tcp: use one bit in TCP_SKB_CB to mark ACK timestamps

Currently, to avoid a cache line miss for accessing skb_shinfo,
tcp_ack_tstamp skips socket that do not have
SOF_TIMESTAMPING_TX_ACK bit set in sk_tsflags. This is
implemented based on an implicit assumption that the
SOF_TIMESTAMPING_TX_ACK is set via socket options for the
duration that ACK timestamps are needed.

To implement per-write timestamps, this check should be
removed and replaced with a per-packet alternative that
quickly skips packets missing ACK timestamps marks without
a cache-line miss.

To enable per-packet marking without a cache line miss, use
one bit in TCP_SKB_CB to mark a whether a SKB might need a
ack tx timestamp or not. Further checks in tcp_ack_tstamp are not
modified and work as before.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f8bb4a4ed3d1e8480586299eb7ac804fee432bb3..a23282996ca9d6a58df9b2840ddb987a69b788fc 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -754,7 +754,8 @@ struct tcp_skb_cb {
                                TCPCB_REPAIRED)
 
        __u8            ip_dsfield;     /* IPv4 tos or IPv6 dsfield     */
-       /* 1 byte hole */
+       __u8            txstamp_ack:1,  /* Record TX timestamp for ack? */
+                       unused:7;
        __u32           ack_seq;        /* Sequence number ACK'd        */
        union {
                struct inet_skb_parm    h4;

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 08b8b960a8edc9e1791c395192746acfc8cb1caa..ce3c9eb901a0de311ab0b5612f2a2940a5d6dd82 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -432,10 +432,12 @@ static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb)
 {
        if (sk->sk_tsflags) {
                struct skb_shared_info *shinfo = skb_shinfo(skb);
+               struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
                sock_tx_timestamp(sk, &shinfo->tx_flags);
                if (shinfo->tx_flags & SKBTX_ANY_TSTAMP)
                        shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+               tcb->txstamp_ack = !!(shinfo->tx_flags & SKBTX_ACK_TSTAMP);
        }
 }
 

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f87b84a7569159b5b94f479b7238b1822553a9bc..a26e2d26235870c16cb03bc6f4b1081589929fd0 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3082,7 +3082,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
        const struct skb_shared_info *shinfo;
 
        /* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
-       if (likely(!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)))
+       if (likely(!TCP_SKB_CB(skb)->txstamp_ack))
                return;
 
        shinfo = skb_shinfo(skb);