inet: add RCU protection to inet->opt

We lack proper synchronization to manipulate inet->opt ip_options

Problem is ip_make_skb() calls ip_setup_cork() and
ip_setup_cork() possibly makes a copy of ipc->opt (struct ip_options),
without any protection against another thread manipulating inet->opt.

Another thread can change inet->opt pointer and free old one under us.

Use RCU to protect inet->opt (changed to inet->inet_opt).

Instead of handling atomic refcounts, just copy ip_options when
necessary, to avoid cache line dirtying.

We cant insert an rcu_head in struct ip_options since its included in
skb->cb[], so this patch is large because I had to introduce a new
ip_options_rcu structure.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 11 insertions, 7 deletions

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b92ab655d44..cbbcc6c036e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -48,6 +48,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
         struct flowi4 fl4;
         struct rtable *rt;
         int err;
+        struct ip_options_rcu *inet_opt;
 
         dp->dccps_role = DCCP_ROLE_CLIENT;
 
@@ -58,10 +59,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
                 return -EAFNOSUPPORT;
 
         nexthop = daddr = usin->sin_addr.s_addr;
-        if (inet->opt != NULL && inet->opt->srr) {
+
+        inet_opt = rcu_dereference_protected(inet->inet_opt,
+                                             sock_owned_by_user(sk));
+        if (inet_opt != NULL && inet_opt->opt.srr) {
                 if (daddr == 0)
                         return -EINVAL;
-                nexthop = inet->opt->faddr;
+                nexthop = inet_opt->opt.faddr;
         }
 
         orig_sport = inet->inet_sport;
@@ -78,7 +82,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
                 return -ENETUNREACH;
         }
 
-        if (inet->opt == NULL || !inet->opt->srr)
+        if (inet_opt == NULL || !inet_opt->opt.srr)
                 daddr = rt->rt_dst;
 
         if (inet->inet_saddr == 0)
@@ -89,8 +93,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
         inet->inet_daddr = daddr;
 
         inet_csk(sk)->icsk_ext_hdr_len = 0;
-        if (inet->opt != NULL)
-                inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
+        if (inet_opt)
+                inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
         /*
          * Socket identity is still unknown (sport may be zero).
          * However we set state to DCCP_REQUESTING and not releasing socket
@@ -405,7 +409,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
         newinet->inet_daddr     = ireq->rmt_addr;
         newinet->inet_rcv_saddr = ireq->loc_addr;
         newinet->inet_saddr     = ireq->loc_addr;
-        newinet->opt       = ireq->opt;
+        newinet->inet_opt       = ireq->opt;
         ireq->opt          = NULL;
         newinet->mc_index  = inet_iif(skb);
         newinet->mc_ttl    = ip_hdr(skb)->ttl;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 73add237324..8dc4348774a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -573,7 +573,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
            First: no IPv4 options.
          */
-        newinet->opt = NULL;
+        newinet->inet_opt = NULL;
 
         /* Clone RX bits */
         newnp->rxopt.all = np->rxopt.all;