Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: Remove automatic enabling of the HUGE_FILE feature flag
ext4: Replace hackish ext4_mb_poll_new_transaction with commit callback
ext4: Update Documentation/filesystems/ext4.txt
ext4: Remove unused mount options: nomballoc, mballoc, nocheck
ext4: Remove compile warnings when building w/o CONFIG_PROC_FS
ext4: Add missing newlines to printk messages
ext4: Fix file fragmentation during large file write.
vfs: Add no_nrwrite_index_update writeback control flag
vfs: Remove the range_cont writeback mode.
ext4: Use tag dirty lookup during mpage_da_submit_io
ext4: let the block device know when unused blocks can be discarded
ext4: Don't reuse released data blocks until transaction commits
ext4: Use an rbtree for tracking blocks freed during transaction.
ext4: Do mballoc init before doing filesystem recovery
ext4: Free ext4_prealloc_space using kmem_cache_free
ext4: Fix Kconfig typo for ext4dev
ext4: Remove an old reference to ext4dev in Makefile comment

Documentation/filesystems/ext4.txt

···
 Ext4 Filesystem
 ===============
 
-This is a development version of the ext4 filesystem, an advanced level
-of the ext3 filesystem which incorporates scalability and reliability
-enhancements for supporting large filesystems (64 bit) in keeping with
-increasing disk capacities and state-of-the-art feature requirements.
+Ext4 is an an advanced level of the ext3 filesystem which incorporates
+scalability and reliability enhancements for supporting large filesystems
+(64 bit) in keeping with increasing disk capacities and state-of-the-art
+feature requirements.
 
-Mailing list: [e-mail]
+Mailing list:	[e-mail]
+Web site:	http://ext4.wiki.kernel.org
 
 
 1. Quick usage instructions:
 ===========================
 
+Note: More extensive information for getting started with ext4 can be
+      found at the ext4 wiki site at the URL:
+      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+
   - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41) from:
+    writing version 1.41.3) from:
 
     http://sourceforge.net/project/showfiles.php?group_id=2406
 	
···
 
     	# mke2fs -t ext4 /dev/hda1
 
-    Or configure an existing ext3 filesystem to support extents and set
-    the test_fs flag to indicate that it's ok for an in-development
-    filesystem to touch this filesystem:
+    Or to configure an existing ext3 filesystem to support extents: 
 
-	# tune2fs -O extents -E test_fs /dev/hda1
+	# tune2fs -O extents /dev/hda1
 
     If the filesystem was created with 128 byte inodes, it can be
     converted to use 256 byte for greater efficiency via:
···
 The big performance win will come with mballoc, delalloc and flex_bg
 grouping of bitmaps and inode tables.  Some test results available here:
 
- - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
- - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
 
 3. Options
 ==========
···
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
 
-check=none		Don't do extra checking of bitmaps on mount.
-nocheck
-
 debug			Extra debugging information is sent to syslog.
 
 errors=remount-ro(*)	Remount the filesystem read-only on an error.
···
 			"nobh" option tries to avoid associating buffer
 			heads (supported only for "writeback" mode).
 
-mballoc		(*)	Use the multiple block allocator for block allocation
-nomballoc		disabled multiple block allocator for block allocation.
 stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data

fs/Kconfig

···
 	  filesystem initially.
 
 	  To compile this file system support as a module, choose M here. The
-	  module will be called ext4dev.
+	  module will be called ext4.
 
 	  If unsure, say N.
 

fs/Makefile

···
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
-obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4dev
+obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4
 obj-$(CONFIG_JBD)		+= jbd/
 obj-$(CONFIG_JBD2)		+= jbd2/
 obj-$(CONFIG_EXT2_FS)		+= ext2/

fs/ext4/balloc.c

···
 
 	/* this isn't the right place to decide whether block is metadata
 	 * inode.c/extents.c knows better, but for safety ... */
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
-			ext4_should_journal_data(inode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		metadata = 1;
+
+	/* We need to make sure we don't reuse
+	 * block released untill the transaction commit.
+	 * writeback mode have weak data consistency so
+	 * don't force data as metadata when freeing block
+	 * for writeback mode.
+	 */
+	if (metadata == 0 && !ext4_should_writeback_data(inode))
 		metadata = 1;
 
 	sb = inode->i_sb;

fs/ext4/ext4.h

···
 /*
  * Mount flags
  */
-#define EXT4_MOUNT_CHECK		0x00001	/* Do mount-time checks */
 #define EXT4_MOUNT_OLDALLOC		0x00002  /* Don't use the new Orlov allocator */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */

fs/ext4/ext4_sb.h

···
 	struct inode *s_buddy_cache;
 	long s_blocks_reserved;
 	spinlock_t s_reserve_lock;
-	struct list_head s_active_transaction;
-	struct list_head s_closed_transaction;
-	struct list_head s_committed_transaction;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
 	unsigned short *s_mb_offsets, *s_mb_maxs;

fs/ext4/inode.c

···
 	int ret = 0, err, nr_pages, i;
 	unsigned long index, end;
 	struct pagevec pvec;
+	long pages_skipped;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
 	pagevec_init(&pvec, 0);
···
 	end = mpd->next_page - 1;
 
 	while (index <= end) {
-		/* XXX: optimize tail */
-		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		/*
+		 * We can use PAGECACHE_TAG_DIRTY lookup here because
+		 * even though we have cleared the dirty flag on the page
+		 * We still keep the page in the radix tree with tag
+		 * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
+		 * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
+		 * which is called via the below writepage callback.
+		 */
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					PAGECACHE_TAG_DIRTY,
+					min(end - index,
+					(pgoff_t)PAGEVEC_SIZE-1) + 1);
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			index = page->index;
-			if (index > end)
-				break;
-			index++;
-
+			pages_skipped = mpd->wbc->pages_skipped;
 			err = mapping->a_ops->writepage(page, mpd->wbc);
-			if (!err)
+			if (!err && (pages_skipped == mpd->wbc->pages_skipped))
+				/*
+				 * have successfully written the page
+				 * without skipping the same
+				 */
 				mpd->pages_written++;
 			/*
 			 * In error case, we have to continue because
···
 			       struct writeback_control *wbc,
 			       struct mpage_da_data *mpd)
 {
-	long to_write;
 	int ret;
 
 	if (!mpd->get_block)
···
 	mpd->pages_written = 0;
 	mpd->retval = 0;
 
-	to_write = wbc->nr_to_write;
-
 	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
-
 	/*
 	 * Handle last extent of pages
 	 */
 	if (!mpd->io_done && mpd->next_page != mpd->first_page) {
 		if (mpage_da_map_blocks(mpd) == 0)
 			mpage_da_submit_io(mpd);
-	}
 
-	wbc->nr_to_write = to_write - mpd->pages_written;
+		mpd->io_done = 1;
+		ret = MPAGE_DA_EXTENT_TAIL;
+	}
+	wbc->nr_to_write -= mpd->pages_written;
 	return ret;
 }
 
···
 static int ext4_da_writepages(struct address_space *mapping,
 			      struct writeback_control *wbc)
 {
+	pgoff_t	index;
+	int range_whole = 0;
 	handle_t *handle = NULL;
-	loff_t range_start = 0;
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
+	int no_nrwrite_index_update;
+	long pages_written = 0, pages_skipped;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
-	long to_write, pages_skipped = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
 	/*
···
 		nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
 		wbc->nr_to_write = sbi->s_mb_stream_request;
 	}
+	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+		range_whole = 1;
 
-	if (!wbc->range_cyclic)
-		/*
-		 * If range_cyclic is not set force range_cont
-		 * and save the old writeback_index
-		 */
-		wbc->range_cont = 1;
-
-	range_start =  wbc->range_start;
-	pages_skipped = wbc->pages_skipped;
+	if (wbc->range_cyclic)
+		index = mapping->writeback_index;
+	else
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
 	mpd.inode = mapping->host;
 
-restart_loop:
-	to_write = wbc->nr_to_write;
-	while (!ret && to_write > 0) {
+	/*
+	 * we don't want write_cache_pages to update
+	 * nr_to_write and writeback_index
+	 */
+	no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+	wbc->no_nrwrite_index_update = 1;
+	pages_skipped = wbc->pages_skipped;
+
+	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
 		 * we  insert one extent at a time. So we need
···
 			dump_stack();
 			goto out_writepages;
 		}
-		to_write -= wbc->nr_to_write;
-
 		mpd.get_block = ext4_da_get_block_write;
 		ret = mpage_da_writepages(mapping, wbc, &mpd);
 
 		ext4_journal_stop(handle);
 
-		if (mpd.retval == -ENOSPC)
+		if (mpd.retval == -ENOSPC) {
+			/* commit the transaction which would
+			 * free blocks released in the transaction
+			 * and try again
+			 */
 			jbd2_journal_force_commit_nested(sbi->s_journal);
-
-		/* reset the retry count */
-		if (ret == MPAGE_DA_EXTENT_TAIL) {
+			wbc->pages_skipped = pages_skipped;
+			ret = 0;
+		} else if (ret == MPAGE_DA_EXTENT_TAIL) {
 			/*
 			 * got one extent now try with
 			 * rest of the pages
 			 */
-			to_write += wbc->nr_to_write;
+			pages_written += mpd.pages_written;
+			wbc->pages_skipped = pages_skipped;
 			ret = 0;
-		} else if (wbc->nr_to_write) {
+		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
 			 * or we requested for a noblocking writeout
 			 * and we found the device congested
 			 */
-			to_write += wbc->nr_to_write;
 			break;
-		}
-		wbc->nr_to_write = to_write;
 	}
+	if (pages_skipped != wbc->pages_skipped)
+		printk(KERN_EMERG "This should not happen leaving %s "
+				"with nr_to_write = %ld ret = %d\n",
+				__func__, wbc->nr_to_write, ret);
 
-	if (wbc->range_cont && (pages_skipped != wbc->pages_skipped)) {
-		/* We skipped pages in this loop */
-		wbc->range_start = range_start;
-		wbc->nr_to_write = to_write +
-				wbc->pages_skipped - pages_skipped;
-		wbc->pages_skipped = pages_skipped;
-		goto restart_loop;
-	}
+	/* Update index */
+	index += pages_written;
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		/*
+		 * set the writeback_index so that range_cyclic
+		 * mode will write it back later
+		 */
+		mapping->writeback_index = index;
 
 out_writepages:
-	wbc->nr_to_write = to_write - nr_to_writebump;
-	wbc->range_start = range_start;
+	if (!no_nrwrite_index_update)
+		wbc->no_nrwrite_index_update = 0;
+	wbc->nr_to_write -= nr_to_writebump;
 	return ret;
 }
 
···
 	struct inode *inode = &(ei->vfs_inode);
 	u64 i_blocks = inode->i_blocks;
 	struct super_block *sb = inode->i_sb;
-	int err = 0;
 
 	if (i_blocks <= ~0U) {
 		/*
···
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = 0;
 		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
-	} else if (i_blocks <= 0xffffffffffffULL) {
+		return 0;
+	}
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+		return -EFBIG;
+
+	if (i_blocks <= 0xffffffffffffULL) {
 		/*
 		 * i_blocks can be represented in a 48 bit variable
 		 * as multiple of 512 bytes
 		 */
-		err = ext4_update_rocompat_feature(handle, sb,
-					    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-		if (err)
-			goto  err_out;
-		/* i_block is stored in the split  48 bit fields */
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
 		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
 	} else {
-		/*
-		 * i_blocks should be represented in a 48 bit variable
-		 * as multiple of  file system block size
-		 */
-		err = ext4_update_rocompat_feature(handle, sb,
-					    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-		if (err)
-			goto  err_out;
 		ei->i_flags |= EXT4_HUGE_FILE_FL;
 		/* i_block is stored in file system block size */
 		i_blocks = i_blocks >> (inode->i_blkbits - 9);
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
 	}
-err_out:
-	return err;
+	return 0;
 }
 
 /*

fs/ext4/mballoc.c

···
 	}
 
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
+	meta_group_info[i]->bb_free_root.rb_node = NULL;;
 
 #ifdef DOUBLE_CHECK
 	{
···
 	}
 
 	spin_lock_init(&sbi->s_md_lock);
-	INIT_LIST_HEAD(&sbi->s_active_transaction);
-	INIT_LIST_HEAD(&sbi->s_closed_transaction);
-	INIT_LIST_HEAD(&sbi->s_committed_transaction);
 	spin_lock_init(&sbi->s_bal_lock);
 
 	sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
···
 	ext4_mb_init_per_dev_proc(sb);
 	ext4_mb_history_init(sb);
 
+	sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
 	printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
 	return 0;
 }
···
 		pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list);
 		list_del(&pa->pa_group_list);
 		count++;
-		kfree(pa);
+		kmem_cache_free(ext4_pspace_cachep, pa);
 	}
 	if (count)
 		mb_debug("mballoc: %u PAs left\n", count);
···
 	int num_meta_group_infos;
 	struct ext4_group_info *grinfo;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	/* release freed, non-committed blocks */
-	spin_lock(&sbi->s_md_lock);
-	list_splice_init(&sbi->s_closed_transaction,
-			&sbi->s_committed_transaction);
-	list_splice_init(&sbi->s_active_transaction,
-			&sbi->s_committed_transaction);
-	spin_unlock(&sbi->s_md_lock);
-	ext4_mb_free_committed_blocks(sb);
 
 	if (sbi->s_group_info) {
 		for (i = 0; i < sbi->s_groups_count; i++) {
···
 	return 0;
 }
 
