ext3: Replace lock/unlock_super() with an explicit lock for resizing

Use a separate lock to protect s_groups_count and the other block
group descriptors which get changed via an on-line resize operation,
so we can stop overloading the use of lock_super().

Port of ext4 commit 32ed5058ce90024efcd811254b4b1de0468099df by
Theodore Ts'o <tytso@mit.edu>.

CC: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 5f83b61791786a06eba1d5014697bfbf31fa47ab..54351ac7cef92deba61a0473ee4ef01589c67c39 100644 (file)
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -209,7 +209,7 @@ static int setup_new_group_blocks(struct super_block *sb,
        if (IS_ERR(handle))
                return PTR_ERR(handle);
 
-       lock_super(sb);
+       mutex_lock(&sbi->s_resize_lock);
        if (input->group != sbi->s_groups_count) {
                err = -EBUSY;
                goto exit_journal;
@@ -324,7 +324,7 @@ exit_bh:
        brelse(bh);
 
 exit_journal:
-       unlock_super(sb);
+       mutex_unlock(&sbi->s_resize_lock);
        if ((err2 = ext3_journal_stop(handle)) && !err)
                err = err2;
 
@@ -662,11 +662,12 @@ exit_free:
  * important part is that the new block and inode counts are in the backup
  * superblocks, and the location of the new group metadata in the GDT backups.
  *
- * We do not need lock_super() for this, because these blocks are not
- * otherwise touched by the filesystem code when it is mounted.  We don't
- * need to worry about last changing from sbi->s_groups_count, because the
- * worst that can happen is that we do not copy the full number of backups
- * at this time.  The resize which changed s_groups_count will backup again.
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted.  We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time.  The resize
+ * which changed s_groups_count will backup again.
  */
 static void update_backups(struct super_block *sb,
                           int blk_off, char *data, int size)
@@ -825,7 +826,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
                goto exit_put;
        }
 
-       lock_super(sb);
+       mutex_lock(&sbi->s_resize_lock);
        if (input->group != sbi->s_groups_count) {
                ext3_warning(sb, __func__,
                             "multiple resizers run on filesystem!");
@@ -856,7 +857,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
        /*
         * OK, now we've set up the new group.  Time to make it active.
         *
-        * Current kernels don't lock all allocations via lock_super(),
+        * We do not lock all allocations via s_resize_lock
         * so we have to be safe wrt. concurrent accesses the group
         * data.  So we need to be careful to set all of the relevant
         * group descriptor data etc. *before* we enable the group.
@@ -900,12 +901,12 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
         *
         * The precise rules we use are:
         *
-        * * Writers of s_groups_count *must* hold lock_super
+        * * Writers of s_groups_count *must* hold s_resize_lock
         * AND
         * * Writers must perform a smp_wmb() after updating all dependent
         *   data and before modifying the groups count
         *
-        * * Readers must hold lock_super() over the access
+        * * Readers must hold s_resize_lock over the access
         * OR
         * * Readers must perform an smp_rmb() after reading the groups count
         *   and before reading any dependent data.
@@ -936,7 +937,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
        ext3_journal_dirty_metadata(handle, sbi->s_sbh);
 
 exit_journal:
-       unlock_super(sb);
+       mutex_unlock(&sbi->s_resize_lock);
        if ((err2 = ext3_journal_stop(handle)) && !err)
                err = err2;
        if (!err) {
@@ -973,7 +974,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 
        /* We don't need to worry about locking wrt other resizers just
         * yet: we're going to revalidate es->s_blocks_count after
-        * taking lock_super() below. */
+        * taking the s_resize_lock below. */
        o_blocks_count = le32_to_cpu(es->s_blocks_count);
        o_groups_count = EXT3_SB(sb)->s_groups_count;
 
@@ -1045,11 +1046,11 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
                goto exit_put;
        }
 
-       lock_super(sb);
+       mutex_lock(&EXT3_SB(sb)->s_resize_lock);
        if (o_blocks_count != le32_to_cpu(es->s_blocks_count)) {
                ext3_warning(sb, __func__,
                             "multiple resizers run on filesystem!");
-               unlock_super(sb);
+               mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
                ext3_journal_stop(handle);
                err = -EBUSY;
                goto exit_put;
@@ -1059,13 +1060,13 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
                                                 EXT3_SB(sb)->s_sbh))) {
                ext3_warning(sb, __func__,
                             "error %d on journal write access", err);
-               unlock_super(sb);
+               mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
                ext3_journal_stop(handle);
                goto exit_put;
        }
        es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
        ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
-       unlock_super(sb);
+       mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
        ext3_debug("freeing blocks %lu through "E3FSBLK"\n", o_blocks_count,
                   o_blocks_count + add);
        ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);

diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 97dd3828384c2dcb313f7ebb5ad6b3e4fbaa8ae4..afa2b569da101094dee07e58fda0f40391f8e045 100644 (file)
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1929,6 +1929,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 #endif
        INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
        mutex_init(&sbi->s_orphan_lock);
+       mutex_init(&sbi->s_resize_lock);
 
        sb->s_root = NULL;
 

diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index dd61d83026a014e86642da0bd36869393c058ca9..258088ab3c6bab4e3bad8ce5b5c987532dc9a90d 100644 (file)
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -73,6 +73,7 @@ struct ext3_sb_info {
        struct journal_s * s_journal;
        struct list_head s_orphan;
        struct mutex s_orphan_lock;
+       struct mutex s_resize_lock;
        unsigned long s_commit_interval;
        struct block_device *journal_bdev;
 #ifdef CONFIG_JBD_DEBUG