diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt index 1fb12f9dfe4877fb5a37744b1298d4b464aa74c6..7059623635b2d32fdaac02856447d6ab851eb04e 100644 --- a/Documentation/filesystems/gfs2-glocks.txt +++ b/Documentation/filesystems/gfs2-glocks.txt @@ -100,14 +100,15 @@ indicates that it is caching uptodate data. Glock locking order within GFS2: - 1. i_mutex (if required) + 1. i_rwsem (if required) 2. Rename glock (for rename only) 3. Inode glock(s) (Parents before children, inodes at "same level" with same parent in lock number order) 4. Rgrp glock(s) (for (de)allocation operations) 5. Transaction glock (via gfs2_trans_begin) for non-read operations - 6. Page lock (always last, very important!) + 6. i_rw_mutex (if required) + 7. Page lock (always last, very important!) There are two glocks per inode. One deals with access to the inode itself (locking order as above), and the other, known as the iopen diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 685c305cbeb6f7bcc6ad097ce20acfd1859ebdf3..278ed0869c3c11b9a3a512de9bb043c0b35bfee8 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1744,7 +1744,7 @@ static int do_grow(struct inode *inode, u64 size) * @newsize: the size to make the file * * The file size can grow, shrink, or stay the same size. This - * is called holding i_mutex and an exclusive glock on the inode + * is called holding i_rwsem and an exclusive glock on the inode * in question. * * Returns: errno diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 82fb5583445ca43f80d61ec3a7ac2fb0e006ef81..097bd3c0f270b690d9e74c9c053698568a03fef9 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1923,28 +1923,37 @@ void gfs2_glock_exit(void) static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi, loff_t n) { - if (n == 0) - gi->gl = rhashtable_walk_peek(&gi->hti); - else { - gi->gl = rhashtable_walk_next(&gi->hti); - n--; + struct gfs2_glock *gl = gi->gl; + + if (gl) { + if (n == 0) + return; + if (!lockref_put_not_zero(&gl->gl_lockref)) + gfs2_glock_queue_put(gl); } for (;;) { - if (IS_ERR_OR_NULL(gi->gl)) { - if (!gi->gl) - return; - if (PTR_ERR(gi->gl) != -EAGAIN) { - gi->gl = NULL; - return; + gl = rhashtable_walk_next(&gi->hti); + if (IS_ERR_OR_NULL(gl)) { + if (gl == ERR_PTR(-EAGAIN)) { + n = 1; + continue; } - n = 0; - } else if (gi->sdp == gi->gl->gl_name.ln_sbd && - !__lockref_is_dead(&gi->gl->gl_lockref)) { - if (!n--) - break; + gl = NULL; + break; + } + if (gl->gl_name.ln_sbd != gi->sdp) + continue; + if (n <= 1) { + if (!lockref_get_not_dead(&gl->gl_lockref)) + continue; + break; + } else { + if (__lockref_is_dead(&gl->gl_lockref)) + continue; + n--; } - gi->gl = rhashtable_walk_next(&gi->hti); } + gi->gl = gl; } static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) @@ -1988,7 +1997,6 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) { struct gfs2_glock_iter *gi = seq->private; - gi->gl = NULL; rhashtable_walk_stop(&gi->hti); } @@ -2076,7 +2084,8 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct seq_file *seq = file->private_data; struct gfs2_glock_iter *gi = seq->private; - gi->gl = NULL; + if (gi->gl) + gfs2_glock_put(gi->gl); rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index e6a0a8a89ea7e5696ea262b2d1d047b0e9962c00..3ba3f167641ccb9d7935532377abf2565fc2d2ea 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -825,7 +825,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo) goto fail_rindex; } /* - * i_mutex on quota files is special. Since this inode is hidden system + * i_rwsem on quota files is special. Since this inode is hidden system * file, we are safe to define locking ourselves. */ lockdep_set_class(&sdp->sd_quota_inode->i_rwsem, diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 2eac32095113177ba60493b956f44b97e525d471..99f17cc8e16300e89c23a95403b2a0712939a771 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -37,6 +37,7 @@ struct lockref { extern void lockref_get(struct lockref *); extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); +extern int lockref_put_not_zero(struct lockref *); extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); diff --git a/lib/lockref.c b/lib/lockref.c index 47169ed7e964f53dbc7735a3ad5b19c492878f45..3d468b53d4c931de6d76d0f51be6a07b3a066ecf 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -80,6 +80,34 @@ int lockref_get_not_zero(struct lockref *lockref) } EXPORT_SYMBOL(lockref_get_not_zero); +/** + * lockref_put_not_zero - Decrements count unless count <= 1 before decrement + * @lockref: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count would become zero + */ +int lockref_put_not_zero(struct lockref *lockref) +{ + int retval; + + CMPXCHG_LOOP( + new.count--; + if (old.count <= 1) + return 0; + , + return 1; + ); + + spin_lock(&lockref->lock); + retval = 0; + if (lockref->count > 1) { + lockref->count--; + retval = 1; + } + spin_unlock(&lockref->lock); + return retval; +} +EXPORT_SYMBOL(lockref_put_not_zero); + /** * lockref_get_or_lock - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure