ipv6: Fix data races around sk->sk_prot.

Commit 086d49058cd8 ("ipv6: annotate some data-races around sk->sk_prot")
fixed some data-races around sk->sk_prot but it was not enough.

Some functions in inet6_(stream|dgram)_ops still access sk->sk_prot
without lock_sock() or rtnl_lock(), so they need READ_ONCE() to avoid
load tearing.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/core/sock.c b/net/core/sock.c
index eeb6cba..a3ba035 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3610,7 +3610,8 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname,
 {
        struct sock *sk = sock->sk;
 
 {
        struct sock *sk = sock->sk;
 

-       return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
+       /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+       return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen);

 }
 EXPORT_SYMBOL(sock_common_getsockopt);
 
 }
 EXPORT_SYMBOL(sock_common_getsockopt);
 


@@ -3636,7 +3637,8 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname,
 {
        struct sock *sk = sock->sk;
 
 {
        struct sock *sk = sock->sk;
 

-       return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
+       /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+       return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen);

 }
 EXPORT_SYMBOL(sock_common_setsockopt);
 
 }
 EXPORT_SYMBOL(sock_common_setsockopt);
 

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e2c2193..3dd0239 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -558,22 +558,27 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
                       int addr_len, int flags)
 {
        struct sock *sk = sock->sk;
                       int addr_len, int flags)
 {
        struct sock *sk = sock->sk;

+       const struct proto *prot;

        int err;
 
        if (addr_len < sizeof(uaddr->sa_family))
                return -EINVAL;
        int err;
 
        if (addr_len < sizeof(uaddr->sa_family))
                return -EINVAL;

+
+       /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+       prot = READ_ONCE(sk->sk_prot);
+

        if (uaddr->sa_family == AF_UNSPEC)
        if (uaddr->sa_family == AF_UNSPEC)

-               return sk->sk_prot->disconnect(sk, flags);
+               return prot->disconnect(sk, flags);

 
        if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
 
        if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {

-               err = sk->sk_prot->pre_connect(sk, uaddr, addr_len);
+               err = prot->pre_connect(sk, uaddr, addr_len);

                if (err)
                        return err;
        }
 
        if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk))
                return -EAGAIN;
                if (err)
                        return err;
        }
 
        if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk))
                return -EAGAIN;

-       return sk->sk_prot->connect(sk, uaddr, addr_len);
+       return prot->connect(sk, uaddr, addr_len);

 }
 EXPORT_SYMBOL(inet_dgram_connect);
 
 }
 EXPORT_SYMBOL(inet_dgram_connect);
 


@@ -734,10 +739,11 @@ EXPORT_SYMBOL(inet_stream_connect);
 int inet_accept(struct socket *sock, struct socket *newsock, int flags,
                bool kern)
 {
 int inet_accept(struct socket *sock, struct socket *newsock, int flags,
                bool kern)
 {

-       struct sock *sk1 = sock->sk;
+       struct sock *sk1 = sock->sk, *sk2;

        int err = -EINVAL;
        int err = -EINVAL;

-       struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);

 
 

+       /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+       sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern);

        if (!sk2)
                goto do_err;
 
        if (!sk2)
                goto do_err;
 


@@ -825,12 +831,15 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
                      size_t size, int flags)
 {
        struct sock *sk = sock->sk;
                      size_t size, int flags)
 {
        struct sock *sk = sock->sk;

+       const struct proto *prot;

 
        if (unlikely(inet_send_prepare(sk)))
                return -EAGAIN;
 
 
        if (unlikely(inet_send_prepare(sk)))
                return -EAGAIN;
 

-       if (sk->sk_prot->sendpage)
-               return sk->sk_prot->sendpage(sk, page, offset, size, flags);
+       /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+       prot = READ_ONCE(sk->sk_prot);
+       if (prot->sendpage)
+               return prot->sendpage(sk, page, offset, size, flags);

        return sock_no_sendpage(sock, page, offset, size, flags);
 }
 EXPORT_SYMBOL(inet_sendpage);
        return sock_no_sendpage(sock, page, offset, size, flags);
 }
 EXPORT_SYMBOL(inet_sendpage);

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a20edae..d7207a5 100644 (file)
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -477,7 +477,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                                sock_prot_inuse_add(net, sk->sk_prot, -1);
                                sock_prot_inuse_add(net, &tcp_prot, 1);
 
                                sock_prot_inuse_add(net, sk->sk_prot, -1);
                                sock_prot_inuse_add(net, &tcp_prot, 1);
 

-                               /* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+                               /* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */

                                WRITE_ONCE(sk->sk_prot, &tcp_prot);
                                icsk->icsk_af_ops = &ipv4_specific;
                                sk->sk_socket->ops = &inet_stream_ops;
                                WRITE_ONCE(sk->sk_prot, &tcp_prot);
                                icsk->icsk_af_ops = &ipv4_specific;
                                sk->sk_socket->ops = &inet_stream_ops;


@@ -492,7 +492,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                                sock_prot_inuse_add(net, sk->sk_prot, -1);
                                sock_prot_inuse_add(net, prot, 1);
 
                                sock_prot_inuse_add(net, sk->sk_prot, -1);
                                sock_prot_inuse_add(net, prot, 1);
 

-                               /* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+                               /* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */

                                WRITE_ONCE(sk->sk_prot, prot);
                                sk->sk_socket->ops = &inet_dgram_ops;
                                sk->sk_family = PF_INET;
                                WRITE_ONCE(sk->sk_prot, prot);
                                sk->sk_socket->ops = &inet_dgram_ops;
                                sk->sk_family = PF_INET;