udp: consistently apply ufo or fragmentation

[GitHub/mt8127/android_kernel_alcatel_ttab.git] / net / ipv4 / ip_output.c

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4bcabf3ab4cad3bdc43f5b9ed33eba9c1357557d..40faf48cb10c14303931fd146f4e3e60090ae078 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -97,6 +97,9 @@ int __ip_local_out(struct sk_buff *skb)
 
        iph->tot_len = htons(skb->len);
        ip_send_check(iph);
+
+       skb->protocol = htons(ETH_P_IP);
+
        return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
                       skb_dst(skb)->dev, dst_output);
 }
@@ -148,7 +151,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
        iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
        iph->saddr    = saddr;
        iph->protocol = sk->sk_protocol;
-       ip_select_ident(iph, &rt->dst, sk);
+       ip_select_ident(skb, sk);
 
        if (opt && opt->opt.optlen) {
                iph->ihl += opt->opt.optlen>>2;
@@ -394,8 +397,7 @@ packet_routed:
                ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
        }
 
-       ip_select_ident_more(iph, &rt->dst, sk,
-                            (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+       ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
        skb->priority = sk->sk_priority;
        skb->mark = sk->sk_mark;
@@ -844,9 +846,12 @@ static int __ip_append_data(struct sock *sk,
                csummode = CHECKSUM_PARTIAL;
 
        cork->length += length;
-       if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+       if ((skb && skb_has_frags(skb)) ||
+           ((length > mtu) &&
+           (skb_queue_len(queue) <= 1) &&
            (sk->sk_protocol == IPPROTO_UDP) &&
-           (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
+           (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+           (sk->sk_type == SOCK_DGRAM))) {
                err = ip_ufo_append_data(sk, queue, getfrag, from, length,
                                         hh_len, fragheaderlen, transhdrlen,
                                         maxfraglen, flags);
@@ -1157,6 +1162,7 @@ ssize_t   ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
        cork->length += size;
        if ((size + skb->len > mtu) &&
+           (skb_queue_len(&sk->sk_write_queue) == 1) &&
            (sk->sk_protocol == IPPROTO_UDP) &&
            (rt->dst.dev->features & NETIF_F_UFO)) {
                skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
@@ -1324,7 +1330,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
        else
                ttl = ip_select_ttl(inet, &rt->dst);
 
-       iph = (struct iphdr *)skb->data;
+       iph = ip_hdr(skb);
        iph->version = 4;
        iph->ihl = 5;
        iph->tos = inet->tos;
@@ -1332,7 +1338,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
        iph->ttl = ttl;
        iph->protocol = sk->sk_protocol;
        ip_copy_addrs(iph, fl4);
-       ip_select_ident(iph, &rt->dst, sk);
+       ip_select_ident(skb, sk);
 
        if (opt) {
                iph->ihl += opt->optlen>>2;
@@ -1455,23 +1461,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *     Generic function to send a packet as reply to another packet.
  *     Used to send some TCP resets/acks so far.
- *
- *     Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-       .sk = {
-               .__sk_common = {
-                       .skc_refcnt = ATOMIC_INIT(1),
-               },
-               .sk_wmem_alloc  = ATOMIC_INIT(1),
-               .sk_allocation  = GFP_ATOMIC,
-               .sk_flags       = (1UL << SOCK_USE_WRITE_QUEUE),
-       },
-       .pmtudisc       = IP_PMTUDISC_WANT,
-       .uc_ttl         = -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
                           __be32 saddr, const struct ip_reply_arg *arg,
                           unsigned int len)
 {
@@ -1479,9 +1470,9 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
        struct ipcm_cookie ipc;
        struct flowi4 fl4;
        struct rtable *rt = skb_rtable(skb);
+       struct net *net = sock_net(sk);
        struct sk_buff *nskb;
-       struct sock *sk;
-       struct inet_sock *inet;
+       int err;
 
        if (ip_options_echo(&replyopts.opt.opt, skb))
                return;
@@ -1508,18 +1499,19 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
        if (IS_ERR(rt))
                return;
 
-       inet = &get_cpu_var(unicast_sock);
+       inet_sk(sk)->tos = arg->tos;
 
-       inet->tos = arg->tos;
-       sk = &inet->sk;
        sk->sk_priority = skb->priority;
        sk->sk_protocol = ip_hdr(skb)->protocol;
        sk->sk_bound_dev_if = arg->bound_dev_if;
-       sock_net_set(sk, net);
-       __skb_queue_head_init(&sk->sk_write_queue);
        sk->sk_sndbuf = sysctl_wmem_default;
-       ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
-                      &ipc, &rt, MSG_DONTWAIT);
+       err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
+                            len, 0, &ipc, &rt, MSG_DONTWAIT);
+       if (unlikely(err)) {
+               ip_flush_pending_frames(sk);
+               goto out;
+       }
+
        nskb = skb_peek(&sk->sk_write_queue);
        if (nskb) {
                if (arg->csumoffset >= 0)
@@ -1527,13 +1519,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
                          arg->csumoffset) = csum_fold(csum_add(nskb->csum,
                                                                arg->csum));
                nskb->ip_summed = CHECKSUM_NONE;
-               skb_orphan(nskb);
                skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
                ip_push_pending_frames(sk, &fl4);
        }
-
-       put_cpu_var(unicast_sock);
-
+out:
        ip_rt_put(rt);
 }