Merge branch 'for_linus' into for_linus_merged

Conflicts:
	fs/ext4/ioctl.c

16 files changed, 1079 insertions, 463 deletions

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 4917cf24a5e0..10ec4639f152 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -581,6 +581,13 @@ Table of Ext4 specific ioctls
 			      behaviour may change in the future as it is
 			      not necessary and has been done this way only
 			      for sake of simplicity.
+
+ EXT4_IOC_RESIZE_FS	      Resize the filesystem to a new size.  The number
+			      of blocks of resized filesystem is passed in via
+			      64 bit integer argument.  The kernel allocates
+			      bitmaps and inode table, the userspace tool thus
+			      just passes the new number of blocks.
+
 ..............................................................................
 
 References
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 12ccacda44e0..f9e2cd8cf711 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -23,6 +23,8 @@
 
 #include <trace/events/ext4.h>
 
+static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+					    ext4_group_t block_group);
 /*
  * balloc.c contains the blocks allocation and deallocation routines
  */
@@ -668,7 +670,7 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
  * This function returns the number of file system metadata clusters at
  * the beginning of a block group, including the reserved gdt blocks.
  */
-unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
 				     ext4_group_t block_group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1554b15f91bc..513004fc3d84 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -511,6 +511,14 @@ struct ext4_new_group_data {
 	__u32 free_blocks_count;
 };
 
+/* Indexes used to index group tables in ext4_new_group_data */
+enum {
+	BLOCK_BITMAP = 0,	/* block bitmap */
+	INODE_BITMAP,		/* inode bitmap */
+	INODE_TABLE,		/* inode tables */
+	GROUP_TABLE_COUNT,
+};
+
 /*
  * Flags used by ext4_map_blocks()
  */
@@ -575,6 +583,7 @@ struct ext4_new_group_data {
  /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
 #define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
 #define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
+#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -957,12 +966,13 @@ struct ext4_inode_info {
 #define test_opt2(sb, opt)		(EXT4_SB(sb)->s_mount_opt2 & \
 					 EXT4_MOUNT2_##opt)
 
-#define ext4_set_bit			__test_and_set_bit_le
+#define ext4_test_and_set_bit		__test_and_set_bit_le
+#define ext4_set_bit			__set_bit_le
 #define ext4_set_bit_atomic		ext2_set_bit_atomic
-#define ext4_clear_bit			__test_and_clear_bit_le
+#define ext4_test_and_clear_bit		__test_and_clear_bit_le
+#define ext4_clear_bit			__clear_bit_le
 #define ext4_clear_bit_atomic		ext2_clear_bit_atomic
 #define ext4_test_bit			test_bit_le
-#define ext4_find_first_zero_bit	find_first_zero_bit_le
 #define ext4_find_next_zero_bit		find_next_zero_bit_le
 #define ext4_find_next_bit		find_next_bit_le
 
@@ -1397,6 +1407,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
 #define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
 #define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
+#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
@@ -1409,6 +1420,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
 #define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
 #define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
+#define EXT4_FEATURE_INCOMPAT_INLINEDATA	0x2000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
 
 #define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
 #define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1790,8 +1803,6 @@ extern void ext4_init_block_bitmap(struct super_block *sb,
 extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      ext4_group_t block_group,
 					      struct ext4_group_desc *gdp);
-extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
-					    ext4_group_t block_group);
 extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
 					   ext4_group_t block_group,
 					   struct ext4_group_desc *gdp);
@@ -1880,16 +1891,9 @@ extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_block_truncate_page(handle_t *handle,
-		struct address_space *mapping, loff_t from);
-extern int ext4_block_zero_page_range(handle_t *handle,
-		struct address_space *mapping, loff_t from, loff_t length);
 extern int ext4_discard_partial_page_buffers(handle_t *handle,
 		struct address_space *mapping, loff_t from,
 		loff_t length, int flags);
-extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
-		struct inode *inode, struct page *page, loff_t from,
-		loff_t length, int flags);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1924,6 +1928,7 @@ extern int ext4_group_add(struct super_block *sb,
 extern int ext4_group_extend(struct super_block *sb,
 				struct ext4_super_block *es,
 				ext4_fsblk_t n_blocks_count);
+extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 
 /* super.c */
 extern void *ext4_kvmalloc(size_t size, gfp_t flags);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 841faf5fb785..74f23c292e1b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3280,6 +3280,9 @@ static int ext4_find_delalloc_range(struct inode *inode,
 	ext4_lblk_t i, pg_lblk;
 	pgoff_t index;
 
+	if (!test_opt(inode->i_sb, DELALLOC))
+		return 0;
+
 	/* reverse search wont work if fs block size is less than page size */
 	if (inode->i_blkbits < PAGE_CACHE_SHIFT)
 		search_hint_reverse = 0;
@@ -3452,8 +3455,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	int err = 0;
 	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
 
-	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
-		  "block %llu, max_blocks %u, flags %d, allocated %u",
+	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
+		  "block %llu, max_blocks %u, flags %x, allocated %u\n",
 		  inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
@@ -3624,7 +3627,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
 	ext4_lblk_t ex_cluster_start, ex_cluster_end;
-	ext4_lblk_t rr_cluster_start, rr_cluster_end;
+	ext4_lblk_t rr_cluster_start;
 	ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
 	ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
 	unsigned short ee_len = ext4_ext_get_actual_len(ex);
@@ -3635,7 +3638,6 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 
 	/* The requested region passed into ext4_map_blocks() */
 	rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
-	rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
 
 	if ((rr_cluster_start == ex_cluster_end) ||
 	    (rr_cluster_start == ex_cluster_start)) {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 4637af036d9c..25d8c9781ad9 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -252,7 +252,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		fatal = ext4_journal_get_write_access(handle, bh2);
 	}
 	ext4_lock_group(sb, block_group);
-	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+	cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data);
 	if (fatal || !cleared) {
 		ext4_unlock_group(sb, block_group);
 		goto out;
@@ -358,7 +358,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
-	unsigned int freei, avefreei;
+	unsigned int freei, avefreei, grp_free;
 	ext4_fsblk_t freeb, avefreec;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
@@ -477,8 +477,8 @@ fallback_retry:
 	for (i = 0; i < ngroups; i++) {
 		grp = (parent_group + i) % ngroups;
 		desc = ext4_get_group_desc(sb, grp, NULL);
-		if (desc && ext4_free_inodes_count(sb, desc) &&
-		    ext4_free_inodes_count(sb, desc) >= avefreei) {
+		grp_free = ext4_free_inodes_count(sb, desc);
+		if (desc && grp_free && grp_free >= avefreei) {
 			*group = grp;
 			return 0;
 		}
@@ -618,7 +618,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	 */
 	down_read(&grp->alloc_sem);
 	ext4_lock_group(sb, group);
-	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
+	if (ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data)) {
 		/* not a free inode */
 		retval = 1;
 		goto err_ret;
@@ -885,8 +885,12 @@ got:
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		goto fail;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index aa8efa6572d6..feaa82fe629d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -71,6 +71,9 @@ static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
 static int __ext4_journalled_writepage(struct page *page, unsigned int len);
 static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
+static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+		struct inode *inode, struct page *page, loff_t from,
+		loff_t length, int flags);
 
 /*
  * Test whether an inode is a fast symlink.
@@ -2759,7 +2762,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	if (!io_end || !size)
 		goto out;
 
-	ext_debug("ext4_end_io_dio(): io_end 0x%p"
+	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
  		  iocb->private, io_end->inode->i_ino, iocb, offset,
 		  size);
@@ -3160,7 +3163,7 @@ int ext4_discard_partial_page_buffers(handle_t *handle,
  *
  * Returns zero on sucess or negative on failure.
  */
-int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
 		struct inode *inode, struct page *page, loff_t from,
 		loff_t length, int flags)
 {
@@ -3300,126 +3303,6 @@ next:
 	return err;
 }
 
-/*
- * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
- * up to the end of the block which corresponds to `from'.
- * This required during truncate. We need to physically zero the tail end
- * of that block so it doesn't yield old data if the file is later grown.
- */
-int ext4_block_truncate_page(handle_t *handle,
-		struct address_space *mapping, loff_t from)
-{
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned length;
-	unsigned blocksize;
-	struct inode *inode = mapping->host;
-
-	blocksize = inode->i_sb->s_blocksize;
-	length = blocksize - (offset & (blocksize - 1));
-
-	return ext4_block_zero_page_range(handle, mapping, from, length);
-}
-
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-int ext4_block_zero_page_range(handle_t *handle,
-		struct address_space *mapping, loff_t from, loff_t length)
-{
-	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
-	ext4_lblk_t iblock;
-	struct inode *inode = mapping->host;
-	struct buffer_head *bh;
-	struct page *page;
-	int err = 0;
-
-	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
-				   mapping_gfp_mask(mapping) & ~__GFP_FS);
-	if (!page)
-		return -ENOMEM;
-
-	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
-
-	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
-
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, blocksize, 0);
-
-	/* Find the buffer that contains "offset" */
-	bh = page_buffers(page);
-	pos = blocksize;
-	while (offset >= pos) {
-		bh = bh->b_this_page;
-		iblock++;
-		pos += blocksize;
-	}
-
-	err = 0;
-	if (buffer_freed(bh)) {
-		BUFFER_TRACE(bh, "freed: skip");
-		goto unlock;
-	}
-
-	if (!buffer_mapped(bh)) {
-		BUFFER_TRACE(bh, "unmapped");
-		ext4_get_block(inode, iblock, bh, 0);
-		/* unmapped? It's a hole - nothing to do */
-		if (!buffer_mapped(bh)) {
-			BUFFER_TRACE(bh, "still unmapped");
-			goto unlock;
-		}
-	}
-
-	/* Ok, it's mapped. Make sure it's up-to-date */
-	if (PageUptodate(page))
-		set_buffer_uptodate(bh);
-
-	if (!buffer_uptodate(bh)) {
-		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
-		wait_on_buffer(bh);
-		/* Uhhuh. Read error. Complain and punt. */
-		if (!buffer_uptodate(bh))
-			goto unlock;
-	}
-
-	if (ext4_should_journal_data(inode)) {
-		BUFFER_TRACE(bh, "get write access");
-		err = ext4_journal_get_write_access(handle, bh);
-		if (err)
-			goto unlock;
-	}
-
-	zero_user(page, offset, length);
-
-	BUFFER_TRACE(bh, "zeroed end of block");
-
-	err = 0;
-	if (ext4_should_journal_data(inode)) {
-		err = ext4_handle_dirty_metadata(handle, inode, bh);
-	} else
-		mark_buffer_dirty(bh);
-
-unlock:
-	unlock_page(page);
-	page_cache_release(page);
-	return err;
-}
-
 int ext4_can_truncate(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode))
@@ -4646,9 +4529,19 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		return 0;
 	if (is_journal_aborted(journal))
 		return -EROFS;
+	/* We have to allocate physical blocks for delalloc blocks
+	 * before flushing journal. otherwise delalloc blocks can not
+	 * be allocated any more. even more truncate on delalloc blocks
+	 * could trigger BUG by flushing delalloc blocks in journal.
+	 * There is no delalloc block in non-journal data mode.
+	 */
+	if (val && test_opt(inode->i_sb, DELALLOC)) {
+		err = ext4_alloc_da_blocks(inode);
+		if (err < 0)
+			return err;
+	}
 
 	jbd2_journal_lock_updates(journal);
-	jbd2_journal_flush(journal);
 
 	/*
 	 * OK, there are no updates running now, and all cached data is
@@ -4660,8 +4553,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 
 	if (val)
 		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
-	else
+	else {
+		jbd2_journal_flush(journal);
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
+	}
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e87a932b073b..6eee25591b81 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -18,6 +18,8 @@
 #include "ext4_jbd2.h"
 #include "ext4.h"
 
+#define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
@@ -186,19 +188,22 @@ setversion_out:
 		if (err)
 			return err;
 
-		if (get_user(n_blocks_count, (__u32 __user *)arg))
-			return -EFAULT;
+		if (get_user(n_blocks_count, (__u32 __user *)arg)) {
+			err = -EFAULT;
+			goto group_extend_out;
+		}
 
 		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 			ext4_msg(sb, KERN_ERR,
 				 "Online resizing not supported with bigalloc");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto group_extend_out;
 		}
 
 		err = mnt_want_write_file(filp);
 		if (err)
-			return err;
+			goto group_extend_out;
 
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
@@ -209,8 +214,8 @@ setversion_out:
 		if (err == 0)
 			err = err2;
 		mnt_drop_write_file(filp);
+group_extend_out:
 		ext4_resize_end(sb);
-
 		return err;
 	}
 
@@ -251,8 +256,7 @@ setversion_out:
 		err = ext4_move_extents(filp, donor_filp, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
 		mnt_drop_write_file(filp);
-		if (me.moved_len > 0)
-			file_remove_suid(donor_filp);
+		mnt_drop_write(filp->f_path.mnt);
 
 		if (copy_to_user((struct move_extent __user *)arg,
 				 &me, sizeof(me)))
@@ -271,19 +275,22 @@ mext_out:
 			return err;
 
 		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
-				sizeof(input)))
-			return -EFAULT;
+				sizeof(input))) {
+			err = -EFAULT;
+			goto group_add_out;
+		}
 
 		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 			ext4_msg(sb, KERN_ERR,
 				 "Online resizing not supported with bigalloc");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto group_add_out;
 		}
 
 		err = mnt_want_write_file(filp);
 		if (err)
-			return err;
+			goto group_add_out;
 
 		err = ext4_group_add(sb, &input);
 		if (EXT4_SB(sb)->s_journal) {
@@ -294,8 +301,8 @@ mext_out:
 		if (err == 0)
 			err = err2;
 		mnt_drop_write_file(filp);
+group_add_out:
 		ext4_resize_end(sb);
-
 		return err;
 	}
 
@@ -335,6 +342,60 @@ mext_out:
 		return err;
 	}
 
+	case EXT4_IOC_RESIZE_FS: {
+		ext4_fsblk_t n_blocks_count;
+		struct super_block *sb = inode->i_sb;
+		int err = 0, err2 = 0;
+
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online resizing not (yet) supported with bigalloc");
+			return -EOPNOTSUPP;
+		}
+
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+			       EXT4_FEATURE_INCOMPAT_META_BG)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online resizing not (yet) supported with meta_bg");
+			return -EOPNOTSUPP;
+		}
+
+		if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
+				   sizeof(__u64))) {
+			return -EFAULT;
+		}
+
+		if (n_blocks_count > MAX_32_NUM &&
+		    !EXT4_HAS_INCOMPAT_FEATURE(sb,
+					       EXT4_FEATURE_INCOMPAT_64BIT)) {
+			ext4_msg(sb, KERN_ERR,
+				 "File system only supports 32-bit block numbers");
+			return -EOPNOTSUPP;
+		}
+
+		err = ext4_resize_begin(sb);
+		if (err)
+			return err;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			goto resizefs_out;
+
+		err = ext4_resize_fs(sb, n_blocks_count);
+		if (EXT4_SB(sb)->s_journal) {
+			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		}
+		if (err == 0)
+			err = err2;
+		mnt_drop_write(filp->f_path.mnt);
+resizefs_out:
+		ext4_resize_end(sb);
+		return err;
+	}
+
 	case FITRIM:
 	{
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
@@ -433,6 +494,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	}
 	case EXT4_IOC_MOVE_EXT:
 	case FITRIM:
+	case EXT4_IOC_RESIZE_FS:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index e2d8be8f28bf..cb990b21c698 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3671,7 +3671,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 
-	trace_ext4_mb_release_group_pa(pa);
+	trace_ext4_mb_release_group_pa(sb, pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
 	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 996780ab4f4e..f9d948f0eb86 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -134,6 +134,172 @@ static int verify_group_input(struct super_block *sb,
 	return err;
 }
 
+/*
+ * ext4_new_flex_group_data is used by 64bit-resize interface to add a flex
+ * group each time.
+ */
+struct ext4_new_flex_group_data {
+	struct ext4_new_group_data *groups;	/* new_group_data for groups
+						   in the flex group */
+	__u16 *bg_flags;			/* block group flags of groups
+						   in @groups */
+	ext4_group_t count;			/* number of groups in @groups
+						 */
+};
+
+/*
+ * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
+ * @flexbg_size.
+ *
+ * Returns NULL on failure otherwise address of the allocated structure.
+ */
+static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
+{
+	struct ext4_new_flex_group_data *flex_gd;
+
+	flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
+	if (flex_gd == NULL)
+		goto out3;
+
+	flex_gd->count = flexbg_size;
+
+	flex_gd->groups = kmalloc(sizeof(struct ext4_new_group_data) *
+				  flexbg_size, GFP_NOFS);
+	if (flex_gd->groups == NULL)
+		goto out2;
+
+	flex_gd->bg_flags = kmalloc(flexbg_size * sizeof(__u16), GFP_NOFS);
+	if (flex_gd->bg_flags == NULL)
+		goto out1;
+
+	return flex_gd;
+
+out1:
+	kfree(flex_gd->groups);
+out2:
+	kfree(flex_gd);
+out3:
+	return NULL;
+}
+
+static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
+{
+	kfree(flex_gd->bg_flags);
+	kfree(flex_gd->groups);
+	kfree(flex_gd);
+}
+
+/*
+ * ext4_alloc_group_tables() allocates block bitmaps, inode bitmaps
+ * and inode tables for a flex group.
+ *
+ * This function is used by 64bit-resize.  Note that this function allocates
+ * group tables from the 1st group of groups contained by @flexgd, which may
+ * be a partial of a flex group.
+ *
+ * @sb: super block of fs to which the groups belongs
+ */
+static void ext4_alloc_group_tables(struct super_block *sb,
+				struct ext4_new_flex_group_data *flex_gd,
+				int flexbg_size)
+{
+	struct ext4_new_group_data *group_data = flex_gd->groups;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	ext4_fsblk_t start_blk;
+	ext4_fsblk_t last_blk;
+	ext4_group_t src_group;
+	ext4_group_t bb_index = 0;
+	ext4_group_t ib_index = 0;
+	ext4_group_t it_index = 0;
+	ext4_group_t group;
+	ext4_group_t last_group;
+	unsigned overhead;
+
+	BUG_ON(flex_gd->count == 0 || group_data == NULL);
+
+	src_group = group_data[0].group;
+	last_group  = src_group + flex_gd->count - 1;
+
+	BUG_ON((flexbg_size > 1) && ((src_group & ~(flexbg_size - 1)) !=
+	       (last_group & ~(flexbg_size - 1))));
+next_group:
+	group = group_data[0].group;
+	start_blk = ext4_group_first_block_no(sb, src_group);
+	last_blk = start_blk + group_data[src_group - group].blocks_count;
+
+	overhead = ext4_bg_has_super(sb, src_group) ?
+		   (1 + ext4_bg_num_gdb(sb, src_group) +
+		    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+
+	start_blk += overhead;
+
+	BUG_ON(src_group >= group_data[0].group + flex_gd->count);
+	/* We collect contiguous blocks as much as possible. */
+	src_group++;
+	for (; src_group <= last_group; src_group++)
+		if (!ext4_bg_has_super(sb, src_group))
+			last_blk += group_data[src_group - group].blocks_count;
+		else
+			break;
+
+	/* Allocate block bitmaps */
+	for (; bb_index < flex_gd->count; bb_index++) {
+		if (start_blk >= last_blk)
+			goto next_group;
+		group_data[bb_index].block_bitmap = start_blk++;
+		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
+		group -= group_data[0].group;
+		group_data[group].free_blocks_count--;
+		if (flexbg_size > 1)
+			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+	}
+
+	/* Allocate inode bitmaps */
+	for (; ib_index < flex_gd->count; ib_index++) {
+		if (start_blk >= last_blk)
+			goto next_group;
+		group_data[ib_index].inode_bitmap = start_blk++;
+		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
+		group -= group_data[0].group;
+		group_data[group].free_blocks_count--;
+		if (flexbg_size > 1)
+			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+	}
+
+	/* Allocate inode tables */
+	for (; it_index < flex_gd->count; it_index++) {
+		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+			goto next_group;
+		group_data[it_index].inode_table = start_blk;
+		ext4_get_group_no_and_offset(sb, start_blk, &group, NULL);
+		group -= group_data[0].group;
+		group_data[group].free_blocks_count -=
+					EXT4_SB(sb)->s_itb_per_group;
+		if (flexbg_size > 1)
+			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+
+		start_blk += EXT4_SB(sb)->s_itb_per_group;
+	}
+
+	if (test_opt(sb, DEBUG)) {
+		int i;
+		group = group_data[0].group;
+
+		printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
+		       "%d groups, flexbg size is %d:\n", flex_gd->count,
+		       flexbg_size);
+
+		for (i = 0; i < flex_gd->count; i++) {
+			printk(KERN_DEBUG "adding %s group %u: %u "
+			       "blocks (%d free)\n",
+			       ext4_bg_has_super(sb, group + i) ? "normal" :
+			       "no-super", group + i,
+			       group_data[i].blocks_count,
+			       group_data[i].free_blocks_count);
+		}
+	}
+}
+
 static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
 				  ext4_fsblk_t blk)
 {
@@ -179,131 +345,250 @@ static int extend_or_restart_transaction(handle_t *handle, int thresh)
 }
 
