#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#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"
/*
* 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, __func__, "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);
+ 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), sb->s_blocksize * 8,
+ 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)
+ext4_read_inode_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);
if (!desc)
- goto error_out;
+ return NULL;
+ bitmap_blk = ext4_inode_bitmap(sb, desc);
+ bh = sb_getblk(sb, bitmap_blk);
+ if (unlikely(!bh)) {
+ ext4_error(sb, __func__,
+ "Cannot read inode bitmap - "
+ "block_group = %u, inode_bitmap = %llu",
+ block_group, bitmap_blk);
+ return NULL;
+ }
+ if (bitmap_uptodate(bh))
+ return bh;
- bh = sb_bread(sb, ext4_inode_bitmap(desc));
- if (!bh)
- ext4_error(sb, "read_inode_bitmap",
+ 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);
+ 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, ext4_inode_bitmap(desc));
-error_out:
+ "block_group = %u, inode_bitmap = %llu",
+ block_group, bitmap_blk);
+ return NULL;
+ }
return bh;
}
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
-void ext4_free_inode (handle_t *handle, struct inode * inode)
+void ext4_free_inode(handle_t *handle, struct inode *inode)
{
- struct super_block * sb = inode->i_sb;
+ struct super_block *sb = inode->i_sb;
int is_directory;
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;
+ struct ext4_group_desc *gdp;
+ struct ext4_super_block *es;
struct ext4_sb_info *sbi;
- int fatal = 0, err;
+ int fatal = 0, err, count;
+ ext4_group_t flex_group;
if (atomic_read(&inode->i_count) > 1) {
- printk ("ext4_free_inode: inode has count=%d\n",
- atomic_read(&inode->i_count));
+ printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
+ atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
- printk ("ext4_free_inode: inode has nlink=%d\n",
- inode->i_nlink);
+ printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
+ inode->i_nlink);
return;
}
if (!sb) {
- printk("ext4_free_inode: inode on nonexistent device\n");
+ printk(KERN_ERR "ext4_free_inode: inode on "
+ "nonexistent device\n");
return;
}
sbi = EXT4_SB(sb);
ino = inode->i_ino;
- ext4_debug ("freeing inode %lu\n", 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,
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
- clear_inode (inode);
+ clear_inode(inode);
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, "ext4_free_inode",
+ "reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
- bitmap_bh = read_inode_bitmap(sb, block_group);
+ bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
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))
- ext4_error (sb, "ext4_free_inode",
- "bit already cleared for inode %lu", ino);
+ ext4_error(sb, "ext4_free_inode",
+ "bit already cleared for inode %lu", ino);
else {
- gdp = ext4_get_group_desc (sb, block_group, &bh2);
+ gdp = ext4_get_group_desc(sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
- gdp->bg_free_inodes_count = cpu_to_le16(
- le16_to_cpu(gdp->bg_free_inodes_count) + 1);
- if (is_directory)
- gdp->bg_used_dirs_count = cpu_to_le16(
- le16_to_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));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
+ if (sbi->s_log_groups_per_flex) {
+ flex_group = ext4_flex_group(sbi, block_group);
+ spin_lock(sb_bgl_lock(sbi, flex_group));
+ sbi->s_flex_groups[flex_group].free_inodes++;
+ spin_unlock(sb_bgl_lock(sbi, flex_group));
+ }
}
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh2);
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bh2);
if (!fatal) fatal = err;
}
- BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
* 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;
- struct buffer_head *bh;
- 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;
for (group = 0; group < ngroups; group++) {
- desc = ext4_get_group_desc (sb, group, &bh);
- if (!desc || !desc->bg_free_inodes_count)
+ desc = ext4_get_group_desc(sb, group, NULL);
+ 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))) {
- best_group = group;
+ (ext4_free_blks_count(sb, desc) >
+ ext4_free_blks_count(sb, best_desc))) {
+ *best_group = group;
best_desc = desc;
+ ret = 0;
+ }
+ }
+ return ret;
+}
+
+#define free_block_ratio 10
+
+static int find_group_flex(struct super_block *sb, struct inode *parent,
+ ext4_group_t *best_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;
+ 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;
+ int flexbg_free_blocks;
+ int flex_freeb_ratio;
+ ext4_group_t n_fbg_groups;
+ ext4_group_t i;
+
+ n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+ sbi->s_log_groups_per_flex;
+
+find_close_to_parent:
+ flexbg_free_blocks = flex_group[best_flex].free_blocks;
+ flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+ if (flex_group[best_flex].free_inodes &&
+ flex_freeb_ratio > free_block_ratio)
+ goto found_flexbg;
+
+ if (best_flex && best_flex == parent_fbg_group) {
+ best_flex--;
+ goto find_close_to_parent;
+ }
+
+ for (i = 0; i < n_fbg_groups; i++) {
+ if (i == parent_fbg_group || i == parent_fbg_group - 1)
+ continue;
+
+ flexbg_free_blocks = flex_group[i].free_blocks;
+ flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+
+ if (flex_freeb_ratio > free_block_ratio &&
+ flex_group[i].free_inodes) {
+ best_flex = i;
+ goto found_flexbg;
}
+
+ if (flex_group[best_flex].free_inodes == 0 ||
+ (flex_group[i].free_blocks >
+ flex_group[best_flex].free_blocks &&
+ flex_group[i].free_inodes))
+ best_flex = i;
}
- return best_group;
+
+ if (!flex_group[best_flex].free_inodes ||
+ !flex_group[best_flex].free_blocks)
+ return -1;
+
+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);
+ if (ext4_free_inodes_count(sb, desc)) {
+ *best_group = i;
+ goto out;
+ }
+ }
+
+ return -1;
+out:
+ return 0;
}
/*
* it has too few free inodes left (min_inodes) or
* it has too few free blocks left (min_blocks) or
* it's already running too large debt (max_debt).
- * Parent's group is prefered, if it doesn't satisfy these
+ * Parent's group is preferred, if it doesn't satisfy these
* conditions we search cyclically through the rest. If none
* of the groups look good we just look for a group with more
* free inodes than average (starting at parent's group).
#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;
- struct buffer_head *bh;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
avefreeb = freeb;
- sector_div(avefreeb, ngroups);
+ do_div(avefreeb, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_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, &bh);
- if (!desc || !desc->bg_free_inodes_count)
+ grp = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc(sb, grp, NULL);
+ 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;
- best_group = group;
- best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+ *group = grp;
+ ret = 0;
+ best_ndir = ext4_used_dirs_count(sb, desc);
}
- if (best_group >= 0)
- return best_group;
+ if (ret == 0)
+ return ret;
goto fallback;
}
blocks_per_dir = ext4_blocks_count(es) - freeb;
- sector_div(blocks_per_dir, ndirs);
+ do_div(blocks_per_dir, ndirs);
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;
max_debt = EXT4_BLOCKS_PER_GROUP(sb);
- sector_div(max_debt, max(blocks_per_dir, (ext4_fsblk_t)BLOCK_COST));
+ max_debt /= max_t(int, blocks_per_dir, BLOCK_COST);
if (max_debt * INODE_COST > inodes_per_group)
max_debt = inodes_per_group / INODE_COST;
if (max_debt > 255)
max_debt = 1;
for (i = 0; i < ngroups; i++) {
- group = (parent_group + i) % ngroups;
- desc = ext4_get_group_desc (sb, group, &bh);
- if (!desc || !desc->bg_free_inodes_count)
+ *group = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc(sb, *group, NULL);
+ 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 group;
+ return 0;
}
fallback:
for (i = 0; i < ngroups; i++) {
- group = (parent_group + i) % ngroups;
- desc = ext4_get_group_desc (sb, group, &bh);
- 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 && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_inodes_count(sb, desc) >= 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;
- struct buffer_head *bh;
- 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, &bh);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
- return group;
+ *group = parent_group;
+ desc = ext4_get_group_desc(sb, *group, NULL);
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
+ 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, &bh);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
- return group;
+ *group += i;
+ if (*group >= ngroups)
+ *group -= ngroups;
+ desc = ext4_get_group_desc(sb, *group, NULL);
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
+ 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, &bh);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count))
- return group;
+ if (++*group >= ngroups)
+ *group = 0;
+ desc = ext4_get_group_desc(sb, *group, NULL);
+ if (desc && ext4_free_inodes_count(sb, desc))
+ return 0;
}
return -1;
}
/*
+ * 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
* 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)
{
struct super_block *sb;
- struct buffer_head *bitmap_bh = NULL;
- struct buffer_head *bh2;
- int group;
+ 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 ext4_group_desc * gdp = NULL;
- struct ext4_super_block * es;
+ 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;
+ ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
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);
sbi = EXT4_SB(sb);
es = sbi->s_es;
+
+ 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 && printk_ratelimit())
+ printk(KERN_NOTICE "ext4: find_group_flex "
+ "failed, fallback succeeded dir %lu\n",
+ dir->i_ino);
+ }
+ goto got_group;
+ }
+
if (S_ISDIR(mode)) {
- if (test_opt (sb, OLDALLOC))
- group = find_group_dir(sb, dir);
+ if (test_opt(sb, OLDALLOC))
+ 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);
+got_group:
err = -ENOSPC;
- if (group == -1)
+ if (ret2 == -1)
goto out;
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 = 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,
- "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle,
- bitmap_bh);
+ BUFFER_TRACE(inode_bitmap_bh,
+ "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
+ inode_bitmap_bh);
if (err)
goto fail;
+ /* zero bit is inode number 1*/
+ ino++;
goto got;
}
/* we lost it */
- jbd2_journal_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 += 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);
- err = -EIO;
- 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_bitmap_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_bitmap_bh);
+ goto fail;
+ }
- BUFFER_TRACE(bh2, "get_write_access");
- err = ext4_journal_get_write_access(handle, bh2);
- if (err) goto fail;
- spin_lock(sb_bgl_lock(sbi, group));
- 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);
