* 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 ext3_read_super).
+ * when a file system is mounted (see ext3_fill_super).
*/
/**
* ext3_get_group_desc() -- load group descriptor from disk
- * @sb: super block
+ * @sb: super block
* @block_group: given block group
* @bh: pointer to the buffer head to store the block
* group descriptor
return desc + offset;
}
+static int ext3_valid_block_bitmap(struct super_block *sb,
+ struct ext3_group_desc *desc,
+ unsigned int block_group,
+ struct buffer_head *bh)
+{
+ ext3_grpblk_t offset;
+ ext3_grpblk_t next_zero_bit;
+ ext3_fsblk_t bitmap_blk;
+ ext3_fsblk_t group_first_block;
+
+ group_first_block = ext3_group_first_block_no(sb, block_group);
+
+ /* check whether block bitmap block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+ offset = bitmap_blk - group_first_block;
+ if (!ext3_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode bitmap block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
+ offset = bitmap_blk - group_first_block;
+ if (!ext3_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode table block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_inode_table);
+ offset = bitmap_blk - group_first_block;
+ next_zero_bit = ext3_find_next_zero_bit(bh->b_data,
+ offset + EXT3_SB(sb)->s_itb_per_group,
+ offset);
+ if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group)
+ /* good bitmap for inode tables */
+ return 1;
+
+err_out:
+ ext3_error(sb, __func__,
+ "Invalid block bitmap - "
+ "block_group = %d, block = %lu",
+ 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.
*/
{
struct ext3_group_desc * desc;
struct buffer_head * bh = NULL;
+ ext3_fsblk_t bitmap_blk;
- desc = ext3_get_group_desc (sb, block_group, NULL);
+ desc = ext3_get_group_desc(sb, block_group, NULL);
if (!desc)
- goto error_out;
- bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap));
- if (!bh)
- ext3_error (sb, "read_block_bitmap",
+ return NULL;
+ bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+ bh = sb_getblk(sb, bitmap_blk);
+ if (unlikely(!bh)) {
+ ext3_error(sb, __func__,
+ "Cannot read block bitmap - "
+ "block_group = %d, block_bitmap = %u",
+ block_group, le32_to_cpu(desc->bg_block_bitmap));
+ return NULL;
+ }
+ if (likely(bh_uptodate_or_lock(bh)))
+ return bh;
+
+ if (bh_submit_read(bh) < 0) {
+ brelse(bh);
+ ext3_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
-error_out:
+ return NULL;
+ }
+ ext3_valid_block_bitmap(sb, desc, block_group, bh);
+ /*
+ * file system mounted not to panic on error, continue with corrupt
+ * bitmap
+ */
return bh;
}
/*
printk("Block Allocation Reservation Windows Map (%s):\n", fn);
while (n) {
- rsv = list_entry(n, struct ext3_reserve_window_node, rsv_node);
+ rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);
if (verbose)
printk("reservation window 0x%p "
"start: %lu, end: %lu\n",
prev = rsv;
}
printk("Window map complete.\n");
- if (bad)
- BUG();
+ BUG_ON(bad);
}
#define rsv_window_dump(root, verbose) \
- __rsv_window_dump((root), (verbose), __FUNCTION__)
+ __rsv_window_dump((root), (verbose), __func__)
#else
#define rsv_window_dump(root, verbose) do {} while (0)
#endif
ext3_fsblk_t group_first_block, group_last_block;
group_first_block = ext3_group_first_block_no(sb, group);
- group_last_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1;
+ group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);
if ((rsv->_rsv_start > group_last_block) ||
(rsv->_rsv_end < group_first_block))
rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
- /*
+ /*
* if filesystem is mounted with NORESERVATION, the goal
* reservation window size is set to zero to indicate
* block reservation is off
in_range (block, le32_to_cpu(desc->bg_inode_table),
sbi->s_itb_per_group) ||
in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
- sbi->s_itb_per_group))
+ sbi->s_itb_per_group)) {
ext3_error (sb, "ext3_free_blocks",
"Freeing blocks in system zones - "
"Block = "E3FSBLK", count = %lu",
block, count);
+ goto error_return;
+ }
/*
* We are about to start releasing blocks in the bitmap,
if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit + i, bitmap_bh->b_data)) {
jbd_unlock_bh_state(bitmap_bh);
- ext3_error(sb, __FUNCTION__,
+ ext3_error(sb, __func__,
"bit already cleared for block "E3FSBLK,
block + i);
jbd_lock_bh_state(bitmap_bh);
jbd_unlock_bh_state(bitmap_bh);
spin_lock(sb_bgl_lock(sbi, block_group));
- desc->bg_free_blocks_count =
- cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) +
- group_freed);
+ le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
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");
count = overflow;
goto do_more;
}
- sb->s_dirt = 1;
+
error_return:
brelse(bitmap_bh);
ext3_std_error(sb, err);
}
ext3_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
if (dquot_freed_blocks)
- DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
+ vfs_dq_free_block(inode, dquot_freed_blocks);
return;
}
jbd_lock_bh_state(bh);
if (jh->b_committed_data)
start = ext3_find_next_zero_bit(jh->b_committed_data,
- maxblocks, next);
+ maxblocks, next);
jbd_unlock_bh_state(bh);
}
return -1;
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 && ext3_test_allocatable(next, bh))
* and at last, allocate the blocks by claiming the found free bit as allocated.
