On Sun, Sep 20, 2015 at 11:11:04PM -0700, David Miller wrote:
>
> Yeah at this point incremental patches work the best.
OK here is the patch:
---8<---
The commit 1f770c0a09da855a2b51af6d19de97fb955eca85 ("netlink:
Fix autobind race condition that leads to zero port ID") created
some new races that can occur due to inconcsistencies between the
two port IDs.
Tejun is right that a barrier is unavoidable. Therefore I am
reverting to the original patch that used a boolean to indicate
that a user netlink socket has been bound.
Barriers have been added where necessary to ensure that a valid
portid is used.
Fixes: 1f770c0a09da ("netlink: Fix autobind race condition that leads to zero
port ID")
Reported-by: Tejun Heo <t...@kernel.org>
Reported-by: Linus Torvalds <torva...@linux-foundation.org>
Signed-off-by: Herbert Xu <herb...@gondor.apana.org.au>
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 303efb7..f5362aae 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -24,6 +24,7 @@
#include <linux/module.h>
+#include <asm/barrier.h>
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -1015,7 +1016,7 @@ static inline int netlink_compare(struct
rhashtable_compare_arg *arg,
const struct netlink_compare_arg *x = arg->key;
const struct netlink_sock *nlk = ptr;
- return nlk->rhash_portid != x->portid ||
+ return nlk->portid != x->portid ||
!net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
}
@@ -1041,7 +1042,7 @@ static int __netlink_insert(struct netlink_table *table,
struct sock *sk)
{
struct netlink_compare_arg arg;
- netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->rhash_portid);
+ netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
return rhashtable_lookup_insert_key(&table->hash, &arg,
&nlk_sk(sk)->node,
netlink_rhashtable_params);
@@ -1095,7 +1096,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
lock_sock(sk);
err = -EBUSY;
- if (nlk_sk(sk)->portid)
+ if (nlk_sk(sk)->bound)
goto err;
err = -ENOMEM;
@@ -1103,7 +1104,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
goto err;
- nlk_sk(sk)->rhash_portid = portid;
+ nlk_sk(sk)->portid = portid;
sock_hold(sk);
err = __netlink_insert(table, sk);
@@ -1119,7 +1120,11 @@ static int netlink_insert(struct sock *sk, u32 portid)
goto err;
}
- nlk_sk(sk)->portid = portid;
+ /* rhashtable_insert carries an implicit write memory barrier
+ * so we don't need an smp_wmb here in order to ensure that
+ * portid is set before bound.
+ */
+ nlk_sk(sk)->bound = portid;
err:
release_sock(sk);
@@ -1521,9 +1526,11 @@ static int netlink_bind(struct socket *sock, struct
sockaddr *addr,
return err;
}
- if (nlk->portid)
+ /* Ensure nlk->portid is up-to-date. */
+ if (smp_load_acquire(&nlk->bound)) {
if (nladdr->nl_pid != nlk->portid)
return -EINVAL;
+ }
if (nlk->netlink_bind && groups) {
int group;
@@ -1539,7 +1546,7 @@ static int netlink_bind(struct socket *sock, struct
sockaddr *addr,
}
}
- if (!nlk->portid) {
+ if (!nlk->bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
@@ -1587,7 +1594,7 @@ static int netlink_connect(struct socket *sock, struct
sockaddr *addr,
!netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
- if (!nlk->portid)
+ if (!nlk->bound)
err = netlink_autobind(sock);
if (err == 0) {
@@ -2428,7 +2435,8 @@ static int netlink_sendmsg(struct socket *sock, struct
msghdr *msg, size_t len)
dst_group = nlk->dst_group;
}
- if (!nlk->portid) {
+ /* Ensure nlk->portid is up-to-date. */
+ if (!smp_load_acquire(&nlk->bound)) {
err = netlink_autobind(sock);
if (err)
goto out;
@@ -3257,7 +3265,7 @@ static inline u32 netlink_hash(const void *data, u32 len,
u32 seed)
const struct netlink_sock *nlk = data;
struct netlink_compare_arg arg;
- netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->rhash_portid);
+ netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
}
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index c96dfa3..e6aae40 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -25,7 +25,6 @@ struct netlink_ring {
struct netlink_sock {
/* struct sock has to be the first member of netlink_sock */
struct sock sk;
- u32 rhash_portid;
u32 portid;
u32 dst_portid;
u32 dst_group;
@@ -36,6 +35,7 @@ struct netlink_sock {
unsigned long state;
size_t max_recvmsg_len;
wait_queue_head_t wait;
+ bool bound;
bool cb_running;
struct netlink_callback cb;
struct mutex *cb_mutex;
--
Email: Herbert Xu <herb...@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
