ipv4: tcp: get rid of ugly unicast_sock

In commit be9f4a44e7d41 ("ipv4: tcp: remove per net tcp_sock")
I tried to address contention on a socket lock, but the solution
I chose was horrible :

commit 3a7c384ffd57e ("ipv4: tcp: unicast_sock should not land outside
of TCP stack") addressed a selinux regression.

commit 0980e56e506b ("ipv4: tcp: set unicast_sock uc_ttl to -1")
took care of another regression.

commit b5ec8eeac46 ("ipv4: fix ip_send_skb()") fixed another regression.

commit 811230cd85 ("tcp: ipv4: initialize unicast_sock sk_pacing_rate")
was another shot in the dark.

Really, just use a proper socket per cpu, and remove the skb_orphan()
call, to re-enable flow control.

This solves a serious problem with FQ packet scheduler when used in
hostile environments, as we do not want to allocate a flow structure
for every RST packet sent in response to a spoofed packet.

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

1 files changed, 32 insertions, 5 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7fc06c..d22f54482bab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -683,7 +683,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
                 arg.bound_dev_if = sk->sk_bound_dev_if;
 
         arg.tos = ip_hdr(skb)->tos;
-        ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                               ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                               &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
         if (oif)
                 arg.bound_dev_if = oif;
         arg.tos = tos;
-        ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                               ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                               &arg, arg.iov[0].iov_len);
 
@@ -2428,14 +2430,39 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+        free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+        int res, cpu;
+
+        net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+        if (!net->ipv4.tcp_sk)
+                return -ENOMEM;
+
+        for_each_possible_cpu(cpu) {
+                struct sock *sk;
+
+                res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+                                           IPPROTO_TCP, net);
+                if (res)
+                        goto fail;
+                *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+        }
         net->ipv4.sysctl_tcp_ecn = 2;
         return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+        tcp_sk_exit(net);
+
+        return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)