+ 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)) {
+ free = ext4_free_blocks_after_init(sb, group, gdp);
+ 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);
+ }
+ 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_bitmap_bh, "dirty block bitmap");
+ err = ext4_handle_dirty_metadata(handle,
+ NULL, block_bitmap_bh);
+ }
+
+ brelse(block_bitmap_bh);
+ if (err)
+ goto fail;
}
- spin_unlock(sb_bgl_lock(sbi, group));
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, 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))
percpu_counter_inc(&sbi->s_dirs_counter);
sb->s_dirt = 1;
- inode->i_uid = current->fsuid;
- if (test_opt (sb, GRPID))
+ if (sbi->s_log_groups_per_flex) {
+ flex_group = ext4_flex_group(sbi, group);
+ spin_lock(sb_bgl_lock(sbi, flex_group));
+ sbi->s_flex_groups[flex_group].free_inodes--;
+ spin_unlock(sb_bgl_lock(sbi, flex_group));
+ }
+
+ inode->i_uid = current_fsuid();
+ if (test_opt(sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
- inode->i_gid = current->fsgid;
+ 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 = CURRENT_TIME_SEC;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
+ ext4_current_time(inode);
memset(ei->i_data, 0, sizeof(ei->i_data));
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;
-#ifdef EXT4_FRAGMENTS
- ei->i_faddr = 0;
- ei->i_frag_no = 0;
- ei->i_frag_size = 0;
-#endif
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;
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
- handle->h_sync = 1;
- insert_inode_hash(inode);
+ ext4_handle_sync(handle);
+ if (insert_inode_locked(inode) < 0) {
+ err = -EINVAL;
+ goto fail_drop;
+ }
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state = EXT4_STATE_NEW;
- ei->i_extra_isize =
- (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) ?
- sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE : 0;
+
+ ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
ret = inode;
- if(DQUOT_ALLOC_INODE(inode)) {
+ if (DQUOT_ALLOC_INODE(inode)) {
err = -EDQUOT;
goto fail_drop;
}
if (err)
goto fail_free_drop;
- err = ext4_init_security(handle,inode, dir);
+ err = ext4_init_security(handle, inode, dir);
if (err)
goto fail_free_drop;
+ 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_ext_tree_init(handle, inode);
+ }
+ }
+
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
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);
- }
- }
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:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
+ unlock_new_inode(inode);
iput(inode);
- brelse(bitmap_bh);
+ brelse(inode_bitmap_bh);
return ERR_PTR(err);
}
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__,
+ ext4_warning(sb, __func__,
"bad orphan ino %lu! e2fsck was run?", ino);
- goto out;
+ goto error;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
- bitmap_bh = read_inode_bitmap(sb, block_group);
+ bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (!bitmap_bh) {
- ext4_warning(sb, __FUNCTION__,
+ ext4_warning(sb, __func__,
"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 the orphans has i_nlinks > 0 then it should be able to be
+ * truncated, otherwise it won't be removed from the orphan list
+ * during processing and an infinite loop will result.
+ */
+ if (inode->i_nlink && !ext4_can_truncate(inode))
+ goto bad_orphan;
+
+ 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, __func__,
+ "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);
+ printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
/* 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 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;
bitmap_count = 0;
gdp = NULL;
for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
- gdp = ext4_get_group_desc (sb, i, NULL);
+ 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 = read_inode_bitmap(sb, i);
+ bitmap_bh = ext4_read_inode_bitmap(sb, i);
if (!bitmap_bh)
continue;
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
- printk("group %d: stored = %d, counted = %lu\n",
- i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+ printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
+ i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
- printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
- le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+ printk(KERN_DEBUG "ext4_count_free_inodes: "
+ "stored = %u, computed = %lu, %lu\n",
+ le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
return desc_count;
#else
desc_count = 0;
for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
- gdp = ext4_get_group_desc (sb, i, NULL);
+ 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;
}
/* Called at mount-time, super-block is locked */
-unsigned long ext4_count_dirs (struct super_block * sb)
+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);
+ 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;
}
-