#define EXT4_ACL_NOT_CACHED ((void *)-1)
/* acl.c */
-extern int ext4_permission (struct inode *, int);
-extern int ext4_acl_chmod (struct inode *);
-extern int ext4_init_acl (handle_t *, struct inode *, struct inode *);
+extern int ext4_permission(struct inode *, int);
+extern int ext4_acl_chmod(struct inode *);
+extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
#else /* CONFIG_EXT4DEV_FS_POSIX_ACL */
#include <linux/sched.h>
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
le32_to_cpu(sbi->s_es->s_first_data_block) -
- (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1));
+ (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
* @bh: pointer to the buffer head to store the block
* group descriptor
*/
-struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
ext4_group_t block_group,
- struct buffer_head ** bh)
+ struct buffer_head **bh)
{
unsigned long group_desc;
unsigned long offset;
- struct ext4_group_desc * desc;
+ struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= sbi->s_groups_count) {
- ext4_error (sb, "ext4_get_group_desc",
- "block_group >= groups_count - "
- "block_group = %lu, groups_count = %lu",
- block_group, sbi->s_groups_count);
+ ext4_error(sb, "ext4_get_group_desc",
+ "block_group >= groups_count - "
+ "block_group = %lu, groups_count = %lu",
+ block_group, sbi->s_groups_count);
return NULL;
}
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
- ext4_error (sb, "ext4_get_group_desc",
- "Group descriptor not loaded - "
- "block_group = %lu, group_desc = %lu, desc = %lu",
- block_group, group_desc, offset);
+ ext4_error(sb, "ext4_get_group_desc",
+ "Group descriptor not loaded - "
+ "block_group = %lu, group_desc = %lu, desc = %lu",
+ block_group, group_desc, offset);
return NULL;
}
struct buffer_head *
ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
{
- struct ext4_group_desc * desc;
- struct buffer_head * bh = NULL;
+ struct ext4_group_desc *desc;
+ struct buffer_head *bh = NULL;
ext4_fsblk_t bitmap_blk;
desc = ext4_get_group_desc(sb, block_group, NULL);
bad = 0;
prev = NULL;
- printk("Block Allocation Reservation Windows Map (%s):\n", fn);
+ printk(KERN_DEBUG "Block Allocation Reservation "
+ "Windows Map (%s):\n", fn);
while (n) {
rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
if (verbose)
- printk("reservation window 0x%p "
+ printk(KERN_DEBUG "reservation window 0x%p "
"start: %llu, end: %llu\n",
rsv, rsv->rsv_start, rsv->rsv_end);
if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
- printk("Bad reservation %p (start >= end)\n",
+ printk(KERN_DEBUG "Bad reservation %p (start >= end)\n",
rsv);
bad = 1;
}
if (prev && prev->rsv_end >= rsv->rsv_start) {
- printk("Bad reservation %p (prev->end >= start)\n",
- rsv);
+ printk(KERN_DEBUG "Bad reservation %p "
+ "(prev->end >= start)\n", rsv);
bad = 1;
}
if (bad) {
if (!verbose) {
- printk("Restarting reservation walk in verbose mode\n");
+ printk(KERN_DEBUG "Restarting reservation "
+ "walk in verbose mode\n");
verbose = 1;
goto restart;
}
n = rb_next(n);
prev = rsv;
}
- printk("Window map complete.\n");
+ printk(KERN_DEBUG "Window map complete.\n");
BUG_ON(bad);
}
#define rsv_window_dump(root, verbose) \
struct rb_node *node = &rsv->rsv_node;
ext4_fsblk_t start = rsv->rsv_start;
- struct rb_node ** p = &root->rb_node;
- struct rb_node * parent = NULL;
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent = NULL;
struct ext4_reserve_window_node *this;
while (*p)
ext4_grpblk_t bit;
unsigned long i;
unsigned long overflow;
- struct ext4_group_desc * desc;
- struct ext4_super_block * es;
+ struct ext4_group_desc *desc;
+ struct ext4_super_block *es;
struct ext4_sb_info *sbi;
int err = 0, ret;
ext4_grpblk_t group_freed;
if (block < le32_to_cpu(es->s_first_data_block) ||
block + count < block ||
block + count > ext4_blocks_count(es)) {
- ext4_error (sb, "ext4_free_blocks",
- "Freeing blocks not in datazone - "
- "block = %llu, count = %lu", block, count);
+ ext4_error(sb, "ext4_free_blocks",
+ "Freeing blocks not in datazone - "
+ "block = %llu, count = %lu", block, count);
goto error_return;
}
- ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1);
+ ext4_debug("freeing block(s) %llu-%llu\n", block, block + count - 1);
do_more:
overflow = 0;
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
- desc = ext4_get_group_desc (sb, block_group, &gd_bh);
+ desc = ext4_get_group_desc(sb, block_group, &gd_bh);
if (!desc)
goto error_return;
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
- ext4_error (sb, "ext4_free_blocks",
- "Freeing blocks in system zones - "
- "Block = %llu, count = %lu",
- block, count);
+ ext4_error(sb, "ext4_free_blocks",
+ "Freeing blocks in system zones - "
+ "Block = %llu, count = %lu",
+ block, count);
goto error_return;
}
ext4_fsblk_t block, unsigned long count,
int metadata)
{
- struct super_block * sb;
+ struct super_block *sb;
unsigned long dquot_freed_blocks;
/* this isn't the right place to decide whether block is metadata
if (ext4_set_bit_atomic(lock, block, bh->b_data))
return 0;
jbd_lock_bh_state(bh);
- if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) {
+ if (jh->b_committed_data && ext4_test_bit(block, jh->b_committed_data)) {
ext4_clear_bit_atomic(lock, block, bh->b_data);
ret = 0;
} else {
static int find_next_reservable_window(
struct ext4_reserve_window_node *search_head,
struct ext4_reserve_window_node *my_rsv,
- struct super_block * sb,
+ struct super_block *sb,
ext4_fsblk_t start_block,
ext4_fsblk_t last_block)
{
prev = rsv;
next = rb_next(&rsv->rsv_node);
- rsv = rb_entry(next,struct ext4_reserve_window_node,rsv_node);
+ rsv = rb_entry(next, struct ext4_reserve_window_node, rsv_node);
/*
* Reached the last reservation, we can just append to the
size = size * 2;
if (size > EXT4_MAX_RESERVE_BLOCKS)
size = EXT4_MAX_RESERVE_BLOCKS;
- my_rsv->rsv_goal_size= size;
+ my_rsv->rsv_goal_size = size;
}
}
ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
ext4_group_t group, struct buffer_head *bitmap_bh,
ext4_grpblk_t grp_goal,
- struct ext4_reserve_window_node * my_rsv,
+ struct ext4_reserve_window_node *my_rsv,
unsigned long *count, int *errp)
{
ext4_fsblk_t group_first_block, group_last_block;
* or the file is not a regular file
* or last attempt to allocate a block with reservation turned on failed
*/
- if (my_rsv == NULL ) {
+ if (my_rsv == NULL) {
ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
grp_goal, count, NULL);
goto out;
return ret;
}
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+ s64 nblocks)
+{
+ s64 free_blocks, dirty_blocks;
+ s64 root_blocks = 0;
+ struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+ struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
+
+ free_blocks = percpu_counter_read_positive(fbc);
+ dirty_blocks = percpu_counter_read_positive(dbc);
+
+ if (!capable(CAP_SYS_RESOURCE) &&
+ sbi->s_resuid != current->fsuid &&
+ (sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
+ root_blocks = ext4_r_blocks_count(sbi->s_es);
+
+ if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+ EXT4_FREEBLOCKS_WATERMARK) {
+ free_blocks = percpu_counter_sum(fbc);
+ dirty_blocks = percpu_counter_sum(dbc);
+ if (dirty_blocks < 0) {
+ printk(KERN_CRIT "Dirty block accounting "
+ "went wrong %lld\n",
+ dirty_blocks);
+ }
+ }
+ /* Check whether we have space after
+ * accounting for current dirty blocks
+ */
+ if (free_blocks < ((root_blocks + nblocks) + dirty_blocks))
+ /* we don't have free space */
+ return -ENOSPC;
+
+ /* Add the blocks to nblocks */
+ percpu_counter_add(dbc, nblocks);
+ return 0;
+}
+
/**
* ext4_has_free_blocks()
* @sbi: in-core super block structure.
* On success, return nblocks
*/
ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
- ext4_fsblk_t nblocks)
+ s64 nblocks)
{
- ext4_fsblk_t free_blocks;
- ext4_fsblk_t root_blocks = 0;
+ s64 free_blocks, dirty_blocks;
+ s64 root_blocks = 0;
+ struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+ struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ free_blocks = percpu_counter_read_positive(fbc);
+ dirty_blocks = percpu_counter_read_positive(dbc);
if (!capable(CAP_SYS_RESOURCE) &&
sbi->s_resuid != current->fsuid &&
(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
root_blocks = ext4_r_blocks_count(sbi->s_es);
-#ifdef CONFIG_SMP
- if (free_blocks - root_blocks < FBC_BATCH)
- free_blocks =
- percpu_counter_sum_and_set(&sbi->s_freeblocks_counter);
-#endif
- if (free_blocks <= root_blocks)
+
+ if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+ EXT4_FREEBLOCKS_WATERMARK) {
+ free_blocks = percpu_counter_sum(fbc);
+ dirty_blocks = percpu_counter_sum(dbc);
+ }
+ if (free_blocks <= (root_blocks + dirty_blocks))
/* we don't have free space */
return 0;
- if (free_blocks - root_blocks < nblocks)
- return free_blocks - root_blocks;
+
+ if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
+ return free_blocks - (root_blocks + dirty_blocks);
return nblocks;
- }
+}
/**
sb = inode->i_sb;
if (!sb) {
*errp = -ENODEV;
- printk("ext4_new_block: nonexistent device");
+ printk(KERN_ERR "ext4_new_block: nonexistent superblock");
return 0;
}
/*
* With delalloc we already reserved the blocks
*/
- *count = ext4_has_free_blocks(sbi, *count);
- }
- if (*count == 0) {
- *errp = -ENOSPC;
- return 0; /*return with ENOSPC error */
+ while (*count && ext4_claim_free_blocks(sbi, *count)) {
+ /* let others to free the space */
+ yield();
+ *count = *count >> 1;
+ }
+ if (!*count) {
+ *errp = -ENOSPC;
+ return 0; /*return with ENOSPC error */
+ }
+ num = *count;
}
- num = *count;
-
/*
* Check quota for allocation of this block.
*/
goto io_error;
free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
- /*
- * if there is not enough free blocks to make a new resevation
- * turn off reservation for this allocation
- */
- if (my_rsv && (free_blocks < windowsz)
- && (rsv_is_empty(&my_rsv->rsv_window)))
- my_rsv = NULL;
if (free_blocks > 0) {
+ /*
+ * try to allocate with group target block
+ * in the goal group. If we have low free_blocks
+ * count turn off reservation
+ */
+ if (my_rsv && (free_blocks < windowsz)
+ && (rsv_is_empty(&my_rsv->rsv_window)))
+ my_rsv = NULL;
+
bitmap_bh = ext4_read_block_bitmap(sb, group_no);
if (!bitmap_bh)
goto io_error;
* 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);
for (i = 0; i < num; i++) {
if (ext4_test_bit(grp_alloc_blk+i,
bh2jh(bitmap_bh)->b_committed_data)) {
- printk("%s: block was unexpectedly set in "
- "b_committed_data\n", __func__);
+ printk(KERN_ERR "%s: block was unexpectedly "
+ "set in b_committed_data\n", __func__);
}
}
}
le16_add_cpu(&gdp->bg_free_blocks_count, -num);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
spin_unlock(sb_bgl_lock(sbi, group_no));
- if (!EXT4_I(inode)->i_delalloc_reserved_flag)
- percpu_counter_sub(&sbi->s_freeblocks_counter, num);
-
+ percpu_counter_sub(&sbi->s_freeblocks_counter, num);
+ /*
+ * Now reduce the dirty block count also. Should not go negative
+ */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, num);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, group_no);
spin_lock(sb_bgl_lock(sbi, flex_group));
/*
* Account for the allocated meta blocks
*/
- if (!(*errp)) {
+ if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_allocated_meta_blocks += *count;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
bitmap_count += x;
}
brelse(bitmap_bh);
- printk("ext4_count_free_blocks: stored = %llu"
- ", computed = %llu, %llu\n",
- ext4_free_blocks_count(es),
- desc_count, bitmap_count);
+ printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
+ ", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+ desc_count, bitmap_count);
return bitmap_count;
#else
desc_count = 0;
if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
metagroup < first_meta_bg)
- return ext4_bg_num_gdb_nometa(sb,group);
+ return ext4_bg_num_gdb_nometa(sb, group);
return ext4_bg_num_gdb_meta(sb,group);
static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-unsigned long ext4_count_free (struct buffer_head * map, unsigned int numchars)
+unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
{
unsigned int i;
unsigned long sum = 0;
if (!map)
- return (0);
+ return 0;
for (i = 0; i < numchars; i++)
sum += nibblemap[map->b_data[i] & 0xf] +
nibblemap[(map->b_data[i] >> 4) & 0xf];
- return (sum);
+ return sum;
}
#endif /* EXT4FS_DEBUG */
};
static int ext4_readdir(struct file *, void *, filldir_t);
-static int ext4_dx_readdir(struct file * filp,
- void * dirent, filldir_t filldir);
-static int ext4_release_dir (struct inode * inode,
- struct file * filp);
+static int ext4_dx_readdir(struct file *filp,
+ void *dirent, filldir_t filldir);
+static int ext4_release_dir(struct inode *inode,
+ struct file *filp);
const struct file_operations ext4_dir_operations = {
.llseek = generic_file_llseek,
}
-int ext4_check_dir_entry (const char * function, struct inode * dir,
- struct ext4_dir_entry_2 * de,
- struct buffer_head * bh,
- unsigned long offset)
+int ext4_check_dir_entry(const char *function, struct inode *dir,
+ struct ext4_dir_entry_2 *de,
+ struct buffer_head *bh,
+ unsigned long offset)
{
- const char * error_msg = NULL;
+ const char *error_msg = NULL;
const int rlen = ext4_rec_len_from_disk(de->rec_len);
if (rlen < EXT4_DIR_REC_LEN(1))
error_msg = "inode out of bounds";
if (error_msg != NULL)
- ext4_error (dir->i_sb, function,
+ ext4_error(dir->i_sb, function,
"bad entry in directory #%lu: %s - "
"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
dir->i_ino, error_msg, offset,
return error_msg == NULL ? 1 : 0;
}
-static int ext4_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int ext4_readdir(struct file *filp,
+ void *dirent, filldir_t filldir)
{
int error = 0;
unsigned long offset;
* of recovering data when there's a bad sector
*/
if (!bh) {
- ext4_error (sb, "ext4_readdir",
+ ext4_error(sb, "ext4_readdir",
"directory #%lu contains a hole at offset %lu",
inode->i_ino, (unsigned long)filp->f_pos);
/* corrupt size? Maybe no more blocks to read */
while (!error && filp->f_pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
- if (!ext4_check_dir_entry ("ext4_readdir", inode, de,
- bh, offset)) {
+ if (!ext4_check_dir_entry("ext4_readdir", inode, de,
+ bh, offset)) {
/*
* On error, skip the f_pos to the next block
*/
filp->f_pos = (filp->f_pos |
(sb->s_blocksize - 1)) + 1;
- brelse (bh);
+ brelse(bh);
ret = stored;
goto out;
}
break;
if (version != filp->f_version)
goto revalidate;
- stored ++;
+ stored++;
}
filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
}
offset = 0;
- brelse (bh);
+ brelse(bh);
}
out:
return ret;
parent = rb_parent(n);
fname = rb_entry(n, struct fname, rb_hash);
while (fname) {
- struct fname * old = fname;
+ struct fname *old = fname;
fname = fname->next;
- kfree (old);
+ kfree(old);
}
if (!parent)
root->rb_node = NULL;
struct ext4_dir_entry_2 *dirent)
{
struct rb_node **p, *parent = NULL;
- struct fname * fname, *new_fn;
+ struct fname *fname, *new_fn;
struct dir_private_info *info;
int len;
* for all entres on the fname linked list. (Normally there is only
* one entry on the linked list, unless there are 62 bit hash collisions.)
*/
-static int call_filldir(struct file * filp, void * dirent,
+static int call_filldir(struct file *filp, void *dirent,
filldir_t filldir, struct fname *fname)
{
struct dir_private_info *info = filp->private_data;
loff_t curr_pos;
struct inode *inode = filp->f_path.dentry->d_inode;
- struct super_block * sb;
+ struct super_block *sb;
int error;
sb = inode->i_sb;
if (!fname) {
- printk("call_filldir: called with null fname?!?\n");
+ printk(KERN_ERR "ext4: call_filldir: called with "
+ "null fname?!?\n");
return 0;
}
curr_pos = hash2pos(fname->hash, fname->minor_hash);
return 0;
}
-static int ext4_dx_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int ext4_dx_readdir(struct file *filp,
+ void *dirent, filldir_t filldir)
{
struct dir_private_info *info = filp->private_data;
struct inode *inode = filp->f_path.dentry->d_inode;
return 0;
}
-static int ext4_release_dir (struct inode * inode, struct file * filp)
+static int ext4_release_dir(struct inode *inode, struct file *filp)
{
if (filp->private_data)
ext4_htree_free_dir_info(filp->private_data);
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...) \
do { \
- printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \
+ printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \
__FILE__, __LINE__, __func__); \
- printk (KERN_DEBUG f, ## a); \
+ printk(KERN_DEBUG f, ## a); \
} while (0)
#else
#define ext4_debug(f, a...) do {} while (0)
#else
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
-#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
#else
#define EXT4_IOC_GETVERSION _IOR('f', 3, long)
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
-#define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input)
+#define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
#ifdef CONFIG_JBD2_DEBUG
};
#ifdef __KERNEL__
-static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb)
+static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
*/
#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \
- ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+ (EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask))
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \
- ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+ (EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask))
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \
- ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+ (EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask))
#define EXT4_SET_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \
unsigned long *count, int *errp);
extern ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
- ext4_fsblk_t nblocks);
-extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
+ s64 nblocks);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
- ext4_fsblk_t block, unsigned long count,
+extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count,
unsigned long *pdquot_freed_blocks);
-extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
-extern void ext4_check_blocks_bitmap (struct super_block *);
+extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
struct buffer_head ** bh);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
/* fsync.c */
-extern int ext4_sync_file (struct file *, struct dentry *, int);
+extern int ext4_sync_file(struct file *, struct dentry *, int);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
dx_hash_info *hinfo);
/* ialloc.c */
-extern struct inode * ext4_new_inode (handle_t *, struct inode *, int);
-extern void ext4_free_inode (handle_t *, struct inode *);
-extern struct inode * ext4_orphan_get (struct super_block *, unsigned long);
-extern unsigned long ext4_count_free_inodes (struct super_block *);
-extern unsigned long ext4_count_dirs (struct super_block *);
-extern void ext4_check_inodes_bitmap (struct super_block *);
-extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
+extern struct inode * ext4_new_inode(handle_t *, struct inode *, int);
+extern void ext4_free_inode(handle_t *, struct inode *);
+extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
+extern unsigned long ext4_count_free_inodes(struct super_block *);
+extern unsigned long ext4_count_dirs(struct super_block *);
+extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned long ext4_count_free(struct buffer_head *, unsigned);
/* mballoc.c */
extern long ext4_mb_stats;
int create, int extend_disksize);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
-extern int ext4_write_inode (struct inode *, int);
-extern int ext4_setattr (struct dentry *, struct iattr *);
+extern int ext4_write_inode(struct inode *, int);
+extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
-extern void ext4_delete_inode (struct inode *);
-extern int ext4_sync_inode (handle_t *, struct inode *);
-extern void ext4_discard_reservation (struct inode *);
+extern void ext4_delete_inode(struct inode *);
+extern int ext4_sync_inode(handle_t *, struct inode *);
+extern void ext4_discard_reservation(struct inode *);
extern void ext4_dirty_inode(struct inode *);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
extern int ext4_can_truncate(struct inode *inode);
-extern void ext4_truncate (struct inode *);
+extern void ext4_truncate(struct inode *);
extern void ext4_set_inode_flags(struct inode *);
extern void ext4_get_inode_flags(struct ext4_inode_info *);
extern void ext4_set_aops(struct inode *inode);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
-extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
+extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void ext4_error (struct super_block *, const char *, const char *, ...)