-static noinline_for_stack void
-ext4_mb_free_committed_blocks(struct super_block *sb)
+/*
+ * This function is called by the jbd2 layer once the commit has finished,
+ * so we know we can free the blocks that were released with that commit.
+ */
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int err;
-	int i;
-	int count = 0;
-	int count2 = 0;
-	struct ext4_free_metadata *md;
+	struct super_block *sb = journal->j_private;
 	struct ext4_buddy e4b;
+	struct ext4_group_info *db;
+	int err, count = 0, count2 = 0;
+	struct ext4_free_data *entry;
+	ext4_fsblk_t discard_block;
+	struct list_head *l, *ltmp;
 
-	if (list_empty(&sbi->s_committed_transaction))
-		return;
-
-	/* there is committed blocks to be freed yet */
-	do {
-		/* get next array of blocks */
-		md = NULL;
-		spin_lock(&sbi->s_md_lock);
-		if (!list_empty(&sbi->s_committed_transaction)) {
-			md = list_entry(sbi->s_committed_transaction.next,
-					struct ext4_free_metadata, list);
-			list_del(&md->list);
-		}
-		spin_unlock(&sbi->s_md_lock);
-
-		if (md == NULL)
-			break;
+	list_for_each_safe(l, ltmp, &txn->t_private_list) {
+		entry = list_entry(l, struct ext4_free_data, list);
 
 		mb_debug("gonna free %u blocks in group %lu (0x%p):",
-				md->num, md->group, md);
+			 entry->count, entry->group, entry);
 
-		err = ext4_mb_load_buddy(sb, md->group, &e4b);
+		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
 		BUG_ON(err != 0);
 
+		db = e4b.bd_info;
 		/* there are blocks to put in buddy to make them really free */
-		count += md->num;
+		count += entry->count;
 		count2++;
-		ext4_lock_group(sb, md->group);
-		for (i = 0; i < md->num; i++) {
-			mb_debug(" %u", md->blocks[i]);
-			mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
+		ext4_lock_group(sb, entry->group);
+		/* Take it out of per group rb tree */
+		rb_erase(&entry->node, &(db->bb_free_root));
+		mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+
+		if (!db->bb_free_root.rb_node) {
+			/* No more items in the per group rb tree
+			 * balance refcounts from ext4_mb_free_metadata()
+			 */
+			page_cache_release(e4b.bd_buddy_page);
+			page_cache_release(e4b.bd_bitmap_page);
 		}
-		mb_debug("\n");
-		ext4_unlock_group(sb, md->group);
+		ext4_unlock_group(sb, entry->group);
+		discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
+			+ entry->start_blk
+			+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+		trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u", sb->s_id,
+			   (unsigned long long) discard_block, entry->count);
+		sb_issue_discard(sb, discard_block, entry->count);
 
-		/* balance refcounts from ext4_mb_free_metadata() */
-		page_cache_release(e4b.bd_buddy_page);
-		page_cache_release(e4b.bd_bitmap_page);
-
-		kfree(md);
+		kmem_cache_free(ext4_free_ext_cachep, entry);
 		ext4_mb_release_desc(&e4b);
-
-	} while (md);
+	}
 
 	mb_debug("freed %u blocks in %u structures\n", count, count2);
 }
···
 
 static int ext4_mb_init_per_dev_proc(struct super_block *sb)
 {
+#ifdef CONFIG_PROC_FS
 	mode_t mode = S_IFREG | S_IRUGO | S_IWUSR;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct proc_dir_entry *proc;
···
 	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
 	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
 	return -ENOMEM;
+#else
+	return 0;
+#endif
 }
 
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb)
 {
+#ifdef CONFIG_PROC_FS
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (sbi->s_proc == NULL)
···
 	remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_proc);
 	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
 	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
-
+#endif
 	return 0;
 }
 
···
 		kmem_cache_destroy(ext4_pspace_cachep);
 		return -ENOMEM;
 	}
+
+	ext4_free_ext_cachep =
+		kmem_cache_create("ext4_free_block_extents",
+				     sizeof(struct ext4_free_data),
+				     0, SLAB_RECLAIM_ACCOUNT, NULL);
+	if (ext4_free_ext_cachep == NULL) {
+		kmem_cache_destroy(ext4_pspace_cachep);
+		kmem_cache_destroy(ext4_ac_cachep);
+		return -ENOMEM;
+	}
 	return 0;
 }
 
···
 	/* XXX: synchronize_rcu(); */
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
+	kmem_cache_destroy(ext4_free_ext_cachep);
 }
 
 
···
 		goto out1;
 	}
 
-	ext4_mb_poll_new_transaction(sb, handle);
-
 	*errp = ext4_mb_initialize_context(ac, ar);
 	if (*errp) {
 		ar->len = 0;
···
 
 	return block;
 }
-static void ext4_mb_poll_new_transaction(struct super_block *sb,
-						handle_t *handle)
+
+/*
+ * We can merge two free data extents only if the physical blocks
+ * are contiguous, AND the extents were freed by the same transaction,
+ * AND the blocks are associated with the same group.
+ */
+static int can_merge(struct ext4_free_data *entry1,
+			struct ext4_free_data *entry2)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	if (sbi->s_last_transaction == handle->h_transaction->t_tid)
-		return;
-
-	/* new transaction! time to close last one and free blocks for
-	 * committed transaction. we know that only transaction can be
-	 * active, so previos transaction can be being logged and we
-	 * know that transaction before previous is known to be already
-	 * logged. this means that now we may free blocks freed in all
-	 * transactions before previous one. hope I'm clear enough ... */
-
-	spin_lock(&sbi->s_md_lock);
-	if (sbi->s_last_transaction != handle->h_transaction->t_tid) {
-		mb_debug("new transaction %lu, old %lu\n",
-				(unsigned long) handle->h_transaction->t_tid,
-				(unsigned long) sbi->s_last_transaction);
-		list_splice_init(&sbi->s_closed_transaction,
-				&sbi->s_committed_transaction);
-		list_splice_init(&sbi->s_active_transaction,
-				&sbi->s_closed_transaction);
-		sbi->s_last_transaction = handle->h_transaction->t_tid;
-	}
-	spin_unlock(&sbi->s_md_lock);
-
-	ext4_mb_free_committed_blocks(sb);
+	if ((entry1->t_tid == entry2->t_tid) &&
+	    (entry1->group == entry2->group) &&
+	    ((entry1->start_blk + entry1->count) == entry2->start_blk))
+		return 1;
+	return 0;
 }
 
 static noinline_for_stack int
···
 	struct ext4_group_info *db = e4b->bd_info;
 	struct super_block *sb = e4b->bd_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_free_metadata *md;
-	int i;
+	struct ext4_free_data *entry, *new_entry;
+	struct rb_node **n = &db->bb_free_root.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node;
+
 
 	BUG_ON(e4b->bd_bitmap_page == NULL);
 	BUG_ON(e4b->bd_buddy_page == NULL);
 
+	new_entry  = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+	new_entry->start_blk = block;
+	new_entry->group  = group;
+	new_entry->count = count;
+	new_entry->t_tid = handle->h_transaction->t_tid;
+	new_node = &new_entry->node;
+
 	ext4_lock_group(sb, group);
-	for (i = 0; i < count; i++) {
-		md = db->bb_md_cur;
-		if (md && db->bb_tid != handle->h_transaction->t_tid) {
-			db->bb_md_cur = NULL;
-			md = NULL;
-		}
-
-		if (md == NULL) {
-			ext4_unlock_group(sb, group);
-			md = kmalloc(sizeof(*md), GFP_NOFS);
-			if (md == NULL)
-				return -ENOMEM;
-			md->num = 0;
-			md->group = group;
-
-			ext4_lock_group(sb, group);
-			if (db->bb_md_cur == NULL) {
-				spin_lock(&sbi->s_md_lock);
-				list_add(&md->list, &sbi->s_active_transaction);
-				spin_unlock(&sbi->s_md_lock);
-				/* protect buddy cache from being freed,
-				 * otherwise we'll refresh it from
-				 * on-disk bitmap and lose not-yet-available
-				 * blocks */
-				page_cache_get(e4b->bd_buddy_page);
-				page_cache_get(e4b->bd_bitmap_page);
-				db->bb_md_cur = md;
-				db->bb_tid = handle->h_transaction->t_tid;
-				mb_debug("new md 0x%p for group %lu\n",
-						md, md->group);
-			} else {
-				kfree(md);
-				md = db->bb_md_cur;
-			}
-		}
-
-		BUG_ON(md->num >= EXT4_BB_MAX_BLOCKS);
-		md->blocks[md->num] = block + i;
-		md->num++;
-		if (md->num == EXT4_BB_MAX_BLOCKS) {
-			/* no more space, put full container on a sb's list */
-			db->bb_md_cur = NULL;
+	if (!*n) {
+		/* first free block exent. We need to
+		   protect buddy cache from being freed,
+		 * otherwise we'll refresh it from
+		 * on-disk bitmap and lose not-yet-available
+		 * blocks */
+		page_cache_get(e4b->bd_buddy_page);
+		page_cache_get(e4b->bd_bitmap_page);
+	}
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_free_data, node);
+		if (block < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (block >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			ext4_error(sb, __func__,
+			    "Double free of blocks %d (%d %d)\n",
+			    block, entry->start_blk, entry->count);
+			return 0;
 		}
 	}
+
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &db->bb_free_root);
+
+	/* Now try to see the extent can be merged to left and right */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
+		}
+	}
+
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
+		}
+	}
+	/* Add the extent to transaction's private list */
+	spin_lock(&sbi->s_md_lock);
+	list_add(&new_entry->list, &handle->h_transaction->t_private_list);
+	spin_unlock(&sbi->s_md_lock);
 	ext4_unlock_group(sb, group);
 	return 0;
 }
···
 	int ret;
 
