#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <asm/byteorder.h>
+
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "group.h"
+
+#include <trace/events/ext4.h>
/*
* ialloc.c contains the inodes allocation and deallocation routines
/* 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 %u",
- block_group);
+ ext4_error(sb, "Checksum bad for group %u", block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
bitmap_blk = ext4_inode_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, __func__,
- "Cannot read inode bitmap - "
+ ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
unlock_buffer(bh);
return bh;
}
- spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_lock_group(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);
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
return bh;
}
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
- ext4_error(sb, __func__,
- "Cannot read inode bitmap - "
+ ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
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);
+ trace_ext4_free_inode(inode);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
- vfs_dq_init(inode);
+ dquot_initialize(inode);
ext4_xattr_delete_inode(handle, inode);
- vfs_dq_free_inode(inode);
- vfs_dq_drop(inode);
+ dquot_free_inode(inode);
+ dquot_drop(inode);
is_directory = S_ISDIR(inode->i_mode);
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
- ext4_error(sb, "ext4_free_inode",
- "reserved or nonexistent inode %lu", ino);
+ ext4_error(sb, "reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
- 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));
+ cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
+ bit, bitmap_bh->b_data);
if (!cleared)
- ext4_error(sb, "ext4_free_inode",
- "bit already cleared for inode %lu", ino);
+ ext4_error(sb, "bit already cleared for inode %lu", ino);
else {
gdp = ext4_get_group_desc(sb, block_group, &bh2);
if (fatal) goto error_return;
if (gdp) {
- spin_lock(sb_bgl_lock(sbi, block_group));
+ ext4_lock_group(sb, block_group);
count = ext4_free_inodes_count(sb, gdp) + 1;
ext4_free_inodes_set(sb, gdp, count);
if (is_directory) {
ext4_group_t f;
f = ext4_flex_group(sbi, block_group);
- atomic_dec(&sbi->s_flex_groups[f].free_inodes);
+ atomic_dec(&sbi->s_flex_groups[f].used_dirs);
}
}
gdp->bg_checksum = ext4_group_desc_csum(sbi,
block_group, gdp);
- spin_unlock(sb_bgl_lock(sbi, block_group));
+ ext4_unlock_group(sb, block_group);
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
static int find_group_dir(struct super_block *sb, struct inode *parent,
ext4_group_t *best_group)
{
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned int freei, avefreei;
struct ext4_group_desc *desc, *best_desc = NULL;
ext4_group_t group;
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *desc;
- struct buffer_head *bh;
struct flex_groups *flex_group = sbi->s_flex_groups;
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
- ext4_group_t ngroups = sbi->s_groups_count;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
int flex_size = ext4_flex_bg_size(sbi);
ext4_group_t best_flex = parent_fbg_group;
int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
ext4_group_t n_fbg_groups;
ext4_group_t i;
- n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+ n_fbg_groups = (ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
find_close_to_parent:
found_flexbg:
for (i = best_flex * flex_size; i < ngroups &&
i < (best_flex + 1) * flex_size; i++) {
- desc = ext4_get_group_desc(sb, i, &bh);
+ desc = ext4_get_group_desc(sb, i, NULL);
if (ext4_free_inodes_count(sb, desc)) {
*best_group = i;
goto out;
*/
static int find_group_orlov(struct super_block *sb, struct inode *parent,
- ext4_group_t *group, int mode)
+ ext4_group_t *group, int mode,
+ const struct qstr *qstr)
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_group_t ngroups = sbi->s_groups_count;
+ ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
unsigned int ndirs;
int max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
- ext4_group_t i, grp, g;
+ ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
int flex_size = ext4_flex_bg_size(sbi);
+ struct dx_hash_info hinfo;
+ ngroups = real_ngroups;
if (flex_size > 1) {
- ngroups = (ngroups + flex_size - 1) >>
+ ngroups = (real_ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
parent_group >>= sbi->s_log_groups_per_flex;
}
int best_ndir = inodes_per_group;
int ret = -1;
- get_random_bytes(&grp, sizeof(grp));
+ if (qstr) {
+ hinfo.hash_version = DX_HASH_HALF_MD4;
+ hinfo.seed = sbi->s_hash_seed;
+ ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
+ grp = hinfo.hash;
+ } else
+ get_random_bytes(&grp, sizeof(grp));
parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
g = (parent_group + i) % ngroups;
*/
grp *= flex_size;
for (i = 0; i < flex_size; i++) {
- if (grp+i >= sbi->s_groups_count)
+ if (grp+i >= real_ngroups)
break;
desc = ext4_get_group_desc(sb, grp+i, NULL);
if (desc && ext4_free_inodes_count(sb, desc)) {
}
fallback:
- ngroups = sbi->s_groups_count;
+ ngroups = real_ngroups;
avefreei = freei / ngroups;
fallback_retry:
parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t *group, int mode)
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
- ext4_group_t i, last;
int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
/*
*group = parent_group + flex_size;
if (*group > ngroups)
*group = 0;
- return find_group_orlov(sb, parent, group, mode);
+ return find_group_orlov(sb, parent, group, mode, 0);
}
/*
/*
* claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's sb_bgl_lock
+ * is uninit we need to take the groups's ext4_group_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
+ * after holding ext4_group_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 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));
+ ext4_lock_group(sb, group);
if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
/* not a free inode */
retval = 1;
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 - "
+ ext4_unlock_group(sb, group);
+ ext4_error(sb, "reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
return 1;
if (sbi->s_log_groups_per_flex) {
ext4_group_t f = ext4_flex_group(sbi, group);
- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ atomic_inc(&sbi->s_flex_groups[f].used_dirs);
}
}
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
err_ret:
- spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_unlock_group(sb, group);
return retval;
}
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
-struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
+struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
+ const struct qstr *qstr, __u32 goal)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
struct buffer_head *group_desc_bh;
- ext4_group_t group = 0;
+ ext4_group_t ngroups, 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 ret2, err = 0;
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);
+ ngroups = ext4_get_groups_count(sb);
+ trace_ext4_request_inode(dir, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT4_I(inode);
-
sbi = EXT4_SB(sb);
- es = sbi->s_es;
+
+ if (!goal)
+ goal = sbi->s_inode_goal;
+
+ if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) {
+ group = (goal - 1) / EXT4_INODES_PER_GROUP(sb);
+ ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb);
+ ret2 = 0;
+ goto got_group;
+ }
if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
ret2 = find_group_flex(sb, dir, &group);
if (test_opt(sb, OLDALLOC))
ret2 = find_group_dir(sb, dir, &group);
else
- ret2 = find_group_orlov(sb, dir, &group, mode);
+ ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
} else
ret2 = find_group_other(sb, dir, &group, mode);
if (ret2 == -1)
goto out;
- for (i = 0; i < sbi->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++, ino = 0) {
err = -EIO;
gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
if (!inode_bitmap_bh)
goto fail;
- ino = 0;
-
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
BUFFER_TRACE(inode_bitmap_bh,
"call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle,
- inode,
+ NULL,
inode_bitmap_bh);
if (err)
goto fail;
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
- if (++group == sbi->s_groups_count)
+ if (++group == ngroups)
group = 0;
}
err = -ENOSPC;
}
free = 0;
- spin_lock(sb_bgl_lock(sbi, group));
+ ext4_lock_group(sb, group);
/* recheck and clear flag under lock if we still need to */
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
free = ext4_free_blocks_after_init(sb, group, gdp);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
- spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_unlock_group(sb, group);
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
}
- inode->i_uid = current_fsuid();
- if (test_opt(sb, GRPID))
- inode->i_gid = dir->i_gid;
- else if (dir->i_mode & S_ISGID) {
+ if (test_opt(sb, GRPID)) {
+ inode->i_mode = mode;
+ inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
- if (S_ISDIR(mode))
- mode |= S_ISGID;
} else
- inode->i_gid = current_fsgid();
- inode->i_mode = mode;
+ inode_init_owner(inode, dir, mode);
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_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
- ei->i_state = EXT4_STATE_NEW;
+ ei->i_state_flags = 0;
+ ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
ret = inode;
- if (vfs_dq_alloc_inode(inode)) {
- err = -EDQUOT;
+ dquot_initialize(inode);
+ err = dquot_alloc_inode(inode);
+ if (err)
goto fail_drop;
- }
err = ext4_init_acl(handle, inode, dir);
if (err)
}
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);
+ trace_ext4_allocate_inode(inode, dir, mode);
goto really_out;
fail:
ext4_std_error(sb, err);
return ret;
fail_free_drop:
- vfs_dq_free_inode(inode);
+ dquot_free_inode(inode);
fail_drop:
- vfs_dq_drop(inode);
+ dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
unlock_new_inode(inode);
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
- ext4_warning(sb, __func__,
- "bad orphan ino %lu! e2fsck was run?", ino);
+ ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
goto error;
}
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (!bitmap_bh) {
- ext4_warning(sb, __func__,
- "inode bitmap error for orphan %lu", ino);
+ ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
goto error;
}
err = PTR_ERR(inode);
inode = NULL;
bad_orphan:
- ext4_warning(sb, __func__,
- "bad orphan inode %lu! e2fsck was run?", ino);
+ ext4_warning(sb, "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));
{
unsigned long desc_count;
struct ext4_group_desc *gdp;
- ext4_group_t i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
unsigned long bitmap_count, x;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
- i, ext4_free_inodes_count(sb, gdp), x);
+ (unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
return desc_count;
#else
desc_count = 0;
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
unsigned long ext4_count_dirs(struct super_block * sb)
{
unsigned long count = 0;
- ext4_group_t i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff