#include <linux/quotaops.h>
#include <linux/buffer_head.h>
+#include "group.h"
/*
* balloc.c contains the blocks allocation and deallocation routines
*/
* Calculate the block group number and offset, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
- unsigned long *blockgrpp, ext4_grpblk_t *offsetp)
+ ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
{
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_grpblk_t offset;
- blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
+ blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
if (offsetp)
*offsetp = offset;
if (blockgrpp)
- *blockgrpp = blocknr;
+ *blockgrpp = blocknr;
}
+/* 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,
+ ext4_group_t 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 %lu\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 = (ext4_inode_table(sb, gdp) - 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
* The file system contains group descriptors which are located after the
* super block. Each descriptor contains the number of the bitmap block and
* the free blocks count in the block. The descriptors are loaded in memory
- * when a file system is mounted (see ext4_read_super).
+ * when a file system is mounted (see ext4_fill_super).
*/
* group descriptor
*/
struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
- unsigned int block_group,
+ ext4_group_t block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
if (block_group >= sbi->s_groups_count) {
ext4_error (sb, "ext4_get_group_desc",
"block_group >= groups_count - "
- "block_group = %d, groups_count = %lu",
+ "block_group = %lu, groups_count = %lu",
block_group, sbi->s_groups_count);
return NULL;
if (!sbi->s_group_desc[group_desc]) {
ext4_error (sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
- "block_group = %d, group_desc = %lu, desc = %lu",
+ "block_group = %lu, group_desc = %lu, desc = %lu",
block_group, group_desc, offset);
return NULL;
}
return desc;
}
+static int ext4_valid_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *desc,
+ unsigned int block_group,
+ struct buffer_head *bh)
+{
+ ext4_grpblk_t offset;
+ ext4_grpblk_t next_zero_bit;
+ ext4_fsblk_t bitmap_blk;
+ ext4_fsblk_t group_first_block;
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+ /* with FLEX_BG, the inode/block bitmaps and itable
+ * blocks may not be in the group at all
+ * so the bitmap validation will be skipped for those groups
+ * or it has to also read the block group where the bitmaps
+ * are located to verify they are set.
+ */
+ return 1;
+ }
+ group_first_block = ext4_group_first_block_no(sb, block_group);
+
+ /* check whether block bitmap block number is set */
+ bitmap_blk = ext4_block_bitmap(sb, desc);
+ offset = bitmap_blk - group_first_block;
+ if (!ext4_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode bitmap block number is set */
+ bitmap_blk = ext4_inode_bitmap(sb, desc);
+ offset = bitmap_blk - group_first_block;
+ if (!ext4_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode table block number is set */
+ bitmap_blk = ext4_inode_table(sb, desc);
+ offset = bitmap_blk - group_first_block;
+ next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
+ offset + EXT4_SB(sb)->s_itb_per_group,
+ offset);
+ if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
+ /* good bitmap for inode tables */
+ return 1;
+
+err_out:
+ ext4_error(sb, __FUNCTION__,
+ "Invalid block bitmap - "
+ "block_group = %d, block = %llu",
+ block_group, bitmap_blk);
+ return 0;
+}
/**
* read_block_bitmap()
* @sb: super block
* @block_group: given block group
*
- * Read the bitmap for a given block_group, reading into the specified
- * slot in the superblock's bitmap cache.
+ * Read the bitmap for a given block_group,and validate the
+ * bits for block/inode/inode tables are set in the bitmaps
*
* Return buffer_head on success or NULL in case of failure.
*/
-static struct buffer_head *
-read_block_bitmap(struct super_block *sb, unsigned int block_group)
+struct buffer_head *
+read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc * desc;
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)
- goto error_out;
- bh = sb_bread(sb, ext4_block_bitmap(sb, desc));
- if (!bh)
- ext4_error (sb, "read_block_bitmap",
+ return NULL;
+ bitmap_blk = ext4_block_bitmap(sb, desc);
+ bh = sb_getblk(sb, bitmap_blk);
+ if (unlikely(!bh)) {
+ ext4_error(sb, __FUNCTION__,
+ "Cannot read block bitmap - "
+ "block_group = %d, block_bitmap = %llu",
+ (int)block_group, (unsigned long long)bitmap_blk);
+ return NULL;
+ }
+ if (bh_uptodate_or_lock(bh))
+ return bh;
+
+ if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ ext4_init_block_bitmap(sb, bh, block_group, desc);
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ return bh;
+ }
+ if (bh_submit_read(bh) < 0) {
+ put_bh(bh);
+ ext4_error(sb, __FUNCTION__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %llu",
- block_group,
- ext4_block_bitmap(sb, desc));
-error_out:
+ (int)block_group, (unsigned long long)bitmap_blk);
+ return NULL;
+ }
+ if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
+ put_bh(bh);
+ return NULL;
+ }
+
return bh;
}
/*
printk("Block Allocation Reservation Windows Map (%s):\n", fn);
while (n) {
- rsv = list_entry(n, struct ext4_reserve_window_node, rsv_node);
+ rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
if (verbose)
printk("reservation window 0x%p "
"start: %llu, end: %llu\n",
*/
static int
goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
- unsigned int group, struct super_block * sb)
+ ext4_group_t group, struct super_block *sb)
{
ext4_fsblk_t group_first_block, group_last_block;
* when setting the reservation window size through ioctl before the file
* is open for write (needs block allocation).
*
- * Needs truncate_mutex protection prior to call this function.
+ * Needs down_write(i_data_sem) protection prior to call this function.
*/
void ext4_init_block_alloc_info(struct inode *inode)
{
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
- unsigned long block_group;
+ ext4_group_t block_group;
ext4_grpblk_t bit;
unsigned long i;
unsigned long overflow;
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
- sbi->s_itb_per_group))
+ sbi->s_itb_per_group)) {
ext4_error (sb, "ext4_free_blocks",
"Freeing blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
+ goto error_return;
+ }
/*
* We are about to start releasing blocks in the bitmap,
/*
* An HJ special. This is expensive...
*/
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
jbd_unlock_bh_state(bitmap_bh);
{
struct buffer_head *debug_bh;
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_mod(&sbi->s_freeblocks_counter, count);
+ percpu_counter_add(&sbi->s_freeblocks_counter, count);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
here = 0;
p = ((char *)bh->b_data) + (here >> 3);
- r = memscan(p, 0, (maxblocks - here + 7) >> 3);
+ r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
next = (r - ((char *)bh->b_data)) << 3;
if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh))
* ext4_journal_release_buffer(), else we'll run out of credits.
*/
static ext4_grpblk_t
-ext4_try_to_allocate(struct super_block *sb, handle_t *handle, int group,
- struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal,
- unsigned long *count, struct ext4_reserve_window *my_rsv)
+ext4_try_to_allocate(struct super_block *sb, handle_t *handle,
+ ext4_group_t group, struct buffer_head *bitmap_bh,
+ ext4_grpblk_t grp_goal, unsigned long *count,
+ struct ext4_reserve_window *my_rsv)
{
ext4_fsblk_t group_first_block;
ext4_grpblk_t start, end;
prev = rsv;
next = rb_next(&rsv->rsv_node);
- rsv = list_entry(next,struct ext4_reserve_window_node,rsv_node);
+ rsv = rb_entry(next,struct ext4_reserve_window_node,rsv_node);
/*
* Reached the last reservation, we can just append to the
*/
static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
ext4_grpblk_t grp_goal, struct super_block *sb,
- unsigned int group, struct buffer_head *bitmap_bh)
+ ext4_group_t group, struct buffer_head *bitmap_bh)
{
struct ext4_reserve_window_node *search_head;
ext4_fsblk_t group_first_block, group_end_block, start_block;
* check if the first free block is within the
* free space we just reserved
*/
- if (start_block >= my_rsv->rsv_start && start_block < my_rsv->rsv_end)
+ if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end)
return 0; /* success */
/*
* if the first free bit we found is out of the reservable space
if (!next)
my_rsv->rsv_end += size;
else {
- next_rsv = list_entry(next, struct ext4_reserve_window_node, rsv_node);
+ next_rsv = rb_entry(next, struct ext4_reserve_window_node, rsv_node);
if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
my_rsv->rsv_end += size;
*/
static ext4_grpblk_t
ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
- unsigned int group, struct buffer_head *bitmap_bh,
+ ext4_group_t group, struct buffer_head *bitmap_bh,
ext4_grpblk_t grp_goal,
struct ext4_reserve_window_node * my_rsv,
unsigned long *count, int *errp)
}
/*
* grp_goal is a group relative block number (if there is a goal)
- * 0 < grp_goal < EXT4_BLOCKS_PER_GROUP(sb)
+ * 0 <= grp_goal < EXT4_BLOCKS_PER_GROUP(sb)
* first block is a filesystem wide block number
* first block is the block number of the first block in this group
*/
if (!goal_in_my_reservation(&my_rsv->rsv_window,
grp_goal, group, sb))
grp_goal = -1;
- } else if (grp_goal > 0 &&
- (my_rsv->rsv_end-grp_goal+1) < *count)
- try_to_extend_reservation(my_rsv, sb,
- *count-my_rsv->rsv_end + grp_goal - 1);
+ } else if (grp_goal >= 0) {
+ int curr = my_rsv->rsv_end -
+ (grp_goal + group_first_block) + 1;
+
+ if (curr < *count)
+ try_to_extend_reservation(my_rsv, sb,
+ *count - curr);
+ }
if ((my_rsv->rsv_start > group_last_block) ||
(my_rsv->rsv_end < group_first_block)) {
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gdp_bh;
- unsigned long group_no;
- int goal_group;
+ ext4_group_t group_no;
+ ext4_group_t goal_group;
ext4_grpblk_t grp_target_blk; /* blockgroup relative goal block */
ext4_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/
ext4_fsblk_t ret_block; /* filesyetem-wide allocated block */
- int bgi; /* blockgroup iteration index */
+ ext4_group_t bgi; /* blockgroup iteration index */
int fatal = 0, err;
int performed_allocation = 0;
ext4_grpblk_t free_blocks; /* number of free blocks in a group */
