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)
{
}
/*
- * 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(handle, NULL, gdb);
- if (unlikely(err)) {
- brelse(gdb);
- goto exit_journal;
+
+ /* Zero out all of the reserved backup group descriptor
+ * table blocks
+ */
+ if (ext4_bg_has_super(sb, group)) {
+ err = sb_issue_zeroout(sb, gdblocks + start + 1,
+ reserved_gdb, GFP_NOFS);
+ if (err)
+ goto out;
}
- brelse(gdb);
- }
- /* Zero out all of the reserved backup group descriptor table blocks */
- ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
- block, sbi->s_itb_per_group);
- err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
- GFP_NOFS);
- if (err)
- goto exit_journal;
+ /* Initialize group tables of the grop @group */
+ if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED))
+ goto handle_bb;
- err = extend_or_restart_transaction(handle, 2);
- if (err)
- goto exit_journal;
+ /* Zero out all of the inode table blocks */
+ block = group_data[i].inode_table;
+ ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
+ block, sbi->s_itb_per_group);
+ err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group,
+ GFP_NOFS);
+ if (err)
+ goto out;
- bh = bclean(handle, sb, input->block_bitmap);
- if (IS_ERR(bh)) {
- err = PTR_ERR(bh);
- goto exit_journal;
- }
+handle_bb:
+ if (bg_flags[i] & EXT4_BG_BLOCK_UNINIT)
+ goto handle_ib;
- if (ext4_bg_has_super(sb, input->group)) {
- ext4_debug("mark backup group tables %#04llx (+0)\n", start);
- ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb + 1);
- }
+ /* Initialize block bitmap of the @group */
+ block = group_data[i].block_bitmap;
+ err = extend_or_restart_transaction(handle, 1);
+ if (err)
+ goto out;
- ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
- input->block_bitmap - start);
- ext4_set_bit(input->block_bitmap - start, bh->b_data);
- ext4_debug("mark inode bitmap %#04llx (+%llu)\n", input->inode_bitmap,
- input->inode_bitmap - start);
- ext4_set_bit(input->inode_bitmap - start, bh->b_data);
-
- /* Zero out all of the inode table blocks */
- block = input->inode_table;
- ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
- block, sbi->s_itb_per_group);
- err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
- if (err)
- goto exit_bh;
- ext4_set_bits(bh->b_data, input->inode_table - start,
- sbi->s_itb_per_group);
+ bh = bclean(handle, sb, block);
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
+ goto out;
+ }
+ if (ext4_bg_has_super(sb, group)) {
+ ext4_debug("mark backup superblock %#04llx (+0)\n",
+ start);
+ ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb +
+ 1);
+ }
+ ext4_mark_bitmap_end(group_data[i].blocks_count,
+ sb->s_blocksize * 8, bh->b_data);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ goto out;
+ brelse(bh);
+handle_ib:
+ if (bg_flags[i] & EXT4_BG_INODE_UNINIT)
+ continue;
- ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8,
- bh->b_data);
- err = ext4_handle_dirty_metadata(handle, NULL, bh);
- if (unlikely(err)) {
- ext4_std_error(sb, err);
- goto exit_bh;
+ /* Initialize inode bitmap of the @group */
+ block = group_data[i].inode_bitmap;
+ err = extend_or_restart_transaction(handle, 1);
+ if (err)
+ goto out;
+ /* Mark unused entries in inode bitmap used */
+ bh = bclean(handle, sb, block);
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
+ goto out;
+ }
+
+ ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
+ sb->s_blocksize * 8, bh->b_data);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ goto out;
+ brelse(bh);
}
- brelse(bh);
- /* Mark unused entries in inode bitmap used */
- ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
- input->inode_bitmap, input->inode_bitmap - start);
- if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
- err = PTR_ERR(bh);
- goto exit_journal;
+ bh = NULL;
+
+ /* Mark group tables in block bitmap */
