2014-08-29, 11:14:48 -0700, Cong Wang wrote:
> On Fri, Aug 29, 2014 at 8:26 AM, Tommi Rantala <tt.rantala@xxxxxxxxx> wrote:
> > [ 77.297196] RTNL: assertion failed at net/ipv6/addrconf.c (1699)
> > [ 77.298080] CPU: 0 PID: 4842 Comm: trinity-main Not tainted 3.17.0-rc2+ #30
> > [ 77.299039] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> > [ 77.299789] ffff88003d76a618 ffff880026133c50 ffffffff8238ba79
> > ffff880037c84520
> > [ 77.300829] ffff880026133c90 ffffffff820bd52b 0000000000000000
> > ffffffff82d86c40
> > [ 77.301869] 0000000000000000 00000000f76fd1e1 ffff8800382d8000
> > ffff8800382d8220
> > [ 77.302906] Call Trace:
> > [ 77.303246] [<ffffffff8238ba79>] dump_stack+0x4d/0x66
> > [ 77.303928] [<ffffffff820bd52b>] addrconf_join_solict+0x4b/0xb0
> > [ 77.304731] [<ffffffff820b031b>] ipv6_dev_ac_inc+0x2bb/0x330
> > [ 77.305498] [<ffffffff820b0060>] ? ac6_seq_start+0x260/0x260
> > [ 77.306257] [<ffffffff820b05fe>] ipv6_sock_ac_join+0x26e/0x360
> > [ 77.307046] [<ffffffff820b0429>] ? ipv6_sock_ac_join+0x99/0x360
> > [ 77.307798] [<ffffffff820cdd60>] do_ipv6_setsockopt.isra.5+0xa70/0xf20
>
>
> I think we should just use rtnl_lock() instead of rcu_read_lock() there,
> it is not a hot path worth optimization.
>
> Please try the attached patch.
note: it doesn't build as it is now, it needs:
-EXPORT_SYMBOL(dev_get_by_flags_rcu);
+EXPORT_SYMBOL(dev_get_by_flags);
I just tried your patch with a basic test program (open
socket/join/leave/close and open socket/join/close).
I think you need to modify ipv6_sock_ac_close as well, or you can still
trigger the assertion when closing the socket without leaving first.
Modified patch attached.
--
Sabrina
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 429801370d0c..1ae0e745b1b1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2077,8 +2077,8 @@ void __dev_remove_pack(struct packet_type *pt);
void dev_add_offload(struct packet_offload *po);
void dev_remove_offload(struct packet_offload *po);
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
- unsigned short mask);
+struct net_device *dev_get_by_flags(struct net *net, unsigned short flags,
+ unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
struct net_device *__dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 443b814db05b..8fede6ef4a39 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -897,23 +897,24 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
- * dev_get_by_flags_rcu - find any device with given flags
+ * dev_get_by_flags - find any device with given flags
* @net: the applicable net namespace
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* Search for any interface with the given flags. Returns NULL if a device
* is not found or a pointer to the device. Must be called inside
- * rcu_read_lock(), and result refcount is unchanged.
+ * rtnl_lock(), and result refcount is unchanged.
*/
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
+struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
unsigned short mask)
{
struct net_device *dev, *ret;
+ ASSERT_RTNL();
ret = NULL;
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
ret = dev;
break;
@@ -921,7 +922,7 @@ struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags
}
return ret;
}
-EXPORT_SYMBOL(dev_get_by_flags_rcu);
+EXPORT_SYMBOL(dev_get_by_flags);
/**
* dev_valid_name - check if name is okay for network device
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 210183244689..6de5caa26ea4 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -77,7 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
pac->acl_next = NULL;
pac->acl_addr = *addr;
- rcu_read_lock();
+ rtnl_lock();
if (ifindex == 0) {
struct rt6_info *rt;
@@ -90,11 +90,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
goto error;
} else {
/* router, no matching interface: just pick one */
- dev = dev_get_by_flags_rcu(net, IFF_UP,
+ dev = dev_get_by_flags(net, IFF_UP,
IFF_UP | IFF_LOOPBACK);
}
} else
- dev = dev_get_by_index_rcu(net, ifindex);
+ dev = __dev_get_by_index(net, ifindex);
if (dev == NULL) {
err = -ENODEV;
@@ -136,7 +136,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
}
error:
- rcu_read_unlock();
+ rtnl_unlock();
if (pac)
sock_kfree_s(sk, pac, sizeof(*pac));
return err;
@@ -171,13 +171,15 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
spin_unlock_bh(&ipv6_sk_ac_lock);
- rcu_read_lock();
- dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+ rtnl_lock();
+ dev = __dev_get_by_index(net, pac->acl_ifindex);
if (dev)
ipv6_dev_ac_dec(dev, &pac->acl_addr);
- rcu_read_unlock();
+ rtnl_unlock();
sock_kfree_s(sk, pac, sizeof(*pac));
+ if (!dev)
+ return -ENODEV;
return 0;
}
@@ -198,12 +200,12 @@ void ipv6_sock_ac_close(struct sock *sk)
spin_unlock_bh(&ipv6_sk_ac_lock);
prev_index = 0;
- rcu_read_lock();
+ rtnl_lock();
while (pac) {
struct ipv6_ac_socklist *next = pac->acl_next;
if (pac->acl_ifindex != prev_index) {
- dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+ dev = __dev_get_by_index(net, pac->acl_ifindex);
prev_index = pac->acl_ifindex;
}
if (dev)
@@ -211,7 +213,7 @@ void ipv6_sock_ac_close(struct sock *sk)
sock_kfree_s(sk, pac, sizeof(*pac));
pac = next;
}
- rcu_read_unlock();
+ rtnl_unlock();
}
static void aca_put(struct ifacaddr6 *ac)