+extern void ext4_error(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void __ext4_std_error (struct super_block *, const char *, int);
-extern void ext4_abort (struct super_block *, const char *, const char *, ...)
+extern void __ext4_std_error(struct super_block *, const char *, int);
+extern void ext4_abort(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning (struct super_block *, const char *, const char *, ...)
+extern void ext4_warning(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void ext4_update_dynamic_rev (struct super_block *sb);
+extern void ext4_update_dynamic_rev(struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
extern int ext4_update_rocompat_feature(handle_t *handle,
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
- ext4_group_t group)
+ ext4_group_t group)
{
struct ext4_group_info ***grp_info;
long indexv, indexh;
__ext4_std_error((sb), __func__, (errno)); \
} while (0)
+#ifdef CONFIG_SMP
+/* Each CPU can accumulate FBC_BATCH blocks in their local
+ * counters. So we need to make sure we have free blocks more
+ * than FBC_BATCH * nr_cpu_ids. Also add a window of 4 times.
+ */
+#define EXT4_FREEBLOCKS_WATERMARK (4 * (FBC_BATCH * nr_cpu_ids))
+#else
+#define EXT4_FREEBLOCKS_WATERMARK 0
+#endif
+
+static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+ /*
+ * XXX: replace with spinlock if seen contended -bzzz
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (newsize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = newsize;
+ up_write(&EXT4_I(inode)->i_data_sem);
+ return ;
+}
+
/*
* Inodes and files operations
*/
unsigned long s_blocks_last; /* Last seen block count */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
- struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
- struct buffer_head ** s_group_desc;
+ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
+ struct buffer_head **s_group_desc;
unsigned long s_mount_opt;
ext4_fsblk_t s_sb_block;
uid_t s_resuid;
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
+ struct percpu_counter s_dirtyblocks_counter;
struct blockgroup_lock s_blockgroup_lock;
/* root of the per fs reservation window tree */
struct ext4_reserve_window_node s_rsv_window_head;
/* Journaling */
- struct inode * s_journal_inode;
- struct journal_s * s_journal;
+ struct inode *s_journal_inode;
+ struct journal_s *s_journal;
struct list_head s_orphan;
unsigned long s_commit_interval;
struct block_device *journal_bdev;
ext_debug("\n");
}
#else
-#define ext4_ext_show_path(inode,path)
-#define ext4_ext_show_leaf(inode,path)
+#define ext4_ext_show_path(inode, path)
+#define ext4_ext_show_leaf(inode, path)
#endif
void ext4_ext_drop_refs(struct ext4_ext_path *path)
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
if (k != 0 &&
le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
- printk("k=%d, ix=0x%p, first=0x%p\n", k,
- ix, EXT_FIRST_INDEX(eh));
- printk("%u <= %u\n",
+ printk(KERN_DEBUG "k=%d, ix=0x%p, "
+ "first=0x%p\n", k,
+ ix, EXT_FIRST_INDEX(eh));
+ printk(KERN_DEBUG "%u <= %u\n",
le32_to_cpu(ix->ei_block),
le32_to_cpu(ix[-1].ei_block));
}
struct ext4_ext_path *path,
struct ext4_extent *newext)
{
- struct ext4_extent_header * eh;
+ struct ext4_extent_header *eh;
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
struct ext4_ext_path *npath = NULL;
*/
if (test_opt(sb, EXTENTS)) {
- printk("EXT4-fs: file extents enabled");
+ printk(KERN_INFO "EXT4-fs: file extents enabled");
#ifdef AGGRESSIVE_TEST
printk(", aggressive tests");
#endif
* Update only when preallocation was requested beyond
* the file size.
*/
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- new_size > i_size_read(inode)) {
- i_size_write(inode, new_size);
- EXT4_I(inode)->i_disksize = new_size;
+ if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+ if (new_size > i_size_read(inode))
+ i_size_write(inode, new_size);
+ if (new_size > EXT4_I(inode)->i_disksize)
+ ext4_update_i_disksize(inode, new_size);
}
}
* from ext4_file_open: open gets called at every open, but release
* gets called only when /all/ the files are closed.
*/
-static int ext4_release_file (struct inode * inode, struct file * filp)
+static int ext4_release_file(struct inode *inode, struct file *filp)
{
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
* inode to disk.
*/
-int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
+int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
sum += DELTA;
b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
- } while(--n);
+ } while (--n);
buf[0] += b0;
buf[1] += b1;
/* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash(const char *name, int len)
{
__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
while (len--) {
val = pad;
if (len > num*4)
len = num * 4;
- for (i=0; i < len; i++) {
+ for (i = 0; i < len; i++) {
if ((i % 4) == 0)
val = pad;
val = msg[i] + (val << 8);
/* Check to see if the seed is all zero's */
if (hinfo->seed) {
- for (i=0; i < 4; i++) {
+ for (i = 0; i < 4; i++) {
if (hinfo->seed[i])
break;
}
* 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;
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;
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);
/*
* 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);
/* 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);
avefreei = freei / ngroups;
for (group = 0; group < ngroups; group++) {
- desc = ext4_get_group_desc (sb, group, NULL);
+ 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)
* 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;
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 ret2, err = 0;
}
if (S_ISDIR(mode)) {
- if (test_opt (sb, OLDALLOC))
+ if (test_opt(sb, OLDALLOC))
ret2 = find_group_dir(sb, dir, &group);
else
ret2 = find_group_orlov(sb, dir, &group);
}
inode->i_uid = current->fsuid;
- if (test_opt (sb, GRPID))
+ if (test_opt(sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
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;
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;
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);
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);
}
/* 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;
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);
/*
* Called at the last iput() if i_nlink is zero.
*/
-void ext4_delete_inode (struct inode * inode)
+void ext4_delete_inode(struct inode *inode)
{
handle_t *handle;
int err;
int final = 0;
if (i_block < 0) {
- ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0");
+ ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
} else if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
- } else if ( (i_block -= direct_blocks) < indirect_blocks) {
+ } else if ((i_block -= direct_blocks) < indirect_blocks) {
offsets[n++] = EXT4_IND_BLOCK;
offsets[n++] = i_block;
final = ptrs;
*err = 0;
/* i_data is not going away, no lock needed */
- add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets);
+ add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
if (!p->key)
goto no_block;
while (--depth) {
bh = sb_bread(sb, le32_to_cpu(p->key));
if (!bh)
goto failure;
- add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
+ add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
/* Reader: end */
if (!p->key)
goto no_block;
static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
+ __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
__le32 *p;
ext4_fsblk_t bg_start;
ext4_fsblk_t last_block;
*err = 0;
return ret;
failed_out:
- for (i = 0; i <index; i++)
+ for (i = 0; i < index; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
return ret;
}
branch[n].p = (__le32 *) bh->b_data + offsets[n];
branch[n].key = cpu_to_le32(new_blocks[n]);
*branch[n].p = branch[n].key;
- if ( n == indirect_blks) {
+ if (n == indirect_blks) {
current_block = new_blocks[n];
/*
* End of chain, update the last new metablock of
BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
ext4_journal_forget(handle, branch[i].bh);
}
- for (i = 0; i <indirect_blks; i++)
+ for (i = 0; i < indirect_blks; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
if (num == 0 && blks > 1) {
current_block = le32_to_cpu(where->key) + 1;
for (i = 1; i < blks; i++)
- *(where->p + i ) = cpu_to_le32(current_block++);
+ *(where->p + i) = cpu_to_le32(current_block++);
}
/*
BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
- /* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+ if (mdb_free) {
+ /* Account for allocated meta_blocks */
+ mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
- /* update fs free blocks counter for truncate case */
- percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+ /* update fs dirty blocks counter */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
+ EXT4_I(inode)->i_allocated_meta_blocks = 0;
+ EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+ }
/* update per-inode reservations */
BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
EXT4_I(inode)->i_reserved_data_blocks -= used;
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
- EXT4_I(inode)->i_allocated_meta_blocks = 0;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
}
BUFFER_TRACE(bh, "call get_create_access");
fatal = ext4_journal_get_create_access(handle, bh);
if (!fatal && !buffer_uptodate(bh)) {
- memset(bh->b_data,0,inode->i_sb->s_blocksize);
+ memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int create, int *err)
{
- struct buffer_head * bh;
+ struct buffer_head *bh;
bh = ext4_getblk(handle, inode, block, create, err);
if (!bh)
return NULL;
}
-static int walk_page_buffers( handle_t *handle,
- struct buffer_head *head,
- unsigned from,
- unsigned to,
- int *partial,
- int (*fn)( handle_t *handle,
- struct buffer_head *bh))
+static int walk_page_buffers(handle_t *handle,
+ struct buffer_head *head,
+ unsigned from,
+ unsigned to,
+ int *partial,
+ int (*fn)(handle_t *handle,
+ struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
int err, ret = 0;
struct buffer_head *next;
- for ( bh = head, block_start = 0;
- ret == 0 && (bh != head || !block_start);
- block_start = block_end, bh = next)
+ for (bh = head, block_start = 0;
+ ret == 0 && (bh != head || !block_start);
+ block_start = block_end, bh = next)
{
next = bh->b_this_page;
block_end = block_start + blocksize;
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- struct inode *inode = mapping->host;
+ struct inode *inode = mapping->host;
int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
handle_t *handle;
int retries = 0;
- struct page *page;
+ struct page *page;
pgoff_t index;
- unsigned from, to;
+ unsigned from, to;
index = pos >> PAGE_CACHE_SHIFT;
- from = pos & (PAGE_CACHE_SIZE - 1);
- to = from + len;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
retry:
- handle = ext4_journal_start(inode, needed_blocks);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
}
page = __grab_cache_page(mapping, index);
}
if (ret) {
- unlock_page(page);
+ unlock_page(page);
ext4_journal_stop(handle);
- page_cache_release(page);
+ page_cache_release(page);
+ /*
+ * block_write_begin may have instantiated a few blocks
+ * outside i_size. Trim these off again. Don't need
+ * i_size_read because we hold i_mutex.
+ */
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
- /*
- * generic_write_end() will run mark_inode_dirty() if i_size
- * changes. So let's piggyback the i_disksize mark_inode_dirty
- * into that.
- */
loff_t new_i_size;
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = new_i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
loff_t new_i_size;
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = new_i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
+ loff_t new_i_size;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
- if (pos+copied > inode->i_size)
+ new_i_size = pos + copied;
+ if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
- if (inode->i_size > EXT4_I(inode)->i_disksize) {
- EXT4_I(inode)->i_disksize = inode->i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
{
+ int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned long md_needed, mdblocks, total = 0;
* in order to allocate nrblocks
* worse case is one extent per block
*/
+repeat:
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
mdblocks = ext4_calc_metadata_amount(inode, total);
md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
total = md_needed + nrblocks;
- if (ext4_has_free_blocks(sbi, total) < total) {
+ if (ext4_claim_free_blocks(sbi, total)) {
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ yield();
+ goto repeat;
+ }
return -ENOSPC;
}
- /* reduce fs free blocks counter */
- percpu_counter_sub(&sbi->s_freeblocks_counter, total);
-
EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
release = to_free + mdb_free;
- /* update fs free blocks counter for truncate case */
- percpu_counter_add(&sbi->s_freeblocks_counter, release);
+ /* update fs dirty blocks counter for truncate case */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
/* update per-inode reservations */
BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
struct writeback_control *wbc;
int io_done;
long pages_written;
+ int retval;
};
/*
unmap_underlying_metadata(bdev, bh->b_blocknr + i);
}
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
+ sector_t logical, long blk_cnt)
+{
+ int nr_pages, i;
+ pgoff_t index, end;
+ struct pagevec pvec;
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
+
+ index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (logical + blk_cnt - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(PageWriteback(page));
+ block_invalidatepage(page, 0);
+ ClearPageUptodate(page);
+ unlock_page(page);
+ }
+ }
+ return;
+}
+
+static void ext4_print_free_blocks(struct inode *inode)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ printk(KERN_EMERG "Total free blocks count %lld\n",
+ ext4_count_free_blocks(inode->i_sb));
+ printk(KERN_EMERG "Free/Dirty block details\n");
+ printk(KERN_EMERG "free_blocks=%lld\n",
+ percpu_counter_sum(&sbi->s_freeblocks_counter));
+ printk(KERN_EMERG "dirty_blocks=%lld\n",
+ percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ printk(KERN_EMERG "Block reservation details\n");
+ printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+ EXT4_I(inode)->i_reserved_data_blocks);
+ printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+ EXT4_I(inode)->i_reserved_meta_blocks);
+ return;
+}
+
/*
* mpage_da_map_blocks - go through given space
*
* The function skips space we know is already mapped to disk blocks.
*
*/
-static void mpage_da_map_blocks(struct mpage_da_data *mpd)
+static int mpage_da_map_blocks(struct mpage_da_data *mpd)
{
int err = 0;
- struct buffer_head *lbh = &mpd->lbh;
- sector_t next = lbh->b_blocknr;
struct buffer_head new;
+ struct buffer_head *lbh = &mpd->lbh;
+ sector_t next;
/*
* We consider only non-mapped and non-allocated blocks
*/
if (buffer_mapped(lbh) && !buffer_delay(lbh))
- return;
-
+ return 0;
new.b_state = lbh->b_state;
new.b_blocknr = 0;
new.b_size = lbh->b_size;
-
+ next = lbh->b_blocknr;
/*
* If we didn't accumulate anything
* to write simply return
*/
if (!new.b_size)
- return;
+ return 0;
err = mpd->get_block(mpd->inode, next, &new, 1);
- if (err)
- return;
+ if (err) {
+
+ /* If get block returns with error
+ * we simply return. Later writepage
+ * will redirty the page and writepages
+ * will find the dirty page again
+ */
+ if (err == -EAGAIN)
+ return 0;
+
+ if (err == -ENOSPC &&
+ ext4_count_free_blocks(mpd->inode->i_sb)) {
+ mpd->retval = err;
+ return 0;
+ }
+
+ /*
+ * get block failure will cause us
+ * to loop in writepages. Because
+ * a_ops->writepage won't be able to
+ * make progress. The page will be redirtied
+ * by writepage and writepages will again
+ * try to write the same.
+ */
+ printk(KERN_EMERG "%s block allocation failed for inode %lu "
+ "at logical offset %llu with max blocks "
+ "%zd with error %d\n",
+ __func__, mpd->inode->i_ino,
+ (unsigned long long)next,
+ lbh->b_size >> mpd->inode->i_blkbits, err);
+ printk(KERN_EMERG "This should not happen.!! "
+ "Data will be lost\n");
+ if (err == -ENOSPC) {
+ ext4_print_free_blocks(mpd->inode);
+ }
+ /* invlaidate all the pages */
+ ext4_da_block_invalidatepages(mpd, next,
+ lbh->b_size >> mpd->inode->i_blkbits);
+ return err;
+ }
BUG_ON(new.b_size == 0);
if (buffer_new(&new))
if (buffer_delay(lbh) || buffer_unwritten(lbh))
mpage_put_bnr_to_bhs(mpd, next, &new);
- return;
+ return 0;
}
#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
* We couldn't merge the block to our extent, so we
* need to flush current extent and start new one
*/
- mpage_da_map_blocks(mpd);
- mpage_da_submit_io(mpd);
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
mpd->io_done = 1;
return;
}
* and start IO on them using writepage()
*/
if (mpd->next_page != mpd->first_page) {
- mpage_da_map_blocks(mpd);
- mpage_da_submit_io(mpd);
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
/*
* skip rest of the page in the page_vec
*/
*/
static int mpage_da_writepages(struct address_space *mapping,
struct writeback_control *wbc,
- get_block_t get_block)
+ struct mpage_da_data *mpd)
{
- struct mpage_da_data mpd;
long to_write;
int ret;
- if (!get_block)
+ if (!mpd->get_block)
return generic_writepages(mapping, wbc);
- mpd.wbc = wbc;
- mpd.inode = mapping->host;
- mpd.lbh.b_size = 0;
- mpd.lbh.b_state = 0;
- mpd.lbh.b_blocknr = 0;
- mpd.first_page = 0;
- mpd.next_page = 0;
- mpd.get_block = get_block;
- mpd.io_done = 0;
- mpd.pages_written = 0;
+ mpd->lbh.b_size = 0;
+ mpd->lbh.b_state = 0;
+ mpd->lbh.b_blocknr = 0;
+ mpd->first_page = 0;
+ mpd->next_page = 0;
+ mpd->io_done = 0;
+ mpd->pages_written = 0;
+ mpd->retval = 0;
to_write = wbc->nr_to_write;
- ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd);
+ ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
/*
* Handle last extent of pages
*/
- if (!mpd.io_done && mpd.next_page != mpd.first_page) {
- mpage_da_map_blocks(&mpd);
- mpage_da_submit_io(&mpd);
+ if (!mpd->io_done && mpd->next_page != mpd->first_page) {
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
}
- wbc->nr_to_write = to_write - mpd.pages_written;
+ wbc->nr_to_write = to_write - mpd->pages_written;
return ret;
}
handle_t *handle = NULL;
handle = ext4_journal_current_handle();
- if (!handle) {
- ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
- bh_result, 0, 0, 0);
- BUG_ON(!ret);
- } else {
- ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
- bh_result, create, 0, EXT4_DELALLOC_RSVED);
- }
-
+ BUG_ON(!handle);
+ ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+ bh_result, create, 0, EXT4_DELALLOC_RSVED);
if (ret > 0) {
+
bh_result->b_size = (ret << inode->i_blkbits);
+ if (ext4_should_order_data(inode)) {
+ int retval;
+ retval = ext4_jbd2_file_inode(handle, inode);
+ if (retval)
+ /*
+ * Failed to add inode for ordered
+ * mode. Don't update file size
+ */
+ return retval;
+ }
+
/*
* Update on-disk size along with block allocation
* we don't use 'extend_disksize' as size may change
if (disksize > i_size_read(inode))
disksize = i_size_read(inode);
if (disksize > EXT4_I(inode)->i_disksize) {
- /*
- * XXX: replace with spinlock if seen contended -bzzz
- */
- down_write(&EXT4_I(inode)->i_data_sem);
- if (disksize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = disksize;
- up_write(&EXT4_I(inode)->i_data_sem);
-
- if (EXT4_I(inode)->i_disksize == disksize) {
- ret = ext4_mark_inode_dirty(handle, inode);
- return ret;
- }
+ ext4_update_i_disksize(inode, disksize);
+ ret = ext4_mark_inode_dirty(handle, inode);
+ return ret;
}
ret = 0;
}
{
handle_t *handle = NULL;
loff_t range_start = 0;
+ struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int needed_blocks, ret = 0, nr_to_writebump = 0;
long to_write, pages_skipped = 0;
range_start = wbc->range_start;
pages_skipped = wbc->pages_skipped;
+ mpd.wbc = wbc;
+ mpd.inode = mapping->host;
+
restart_loop:
to_write = wbc->nr_to_write;
while (!ret && to_write > 0) {
dump_stack();
goto out_writepages;
}
- if (ext4_should_order_data(inode)) {
- /*
- * With ordered mode we need to add
- * the inode to the journal handl
- * when we do block allocation.