+ for (j = 0; j < GROUP_TABLE_COUNT; j++) {
+ count = group_table_count[j];
+ start = (&group_data[0].block_bitmap)[j];
+ block = start;
+ for (i = 1; i < flex_gd->count; i++) {
+ block += group_table_count[j];
+ if (block == (&group_data[i].block_bitmap)[j]) {
+ count += group_table_count[j];
+ continue;
+ }
+ err = set_flexbg_block_bitmap(sb, handle,
+ flex_gd, start, count);
+ if (err)
+ goto out;
+ count = group_table_count[j];
+ start = group_data[i].block_bitmap;
+ block = start;
+ }
+
+ if (count) {
+ err = set_flexbg_block_bitmap(sb, handle,
+ flex_gd, start, count);
+ if (err)
+ goto out;
+ }
}
- ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
- bh->b_data);
- err = ext4_handle_dirty_metadata(handle, NULL, bh);
- if (unlikely(err))
- ext4_std_error(sb, err);
-exit_bh:
+out:
brelse(bh);
-
-exit_journal:
- if ((err2 = ext4_journal_stop(handle)) && !err)
+ err2 = ext4_journal_stop(handle);
+ if (err2 && !err)
err = err2;
return err;
* groups in current filesystem that have BACKUPS, or -ve error code.
*/
static int verify_reserved_gdb(struct super_block *sb,
+ ext4_group_t end,
struct buffer_head *primary)
{
const ext4_fsblk_t blk = primary->b_blocknr;
- const ext4_group_t end = EXT4_SB(sb)->s_groups_count;
unsigned three = 1;
unsigned five = 5;
unsigned seven = 7;
if (!gdb_bh)
return -EIO;
- gdbackups = verify_reserved_gdb(sb, gdb_bh);
+ gdbackups = verify_reserved_gdb(sb, group, gdb_bh);
if (gdbackups < 0) {
err = gdbackups;
goto exit_bh;
err = -EIO;
goto exit_bh;
}
- if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
+ gdbackups = verify_reserved_gdb(sb, group, primary[res]);
+ if (gdbackups < 0) {
brelse(primary[res]);
err = gdbackups;
goto exit_bh;
}
}
+/*
+ * ext4_add_new_descs() adds @count group descriptor of groups
+ * starting at @group
+ *
+ * @handle: journal handle
+ * @sb: super block
+ * @group: the group no. of the first group desc to be added
+ * @resize_inode: the resize inode
+ * @count: number of group descriptors to be added
+ */
+static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
+ ext4_group_t group, struct inode *resize_inode,
+ ext4_group_t count)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head *gdb_bh;
+ int i, gdb_off, gdb_num, err = 0;
+
+ for (i = 0; i < count; i++, group++) {
+ int reserved_gdb = ext4_bg_has_super(sb, group) ?
+ le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
+
+ gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
+ gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
+
+ /*
+ * We will only either add reserved group blocks to a backup group
+ * or remove reserved blocks for the first group in a new group block.
+ * Doing both would be mean more complex code, and sane people don't
+ * use non-sparse filesystems anymore. This is already checked above.
+ */
+ if (gdb_off) {
+ gdb_bh = sbi->s_group_desc[gdb_num];
+ err = ext4_journal_get_write_access(handle, gdb_bh);
+
+ if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
+ err = reserve_backup_gdb(handle, resize_inode, group);
+ } else
+ err = add_new_gdb(handle, resize_inode, group);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+/*
+ * ext4_setup_new_descs() will set up the group descriptor descriptors of a flex bg
+ */
+static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
+ struct ext4_new_flex_group_data *flex_gd)
+{
+ struct ext4_new_group_data *group_data = flex_gd->groups;
+ struct ext4_group_desc *gdp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct buffer_head *gdb_bh;
+ ext4_group_t group;
+ __u16 *bg_flags = flex_gd->bg_flags;
+ int i, gdb_off, gdb_num, err = 0;
+
+
+ for (i = 0; i < flex_gd->count; i++, group_data++, bg_flags++) {
+ group = group_data->group;
+
+ gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
+ gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
+
+ /*
+ * get_write_access() has been called on gdb_bh by ext4_add_new_desc().
+ */
+ gdb_bh = sbi->s_group_desc[gdb_num];
+ /* Update group descriptor block for new group */
+ gdp = (struct ext4_group_desc *)((char *)gdb_bh->b_data +
+ gdb_off * EXT4_DESC_SIZE(sb));
+
+ memset(gdp, 0, EXT4_DESC_SIZE(sb));
+ ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap);
+ ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
+ ext4_inode_table_set(sb, gdp, group_data->inode_table);
+ ext4_free_group_clusters_set(sb, gdp,
+ EXT4_B2C(sbi, group_data->free_blocks_count));
+ ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
+ gdp->bg_flags = cpu_to_le16(*bg_flags);
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+
+ err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
+ if (unlikely(err)) {
+ ext4_std_error(sb, err);
+ break;
+ }
+
+ /*
+ * We can allocate memory for mb_alloc based on the new group
+ * descriptor
+ */
+ err = ext4_mb_add_groupinfo(sb, group, gdp);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+/*
+ * ext4_update_super() updates the super block so that the newly added
+ * groups can be seen by the filesystem.
+ *
+ * @sb: super block
+ * @flex_gd: new added groups
+ */
+static void ext4_update_super(struct super_block *sb,
+ struct ext4_new_flex_group_data *flex_gd)
+{
+ ext4_fsblk_t blocks_count = 0;
+ ext4_fsblk_t free_blocks = 0;
+ ext4_fsblk_t reserved_blocks = 0;
+ struct ext4_new_group_data *group_data = flex_gd->groups;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ int i;
+
+ BUG_ON(flex_gd->count == 0 || group_data == NULL);
+ /*
+ * Make the new blocks and inodes valid next. We do this before
+ * increasing the group count so that once the group is enabled,
+ * all of its blocks and inodes are already valid.
+ *
+ * We always allocate group-by-group, then block-by-block or
+ * inode-by-inode within a group, so enabling these
+ * blocks/inodes before the group is live won't actually let us
+ * allocate the new space yet.
+ */
+ for (i = 0; i < flex_gd->count; i++) {
+ blocks_count += group_data[i].blocks_count;
+ free_blocks += group_data[i].free_blocks_count;
+ }
+
+ reserved_blocks = ext4_r_blocks_count(es) * 100;
+ do_div(reserved_blocks, ext4_blocks_count(es));
+ reserved_blocks *= blocks_count;
+ do_div(reserved_blocks, 100);
+
+ ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
+ le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
+ flex_gd->count);
+
+ /*
+ * We need to protect s_groups_count against other CPUs seeing
+ * inconsistent state in the superblock.
+ *
+ * The precise rules we use are:
+ *
+ * * Writers must perform a smp_wmb() after updating all
+ * dependent data and before modifying the groups count
+ *
+ * * Readers must perform an smp_rmb() after reading the groups
+ * count and before reading any dependent data.
+ *
+ * NB. These rules can be relaxed when checking the group count
+ * while freeing data, as we can only allocate from a block
+ * group after serialising against the group count, and we can
+ * only then free after serialising in turn against that
+ * allocation.
+ */
+ smp_wmb();
+
+ /* Update the global fs size fields */
+ sbi->s_groups_count += flex_gd->count;
+
+ /* Update the reserved block counts only once the new group is
+ * active. */
+ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
+ reserved_blocks);
+
+ /* Update the free space counts */
+ percpu_counter_add(&sbi->s_freeclusters_counter,
+ EXT4_B2C(sbi, free_blocks));
+ percpu_counter_add(&sbi->s_freeinodes_counter,
+ EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+ sbi->s_log_groups_per_flex) {
+ ext4_group_t flex_group;
+ flex_group = ext4_flex_group(sbi, group_data[0].group);
+ atomic_add(EXT4_B2C(sbi, free_blocks),
+ &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
+ &sbi->s_flex_groups[flex_group].free_inodes);
+ }
+
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG "EXT4-fs: added group %u:"
+ "%llu blocks(%llu free %llu reserved)\n", flex_gd->count,
+ blocks_count, free_blocks, reserved_blocks);
+}
+
+/* Add a flex group to an fs. Ensure we handle all possible error conditions
+ * _before_ we start modifying the filesystem, because we cannot abort the
+ * transaction and not have it write the data to disk.
+ */
+static int ext4_flex_group_add(struct super_block *sb,
+ struct inode *resize_inode,
+ struct ext4_new_flex_group_data *flex_gd)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ ext4_fsblk_t o_blocks_count;
+ ext4_grpblk_t last;
+ ext4_group_t group;
+ handle_t *handle;
+ unsigned reserved_gdb;
+ int err = 0, err2 = 0, credit;
+
+ BUG_ON(!flex_gd->count || !flex_gd->groups || !flex_gd->bg_flags);
+
+ reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
+ o_blocks_count = ext4_blocks_count(es);
+ ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
+ BUG_ON(last);
+
+ err = setup_new_flex_group_blocks(sb, flex_gd);
+ if (err)
+ goto exit;
+ /*
+ * We will always be modifying at least the superblock and GDT
+ * block. If we are adding a group past the last current GDT block,
+ * we will also modify the inode and the dindirect block. If we
+ * are adding a group with superblock/GDT backups we will also
+ * modify each of the reserved GDT dindirect blocks.
+ */
+ credit = flex_gd->count * 4 + reserved_gdb;
+ handle = ext4_journal_start_sb(sb, credit);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto exit;
+ }
+
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+ if (err)
+ goto exit_journal;
+
+ group = flex_gd->groups[0].group;
+ BUG_ON(group != EXT4_SB(sb)->s_groups_count);
+ err = ext4_add_new_descs(handle, sb, group,
+ resize_inode, flex_gd->count);
+ if (err)
+ goto exit_journal;
+
+ err = ext4_setup_new_descs(handle, sb, flex_gd);
+ if (err)
+ goto exit_journal;
+
+ ext4_update_super(sb, flex_gd);
+
+ err = ext4_handle_dirty_super(handle, sb);
+
+exit_journal:
+ err2 = ext4_journal_stop(handle);
+ if (!err)
+ err = err2;
+
+ if (!err) {
+ int i;
+ update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
+ sizeof(struct ext4_super_block));
+ for (i = 0; i < flex_gd->count; i++, group++) {
+ struct buffer_head *gdb_bh;
+ int gdb_num;
+ gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb);
+ gdb_bh = sbi->s_group_desc[gdb_num];
+ update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
+ gdb_bh->b_size);
+ }
+ }
+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
*/
int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
{
+ struct ext4_new_flex_group_data flex_gd;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
- struct buffer_head *primary = NULL;
- struct ext4_group_desc *gdp;
struct inode *inode = NULL;
- handle_t *handle;
int gdb_off, gdb_num;
- int err, err2;
+ int err;
+ __u16 bg_flags = 0;
gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
}
- if ((err = verify_group_input(sb, input)))
- goto exit_put;
+ err = verify_group_input(sb, input);
+ if (err)
+ goto out;
- if ((err = setup_new_group_blocks(sb, input)))
- goto exit_put;
+ flex_gd.count = 1;
+ flex_gd.groups = input;
+ flex_gd.bg_flags = &bg_flags;
+ err = ext4_flex_group_add(sb, inode, &flex_gd);
+out:
+ iput(inode);
+ return err;
+} /* ext4_group_add */
- /*
- * We will always be modifying at least the superblock and a GDT
- * block. If we are adding a group past the last current GDT block,
- * we will also modify the inode and the dindirect block. If we
- * are adding a group with superblock/GDT backups we will also
- * modify each of the reserved GDT dindirect blocks.
