// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/resize.c * * Support for resizing an ext4 filesystem while it is mounted. * * Copyright (C) 2001, 2002 Andreas Dilger * * This could probably be made into a module, because it is not often in use. */ #define EXT4FS_DEBUG #include #include #include "ext4_jbd2.h" int ext4_resize_begin(struct super_block *sb) { int ret = 0; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; /* * If we are not using the primary superblock/GDT copy don't resize, * because the user tools have no way of handling this. Probably a * bad time to do it anyways. */ if (EXT4_SB(sb)->s_sbh->b_blocknr != le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); return -EPERM; } /* * We are not allowed to do online-resizing on a filesystem mounted * with error, because it can destroy the filesystem easily. */ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { ext4_warning(sb, "There are errors in the filesystem, " "so online resizing is not allowed"); return -EPERM; } if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags)) ret = -EBUSY; return ret; } void ext4_resize_end(struct super_block *sb) { clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags); smp_mb__after_atomic(); } static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, ext4_group_t group) { return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) << EXT4_DESC_PER_BLOCK_BITS(sb); } static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb, ext4_group_t group) { group = ext4_meta_bg_first_group(sb, group); return ext4_group_first_block_no(sb, group); } static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, ext4_group_t group) { ext4_grpblk_t overhead; overhead = ext4_bg_num_gdb(sb, group); if (ext4_bg_has_super(sb, group)) overhead += 1 + le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); return overhead; } #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) static int verify_group_input(struct super_block *sb, struct ext4_new_group_data *input) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_fsblk_t start = ext4_blocks_count(es); ext4_fsblk_t end = start + input->blocks_count; ext4_group_t group = input->group; ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group; unsigned overhead; ext4_fsblk_t metaend; struct buffer_head *bh = NULL; ext4_grpblk_t free_blocks_count, offset; int err = -EINVAL; if (group != sbi->s_groups_count) { ext4_warning(sb, "Cannot add at group %u (only %u groups)", input->group, sbi->s_groups_count); return -EINVAL; } overhead = ext4_group_overhead_blocks(sb, group); metaend = start + overhead; input->free_clusters_count = free_blocks_count = input->blocks_count - 2 - overhead - sbi->s_itb_per_group; if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks " "(%d free, %u reserved)\n", ext4_bg_has_super(sb, input->group) ? "normal" : "no-super", input->group, input->blocks_count, free_blocks_count, input->reserved_blocks); ext4_get_group_no_and_offset(sb, start, NULL, &offset); if (offset != 0) ext4_warning(sb, "Last group not full"); else if (input->reserved_blocks > input->blocks_count / 5) ext4_warning(sb, "Reserved blocks too high (%u)", input->reserved_blocks); else if (free_blocks_count < 0) ext4_warning(sb, "Bad blocks count %u", input->blocks_count); else if (!(bh = sb_bread(sb, end - 1))) ext4_warning(sb, "Cannot read last block (%llu)", end - 1); else if (outside(input->block_bitmap, start, end)) ext4_warning(sb, "Block bitmap not in group (block %llu)", (unsigned long long)input->block_bitmap); else if (outside(input->inode_bitmap, start, end)) ext4_warning(sb, "Inode bitmap not in group (block %llu)", (unsigned long long)input->inode_bitmap); else if (outside(input->inode_table, start, end) || outside(itend - 1, start, end)) ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)", (unsigned long long)input->inode_table, itend - 1); else if (input->inode_bitmap == input->block_bitmap) ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)", (unsigned long long)input->block_bitmap); else if (inside(input->block_bitmap, input->inode_table, itend)) ext4_warning(sb, "Block bitmap (%llu) in inode table " "(%llu-%llu)", (unsigned long long)input->block_bitmap, (unsigned long long)input->inode_table, itend - 1); else if (inside(input->inode_bitmap, input->inode_table, itend)) ext4_warni
#include <linux/buffer_head.h>
#include "minix.h"

enum {DIRECT = 7, DEPTH = 4};	/* Have triple indirect */

typedef u32 block_t;	/* 32 bit, host order */

static inline unsigned long block_to_cpu(block_t n)
{
	return n;
}

static inline block_t cpu_to_block(unsigned long n)
{
	return n;
}

static inline block_t *i_data(struct inode *inode)
{
	return (block_t *)minix_i(inode)->u.i2_data;
}

static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
{
	int n = 0;
	struct super_block *sb = inode->i_sb;

	if (block < 0) {
		printk("minix_bmap: block<0\n");
	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/sb->s_blocksize)) {
		printk("minix_bmap: block>big\n");
	} else if (block < 7) {
		offsets[n++] = block;
	} else if ((block -= 7) < 256) {
		offsets[n++] = 7;
		offsets[n++] = block;
	} else if ((block -= 256) < 256*256) {
		offsets[n++] = 8;
		offsets[n++] = block>>8;
		offsets[n++] = block & 255;
	} else {
		block -= 256*256;
		offsets[n++] = 9;
		offsets[n++] = block>>16;
		offsets[n++] = (block>>8) & 255;
		offsets[n++] = block & 255;
	}
	return n;
}

#include "itree_common.c"

int V2_minix_get_block(struct inode * inode, long block,
			struct buffer_head *bh_result, int create)
{
	return get_block(inode, block, bh_result, create);
}

void V2_minix_truncate(struct inode * inode)
{
	truncate(inode);
}

unsigned V2_minix_blocks(loff_t size, struct super_block *sb)
{
	return nblocks(size, sb);
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-12 05:28:35 +0000
if (!n_group_desc) { err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); goto exit_inode; } /* * Finally, we have all of the possible failures behind us... * * Remove new GDT block from inode double-indirect block and clear out * the new GDT block for use (which also "frees" the backup GDT blocks * from the reserved inode). We don't need to change the bitmaps for * these blocks, because they are marked as in-use from being in the * reserved inode, and will become GDT blocks (primary and backup). */ data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0; err = ext4_handle_dirty_metadata(handle, NULL, dind); if (unlikely(err)) { ext4_std_error(sb, err); goto exit_inode; } inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> (9 - EXT4_SB(sb)->s_cluster_bits); ext4_mark_iloc_dirty(handle, inode, &iloc); memset(gdb_bh->b_data, 0, sb->s_blocksize); err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); goto exit_inode; } brelse(dind); o_group_desc = EXT4_SB(sb)->s_group_desc; memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); n_group_desc[gdb_num] = gdb_bh; EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); return err; exit_inode: kvfree(n_group_desc); brelse(iloc.bh); exit_dind: brelse(dind); exit_bh: brelse(gdb_bh); ext4_debug("leaving with error %d\n", err); return err; } /* * add_new_gdb_meta_bg is the sister of add_new_gdb. */ static int add_new_gdb_meta_bg(struct super_block *sb, handle_t *handle, ext4_group_t group) { ext4_fsblk_t gdblock; struct buffer_head *gdb_bh; struct buffer_head **o_group_desc, **n_group_desc; unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int err; gdblock = ext4_meta_bg_first_block_no(sb, group) + ext4_bg_has_super(sb, group); gdb_bh = sb_bread(sb, gdblock); if (!gdb_bh) return -EIO; n_group_desc = ext4_kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); return err; } o_group_desc = EXT4_SB(sb)->s_group_desc; memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); n_group_desc[gdb_num] = gdb_bh; EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); if (unlikely(err)) brelse(gdb_bh); return err; } /* * Called when we are adding a new group which has a backup copy of each of * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks. * We need to add these reserved backup GDT blocks to the resize inode, so * that they are kept for future resizing and not allocated to files. * * Each reserved backup GDT block will go into a different indirect block. * The indirect blocks are actually the primary reserved GDT blocks, * so we know in advance what their block numbers are. We only get the * double-indirect block to verify it is pointing to the primary reserved * GDT blocks so we don't overwrite a data block by accident. The reserved * backup GDT blocks are stored in their reserved primary GDT block. */ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, ext4_group_t group) { struct super_block *sb = inode->i_sb; int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); int cluster_bits = EXT4_SB(sb)->s_cluster_bits; struct buffer_head **primary; struct buffer_head *dind; struct ext4_iloc iloc; ext4_fsblk_t blk; __le32 *data, *end; int gdbackups = 0; int res, i; int err; primary = kmalloc_array(reserved_gdb, sizeof(*primary), GFP_NOFS); if (!primary) return -ENOMEM; data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK; dind = sb_bread(sb, le32_to_cpu(*data)); if (!dind) { err = -EIO; goto exit_free; } blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count; data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count % EXT4_ADDR_PER_BLOCK(sb)); end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb); /* Get each reserved primary GDT block and verify it holds backups */ for (res = 0; res < reserved_gdb; res++, blk++) { if (le32_to_cpu(*data) != blk) { ext4_warning(sb, "reserved block %llu" " not at offset %ld", blk, (long)(data - (__le32 *)dind->b_data)); err = -EINVAL; goto exit_bh; } primary[res] = sb_bread(sb, blk); if (!primary[res]) { err = -EIO; goto exit_bh; } gdbackups = verify_reserved_gdb(sb, group, primary[res]); if (gdbackups < 0) { brelse(primary[res]); err = gdbackups; goto exit_bh; } if (++data >= end) data = (__le32 *)dind->b_data; } for (i = 0; i < reserved_gdb; i++) { BUFFER_TRACE(primary[i], "get_write_access"); if ((err = ext4_journal_get_write_access(handle, primary[i]))) goto exit_bh; } if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) goto exit_bh; /* * Finally we can add each of the reserved backup GDT blocks from * the new group to its reserved primary GDT block. */ blk = group * EXT4_BLOCKS_PER_GROUP(sb); for (i = 0; i < reserved_gdb; i++) { int err2; data = (__le32 *)primary[i]->b_data; /* printk("reserving backup %lu[%u] = %lu\n", primary[i]->b_blocknr, gdbackups, blk + primary[i]->b_blocknr); */ data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr); err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]); if (!err) err = err2; } inode->i_blocks += reserved_gdb * sb->s_blocksize >> (9 - cluster_bits); ext4_mark_iloc_dirty(handle, inode, &iloc); exit_bh: while (--res >= 0) brelse(primary[res]); brelse(dind); exit_free: kfree(primary); return err; } /* * Update the backup copies of the ext4 metadata. These don't need to be part * of the main resize transaction, because e2fsck will re-write them if there * is a problem (basically only OOM will cause a problem). However, we * _should_ update the backups if possible, in case the primary gets trashed * for some reason and we need to run e2fsck from a backup superblock. The * important part is that the new block and inode counts are in the backup * superblocks, and the location of the new group metadata in the GDT backups. * * We do not need take the s_resize_lock for this, because these * blocks are not otherwise touched by the filesystem code when it is * mounted. We don't need to worry about last changing from * sbi->s_groups_count, because the worst that can happen is that we * do not copy the full number of backups at this time. The resize * which changed s_groups_count will backup again. */ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, int size, int meta_bg) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t last; const int bpg = EXT4_BLOCKS_PER_GROUP(sb); unsigned three = 1; unsigned five = 5; unsigned seven = 7; ext4_group_t group = 0; int rest = sb->s_blocksize - size; handle_t *handle; int err = 0, err2; handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA); if (IS_ERR(handle)) { group = 1; err = PTR_ERR(handle); goto exit_err; } if (meta_bg == 0) { group = ext4_list_backups(sb, &three, &five, &seven); last = sbi->s_groups_count; } else { group = ext4_get_group_number(sb, blk_off) + 1; last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2); } while (group < sbi->s_groups_count) { struct buffer_head *bh; ext4_fsblk_t backup_block; /* Out of journal space, and can't get more - abort - so sad */ if (ext4_handle_valid(handle) && handle->h_buffer_credits == 0 && ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) && (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) break; if (meta_bg == 0) backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; else backup_block = (ext4_group_first_block_no(sb, group) + ext4_bg_has_super(sb, group)); bh = sb_getblk(sb, backup_block); if (unlikely(!bh)) { err = -ENOMEM; break; } ext4_debug("update metadata backup %llu(+%llu)\n", backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); if ((err = ext4_journal_get_write_access(handle, bh))) break; lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) memset(bh->b_data + size, 0, rest); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); if (unlikely(err)) ext4_std_error(sb, err); brelse(bh); if (meta_bg == 0) group = ext4_list_backups(sb, &three, &five, &seven); else if (group == last) break; else group = last; } if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; /* * Ugh! Need to have e2fsck write the backup copies. It is too * late to revert the resize, we shouldn't fail just because of * the backup copies (they are only needed in case of corruption). * * However, if we got here we have a journal problem too, so we * can't really start a transaction to mark the superblock. * Chicken out and just set the flag on the hope it will be written * to disk, and if not - we will simply wait until next fsck. */ exit_err: if (err) { ext4_warning(sb, "can't update backup for group %u (err %d), " "forcing fsck on next reboot", group, err); sbi->s_mount_state &= ~EXT4_VALID_FS; sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS); mark_buffer_dirty(sbi->s_sbh); } } /* * 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; int meta_bg; meta_bg = ext4_has_feature_meta_bg(sb); 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]; BUFFER_TRACE(gdb_bh, "get_write_access"); 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 if (meta_bg != 0) { err = add_new_gdb_meta_bg(sb, handle, group); } else { err = add_new_gdb(handle, resize_inode, group); } if (err) break; } return err; } static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block) { struct buffer_head *bh = sb_getblk(sb, block); if (unlikely(!bh)) return NULL; if (!bh_uptodate_or_lock(bh)) { if (bh_submit_read(bh) < 0) { brelse(bh); return NULL; } } return bh; } static int ext4_set_bitmap_checksums(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct ext4_new_group_data *group_data) { struct buffer_head *bh; if (!ext4_has_metadata_csum(sb)) return 0; bh = ext4_get_bitmap(sb, group_data->inode_bitmap); if (!bh) return -EIO; ext4_inode_bitmap_csum_set(sb, group, gdp, bh, EXT4_INODES_PER_GROUP(sb) / 8); brelse(bh); bh = ext4_get_bitmap(sb, group_data->block_bitmap); if (!bh) return -EIO; ext4_block_bitmap_csum_set(sb, group, gdp, bh); brelse(bh); return 0; } /* * 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 *)(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); err = ext4_set_bitmap_checksums(sb, group, gdp, group_data); if (err) { ext4_std_error(sb, err); break; } ext4_inode_table_set(sb, gdp, group_data->inode_table); ext4_free_group_clusters_set(sb, gdp, group_data->free_clusters_count); ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); if (ext4_has_group_desc_csum(sb)) ext4_itable_unused_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); gdp->bg_flags = cpu_to_le16(*bg_flags); ext4_group_desc_csum_set(sb, 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 += EXT4_C2B(sbi, group_data[i].free_clusters_count); } reserved_blocks = ext4_r_blocks_count(es) * 100; reserved_blocks = div64_u64(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); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); ext4_debug("free blocks count %llu", ext4_free_blocks_count(es)); /* * 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; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); /* 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_NUM_B2C(sbi, free_blocks)); percpu_counter_add(&sbi->s_freeinodes_counter, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); ext4_debug("free blocks count %llu", percpu_counter_read(&sbi->s_freeclusters_counter)); if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; flex_group = ext4_flex_group(sbi, group_data[0].group); atomic64_add(EXT4_NUM_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); } /* * Update the fs overhead information */ ext4_calculate_overhead(sb); 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 * blocks. 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 = 3; /* sb, resize inode, resize inode dindirect */ /* GDT blocks */ credit += 1 + DIV_ROUND_UP(flex_gd->count, EXT4_DESC_PER_BLOCK(sb)); credit += reserved_gdb; /* Reserved GDT dindirect blocks */ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credit); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto exit; } BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto exit_journal; group = flex_gd->groups[0].group; BUG_ON(group != sbi->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 gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); sector_t old_gdb = 0; update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, sizeof(struct ext4_super_block), 0); for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; gdb_bh = sbi->s_group_desc[gdb_num]; if (old_gdb == gdb_bh->b_blocknr) continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, gdb_bh->b_size, meta_bg); old_gdb = gdb_bh->b_blocknr; } } 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_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->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 clusters_per_group; unsigned long i; clusters_per_group = EXT4_CLUSTERS_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 = EXT4_BLOCKS_PER_GROUP(sb); overhead = ext4_group_overhead_blocks(sb, group + i); group_data[i].mdata_blocks = overhead; group_data[i].free_clusters_count = EXT4_CLUSTERS_PER_GROUP(sb); if (ext4_has_group_desc_csum(sb)) { flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT | EXT4_BG_INODE_UNINIT; if (!test_opt(sb, INIT_INODE_TABLE)) flex_gd->bg_flags[i] |= EXT4_BG_INODE_ZEROED; } else flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED; } if (last_group == n_group && ext4_has_group_desc_csum(sb)) /* 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 != clusters_per_group - 1)) { group_data[i - 1].blocks_count = EXT4_C2B(sbi, last + 1); group_data[i - 1].free_clusters_count -= clusters_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 * write the data to disk. * * If we are on a GDT block boundary, we need to get the reserved GDT block. * Otherwise, we may need to add backup GDT blocks for a sparse group. * * We only need to hold the superblock lock while we are actually adding * in the new group's counts to the superblock. Prior to that we have * not really "added" the group at all. We re-check that we are still * adding in the last group in case things have changed since verifying. */ 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 inode *inode = NULL; int gdb_off; int err; __u16 bg_flags = 0; gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb); if (gdb_off == 0 && !ext4_has_feature_sparse_super(sb)) { ext4_warning(sb, "Can't resize non-sparse filesystem further"); return -EPERM; } if (ext4_blocks_count(es) + input->blocks_count < ext4_blocks_count(es)) { ext4_warning(sb, "blocks_count overflow"); return -EINVAL; } if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) < le32_to_cpu(es->s_inodes_count)) { ext4_warning(sb, "inodes_count overflow"); return -EINVAL; } if (reserved_gdb || gdb_off == 0) { if (ext4_has_feature_resize_inode(sb) || !le16_to_cpu(es->s_reserved_gdt_blocks)) { ext4_warning(sb, "No reserved GDT blocks, can't resize"); return -EPERM; } inode = ext4_iget(sb, EXT4_RESIZE_INO); if (IS_ERR(inode)) { ext4_warning(sb, "Error opening resize inode"); return PTR_ERR(inode); } } err = verify_group_input(sb, input); if (err) goto out; err = ext4_alloc_flex_bg_array(sb, input->group + 1); if (err) goto out; err = ext4_mb_alloc_groupinfo(sb, input->group + 1); if (err) goto out; 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 */ /* * 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_HT_RESIZE, 3); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_warning(sb, "error %d on journal start", err); return err; } BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); 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; } ext4_blocks_count_set(es, o_blocks_count + add); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + 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 errout; ext4_handle_dirty_super(handle, sb); 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) { 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), 0); } return err; } /* * Extend the filesystem to the new number of blocks specified. This entry * point is only used to extend the current filesystem to the end of the last * existing group. It can be accessed via ioctl, or by "remount,resize=" * for emergencies (because it has no dependencies on reserved blocks). * * If we _really_ wanted, we could use default values to call ext4_group_add() * allow the "remount" trick to work for arbitrary resizing, assuming enough * GDT blocks are reserved to grow to the desired size. */ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t n_blocks_count) { ext4_fsblk_t o_blocks_count; ext4_grpblk_t last; ext4_grpblk_t add; struct buffer_head *bh; int err; ext4_group_t group; o_blocks_count = ext4_blocks_count(es); if (test_opt(sb, DEBUG)) ext4_msg(sb, KERN_DEBUG, "extending last group from %llu to %llu blocks", o_blocks_count, n_blocks_count); if (n_blocks_count == 0 || n_blocks_count == o_blocks_count) return 0; if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { ext4_msg(sb, KERN_ERR, "filesystem too large to resize to %llu blocks safely", n_blocks_count); if (sizeof(sector_t) < 8) ext4_warning(sb, "CONFIG_LBDAF not enabled"); return -EINVAL; } if (n_blocks_count < o_blocks_count) { ext4_warning(sb, "can't shrink FS - resize aborted"); return -EINVAL; } /* Handle the remaining blocks in the last group only. */ ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last); if (last == 0) { ext4_warning(sb, "need to use ext2online to resize further"); return -EPERM; } add = EXT4_BLOCKS_PER_GROUP(sb) - last; if (o_blocks_count + add < o_blocks_count) { ext4_warning(sb, "blocks_count overflow"); return -EINVAL; } if (o_blocks_count + add > n_blocks_count) add = n_blocks_count - o_blocks_count; if (o_blocks_count + add < n_blocks_count) ext4_warning(sb, "will only finish group (%llu blocks, %u new)", o_blocks_count + add, add); /* See if the device is actually as big as what was requested */ bh = sb_bread(sb, o_blocks_count + add - 1); if (!bh) { ext4_warning(sb, "can't read last block, resize aborted"); return -ENOSPC; } brelse(bh); err = ext4_group_extend_no_check(sb, o_blocks_count, add); return err; } /* ext4_group_extend */ static int num_desc_blocks(struct super_block *sb, ext4_group_t groups) { return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); } /* * Release the resize inode and drop the resize_inode feature if there * are no more reserved gdt blocks, and then convert the file system * to enable meta_bg */ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) { handle_t *handle; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); ext4_fsblk_t nr; int i, ret, err = 0; int credits = 1; ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg"); if (inode) { if (es->s_reserved_gdt_blocks) { ext4_error(sb, "Unexpected non-zero " "s_reserved_gdt_blocks"); return -EPERM; } /* Do a quick sanity check of the resize inode */ if (inode->i_blocks != 1 << (inode->i_blkbits - (9 - sbi->s_cluster_bits))) goto invalid_resize_inode; for (i = 0; i < EXT4_N_BLOCKS; i++) { if (i == EXT4_DIND_BLOCK) { if (ei->i_data[i]) continue; else goto invalid_resize_inode; } if (ei->i_data[i]) goto invalid_resize_inode; } credits += 3; /* block bitmap, bg descriptor, resize inode */ } handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto errout; ext4_clear_feature_resize_inode(sb); ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); err = ext4_handle_dirty_super(handle, sb); if (err) { ext4_std_error(sb, err); goto errout; } if (inode) { nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]); ext4_free_blocks(handle, inode, NULL, nr, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); ei->i_data[EXT4_DIND_BLOCK] = 0; inode->i_blocks = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) ext4_std_error(sb, err); } errout: ret = ext4_journal_stop(handle); if (!err) err = ret; return ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); return -EINVAL; } /* * 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 = NULL; ext4_grpblk_t add, offset; unsigned long n_desc_blocks; unsigned long o_desc_blocks; ext4_group_t o_group; ext4_group_t n_group; ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; int meta_bg; /* 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); retry: o_blocks_count = ext4_blocks_count(es); ext4_msg(sb, KERN_INFO, "resizing filesystem from %llu " "to %llu blocks", 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; n_group = ext4_get_group_number(sb, n_blocks_count - 1); if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { ext4_warning(sb, "resize would cause inodes_count overflow"); return -EINVAL; } ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); n_desc_blocks = num_desc_blocks(sb, n_group + 1); o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count); meta_bg = ext4_has_feature_meta_bg(sb); if (ext4_has_feature_resize_inode(sb)) { if (meta_bg) { ext4_error(sb, "resize_inode and meta_bg enabled " "simultaneously"); return -EINVAL; } if (n_desc_blocks > o_desc_blocks + le16_to_cpu(es->s_reserved_gdt_blocks)) { n_blocks_count_retry = n_blocks_count; n_desc_blocks = o_desc_blocks + le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); n_blocks_count = (ext4_fsblk_t)n_group * EXT4_BLOCKS_PER_GROUP(sb); n_group--; /* set to last group number */ } if (!resize_inode) 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); } } if ((!resize_inode && !meta_bg) || n_blocks_count == o_blocks_count) { err = ext4_convert_meta_bg(sb, resize_inode); if (err) goto out; if (resize_inode) { iput(resize_inode); resize_inode = NULL; } if (n_blocks_count_retry) { n_blocks_count = n_blocks_count_retry; n_blocks_count_retry = 0; goto retry; } } /* extend the last group */ if (n_group == o_group) add = n_blocks_count - o_blocks_count; else add = EXT4_C2B(sbi, EXT4_CLUSTERS_PER_GROUP(sb) - (offset + 1)); if (add > 0) { err = ext4_group_extend_no_check(sb, o_blocks_count, add); if (err) goto out; } if (ext4_blocks_count(es) == n_blocks_count) goto out; err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) return err; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) 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)) { if (jiffies - last_update_time > HZ * 10) { if (last_update_time) ext4_msg(sb, KERN_INFO, "resized to %llu blocks", ext4_blocks_count(es)); last_update_time = jiffies; } if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0) break; err = ext4_flex_group_add(sb, resize_inode, flex_gd); if (unlikely(err)) break; } if (!err && n_blocks_count_retry) { n_blocks_count = n_blocks_count_retry; n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; goto retry; } out: if (flex_gd) free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); return err; }