From c72e05756b900b3be24cd73a16de52bab80984c0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 16 May 2009 18:12:08 +0200 Subject: 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 Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- fs/reiserfs/journal.c | 34 ---------------------------------- fs/reiserfs/xattr.c | 4 ++-- 2 files changed, 2 insertions(+), 36 deletions(-) (limited to 'fs/reiserfs') diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index e9a972bd032..d23d6d7a45a 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 6925b835a43..59870a4751c 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, -- cgit v1.2.3