 	*freed = 0;
-
-	ext4_mb_poll_new_transaction(sb, handle);
 
 	sbi = EXT4_SB(sb);
 	es = EXT4_SB(sb)->s_es;

fs/ext4/mballoc.h

···
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
 #include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/marker.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "group.h"
···
 
 static struct kmem_cache *ext4_pspace_cachep;
 static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
 
-#ifdef EXT4_BB_MAX_BLOCKS
-#undef EXT4_BB_MAX_BLOCKS
-#endif
-#define EXT4_BB_MAX_BLOCKS	30
+struct ext4_free_data {
+	/* this links the free block information from group_info */
+	struct rb_node node;
 
-struct ext4_free_metadata {
-	ext4_group_t group;
-	unsigned short num;
-	ext4_grpblk_t  blocks[EXT4_BB_MAX_BLOCKS];
+	/* this links the free block information from ext4_sb_info */
 	struct list_head list;
+
+	/* group which free block extent belongs */
+	ext4_group_t group;
+
+	/* free block extent */
+	ext4_grpblk_t start_blk;
+	ext4_grpblk_t count;
+
+	/* transaction which freed this extent */
+	tid_t	t_tid;
 };
 
 struct ext4_group_info {
 	unsigned long	bb_state;
-	unsigned long	bb_tid;
-	struct ext4_free_metadata *bb_md_cur;
+	struct rb_root  bb_free_root;
 	unsigned short	bb_first_free;
 	unsigned short	bb_free;
 	unsigned short	bb_fragments;
···
 
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
-static void ext4_mb_poll_new_transaction(struct super_block *, handle_t *);
-static void ext4_mb_free_committed_blocks(struct super_block *);
 static void ext4_mb_return_to_preallocation(struct inode *inode,
 					struct ext4_buddy *e4b, sector_t block,
 					int count);
···
 			struct super_block *, struct ext4_prealloc_space *pa);
 static int ext4_mb_init_per_dev_proc(struct super_block *sb);
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
 
 
 static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)

