ipv6: lockless IPV6_MTU implementation

np->frag_size can be read/written without holding socket lock.

Add missing annotations and make IPV6_MTU setsockopt() lockless.

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

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1e16d56d8c38ac51bd999038ae4e8478bf2f5f8c..ab7ede4a731a96fe6dce3205df29b298c923acc7 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -881,9 +881,11 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
                        mtu = IPV6_MIN_MTU;
        }
 
-       if (np && np->frag_size < mtu) {
-               if (np->frag_size)
-                       mtu = np->frag_size;
+       if (np) {
+               u32 frag_size = READ_ONCE(np->frag_size);
+
+               if (frag_size && frag_size < mtu)
+                       mtu = frag_size;
        }
        if (mtu < hlen + sizeof(struct frag_hdr) + 8)
                goto fail_toobig;
@@ -1392,7 +1394,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
                          struct rt6_info *rt)
 {
        struct ipv6_pinfo *np = inet6_sk(sk);
-       unsigned int mtu;
+       unsigned int mtu, frag_size;
        struct ipv6_txoptions *nopt, *opt = ipc6->opt;
 
        /* callers pass dst together with a reference, set it first so
@@ -1441,10 +1443,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
        else
                mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
                        READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
-       if (np->frag_size < mtu) {
-               if (np->frag_size)
-                       mtu = np->frag_size;
-       }
+
+       frag_size = READ_ONCE(np->frag_size);
+       if (frag_size && frag_size < mtu)
+               mtu = frag_size;
+
        cork->base.fragsize = mtu;
        cork->base.gso_size = ipc6->gso_size;
        cork->base.tx_flags = 0;

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5fff19a87c75518358bae067dfeb227d6738bb03..3b2a34828daab5c666d7b429afa961279739c70b 100644 (file)
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -441,6 +441,13 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                WRITE_ONCE(np->mcast_hops,
                           val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
                return 0;
+       case IPV6_MTU:
+               if (optlen < sizeof(int))
+                       return -EINVAL;
+               if (val && val < IPV6_MIN_MTU)
+                       return -EINVAL;
+               WRITE_ONCE(np->frag_size, val);
+               return 0;
        }
        if (needs_rtnl)
                rtnl_lock();
@@ -910,14 +917,6 @@ done:
                np->pmtudisc = val;
                retv = 0;
                break;
-       case IPV6_MTU:
-               if (optlen < sizeof(int))
-                       goto e_inval;
-               if (val && val < IPV6_MIN_MTU)
-                       goto e_inval;
-               np->frag_size = val;
-               retv = 0;
-               break;
        case IPV6_RECVERR:
                if (optlen < sizeof(int))
                        goto e_inval;