tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)"
depends on EXPERIMENTAL
select JBD2
+ select CRC16
help
Ext4dev is a predecessor filesystem of the next generation
extended fs ext4, based on ext3 filesystem code. It will be
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
+#include "group.h"
/*
* balloc.c contains the blocks allocation and deallocation routines
*/
}
+/* Initializes an uninitialized block bitmap if given, and returns the
+ * number of blocks free in the group. */
+unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
+ int block_group, struct ext4_group_desc *gdp)
+{
+ unsigned long start;
+ int bit, bit_max;
+ unsigned free_blocks, group_blocks;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (bh) {
+ J_ASSERT_BH(bh, buffer_locked(bh));
+
+ /* If checksum is bad mark all blocks used to prevent allocation
+ * essentially implementing a per-group read-only flag. */
+ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+ ext4_error(sb, __FUNCTION__,
+ "Checksum bad for group %u\n", block_group);
+ gdp->bg_free_blocks_count = 0;
+ gdp->bg_free_inodes_count = 0;
+ gdp->bg_itable_unused = 0;
+ memset(bh->b_data, 0xff, sb->s_blocksize);
+ return 0;
+ }
+ memset(bh->b_data, 0, sb->s_blocksize);
+ }
+
+ /* Check for superblock and gdt backups in this group */
+ bit_max = ext4_bg_has_super(sb, block_group);
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+ block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
+ sbi->s_desc_per_block) {
+ if (bit_max) {
+ bit_max += ext4_bg_num_gdb(sb, block_group);
+ bit_max +=
+ le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+ }
+ } else { /* For META_BG_BLOCK_GROUPS */
+ int group_rel = (block_group -
+ le32_to_cpu(sbi->s_es->s_first_meta_bg)) %
+ EXT4_DESC_PER_BLOCK(sb);
+ if (group_rel == 0 || group_rel == 1 ||
+ (group_rel == EXT4_DESC_PER_BLOCK(sb) - 1))
+ bit_max += 1;
+ }
+
+ if (block_group == sbi->s_groups_count - 1) {
+ /*
+ * Even though mke2fs always initialize first and last group
+ * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
+ * to make sure we calculate the right free blocks
+ */
+ group_blocks = ext4_blocks_count(sbi->s_es) -
+ le32_to_cpu(sbi->s_es->s_first_data_block) -
+ (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1));
+ } else {
+ group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
+ }
+
+ free_blocks = group_blocks - bit_max;
+
+ if (bh) {
+ for (bit = 0; bit < bit_max; bit++)
+ ext4_set_bit(bit, bh->b_data);
+
+ start = block_group * EXT4_BLOCKS_PER_GROUP(sb) +
+ le32_to_cpu(sbi->s_es->s_first_data_block);
+
+ /* Set bits for block and inode bitmaps, and inode table */
+ ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
+ ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data);
+ for (bit = le32_to_cpu(gdp->bg_inode_table) - start,
+ bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++)
+ ext4_set_bit(bit, bh->b_data);
+
+ /*
+ * Also if the number of blocks within the group is
+ * less than the blocksize * 8 ( which is the size
+ * of bitmap ), set rest of the block bitmap to 1
+ */
+ mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
+ }
+
+ return free_blocks - sbi->s_itb_per_group - 2;
+}
+
+
/*
* The free blocks are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
*
* Return buffer_head on success or NULL in case of failure.
*/
-static struct buffer_head *
+struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
int i;
struct buffer_head * bh = NULL;
ext4_fsblk_t bitmap_blk;
- desc = ext4_get_group_desc (sb, block_group, NULL);
+ desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
bitmap_blk = ext4_block_bitmap(sb, desc);
- bh = sb_bread(sb, bitmap_blk);
+ if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ bh = sb_getblk(sb, bitmap_blk);
+ if (!buffer_uptodate(bh)) {
+ lock_buffer(bh);
+ if (!buffer_uptodate(bh)) {
+ ext4_init_block_bitmap(sb, bh, block_group,
+ desc);
+ set_buffer_uptodate(bh);
+ }
+ unlock_buffer(bh);
+ }
+ } else {
+ bh = sb_bread(sb, bitmap_blk);
+ }
if (!bh)
ext4_error (sb, __FUNCTION__,
"Cannot read block bitmap - "
desc->bg_free_blocks_count =
cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) +
group_freed);
+ desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_add(&sbi->s_freeblocks_counter, count);
ret_block, goal_hits, goal_attempts);
spin_lock(sb_bgl_lock(sbi, group_no));
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
gdp->bg_free_blocks_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num);
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
spin_unlock(sb_bgl_lock(sbi, group_no));
percpu_counter_sub(&sbi->s_freeblocks_counter, num);
--- /dev/null
+/*
+ * linux/fs/ext4/group.h
+ *
+ * Copyright (C) 2007 Cluster File Systems, Inc
+ *
+ * Author: Andreas Dilger <adilger@clusterfs.com>
+ */
+
+#ifndef _LINUX_EXT4_GROUP_H
+#define _LINUX_EXT4_GROUP_H
+
+extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
+ struct ext4_group_desc *gdp);
+extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
+ struct ext4_group_desc *gdp);
+struct buffer_head *read_block_bitmap(struct super_block *sb,
+ unsigned int block_group);
+extern unsigned ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh, int group,
+ struct ext4_group_desc *desc);
+#define ext4_free_blocks_after_init(sb, group, desc) \
+ ext4_init_block_bitmap(sb, NULL, group, desc)
+extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
+ struct buffer_head *bh, int group,
+ struct ext4_group_desc *desc);
+extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+#endif /* _LINUX_EXT4_GROUP_H */
#include "xattr.h"
#include "acl.h"
+#include "group.h"
/*
* ialloc.c contains the inodes allocation and deallocation routines
* the free blocks count in the block.