fs/ext4/super.c

···
 	 */
 }
 
-int ext4_update_compat_feature(handle_t *handle,
-					struct super_block *sb, __u32 compat)
-{
-	int err = 0;
-	if (!EXT4_HAS_COMPAT_FEATURE(sb, compat)) {
-		err = ext4_journal_get_write_access(handle,
-				EXT4_SB(sb)->s_sbh);
-		if (err)
-			return err;
-		EXT4_SET_COMPAT_FEATURE(sb, compat);
-		sb->s_dirt = 1;
-		handle->h_sync = 1;
-		BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-					"call ext4_journal_dirty_met adata");
-		err = ext4_journal_dirty_metadata(handle,
-				EXT4_SB(sb)->s_sbh);
-	}
-	return err;
-}
-
-int ext4_update_rocompat_feature(handle_t *handle,
-					struct super_block *sb, __u32 rocompat)
-{
-	int err = 0;
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, rocompat)) {
-		err = ext4_journal_get_write_access(handle,
-				EXT4_SB(sb)->s_sbh);
-		if (err)
-			return err;
-		EXT4_SET_RO_COMPAT_FEATURE(sb, rocompat);
-		sb->s_dirt = 1;
-		handle->h_sync = 1;
-		BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-					"call ext4_journal_dirty_met adata");
-		err = ext4_journal_dirty_metadata(handle,
-				EXT4_SB(sb)->s_sbh);
-	}
-	return err;
-}
-
-int ext4_update_incompat_feature(handle_t *handle,
-					struct super_block *sb, __u32 incompat)
-{
-	int err = 0;
-	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, incompat)) {
-		err = ext4_journal_get_write_access(handle,
-				EXT4_SB(sb)->s_sbh);
-		if (err)
-			return err;
-		EXT4_SET_INCOMPAT_FEATURE(sb, incompat);
-		sb->s_dirt = 1;
-		handle->h_sync = 1;
-		BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-					"call ext4_journal_dirty_met adata");
-		err = ext4_journal_dirty_metadata(handle,
-				EXT4_SB(sb)->s_sbh);
-	}
-	return err;
-}
-
 /*
  * Open the external journal device
  */
···
 enum {
 	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
 	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
-	Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
+	Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
 	Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
 	Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
 	Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
···
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
 	Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
-	Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+	Opt_stripe, Opt_delalloc, Opt_nodelalloc,
 	Opt_inode_readahead_blks
 };
 
···
 	{Opt_err_panic, "errors=panic"},
 	{Opt_err_ro, "errors=remount-ro"},
 	{Opt_nouid32, "nouid32"},
-	{Opt_nocheck, "nocheck"},
-	{Opt_nocheck, "check=none"},
 	{Opt_debug, "debug"},
 	{Opt_oldalloc, "oldalloc"},
 	{Opt_orlov, "orlov"},
···
 	{Opt_extents, "extents"},
 	{Opt_noextents, "noextents"},
 	{Opt_i_version, "i_version"},
-	{Opt_mballoc, "mballoc"},
-	{Opt_nomballoc, "nomballoc"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_resize, "resize"},
 	{Opt_delalloc, "delalloc"},
···
 			break;
 		case Opt_nouid32:
 			set_opt(sbi->s_mount_opt, NO_UID32);
-			break;
-		case Opt_nocheck:
-			clear_opt(sbi->s_mount_opt, CHECK);
 			break;
 		case Opt_debug:
 			set_opt(sbi->s_mount_opt, DEBUG);
···
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
 			       "Block bitmap for group %lu not in group "
-			       "(block %llu)!", i, block_bitmap);
+			       "(block %llu)!\n", i, block_bitmap);
 			return 0;
 		}
 		inode_bitmap = ext4_inode_bitmap(sb, gdp);
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
 			       "Inode bitmap for group %lu not in group "
-			       "(block %llu)!", i, inode_bitmap);
+			       "(block %llu)!\n", i, inode_bitmap);
 			return 0;
 		}
 		inode_table = ext4_inode_table(sb, gdp);
···
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
 			       "Inode table for group %lu not in group "
-			       "(block %llu)!", i, inode_table);
+			       "(block %llu)!\n", i, inode_table);
 			return 0;
 		}
 		spin_lock(sb_bgl_lock(sbi, i));
···
  *
  * Note, this does *not* consider any metadata overhead for vfs i_blocks.
  */
-static loff_t ext4_max_size(int blkbits)
+static loff_t ext4_max_size(int blkbits, int has_huge_files)
 {
 	loff_t res;
 	loff_t upper_limit = MAX_LFS_FILESIZE;
 
 	/* small i_blocks in vfs inode? */
-	if (sizeof(blkcnt_t) < sizeof(u64)) {
+	if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
 		/*
 		 * CONFIG_LSF is not enabled implies the inode
 		 * i_block represent total blocks in 512 bytes
···
  * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
  * We need to be 1 filesystem block less than the 2^48 sector limit.
  */
-static loff_t ext4_max_bitmap_size(int bits)
+static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 {
 	loff_t res = EXT4_NDIR_BLOCKS;
 	int meta_blocks;
···
 	 * total number of  512 bytes blocks of the file
 	 */
 
-	if (sizeof(blkcnt_t) < sizeof(u64)) {
+	if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
 		/*
-		 * CONFIG_LSF is not enabled implies the inode
-		 * i_block represent total blocks in 512 bytes
-		 * 32 == size of vfs inode i_blocks * 8
+		 * !has_huge_files or CONFIG_LSF is not enabled
+		 * implies the inode i_block represent total blocks in
+		 * 512 bytes 32 == size of vfs inode i_blocks * 8
 		 */
 		upper_limit = (1LL << 32) - 1;
 
