/* 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, __func__, "Checksum bad for group %lu\n",
+ ext4_error(sb, __func__, "Checksum bad for group %u",
block_group);
- gdp->bg_free_blocks_count = 0;
- gdp->bg_free_inodes_count = 0;
- gdp->bg_itable_unused = 0;
+ ext4_free_blks_set(sb, gdp, 0);
+ ext4_free_inodes_set(sb, gdp, 0);
+ ext4_itable_unused_set(sb, gdp, 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),
+ mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
bh->b_data);
return EXT4_INODES_PER_GROUP(sb);
if (unlikely(!bh)) {
ext4_error(sb, __func__,
"Cannot read inode bitmap - "
- "block_group = %lu, inode_bitmap = %llu",
+ "block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
}
- if (buffer_uptodate(bh) &&
- !(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+ if (bitmap_uptodate(bh))
return bh;
lock_buffer(bh);
+ if (bitmap_uptodate(bh)) {
+ unlock_buffer(bh);
+ return bh;
+ }
spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
ext4_init_inode_bitmap(sb, bh, block_group, desc);
+ set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
- unlock_buffer(bh);
spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ unlock_buffer(bh);
return bh;
}
spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ if (buffer_uptodate(bh)) {
+ /*
+ * if not uninit if bh is uptodate,
+ * bitmap is also uptodate
+ */
+ set_bitmap_uptodate(bh);
+ unlock_buffer(bh);
+ return bh;
+ }
+ /*
+ * submit the buffer_head for read. We can
+ * safely mark the bitmap as uptodate now.
+ * We do it here so the bitmap uptodate bit
+ * get set with buffer lock held.
+ */
+ set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
ext4_error(sb, __func__,
"Cannot read inode bitmap - "
- "block_group = %lu, inode_bitmap = %llu",
+ "block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
}
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
- int fatal = 0, err;
+ int fatal = 0, err, count, cleared;
ext4_group_t flex_group;
if (atomic_read(&inode->i_count) > 1) {
ino = inode->i_ino;
ext4_debug("freeing inode %lu\n", ino);
+ trace_mark(ext4_free_inode,
+ "dev %s ino %lu mode %d uid %lu gid %lu bocks %llu",
+ sb->s_id, inode->i_ino, inode->i_mode,
+ (unsigned long) inode->i_uid, (unsigned long) inode->i_gid,
+ (unsigned long long) inode->i_blocks);
/*
* Note: we must free any quota before locking the superblock,
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
- if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
- bit, bitmap_bh->b_data))
+ spin_lock(sb_bgl_lock(sbi, block_group));
+ cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+ spin_unlock(sb_bgl_lock(sbi, block_group));
+ if (!cleared)
ext4_error(sb, "ext4_free_inode",
"bit already cleared for inode %lu", ino);
else {
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
- le16_add_cpu(&gdp->bg_free_inodes_count, 1);
- if (is_directory)
- le16_add_cpu(&gdp->bg_used_dirs_count, -1);
+ count = ext4_free_inodes_count(sb, gdp) + 1;
+ ext4_free_inodes_set(sb, gdp, count);
+ if (is_directory) {
+ count = ext4_used_dirs_count(sb, gdp) - 1;
+ ext4_used_dirs_set(sb, gdp, count);
+ }
gdp->bg_checksum = ext4_group_desc_csum(sbi,
block_group, gdp);
spin_unlock(sb_bgl_lock(sbi, block_group));
for (group = 0; group < ngroups; group++) {
desc = ext4_get_group_desc(sb, group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ if (ext4_free_inodes_count(sb, desc) < avefreei)
continue;
if (!best_desc ||
- (le16_to_cpu(desc->bg_free_blocks_count) >
- le16_to_cpu(best_desc->bg_free_blocks_count))) {
+ (ext4_free_blks_count(sb, desc) >
+ ext4_free_blks_count(sb, best_desc))) {
*best_group = group;
best_desc = desc;
ret = 0;
for (i = best_flex * flex_size; i < ngroups &&
i < (best_flex + 1) * flex_size; i++) {
desc = ext4_get_group_desc(sb, i, &bh);
- if (le16_to_cpu(desc->bg_free_inodes_count)) {
+ if (ext4_free_inodes_count(sb, desc)) {
*best_group = i;
goto out;
}
for (i = 0; i < ngroups; i++) {
grp = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, grp, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
+ if (ext4_used_dirs_count(sb, desc) >= best_ndir)
