3c99cd093fd4e43..8f639a4face9c7bd349a6d14fcd35cc7b602c4b3 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4093,7 +4093,7 @@ static void tcp_ofo_queue(struct sock *sk)
                __skb_unlink(skb, &tp->out_of_order_queue);
                __skb_queue_tail(&sk->sk_receive_queue, skb);
                tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-               if (tcp_hdr(skb)->fin)
+               if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                        tcp_fin(sk);
        }
 }
@@ -4513,7 +4513,7 @@ restart:
                 * - bloated or contains data before "start" or
                 *   overlaps to the next one.
                 */
-               if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
+               if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
                    (tcp_win_from_space(skb->truesize) > skb->len ||
                     before(TCP_SKB_CB(skb)->seq, start))) {
                        end_of_skbs = false;
@@ -4532,7 +4532,8 @@ restart:
                /* Decided to skip this, advance start seq. */
                start = TCP_SKB_CB(skb)->end_seq;
        }
-       if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
+       if (end_of_skbs ||
+           (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
                return;
 
        while (before(start, end)) {
@@ -4579,8 +4580,7 @@ restart:
                                skb = tcp_collapse_one(sk, skb, list);
                                if (!skb ||
                                    skb == tail ||
-                                   tcp_hdr(skb)->syn ||
-                                   tcp_hdr(skb)->fin)
+                                   (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
                                        return;
                        }
                }

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7881b96d2b7214a87563c52ab0d06f15efc7e1bb..006b045716d87495d51363236825435e54657b10 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1638,6 +1638,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
        TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
                                    skb->len - th->doff * 4);
        TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+       TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
        TCP_SKB_CB(skb)->tcp_tw_isn = 0;
        TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
        TCP_SKB_CB(skb)->sacked  = 0;

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 1835480336acb9344558ff5a71e037c8992204f1..de51a88bec6f70279fa50b96517d4ee03b5443dd 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1415,6 +1415,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
        TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
                                    skb->len - th->doff*4);
        TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+       TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
        TCP_SKB_CB(skb)->tcp_tw_isn = 0;
        TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
        TCP_SKB_CB(skb)->sacked = 0;