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, 12 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 74e35e5736e2..cfeca3c2152d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -108,8 +108,7 @@ struct icmp_bxm {
                 __be32         times[3];
         } data;
         int head_len;
-        struct ip_options replyopts;
-        unsigned char  optbuf[40];
+        struct ip_options_data replyopts;
 };
 
 /* An array of errno for error messages from dest unreach. */
@@ -333,7 +332,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
         struct inet_sock *inet;
         __be32 daddr;
 
-        if (ip_options_echo(&icmp_param->replyopts, skb))
+        if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
                 return;
 
         sk = icmp_xmit_lock(net);
@@ -347,10 +346,10 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
         daddr = ipc.addr = rt->rt_src;
         ipc.opt = NULL;
         ipc.tx_flags = 0;
-        if (icmp_param->replyopts.optlen) {
-                ipc.opt = &icmp_param->replyopts;
-                if (ipc.opt->srr)
-                        daddr = icmp_param->replyopts.faddr;
+        if (icmp_param->replyopts.opt.opt.optlen) {
+                ipc.opt = &icmp_param->replyopts.opt;
+                if (ipc.opt->opt.srr)
+                        daddr = icmp_param->replyopts.opt.opt.faddr;
         }
         {
                 struct flowi4 fl4 = {
@@ -379,8 +378,8 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
                                         struct icmp_bxm *param)
 {
         struct flowi4 fl4 = {
-                .daddr = (param->replyopts.srr ?
-                          param->replyopts.faddr : iph->saddr),
+                .daddr = (param->replyopts.opt.opt.srr ?
+                          param->replyopts.opt.opt.faddr : iph->saddr),
                 .saddr = saddr,
                 .flowi4_tos = RT_TOS(tos),
                 .flowi4_proto = IPPROTO_ICMP,
@@ -581,7 +580,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
                                            IPTOS_PREC_INTERNETCONTROL) :
                                           iph->tos;
 
-        if (ip_options_echo(&icmp_param.replyopts, skb_in))
+        if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
                 goto out_unlock;
 
 
@@ -597,7 +596,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
         icmp_param.offset = skb_network_offset(skb_in);
         inet_sk(sk)->tos = tos;
         ipc.addr = iph->saddr;
-        ipc.opt = &icmp_param.replyopts;
+        ipc.opt = &icmp_param.replyopts.opt;
         ipc.tx_flags = 0;
 
         rt = icmp_route_lookup(net, skb_in, iph, saddr, tos,
@@ -613,7 +612,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
         room = dst_mtu(&rt->dst);
         if (room > 576)
                 room = 576;
-        room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen;
+        room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
         room -= sizeof(struct icmphdr);
 
         icmp_param.data_len = skb_in->len - icmp_param.offset;