+/*
+ * extend a group without checking assuming that checking has been done.
+ */
+static int ext4_group_extend_no_check(struct super_block *sb,
+ ext4_fsblk_t o_blocks_count, ext4_grpblk_t add)
+{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ handle_t *handle;
+ int err = 0, err2;
+
+ /* We will update the superblock, one block bitmap, and
+ * one group descriptor via ext4_group_add_blocks().
*/
- handle = ext4_journal_start_sb(sb,
- ext4_bg_has_super(sb, input->group) ?
- 3 + reserved_gdb : 4);
+ handle = ext4_journal_start_sb(sb, 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
- goto exit_put;
+ ext4_warning(sb, "error %d on journal start", err);
+ return err;
}
- if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
- goto exit_journal;
-
- /*
- * We will only either add reserved group blocks to a backup group
- * or remove reserved blocks for the first group in a new group block.
- * Doing both would be mean more complex code, and sane people don't
- * use non-sparse filesystems anymore. This is already checked above.
- */
- if (gdb_off) {
- primary = sbi->s_group_desc[gdb_num];
- if ((err = ext4_journal_get_write_access(handle, primary)))
- goto exit_journal;
-
- if (reserved_gdb && ext4_bg_num_gdb(sb, input->group)) {
- err = reserve_backup_gdb(handle, inode, input->group);
- if (err)
- goto exit_journal;
- }
- } else {
- /*
- * Note that we can access new group descriptor block safely
- * only if add_new_gdb() succeeds.
- */
- err = add_new_gdb(handle, inode, input->group);
- if (err)
- goto exit_journal;
- primary = sbi->s_group_desc[gdb_num];
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err) {
+ ext4_warning(sb, "error %d on journal write access", err);
+ goto errout;
}
- /*
- * OK, now we've set up the new group. Time to make it active.
- *
- * 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.
- *
- * The key field here is sbi->s_groups_count: as long as
- * that retains its old value, nobody is going to access the new
- * group.
- *
- * So first we update all the descriptor metadata for the new
- * group; then we update the total disk blocks count; then we
- * update the groups count to enable the group; then finally we
- * update the free space counts so that the system can start
- * using the new disk blocks.
- */
-
- /* Update group descriptor block for new group */
- gdp = (struct ext4_group_desc *)((char *)primary->b_data +
- gdb_off * EXT4_DESC_SIZE(sb));
-
- memset(gdp, 0, EXT4_DESC_SIZE(sb));
- ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
- ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
- ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
- ext4_free_group_clusters_set(sb, gdp, input->free_blocks_count);
- ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
- gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
- gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
-
- /*
- * We can allocate memory for mb_alloc based on the new group
- * descriptor
- */
- err = ext4_mb_add_groupinfo(sb, input->group, gdp);
+ ext4_blocks_count_set(es, o_blocks_count + add);
+ ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
+ o_blocks_count + add);
+ /* We add the blocks to the bitmap and set the group need init bit */
+ err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
if (err)
- goto exit_journal;
-
- /*
- * Make the new blocks and inodes valid next. We do this before
- * increasing the group count so that once the group is enabled,
- * all of its blocks and inodes are already valid.
- *
- * We always allocate group-by-group, then block-by-block or
- * inode-by-inode within a group, so enabling these
- * blocks/inodes before the group is live won't actually let us
- * allocate the new space yet.
- */
- ext4_blocks_count_set(es, ext4_blocks_count(es) +
- input->blocks_count);
- le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb));
-
- /*
- * We need to protect s_groups_count against other CPUs seeing
- * inconsistent state in the superblock.
- *
- * The precise rules we use are:
- *
- * * Writers must perform a smp_wmb() after updating all dependent
- * data and before modifying the groups count
- *
- * * Readers must perform an smp_rmb() after reading the groups count
- * and before reading any dependent data.
- *
- * NB. These rules can be relaxed when checking the group count
- * while freeing data, as we can only allocate from a block
- * group after serialising against the group count, and we can
- * only then free after serialising in turn against that
- * allocation.
- */
- smp_wmb();
-
- /* Update the global fs size fields */
- sbi->s_groups_count++;
-
- err = ext4_handle_dirty_metadata(handle, NULL, primary);
- if (unlikely(err)) {
- ext4_std_error(sb, err);
- goto exit_journal;
- }
-
- /* Update the reserved block counts only once the new group is
- * active. */
- ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
- input->reserved_blocks);
-
- /* Update the free space counts */
- percpu_counter_add(&sbi->s_freeclusters_counter,
- EXT4_B2C(sbi, input->free_blocks_count));
- percpu_counter_add(&sbi->s_freeinodes_counter,
- EXT4_INODES_PER_GROUP(sb));
-
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
- sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group;
- flex_group = ext4_flex_group(sbi, input->group);
- atomic_add(EXT4_B2C(sbi, input->free_blocks_count),
- &sbi->s_flex_groups[flex_group].free_clusters);
- atomic_add(EXT4_INODES_PER_GROUP(sb),
- &sbi->s_flex_groups[flex_group].free_inodes);
- }
-
+ goto errout;
ext4_handle_dirty_super(handle, sb);
-
-exit_journal:
- if ((err2 = ext4_journal_stop(handle)) && !err)
+ ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
+ o_blocks_count + add);
+errout:
+ err2 = ext4_journal_stop(handle);
+ if (err2 && !err)
err = err2;
- if (!err && primary) {
- update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
+
+ if (!err) {
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
+ "blocks\n", ext4_blocks_count(es));
+ update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
sizeof(struct ext4_super_block));
- update_backups(sb, primary->b_blocknr, primary->b_data,
- primary->b_size);
}
-exit_put:
- iput(inode);
return err;
-} /* ext4_group_add */
+}
/*
* Extend the filesystem to the new number of blocks specified. This entry
ext4_grpblk_t last;
ext4_grpblk_t add;
struct buffer_head *bh;
- handle_t *handle;
- int err, err2;
+ int err;
ext4_group_t group;
o_blocks_count = ext4_blocks_count(es);
}
brelse(bh);
- /* We will update the superblock, one block bitmap, and
- * one group descriptor via ext4_free_blocks().
- */
- handle = ext4_journal_start_sb(sb, 3);
- if (IS_ERR(handle)) {
- err = PTR_ERR(handle);
- ext4_warning(sb, "error %d on journal start", err);
- goto exit_put;
+ err = ext4_group_extend_no_check(sb, o_blocks_count, add);
+ 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 ((err = ext4_journal_get_write_access(handle,
- EXT4_SB(sb)->s_sbh))) {
- ext4_warning(sb, "error %d on journal write access", err);
- ext4_journal_stop(handle);
- goto exit_put;
+ 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;
}
- ext4_blocks_count_set(es, o_blocks_count + add);
- ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
- o_blocks_count + add);
- /* We add the blocks to the bitmap and set the group need init bit */
- err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
- ext4_handle_dirty_super(handle, sb);
- ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
- o_blocks_count + add);
- err2 = ext4_journal_stop(handle);
- if (!err && err2)
- err = err2;
- if (err)
- goto exit_put;
+ 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: extended group to %llu blocks\n",
- ext4_blocks_count(es));
- update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
- sizeof(struct ext4_super_block));
-exit_put:
+ printk(KERN_DEBUG "EXT4-fs: resized filesystem from %llu "
+ "upto %llu blocks\n", o_blocks_count, n_blocks_count);
return err;
-} /* ext4_group_extend */
+}
projects / ~andy / linux / blobdiff