* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (57 commits)
jbd2: Fix oops in jbd2_journal_init_inode() on corrupted fs
ext4: Remove "extents" mount option
block: Add Kconfig help which notes that ext4 needs CONFIG_LBD
ext4: Make printk's consistently prefixed with "EXT4-fs: "
ext4: Add sanity checks for the superblock before mounting the filesystem
ext4: Add mount option to set kjournald's I/O priority
jbd2: Submit writes to the journal using WRITE_SYNC
jbd2: Add pid and journal device name to the "kjournald2 starting" message
ext4: Add markers for better debuggability
ext4: Remove code to create the journal inode
ext4: provide function to release metadata pages under memory pressure
ext3: provide function to release metadata pages under memory pressure
add releasepage hooks to block devices which can be used by file systems
ext4: Fix s_dirty_blocks_counter if block allocation failed with nodelalloc
ext4: Init the complete page while building buddy cache
ext4: Don't allow new groups to be added during block allocation
ext4: mark the blocks/inode bitmap beyond end of group as used
ext4: Use new buffer_head flag to check uninit group bitmaps initialization
ext4: Fix the race between read_inode_bitmap() and ext4_new_inode()
ext4: code cleanup
...
}
lock_kernel();
+ restart:
ret = -ENXIO;
disk = get_gendisk(bdev->bd_dev, &partno);
if (disk->fops->open) {
ret = disk->fops->open(bdev, mode);
+ if (ret == -ERESTARTSYS) {
+ /* Lost a race with 'disk' being
+ * deleted, try again.
+ * See md.c
+ */
+ disk_put_part(bdev->bd_part);
+ bdev->bd_part = NULL;
+ module_put(disk->fops->owner);
+ put_disk(disk);
+ bdev->bd_disk = NULL;
+ mutex_unlock(&bdev->bd_mutex);
+ goto restart;
+ }
if (ret)
goto out_clear;
}
return blkdev_ioctl(bdev, mode, cmd, arg);
}
+ /*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+ static int blkdev_releasepage(struct page *page, gfp_t wait)
+ {
+ struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+ if (super && super->s_op->bdev_try_to_free_page)
+ return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+ return try_to_free_buffers(page);
+ }
+
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = generic_writepages,
+ .releasepage = blkdev_releasepage,
.direct_IO = blkdev_direct_IO,
};
/**
* lookup_bdev - lookup a struct block_device by name
- * @path: special file representing the block device
+ * @pathname: special file representing the block device
*
* Get a reference to the blockdevice at @pathname in the current
* namespace if possible and return it. Return ERR_PTR(error)
#define assert(test) J_ASSERT(test)
#endif
-#ifndef swap
-#define swap(x, y) do { typeof(x) z = x; x = y; y = z; } while (0)
-#endif
-
#ifdef DX_DEBUG
#define dxtrace(command) command
#else
goto fail;
}
hinfo->hash_version = root->info.hash_version;
+ if (hinfo->hash_version <= DX_HASH_TEA)
+ hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
if (entry)
ext3fs_dirhash(entry->name, entry->len, hinfo);
dir = dir_file->f_path.dentry->d_inode;
if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version +=
+ EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
start_hash, start_minor_hash);
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split, move, size, i;
+ unsigned split, move, size;
struct ext3_dir_entry_2 *de = NULL, *de2;
- int err = 0;
+ int err = 0, i;
bh2 = ext3_append (handle, dir, &newblock, &err);
if (!(bh2)) {
/* Initialize as for dx_probe */
hinfo.hash_version = root->info.hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
ext3fs_dirhash(name, namelen, &hinfo);
frame = frames;
ext3_blkdev_remove(sbi);
}
sb->s_fs_info = NULL;
+ kfree(sbi->s_blockgroup_lock);
kfree(sbi);
return;
}
ext3_nfs_get_inode);
}
+ /*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device. Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd layer's try_to_free_buffers() function to release them.
+ */
+ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+ gfp_t wait)
+ {
+ journal_t *journal = EXT3_SB(sb)->s_journal;
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ if (journal)
+ return journal_try_to_free_buffers(journal, page,
+ wait & ~__GFP_WAIT);
+ return try_to_free_buffers(page);
+ }
+
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
.acquire_dquot = ext3_acquire_dquot,
.release_dquot = ext3_release_dquot,
.mark_dirty = ext3_mark_dquot_dirty,
- .write_info = ext3_write_info
+ .write_info = ext3_write_info,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
};
static struct quotactl_ops ext3_qctl_operations = {
.quota_read = ext3_quota_read,
.quota_write = ext3_quota_write,
#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext3_export_ops = {
case Opt_grpjquota:
qtype = GRPQUOTA;
set_qf_name:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
printk(KERN_ERR
"EXT3-fs: Cannot change journaled "
case Opt_offgrpjquota:
qtype = GRPQUOTA;
clear_qf_name:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
sbi->s_qf_names[qtype]) {
printk(KERN_ERR "EXT3-fs: Cannot change "
"journaled quota options when "
case Opt_jqfmt_vfsv0:
qfmt = QFMT_VFS_V0;
set_qf_format:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
printk(KERN_ERR "EXT3-fs: Cannot change "
"journaled quota options when "
set_opt(sbi->s_mount_opt, GRPQUOTA);
break;
case Opt_noquota:
- if (sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) {
+ if (sb_any_quota_loaded(sb)) {
printk(KERN_ERR "EXT3-fs: Cannot change quota "
"options when quota turned on.\n");
return 0;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
+
+ sbi->s_blockgroup_lock =
+ kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
+ if (!sbi->s_blockgroup_lock) {
+ kfree(sbi);
+ return -ENOMEM;
+ }
sb->s_fs_info = sbi;
sbi->s_mount_opt = 0;
sbi->s_resuid = EXT3_DEF_RESUID;
for (i=0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ #ifdef __CHAR_UNSIGNED__
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
+ #else
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ #endif
+ sb->s_dirt = 1;
+ }
if (sbi->s_blocks_per_group > blocksize * 8) {
printk (KERN_ERR
goto failed_mount;
}
- bgl_lock_init(&sbi->s_blockgroup_lock);
+ bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logic_sb_block, i);
#include <linux/types.h>
#include <linux/blkdev.h>
#include <linux/magic.h>
+ #include <linux/jbd2.h>
#include "ext4_i.h"
/*
/* phys. block for ^^^ */
ext4_fsblk_t pright;
/* how many blocks we want to allocate */
- unsigned long len;
+ unsigned int len;
/* flags. see above EXT4_MB_HINT_* */
- unsigned long flags;
+ unsigned int flags;
};
/*
__le32 bg_block_bitmap_lo; /* Blocks bitmap block */
__le32 bg_inode_bitmap_lo; /* Inodes bitmap block */
__le32 bg_inode_table_lo; /* Inodes table block */
- __le16 bg_free_blocks_count; /* Free blocks count */
- __le16 bg_free_inodes_count; /* Free inodes count */
- __le16 bg_used_dirs_count; /* Directories count */
+ __le16 bg_free_blocks_count_lo;/* Free blocks count */
+ __le16 bg_free_inodes_count_lo;/* Free inodes count */
+ __le16 bg_used_dirs_count_lo; /* Directories count */
__le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
__u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */
- __le16 bg_itable_unused; /* Unused inodes count */
+ __le16 bg_itable_unused_lo; /* Unused inodes count */
__le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
__le16 bg_free_blocks_count_hi;/* Free blocks count MSB */
__le16 bg_free_inodes_count_hi;/* Free inodes count MSB */
__le16 bg_used_dirs_count_hi; /* Directories count MSB */
- __le16 bg_itable_unused_hi; /* Unused inodes count MSB */
+ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */
__u32 bg_reserved2[3];
};
uid_t s_resuid;
gid_t s_resgid;
unsigned long s_commit_interval;
+ u32 s_min_batch_time, s_max_batch_time;
#ifdef CONFIG_QUOTA
int s_jquota_fmt;
char *s_qf_names[MAXQUOTAS];
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
- #define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
*/
#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)) != 0)
#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)) != 0)
#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)) != 0)
#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) \
#define EXT4_DEFM_JMODE_ORDERED 0x0040
#define EXT4_DEFM_JMODE_WBACK 0x0060
+ /*
+ * Default journal batch times
+ */
+ #define EXT4_DEF_MIN_BATCH_TIME 0
+ #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */
+
/*
* Structure of a directory entry
*/
#define DX_HASH_LEGACY 0
#define DX_HASH_HALF_MD4 1
#define DX_HASH_TEA 2
+ #define DX_HASH_LEGACY_UNSIGNED 3
+ #define DX_HASH_HALF_MD4_UNSIGNED 4
+ #define DX_HASH_TEA_UNSIGNED 5
#ifdef __KERNEL__
#define ERR_BAD_DX_DIR -75000
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
- unsigned long *blockgrpp, ext4_grpblk_t *offsetp);
+ ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
extern struct proc_dir_entry *ext4_proc_root;
# define ATTRIB_NORET __attribute__((noreturn))
# define NORET_AND noreturn,
+ /* bitmap.c */
+ extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+
/* balloc.c */
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
ext4_group_t group);
- extern ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
- ext4_fsblk_t goal, int *errp);
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
- extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- unsigned long *count, int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, 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,
- unsigned long *pdquot_freed_blocks);
+ extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count);
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,
/* dir.c */
extern int ext4_check_dir_entry(const char *, struct inode *,
struct ext4_dir_entry_2 *,
- struct buffer_head *, unsigned long);
+ struct buffer_head *, unsigned int);
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
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;
extern void exit_ext4_mballoc(void);
extern void ext4_mb_free_blocks(handle_t *, struct inode *,
unsigned long, unsigned long, int, unsigned long *);
- extern int ext4_mb_add_more_groupinfo(struct super_block *sb,
+ extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
ext4_grpblk_t add);
-
-
+ extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
+ extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
+ ext4_group_t, int);
/* inode.c */
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr);
ext4_lblk_t, int, int *);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
- int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
- int create, int extend_disksize);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
extern int ext4_write_inode(struct inode *, int);
__attribute__ ((format (printf, 3, 4)));
extern void ext4_warning(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
+ extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
+ const char *, const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
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);
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
+ extern __u32 ext4_free_blks_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+ extern __u32 ext4_free_inodes_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+ extern __u32 ext4_used_dirs_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+ extern __u32 ext4_itable_unused_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
extern void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
+ extern void ext4_free_blks_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+ extern void ext4_free_inodes_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+ extern void ext4_used_dirs_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+ extern void ext4_itable_unused_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
} while (0)
#ifdef CONFIG_SMP
-/* Each CPU can accumulate FBC_BATCH blocks in their local
+/* Each CPU can accumulate percpu_counter_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.
+ * than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
-#define EXT4_FREEBLOCKS_WATERMARK (4 * (FBC_BATCH * nr_cpu_ids))
+#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
#define EXT4_FREEBLOCKS_WATERMARK 0
#endif
return ;
}
+ struct ext4_group_info {
+ unsigned long bb_state;
+ struct rb_root bb_free_root;
+ unsigned short bb_first_free;
+ unsigned short bb_free;
+ unsigned short bb_fragments;
+ struct list_head bb_prealloc_list;
+ #ifdef DOUBLE_CHECK
+ void *bb_bitmap;
+ #endif
+ struct rw_semaphore alloc_sem;
+ unsigned short bb_counters[];
+ };
+
+ #define EXT4_GROUP_INFO_NEED_INIT_BIT 0
+ #define EXT4_GROUP_INFO_LOCKED_BIT 1
+
+ #define EXT4_MB_GRP_NEED_INIT(grp) \
+ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+
+ static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+ {
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+ }
+
+ static inline void ext4_unlock_group(struct super_block *sb,
+ ext4_group_t group)
+ {
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+ }
+
+ static inline int ext4_is_group_locked(struct super_block *sb,
+ ext4_group_t group)
+ {
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
+ &(grinfo->bb_state));
+ }
+
/*
* Inodes and files operations
*/
extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
int chunk);
extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock,
- unsigned long max_blocks, struct buffer_head *bh_result,
- int create, int extend_disksize);
+ ext4_lblk_t iblock, unsigned int max_blocks,
+ struct buffer_head *bh_result,
+ int create, int extend_disksize);
extern void ext4_ext_truncate(struct inode *);
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
- sector_t block, unsigned long max_blocks,
+ sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int create,
int extend_disksize, int flag);
+ extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len);
+
+ /*
+ * Add new method to test wether block and inode bitmaps are properly
+ * initialized. With uninit_bg reading the block from disk is not enough
+ * to mark the bitmap uptodate. We need to also zero-out the bitmap
+ */
+ #define BH_BITMAP_UPTODATE BH_JBDPrivateStart
+
+ static inline int bitmap_uptodate(struct buffer_head *bh)
+ {
+ return (buffer_uptodate(bh) &&
+ test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
+ }
+ static inline void set_bitmap_uptodate(struct buffer_head *bh)
+ {
+ set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+ }
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
if (handle->h_buffer_credits > needed)
return 0;
err = ext4_journal_extend(handle, needed);
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_journal_dirty_metadata(handle, path->p_bh);
+ err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
ext4_fsblk_t goal, newblock;
goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
- newblock = ext4_new_meta_block(handle, inode, goal, err);
+ newblock = ext4_new_meta_blocks(handle, inode, goal, NULL, err);
return newblock;
}
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto out;
while (--depth >= 0) {
ix = path[depth].p_idx;
if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
- break;
+ goto got_index;
}
- if (depth < 0) {
- /* we've gone up to the root and
- * found no index to the right */
- return 0;
- }
+ /* we've gone up to the root and found no index to the right */
+ return 0;
+ got_index:
/* we've found index to the right, let's
* follow it and find the closest allocated
* block to the right */
*phys = ext_pblock(ex);
put_bh(bh);
return 0;
-
}
/*
ext4_ext_drop_refs(npath);
kfree(npath);
}
- ext4_ext_tree_changed(inode);
ext4_ext_invalidate_cache(inode);
return err;
}
}
}
out:
- ext4_ext_tree_changed(inode);
ext4_ext_drop_refs(path);
kfree(path);
ext4_journal_stop(handle);
* possible initialization would be here
*/
- if (test_opt(sb, EXTENTS)) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
printk(KERN_INFO "EXT4-fs: file extents enabled");
#ifdef AGGRESSIVE_TEST
printk(", aggressive tests");
*/
void ext4_ext_release(struct super_block *sb)
{
- if (!test_opt(sb, EXTENTS))
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
return;
#ifdef EXTENTS_STATS
struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t iblock,
- unsigned long max_blocks)
+ unsigned int max_blocks)
{
struct ext4_extent *ex, newex, orig_ex;
struct ext4_extent *ex1 = NULL;
*/
newdepth = ext_depth(inode);
/*
- * update the extent length after successfull insert of the
+ * update the extent length after successful insert of the
* split extent
*/
orig_ex.ee_len = cpu_to_le16(ee_len -
*/
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock,
- unsigned long max_blocks, struct buffer_head *bh_result,
+ unsigned int max_blocks, struct buffer_head *bh_result,
int create, int extend_disksize)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
struct ext4_extent newex, *ex;
- ext4_fsblk_t goal, newblock;
- int err = 0, depth, ret;
- unsigned long allocated = 0;
+ ext4_fsblk_t newblock;
+ int err = 0, depth, ret, cache_type;
+ unsigned int allocated = 0;
struct ext4_allocation_request ar;
loff_t disksize;
__clear_bit(BH_New, &bh_result->b_state);
- ext_debug("blocks %u/%lu requested for inode %u\n",
+ ext_debug("blocks %u/%u requested for inode %u\n",
iblock, max_blocks, inode->i_ino);
/* check in cache */
- goal = ext4_ext_in_cache(inode, iblock, &newex);
- if (goal) {
- if (goal == EXT4_EXT_CACHE_GAP) {
+ cache_type = ext4_ext_in_cache(inode, iblock, &newex);
+ if (cache_type) {
+ if (cache_type == EXT4_EXT_CACHE_GAP) {
if (!create) {
/*
* block isn't allocated yet and
goto out2;
}
/* we should allocate requested block */
- } else if (goal == EXT4_EXT_CACHE_EXTENT) {
+ } else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
/* block is already allocated */
newblock = iblock
- le32_to_cpu(newex.ee_block)
if (!newblock)
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
- goal, newblock, allocated);
+ ar.goal, newblock, allocated);
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
* transaction synchronous.
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
up_write(&EXT4_I(inode)->i_data_sem);
handle_t *handle;
ext4_lblk_t block;
loff_t new_size;
- unsigned long max_blocks;
+ unsigned int max_blocks;
int ret = 0;
int ret2 = 0;
int retries = 0;
/*
* Callback function called for each extent to gather FIEMAP information.
*/
- int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
struct ext4_ext_cache *newex, struct ext4_extent *ex,
void *data)
{
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
- int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+ static int ext4_xattr_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo)
{
__u64 physical = 0;
__u64 length;
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling so there's nothing to do.
*/
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
might_sleep();
BUFFER_TRACE(bh, "enter");
*/
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
- if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ if (!ext4_handle_valid(handle))
+ return 0;
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
return 0;
*/
static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
{
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
return ext4_journal_restart(handle, blocks_for_truncate(inode));
}
}
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
* enough credits left in the handle to remove the inode from
* the orphan list and set the dtime field.
*/
- if (handle->h_buffer_credits < 3) {
+ if (!ext4_handle_has_enough_credits(handle, 3)) {
err = ext4_journal_extend(handle, 3);
if (err > 0)
err = ext4_journal_restart(handle, 3);
* return the total number of blocks to be allocate, including the
* direct and indirect blocks.
*/
- static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
+ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
int blocks_to_boundary)
{
- unsigned long count = 0;
+ unsigned int count = 0;
/*
* Simple case, [t,d]Indirect block(s) has not allocated yet
int indirect_blks, int blks,
ext4_fsblk_t new_blocks[4], int *err)
{
+ struct ext4_allocation_request ar;
int target, i;
unsigned long count = 0, blk_allocated = 0;
int index = 0;
if (!target)
goto allocated;
/* Now allocate data blocks */
- count = target;
- /* allocating blocks for data blocks */
- current_block = ext4_new_blocks(handle, inode, iblock,
- goal, &count, err);
+ memset(&ar, 0, sizeof(ar));
+ ar.inode = inode;
+ ar.goal = goal;
+ ar.len = target;
+ ar.logical = iblock;
+ if (S_ISREG(inode->i_mode))
+ /* enable in-core preallocation only for regular files */
+ ar.flags = EXT4_MB_HINT_DATA;
+
+ current_block = ext4_mb_new_blocks(handle, &ar, err);
+
if (*err && (target == blks)) {
/*
* if the allocation failed and we didn't allocate
*/
new_blocks[index] = current_block;
}
- blk_allocated += count;
+ blk_allocated += ar.len;
}
allocated:
/* total number of blocks allocated for direct blocks */
set_buffer_uptodate(bh);
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto failed;
}
* generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
*/
jbd_debug(5, "splicing indirect only\n");
- BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, where->bh);
+ BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, where->bh);
if (err)
goto err_out;
} else {
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
* (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
*/
- int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
- int create, int extend_disksize)
+ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+ ext4_lblk_t iblock, unsigned int maxblocks,
+ struct buffer_head *bh_result,
+ int create, int extend_disksize)
{
int err = -EIO;
ext4_lblk_t offsets[4];
* It returns the error in case of allocation failure.
*/
int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
- unsigned long max_blocks, struct buffer_head *bh,
+ unsigned int max_blocks, struct buffer_head *bh,
int create, int extend_disksize, int flag)
{
int retval;
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (!fatal)
fatal = err;
} else {
pgoff_t index;
unsigned from, to;
+ trace_mark(ext4_write_begin,
+ "dev %s ino %lu pos %llu len %u flags %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, flags);
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
- return ext4_journal_dirty_metadata(handle, bh);
+ return ext4_handle_dirty_metadata(handle, NULL, bh);
}
/*
struct inode *inode = mapping->host;
int ret = 0, ret2;
+ trace_mark(ext4_ordered_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
int ret = 0, ret2;
loff_t new_i_size;
+ trace_mark(ext4_writeback_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
new_i_size = pos + copied;
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
unsigned from, to;
loff_t new_i_size;
+ trace_mark(ext4_journalled_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
get_block_t *get_block;
struct writeback_control *wbc;
int io_done;
- long pages_written;
+ int pages_written;
int retval;
};
*/
static int mpage_da_submit_io(struct mpage_da_data *mpd)
{
- struct address_space *mapping = mpd->inode->i_mapping;
- int ret = 0, err, nr_pages, i;
- unsigned long index, end;
- struct pagevec pvec;
long pages_skipped;
+ struct pagevec pvec;
+ unsigned long index, end;
+ int ret = 0, err, nr_pages, i;
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
BUG_ON(mpd->next_page <= mpd->first_page);
- pagevec_init(&pvec, 0);
+ /*
+ * We need to start from the first_page to the next_page - 1
+ * to make sure we also write the mapped dirty buffer_heads.
