Ding Tianhong
2013-Sep-03 07:15 UTC
[Bridge] [PATCH net] bridge: netfiler: update find_inlist_lock_noload() more accurate
Baoquan He <baoquan.he at gmail.com> has report a problem which occurred
by the following command:
make SUBDIRS=net/bridge/netfilter/
cp /net/bridge/netfilter/ebtables.ko
/lib/modules/3.11.0-rc7+/kernel/net/bridge/netfilter/ebtables.ko
depmod
modprobe ebtables.ko
reboot
----------------------------------------------------------------------
[ 48.895000] BUG: soft lockup - CPU#1 stuck for 22s! [ebtables:444]
[ 48.901191] Modules linked in: bnep(F) bluetooth(F) ebtables(F)
ip6table_filter(F) ip6_tables(F) rfkill(F) snd_hda_intel(F+)
snd_hda_codec(F) snd_hwdep(F) snd_seq(F) sn)
[ 48.950034] CPU: 1 PID: 444 Comm: ebtables Tainted: GF D
3.11.0-rc7+ #1
[ 48.957433] Hardware name: Hewlett-Packard HP Z420 Workstation/1589,
BIOS J61 v01.02 03/09/2012
[ 48.966131] task: ffff88040c2dc650 ti: ffff8804187d2000 task.ti:
ffff8804187d2000
[ 48.973610] RIP: 0010:[<ffffffff812e57a7>] [<ffffffff812e57a7>]
strcmp+0x27/0x40
[ 48.981119] RSP: 0018:ffff8804187d3db8 EFLAGS: 00000246
[ 48.986430] RAX: 0000000000000000 RBX: 00007fffda942730 RCX:
ffff8804187d3fd8
[ 48.993566] RDX: 0000000000000000 RSI: ffff8804187d3e01 RDI:
ffffffff81cb8a39
[ 49.000707] RBP: ffff8804187d3db8 R08: 00000000fffffff2 R09:
0000000000000000
[ 49.007841] R10: 0000000000000163 R11: 0000000000000000 R12:
ffffffff8128300c
[ 49.014972] R13: ffff8804187d3d98 R14: ffff8804187d3ef4 R15:
0000000000000004
[ 49.022112] FS: 00007faab6589740(0000) GS:ffff88042fc80000(0000)
knlGS:0000000000000000
[ 49.030194] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 49.035942] CR2: 0000003f0d810414 CR3: 000000040d2cc000 CR4:
00000000000407e0
[ 49.043077] Stack:
[ 49.045096] ffff8804187d3de8 ffffffffa0249674 0000000000000080
ffffffff81cb8180
[ 49.052559] 00007fffda942730 ffff8804187d3ef4 ffff8804187d3ea0
ffffffffa02497a9
[ 49.060020] 0000000000000000 00007265746c6966 0000003f0d7b92c0
00007fffda942850
[ 49.067487] Call Trace:
[ 49.069949] [<ffffffffa0249674>]
find_inlist_lock.constprop.16+0x54/0x100 [ebtables]
[ 49.077779] [<ffffffffa02497a9>] do_ebt_get_ctl+0x89/0x1d0 [ebtables]
[ 49.084306] [<ffffffff81551ca8>] nf_getsockopt+0x68/0x90
[ 49.089717] [<ffffffff81560d40>] ip_getsockopt+0x80/0xa0
[ 49.095113] [<ffffffff815835c5>] raw_getsockopt+0x25/0x50
[ 49.100588] [<ffffffff8150ddd4>] sock_common_getsockopt+0x14/0x20
[ 49.106766] [<ffffffff8150d208>] SyS_getsockopt+0x68/0xd0
[ 49.112257] [<ffffffff8162c682>] system_call_fastpath+0x16/0x1b
[ 49.118260] Code: 00 00 00 00 55 48 89 e5 eb 0e 66 2e 0f 1f 84 00 00
00 00 00 84 c0 74 1c 48 83 c7 01 0f b6 47 ff 48 83 c6 01 3a 46 ff 74 eb
19 c0 <83> c8 01 5d c3 0f 1
[ 76.925880] BUG: soft lockup - CPU#1 stuck for 22s! [ebtables:444]
[ 76.932069] Modules linked in: bnep(F) bluetooth(F) ebtables(F)
ip6table_filter(F) ip6_tables(F) rfkill(F) snd_hda_intel(F+)
snd_hda_codec(F) snd_hwdep(F) snd_seq(F) sn)
[ 76.980847] CPU: 1 PID: 444 Comm: ebtables Tainted: GF D
3.11.0-rc7+ #1
[ 76.988245] Hardware name: Hewlett-Packard HP Z420 Workstation/1589,
BIOS J61 v01.02 03/09/2012
[ 76.996940] task: ffff88040c2dc650 ti: ffff8804187d2000 task.ti:
ffff8804187d2000
[ 77.004426] RIP: 0010:[<ffffffff812e5784>] [<ffffffff812e5784>]
strcmp+0x4/0x40
[ 77.011849] RSP: 0018:ffff8804187d3db8 EFLAGS: 00000212
[ 77.017163] RAX: 0000000000000001 RBX: 00007fffda942730 RCX:
ffff8804187d3fd8
[ 77.024304] RDX: 0000000000000000 RSI: ffff8804187d3e00 RDI:
ffffffff81cb8a38
[ 77.031434] RBP: ffff8804187d3db8 R08: 00000000fffffff2 R09:
0000000000000000
[ 77.038566] R10: 0000000000000163 R11: 0000000000000000 R12:
ffffffff8128300c
[ 77.045699] R13: ffff8804187d3d98 R14: ffff8804187d3ef4 R15:
0000000000000004
[ 77.052842] FS: 00007faab6589740(0000) GS:ffff88042fc80000(0000)
knlGS:0000000000000000
[ 77.060934] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 77.066668] CR2: 0000003f0d810414 CR3: 000000040d2cc000 CR4:
00000000000407e0
[ 77.073799] Stack:
[ 77.075818] ffff8804187d3de8 ffffffffa0249674 0000000000000080
ffffffff81cb8180
[ 77.083287] 00007fffda942730 ffff8804187d3ef4 ffff8804187d3ea0
ffffffffa02497a9
[ 77.090749] 0000000000000000 00007265746c6966 0000003f0d7b92c0
00007fffda942850
[ 77.098215] Call Trace:
[ 77.100668] [<ffffffffa0249674>]
find_inlist_lock.constprop.16+0x54/0x100 [ebtables]
[ 77.108500] [<ffffffffa02497a9>] do_ebt_get_ctl+0x89/0x1d0 [ebtables]
[ 77.115035] [<ffffffff81551ca8>] nf_getsockopt+0x68/0x90
[ 77.120438] [<ffffffff81560d40>] ip_getsockopt+0x80/0xa0
[ 77.125845] [<ffffffff815835c5>] raw_getsockopt+0x25/0x50
[ 77.131328] [<ffffffff8150ddd4>] sock_common_getsockopt+0x14/0x20
[ 77.137515] [<ffffffff8150d208>] SyS_getsockopt+0x68/0xd0
[ 77.143011] [<ffffffff8162c682>] system_call_fastpath+0x16/0x1b
[ 77.149019] Code: 0f 1f 80 00 00 00 00 48 83 c6 01 0f b6 4e ff 48 83
c2 01 84 c9 88 4a ff 75 ed 5d c3 66 66 2e 0f 1f 84 00 00 00 00 00 55 48
89 e5 <eb> 0e 66 2e 0f 1f 8
---------------------------------------------------------------------------
The find_inlist_lock did not distinguish the error whether lock failed or
module non-existent, the imperfection processing procedure may course the
problem.
Return the correct value if mutex_lock_interruptible() failed, avoid
confusion with that the modules is not exist, and deal with the return
value in right way.
After the patch, the problem didn't happened again, so I confident the bug
was fixed.
Reported-by: Baoquan He <baoquan.he at gmail.com>
Signed-off-by: Ding Tianhong <dingtianhong at huawei.com>
Cc: Baoquan He <baoquan.he at gmail.com>
---
net/bridge/netfilter/ebtables.c | 17 +++++++----------
1 file changed, 7 insertions(+), 10 deletions(-)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index ac78024..e7fe9f8 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -322,17 +322,14 @@ static inline void *
find_inlist_lock_noload(struct list_head *head, const char *name, int *error,
struct mutex *mutex)
{
- struct {
- struct list_head list;
- char name[EBT_FUNCTION_MAXNAMELEN];
- } *e;
+ struct ebt_table *e;
*error = mutex_lock_interruptible(mutex);
if (*error != 0)
- return NULL;
+ return ERR_PTR(-EINTR);
list_for_each_entry(e, head, list) {
- if (strcmp(e->name, name) == 0)
+ if (strcmp(e->name, name) == 0 && try_module_get(e->me))
return e;
}
*error = -ENOENT;
@@ -1005,7 +1002,7 @@ static int do_replace_finish(struct net *net, struct
ebt_replace *repl,
goto free_counterstmp;
t = find_table_lock(net, repl->name, &ret, &ebt_mutex);
- if (!t) {
+ if (IS_ERR_OR_NULL(t)) {
ret = -ENOENT;
goto free_iterate;
}
@@ -1284,7 +1281,7 @@ static int do_update_counters(struct net *net, const char
*name,
return -ENOMEM;
t = find_table_lock(net, name, &ret, &ebt_mutex);
- if (!t)
+ if (IS_ERR_OR_NULL(t))
goto free_tmp;
if (num_counters != t->private->nentries) {
@@ -1504,7 +1501,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void
__user *user, int *len)
return -EFAULT;
t = find_table_lock(net, tmp.name, &ret, &ebt_mutex);
- if (!t)
+ if (IS_ERR_OR_NULL(t))
return ret;
switch(cmd) {
@@ -2319,7 +2316,7 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd,
return -EFAULT;
t = find_table_lock(net, tmp.name, &ret, &ebt_mutex);
- if (!t)
+ if (IS_ERR_OR_NULL(t))
return ret;
xt_compat_lock(NFPROTO_BRIDGE);
--
1.8.2.1