[NET]: Add ECN support for TSO

In the current TSO implementation, NETIF_F_TSO and ECN cannot be
turned on together in a TCP connection.  The problem is that most
hardware that supports TSO does not handle CWR correctly if it is set
in the TSO packet.  Correct handling requires CWR to be set in the
first packet only if it is set in the TSO header.

This patch adds the ability to turn on NETIF_F_TSO and ECN using
GSO if necessary to handle TSO packets with CWR set.  Hardware
that handles CWR correctly can turn on NETIF_F_TSO_ECN in the dev->
features flag.

All TSO packets with CWR set will have the SKB_GSO_TCPV4_ECN set.  If
the output device does not have the NETIF_F_TSO_ECN feature set, GSO
will split the packet up correctly with CWR only set in the first
segment.

With help from Herbert Xu <herbert@gondor.apana.org.au>.

Since ECN can always be enabled with TSO, the SOCK_NO_LARGESEND sock
flag is completely removed.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index efd1e2af0bf32ce4d09bcb28f64b4a4621edd172..aa2d3c12c4d80cffdb6a011ee1d01a0ca57f8af9 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -316,6 +316,7 @@ struct net_device
 #define NETIF_F_TSO            (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
 #define NETIF_F_UFO            (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
 #define NETIF_F_GSO_ROBUST     (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
+#define NETIF_F_TSO_ECN                (SKB_GSO_TCPV4_ECN << NETIF_F_GSO_SHIFT)
 
 #define NETIF_F_GEN_CSUM       (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
 #define NETIF_F_ALL_CSUM       (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5fb72da7da03656cad40587408751f94954a11d5..e74c294929a0792c038a2aa91199e2f6ae030859 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -175,6 +175,9 @@ enum {
 
        /* This indicates the skb is from an untrusted source. */
        SKB_GSO_DODGY = 1 << 2,
+
+       /* This indicates the tcp segment has CWR set. */
+       SKB_GSO_TCPV4_ECN = 1 << 3,
 };
 
 /** 

diff --git a/include/net/sock.h b/include/net/sock.h
index 2d8d6adf16161b9dff029cfee3418e66b77d5f1f..7136bae48c2f1d98977542f253d7b0b97a055829 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -383,7 +383,6 @@ enum sock_flags {
        SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
        SOCK_DBG, /* %SO_DEBUG setting */
        SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
-       SOCK_NO_LARGESEND, /* whether to sent large segments or not */
        SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
        SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
 };
@@ -1033,7 +1032,7 @@ static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
        if (sk->sk_route_caps & NETIF_F_GSO)
                sk->sk_route_caps |= NETIF_F_TSO;
        if (sk->sk_route_caps & NETIF_F_TSO) {
-               if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
+               if (dst->header_len)
                        sk->sk_route_caps &= ~NETIF_F_TSO;
                else 
                        sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;

diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index c6b84397448dac0b810079c96fe1c642773b16fd..7bb366f70934787e19b7dfa2f0ddd05895cd12a0 100644 (file)
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -31,10 +31,9 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct tcp_sock *tp,
                                    struct sk_buff *skb)
 {
        tp->ecn_flags = 0;
-       if (sysctl_tcp_ecn && !(sk->sk_route_caps & NETIF_F_TSO)) {
+       if (sysctl_tcp_ecn) {
                TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE|TCPCB_FLAG_CWR;
                tp->ecn_flags = TCP_ECN_OK;
-               sock_set_flag(sk, SOCK_NO_LARGESEND);
        }
 }
 
@@ -56,6 +55,9 @@ static inline void TCP_ECN_send(struct sock *sk, struct tcp_sock *tp,
                        if (tp->ecn_flags&TCP_ECN_QUEUE_CWR) {
                                tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
                                skb->h.th->cwr = 1;
+                               if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+                                       skb_shinfo(skb)->gso_type |=
+                                               SKB_GSO_TCPV4_ECN;
                        }
                } else {
                        /* ACK or retransmitted segment: clear ECT|CE */

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 94fe5b1f9dcbeb1b819da503b8d5a09d0c35569c..7fa0b4a8a389c6e08c7eaf51ba1ceb922e1eede9 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4178,8 +4178,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                 */
 
                TCP_ECN_rcv_synack(tp, th);
-               if (tp->ecn_flags&TCP_ECN_OK)
-                       sock_set_flag(sk, SOCK_NO_LARGESEND);
 
                tp->snd_wl1 = TCP_SKB_CB(skb)->seq;
                tcp_ack(sk, skb, FLAG_SLOWPATH);
@@ -4322,8 +4320,6 @@ discard:
                tp->max_window = tp->snd_wnd;
 
                TCP_ECN_rcv_syn(tp, th);
-               if (tp->ecn_flags&TCP_ECN_OK)
-                       sock_set_flag(sk, SOCK_NO_LARGESEND);
 
                tcp_mtup_init(sk);
                tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2b9b7f6c7f7c101867d1318bcc56d64b995eb0ed..54b2ef7d3efeb26e2fa7866d344604faa47c8bca 100644 (file)
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -440,8 +440,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                        newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
                newtp->rx_opt.mss_clamp = req->mss;
                TCP_ECN_openreq_child(newtp, req);
-               if (newtp->ecn_flags&TCP_ECN_OK)
-                       sock_set_flag(newsk, SOCK_NO_LARGESEND);
 
                TCP_INC_STATS_BH(TCP_MIB_PASSIVEOPENS);
        }

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bdd71db8bf908e3d20dad25ee43ec777970c139c..5a7cb4a9c867f7a0cd4c1edf738dae2138a9e6c6 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2044,8 +2044,6 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
        memset(th, 0, sizeof(struct tcphdr));
        th->syn = 1;
        th->ack = 1;
-       if (dst->dev->features&NETIF_F_TSO)
-               ireq->ecn_ok = 0;
        TCP_ECN_make_synack(req, th);
        th->source = inet_sk(sk)->sport;
        th->dest = ireq->rmt_port;