+ * If we look at mpd->lbh.b_blocknr we would only be looking
+ * at the currently mapped buffer_heads.
+ */
index = mpd->first_page;
end = mpd->next_page - 1;
+ pagevec_init(&pvec, 0);
while (index <= end) {
- /*
- * We can use PAGECACHE_TAG_DIRTY lookup here because
- * even though we have cleared the dirty flag on the page
- * We still keep the page in the radix tree with tag
- * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
- * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
- * which is called via the below writepage callback.
- */
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index,
- (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ 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));
+
pages_skipped = mpd->wbc->pages_skipped;
err = mapping->a_ops->writepage(page, mpd->wbc);
if (!err && (pages_skipped == mpd->wbc->pages_skipped))
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));
+ (long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
printk(KERN_EMERG "dirty_blocks=%lld\n",
- percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
printk(KERN_EMERG "Block reservation details\n");
- printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+ printk(KERN_EMERG "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
- printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+ printk(KERN_EMERG "i_reserved_meta_blocks=%u\n",
EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
bh = head;
do {
BUG_ON(buffer_locked(bh));
+ /*
+ * We need to try to allocate
+ * unmapped blocks in the same page.
+ * Otherwise we won't make progress
+ * with the page in ext4_da_writepage
+ */
if (buffer_dirty(bh) &&
(!buffer_mapped(bh) || buffer_delay(bh))) {
mpage_add_bh_to_extent(mpd, logical, bh);
if (mpd->io_done)
return MPAGE_DA_EXTENT_TAIL;
+ } else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+ /*
+ * mapped dirty buffer. We need to update
+ * the b_state because we look at
+ * b_state in mpage_da_map_blocks. We don't
+ * update b_size because if we find an
+ * unmapped buffer_head later we need to
+ * use the b_state flag of that buffer_head.
+ */
+ if (mpd->lbh.b_size == 0)
+ mpd->lbh.b_state =
+ bh->b_state & BH_FLAGS;
}
logical++;
} while ((bh = bh->b_this_page) != head);
{
int ret = 0;
loff_t size;
- unsigned long len;
+ unsigned int len;
struct buffer_head *page_bufs;
struct inode *inode = page->mapping->host;
+ trace_mark(ext4_da_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
size = i_size_read(inode);
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int no_nrwrite_index_update;
- long pages_written = 0, pages_skipped;
+ int pages_written = 0;
+ long pages_skipped;
int needed_blocks, ret = 0, nr_to_writebump = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+ trace_mark(ext4_da_writepages,
+ "dev %s ino %lu nr_t_write %ld "
+ "pages_skipped %ld range_start %llu "
+ "range_end %llu nonblocking %d "
+ "for_kupdate %d for_reclaim %d "
+ "for_writepages %d range_cyclic %d",
+ inode->i_sb->s_id, inode->i_ino,
+ wbc->nr_to_write, wbc->pages_skipped,
+ (unsigned long long) wbc->range_start,
+ (unsigned long long) wbc->range_end,
+ wbc->nonblocking, wbc->for_kupdate,
+ wbc->for_reclaim, wbc->for_writepages,
+ wbc->range_cyclic);
+
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
+
+ /*
+ * If the filesystem has aborted, it is read-only, so return
+ * right away instead of dumping stack traces later on that
+ * will obscure the real source of the problem. We test
+ * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+ * the latter could be true if the filesystem is mounted
+ * read-only, and in that case, ext4_da_writepages should
+ * *never* be called, so if that ever happens, we would want
+ * the stack trace.
+ */
+ if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+ return -EROFS;
+
/*
* Make sure nr_to_write is >= sbi->s_mb_stream_request
* This make sure small files blocks are allocated in
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- printk(KERN_EMERG "%s: jbd2_start: "
+ printk(KERN_CRIT "%s: jbd2_start: "
"%ld pages, ino %lu; err %d\n", __func__,
wbc->nr_to_write, inode->i_ino, ret);
dump_stack();
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
wbc->nr_to_write -= nr_to_writebump;
+ trace_mark(ext4_da_writepage_result,
+ "dev %s ino %lu ret %d pages_written %d "
+ "pages_skipped %ld congestion %d "
+ "more_io %d no_nrwrite_index_update %d",
+ inode->i_sb->s_id, inode->i_ino, ret,
+ pages_written, wbc->pages_skipped,
+ wbc->encountered_congestion, wbc->more_io,
+ wbc->no_nrwrite_index_update);
return ret;
}
/*
* 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
+ * counters can get slightly wrong with percpu_counter_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.
len, flags, pagep, fsdata);
}
*fsdata = (void *)0;
+
+ trace_mark(ext4_da_write_begin,
+ "dev %s ino %lu pos %llu len %u flags %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, flags);
retry:
/*
* With delayed allocation, we don't log the i_disksize update
}
}
+ trace_mark(ext4_da_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
start = pos & (PAGE_CACHE_SIZE - 1);
end = start + copied - 1;
filemap_write_and_wait(mapping);
}
- if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ BUG_ON(!EXT4_JOURNAL(inode) &&
+ EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
+
+ if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
loff_t size = i_size_read(inode);
loff_t len;
+ trace_mark(ext4_normal_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
J_ASSERT(PageLocked(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
loff_t size = i_size_read(inode);
loff_t len;
+ trace_mark(ext4_journalled_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
J_ASSERT(PageLocked(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
if (offset == 0)
ClearPageChecked(page);
- jbd2_journal_invalidatepage(journal, page, offset);
+ if (journal)
+ jbd2_journal_invalidatepage(journal, page, offset);
+ else
+ block_invalidatepage(page, offset);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
- return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ if (journal)
+ return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ else
+ return try_to_free_buffers(page);
}
/*
err = 0;
if (ext4_should_journal_data(inode)) {
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
if (ext4_should_order_data(inode))
err = ext4_jbd2_file_inode(handle, inode);
__le32 *p;
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, inode, bh);
}
ext4_mark_inode_dirty(handle, inode);
ext4_journal_test_restart(handle, inode);
count, block_to_free_p, p);
if (this_bh) {
- BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata");
+ BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
/*
* The buffer head should have an attached journal head at this
* the block was cleared. Check for this instead of OOPSing.
*/
if (bh2jh(this_bh))
- ext4_journal_dirty_metadata(handle, this_bh);
+ ext4_handle_dirty_metadata(handle, inode, this_bh);
else
ext4_error(inode->i_sb, __func__,
"circular indirect block detected, "
ext4_fsblk_t nr;
__le32 *p;
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (depth--) {
* will merely complain about releasing a free block,
* rather than leaking blocks.
*/
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (try_to_extend_transaction(handle, inode)) {
ext4_mark_inode_dirty(handle, inode);
parent_bh)){
*p = 0;
BUFFER_TRACE(parent_bh,
- "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle,
- parent_bh);
+ "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle,
+ inode,
+ parent_bh);
}
}
}
* synchronous
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
/*
* If this was a simple ftruncate(), and the file will remain alive
ext4_fsblk_t block;
int inodes_per_block, inode_offset;
- iloc->bh = 0;
+ iloc->bh = NULL;
if (!ext4_valid_inum(sb, inode->i_ino))
return -EIO;
num = EXT4_INODES_PER_GROUP(sb);
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
- num -= le16_to_cpu(gdp->bg_itable_unused);
+ num -= ext4_itable_unused_count(sb, gdp);
table += num / inodes_per_block;
if (end > table)
end = table;
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
- handle->h_sync = 1;
- err = ext4_journal_dirty_metadata(handle,
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_metadata(handle, inode,
EXT4_SB(sb)->s_sbh);
}
}
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
-
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- rc = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ rc = ext4_handle_dirty_metadata(handle, inode, bh);
if (!err)
err = rc;
ei->i_state &= ~EXT4_STATE_NEW;
return ext4_force_commit(inode->i_sb);
}
+ int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
+ {
+ int err = 0;
+
+ mark_buffer_dirty(bh);
+ if (inode && inode_needs_sync(inode)) {
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)bh->b_blocknr);
+ err = -EIO;
+ }
+ }
+ return err;
+ }
+
/*
* ext4_setattr()
*
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
- int err = 0;
- if (handle) {
- err = ext4_get_inode_loc(inode, iloc);
- if (!err) {
- BUFFER_TRACE(iloc->bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, iloc->bh);
- if (err) {
- brelse(iloc->bh);
- iloc->bh = NULL;
- }
+ int err;
+
+ err = ext4_get_inode_loc(inode, iloc);
+ if (!err) {
+ BUFFER_TRACE(iloc->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, iloc->bh);
+ if (err) {
+ brelse(iloc->bh);
+ iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
might_sleep();
err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+ if (ext4_handle_valid(handle) &&
+ EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
handle_t *current_handle = ext4_journal_current_handle();
handle_t *handle;
+ if (!ext4_handle_valid(current_handle)) {
+ ext4_mark_inode_dirty(current_handle, inode);
+ return;
+ }
+
handle = ext4_journal_start(inode, 2);
if (IS_ERR(handle))
goto out;
BUFFER_TRACE(iloc.bh, "get_write_access");
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
- err = ext4_journal_dirty_metadata(handle,
- iloc.bh);
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
+ iloc.bh);
brelse(iloc.bh);
}
}
*/
journal = EXT4_JOURNAL(inode);
+ if (!journal)
+ return 0;
if (is_journal_aborted(journal))
return -EROFS;
return PTR_ERR(handle);
err = ext4_mark_inode_dirty(handle, inode);
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
#define assert(test) J_ASSERT(test)
#endif
-#ifndef swap
-#define swap(x, y) do { typeof(x) z = x; x = y; y = z; } while (0)
-#endif
-
#ifdef DX_DEBUG
#define dxtrace(command) command
#else
goto fail;
}
hinfo->hash_version = root->info.hash_version;
+ if (hinfo->hash_version <= DX_HASH_TEA)
+ hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
if (d_name)
ext4fs_dirhash(d_name->name, d_name->len, hinfo);
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;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version +=
+ EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
start_hash, start_minor_hash);
static inline int search_dirblock(struct buffer_head *bh,
struct inode *dir,
const struct qstr *d_name,
- unsigned long offset,
+ unsigned int offset,
struct ext4_dir_entry_2 ** res_dir)
{
struct ext4_dir_entry_2 * de;
bh = ext4_find_entry(dir, &dentry->d_name, &de);
inode = NULL;
if (bh) {
- unsigned long ino = le32_to_cpu(de->inode);
+ __u32 ino = le32_to_cpu(de->inode);
brelse(bh);
if (!ext4_valid_inum(dir->i_sb, ino)) {
ext4_error(dir->i_sb, "ext4_lookup",
- "bad inode number: %lu", ino);
+ "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
inode = ext4_iget(dir->i_sb, ino);
struct dentry *ext4_get_parent(struct dentry *child)
{
- unsigned long ino;
+ __u32 ino;
struct inode *inode;
static const struct qstr dotdot = {
.name = "..",
if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
ext4_error(child->d_inode->i_sb, "ext4_get_parent",
- "bad inode number: %lu", ino);
+ "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split, move, size, i;
+ unsigned split, move, size;
struct ext4_dir_entry_2 *de = NULL, *de2;
- int err = 0;
+ int err = 0, i;
bh2 = ext4_append (handle, dir, &newblock, &err);
if (!(bh2)) {
de = de2;
}
dx_insert_block(frame, hash2 + continued, newblock);
- err = ext4_journal_dirty_metadata(handle, bh2);
+ err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
- err = ext4_journal_dirty_metadata(handle, frame->bh);
+ err = ext4_handle_dirty_metadata(handle, dir, frame->bh);
if (err)
goto journal_error;
brelse(bh2);
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
- unsigned long offset = 0;
+ unsigned int offset = 0;
unsigned short reclen;
int nlen, rlen, err;
char *top;
ext4_update_dx_flag(dir);
dir->i_version++;
ext4_mark_inode_dirty(handle, dir);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, dir, bh);
if (err)
ext4_std_error(dir->i_sb, err);
brelse(bh);
/* Initialize as for dx_probe */
hinfo.hash_version = root->info.hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
ext4fs_dirhash(name, namelen, &hinfo);
frame = frames;
struct inode *inode)
{
struct inode *dir = dentry->d_parent->d_inode;
- unsigned long offset;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
ext4_mark_inode_dirty(handle, dir);
}
blocks = dir->i_size >> sb->s_blocksize_bits;
- for (block = 0, offset = 0; block < blocks; block++) {
+ for (block = 0; block < blocks; block++) {
bh = ext4_bread(handle, dir, block, 0, &retval);
if(!bh)
return retval;
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);
+ err = ext4_handle_dirty_metadata(handle, inode, bh2);
if (err)
goto journal_error;
brelse (bh2);
if (err)
goto journal_error;
}
- ext4_journal_dirty_metadata(handle, frames[0].bh);
+ ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
}
de = do_split(handle, dir, &bh, frame, &hinfo, &err);
if (!de)
else
de->inode = 0;
dir->i_version++;
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, bh);
return 0;
}
i += ext4_rec_len_from_disk(de->rec_len);
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode (handle, dir, mode);
err = PTR_ERR(inode);
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, mode);
err = PTR_ERR(inode);
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
err = PTR_ERR(inode);
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);
+ BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, dir_block);
brelse(dir_block);
ext4_mark_inode_dirty(handle, inode);
err = ext4_add_entry(handle, dentry, inode);
*/
static int empty_dir(struct inode *inode)
{
- unsigned long offset;
+ unsigned int offset;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de, *de1;
struct super_block *sb;
if (err)
ext4_error(sb, __func__,
"error %d reading directory"
- " #%lu offset %lu",
+ " #%lu offset %u",
err, inode->i_ino, offset);
offset += sb->s_blocksize;
continue;
struct ext4_iloc iloc;
int err = 0, rc;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(sb);
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
struct list_head *prev;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi;
- unsigned long ino_next;
+ __u32 ino_next;
struct ext4_iloc iloc;
int err = 0;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(inode->i_sb);
if (list_empty(&ei->i_orphan)) {
unlock_super(inode->i_sb);
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
+ if (sbi->s_journal && !handle)
goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
goto out_err;
if (prev == &sbi->s_orphan) {
- jbd_debug(4, "superblock will point to %lu\n", ino_next);
+ jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
- err = ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
- jbd_debug(4, "orphan inode %lu will point to %lu\n",
+ jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
if (err)
goto end_rmdir;
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = dentry->d_inode;
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de);
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
err = PTR_ERR(inode);
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_ctime = ext4_current_time(inode);
ext4_inc_count(handle, inode);
return PTR_ERR(handle);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
/*
new_dir->i_ctime = new_dir->i_mtime =
ext4_current_time(new_dir);
ext4_mark_inode_dirty(handle, new_dir);
- BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, new_bh);
+ BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, new_dir, new_bh);
brelse(new_bh);
new_bh = NULL;
}
BUFFER_TRACE(dir_bh, "get_write_access");
ext4_journal_get_write_access(handle, dir_bh);
PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
- BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, dir_bh);
+ BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
ext4_dec_count(handle, old_dir);
if (new_inode) {
/* checked empty_dir above, can't have another parent,
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
- static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
- unsigned int);
static void ext4_commit_super(struct super_block *sb,
struct ext4_super_block *es, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
+ __u32 ext4_free_blks_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+ {
+ return le16_to_cpu(bg->bg_free_blocks_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+ }
+
+ __u32 ext4_free_inodes_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+ {
+ return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+ }
+
+ __u32 ext4_used_dirs_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+ {
+ return le16_to_cpu(bg->bg_used_dirs_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+ }
+
+ __u32 ext4_itable_unused_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+ {
+ return le16_to_cpu(bg->bg_itable_unused_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+ }
+
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
+ void ext4_free_blks_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+ {
+ bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
+ }
+
+ void ext4_free_inodes_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+ {
+ bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+ }
+
+ void ext4_used_dirs_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+ {
+ bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
+ }
+
+ void ext4_itable_unused_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+ {
+ bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
+ }
+
/*
* Wrappers for jbd2_journal_start/end.
*
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, __func__,
- "Detected aborted journal");
- return ERR_PTR(-EROFS);
+ if (journal) {
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, __func__,
+ "Detected aborted journal");
+ return ERR_PTR(-EROFS);
+ }
+ return jbd2_journal_start(journal, nblocks);
}
-
- return jbd2_journal_start(journal, nblocks);
+ /*
+ * We're not journaling, return the appropriate indication.
+ */
+ current->journal_info = EXT4_NOJOURNAL_HANDLE;
+ return current->journal_info;
}
/*
int err;
int rc;
+ if (!ext4_handle_valid(handle)) {
+ /*
+ * Do this here since we don't call jbd2_journal_stop() in
+ * no-journal mode.
+ */
+ current->journal_info = NULL;
+ return 0;
+ }
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
+ BUG_ON(!ext4_handle_valid(handle));
+
if (bh)
BUFFER_TRACE(bh, "abort");
va_end(args);
}
+ void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp,
+ const char *function, const char *fmt, ...)
+ __releases(bitlock)
+ __acquires(bitlock)
+ {
+ va_list args;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ if (test_opt(sb, ERRORS_CONT)) {
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ ext4_commit_super(sb, es, 0);
+ return;
+ }
+ ext4_unlock_group(sb, grp);
+ ext4_handle_error(sb);
+ /*
+ * We only get here in the ERRORS_RO case; relocking the group
+ * may be dangerous, but nothing bad will happen since the
+ * filesystem will have already been marked read/only and the
+ * journal has been aborted. We return 1 as a hint to callers
+ * who might what to use the return value from
+ * ext4_grp_locked_error() to distinguish beween the
+ * ERRORS_CONT and ERRORS_RO case, and perhaps return more
+ * aggressively from the ext4 function in question, with a
+ * more appropriate error code.
+ */
+ ext4_lock_group(sb, grp);
+ return;
+ }
+
+
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
return bdev;
fail:
- printk(KERN_ERR "EXT4: failed to open journal device %s: %ld\n",
+ printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
- err = jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
- if (err < 0)
- ext4_abort(sb, __func__, "Couldn't clean up the journal");
-
+ if (sbi->s_journal) {
+ err = jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ if (err < 0)
+ ext4_abort(sb, __func__,
+ "Couldn't clean up the journal");
+ }
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
+ /*
+ * Note: We can be called before EXT4_SB(sb)->s_journal is set,
+ * therefore it can be null here. Don't check it, just initialize
+ * jinode.
+ */
jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
}
#endif
ext4_discard_preallocations(inode);
- jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+ if (EXT4_JOURNAL(inode))
+ jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
&EXT4_I(inode)->jinode);
}
#endif
if (!test_opt(sb, RESERVATION))
seq_puts(seq, ",noreservation");
- if (sbi->s_commit_interval) {
+ if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
seq_printf(seq, ",commit=%u",
(unsigned) (sbi->s_commit_interval / HZ));
}
+ if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
+ seq_printf(seq, ",min_batch_time=%u",
+ (unsigned) sbi->s_min_batch_time);
+ }
+ if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
+ seq_printf(seq, ",max_batch_time=%u",
+ (unsigned) sbi->s_min_batch_time);
+ }
+
/*
* We're changing the default of barrier mount option, so
* let's always display its mount state so it's clear what its
seq_puts(seq, ",journal_async_commit");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
- if (!test_opt(sb, EXTENTS))
- seq_puts(seq, ",noextents");
if (test_opt(sb, I_VERSION))
seq_puts(seq, ",i_version");
if (!test_opt(sb, DELALLOC))
ext4_nfs_get_inode);
}
+ /*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device. Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd2 layer's try_to_free_buffers() function to release them.
+ */
+ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait)
+ {
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ if (journal)
+ return jbd2_journal_try_to_free_buffers(journal, page,
+ wait & ~__GFP_WAIT);
+ return try_to_free_buffers(page);
+ }
+
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
.mark_dirty = ext4_mark_dquot_dirty,
- .write_info = ext4_write_info
+ .write_info = ext4_write_info,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
};
static struct quotactl_ops ext4_qctl_operations = {
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext4_export_ops = {
Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
- Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
+ Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
+ Opt_journal_update, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
- Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
+ Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
- Opt_inode_readahead_blks
+ Opt_inode_readahead_blks, Opt_journal_ioprio
};
static const match_table_t tokens = {
{Opt_nobh, "nobh"},
{Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
+ {Opt_min_batch_time, "min_batch_time=%u"},
+ {Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_update, "journal=update"},
- {Opt_journal_inum, "journal=%u"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
- {Opt_extents, "extents"},
- {Opt_noextents, "noextents"},
{Opt_i_version, "i_version"},
{Opt_stripe, "stripe=%u"},
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
+ {Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_err, NULL},
};
return sb_block;
}
+ #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+
static int parse_options(char *options, struct super_block *sb,
- unsigned int *inum, unsigned long *journal_devnum,
+ unsigned long *journal_devnum,
+ unsigned int *journal_ioprio,
ext4_fsblk_t *n_blocks_count, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int qtype, qfmt;
char *qname;
#endif
- ext4_fsblk_t last_block;
if (!options)
return 1;
}
set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
break;
- case Opt_journal_inum:
- if (is_remount) {
- printk(KERN_ERR "EXT4-fs: cannot specify "
- "journal on remount\n");
- return 0;
- }
- if (match_int(&args[0], &option))
- return 0;
- *inum = option;
- break;
case Opt_journal_dev:
if (is_remount) {
printk(KERN_ERR "EXT4-fs: cannot specify "
option = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * option;
break;
+ case Opt_max_batch_time:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ if (option == 0)
+ option = EXT4_DEF_MAX_BATCH_TIME;
+ sbi->s_max_batch_time = option;
+ break;
+ case Opt_min_batch_time:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ sbi->s_min_batch_time = option;
+ break;
case Opt_data_journal:
data_opt = EXT4_MOUNT_JOURNAL_DATA;
goto datacheck;
case Opt_grpjquota:
qtype = GRPQUOTA;
set_qf_name:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
printk(KERN_ERR
"EXT4-fs: Cannot change journaled "
case Opt_offgrpjquota:
qtype = GRPQUOTA;
clear_qf_name:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
sbi->s_qf_names[qtype]) {
printk(KERN_ERR "EXT4-fs: Cannot change "
"journaled quota options when "
case Opt_jqfmt_vfsv0:
qfmt = QFMT_VFS_V0;
set_qf_format:
- if ((sb_any_quota_enabled(sb) ||
- sb_any_quota_suspended(sb)) &&
+ if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
printk(KERN_ERR "EXT4-fs: Cannot change "
"journaled quota options when "
set_opt(sbi->s_mount_opt, GRPQUOTA);
break;
case Opt_noquota:
- if (sb_any_quota_enabled(sb)) {
+ if (sb_any_quota_loaded(sb)) {
printk(KERN_ERR "EXT4-fs: Cannot change quota "
"options when quota turned on.\n");
return 0;
case Opt_bh:
clear_opt(sbi->s_mount_opt, NOBH);
break;
- case Opt_extents:
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_EXTENTS)) {
- ext4_warning(sb, __func__,
- "extents feature not enabled "
- "on this filesystem, use tune2fs\n");
- return 0;
- }
- set_opt(sbi->s_mount_opt, EXTENTS);
- break;
- case Opt_noextents:
- /*
- * When e2fsprogs support resizing an already existing
- * ext3 file system to greater than 2**32 we need to
- * add support to block allocator to handle growing
- * already existing block mapped inode so that blocks
- * allocated for them fall within 2**32
- */
- last_block = ext4_blocks_count(sbi->s_es) - 1;
- if (last_block > 0xffffffffULL) {
- printk(KERN_ERR "EXT4-fs: Filesystem too "
- "large to mount with "
- "-o noextents options\n");
- return 0;
- }
- clear_opt(sbi->s_mount_opt, EXTENTS);
- break;
case Opt_i_version:
set_opt(sbi->s_mount_opt, I_VERSION);
sb->s_flags |= MS_I_VERSION;
return 0;
sbi->s_inode_readahead_blks = option;
break;
+ case Opt_journal_ioprio:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0 || option > 7)
+ break;
+ *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
+ option);
+ break;
default:
printk(KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
printk(KERN_WARNING
"EXT4-fs warning: checktime reached, "
"running e2fsck is recommended\n");
- #if 0
- /* @@@ We _will_ want to clear the valid bit if we find
- * inconsistencies, to force a fsck at reboot. But for
- * a plain journaled filesystem we can keep it set as
- * valid forever! :)
- */
- es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
- #endif
+ if (!sbi->s_journal)
+ es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ if (sbi->s_journal)
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, es, 1);
if (test_opt(sb, DEBUG))
- printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%lu, "
+ printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04lx]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
- printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
- sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
- "external", EXT4_SB(sb)->s_journal->j_devname);
+ if (EXT4_SB(sb)->s_journal) {
+ printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
+ sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+ "external", EXT4_SB(sb)->s_journal->j_devname);
+ } else {
+ printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id);
+ }
return res;
}
ext4_group_t flex_group_count;
ext4_group_t flex_group;
int groups_per_flex = 0;
- __u64 block_bitmap = 0;
int i;
if (!sbi->s_es->s_log_groups_per_flex) {
sizeof(struct flex_groups), GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
printk(KERN_ERR "EXT4-fs: not enough memory for "
- "%lu flex groups\n", flex_group_count);
+ "%u flex groups\n", flex_group_count);
goto failed;
}
- gdp = ext4_get_group_desc(sb, 1, &bh);
- block_bitmap = ext4_block_bitmap(sb, gdp) - 1;
-
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext4_get_group_desc(sb, i, &bh);
flex_group = ext4_flex_group(sbi, i);
sbi->s_flex_groups[flex_group].free_inodes +=
- le16_to_cpu(gdp->bg_free_inodes_count);
+ ext4_free_inodes_count(sb, gdp);
sbi->s_flex_groups[flex_group].free_blocks +=
- le16_to_cpu(gdp->bg_free_blocks_count);
+ ext4_free_blks_count(sb, gdp);
}
return 1;
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Block bitmap for group %lu not in group "
+ "Block bitmap for group %u not in group "
"(block %llu)!\n", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap < first_block || inode_bitmap > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Inode bitmap for group %lu not in group "
+ "Inode bitmap for group %u not in group "
"(block %llu)!\n", i, inode_bitmap);
return 0;
}
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Inode table for group %lu not in group "
+ "Inode table for group %u not in group "
"(block %llu)!\n", i, inode_table);
return 0;
}
spin_lock(sb_bgl_lock(sbi, i));
if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Checksum for group %lu failed (%u!=%u)\n",
+ "Checksum for group %u 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)) {
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
unsigned long offset = 0;
- unsigned int journal_inum = 0;
unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
char *cp;
+ const char *descr;
int ret = -EINVAL;
int blocksize;
- int db_count;
- int i;
+ unsigned int db_count;
+ unsigned int i;
int needs_recovery, has_huge_files;
- __le32 features;
+ int features;
__u64 blocks_count;
int err;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+ sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
+ sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
+ sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
set_opt(sbi->s_mount_opt, RESERVATION);
set_opt(sbi->s_mount_opt, BARRIER);
- /*
- * turn on extents feature by default in ext4 filesystem
- * only if feature flag already set by mkfs or tune2fs.
- * Use -o noextents to turn it off
- */
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
- set_opt(sbi->s_mount_opt, EXTENTS);
- else
- ext4_warning(sb, __func__,
- "extents feature not enabled on this filesystem, "
- "use tune2fs.\n");
-
/*
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
set_opt(sbi->s_mount_opt, DELALLOC);
- if (!parse_options((char *) data, sb, &journal_inum, &journal_devnum,
- NULL, 0))
+ if (!parse_options((char *) data, sb, &journal_devnum,
+ &journal_ioprio, NULL, 0))
goto failed_mount;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
if (features) {
printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
- "unsupported optional features (%x).\n",
- sb->s_id, le32_to_cpu(features));
+ "unsupported optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
+ ~EXT4_FEATURE_INCOMPAT_SUPP));
goto failed_mount;
}
features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
if (!(sb->s_flags & MS_RDONLY) && features) {
printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
- "unsupported optional features (%x).\n",
- sb->s_id, le32_to_cpu(features));
+ "unsupported optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
goto failed_mount;
}
has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ #ifdef __CHAR_UNSIGNED__
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
+ #else
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ #endif
+ sb->s_dirt = 1;
+ }
if (sbi->s_blocks_per_group > blocksize * 8) {
printk(KERN_ERR
if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext4;
- /* ensure blocks_count calculation below doesn't sign-extend */
- if (ext4_blocks_count(es) + EXT4_BLOCKS_PER_GROUP(sb) <
- le32_to_cpu(es->s_first_data_block) + 1) {
- printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu, "
- "first data block %u, blocks per group %lu\n",
- ext4_blocks_count(es),
- le32_to_cpu(es->s_first_data_block),
- EXT4_BLOCKS_PER_GROUP(sb));
+ /*
+ * It makes no sense for the first data block to be beyond the end
+ * of the filesystem.
+ */
+ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+ printk(KERN_WARNING "EXT4-fs: bad geometry: first data"
+ "block %u is beyond end of filesystem (%llu)\n",
+ le32_to_cpu(es->s_first_data_block),
+ ext4_blocks_count(es));
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
+ if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
+ printk(KERN_WARNING "EXT4-fs: groups count too large: %u "
+ "(block count %llu, first data block %u, "
+ "blocks per group %lu)\n", sbi->s_groups_count,
+ ext4_blocks_count(es),
+ le32_to_cpu(es->s_first_data_block),
+ EXT4_BLOCKS_PER_GROUP(sb));
+ goto failed_mount;
+ }
sbi->s_groups_count = blocks_count;
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, es, 1);
- printk(KERN_CRIT
- "EXT4-fs (device %s): mount failed\n",
- sb->s_id);
goto failed_mount4;
}
}
- } else if (journal_inum) {
- if (ext4_create_journal(sb, es, journal_inum))
- goto failed_mount3;
+ } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
+ EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ printk(KERN_ERR "EXT4-fs: required journal recovery "
+ "suppressed and not mounted read-only\n");
+ goto failed_mount4;
} else {
- if (!silent)
- printk(KERN_ERR
- "ext4: No journal on filesystem on %s\n",
- sb->s_id);
- goto failed_mount3;
+ clear_opt(sbi->s_mount_opt, DATA_FLAGS);
+ set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ sbi->s_journal = NULL;
+ needs_recovery = 0;
+ goto no_journal;
}
if (ext4_blocks_count(es) > 0xffffffffULL &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
- printk(KERN_ERR "ext4: Failed to set 64-bit journal feature\n");
+ printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n");
goto failed_mount4;
}
default:
break;
}
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+
+ no_journal:
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
- if (needs_recovery)
+ if (needs_recovery) {
printk(KERN_INFO "EXT4-fs: recovery complete.\n");
- ext4_mark_recovery_complete(sb, es);
- printk(KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
- "writeback");
+ ext4_mark_recovery_complete(sb, es);
+ }
+ if (EXT4_SB(sb)->s_journal) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ descr = " journalled data mode";
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ descr = " ordered data mode";
+ else
+ descr = " writeback data mode";
+ } else
+ descr = "out journal";
+
+ printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n",
+ sb->s_id, descr);
lock_kernel();
return 0;
goto failed_mount;
failed_mount4:
- jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
+ printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id);
+ if (sbi->s_journal) {
+ jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ }
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (sbi->s_commit_interval)
- journal->j_commit_interval = sbi->s_commit_interval;
- /* We could also set up an ext4-specific default for the commit
- * interval here, but for now we'll just fall back to the jbd
- * default. */
+ journal->j_commit_interval = sbi->s_commit_interval;
+ journal->j_min_batch_time = sbi->s_min_batch_time;
+ journal->j_max_batch_time = sbi->s_max_batch_time;
spin_lock(&journal->j_state_lock);
if (test_opt(sb, BARRIER))
struct inode *journal_inode;
journal_t *journal;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
/* First, test for the existence of a valid inode on disk. Bad
* things happen if we iget() an unused inode, as the subsequent
* iput() will try to delete it. */
struct ext4_super_block *es;
struct block_device *bdev;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
bdev = ext4_blkdev_get(j_dev);
if (bdev == NULL)
return NULL;
if (bd_claim(bdev, sb)) {
printk(KERN_ERR
- "EXT4: failed to claim external journal device.\n");
+ "EXT4-fs: failed to claim external journal device.\n");
blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
return NULL;
}
int err = 0;
int really_read_only;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
printk(KERN_INFO "EXT4-fs: external journal device major/minor "
return 0;
}
- static int ext4_create_journal(struct super_block *sb,
- struct ext4_super_block *es,
- unsigned int journal_inum)
- {
- journal_t *journal;
- int err;
-
- if (sb->s_flags & MS_RDONLY) {
- printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to "
- "create journal.\n");
- return -EROFS;
- }
-
- journal = ext4_get_journal(sb, journal_inum);
- if (!journal)
- return -EINVAL;
-
- printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n",
- journal_inum);
-
- err = jbd2_journal_create(journal);
- if (err) {
- printk(KERN_ERR "EXT4-fs: error creating journal.\n");
- jbd2_journal_destroy(journal);
- return -EIO;
- }
-
- EXT4_SB(sb)->s_journal = journal;
-
- ext4_update_dynamic_rev(sb);
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL);
-
- es->s_journal_inum = cpu_to_le32(journal_inum);
- sb->s_dirt = 1;
-
- /* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, es, 1);
-
- return 0;
- }
-
static void ext4_commit_super(struct super_block *sb,
struct ext4_super_block *es, int sync)
{
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
- printk(KERN_ERR "ext4: previous I/O error to "
+ printk(KERN_ERR "EXT4-fs: previous I/O error to "
"superblock detected for %s.\n", sb->s_id);
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
es->s_wtime = cpu_to_le32(get_seconds());
- ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb));
- es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
+ ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeblocks_counter));
+ es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeinodes_counter));
+
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
if (sync) {
sync_dirty_buffer(sbh);
if (buffer_write_io_error(sbh)) {
- printk(KERN_ERR "ext4: I/O error while writing "
+ printk(KERN_ERR "EXT4-fs: I/O error while writing "
"superblock for %s.\n", sb->s_id);
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ BUG_ON(journal != NULL);
+ return;
+ }
jbd2_journal_lock_updates(journal);
if (jbd2_journal_flush(journal) < 0)
goto out;
int j_errno;
const char *errstr;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
journal = EXT4_SB(sb)->s_journal;
/*
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
- int ret;
+ int ret = 0;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
- sb->s_dirt = 0;
- ret = ext4_journal_force_commit(journal);
+ if (journal) {
+ sb->s_dirt = 0;
+ ret = ext4_journal_force_commit(journal);
+ }
+
return ret;
}
*/
static void ext4_write_super(struct super_block *sb)
{
- if (mutex_trylock(&sb->s_lock) != 0)
- BUG();
- sb->s_dirt = 0;
+ if (EXT4_SB(sb)->s_journal) {
+ if (mutex_trylock(&sb->s_lock) != 0)
+ BUG();
+ sb->s_dirt = 0;
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
+ }
}
static int ext4_sync_fs(struct super_block *sb, int wait)
trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
sb->s_dirt = 0;
- if (wait)
- ret = ext4_force_commit(sb);
- else
- jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ if (EXT4_SB(sb)->s_journal) {
+ if (wait)
+ ret = ext4_force_commit(sb);
+ else
+ jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
+ }
return ret;
}
if (!(sb->s_flags & MS_RDONLY)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- /* Now we set up the journal barrier. */
- jbd2_journal_lock_updates(journal);
+ if (journal) {
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
- /*
- * We don't want to clear needs_recovery flag when we failed
- * to flush the journal.
- */
- if (jbd2_journal_flush(journal) < 0)
- return;
+ /*
+ * We don't want to clear needs_recovery flag when we
+ * failed to flush the journal.
+ */
+ if (jbd2_journal_flush(journal) < 0)
+ return;
+ }
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
*/
static void ext4_unlockfs(struct super_block *sb)
{
- if (!(sb->s_flags & MS_RDONLY)) {
+ if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {
lock_super(sb);
/* Reser the needs_recovery flag before the fs is unlocked. */
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
ext4_group_t g;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
+ old_opts.s_min_batch_time = sbi->s_min_batch_time;
+ old_opts.s_max_batch_time = sbi->s_max_batch_time;
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
old_opts.s_qf_names[i] = sbi->s_qf_names[i];
#endif
+ if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+ journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
/*
* Allow the "check" option to be passed as a remount option.
*/
- if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
+ if (!parse_options(data, sb, NULL, &journal_ioprio,
+ &n_blocks_count, 1)) {
err = -EINVAL;
goto restore_opts;
}
es = sbi->s_es;
- ext4_init_journal_params(sb, sbi->s_journal);
+ if (sbi->s_journal) {
+ ext4_init_journal_params(sb, sbi->s_journal);
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ }
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
* We have to unlock super so that we can wait for
* transactions.
*/
- unlock_super(sb);
- ext4_mark_recovery_complete(sb, es);
- lock_super(sb);
+ if (sbi->s_journal) {
+ unlock_super(sb);
+ ext4_mark_recovery_complete(sb, es);
+ lock_super(sb);
+ }
} else {
- __le32 ret;
+ int ret;
if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
~EXT4_FEATURE_RO_COMPAT_SUPP))) {
printk(KERN_WARNING "EXT4-fs: %s: couldn't "
"remount RDWR because of unsupported "
- "optional features (%x).\n",
- sb->s_id, le32_to_cpu(ret));
+ "optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
err = -EROFS;
goto restore_opts;
}
if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
printk(KERN_ERR
"EXT4-fs: ext4_remount: "
- "Checksum for group %lu failed (%u!=%u)\n",
+ "Checksum for group %u failed (%u!=%u)\n",
g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
err = -EINVAL;
* been changed by e2fsck since we originally mounted
* the partition.)
*/
- ext4_clear_journal_err(sb, es);
+ if (sbi->s_journal)
+ ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if ((err = ext4_group_extend(sb, es, n_blocks_count)))
goto restore_opts;
sb->s_flags &= ~MS_RDONLY;
}
}
+ if (sbi->s_journal == NULL)
+ ext4_commit_super(sb, es, 1);
+
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
+ sbi->s_min_batch_time = old_opts.s_min_batch_time;
+ sbi->s_max_batch_time = old_opts.s_max_batch_time;
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
- if (ext4_should_journal_data(path.dentry->d_inode)) {
+ if (EXT4_SB(sb)->s_journal &&
+ ext4_should_journal_data(path.dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
- if (!handle) {
+ if (EXT4_SB(sb)->s_journal && !handle) {
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);
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
if (journal_quota)
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
else {
/* Always do at least ordered writes for quotas */
err = ext4_jbd2_file_inode(handle, inode);
static ssize_t ext4_ui_proc_write(struct file *file, const char __user *buf,
size_t cnt, loff_t *ppos)
{
- unsigned int *p = PDE(file->f_path.dentry->d_inode)->data;
+ unsigned long *p = PDE(file->f_path.dentry->d_inode)->data;
char str[32];
- unsigned long value;
if (cnt >= sizeof(str))
return -EINVAL;
if (copy_from_user(str, buf, cnt))
return -EFAULT;
- value = simple_strtol(str, NULL, 0);
- if (value < 0)
- return -ERANGE;
- *p = value;
+
+ *p = simple_strtoul(str, NULL, 0);
return cnt;
}
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
- MODULE_DESCRIPTION("Fourth Extended Filesystem with extents");
+ MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
module_init(init_ext4_fs)
module_exit(exit_ext4_fs)
#include <linux/crc32.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
+ #include <linux/bio.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
set_buffer_ordered(bh);
barrier_done = 1;
}
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
if (barrier_done)
clear_buffer_ordered(bh);
lock_buffer(bh);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
}
*cbh = bh;
return ret;
* This function along with journal_submit_commit_record
* allows to write the commit record asynchronously.
*/
- static int journal_wait_on_commit_record(struct buffer_head *bh)
+ static int journal_wait_on_commit_record(journal_t *journal,
+ struct buffer_head *bh)
{
int ret = 0;
+ retry:
clear_buffer_dirty(bh);
wait_on_buffer(bh);
+ if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
+ printk(KERN_WARNING
+ "JBD2: wait_on_commit_record: sync failed on %s - "
+ "disabling barriers\n", journal->j_devname);
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags &= ~JBD2_BARRIER;
+ spin_unlock(&journal->j_state_lock);
+
+ lock_buffer(bh);
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ bh->b_end_io = journal_end_buffer_io_sync;
+
+ ret = submit_bh(WRITE_SYNC, bh);
+ if (ret) {
+ unlock_buffer(bh);
+ return ret;
+ }
+ goto retry;
+ }
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
int flags;
int err;
unsigned long long blocknr;
+ ktime_t start_time;
+ u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
int space_left = 0;
int first_tag = 0;
int tag_flag;
- int i;
+ int i, to_free = 0;
int tag_bytes = journal_tag_bytes(journal);
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
+ start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
spin_unlock(&journal->j_state_lock);
if (is_journal_aborted(journal)) {
clear_buffer_jbddirty(jh2bh(jh));
JBUFFER_TRACE(jh, "journal is aborting: refile");
+ jbd2_buffer_abort_trigger(jh,
+ jh->b_frozen_data ?
+ jh->b_frozen_triggers :
+ jh->b_triggers);
jbd2_journal_refile_buffer(journal, jh);
/* If that was the last one, we need to clean up
* any descriptor buffers which may have been
__jbd2_journal_abort_hard(journal);
}
if (!err && !is_journal_aborted(journal))
- err = journal_wait_on_commit_record(cbh);
+ err = journal_wait_on_commit_record(journal, cbh);
if (err)
jbd2_journal_abort(journal, err);
* data.
*
* Otherwise, we can just throw away the frozen data now.
+ *
+ * We also know that the frozen data has already fired
+ * its triggers if they exist, so we can clear that too.
*/
if (jh->b_committed_data) {
jbd2_free(jh->b_committed_data, bh->b_size);
if (jh->b_frozen_data) {
jh->b_committed_data = jh->b_frozen_data;
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
} else if (jh->b_frozen_data) {
jbd2_free(jh->b_frozen_data, bh->b_size);
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
spin_lock(&journal->j_list_lock);
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
- spin_unlock(&journal->j_state_lock);
+ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
- if (journal->j_commit_callback)
- journal->j_commit_callback(journal, commit_transaction);
+ /*
+ * weight the commit time higher than the average time so we don't
+ * react too strongly to vast changes in the commit time
+ */
+ if (likely(journal->j_average_commit_time))
+ journal->j_average_commit_time = (commit_time +
+ journal->j_average_commit_time*3) / 4;
+ else
+ journal->j_average_commit_time = commit_time;
+ spin_unlock(&journal->j_state_lock);
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__jbd2_journal_drop_transaction(journal, commit_transaction);
+ to_free = 1;
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
}
spin_unlock(&journal->j_list_lock);
+ if (journal->j_commit_callback)
+ journal->j_commit_callback(journal, commit_transaction);
+
trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
- journal->j_devname, journal->j_commit_sequence,
+ journal->j_devname, commit_transaction->t_tid,
journal->j_tail_sequence);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
+ if (to_free)
+ kfree(commit_transaction);
wake_up(&journal->j_wait_done_commit);
}
#include <asm/uaccess.h>
#include <asm/page.h>
+ #include <asm/div64.h>
EXPORT_SYMBOL(jbd2_journal_start);
EXPORT_SYMBOL(jbd2_journal_restart);
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
+EXPORT_SYMBOL(jbd2_journal_set_triggers);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
- EXPORT_SYMBOL(jbd2_journal_create);
EXPORT_SYMBOL(jbd2_journal_load);
EXPORT_SYMBOL(jbd2_journal_destroy);
EXPORT_SYMBOL(jbd2_journal_abort);
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
- printk(KERN_INFO "kjournald2 starting. Commit interval %ld seconds\n",
- journal->j_commit_interval / HZ);
+ printk(KERN_INFO "kjournald2 starting: pid %d, dev %s, "
+ "commit interval %ld seconds\n", current->pid,
+ journal->j_devname, journal->j_commit_interval / HZ);
/*
* And now, wait forever for commit wakeup events.
struct page *new_page;
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
+ struct jbd2_buffer_trigger_type *triggers;
/*
* The buffer really shouldn't be locked: only the current committing
done_copy_out = 1;
new_page = virt_to_page(jh_in->b_frozen_data);
new_offset = offset_in_page(jh_in->b_frozen_data);
+ triggers = jh_in->b_frozen_triggers;
} else {
new_page = jh2bh(jh_in)->b_page;
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
+ triggers = jh_in->b_triggers;
}
mapped_data = kmap_atomic(new_page, KM_USER0);
+ /*
+ * Fire any commit trigger. Do this before checking for escaping,
+ * as the trigger may modify the magic offset. If a copy-out
+ * happens afterwards, it will have the correct data in the buffer.
+ */
+ jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
+ triggers);
+
/*
* Check for escaping
*/
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
done_copy_out = 1;
+
+ /*
+ * This isn't strictly necessary, as we're using frozen
+ * data for the escaping, but it keeps consistency with
+ * b_frozen_data usage.
+ */
+ jh_in->b_frozen_triggers = jh_in->b_triggers;
}
/*
return NULL;
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh)
+ return NULL;
lock_buffer(bh);
memset(bh->b_data, 0, journal->j_blocksize);
set_buffer_uptodate(bh);
jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
seq_printf(seq, " %ums logging transaction\n",
jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
+ seq_printf(seq, " %luus average transaction commit time\n",
+ do_div(s->journal->j_average_commit_time, 1000));
seq_printf(seq, " %lu handles per transaction\n",
s->stats->u.run.rs_handle_count / s->stats->ts_tid);
seq_printf(seq, " %lu blocks per transaction\n",
spin_lock_init(&journal->j_state_lock);
journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
+ journal->j_min_batch_time = 0;
+ journal->j_max_batch_time = 15000; /* 15ms */
/* The journal is marked for error until we succeed with recovery! */
journal->j_flags = JBD2_ABORT;
/* journal descriptor can store up to n blocks -bzzz */
journal->j_blocksize = blocksize;
+ jbd2_stats_proc_init(journal);
n = journal->j_blocksize / sizeof(journal_block_tag_t);
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
if (!journal->j_wbuf) {
printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
__func__);
- kfree(journal);
- journal = NULL;
- goto out;
+ goto out_err;
}
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
p = journal->j_devname;
while ((p = strchr(p, '/')))
*p = '!';
- jbd2_stats_proc_init(journal);
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
- out:
+
return journal;
+ out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/**
if (!journal->j_wbuf) {
printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
__func__);
- jbd2_stats_proc_exit(journal);
- kfree(journal);
- return NULL;
+ goto out_err;
}
err = jbd2_journal_bmap(journal, 0, &blocknr);
if (err) {
printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
__func__);
- jbd2_stats_proc_exit(journal);
- kfree(journal);
- return NULL;
+ goto out_err;
}
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+ out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/*
return jbd2_journal_start_thread(journal);
}
- /**
- * int jbd2_journal_create() - Initialise the new journal file
- * @journal: Journal to create. This structure must have been initialised
- *
- * Given a journal_t structure which tells us which disk blocks we can
- * use, create a new journal superblock and initialise all of the
- * journal fields from scratch.
- **/
- int jbd2_journal_create(journal_t *journal)
- {
- unsigned long long blocknr;
- struct buffer_head *bh;
- journal_superblock_t *sb;
- int i, err;
-
- if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
- printk (KERN_ERR "Journal length (%d blocks) too short.\n",
- journal->j_maxlen);
- journal_fail_superblock(journal);
- return -EINVAL;
- }
-
- if (journal->j_inode == NULL) {
- /*
- * We don't know what block to start at!
- */
- printk(KERN_EMERG
- "%s: creation of journal on external device!\n",
- __func__);
- BUG();
- }
-
- /* Zero out the entire journal on disk. We cannot afford to
- have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
- jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
- for (i = 0; i < journal->j_maxlen; i++) {
- err = jbd2_journal_bmap(journal, i, &blocknr);
- if (err)
- return err;
- bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- lock_buffer(bh);
- memset (bh->b_data, 0, journal->j_blocksize);
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- BUFFER_TRACE(bh, "marking uptodate");
- set_buffer_uptodate(bh);
- unlock_buffer(bh);
- __brelse(bh);
- }
-
- sync_blockdev(journal->j_dev);
- jbd_debug(1, "JBD: journal cleared.\n");
-
- /* OK, fill in the initial static fields in the new superblock */
- sb = journal->j_superblock;
-
- sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
- sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
-
- sb->s_blocksize = cpu_to_be32(journal->j_blocksize);
- sb->s_maxlen = cpu_to_be32(journal->j_maxlen);
- sb->s_first = cpu_to_be32(1);
-
- journal->j_transaction_sequence = 1;
-
- journal->j_flags &= ~JBD2_ABORT;
- journal->j_format_version = 2;
-
- return journal_reset(journal);
- }
-
/**
* void jbd2_journal_update_superblock() - Update journal sb on disk.
* @journal: The journal to update.
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
+ mutex_lock(&journal->j_checkpoint_mutex);
jbd2_log_do_checkpoint(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/highmem.h>
+ #include <linux/hrtimer.h>
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
{
transaction->t_journal = journal;
transaction->t_state = T_RUNNING;
+ transaction->t_start_time = ktime_get();
transaction->t_tid = journal->j_transaction_sequence++;
transaction->t_expires = jiffies + journal->j_commit_interval;
spin_lock_init(&transaction->t_handle_lock);
source = kmap_atomic(page, KM_USER0);
memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
kunmap_atomic(source, KM_USER0);
+
+ /*
+ * Now that the frozen data is saved off, we need to store
+ * any matching triggers.
+ */
+ jh->b_frozen_triggers = jh->b_triggers;
}
jbd_unlock_bh_state(bh);
return err;
}
+/**
+ * void jbd2_journal_set_triggers() - Add triggers for commit writeout
+ * @bh: buffer to trigger on
+ * @type: struct jbd2_buffer_trigger_type containing the trigger(s).
+ *
+ * Set any triggers on this journal_head. This is always safe, because
+ * triggers for a committing buffer will be saved off, and triggers for
+ * a running transaction will match the buffer in that transaction.
+ *
+ * Call with NULL to clear the triggers.
+ */
+void jbd2_journal_set_triggers(struct buffer_head *bh,
+ struct jbd2_buffer_trigger_type *type)
+{
+ struct journal_head *jh = bh2jh(bh);
+
+ jh->b_triggers = type;
+}
+
+void jbd2_buffer_commit_trigger(struct journal_head *jh, void *mapped_data,
+ struct jbd2_buffer_trigger_type *triggers)
+{
+ struct buffer_head *bh = jh2bh(jh);
+
+ if (!triggers || !triggers->t_commit)
+ return;
+
+ triggers->t_commit(triggers, bh, mapped_data, bh->b_size);
+}
+
+void jbd2_buffer_abort_trigger(struct journal_head *jh,
+ struct jbd2_buffer_trigger_type *triggers)
+{
+ if (!triggers || !triggers->t_abort)
+ return;
+
+ triggers->t_abort(triggers, jh2bh(jh));
+}
+
+
+
/**
* int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
* @handle: transaction to add buffer to.
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
- int old_handle_count, err;
+ int err;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
/*
* Implement synchronous transaction batching. If the handle
* was synchronous, don't force a commit immediately. Let's
- * yield and let another thread piggyback onto this transaction.
- * Keep doing that while new threads continue to arrive.
- * It doesn't cost much - we're about to run a commit and sleep
- * on IO anyway. Speeds up many-threaded, many-dir operations
- * by 30x or more...
+ * yield and let another thread piggyback onto this
+ * transaction. Keep doing that while new threads continue to
+ * arrive. It doesn't cost much - we're about to run a commit
+ * and sleep on IO anyway. Speeds up many-threaded, many-dir
+ * operations by 30x or more...
+ *
+ * We try and optimize the sleep time against what the
+ * underlying disk can do, instead of having a static sleep
+ * time. This is useful for the case where our storage is so
+ * fast that it is more optimal to go ahead and force a flush
+ * and wait for the transaction to be committed than it is to
+ * wait for an arbitrary amount of time for new writers to
+ * join the transaction. We achieve this by measuring how
+ * long it takes to commit a transaction, and compare it with
+ * how long this transaction has been running, and if run time
+ * < commit time then we sleep for the delta and commit. This
+ * greatly helps super fast disks that would see slowdowns as
+ * more threads started doing fsyncs.
*
- * But don't do this if this process was the most recent one to
- * perform a synchronous write. We do this to detect the case where a
- * single process is doing a stream of sync writes. No point in waiting
- * for joiners in that case.
+ * But don't do this if this process was the most recent one
+ * to perform a synchronous write. We do this to detect the
+ * case where a single process is doing a stream of sync
+ * writes. No point in waiting for joiners in that case.
*/
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
+ u64 commit_time, trans_time;
+
journal->j_last_sync_writer = pid;
- do {
- old_handle_count = transaction->t_handle_count;
- schedule_timeout_uninterruptible(1);
- } while (old_handle_count != transaction->t_handle_count);
+
+ spin_lock(&journal->j_state_lock);
+ commit_time = journal->j_average_commit_time;
+ spin_unlock(&journal->j_state_lock);
+
+ trans_time = ktime_to_ns(ktime_sub(ktime_get(),
+ transaction->t_start_time));
+
+ commit_time = max_t(u64, commit_time,
+ 1000*journal->j_min_batch_time);
+ commit_time = min_t(u64, commit_time,
+ 1000*journal->j_max_batch_time);
+
+ if (trans_time < commit_time) {
+ ktime_t expires = ktime_add_ns(ktime_get(),
+ commit_time);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+ }
}
current->journal_info = NULL;
#include <linux/kobject.h>
#include <linux/mutex.h>
#include <linux/file.h>
+#include <linux/async.h>
#include <asm/uaccess.h>
#include "internal.h"
INIT_HLIST_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
INIT_LIST_HEAD(&s->s_dentry_lru);
+ INIT_LIST_HEAD(&s->s_async_list);
init_rwsem(&s->s_umount);
mutex_init(&s->s_lock);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
{
const struct super_operations *sop = sb->s_op;
+
if (sb->s_root) {
shrink_dcache_for_umount(sb);
fsync_super(sb);
lock_super(sb);
sb->s_flags &= ~MS_ACTIVE;
+
+ /*
+ * wait for asynchronous fs operations to finish before going further
+ */
+ async_synchronize_full_special(&sb->s_async_list);
+
/* bad name - it should be evict_inodes() */
invalidate_inodes(sb);
lock_kernel();
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
+ async_synchronize_full_special(&sb->s_async_list);
if (sb->s_root && (wait || sb->s_dirt))
sb->s_op->sync_fs(sb, wait);
up_read(&sb->s_umount);
}
s->s_flags |= MS_ACTIVE;
+ bdev->bd_super = s;
}
return simple_set_mnt(mnt, s);
struct block_device *bdev = sb->s_bdev;
fmode_t mode = sb->s_mode;
+ bdev->bd_super = 0;
generic_shutdown_super(sb);
sync_blockdev(bdev);
close_bdev_exclusive(bdev, mode);
#define EXT3_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
#define EXT3_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\
+ EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\
+ EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\
+ EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\
+ EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT3_REG_FLMASK (~(EXT3_DIRSYNC_FL | EXT3_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT3_OTHER_FLMASK (EXT3_NODUMP_FL | EXT3_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags)
+{
+ if (S_ISDIR(mode))
+ return flags;
+ else if (S_ISREG(mode))
+ return flags & EXT3_REG_FLMASK;
+ else
+ return flags & EXT3_OTHER_FLMASK;
+}
+
/*
* Inode dynamic state flags
*/
#define EXT3_ERROR_FS 0x0002 /* Errors detected */
#define EXT3_ORPHAN_FS 0x0004 /* Orphans being recovered */
+ /*
+ * Misc. filesystem flags
+ */
+ #define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
+ #define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
+ #define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */
+
/*
* Mount flags
*/
__u16 s_reserved_word_pad;
__le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
- __u32 s_reserved[190]; /* Padding to the end of the block */
+ __le32 s_mkfs_time; /* When the filesystem was created */
+ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */
+ /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+ /*150*/ __le32 s_blocks_count_hi; /* Blocks count */
+ __le32 s_r_blocks_count_hi; /* Reserved blocks count */
+ __le32 s_free_blocks_count_hi; /* Free blocks count */
+ __le16 s_min_extra_isize; /* All inodes have at least # bytes */
+ __le16 s_want_extra_isize; /* New inodes should reserve # bytes */
+ __le32 s_flags; /* Miscellaneous flags */
+ __le16 s_raid_stride; /* RAID stride */
+ __le16 s_mmp_interval; /* # seconds to wait in MMP checking */
+ __le64 s_mmp_block; /* Block for multi-mount protection */
+ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
+ __u8 s_log_groups_per_flex; /* FLEX_BG group size */
+ __u8 s_reserved_char_pad2;
+ __le16 s_reserved_pad;
+ __u32 s_reserved[162]; /* Padding to the end of the block */
};
#ifdef __KERNEL__
#define DX_HASH_LEGACY 0
#define DX_HASH_HALF_MD4 1
#define DX_HASH_TEA 2
+ #define DX_HASH_LEGACY_UNSIGNED 3
+ #define DX_HASH_HALF_MD4_UNSIGNED 4
+ #define DX_HASH_TEA_UNSIGNED 5
#ifdef __KERNEL__
u32 s_next_generation;
u32 s_hash_seed[4];
int s_def_hash_version;
+ int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
- struct blockgroup_lock s_blockgroup_lock;
+ struct blockgroup_lock *s_blockgroup_lock;
/* root of the per fs reservation window tree */
spinlock_t s_rsv_window_lock;
static inline spinlock_t *
sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group)
{
- return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group);
+ return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
}
#endif /* _LINUX_EXT3_FS_SB */
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
struct inode * bd_inode; /* will die */
+ struct super_block * bd_super;
int bd_openers;
struct mutex bd_mutex; /* open/close mutex */
struct semaphore bd_mount_sem;
struct rw_semaphore s_umount;
struct mutex s_lock;
int s_count;
- int s_syncing;
int s_need_sync_fs;
atomic_t s_active;
#ifdef CONFIG_SECURITY
* generic_show_options()
*/
char *s_options;
+
+ /*
+ * storage for asynchronous operations
+ */
+ struct list_head s_async_list;
};
extern struct timespec current_fs_time(struct super_block *sb);
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
+ int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
};
/*
extern int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
-extern long do_fsync(struct file *file, int datasync);
+extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
extern void sync_supers(void);
extern void sync_filesystems(int wait);
extern void __fsync_super(struct super_block *sb);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int __generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern int generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start,
u64 len, get_block_t *get_block);
*/
unsigned long t_expires;
+ /*
+ * When this transaction started, in nanoseconds [no locking]
+ */
+ ktime_t t_start_time;
+
/*
* How many handles used this transaction? [t_handle_lock]
*/
return end + (MAX_JIFFY_OFFSET - start);
}
+ #define JBD2_NR_BATCH 64
+
/**
* struct journal_s - The journal_s type is the concrete type associated with
* journal_t.
/* Semaphore for locking against concurrent checkpoints */
struct mutex j_checkpoint_mutex;
+ /*
+ * List of buffer heads used by the checkpoint routine. This
+ * was moved from jbd2_log_do_checkpoint() to reduce stack
+ * usage. Access to this array is controlled by the
+ * j_checkpoint_mutex. [j_checkpoint_mutex]
+ */
+ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH];
+
/*
* Journal head: identifies the first unused block in the journal.
* [j_state_lock]
struct buffer_head **j_wbuf;
int j_wbufsize;
+ /*
+ * this is the pid of hte last person to run a synchronous operation
+ * through the journal
+ */
pid_t j_last_sync_writer;
+ /*
+ * the average amount of time in nanoseconds it takes to commit a
+ * transaction to disk. [j_state_lock]
+ */
+ u64 j_average_commit_time;
+
+ /*
+ * minimum and maximum times that we should wait for
+ * additional filesystem operations to get batched into a
+ * synchronous handle in microseconds
+ */
+ u32 j_min_batch_time;
+ u32 j_max_batch_time;
+
/* This function is called when a transaction is closed */
void (*j_commit_callback)(journal_t *,
transaction_t *);
int __jbd2_journal_remove_checkpoint(struct journal_head *);
void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
+
+/*
+ * Triggers
+ */
+
+struct jbd2_buffer_trigger_type {
+ /*
+ * Fired just before a buffer is written to the journal.
+ * mapped_data is a mapped buffer that is the frozen data for
+ * commit.
+ */
+ void (*t_commit)(struct jbd2_buffer_trigger_type *type,
+ struct buffer_head *bh, void *mapped_data,
+ size_t size);
+
+ /*
+ * Fired during journal abort for dirty buffers that will not be
+ * committed.
+ */
+ void (*t_abort)(struct jbd2_buffer_trigger_type *type,
+ struct buffer_head *bh);
+};
+
+extern void jbd2_buffer_commit_trigger(struct journal_head *jh,
+ void *mapped_data,
+ struct jbd2_buffer_trigger_type *triggers);
+extern void jbd2_buffer_abort_trigger(struct journal_head *jh,
+ struct jbd2_buffer_trigger_type *triggers);
+
/* Buffer IO */
extern int
jbd2_journal_write_metadata_buffer(transaction_t *transaction,
extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
+void jbd2_journal_set_triggers(struct buffer_head *,
+ struct jbd2_buffer_trigger_type *type);
extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
extern int jbd2_journal_forget (handle_t *, struct buffer_head *);
(journal_t *, unsigned long, unsigned long, unsigned long);
extern void jbd2_journal_clear_features
(journal_t *, unsigned long, unsigned long, unsigned long);
- extern int jbd2_journal_create (journal_t *);
extern int jbd2_journal_load (journal_t *journal);
extern int jbd2_journal_destroy (journal_t *);
extern int jbd2_journal_recover (journal_t *journal);
int jbd2_log_do_checkpoint(journal_t *journal);
void __jbd2_log_wait_for_space(journal_t *journal);
- extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
- extern int jbd2_cleanup_journal_tail(journal_t *);
+ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
+ extern int jbd2_cleanup_journal_tail(journal_t *);
/* Debugging code only: */