*/
+/*
+ * To avoid calling the atomic setbit hundreds or thousands of times, we only
+ * need to use it within a single byte (to ensure we get endianness right).
+ * We can use memset for the rest of the bitmap as there are no other users.
+ */
+void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+{
+ int i;
+
+ if (start_bit >= end_bit)
+ return;
+
+ ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
+ for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
+ ext4_set_bit(i, bitmap);
+ if (i < end_bit)
+ memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
+}
+
+/* Initializes an uninitialized inode bitmap */
+unsigned ext4_init_inode_bitmap(struct super_block *sb,
+ struct buffer_head *bh, int block_group,
+ struct ext4_group_desc *gdp)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ J_ASSERT_BH(bh, buffer_locked(bh));
+
+ /* If checksum is bad mark all blocks and inodes use to prevent
+ * allocation, essentially implementing a per-group read-only flag. */
+ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+ ext4_error(sb, __FUNCTION__, "Checksum bad for group %u\n",
+ block_group);
+ gdp->bg_free_blocks_count = 0;
+ gdp->bg_free_inodes_count = 0;
+ gdp->bg_itable_unused = 0;
+ memset(bh->b_data, 0xff, sb->s_blocksize);
+ return 0;
+ }
+
+ memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
+ mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
+ bh->b_data);
+
+ return EXT4_INODES_PER_GROUP(sb);
+}
/*
* Read the inode allocation bitmap for a given block_group, reading
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
goto error_out;
-
- bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
+ if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ bh = sb_getblk(sb, ext4_inode_bitmap(sb, desc));
+ if (!buffer_uptodate(bh)) {
+ lock_buffer(bh);
+ if (!buffer_uptodate(bh)) {
+ ext4_init_inode_bitmap(sb, bh, block_group,
+ desc);
+ set_buffer_uptodate(bh);
+ }
+ unlock_buffer(bh);
+ }
+ } else {
+ bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
+ }
if (!bh)
ext4_error(sb, "read_inode_bitmap",
"Cannot read inode bitmap - "
if (is_directory)
gdp->bg_used_dirs_count = cpu_to_le16(
le16_to_cpu(gdp->bg_used_dirs_count) - 1);
+ gdp->bg_checksum = ext4_group_desc_csum(sbi,
+ block_group, gdp);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
struct ext4_sb_info *sbi;
int err = 0;
struct inode *ret;
- int i;
+ int i, free = 0;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
goto out;
got:
- ino += group * EXT4_INODES_PER_GROUP(sb) + 1;
- if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
- ext4_error (sb, "ext4_new_inode",
- "reserved inode or inode > inodes count - "
- "block_group = %d, inode=%lu", group, ino);
+ ino++;
+ if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
+ ino > EXT4_INODES_PER_GROUP(sb)) {
+ ext4_error(sb, __FUNCTION__,
+ "reserved inode or inode > inodes count - "
+ "block_group = %d, inode=%lu", group,
+ ino + group * EXT4_INODES_PER_GROUP(sb));
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext4_journal_get_write_access(handle, bh2);
if (err) goto fail;
+
+ /* We may have to initialize the block bitmap if it isn't already */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
+ gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ struct buffer_head *block_bh = read_block_bitmap(sb, group);
+
+ BUFFER_TRACE(block_bh, "get block bitmap access");
+ err = ext4_journal_get_write_access(handle, block_bh);
+ if (err) {
+ brelse(block_bh);
+ goto fail;
+ }
+
+ free = 0;
+ spin_lock(sb_bgl_lock(sbi, group));
+ /* recheck and clear flag under lock if we still need to */
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ free = ext4_free_blocks_after_init(sb, group, gdp);
+ gdp->bg_free_blocks_count = cpu_to_le16(free);
+ }
+ spin_unlock(sb_bgl_lock(sbi, group));
+
+ /* Don't need to dirty bitmap block if we didn't change it */
+ if (free) {
+ BUFFER_TRACE(block_bh, "dirty block bitmap");
+ err = ext4_journal_dirty_metadata(handle, block_bh);
+ }
+
+ brelse(block_bh);
+ if (err)
+ goto fail;
+ }
+
spin_lock(sb_bgl_lock(sbi, group));
+ /* If we didn't allocate from within the initialized part of the inode
+ * table then we need to initialize up to this inode. */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+
+ /* When marking the block group with
+ * ~EXT4_BG_INODE_UNINIT we don't want to depend
+ * on the value of bg_itable_unsed even though
+ * mke2fs could have initialized the same for us.