*
* To set the range of this allocation:
- * if there is a reservation window, only try to allocate block(s) from the
+ * if there is a reservation window, only try to allocate block(s) from the
* file's own reservation window;
* Otherwise, the allocation range starts from the give goal block, ends at
- * the block group's last block.
+ * the block group's last block.
*
* If we failed to allocate the desired block then we may end up crossing to a
* new bitmap. In that case we must release write access to the old one via
}
/**
- * find_next_reservable_window():
+ * find_next_reservable_window():
* find a reservable space within the given range.
* It does not allocate the reservation window for now:
* alloc_new_reservation() will do the work later.
*
- * @search_head: the head of the searching list;
+ * @search_head: the head of the searching list;
* This is not necessarily the list head of the whole filesystem
*
* We have both head and start_block to assist the search
* but we will shift to the place where start_block is,
* then start from there, when looking for a reservable space.
*
- * @size: the target new reservation window size
+ * @size: the target new reservation window size
*
- * @group_first_block: the first block we consider to start
+ * @group_first_block: the first block we consider to start
* the real search from
*
- * @last_block:
+ * @last_block:
* the maximum block number that our goal reservable space
* could start from. This is normally the last block in this
* group. The search will end when we found the start of next
* This could handle the cross boundary reservation window
* request.
*
- * basically we search from the given range, rather than the whole
- * reservation double linked list, (start_block, last_block)
- * to find a free region that is of my size and has not
- * been reserved.
+ * basically we search from the given range, rather than the whole
+ * reservation double linked list, (start_block, last_block)
+ * to find a free region that is of my size and has not
+ * been reserved.
*
*/
static int find_next_reservable_window(
prev = rsv;
next = rb_next(&rsv->rsv_node);
- rsv = list_entry(next,struct ext3_reserve_window_node,rsv_node);
+ rsv = rb_entry(next,struct ext3_reserve_window_node,rsv_node);
/*
* Reached the last reservation, we can just append to the
/*
* Found a reserveable space big enough. We could
* have a reservation across the group boundary here
- */
+ */
break;
}
}
}
/**
- * alloc_new_reservation()--allocate a new reservation window
+ * alloc_new_reservation()--allocate a new reservation window
*
* To make a new reservation, we search part of the filesystem
* reservation list (the list that inside the group). We try to
spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;
group_first_block = ext3_group_first_block_no(sb, group);
- group_end_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1;
+ group_end_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);
if (grp_goal < 0)
start_block = group_first_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 ext3_reserve_window_node, rsv_node);
+ next_rsv = rb_entry(next, struct ext3_reserve_window_node, rsv_node);
if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
my_rsv->rsv_end += size;
struct ext3_reserve_window_node * my_rsv,
unsigned long *count, int *errp)
{
- ext3_fsblk_t group_first_block;
+ ext3_fsblk_t group_first_block, group_last_block;
ext3_grpblk_t ret = 0;
int fatal;
unsigned long num = *count;
}
/*
* grp_goal is a group relative block number (if there is a goal)
- * 0 < grp_goal < EXT3_BLOCKS_PER_GROUP(sb)
+ * 0 <= grp_goal < EXT3_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
*/
group_first_block = ext3_group_first_block_no(sb, group);
+ group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);
/*
* Basically we will allocate a new block from inode's reservation
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);
-
- if ((my_rsv->rsv_start >= group_first_block +
- EXT3_BLOCKS_PER_GROUP(sb))
- || (my_rsv->rsv_end < group_first_block)) {
+ } 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)) {
rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1);
BUG();
}
free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
- sbi->s_resuid != current->fsuid &&
+ sbi->s_resuid != current_fsuid() &&
(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
return 0;
}
/*
* Check quota for allocation of this block.