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ if (ext4_free_inodes_count(sb, desc) < avefreei)
continue;
- if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
+ if (ext4_free_blks_count(sb, desc) < avefreeb)
continue;
*group = grp;
ret = 0;
- best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+ best_ndir = ext4_used_dirs_count(sb, desc);
}
if (ret == 0)
return ret;
for (i = 0; i < ngroups; i++) {
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
+ if (ext4_used_dirs_count(sb, desc) >= max_dirs)
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
+ if (ext4_free_inodes_count(sb, desc) < min_inodes)
continue;
- if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
+ if (ext4_free_blks_count(sb, desc) < min_blocks)
continue;
return 0;
}
for (i = 0; i < ngroups; i++) {
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && desc->bg_free_inodes_count &&
- le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_inodes_count(sb, desc) >= avefreei)
return 0;
}
*/
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
return 0;
/*
if (*group >= ngroups)
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
return 0;
}
if (++*group >= ngroups)
*group = 0;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+ if (desc && ext4_free_inodes_count(sb, desc))
return 0;
}
}
/*
+ * claim the inode from the inode bitmap. If the group
+ * is uninit we need to take the groups's sb_bgl_lock
+ * and clear the uninit flag. The inode bitmap update
+ * and group desc uninit flag clear should be done
+ * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * doesn't race with the ext4_claim_inode
+ */
+static int ext4_claim_inode(struct super_block *sb,
+ struct buffer_head *inode_bitmap_bh,
+ unsigned long ino, ext4_group_t group, int mode)
+{
+ int free = 0, retval = 0, count;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+ spin_lock(sb_bgl_lock(sbi, group));
+ if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
+ /* not a free inode */
+ retval = 1;
+ goto err_ret;
+ }
+ ino++;
+ if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
+ ino > EXT4_INODES_PER_GROUP(sb)) {
+ spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_error(sb, __func__,
+ "reserved inode or inode > inodes count - "
+ "block_group = %u, inode=%lu", group,
+ ino + group * EXT4_INODES_PER_GROUP(sb));
+ return 1;
+ }
+ /* 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_unused 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) -
+ ext4_itable_unused_count(sb, gdp);
+ }
+
+ /*
+ * 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)
+ ext4_itable_unused_set(sb, gdp,
+ (EXT4_INODES_PER_GROUP(sb) - ino));
+ }
+ count = ext4_free_inodes_count(sb, gdp) - 1;
+ ext4_free_inodes_set(sb, gdp, count);
+ if (S_ISDIR(mode)) {
+ count = ext4_used_dirs_count(sb, gdp) + 1;
+ ext4_used_dirs_set(sb, gdp, count);
+ }
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+err_ret:
+ spin_unlock(sb_bgl_lock(sbi, group));
+ return retval;
+}
+
+/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
{
struct super_block *sb;
- struct buffer_head *bitmap_bh = NULL;
- struct buffer_head *bh2;
+ struct buffer_head *inode_bitmap_bh = NULL;
+ struct buffer_head *group_desc_bh;
ext4_group_t group = 0;
unsigned long ino = 0;
struct inode *inode;
struct inode *ret;
ext4_group_t i;
int free = 0;
+ static int once = 1;
ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
return ERR_PTR(-EPERM);
sb = dir->i_sb;
+ trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
+ dir->i_ino, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
if (sbi->s_log_groups_per_flex) {
ret2 = find_group_flex(sb, dir, &group);
+ if (ret2 == -1) {
+ ret2 = find_group_other(sb, dir, &group);
+ if (ret2 == 0 && once)
+ once = 0;
+ printk(KERN_NOTICE "ext4: find_group_flex "
+ "failed, fallback succeeded dir %lu\n",
+ dir->i_ino);
+ }
goto got_group;
}
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
- gdp = ext4_get_group_desc(sb, group, &bh2);
+ gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
if (!gdp)
goto fail;
- brelse(bitmap_bh);
- bitmap_bh = ext4_read_inode_bitmap(sb, group);
- if (!bitmap_bh)
+ brelse(inode_bitmap_bh);
+ inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+ if (!inode_bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
- bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
+ inode_bitmap_bh->b_data,
+ EXT4_INODES_PER_GROUP(sb), ino);
+
if (ino < EXT4_INODES_PER_GROUP(sb)) {
- BUFFER_TRACE(bitmap_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, bitmap_bh);
+ BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle,
+ inode_bitmap_bh);
if (err)
goto fail;
- if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
- ino, bitmap_bh->b_data)) {
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle,
+ group_desc_bh);
+ if (err)
+ goto fail;
+ if (!ext4_claim_inode(sb, inode_bitmap_bh,
+ ino, group, mode)) {
/* we won it */
- BUFFER_TRACE(bitmap_bh,
+ BUFFER_TRACE(inode_bitmap_bh,
"call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle,
- inode,
- bitmap_bh);
+ inode,
+ inode_bitmap_bh);
if (err)
goto fail;
+ /* zero bit is inode number 1*/
+ ino++;
goto got;
}
/* we lost it */
- ext4_handle_release_buffer(handle, bitmap_bh);
+ ext4_handle_release_buffer(handle, inode_bitmap_bh);
+ ext4_handle_release_buffer(handle, group_desc_bh);
if (++ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
goto out;
got:
- ino++;
- if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
- ino > EXT4_INODES_PER_GROUP(sb)) {
- ext4_error(sb, __func__,
- "reserved inode or inode > inodes count - "
- "block_group = %lu, 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 = ext4_read_block_bitmap(sb, group);
+ struct buffer_head *block_bitmap_bh;
- BUFFER_TRACE(block_bh, "get block bitmap access");
- err = ext4_journal_get_write_access(handle, block_bh);
+ block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+ BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
+ err = ext4_journal_get_write_access(handle, block_bitmap_bh);
if (err) {
- brelse(block_bh);
+ brelse(block_bitmap_bh);
goto fail;
}
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);
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_blks_set(sb, gdp, free);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
- BUFFER_TRACE(block_bh, "dirty block bitmap");
+ BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
err = ext4_handle_dirty_metadata(handle,
- NULL, block_bh);
+ NULL, block_bitmap_bh);
}
- brelse(block_bh);
+ brelse(block_bitmap_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_unused 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);
- }
-
- le16_add_cpu(&gdp->bg_free_inodes_count, -1);
- if (S_ISDIR(mode)) {
- le16_add_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_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, NULL, bh2);
- if (err) goto fail;
+ BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
+ if (err)
+ goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
if (err)
goto fail_free_drop;
- if (test_opt(sb, EXTENTS)) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
/* set extent flag only for directory, file and normal symlink*/
if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
}
ext4_debug("allocating inode %lu\n", inode->i_ino);
+ trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d",
+ sb->s_id, inode->i_ino, dir->i_ino, mode);
goto really_out;
fail:
ext4_std_error(sb, err);
iput(inode);
ret = ERR_PTR(err);
really_out:
- brelse(bitmap_bh);
+ brelse(inode_bitmap_bh);
return ret;
fail_free_drop:
inode->i_nlink = 0;
unlock_new_inode(inode);
iput(inode);
- brelse(bitmap_bh);
+ brelse(inode_bitmap_bh);
return ERR_PTR(err);
}
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ desc_count += ext4_free_inodes_count(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_inode_bitmap(sb, i);
if (!bitmap_bh)
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
- i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+ i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ desc_count += ext4_free_inodes_count(sb, gdp);
cond_resched();
}
return desc_count;
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- count += le16_to_cpu(gdp->bg_used_dirs_count);
+ count += ext4_used_dirs_count(sb, gdp);
}
return count;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff