1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
From 26c9f57c6ada2518c265d0a52b29a26be7bcb746 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Tue, 10 Jan 2012 18:22:25 +0100
Subject: [PATCH 076/130] fix shrink_dcache_parent() livelock
commit eaf5f9073533cde21c7121c136f1c3f072d9cf59 upstream.
Two (or more) concurrent calls of shrink_dcache_parent() on the same dentry may
cause shrink_dcache_parent() to loop forever.
Here's what appears to happen:
1 - CPU0: select_parent(P) finds C and puts it on dispose list, returns 1
2 - CPU1: select_parent(P) locks P->d_lock
3 - CPU0: shrink_dentry_list() locks C->d_lock
dentry_kill(C) tries to lock P->d_lock but fails, unlocks C->d_lock
4 - CPU1: select_parent(P) locks C->d_lock,
moves C from dispose list being processed on CPU0 to the new
dispose list, returns 1
5 - CPU0: shrink_dentry_list() finds dispose list empty, returns
6 - Goto 2 with CPU0 and CPU1 switched
Basically select_parent() steals the dentry from shrink_dentry_list() and thinks
it found a new one, causing shrink_dentry_list() to think it's making progress
and loop over and over.
One way to trigger this is to make udev calls stat() on the sysfs file while it
is going away.
Having a file in /lib/udev/rules.d/ with only this one rule seems to the trick:
ATTR{vendor}=="0x8086", ATTR{device}=="0x10ca", ENV{PCI_SLOT_NAME}="%k", ENV{MATCHADDR}="$attr{address}", RUN+="/bin/true"
Then execute the following loop:
while true; do
echo -bond0 > /sys/class/net/bonding_masters
echo +bond0 > /sys/class/net/bonding_masters
echo -bond1 > /sys/class/net/bonding_masters
echo +bond1 > /sys/class/net/bonding_masters
done
One fix would be to check all callers and prevent concurrent calls to
shrink_dcache_parent(). But I think a better solution is to stop the
stealing behavior.
This patch adds a new dentry flag that is set when the dentry is added to the
dispose list. The flag is cleared in dentry_lru_del() in case the dentry gets a
new reference just before being pruned.
If the dentry has this flag, select_parent() will skip it and let
shrink_dentry_list() retry pruning it. With select_parent() skipping those
dentries there will not be the appearance of progress (new dentries found) when
there is none, hence shrink_dcache_parent() will not loop forever.
Set the flag is also set in prune_dcache_sb() for consistency as suggested by
Linus.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
fs/dcache.c | 15 +++++++++++----
include/linux/dcache.h | 1 +
2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 108116e..f7908ae 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -242,6 +242,7 @@ static void dentry_lru_add(struct dentry *dentry)
static void __dentry_lru_del(struct dentry *dentry)
{
list_del_init(&dentry->d_lru);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
dentry->d_sb->s_nr_dentry_unused--;
dentry_stat.nr_unused--;
}
@@ -805,6 +806,7 @@ relock:
spin_unlock(&dentry->d_lock);
} else {
list_move_tail(&dentry->d_lru, &tmp);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
spin_unlock(&dentry->d_lock);
if (!--count)
break;
@@ -1096,14 +1098,19 @@ resume:
/*
* move only zero ref count dentries to the dispose list.
+ *
+ * Those which are presently on the shrink list, being processed
+ * by shrink_dentry_list(), shouldn't be moved. Otherwise the
+ * loop in shrink_dcache_parent() might not make any progress
+ * and loop forever.
*/
- if (!dentry->d_count) {
+ if (dentry->d_count) {
+ dentry_lru_del(dentry);
+ } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
dentry_lru_move_list(dentry, dispose);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
found++;
- } else {
- dentry_lru_del(dentry);
}
-
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index ed9f74f..4eb8c80 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -203,6 +203,7 @@ struct dentry_operations {
#define DCACHE_CANT_MOUNT 0x0100
#define DCACHE_GENOCIDE 0x0200
+#define DCACHE_SHRINK_LIST 0x0400
#define DCACHE_NFSFS_RENAMED 0x1000
/* this dentry has been "silly renamed" and has to be deleted on the last
--
1.7.7.4
|