+ * Instead we calculated the value below
+ */
+
+ free = 0;
+ } else {
+ free = EXT4_INODES_PER_GROUP(sb) -
+ le16_to_cpu(gdp->bg_itable_unused);
+ }
+
+ /*
+ * Check the relative inode number against the last used
+ * relative inode number in this group. if it is greater
+ * we need to update the bg_itable_unused count
+ *
+ */
+ if (ino > free)
+ gdp->bg_itable_unused =
+ cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
+ }
+
gdp->bg_free_inodes_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
if (S_ISDIR(mode)) {
gdp->bg_used_dirs_count =
cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
}
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bh2);
inode->i_gid = current->fsgid;
inode->i_mode = mode;
- inode->i_ino = ino;
+ inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
#include <linux/errno.h>
#include <linux/slab.h>
+#include "group.h"
#define outside(b, first, last) ((b) < (first) || (b) >= (last))
#define inside(b, first, last) ((b) >= (first) && (b) < (last))
return bh;
}
-/*
- * To avoid calling the atomic setbit hundreds or thousands of times, we only
- * need to use it within a single byte (to ensure we get endianness right).
- * We can use memset for the rest of the bitmap as there are no other users.
- */
-static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
-{
- int i;
-
- if (start_bit >= end_bit)
- return;
-
- ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
- for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
- ext4_set_bit(i, bitmap);
- if (i < end_bit)
- memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
-}
-
/*
* Set up the block and inode bitmaps, and the inode table for the new group.
* This doesn't need to be part of the main transaction, since we are only
ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
/*
* Make the new blocks and inodes valid next. We do this before
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/log2.h>
+#include <linux/crc16.h>
#include <asm/uaccess.h>
#include "xattr.h"
#include "acl.h"
#include "namei.h"
+#include "group.h"
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
return res;
}
+__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
+ struct ext4_group_desc *gdp)
+{
+ __u16 crc = 0;
+
+ if (sbi->s_es->s_feature_ro_compat &
+ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+ int offset = offsetof(struct ext4_group_desc, bg_checksum);
+ __le32 le_group = cpu_to_le32(block_group);
+
+ crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
+ crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
+ crc = crc16(crc, (__u8 *)gdp, offset);
+ offset += sizeof(gdp->bg_checksum); /* skip checksum */
+ /* for checksum of struct ext4_group_desc do the rest...*/
+ if ((sbi->s_es->s_feature_incompat &
+ cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
+ offset < le16_to_cpu(sbi->s_es->s_desc_size))
+ crc = crc16(crc, (__u8 *)gdp + offset,
+ le16_to_cpu(sbi->s_es->s_desc_size) -
+ offset);
+ }
+
+ return cpu_to_le16(crc);
+}
+
+int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
+ struct ext4_group_desc *gdp)
+{
+ if ((sbi->s_es->s_feature_ro_compat &
+ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) &&
+ (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp)))
+ return 0;
+
+ return 1;
+}
+
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors (struct super_block * sb)
{
i, inode_table);
return 0;
}
+ if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
+ ext4_error(sb, __FUNCTION__,
+ "Checksum for group %d failed (%u!=%u)\n", i,
+ le16_to_cpu(ext4_group_desc_csum(sbi, i,
+ gdp)),
+ le16_to_cpu(gdp->bg_checksum));
+ return 0;
+ }
first_block += EXT4_BLOCKS_PER_GROUP(sb);
gdp = (struct ext4_group_desc *)
((__u8 *)gdp + EXT4_DESC_SIZE(sb));
*/
struct ext4_group_desc
{
- __le32 bg_block_bitmap; /* Blocks bitmap block */
- __le32 bg_inode_bitmap; /* Inodes bitmap block */
+ __le32 bg_block_bitmap; /* Blocks bitmap block */
+ __le32 bg_inode_bitmap; /* Inodes bitmap block */
__le32 bg_inode_table; /* Inodes table block */
__le16 bg_free_blocks_count; /* Free blocks count */
__le16 bg_free_inodes_count; /* Free inodes count */
__le16 bg_used_dirs_count; /* Directories count */
- __u16 bg_flags;
- __u32 bg_reserved[3];
+ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
+ __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */
+ __le16 bg_itable_unused; /* Unused inodes count */
+ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
__le32 bg_inode_table_hi; /* Inodes table block MSB */
};
+#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
+#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
+#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
+
#ifdef __KERNEL__
#include <linux/ext4_fs_i.h>
#include <linux/ext4_fs_sb.h>
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
+#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
EXT4_FEATURE_INCOMPAT_64BIT)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
projects / linux-2.6 / commitdiff