struct ext4_reserve_window_node *my_rsv = NULL;
struct ext4_block_alloc_info *block_i;
unsigned short windowsz = 0;
-#ifdef EXT4FS_DEBUG
- static int goal_hits, goal_attempts;
-#endif
- unsigned long ngroups;
+ ext4_group_t ngroups;
unsigned long num = *count;
*errp = -ENOSPC;
sbi = EXT4_SB(sb);
es = EXT4_SB(sb)->s_es;
- ext4_debug("goal=%lu.\n", goal);
+ ext4_debug("goal=%llu.\n", goal);
/*
* Allocate a block from reservation only when
* filesystem is mounted with reservation(default,-o reservation), and
if (group_no >= ngroups)
group_no = 0;
gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
- if (!gdp) {
- *errp = -EIO;
- goto out;
- }
+ if (!gdp)
+ goto io_error;
free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
/*
* skip this group if the number of
*/
if (my_rsv) {
my_rsv = NULL;
+ windowsz = 0;
group_no = goal_group;
goto retry_alloc;
}
allocated:
- ext4_debug("using block group %d(%d)\n",
+ ext4_debug("using block group %lu(%d)\n",
group_no, gdp->bg_free_blocks_count);
BUFFER_TRACE(gdp_bh, "get_write_access");
ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no);
if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
- in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
+ in_range(ext4_inode_bitmap(sb, gdp), ret_block, num) ||
in_range(ret_block, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group) ||
in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group))
+ EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, "ext4_new_block",
"Allocating block in system zone - "
"blocks from %llu, length %lu",
ret_block, num);
+ goto out;
+ }
performed_allocation = 1;
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
{
struct buffer_head *debug_bh;
* list of some description. We don't know in advance whether
* the caller wants to use it as metadata or data.
*/
- ext4_debug("allocating block %lu. Goal hits %d of %d.\n",
- 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_mod(&sbi->s_freeblocks_counter, -num);
+ percpu_counter_sub(&sbi->s_freeblocks_counter, num);
BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
err = ext4_journal_dirty_metadata(handle, gdp_bh);
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
- int i;
- unsigned long ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t i;
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
continue;
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
- printk("group %d: stored = %d, counted = %lu\n",
+ printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
i, le16_to_cpu(gdp->bg_free_blocks_count), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk("ext4_count_free_blocks: stored = %llu"
", computed = %llu, %llu\n",
- EXT4_FREE_BLOCKS_COUNT(es),
+ ext4_free_blocks_count(es),
desc_count, bitmap_count);
return bitmap_count;
#else
#endif
}
-static inline int
-block_in_use(ext4_fsblk_t block, struct super_block *sb, unsigned char *map)
-{
- ext4_grpblk_t offset;
-
- ext4_get_group_no_and_offset(sb, block, NULL, &offset);
- return ext4_test_bit (offset, map);
-}
-
-static inline int test_root(int a, int b)
+static inline int test_root(ext4_group_t a, int b)
{
int num = b;
return num == a;
}
-static int ext4_group_sparse(int group)
+static int ext4_group_sparse(ext4_group_t group)
{
if (group <= 1)
return 1;
* Return the number of blocks used by the superblock (primary or backup)
* in this group. Currently this will be only 0 or 1.
*/
-int ext4_bg_has_super(struct super_block *sb, int group)
+int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
return 1;
}
-static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group)
+static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
+ ext4_group_t group)
{
unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
- unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb);
- unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
+ ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb);
+ ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
if (group == first || group == first + 1 || group == last)
return 1;
return 0;
}
-static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
+static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
+ ext4_group_t group)
{
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
* (primary or backup) in this group. In the future there may be a
* different number of descriptor blocks in each group.
*/
-unsigned long ext4_bg_num_gdb(struct super_block *sb, int group)
+unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
{
unsigned long first_meta_bg =
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
projects / linux.git / blobdiff