[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120705134857.GA14643@localhost>
Date: Thu, 5 Jul 2012 21:48:57 +0800
From: wfg@...ux.intel.com
To: "David S. Miller" <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>
Subject: [net-next:master] general protection fault in __nla_put()
Hi David,
This is a very reproducible bug, introduced by the following commit
tree: git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
head: 36bdbcae2fa2a6dfa99344d4190fcea0aa7b7c25
commit: 97cac0821af4474ec4ba3a9e7a36b98ed9b6db88 [96/99] ipv6: Store route neighbour in rt6_info struct.
[ 80.878774] IPv6: ADDRCONF(NETDEV_UP): bond0: link is not ready
[ 80.880350] 8021q: adding VLAN 0 to HW filter on device bond0
[ 80.882116] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
[ 80.883606] CPU 0
[ 80.884216] Modules linked in:
[ 80.884296]
[ 80.884296] Pid: 1, comm: swapper/0 Not tainted 3.5.0-rc4+ #16 Bochs Bochs
[ 80.884296] RIP: 0010:[<ffffffff816ce77e>] [<ffffffff816ce77e>] __nla_put+0x1f/0x26
[ 80.884296] RSP: 0018:ffff88001d819910 EFLAGS: 00010282
[ 80.884296] RAX: ffff880012167c2c RBX: 5a5a5a5a5a5a5d3a RCX: 0000000000000010
[ 80.884296] RDX: ffff880012167c3c RSI: 5a5a5a5a5a5a5d3a RDI: ffff880012167c2c
[ 80.884296] RBP: ffff88001d819920 R08: ffff880012167c28 R09: ffff880012167bf0
[ 80.884296] R10: ffffffff840401a0 R11: ffffffff840401a0 R12: 0000000000000010
[ 80.884296] R13: ffff8800120c3f00 R14: 0000000000000000 R15: 0000000000000000
[ 80.884296] FS: 0000000000000000(0000) GS:ffff88001f200000(0000) knlGS:0000000000000000
[ 80.884296] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 80.884296] CR2: 0000000000000000 CR3: 0000000004014000 CR4: 00000000000006f0
[ 80.884296] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 80.884296] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 80.884296] Process swapper/0 (pid: 1, threadinfo ffff88001d818000, task ffff88001d814040)
[ 80.884296] Stack:
[ 80.884296] ffff8800120c3f00 ffff880012168e70 ffff88001d819960 ffffffff816ce7bf
[ 80.884296] ffff88001d819950 5a5a5a5a5a5a5d3a ffffffff00000010 ffff880000000005
[ 80.884296] ffff88001d819960 ffff880012167bf0 ffff88001d819a00 ffffffff82afa9b0
[ 80.884296] Call Trace:
[ 80.884296] [<ffffffff816ce7bf>] nla_put+0x3a/0x4a
[ 80.884296] [<ffffffff82afa9b0>] rt6_fill_node.constprop.35+0x325/0x486
[ 80.884296] [<ffffffff8117598d>] ? __kmalloc_node_track_caller+0x35/0x3e
[ 80.884296] [<ffffffff829d69cb>] ? __alloc_skb+0xaf/0x15a
[ 80.884296] [<ffffffff82afaf82>] inet6_rt_notify+0xb2/0x130
[ 80.884296] [<ffffffff82afc56f>] fib6_add+0x359/0x55a
[ 80.884296] [<ffffffff810dbeb0>] ? lock_acquired+0x1e4/0x219
[ 80.884296] [<ffffffff82af7ae5>] __ip6_ins_rt+0x3c/0x57
[ 80.884296] [<ffffffff82af9c10>] ip6_route_add+0x49e/0x58d
[ 80.884296] [<ffffffff82af0bcc>] addrconf_add_mroute+0x82/0x98
[ 80.884296] [<ffffffff82af24a8>] addrconf_add_dev+0x61/0x83
[ 80.884296] [<ffffffff82af429a>] addrconf_dev_config+0x78/0xd4
[ 80.884296] [<ffffffff82af5fb1>] addrconf_notify+0x164/0x283
[ 80.884296] [<ffffffff82e4fcc2>] notifier_call_chain+0x65/0x95
[ 80.884296] [<ffffffff810b54ab>] __raw_notifier_call_chain+0xe/0x10
[ 80.884296] [<ffffffff810b54c1>] raw_notifier_call_chain+0x14/0x16
[ 80.884296] [<ffffffff829df1c8>] call_netdevice_notifiers+0x4a/0x4f
[ 80.884296] [<ffffffff829e4934>] __dev_notify_flags+0x37/0x5b
[ 80.884296] [<ffffffff829e49a0>] dev_change_flags+0x48/0x54
[ 80.884296] [<ffffffff8467e322>] ip_auto_config.part.10+0x14a/0xd52
[ 80.884296] [<ffffffff82e4c452>] ? _raw_spin_unlock+0x28/0x3b
[ 80.884296] [<ffffffff811da21f>] ? proc_register+0x192/0x1a6
[ 80.884296] [<ffffffff8467c8c6>] ? tcp_v4_init+0x30/0x30
[ 80.884296] [<ffffffff8467ef2a>] ? ip_auto_config.part.10+0xd52/0xd52
[ 80.884296] [<ffffffff8467ef5d>] ip_auto_config+0x33/0x35
[ 80.884296] [<ffffffff81002099>] do_one_initcall+0x7f/0x13a
[ 80.884296] [<ffffffff845f1d0a>] kernel_init+0x141/0x1c5
[ 80.884296] [<ffffffff845f1590>] ? do_early_param+0x8c/0x8c
[ 80.884296] [<ffffffff82e545f4>] kernel_thread_helper+0x4/0x10
[ 80.884296] [<ffffffff82e4c830>] ? retint_restore_args+0x13/0x13
[ 80.884296] [<ffffffff845f1bc9>] ? start_kernel+0x3e7/0x3e7
[ 80.884296] [<ffffffff82e545f0>] ? gs_change+0x13/0x13
[ 80.884296] Code: 4c 89 c0 41 5b 5b 41 5c 41 5d 5d c3 55 48 89 e5 41 54 41 89 d4 53 48 89 cb e8 a2 ff ff ff 48 83 c0 04 49 63 cc 48 89 de 48 89 c7 <f3> a4 5b 41 5c 5d c3 55 48 89 e5 53 48 89 fb 48 83 ec 28 89 55
[ 80.884296] RIP [<ffffffff816ce77e>] __nla_put+0x1f/0x26
[ 80.884296] RSP <ffff88001d819910>
[ 80.964726] ---[ end trace 7265c51d764fcc58 ]---
[ 80.965811] Kernel panic - not syncing: Fatal exception in interrupt
commit 97cac0821af4474ec4ba3a9e7a36b98ed9b6db88
Author: David S. Miller <davem@...emloft.net>
Date: Mon Jul 2 22:43:47 2012 -0700
ipv6: Store route neighbour in rt6_info struct.
This makes for a simplified conversion away from dst_get_neighbour*().
All code outside of ipv6 will use neigh lookups via dst_neigh_lookup*().
Signed-off-by: David S. Miller <davem@...emloft.net>
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a192f78..0fedbd8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -86,6 +86,8 @@ struct fib6_table;
struct rt6_info {
struct dst_entry dst;
+ struct neighbour *n;
+
/*
* Tail elements of dst_entry (__refcnt etc.)
* and these elements (rarely used in hot path) are in
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index c94e4aa..6d9c0ab 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -88,6 +88,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
+ struct rt6_info *rt;
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
@@ -123,7 +124,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
}
rcu_read_lock();
- neigh = dst_get_neighbour_noref(dst);
+ rt = (struct rt6_info *) dst;
+ neigh = rt->n;
if (neigh) {
int res = dst_neigh_output(dst, neigh, skb);
@@ -944,6 +946,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
+ struct rt6_info *rt;
#endif
int err;
@@ -972,7 +975,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
* dst entry of the nexthop router
*/
rcu_read_lock();
- n = dst_get_neighbour_noref(*dst);
+ rt = (struct rt6_info *) dst;
+ n = rt->n;
if (n && !(n->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 34b2988..ceff71d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -155,7 +155,7 @@ static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
if (IS_ERR(n))
return PTR_ERR(n);
}
- dst_set_neighbour(&rt->dst, n);
+ rt->n = n;
return 0;
}
@@ -285,6 +285,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
+ if (rt->n)
+ neigh_release(rt->n);
+
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
@@ -335,12 +338,19 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
struct net_device *loopback_dev =
dev_net(dev)->loopback_dev;
- if (dev != loopback_dev && idev && idev->dev == dev) {
- struct inet6_dev *loopback_idev =
- in6_dev_get(loopback_dev);
- if (loopback_idev) {
- rt->rt6i_idev = loopback_idev;
- in6_dev_put(idev);
+ if (dev != loopback_dev) {
+ if (idev && idev->dev == dev) {
+ struct inet6_dev *loopback_idev =
+ in6_dev_get(loopback_dev);
+ if (loopback_idev) {
+ rt->rt6i_idev = loopback_idev;
+ in6_dev_put(idev);
+ }
+ }
+ if (rt->n && rt->n->dev == dev) {
+ rt->n->dev = loopback_dev;
+ dev_hold(loopback_dev);
+ dev_put(dev);
}
}
}
@@ -430,7 +440,7 @@ static void rt6_probe(struct rt6_info *rt)
* to no more than one per minute.
*/
rcu_read_lock();
- neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL;
+ neigh = rt ? rt->n : NULL;
if (!neigh || (neigh->nud_state & NUD_VALID))
goto out;
read_lock_bh(&neigh->lock);
@@ -477,7 +487,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
int m;
rcu_read_lock();
- neigh = dst_get_neighbour_noref(&rt->dst);
+ neigh = rt->n;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
m = 1;
@@ -824,7 +834,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
if (rt) {
rt->rt6i_flags |= RTF_CACHE;
- dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst)));
+ rt->n = neigh_clone(ort->n);
}
return rt;
}
@@ -858,7 +868,7 @@ restart:
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+ if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -1178,7 +1188,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
- dst_set_neighbour(&rt->dst, neigh);
+ rt->n = neigh;
atomic_set(&rt->dst.__refcnt, 1);
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
@@ -1715,7 +1725,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
dst_confirm(&rt->dst);
/* Duplicate redirect: silently ignore. */
- old_neigh = dst_get_neighbour_noref_raw(&rt->dst);
+ old_neigh = rt->n;
if (neigh == old_neigh)
goto out;
@@ -1728,7 +1738,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
nrt->rt6i_flags &= ~RTF_GATEWAY;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
- dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
+ nrt->n = neigh_clone(neigh);
if (ip6_ins_rt(nrt))
goto out;
@@ -2442,7 +2452,7 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
rcu_read_lock();
- n = dst_get_neighbour_noref(&rt->dst);
+ n = rt->n;
if (n) {
if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) {
rcu_read_unlock();
@@ -2666,7 +2676,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
rcu_read_lock();
- n = dst_get_neighbour_noref(&rt->dst);
+ n = rt->n;
if (n) {
seq_printf(m, "%pi6", n->primary_key);
} else {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index d749484..bb02038 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -103,6 +103,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
+ xdst->u.rt6.n = neigh_clone(rt->n);
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
Download attachment "dmesg-kvm-waimea-20382-2012-07-05-21-02-50" of type "application/octet-stream" (259760 bytes)
View attachment "config-3.5.0-rc4+" of type "text/plain" (136856 bytes)
Powered by blists - more mailing lists