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>

1 files changed, 11 insertions, 3 deletions

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 7a37369f8ea3..ed2ba6eca724 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -57,7 +57,15 @@ struct ip_options {
         unsigned char   __data[0];
 };
 
-#define optlength(opt) (sizeof(struct ip_options) + opt->optlen)
+struct ip_options_rcu {
+        struct rcu_head rcu;
+        struct ip_options opt;
+};
+
+struct ip_options_data {
+        struct ip_options_rcu   opt;
+        char                    data[40];
+};
 
 struct inet_request_sock {
         struct request_sock     req;
@@ -78,7 +86,7 @@ struct inet_request_sock {
                                 acked      : 1,
                                 no_srccheck: 1;
         kmemcheck_bitfield_end(flags);
-        struct ip_options       *opt;
+        struct ip_options_rcu   *opt;
 };
 
 static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
@@ -140,7 +148,7 @@ struct inet_sock {
         __be16                  inet_sport;
         __u16                   inet_id;
 
-        struct ip_options       *opt;
+        struct ip_options_rcu __rcu     *inet_opt;
         __u8                    tos;
         __u8                    min_ttl;
         __u8                    mc_ttl;