summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2009-05-16 18:12:08 +0200
committerFrederic Weisbecker <fweisbec@gmail.com>2009-09-14 07:18:24 +0200
commitc72e05756b900b3be24cd73a16de52bab80984c0 (patch)
tree4fc35ad9efc1a6a9ca14baa3612e551fb4da793e
parent2ac626955ed62ee8596f00581f959cc86e6198d1 (diff)
downloadop-kernel-dev-c72e05756b900b3be24cd73a16de52bab80984c0.zip
op-kernel-dev-c72e05756b900b3be24cd73a16de52bab80984c0.tar.gz
kill-the-bkl/reiserfs: acquire the inode mutex safely
While searching a pathname, an inode mutex can be acquired in do_lookup() which calls reiserfs_lookup() which in turn acquires the write lock. On the other side reiserfs_fill_super() can acquire the write_lock and then call reiserfs_lookup_privroot() which can acquire an inode mutex (the root of the mount point). So we theoretically risk an AB - BA lock inversion that could lead to a deadlock. As for other lock dependencies found since the bkl to mutex conversion, the fix is to use reiserfs_mutex_lock_safe() which drops the lock dependency to the write lock. [ Impact: fix a possible deadlock with reiserfs ] Cc: Jeff Mahoney <jeffm@suse.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
-rw-r--r--fs/reiserfs/journal.c34
-rw-r--r--fs/reiserfs/xattr.c4
-rw-r--r--include/linux/reiserfs_fs.h35
3 files changed, 37 insertions, 36 deletions
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index e9a972b..d23d6d7 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -537,40 +537,6 @@ static inline void insert_journal_hash(struct reiserfs_journal_cnode **table,
journal_hash(table, cn->sb, cn->blocknr) = cn;
}
-/*
- * Several mutexes depend on the write lock.
- * However sometimes we want to relax the write lock while we hold
- * these mutexes, according to the release/reacquire on schedule()
- * properties of the Bkl that were used.
- * Reiserfs performances and locking were based on this scheme.
- * Now that the write lock is a mutex and not the bkl anymore, doing so
- * may result in a deadlock:
- *
- * A acquire write_lock
- * A acquire j_commit_mutex
- * A release write_lock and wait for something
- * B acquire write_lock
- * B can't acquire j_commit_mutex and sleep
- * A can't acquire write lock anymore
- * deadlock
- *
- * What we do here is avoiding such deadlock by playing the same game
- * than the Bkl: if we can't acquire a mutex that depends on the write lock,
- * we release the write lock, wait a bit and then retry.
- *
- * The mutexes concerned by this hack are:
- * - The commit mutex of a journal list
- * - The flush mutex
- * - The journal lock
- */
-static inline void reiserfs_mutex_lock_safe(struct mutex *m,
- struct super_block *s)
-{
- reiserfs_write_unlock(s);
- mutex_lock(m);
- reiserfs_write_lock(s);
-}
-
/* lock the current transaction */
static inline void lock_journal(struct super_block *sb)
{
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 6925b83..59870a4 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -975,7 +975,7 @@ int reiserfs_lookup_privroot(struct super_block *s)
int err = 0;
/* If we don't have the privroot located yet - go find it */
- mutex_lock(&s->s_root->d_inode->i_mutex);
+ reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s);
dentry = lookup_one_len(PRIVROOT_NAME, s->s_root,
strlen(PRIVROOT_NAME));
if (!IS_ERR(dentry)) {
@@ -1011,7 +1011,7 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
if (privroot->d_inode) {
s->s_xattr = reiserfs_xattr_handlers;
- mutex_lock(&privroot->d_inode->i_mutex);
+ reiserfs_mutex_lock_safe(&privroot->d_inode->i_mutex, s);
if (!REISERFS_SB(s)->xattr_root) {
struct dentry *dentry;
dentry = lookup_one_len(XAROOT_NAME, privroot,
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 508fb52..a498d92 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -63,6 +63,41 @@ int reiserfs_write_lock_once(struct super_block *s);
void reiserfs_write_unlock_once(struct super_block *s, int lock_depth);
/*
+ * Several mutexes depend on the write lock.
+ * However sometimes we want to relax the write lock while we hold
+ * these mutexes, according to the release/reacquire on schedule()
+ * properties of the Bkl that were used.
+ * Reiserfs performances and locking were based on this scheme.
+ * Now that the write lock is a mutex and not the bkl anymore, doing so
+ * may result in a deadlock:
+ *
+ * A acquire write_lock
+ * A acquire j_commit_mutex
+ * A release write_lock and wait for something
+ * B acquire write_lock
+ * B can't acquire j_commit_mutex and sleep
+ * A can't acquire write lock anymore
+ * deadlock
+ *
+ * What we do here is avoiding such deadlock by playing the same game
+ * than the Bkl: if we can't acquire a mutex that depends on the write lock,
+ * we release the write lock, wait a bit and then retry.
+ *
+ * The mutexes concerned by this hack are:
+ * - The commit mutex of a journal list
+ * - The flush mutex
+ * - The journal lock
+ * - The inode mutex
+ */
+static inline void reiserfs_mutex_lock_safe(struct mutex *m,
+ struct super_block *s)
+{
+ reiserfs_write_unlock(s);
+ mutex_lock(m);
+ reiserfs_write_lock(s);
+}
+
+/*
* When we schedule, we usually want to also release the write lock,
* according to the previous bkl based locking scheme of reiserfs.
*/
OpenPOWER on IntegriCloud