#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,
+ ext4_group_t 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 %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, (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
* Return buffer_head of bitmap on success or NULL.
*/
static struct buffer_head *
-read_inode_bitmap(struct super_block * sb, unsigned long block_group)
+read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
struct buffer_head *bh = NULL;
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 - "
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
- unsigned long block_group;
+ ext4_group_t block_group;
unsigned long bit;
struct ext4_group_desc * gdp;
struct ext4_super_block * es;
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)
* For other inodes, search forward from the parent directory\'s block
* group to find a free inode.
*/
-static int find_group_dir(struct super_block *sb, struct inode *parent)
+static int find_group_dir(struct super_block *sb, struct inode *parent,
+ ext4_group_t *best_group)
{
- int ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
unsigned int freei, avefreei;
struct ext4_group_desc *desc, *best_desc = NULL;
- int group, best_group = -1;
+ ext4_group_t group;
+ int ret = -1;
freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
avefreei = freei / ngroups;
if (!best_desc ||
(le16_to_cpu(desc->bg_free_blocks_count) >
le16_to_cpu(best_desc->bg_free_blocks_count))) {
- best_group = group;
+ *best_group = group;
best_desc = desc;
+ ret = 0;
}
}
- return best_group;
+ return ret;
}
/*
#define INODE_COST 64
#define BLOCK_COST 256
-static int find_group_orlov(struct super_block *sb, struct inode *parent)
+static int find_group_orlov(struct super_block *sb, struct inode *parent,
+ ext4_group_t *group)
{
- int parent_group = EXT4_I(parent)->i_block_group;
+ ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
- int ngroups = sbi->s_groups_count;
+ ext4_group_t ngroups = sbi->s_groups_count;
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
unsigned int ndirs;
int max_debt, max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
- int group = -1, i;
+ ext4_group_t i;
struct ext4_group_desc *desc;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
if ((parent == sb->s_root->d_inode) ||
(EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
- int best_group = -1;
+ ext4_group_t grp;
+ int ret = -1;
- get_random_bytes(&group, sizeof(group));
- parent_group = (unsigned)group % ngroups;
+ get_random_bytes(&grp, sizeof(grp));
+ parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
- group = (parent_group + i) % ngroups;
- desc = ext4_get_group_desc (sb, group, NULL);
+ grp = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc(sb, grp, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
continue;
- best_group = group;
+ *group = grp;
+ ret = 0;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
}
- if (best_group >= 0)
- return best_group;
+ if (ret == 0)
+ return ret;
goto fallback;
}
max_debt = 1;
for (i = 0; i < ngroups; i++) {
- group = (parent_group + i) % ngroups;
- desc = ext4_get_group_desc (sb, group, NULL);
+ *group = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc(sb, *group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
continue;
- return group;
+ return 0;
}
fallback:
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)
- continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
- return group;
+ *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)
+ return 0;
}
if (avefreei) {
return -1;
}
-static int find_group_other(struct super_block *sb, struct inode *parent)
+static int find_group_other(struct super_block *sb, struct inode *parent,
+ ext4_group_t *group)
{
- int parent_group = EXT4_I(parent)->i_block_group;
- int ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *desc;
- int group, i;
+ ext4_group_t i;
/*
* Try to place the inode in its parent directory
*/
- group = parent_group;
- desc = ext4_get_group_desc (sb, group, NULL);
+ *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))
- return group;
+ return 0;
/*
* We're going to place this inode in a different blockgroup from its
*
* So add our directory's i_ino into the starting point for the hash.
*/
- group = (group + parent->i_ino) % ngroups;
+ *group = (*group + parent->i_ino) % ngroups;
/*
* Use a quadratic hash to find a group with a free inode and some free
* blocks.
*/
for (i = 1; i < ngroups; i <<= 1) {
- group += i;
- if (group >= ngroups)
- group -= ngroups;
- desc = ext4_get_group_desc (sb, group, NULL);
+ *group += i;
+ 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))
- return group;
+ return 0;
}
/*
* That failed: try linear search for a free inode, even if that group
* has no free blocks.
*/
- group = parent_group;
+ *group = parent_group;
for (i = 0; i < ngroups; i++) {
- if (++group >= ngroups)
- group = 0;
- desc = ext4_get_group_desc (sb, group, NULL);
+ if (++*group >= ngroups)
+ *group = 0;
+ desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && le16_to_cpu(desc->bg_free_inodes_count))
- return group;
+ return 0;
}
return -1;
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
- int group;
+ ext4_group_t group = 0;
unsigned long ino = 0;
struct inode * inode;
struct ext4_group_desc * gdp = NULL;
struct ext4_super_block * es;
struct ext4_inode_info *ei;
struct ext4_sb_info *sbi;
- int err = 0;
+ int ret2, err = 0;
struct inode *ret;
- int i;
+ ext4_group_t i;
+ int free = 0;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
- group = find_group_dir(sb, dir);
+ ret2 = find_group_dir(sb, dir, &group);
else
- group = find_group_orlov(sb, dir);
+ ret2 = find_group_orlov(sb, dir, &group);
} else
- group = find_group_other(sb, dir);
+ ret2 = find_group_other(sb, dir, &group);
err = -ENOSPC;
- if (group == -1)
+ if (ret2 == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
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 = %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 = 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 =
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
- ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
+ /*
+ * Don't inherit extent flag from directory. We set extent flag on
+ * newly created directory and file only if -o extent mount option is
+ * specified
+ */
+ ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL);
if (S_ISLNK(mode))
ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
/* dirsync only applies to directories */
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT4_DIRSYNC_FL;
ei->i_file_acl = 0;
- ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
goto fail_free_drop;
}
if (test_opt(sb, EXTENTS)) {
- EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
- ext4_ext_tree_init(handle, inode);
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
- err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
- if (err) goto fail;
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
- BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ /* set extent flag only for directory and file */
+ if (S_ISDIR(mode) || S_ISREG(mode)) {
+ EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+ ext4_ext_tree_init(handle, inode);
+ err = ext4_update_incompat_feature(handle, sb,
+ EXT4_FEATURE_INCOMPAT_EXTENTS);
+ if (err)
+ goto fail;
}
}
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
{
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
- unsigned long block_group;
+ ext4_group_t block_group;
int bit;
- struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *bitmap_bh;
struct inode *inode = NULL;
+ long err = -EIO;
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
ext4_warning(sb, __FUNCTION__,
"bad orphan ino %lu! e2fsck was run?", ino);
- goto out;
+ goto error;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
if (!bitmap_bh) {
ext4_warning(sb, __FUNCTION__,
"inode bitmap error for orphan %lu", ino);
- goto out;
+ goto error;
}
/* Having the inode bit set should be a 100% indicator that this
* is a valid orphan (no e2fsck run on fs). Orphans also include
* inodes that were being truncated, so we can't check i_nlink==0.
*/
- if (!ext4_test_bit(bit, bitmap_bh->b_data) ||
- !(inode = iget(sb, ino)) || is_bad_inode(inode) ||
- NEXT_ORPHAN(inode) > max_ino) {
- ext4_warning(sb, __FUNCTION__,
- "bad orphan inode %lu! e2fsck was run?", ino);
- printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
- bit, (unsigned long long)bitmap_bh->b_blocknr,
- ext4_test_bit(bit, bitmap_bh->b_data));
- printk(KERN_NOTICE "inode=%p\n", inode);
- if (inode) {
- printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
- is_bad_inode(inode));
- printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
- NEXT_ORPHAN(inode));
- printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
- }
+ if (!ext4_test_bit(bit, bitmap_bh->b_data))
+ goto bad_orphan;
+
+ inode = ext4_iget(sb, ino);
+ if (IS_ERR(inode))
+ goto iget_failed;
+
+ if (NEXT_ORPHAN(inode) > max_ino)
+ goto bad_orphan;
+ brelse(bitmap_bh);
+ return inode;
+
+iget_failed:
+ err = PTR_ERR(inode);
+ inode = NULL;
+bad_orphan:
+ ext4_warning(sb, __FUNCTION__,
+ "bad orphan inode %lu! e2fsck was run?", ino);
+ printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ bit, (unsigned long long)bitmap_bh->b_blocknr,
+ ext4_test_bit(bit, bitmap_bh->b_data));
+ printk(KERN_NOTICE "inode=%p\n", inode);
+ if (inode) {
+ printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+ is_bad_inode(inode));
+ printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+ NEXT_ORPHAN(inode));
+ printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
/* Avoid freeing blocks if we got a bad deleted inode */
- if (inode && inode->i_nlink == 0)
+ if (inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
- inode = NULL;
}
-out:
brelse(bitmap_bh);
- return inode;
+error:
+ return ERR_PTR(err);
}
unsigned long ext4_count_free_inodes (struct super_block * sb)
{
unsigned long desc_count;
struct ext4_group_desc *gdp;
- int i;
+ ext4_group_t i;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
unsigned long bitmap_count, x;
continue;
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
- 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_inodes_count), x);
bitmap_count += x;
}
unsigned long ext4_count_dirs (struct super_block * sb)
{
unsigned long count = 0;
- int i;
+ ext4_group_t i;
for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff