aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2009-02-18 14:48:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-02-18 15:37:55 -0800
commitada723dcd681e2dffd7d73345cc8fda0eb0df9bd (patch)
tree5f1b114d225721ae7a65fca08a6d053f89f36c43 /fs
parent27c0c8e511fa9e2389503926840fac606d90a049 (diff)
fs/super.c: add lockdep annotation to s_umount
Li Zefan said: Thread 1: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 cat /mnt/cpus > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } Thread 2: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } (Note: It is irrelevant which cgroup subsys is used.) After a while a lockdep warning showed up: ============================================= [ INFO: possible recursive locking detected ] 2.6.28 #479 --------------------------------------------- mount/13554 is trying to acquire lock: (&type->s_umount_key#19){--..}, at: [<c049d888>] sget+0x5e/0x321 but task is already holding lock: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 other info that might help us debug this: 1 lock held by mount/13554: #0: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 stack backtrace: Pid: 13554, comm: mount Not tainted 2.6.28-mc #479 Call Trace: [<c044ad2e>] validate_chain+0x4c6/0xbbd [<c044ba9b>] __lock_acquire+0x676/0x700 [<c044bb82>] lock_acquire+0x5d/0x7a [<c049d888>] ? sget+0x5e/0x321 [<c061b9b8>] down_write+0x34/0x50 [<c049d888>] ? sget+0x5e/0x321 [<c049d888>] sget+0x5e/0x321 [<c045a2e7>] ? cgroup_set_super+0x0/0x3e [<c045959f>] ? cgroup_test_super+0x0/0x2f [<c045bcea>] cgroup_get_sb+0x98/0x2e7 [<c045cfb6>] cpuset_get_sb+0x4a/0x5f [<c049dfa4>] vfs_kern_mount+0x40/0x7b [<c049e02d>] do_kern_mount+0x37/0xbf [<c04af4a0>] do_mount+0x5c3/0x61a [<c04addd2>] ? copy_mount_options+0x2c/0x111 [<c04af560>] sys_mount+0x69/0xa0 [<c0403251>] sysenter_do_call+0x12/0x31 The cause is after alloc_super() and then retry, an old entry in list fs_supers is found, so grab_super(old) is called, but both functions hold s_umount lock: struct super_block *sget(...) { ... retry: spin_lock(&sb_lock); if (test) { list_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (!grab_super(old)) <--- 2nd: down_write(&old->s_umount); goto retry; if (s) destroy_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type); <--- 1th: down_write(&s->s_umount) if (!s) return ERR_PTR(-ENOMEM); goto retry; } ... } It seems like a false positive, and seems like VFS but not cgroup needs to be fixed. Peter said: We can simply put the new s_umount instance in a but lockdep doesn't particularly cares about subclass order. If there's any issue with the callers of sget() assuming the s_umount lock being of sublcass 0, then there is another annotation we can use to fix that, but lets not bother with that if this is sufficient. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12673 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Li Zefan <lizf@cn.fujitsu.com> Reported-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Paul Menage <menage@google.com> Cc: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/super.c17
1 files changed, 16 insertions, 1 deletions
diff --git a/fs/super.c b/fs/super.c
index 61dce001dd5..8349ed6b141 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -82,7 +82,22 @@ static struct super_block *alloc_super(struct file_system_type *type)
* lock ordering than usbfs:
*/
lockdep_set_class(&s->s_lock, &type->s_lock_key);
- down_write(&s->s_umount);
+ /*
+ * sget() can have s_umount recursion.
+ *
+ * When it cannot find a suitable sb, it allocates a new
+ * one (this one), and tries again to find a suitable old
+ * one.
+ *
+ * In case that succeeds, it will acquire the s_umount
+ * lock of the old one. Since these are clearly distrinct
+ * locks, and this object isn't exposed yet, there's no
+ * risk of deadlocks.
+ *
+ * Annotate this by putting this lock in a different
+ * subclass.
+ */
+ down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
s->s_count = S_BIAS;
atomic_set(&s->s_active, 1);
mutex_init(&s->s_vfs_rename_mutex);