ext4: add new online resize interface

This patch adds new online resize interface, whose input argument is a
64-bit integer indicating how many blocks there are in the resized fs.

In new resize impelmentation, all work like allocating group tables
are done by kernel side, so the new resize interface can support
flex_bg feature and prepares ground for suppoting resize with features
like bigalloc and exclude bitmap. Besides these, user-space tools just
passes in the new number of blocks.

We delay initializing the bitmaps and inode tables of added groups if
possible and add multi groups (a flex groups) each time, so new resize
is very fast like mkfs.

Signed-off-by: Yongqiang Yang <xiaoqiangnk@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

4 files changed, 243 insertions, 0 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/ext4.h b/fs/ext4/ext4.h
index 05058e2b7f4f..4bc0e82a9054 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -583,6 +583,7 @@ enum {
  /* 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)
 /*
@@ -1929,6 +1930,7 @@ 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/ioctl.c b/fs/ext4/ioctl.c
index ff1aab7cd6e8..c1a98804a383 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;
@@ -329,6 +331,60 @@ 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);
@@ -427,6 +483,7 @@ 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/resize.c b/fs/ext4/resize.c
index dac23561f3eb..5fe2a013ee65 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1430,6 +1430,70 @@ exit:
 	return err;
 }
 
+static int ext4_setup_next_flex_gd(struct super_block *sb,
+				    struct ext4_new_flex_group_data *flex_gd,
+				    ext4_fsblk_t n_blocks_count,
+				    unsigned long flexbg_size)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct ext4_new_group_data *group_data = flex_gd->groups;
+	ext4_fsblk_t o_blocks_count;
+	ext4_group_t n_group;
+	ext4_group_t group;
+	ext4_group_t last_group;
+	ext4_grpblk_t last;
+	ext4_grpblk_t blocks_per_group;
+	unsigned long i;
+
+	blocks_per_group = EXT4_BLOCKS_PER_GROUP(sb);
+
+	o_blocks_count = ext4_blocks_count(es);
+
+	if (o_blocks_count == n_blocks_count)
+		return 0;
+
+	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
+	BUG_ON(last);
+	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);
+
+	last_group = group | (flexbg_size - 1);
+	if (last_group > n_group)
+		last_group = n_group;
+
+	flex_gd->count = last_group - group + 1;
+
+	for (i = 0; i < flex_gd->count; i++) {
+		int overhead;
+
+		group_data[i].group = group + i;
+		group_data[i].blocks_count = blocks_per_group;
+		overhead = ext4_bg_has_super(sb, group + i) ?
+			   (1 + ext4_bg_num_gdb(sb, group + i) +
+			    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+		group_data[i].free_blocks_count = blocks_per_group - overhead;
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+			flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
+					       EXT4_BG_INODE_UNINIT;
+		else
+			flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED;
+	}
+
+	if (last_group == n_group &&
+	    EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+		/* We need to initialize block bitmap of last group. */
+		flex_gd->bg_flags[i - 1] &= ~EXT4_BG_BLOCK_UNINIT;
+
+	if ((last_group == n_group) && (last != blocks_per_group - 1)) {
+		group_data[i - 1].blocks_count = last + 1;
+		group_data[i - 1].free_blocks_count -= blocks_per_group-
+					last - 1;
+	}
+
+	return 1;
+}
+
 /* Add group descriptor data to an existing or new group descriptor block.
  * Ensure we handle all possible error conditions _before_ we start modifying
  * the filesystem, because we cannot abort the transaction and not have it
@@ -1827,3 +1891,116 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 exit_put:
 	return err;
 } /* ext4_group_extend */
+
+/*
+ * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count
+ *
+ * @sb: super block of the fs to be resized
+ * @n_blocks_count: the number of blocks resides in the resized fs
+ */
+int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
+{
+	struct ext4_new_flex_group_data *flex_gd = NULL;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	struct buffer_head *bh;
+	struct inode *resize_inode;
+	ext4_fsblk_t o_blocks_count;
+	ext4_group_t o_group;
+	ext4_group_t n_group;
+	ext4_grpblk_t offset;
+	unsigned long n_desc_blocks;
+	unsigned long o_desc_blocks;
+	unsigned long desc_blocks;
+	int err = 0, flexbg_size = 1;
+
+	o_blocks_count = ext4_blocks_count(es);
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT4-fs: resizing filesystem from %llu "
+		       "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+
+	if (n_blocks_count < o_blocks_count) {
+		/* On-line shrinking not supported */
+		ext4_warning(sb, "can't shrink FS - resize aborted");
+		return -EINVAL;
+	}
+
+	if (n_blocks_count == o_blocks_count)
+		/* Nothing need to do */
+		return 0;
+
+	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
+	ext4_get_group_no_and_offset(sb, o_blocks_count, &o_group, &offset);
+
+	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
+			EXT4_DESC_PER_BLOCK(sb);
+	o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
+			EXT4_DESC_PER_BLOCK(sb);
+	desc_blocks = n_desc_blocks - o_desc_blocks;
+
+	if (desc_blocks &&
+	    (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) ||
+	     le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) {
+		ext4_warning(sb, "No reserved GDT blocks, can't resize");
+		return -EPERM;
+	}
+
+	resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
+	if (IS_ERR(resize_inode)) {
+		ext4_warning(sb, "Error opening resize inode");
+		return PTR_ERR(resize_inode);
+	}
+
+	/* See if the device is actually as big as what was requested */
+	bh = sb_bread(sb, n_blocks_count - 1);
+	if (!bh) {
+		ext4_warning(sb, "can't read last block, resize aborted");
+		return -ENOSPC;
+	}
+	brelse(bh);
+
+	if (offset != 0) {
+		/* extend the last group */
+		ext4_grpblk_t add;
+		add = EXT4_BLOCKS_PER_GROUP(sb) - offset;
+		err = ext4_group_extend_no_check(sb, o_blocks_count, add);
+		if (err)
+			goto out;
+	}
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+	    es->s_log_groups_per_flex)
+		flexbg_size = 1 << es->s_log_groups_per_flex;
+
+	o_blocks_count = ext4_blocks_count(es);
+	if (o_blocks_count == n_blocks_count)
+		goto out;
+
+	flex_gd = alloc_flex_gd(flexbg_size);
+	if (flex_gd == NULL) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Add flex groups. Note that a regular group is a
+	 * flex group with 1 group.
+	 */
+	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
+					      flexbg_size)) {
+		ext4_alloc_group_tables(sb, flex_gd, flexbg_size);
+		err = ext4_flex_group_add(sb, resize_inode, flex_gd);
+		if (unlikely(err))
+			break;
+	}
+
+out:
+	if (flex_gd)
+		free_flex_gd(flex_gd);
+
+	iput(resize_inode);
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT4-fs: resized filesystem from %llu "
+		       "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+	return err;
+}