···
 	int blocksize;
 	int db_count;
 	int i;
-	int needs_recovery;
+	int needs_recovery, has_huge_files;
 	__le32 features;
 	__u64 blocks_count;
 	int err;
···
 		       sb->s_id, le32_to_cpu(features));
 		goto failed_mount;
 	}
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+	has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
+	if (has_huge_files) {
 		/*
 		 * Large file size enabled file system can only be
 		 * mount if kernel is build with CONFIG_LSF
···
 		}
 	}
 
-	sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits);
-	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits);
+	sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
+						      has_huge_files);
+	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
 
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
···
 			"available.\n");
 	}
 
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+		printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
+				"requested data journaling mode\n");
+		clear_opt(sbi->s_mount_opt, DELALLOC);
+	} else if (test_opt(sb, DELALLOC))
+		printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
+
+	ext4_ext_init(sb);
+	err = ext4_mb_init(sb, needs_recovery);
+	if (err) {
+		printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
+		       err);
+		goto failed_mount4;
+	}
+
 	/*
 	 * akpm: core read_super() calls in here with the superblock locked.
 	 * That deadlocks, because orphan cleanup needs to lock the superblock
···
 	       test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
 	       test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
 	       "writeback");
-
-	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
-				"requested data journaling mode\n");
-		clear_opt(sbi->s_mount_opt, DELALLOC);
-	} else if (test_opt(sb, DELALLOC))
-		printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
-
-	ext4_ext_init(sb);
-	err = ext4_mb_init(sb, needs_recovery);
-	if (err) {
-		printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
-		       err);
-		goto failed_mount4;
-	}
 
 	lock_kernel();
 	return 0;

fs/jbd2/commit.c

···
 	}
 	spin_unlock(&journal->j_list_lock);
 
+	if (journal->j_commit_callback)
+		journal->j_commit_callback(journal, commit_transaction);
+
 	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
 		   journal->j_devname, commit_transaction->t_tid,
 		   journal->j_tail_sequence);

fs/jbd2/transaction.c

···
 	transaction->t_expires = jiffies + journal->j_commit_interval;
 	spin_lock_init(&transaction->t_handle_lock);
 	INIT_LIST_HEAD(&transaction->t_inode_list);
+	INIT_LIST_HEAD(&transaction->t_private_list);
 
 	/* Set up the commit timer for the new transaction. */
 	journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);

include/linux/jbd2.h

···
 	 */
 	int t_handle_count;
 
+	/*
+	 * For use by the filesystem to store fs-specific data
+	 * structures associated with the transaction
+	 */
+	struct list_head	t_private_list;
 };
 
 struct transaction_run_stats_s {
···
 	int			j_wbufsize;
 
 	pid_t			j_last_sync_writer;
+
+	/* This function is called when a transaction is closed */
+	void			(*j_commit_callback)(journal_t *,
+						     transaction_t *);
 
 	/*
 	 * Journal statistics

include/linux/writeback.h

···
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned more_io:1;		/* more io to be dispatched */
-	unsigned range_cont:1;
+	/*
+	 * write_cache_pages() won't update wbc->nr_to_write and
+	 * mapping->writeback_index if no_nrwrite_index_update
+	 * is set.  write_cache_pages() may write more than we
+	 * requested and we want to make sure nr_to_write and
+	 * writeback_index are updated in a consistent manner
+	 * so we use a single control to update them
+	 */
+	unsigned no_nrwrite_index_update:1;
 };
 
 /*

mm/page-writeback.c

···
 	pgoff_t end;		/* Inclusive */
 	int scanned = 0;
 	int range_whole = 0;
+	long nr_to_write = wbc->nr_to_write;
 
 	if (wbc->nonblocking && bdi_write_congested(bdi)) {
 		wbc->encountered_congestion = 1;
···
 				unlock_page(page);
 				ret = 0;
 			}
-			if (ret || (--(wbc->nr_to_write) <= 0))
+			if (ret || (--nr_to_write <= 0))
 				done = 1;
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
···
 		index = 0;
 		goto retry;
 	}
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+	if (!wbc->no_nrwrite_index_update) {
+		if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
+			mapping->writeback_index = index;
+		wbc->nr_to_write = nr_to_write;
+	}
 
-	if (wbc->range_cont)
-		wbc->range_start = index << PAGE_CACHE_SHIFT;
 	return ret;
 }
 EXPORT_SYMBOL(write_cache_pages);