*/
- if (DQUOT_ALLOC_BLOCK(inode, num)) {
+ if (vfs_dq_alloc_block(inode, num)) {
*errp = -EDQUOT;
return 0;
}
* turn off reservation for this allocation
*/
if (my_rsv && (free_blocks < windowsz)
+ && (free_blocks > 0)
&& (rsv_is_empty(&my_rsv->rsv_window)))
my_rsv = NULL;
/*
* Now search the rest of the groups. We assume that
- * i and gdp correctly point to the last group visited.
+ * group_no and gdp correctly point to the last group visited.
*/
for (bgi = 0; bgi < ngroups; bgi++) {
group_no++;
if (group_no >= ngroups)
group_no = 0;
gdp = ext3_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
* free blocks is less than half of the reservation
* window size.
*/
- if (free_blocks <= (windowsz/2))
+ if (my_rsv && (free_blocks <= (windowsz/2)))
continue;
brelse(bitmap_bh);
*/
if (my_rsv) {
my_rsv = NULL;
+ windowsz = 0;
group_no = goal_group;
goto retry_alloc;
}
in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
EXT3_SB(sb)->s_itb_per_group) ||
in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table),
- EXT3_SB(sb)->s_itb_per_group))
+ EXT3_SB(sb)->s_itb_per_group)) {
ext3_error(sb, "ext3_new_block",
"Allocating block in system zone - "
"blocks from "E3FSBLK", length %lu",
ret_block, num);
+ /*
+ * claim_block() marked the blocks we allocated as in use. So we
+ * may want to selectively mark some of the blocks as free.
+ */
+ goto retry_alloc;
+ }
performed_allocation = 1;
if (ext3_test_bit(grp_alloc_blk+i,
bh2jh(bitmap_bh)->b_committed_data)) {
printk("%s: block was unexpectedly set in "
- "b_committed_data\n", __FUNCTION__);
+ "b_committed_data\n", __func__);
}
}
}
ret_block, goal_hits, goal_attempts);
spin_lock(sb_bgl_lock(sbi, group_no));
- gdp->bg_free_blocks_count =
- cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num);
+ le16_add_cpu(&gdp->bg_free_blocks_count, -num);
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 = ext3_journal_dirty_metadata(handle, gdp_bh);
if (!fatal)
fatal = err;
- sb->s_dirt = 1;
if (fatal)
goto out;
*errp = 0;
brelse(bitmap_bh);
- DQUOT_FREE_BLOCK(inode, *count-num);
+ vfs_dq_free_block(inode, *count-num);
*count = num;
return ret_block;
* Undo the block allocation
*/
if (!performed_allocation)
- DQUOT_FREE_BLOCK(inode, *count);
+ vfs_dq_free_block(inode, *count);
brelse(bitmap_bh);
return 0;
}
#endif
}
-static inline int
-block_in_use(ext3_fsblk_t block, struct super_block *sb, unsigned char *map)
-{
- return ext3_test_bit ((block -
- le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block)) %
- EXT3_BLOCKS_PER_GROUP(sb), map);
-}
-
static inline int test_root(int a, int b)
{
int num = b;
static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group)
{
- if (EXT3_HAS_RO_COMPAT_FEATURE(sb,
- EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
- !ext3_group_sparse(group))
- return 0;
- return EXT3_SB(sb)->s_gdb_count;
+ return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0;
}
/**
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff