net: Add net protocol offload registration infrustructure

[~andy/linux] / net / ipv4 / af_inet.c

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fe4582ca969a4ff85c862f8fd96d3b6ec3d03a4d..3918d869d6d4f7b7e02f9f254158452f156987f2 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -212,6 +212,26 @@ int inet_listen(struct socket *sock, int backlog)
         * we can only allow the backlog to be adjusted.
         */
        if (old_state != TCP_LISTEN) {
+               /* Check special setups for testing purpose to enable TFO w/o
+                * requiring TCP_FASTOPEN sockopt.
+                * Note that only TCP sockets (SOCK_STREAM) will reach here.
+                * Also fastopenq may already been allocated because this
+                * socket was in TCP_LISTEN state previously but was
+                * shutdown() (rather than close()).
+                */
+               if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 &&
+                   inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) {
+                       if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0)
+                               err = fastopen_init_queue(sk, backlog);
+                       else if ((sysctl_tcp_fastopen &
+                                 TFO_SERVER_WO_SOCKOPT2) != 0)
+                               err = fastopen_init_queue(sk,
+                                   ((uint)sysctl_tcp_fastopen) >> 16);
+                       else
+                               err = 0;
+                       if (err)
+                               goto out;
+               }
                err = inet_csk_listen_start(sk, backlog);
                if (err)
                        goto out;
@@ -701,7 +721,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
 
        sock_rps_record_flow(sk2);
        WARN_ON(!((1 << sk2->sk_state) &
-                 (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+                 (TCPF_ESTABLISHED | TCPF_SYN_RECV |
+                 TCPF_CLOSE_WAIT | TCPF_CLOSE)));
 
        sock_graft(sk2, newsock);
 
@@ -1364,7 +1385,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
        if (*(u8 *)iph != 0x45)
                goto out_unlock;
 
-       if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
+       if (unlikely(ip_fast_csum((u8 *)iph, 5)))
                goto out_unlock;
 
        id = ntohl(*(__be32 *)&iph->id);
@@ -1380,7 +1401,6 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
                iph2 = ip_hdr(p);
 
                if ((iph->protocol ^ iph2->protocol) |
-                   (iph->tos ^ iph2->tos) |
                    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
                    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
                        NAPI_GRO_CB(p)->same_flow = 0;
@@ -1390,6 +1410,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
                /* All fields must match except length and checksum. */
                NAPI_GRO_CB(p)->flush |=
                        (iph->ttl ^ iph2->ttl) |
+                       (iph->tos ^ iph2->tos) |
                        ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 
                NAPI_GRO_CB(p)->flush |= flush;
@@ -1545,6 +1566,13 @@ static const struct net_protocol tcp_protocol = {
        .netns_ok       =       1,
 };
 
+static const struct net_offload tcp_offload = {
+       .gso_send_check =       tcp_v4_gso_send_check,
+       .gso_segment    =       tcp_tso_segment,
+       .gro_receive    =       tcp4_gro_receive,
+       .gro_complete   =       tcp4_gro_complete,
+};
+
 static const struct net_protocol udp_protocol = {
        .handler =      udp_rcv,
        .err_handler =  udp_err,
@@ -1554,6 +1582,11 @@ static const struct net_protocol udp_protocol = {
        .netns_ok =     1,
 };
 
+static const struct net_offload udp_offload = {
+       .gso_send_check = udp4_ufo_send_check,
+       .gso_segment = udp4_ufo_fragment,
+};
+
 static const struct net_protocol icmp_protocol = {
        .handler =      icmp_rcv,
        .err_handler =  ping_err,
@@ -1641,6 +1674,10 @@ static int ipv4_proc_init(void);
 static struct packet_type ip_packet_type __read_mostly = {
        .type = cpu_to_be16(ETH_P_IP),
        .func = ip_rcv,
+};
+
+static struct packet_offload ip_packet_offload __read_mostly = {
+       .type = cpu_to_be16(ETH_P_IP),
        .gso_send_check = inet_gso_send_check,
        .gso_segment = inet_gso_segment,
        .gro_receive = inet_gro_receive,
@@ -1760,6 +1797,7 @@ static int __init inet_init(void)
 
        ipfrag_init();
 
+       dev_add_offload(&ip_packet_offload);
        dev_add_pack(&ip_packet_type);
 
        rc = 0;