 /*
- * Set up the block and inode bitmaps, and the inode table for the new group.
+ * set_flexbg_block_bitmap() mark @count blocks starting from @block used.
+ *
+ * Helper function for ext4_setup_new_group_blocks() which set .
+ *
+ * @sb: super block
+ * @handle: journal handle
+ * @flex_gd: flex group data
+ */
+static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
+			struct ext4_new_flex_group_data *flex_gd,
+			ext4_fsblk_t block, ext4_group_t count)
+{
+	ext4_group_t count2;
+
+	ext4_debug("mark blocks [%llu/%u] used\n", block, count);
+	for (count2 = count; count > 0; count -= count2, block += count2) {
+		ext4_fsblk_t start;
+		struct buffer_head *bh;
+		ext4_group_t group;
+		int err;
+
+		ext4_get_group_no_and_offset(sb, block, &group, NULL);
+		start = ext4_group_first_block_no(sb, group);
+		group -= flex_gd->groups[0].group;
+
+		count2 = sb->s_blocksize * 8 - (block - start);
+		if (count2 > count)
+			count2 = count;
+
+		if (flex_gd->bg_flags[group] & EXT4_BG_BLOCK_UNINIT) {
+			BUG_ON(flex_gd->count > 1);
+			continue;
+		}
+
+		err = extend_or_restart_transaction(handle, 1);
+		if (err)
+			return err;
+
+		bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap);
+		if (!bh)
+			return -EIO;
+
+		err = ext4_journal_get_write_access(handle, bh);
+		if (err)
+			return err;
+		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block,
+			   block - start, count2);
+		ext4_set_bits(bh->b_data, block - start, count2);
+
+		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		if (unlikely(err))
+			return err;
+		brelse(bh);
+	}
+
+	return 0;
+}
+
+/*
+ * Set up the block and inode bitmaps, and the inode table for the new groups.
  * This doesn't need to be part of the main transaction, since we are only
  * changing blocks outside the actual filesystem.  We still do journaling to
  * ensure the recovery is correct in case of a failure just after resize.
  * If any part of this fails, we simply abort the resize.
+ *
+ * setup_new_flex_group_blocks handles a flex group as follow:
+ *  1. copy super block and GDT, and initialize group tables if necessary.
+ *     In this step, we only set bits in blocks bitmaps for blocks taken by
+ *     super block and GDT.
+ *  2. allocate group tables in block bitmaps, that is, set bits in block
+ *     bitmap for blocks taken by group tables.
  */
-static int setup_new_group_blocks(struct super_block *sb,
-				  struct ext4_new_group_data *input)
+static int setup_new_flex_group_blocks(struct super_block *sb,
+				struct ext4_new_flex_group_data *flex_gd)
 {
+	int group_table_count[] = {1, 1, EXT4_SB(sb)->s_itb_per_group};
+	ext4_fsblk_t start;
+	ext4_fsblk_t block;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_fsblk_t start = ext4_group_first_block_no(sb, input->group);
-	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
-		le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
-	unsigned long gdblocks = ext4_bg_num_gdb(sb, input->group);
-	struct buffer_head *bh;
+	struct ext4_super_block *es = sbi->s_es;
+	struct ext4_new_group_data *group_data = flex_gd->groups;
+	__u16 *bg_flags = flex_gd->bg_flags;
 	handle_t *handle;
-	ext4_fsblk_t block;
-	ext4_grpblk_t bit;
-	int i;
-	int err = 0, err2;
+	ext4_group_t group, count;
+	struct buffer_head *bh = NULL;
+	int reserved_gdb, i, j, err = 0, err2;
+
+	BUG_ON(!flex_gd->count || !group_data ||
+	       group_data[0].group != sbi->s_groups_count);
+
+	reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
 
 	/* This transaction may be extended/restarted along the way */
 	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
-
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	BUG_ON(input->group != sbi->s_groups_count);
+	group = group_data[0].group;
+	for (i = 0; i < flex_gd->count; i++, group++) {
+		unsigned long gdblocks;
 
-	/* Copy all of the GDT blocks into the backup in this group */
-	for (i = 0, bit = 1, block = start + 1;
-	     i < gdblocks; i++, block++, bit++) {
-		struct buffer_head *gdb;
+		gdblocks = ext4_bg_num_gdb(sb, group);
+		start = ext4_group_first_block_no(sb, group);
 
-		ext4_debug("update backup group %#04llx (+%d)\n", block, bit);
-		err = extend_or_restart_transaction(handle, 1);
-		if (err)
-			goto exit_journal;
+		/* Copy all of the GDT blocks into the backup in this group */
+		for (j = 0, block = start + 1; j < gdblocks; j++, block++) {
+			struct buffer_head *gdb;
 
-		gdb = sb_getblk(sb, block);
-		if (!gdb) {
-			err = -EIO;
-			goto exit_journal;
-		}
-		if ((err = ext4_journal_get_write_access(handle, gdb))) {
+			ext4_debug("update backup group %#04llx\n", block);
+			err = extend_or_restart_transaction(handle, 1);
+			if (err)
+				goto out;
+
+			gdb = sb_getblk(sb, block);
+			if (!gdb) {
+				err = -EIO;
+				goto out;
+			}
+
+			err = ext4_journal_get_write_access(handle, gdb);
+			if (err) {
+				brelse(gdb);
+				goto out;
+			}
+			memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data,
+			       gdb->b_size);
+			set_buffer_uptodate(gdb);
+
+			err = ext4_handle_dirty_metadata(handle, NULL, gdb);
+			if (unlikely(err)) {
+				brelse(gdb);
+				goto out;
+			}
 			brelse(gdb);
-			goto exit_journal;
 		}
-		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
-		set_buffer_uptodate(gdb);
-		err = ext4_handle_dirty_metadata