- */
- ret = ext4_jbd2_file_inode(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out_writepages;
- }
- }
-
to_write -= wbc->nr_to_write;
- ret = mpage_da_writepages(mapping, wbc,
- ext4_da_get_block_write);
+
+ mpd.get_block = ext4_da_get_block_write;
+ ret = mpage_da_writepages(mapping, wbc, &mpd);
+
ext4_journal_stop(handle);
+
+ if (mpd.retval == -ENOSPC)
+ jbd2_journal_force_commit_nested(sbi->s_journal);
+
+ /* reset the retry count */
if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
* got one extent now try with
return ret;
}
+#define FALL_BACK_TO_NONDELALLOC 1
+static int ext4_nonda_switch(struct super_block *sb)
+{
+ s64 free_blocks, dirty_blocks;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ /*
+ * switch to non delalloc mode if we are running low
+ * on free block. The free block accounting via percpu
+ * counters can get slightly wrong with FBC_BATCH getting
+ * accumulated on each CPU without updating global counters
+ * Delalloc need an accurate free block accounting. So switch
+ * to non delalloc when we are near to error range.
+ */
+ free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ if (2 * free_blocks < 3 * dirty_blocks ||
+ free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ /*
+ * free block count is less that 150% of dirty blocks
+ * or free blocks is less that watermark
+ */
+ return 1;
+ }
+ return 0;
+}
+
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
+ if (ext4_nonda_switch(inode->i_sb)) {
+ *fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
+ return ext4_write_begin(file, mapping, pos,
+ len, flags, pagep, fsdata);
+ }
+ *fsdata = (void *)0;
retry:
/*
* With delayed allocation, we don't log the i_disksize update
unlock_page(page);
ext4_journal_stop(handle);
page_cache_release(page);
+ /*
+ * block_write_begin may have instantiated a few blocks
+ * outside i_size. Trim these off again. Don't need
+ * i_size_read because we hold i_mutex.
+ */
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
bh = page_buffers(page);
idx = offset >> inode->i_blkbits;
- for (i=0; i < idx; i++)
+ for (i = 0; i < idx; i++)
bh = bh->b_this_page;
if (!buffer_mapped(bh) || (buffer_delay(bh)))
handle_t *handle = ext4_journal_current_handle();
loff_t new_i_size;
unsigned long start, end;
+ int write_mode = (int)fsdata;
+
+ if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+ if (ext4_should_order_data(inode)) {
+ return ext4_ordered_write_end(file, mapping, pos,
+ len, copied, page, fsdata);
+ } else if (ext4_should_writeback_data(inode)) {
+ return ext4_writeback_write_end(file, mapping, pos,
+ len, copied, page, fsdata);
+ } else {
+ BUG();
+ }
+ }
start = pos & (PAGE_CACHE_SIZE - 1);
- end = start + copied -1;
+ end = start + copied - 1;
/*
* generic_write_end() will run mark_inode_dirty() if i_size
EXT4_I(inode)->i_disksize = new_i_size;
}
up_write(&EXT4_I(inode)->i_data_sem);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
}
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
return 0;
}
- return generic_block_bmap(mapping,block,ext4_get_block);
+ return generic_block_bmap(mapping, block, ext4_get_block);
}
static int bget_one(handle_t *handle, struct buffer_head *bh)
if (!partial->key && *partial->p)
/* Writer: end */
goto no_top;
- for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--)
+ for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
;
/*
* OK, we've found the last block that must survive. The rest of our
}
/* Writer: end */
- while(partial > p) {
+ while (partial > p) {
brelse(partial->bh);
partial--;
}
/* This zaps the entire block. Bottom up. */
BUFFER_TRACE(bh, "free child branches");
ext4_free_branches(handle, inode, bh,
- (__le32*)bh->b_data,
- (__le32*)bh->b_data + addr_per_block,
- depth);
+ (__le32 *) bh->b_data,
+ (__le32 *) bh->b_data + addr_per_block,
+ depth);
/*
* We've probably journalled the indirect block several
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
- if(!(test_opt (inode->i_sb, NO_UID32))) {
+ if (!(test_opt(inode->i_sb, NO_UID32))) {
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
if (inode->i_mode == 0 ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
/* this inode is deleted */
- brelse (bh);
+ brelse(bh);
ret = -ESTALE;
goto bad_inode;
}
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb)) {
- brelse (bh);
+ brelse(bh);
ret = -EIO;
goto bad_inode;
}
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
}
- brelse (iloc.bh);
+ brelse(iloc.bh);
ext4_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;
ext4_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
- if(!(test_opt(inode->i_sb, NO_UID32))) {
+ if (!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
/*
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
- if(!ei->i_dtime) {
+ if (!ei->i_dtime) {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(inode->i_uid));
raw_inode->i_gid_high =
ei->i_state &= ~EXT4_STATE_NEW;
out_brelse:
- brelse (bh);
+ brelse(bh);
ext4_std_error(inode->i_sb, err);
return err;
}
loff_t size;
unsigned long len;
int ret = -EINVAL;
+ void *fsdata;
struct file *file = vma->vm_file;
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
* on the same page though
*/
ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
- len, AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+ len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
if (ret < 0)
goto out_unlock;
ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
- len, len, page, NULL);
+ len, len, page, fsdata);
if (ret < 0)
goto out_unlock;
ret = 0;
unsigned int flags;
unsigned short rsv_window_size;
- ext4_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+ ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
case EXT4_IOC_SETRSVSZ: {
int err;
- if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
+ if (!test_opt(inode->i_sb, RESERVATION) || !S_ISREG(inode->i_mode))
return -ENOTTY;
if (!is_owner_or_cap(inode))
b2 = (unsigned char *) bitmap;
for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
if (b1[i] != b2[i]) {
- printk("corruption in group %lu at byte %u(%u):"
- " %x in copy != %x on disk/prealloc\n",
- e4b->bd_group, i, i * 8, b1[i], b2[i]);
+ printk(KERN_ERR "corruption in group %lu "
+ "at byte %u(%u): %x in copy != %x "
+ "on disk/prealloc\n",
+ e4b->bd_group, i, i * 8, b1[i], b2[i]);
BUG();
}
}
ext4_mb_init_per_dev_proc(sb);
ext4_mb_history_init(sb);
- printk("EXT4-fs: mballoc enabled\n");
+ printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
return 0;
}
mode_t mode = S_IFREG | S_IRUGO | S_IWUSR;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct proc_dir_entry *proc;
- char devname[64];
+ char devname[64], *p;
if (proc_root_ext4 == NULL) {
sbi->s_mb_proc = NULL;
return -EINVAL;
}
bdevname(sb->s_bdev, devname);
+ p = devname;
+ while ((p = strchr(p, '/')))
+ *p = '!';
+
sbi->s_mb_proc = proc_mkdir(devname, proc_root_ext4);
+ if (!sbi->s_mb_proc)
+ goto err_create_dir;
MB_PROC_HANDLER(EXT4_MB_STATS_NAME, stats);
MB_PROC_HANDLER(EXT4_MB_MAX_TO_SCAN_NAME, max_to_scan);
return 0;
err_out:
- printk(KERN_ERR "EXT4-fs: Unable to create %s\n", devname);
remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc);
remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc);
remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc);
remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_mb_proc);
remove_proc_entry(devname, proc_root_ext4);
sbi->s_mb_proc = NULL;
+err_create_dir:
+ printk(KERN_ERR "EXT4-fs: Unable to create %s\n", devname);
return -ENOMEM;
}
le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-
+ percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
/*
- * free blocks account has already be reduced/reserved
- * at write_begin() time for delayed allocation
- * do not double accounting
+ * Now reduce the dirty block count also. Should not go negative
*/
- if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
- percpu_counter_sub(&sbi->s_freeblocks_counter,
- ac->ac_b_ex.fe_len);
-
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, ac->ac_b_ex.fe_len);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
/*
* With delalloc we already reserved the blocks
*/
- ar->len = ext4_has_free_blocks(sbi, ar->len);
- }
-
- if (ar->len == 0) {
- *errp = -ENOSPC;
- return 0;
+ while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+ /* let others to free the space */
+ yield();
+ ar->len = ar->len >> 1;
+ }
+ if (!ar->len) {
+ *errp = -ENOSPC;
+ return 0;
+ }
}
-
while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
ar->flags |= EXT4_MB_HINT_NOPREALLOC;
ar->len--;
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
-static inline unsigned dx_get_hash (struct dx_entry *entry);
-static void dx_set_hash (struct dx_entry *entry, unsigned value);
-static unsigned dx_get_count (struct dx_entry *entries);
-static unsigned dx_get_limit (struct dx_entry *entries);
-static void dx_set_count (struct dx_entry *entries, unsigned value);
-static void dx_set_limit (struct dx_entry *entries, unsigned value);
-static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
-static unsigned dx_node_limit (struct inode *dir);
+static inline unsigned dx_get_hash(struct dx_entry *entry);
+static void dx_set_hash(struct dx_entry *entry, unsigned value);
+static unsigned dx_get_count(struct dx_entry *entries);
+static unsigned dx_get_limit(struct dx_entry *entries);
+static void dx_set_count(struct dx_entry *entries, unsigned value);
+static void dx_set_limit(struct dx_entry *entries, unsigned value);
+static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
+static unsigned dx_node_limit(struct inode *dir);
static struct dx_frame *dx_probe(struct dentry *dentry,
struct inode *dir,
struct dx_hash_info *hinfo,
struct dx_frame *frame,
int *err);
-static void dx_release (struct dx_frame *frames);
-static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
- struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static void dx_release(struct dx_frame *frames);
+static int dx_make_map(struct ext4_dir_entry_2 *de, int size,
+ struct dx_hash_info *hinfo, struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
-static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to,
+static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
struct dx_map_entry *offsets, int count);
-static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size);
static void dx_insert_block(struct dx_frame *frame,
u32 hash, ext4_lblk_t block);
static int ext4_htree_next_block(struct inode *dir, __u32 hash,
entry->block = cpu_to_le32(value);
}
-static inline unsigned dx_get_hash (struct dx_entry *entry)
+static inline unsigned dx_get_hash(struct dx_entry *entry)
{
return le32_to_cpu(entry->hash);
}
-static inline void dx_set_hash (struct dx_entry *entry, unsigned value)
+static inline void dx_set_hash(struct dx_entry *entry, unsigned value)
{
entry->hash = cpu_to_le32(value);
}
-static inline unsigned dx_get_count (struct dx_entry *entries)
+static inline unsigned dx_get_count(struct dx_entry *entries)
{
return le16_to_cpu(((struct dx_countlimit *) entries)->count);
}
-static inline unsigned dx_get_limit (struct dx_entry *entries)
+static inline unsigned dx_get_limit(struct dx_entry *entries)
{
return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
}
-static inline void dx_set_count (struct dx_entry *entries, unsigned value)
+static inline void dx_set_count(struct dx_entry *entries, unsigned value)
{
((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
}
-static inline void dx_set_limit (struct dx_entry *entries, unsigned value)
+static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
{
((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
}
-static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
+static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
{
unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
EXT4_DIR_REC_LEN(2) - infosize;
return entry_space / sizeof(struct dx_entry);
}
-static inline unsigned dx_node_limit (struct inode *dir)
+static inline unsigned dx_node_limit(struct inode *dir)
{
unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
return entry_space / sizeof(struct dx_entry);
* Debug
*/
#ifdef DX_DEBUG
-static void dx_show_index (char * label, struct dx_entry *entries)
+static void dx_show_index(char * label, struct dx_entry *entries)
{
int i, n = dx_get_count (entries);
- printk("%s index ", label);
+ printk(KERN_DEBUG "%s index ", label);
for (i = 0; i < n; i++) {
- printk("%x->%lu ", i? dx_get_hash(entries + i) :
+ printk("%x->%lu ", i ? dx_get_hash(entries + i) :
0, (unsigned long)dx_get_block(entries + i));
}
printk("\n");
struct dx_entry *entries, int levels)
{
unsigned blocksize = dir->i_sb->s_blocksize;
- unsigned count = dx_get_count (entries), names = 0, space = 0, i;
+ unsigned count = dx_get_count(entries), names = 0, space = 0, i;
unsigned bcount = 0;
struct buffer_head *bh;
int err;
names += stats.names;
space += stats.space;
bcount += stats.bcount;
- brelse (bh);
+ brelse(bh);
}
if (bcount)
- printk("%snames %u, fullness %u (%u%%)\n", levels?"":" ",
- names, space/bcount,(space/bcount)*100/blocksize);
+ printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n",
+ levels ? "" : " ", names, space/bcount,
+ (space/bcount)*100/blocksize);
return (struct stats) { names, space, bcount};
}
#endif /* DX_DEBUG */
goto fail;
}
- dxtrace (printk("Look up %x", hash));
+ dxtrace(printk("Look up %x", hash));
while (1)
{
count = dx_get_count(entries);
0, &err)))
return err; /* Failure */
p++;
- brelse (p->bh);
+ brelse(p->bh);
p->bh = bh;
p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
}
/* On error, skip the f_pos to the next block. */
dir_file->f_pos = (dir_file->f_pos |
(dir->i_sb->s_blocksize - 1)) + 1;
- brelse (bh);
+ brelse(bh);
return count;
}
ext4fs_dirhash(de->name, de->name_len, hinfo);
int ret, err;
__u32 hashval;
- dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
- start_minor_hash));
+ dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
+ start_hash, start_minor_hash));
dir = dir_file->f_path.dentry->d_inode;
if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
break;
}
dx_release(frames);
- dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n",
- count, *next_hash));
+ dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, "
+ "next hash: %x\n", count, *next_hash));
return count;
errout:
dx_release(frames);
/*
* Returns 0 if not found, -1 on failure, and 1 on success
*/
-static inline int search_dirblock(struct buffer_head * bh,
+static inline int search_dirblock(struct buffer_head *bh,
struct inode *dir,
struct dentry *dentry,
unsigned long offset,
static struct buffer_head * ext4_find_entry (struct dentry *dentry,
struct ext4_dir_entry_2 ** res_dir)
{
- struct super_block * sb;
- struct buffer_head * bh_use[NAMEI_RA_SIZE];
- struct buffer_head * bh, *ret = NULL;
+ struct super_block *sb;
+ struct buffer_head *bh_use[NAMEI_RA_SIZE];
+ struct buffer_head *bh, *ret = NULL;
ext4_lblk_t start, block, b;
int ra_max = 0; /* Number of bh's in the readahead
buffer, bh_use[] */
*/
if (bh || (err != ERR_BAD_DX_DIR))
return bh;
- dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
+ dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+ "falling back\n"));
}
nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
start = EXT4_I(dir)->i_dir_start_lookup;
cleanup_and_exit:
/* Clean up the read-ahead blocks */
for (; ra_ptr < ra_max; ra_ptr++)
- brelse (bh_use[ra_ptr]);
+ brelse(bh_use[ra_ptr]);
return ret;
}
return bh;
}
}
- brelse (bh);
+ brelse(bh);
/* Check to see if we should continue to search */
retval = ext4_htree_next_block(dir, hash, frame,
frames, NULL);
*err = -ENOENT;
errout:
- dxtrace(printk("%s not found\n", name));
+ dxtrace(printk(KERN_DEBUG "%s not found\n", name));
dx_release (frames);
return NULL;
}
-static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
- struct inode * inode;
- struct ext4_dir_entry_2 * de;
- struct buffer_head * bh;
+ struct inode *inode;
+ struct ext4_dir_entry_2 *de;
+ struct buffer_head *bh;
if (dentry->d_name.len > EXT4_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
inode = NULL;
if (bh) {
unsigned long ino = le32_to_cpu(de->inode);
- brelse (bh);
+ brelse(bh);
if (!ext4_valid_inum(dir->i_sb, ino)) {
ext4_error(dir->i_sb, "ext4_lookup",
"bad inode number: %lu", ino);
/* create map in the end of data2 block */
map = (struct dx_map_entry *) (data2 + blocksize);
- count = dx_make_map ((struct ext4_dir_entry_2 *) data1,
+ count = dx_make_map((struct ext4_dir_entry_2 *) data1,
blocksize, hinfo, map);
map -= count;
- dx_sort_map (map, count);
+ dx_sort_map(map, count);
/* Split the existing block in the middle, size-wise */
size = 0;
move = 0;
/* Fancy dance to stay within two buffers */
de2 = dx_move_dirents(data1, data2, map + split, count - split);
- de = dx_pack_dirents(data1,blocksize);
+ de = dx_pack_dirents(data1, blocksize);
de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2);
dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
swap(*bh, bh2);
de = de2;
}
- dx_insert_block (frame, hash2 + continued, newblock);
- err = ext4_journal_dirty_metadata (handle, bh2);
+ dx_insert_block(frame, hash2 + continued, newblock);
+ err = ext4_journal_dirty_metadata(handle, bh2);
if (err)
goto journal_error;
- err = ext4_journal_dirty_metadata (handle, frame->bh);
+ err = ext4_journal_dirty_metadata(handle, frame->bh);
if (err)
goto journal_error;
- brelse (bh2);
- dxtrace(dx_show_index ("frame", frame->entries));
+ brelse(bh2);
+ dxtrace(dx_show_index("frame", frame->entries));
return de;
journal_error:
*/
static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
struct inode *inode, struct ext4_dir_entry_2 *de,
- struct buffer_head * bh)
+ struct buffer_head *bh)
{
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
while ((char *) de <= top) {
if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
bh, offset)) {
- brelse (bh);
+ brelse(bh);
return -EIO;
}
- if (ext4_match (namelen, name, de)) {
- brelse (bh);
+ if (ext4_match(namelen, name, de)) {
+ brelse(bh);
return -EEXIST;
}
nlen = EXT4_DIR_REC_LEN(de->name_len);
} else
de->inode = 0;
de->name_len = namelen;
- memcpy (de->name, name, namelen);
+ memcpy(de->name, name, namelen);
/*
* XXX shouldn't update any times until successful
* completion of syscall, but too many callers depend
struct fake_dirent *fde;
blocksize = dir->i_sb->s_blocksize;
- dxtrace(printk("Creating index\n"));
+ dxtrace(printk(KERN_DEBUG "Creating index\n"));
retval = ext4_journal_get_write_access(handle, bh);
if (retval) {
ext4_std_error(dir->i_sb, retval);
}
root = (struct dx_root *) bh->b_data;
- bh2 = ext4_append (handle, dir, &block, &retval);
+ bh2 = ext4_append(handle, dir, &block, &retval);
if (!(bh2)) {
brelse(bh);
return retval;
root->info.info_length = sizeof(root->info);
root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
entries = root->entries;
- dx_set_block (entries, 1);
- dx_set_count (entries, 1);
- dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info)));
+ dx_set_block(entries, 1);
+ dx_set_count(entries, 1);
+ dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));
/* Initialize as for dx_probe */
hinfo.hash_version = root->info.hash_version;
* may not sleep between calling this and putting something into
* the entry, as someone else might have used it while you slept.
*/
-static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
- struct inode *inode)
+static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
+ struct inode *inode)
{
struct inode *dir = dentry->d_parent->d_inode;
unsigned long offset;
- struct buffer_head * bh;
+ struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
- struct super_block * sb;
+ struct super_block *sb;
int retval;
int dx_fallback=0;
unsigned blocksize;
struct dx_frame frames[2], *frame;
struct dx_entry *entries, *at;
struct dx_hash_info hinfo;
- struct buffer_head * bh;
+ struct buffer_head *bh;
struct inode *dir = dentry->d_parent->d_inode;
- struct super_block * sb = dir->i_sb;
+ struct super_block *sb = dir->i_sb;
struct ext4_dir_entry_2 *de;
int err;
}
/* Block full, should compress but for now just split */
- dxtrace(printk("using %u of %u node entries\n",
+ dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
dx_get_count(entries), dx_get_limit(entries)));
/* Need to split index? */
if (dx_get_count(entries) == dx_get_limit(entries)) {
if (levels) {
unsigned icount1 = icount/2, icount2 = icount - icount1;
unsigned hash2 = dx_get_hash(entries + icount1);
- dxtrace(printk("Split index %i/%i\n", icount1, icount2));
+ dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
+ icount1, icount2));
BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
err = ext4_journal_get_write_access(handle,
if (err)
goto journal_error;
- memcpy ((char *) entries2, (char *) (entries + icount1),
- icount2 * sizeof(struct dx_entry));
- dx_set_count (entries, icount1);
- dx_set_count (entries2, icount2);
- dx_set_limit (entries2, dx_node_limit(dir));
+ memcpy((char *) entries2, (char *) (entries + icount1),
+ icount2 * sizeof(struct dx_entry));
+ dx_set_count(entries, icount1);
+ dx_set_count(entries2, icount2);
+ dx_set_limit(entries2, dx_node_limit(dir));
/* Which index block gets the new entry? */
if (at - entries >= icount1) {
frame->entries = entries = entries2;
swap(frame->bh, bh2);
}
- dx_insert_block (frames + 0, hash2, newblock);
- dxtrace(dx_show_index ("node", frames[1].entries));
- dxtrace(dx_show_index ("node",
+ dx_insert_block(frames + 0, hash2, newblock);
+ dxtrace(dx_show_index("node", frames[1].entries));
+ dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
err = ext4_journal_dirty_metadata(handle, bh2);
if (err)
goto journal_error;
brelse (bh2);
} else {
- dxtrace(printk("Creating second level index...\n"));
+ dxtrace(printk(KERN_DEBUG
+ "Creating second level index...\n"));
memcpy((char *) entries2, (char *) entries,
icount * sizeof(struct dx_entry));
dx_set_limit(entries2, dx_node_limit(dir));
* ext4_delete_entry deletes a directory entry by merging it with the
* previous entry
*/
-static int ext4_delete_entry (handle_t *handle,
- struct inode * dir,
- struct ext4_dir_entry_2 * de_del,
- struct buffer_head * bh)
+static int ext4_delete_entry(handle_t *handle,
+ struct inode *dir,
+ struct ext4_dir_entry_2 *de_del,
+ struct buffer_head *bh)
{
- struct ext4_dir_entry_2 * de, * pde;
+ struct ext4_dir_entry_2 *de, *pde;
int i;
i = 0;
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext4_create (struct inode * dir, struct dentry * dentry, int mode,
- struct nameidata *nd)
+static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
+ struct nameidata *nd)
{
handle_t *handle;
- struct inode * inode;
+ struct inode *inode;
int err, retries = 0;
retry:
return err;
}
-static int ext4_mknod (struct inode * dir, struct dentry *dentry,
- int mode, dev_t rdev)
+static int ext4_mknod(struct inode *dir, struct dentry *dentry,
+ int mode, dev_t rdev)
{
handle_t *handle;
struct inode *inode;
if (IS_DIRSYNC(dir))
handle->h_sync = 1;
- inode = ext4_new_inode (handle, dir, mode);
+ inode = ext4_new_inode(handle, dir, mode);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
return err;
}
-static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
handle_t *handle;
- struct inode * inode;
- struct buffer_head * dir_block;
- struct ext4_dir_entry_2 * de;
+ struct inode *inode;
+ struct buffer_head *dir_block;
+ struct ext4_dir_entry_2 *de;
int err, retries = 0;
if (EXT4_DIR_LINK_MAX(dir))
if (IS_DIRSYNC(dir))
handle->h_sync = 1;
- inode = ext4_new_inode (handle, dir, S_IFDIR | mode);
+ inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
- dir_block = ext4_bread (handle, inode, 0, 1, &err);
+ dir_block = ext4_bread(handle, inode, 0, 1, &err);
if (!dir_block)
goto out_clear_inode;
BUFFER_TRACE(dir_block, "get_write_access");
de->inode = cpu_to_le32(inode->i_ino);
de->name_len = 1;
de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len));
- strcpy (de->name, ".");
+ strcpy(de->name, ".");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
de = ext4_next_entry(de);
de->inode = cpu_to_le32(dir->i_ino);
de->rec_len = ext4_rec_len_to_disk(inode->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(1));
de->name_len = 2;
- strcpy (de->name, "..");
+ strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
ext4_journal_dirty_metadata(handle, dir_block);
- brelse (dir_block);
+ brelse(dir_block);
ext4_mark_inode_dirty(handle, inode);
- err = ext4_add_entry (handle, dentry, inode);
+ err = ext4_add_entry(handle, dentry, inode);
if (err) {
out_clear_inode:
clear_nlink(inode);
ext4_mark_inode_dirty(handle, inode);
- iput (inode);
+ iput(inode);
goto out_stop;
}
ext4_inc_count(handle, dir);
/*
* routine to check that the specified directory is empty (for rmdir)
*/
-static int empty_dir (struct inode * inode)
+static int empty_dir(struct inode *inode)
{
unsigned long offset;
- struct buffer_head * bh;
- struct ext4_dir_entry_2 * de, * de1;
- struct super_block * sb;
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de, *de1;
+ struct super_block *sb;
int err = 0;
sb = inode->i_sb;
if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
- !(bh = ext4_bread (NULL, inode, 0, 0, &err))) {
+ !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
if (err)
ext4_error(inode->i_sb, __func__,
"error %d reading directory #%lu offset 0",
de1 = ext4_next_entry(de);
if (le32_to_cpu(de->inode) != inode->i_ino ||
!le32_to_cpu(de1->inode) ||
- strcmp (".", de->name) ||
- strcmp ("..", de1->name)) {
- ext4_warning (inode->i_sb, "empty_dir",
- "bad directory (dir #%lu) - no `.' or `..'",
- inode->i_ino);
- brelse (bh);
+ strcmp(".", de->name) ||
+ strcmp("..", de1->name)) {
+ ext4_warning(inode->i_sb, "empty_dir",
+ "bad directory (dir #%lu) - no `.' or `..'",
+ inode->i_ino);
+ brelse(bh);
return 1;
}
offset = ext4_rec_len_from_disk(de->rec_len) +
ext4_rec_len_from_disk(de1->rec_len);
de = ext4_next_entry(de1);
- while (offset < inode->i_size ) {
+ while (offset < inode->i_size) {
if (!bh ||
(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
err = 0;
- brelse (bh);
- bh = ext4_bread (NULL, inode,
+ brelse(bh);
+ bh = ext4_bread(NULL, inode,
offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
if (!bh) {
if (err)
continue;
}
if (le32_to_cpu(de->inode)) {
- brelse (bh);
+ brelse(bh);
return 0;
}
offset += ext4_rec_len_from_disk(de->rec_len);
de = ext4_next_entry(de);
}
- brelse (bh);
+ brelse(bh);
return 1;
}
* ->i_nlink. For, say it, character device. Not a regular file,
* not a directory, not a symlink and ->i_nlink > 0.
*/
- J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+ J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
goto out_err;
}
-static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
+static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
{
int retval;
- struct inode * inode;
- struct buffer_head * bh;
- struct ext4_dir_entry_2 * de;
+ struct inode *inode;
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de;
handle_t *handle;
/* Initialize quotas before so that eventual writes go in
return PTR_ERR(handle);
retval = -ENOENT;
- bh = ext4_find_entry (dentry, &de);
+ bh = ext4_find_entry(dentry, &de);
if (!bh)
goto end_rmdir;
goto end_rmdir;
retval = -ENOTEMPTY;
- if (!empty_dir (inode))
+ if (!empty_dir(inode))
goto end_rmdir;
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto end_rmdir;
if (!EXT4_DIR_LINK_EMPTY(inode))
- ext4_warning (inode->i_sb, "ext4_rmdir",
- "empty directory has too many links (%d)",
- inode->i_nlink);
+ ext4_warning(inode->i_sb, "ext4_rmdir",
+ "empty directory has too many links (%d)",
+ inode->i_nlink);
inode->i_version++;
clear_nlink(inode);
/* There's no need to set i_disksize: the fact that i_nlink is
end_rmdir:
ext4_journal_stop(handle);
- brelse (bh);
+ brelse(bh);
return retval;
}
-static int ext4_unlink(struct inode * dir, struct dentry *dentry)
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
{
int retval;
- struct inode * inode;
- struct buffer_head * bh;
- struct ext4_dir_entry_2 * de;
+ struct inode *inode;
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de;
handle_t *handle;
/* Initialize quotas before so that eventual writes go
handle->h_sync = 1;
retval = -ENOENT;
- bh = ext4_find_entry (dentry, &de);
+ bh = ext4_find_entry(dentry, &de);
if (!bh)
goto end_unlink;
goto end_unlink;
if (!inode->i_nlink) {
- ext4_warning (inode->i_sb, "ext4_unlink",
- "Deleting nonexistent file (%lu), %d",
- inode->i_ino, inode->i_nlink);
+ ext4_warning(inode->i_sb, "ext4_unlink",
+ "Deleting nonexistent file (%lu), %d",
+ inode->i_ino, inode->i_nlink);
inode->i_nlink = 1;
}
retval = ext4_delete_entry(handle, dir, de, bh);
end_unlink:
ext4_journal_stop(handle);
- brelse (bh);
+ brelse(bh);
return retval;
}
-static int ext4_symlink (struct inode * dir,
- struct dentry *dentry, const char * symname)
+static int ext4_symlink(struct inode *dir,
+ struct dentry *dentry, const char *symname)
{
handle_t *handle;
- struct inode * inode;
+ struct inode *inode;
int l, err, retries = 0;
l = strlen(symname)+1;
if (IS_DIRSYNC(dir))
handle->h_sync = 1;
- inode = ext4_new_inode (handle, dir, S_IFLNK|S_IRWXUGO);
+ inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
- if (l > sizeof (EXT4_I(inode)->i_data)) {
+ if (l > sizeof(EXT4_I(inode)->i_data)) {
inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
/*
if (err) {
clear_nlink(inode);
ext4_mark_inode_dirty(handle, inode);
- iput (inode);
+ iput(inode);
goto out_stop;
}
} else {
/* clear the extent format for fast symlink */
EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
inode->i_op = &ext4_fast_symlink_inode_operations;
- memcpy((char*)&EXT4_I(inode)->i_data,symname,l);
+ memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
inode->i_size = l-1;
}
EXT4_I(inode)->i_disksize = inode->i_size;
return err;
}
-static int ext4_link (struct dentry * old_dentry,
- struct inode * dir, struct dentry *dentry)
+static int ext4_link(struct dentry *old_dentry,
+ struct inode *dir, struct dentry *dentry)
{
handle_t *handle;
struct inode *inode = old_dentry->d_inode;
* Anybody can rename anything with this: the permission checks are left to the
* higher-level routines.
*/
-static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
- struct inode * new_dir,struct dentry *new_dentry)
+static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
{
handle_t *handle;
- struct inode * old_inode, * new_inode;
- struct buffer_head * old_bh, * new_bh, * dir_bh;
- struct ext4_dir_entry_2 * old_de, * new_de;
+ struct inode *old_inode, *new_inode;
+ struct buffer_head *old_bh, *new_bh, *dir_bh;
+ struct ext4_dir_entry_2 *old_de, *new_de;
int retval;
old_bh = new_bh = dir_bh = NULL;
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
handle->h_sync = 1;
- old_bh = ext4_find_entry (old_dentry, &old_de);
+ old_bh = ext4_find_entry(old_dentry, &old_de);
/*
* Check for inode number is _not_ due to possible IO errors.
* We might rmdir the source, keep it as pwd of some process
goto end_rename;
new_inode = new_dentry->d_inode;
- new_bh = ext4_find_entry (new_dentry, &new_de);
+ new_bh = ext4_find_entry(new_dentry, &new_de);
if (new_bh) {
if (!new_inode) {
- brelse (new_bh);
+ brelse(new_bh);
new_bh = NULL;
}
}
if (S_ISDIR(old_inode->i_mode)) {
if (new_inode) {
retval = -ENOTEMPTY;
- if (!empty_dir (new_inode))
+ if (!empty_dir(new_inode))
goto end_rename;
}
retval = -EIO;
- dir_bh = ext4_bread (handle, old_inode, 0, 0, &retval);
+ dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
if (!dir_bh)
goto end_rename;
if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
goto end_rename;
retval = -EMLINK;
- if (!new_inode && new_dir!=old_dir &&
+ if (!new_inode && new_dir != old_dir &&
new_dir->i_nlink >= EXT4_LINK_MAX)
goto end_rename;
}
if (!new_bh) {
- retval = ext4_add_entry (handle, new_dentry, old_inode);
+ retval = ext4_add_entry(handle, new_dentry, old_inode);
if (retval)
goto end_rename;
} else {
retval = 0;
end_rename:
- brelse (dir_bh);
- brelse (old_bh);
- brelse (new_bh);
+ brelse(dir_bh);
+ brelse(old_bh);
+ brelse(new_bh);
ext4_journal_stop(handle);
return retval;
}
"EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
gdb_num);
- /*
- * If we are not using the primary superblock/GDT copy don't resize,
+ /*
+ * If we are not using the primary superblock/GDT copy don't resize,
* because the user tools have no way of handling this. Probably a
* bad time to do it anyways.
*/
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb));
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+ ext4_group_t flex_group;
+ flex_group = ext4_flex_group(sbi, input->group);
+ sbi->s_flex_groups[flex_group].free_blocks +=
+ input->free_blocks_count;
+ sbi->s_flex_groups[flex_group].free_inodes +=
+ EXT4_INODES_PER_GROUP(sb);
+ }
+
ext4_journal_dirty_metadata(handle, sbi->s_sbh);
sb->s_dirt = 1;
ext4_group_t o_groups_count;
ext4_grpblk_t last;
ext4_grpblk_t add;
- struct buffer_head * bh;
+ struct buffer_head *bh;
handle_t *handle;
int err;
unsigned long freed_blocks;
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
if (sbi->s_jquota_fmt)
seq_printf(seq, ",jqfmt=%s",
- (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
+ (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
if (sbi->s_qf_names[USRQUOTA])
seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
}
#ifdef CONFIG_QUOTA
-#define QTYPE2NAME(t) ((t) == USRQUOTA?"user":"group")
+#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
static int ext4_dquot_initialize(struct inode *inode, int type);
/*todo: use simple_strtoll with >32bit ext4 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
- printk("EXT4-fs: Invalid sb specification: %s\n",
+ printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
(char *) *data);
return 1;
}
#else
case Opt_user_xattr:
case Opt_nouser_xattr:
- printk("EXT4 (no)user_xattr options not supported\n");
+ printk(KERN_ERR "EXT4 (no)user_xattr options "
+ "not supported\n");
break;
#endif
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
#else
case Opt_acl:
case Opt_noacl:
- printk("EXT4 (no)acl options not supported\n");
+ printk(KERN_ERR "EXT4 (no)acl options "
+ "not supported\n");
break;
#endif
case Opt_reservation:
sb_any_quota_suspended(sb)) &&
!sbi->s_qf_names[qtype]) {
printk(KERN_ERR
- "EXT4-fs: Cannot change journaled "
- "quota options when quota turned on.\n");
+ "EXT4-fs: Cannot change journaled "
+ "quota options when quota turned on.\n");
return 0;
}
qname = match_strdup(&args[0]);
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
- printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id);
if (EXT4_SB(sb)->s_journal->j_inode == NULL) {
char b[BDEVNAME_SIZE];
- printk("external journal on %s\n",
- bdevname(EXT4_SB(sb)->s_journal->j_dev, b));
+ printk(KERN_INFO "EXT4 FS on %s, external journal on %s\n",
+ sb->s_id, bdevname(EXT4_SB(sb)->s_journal->j_dev, b));
} else {
- printk("internal journal\n");
+ printk(KERN_INFO "EXT4 FS on %s, internal journal\n",
+ sb->s_id);
}
return res;
}
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
groups_per_flex = 1 << sbi->s_log_groups_per_flex;
- flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
- groups_per_flex;
+ /* We allocate both existing and potentially added groups */
+ flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
+ ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
+ EXT4_DESC_PER_BLOCK_BITS(sb))) /
+ groups_per_flex;
sbi->s_flex_groups = kzalloc(flex_group_count *
sizeof(struct flex_groups), GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
flexbg_flag = 1;
- ext4_debug ("Checking group descriptors");
+ ext4_debug("Checking group descriptors");
for (i = 0; i < sbi->s_groups_count; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
"Checksum for group %lu failed (%u!=%u)\n",
i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
- if (!(sb->s_flags & MS_RDONLY))
+ if (!(sb->s_flags & MS_RDONLY)) {
+ spin_unlock(sb_bgl_lock(sbi, i));
return 0;
+ }
}
spin_unlock(sb_bgl_lock(sbi, i));
if (!flexbg_flag)
DQUOT_INIT(inode);
if (inode->i_nlink) {
printk(KERN_DEBUG
- "%s: truncating inode %lu to %Ld bytes\n",
+ "%s: truncating inode %lu to %lld bytes\n",
__func__, inode->i_ino, inode->i_size);
- jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
+ jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
ext4_truncate(inode);
nr_truncates++;
err = percpu_counter_init(&sbi->s_dirs_counter,
ext4_count_dirs(sb));
}
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ }
if (err) {
printk(KERN_ERR "EXT4-fs: insufficient memory\n");
goto failed_mount3;
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
return NULL;
}
- jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
+ jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
journal_inode, journal_inode->i_size);
if (!S_ISREG(journal_inode->i_mode)) {
printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
return -EINVAL;
}
+ if (journal->j_flags & JBD2_BARRIER)
+ printk(KERN_INFO "EXT4-fs: barriers enabled\n");
+ else
+ printk(KERN_INFO "EXT4-fs: barriers disabled\n");
+
if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
err = jbd2_journal_update_format(journal);
if (err) {
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
- buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+ buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
ext4_free_blocks_count_set(es, buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
handle_t *handle = journal_current_handle();
if (!handle) {
- printk(KERN_WARNING "EXT4-fs: Quota write (off=%Lu, len=%Lu)"
+ printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
" cancelled because transaction is not started.\n",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
#include "ext4.h"
#include "xattr.h"
-static void * ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
- nd_set_link(nd, (char*)ei->i_data);
+ nd_set_link(nd, (char *) ei->i_data);
return NULL;
}
(((name_len) + EXT4_XATTR_ROUND + \
sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
#define EXT4_XATTR_NEXT(entry) \
- ( (struct ext4_xattr_entry *)( \
- (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)) )
+ ((struct ext4_xattr_entry *)( \
+ (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)))
#define EXT4_XATTR_SIZE(size) \
(((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
void percpu_counter_destroy(struct percpu_counter *fbc);
void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
-s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
+s64 __percpu_counter_sum(struct percpu_counter *fbc);
static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
{
- s64 ret = __percpu_counter_sum(fbc, 0);
+ s64 ret = __percpu_counter_sum(fbc);
return ret < 0 ? 0 : ret;
}
-static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
-{
- return __percpu_counter_sum(fbc, 1);
-}
-
-
static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
{
- return __percpu_counter_sum(fbc, 0);
+ return __percpu_counter_sum(fbc);
}
static inline s64 percpu_counter_read(struct percpu_counter *fbc)
* Add up all the per-cpu counts, return the result. This is a more accurate
* but much slower version of percpu_counter_read_positive()
*/
-s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
{
s64 ret;
int cpu;
for_each_online_cpu(cpu) {
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
ret += *pcount;
- if (set)
- *pcount = 0;
+ *pcount = 0;
}
- if (set)
- fbc->count = ret;
+ fbc->count = ret;
spin_unlock(&fbc->lock);
return ret;