Commit 1f63b9c1 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (36 commits)
  ext4: fix up rb_root initializations to use RB_ROOT
  ext4: Code cleanup for EXT4_IOC_MOVE_EXT ioctl
  ext4: Fix the NULL reference in double_down_write_data_sem()
  ext4: Fix insertion point of extent in mext_insert_across_blocks()
  ext4: consolidate in_range() definitions
  ext4: cleanup to use ext4_grp_offs_to_block()
  ext4: cleanup to use ext4_group_first_block_no()
  ext4: Release page references acquired in ext4_da_block_invalidatepages
  ext4: Fix ext4_quota_write cross block boundary behaviour
  ext4: Convert BUG_ON checks to use ext4_error() instead
  ext4: Use direct_IO_no_locking in ext4 dio read
  ext4: use ext4_get_block_write in buffer write
  ext4: mechanical rename some of the direct I/O get_block's identifiers
  ext4: make "offset" consistent in ext4_check_dir_entry()
  ext4: Handle non empty on-disk orphan link
  ext4: explicitly remove inode from orphan list after failed direct io
  ext4: fix error handling in migrate
  ext4: deprecate obsoleted mount options
  ext4: Fix fencepost error in chosing choosing group vs file preallocation.
  jbd2: clean up an assertion in jbd2_journal_commit_transaction()
  ...
parents b24bc1e6 64e290ec
......@@ -97,8 +97,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, __func__,
"Checksum bad for group %u", block_group);
ext4_error(sb, "Checksum bad for group %u",
block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
......@@ -130,8 +130,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
le32_to_cpu(sbi->s_es->s_first_data_block) -
(EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
ext4_group_first_block_no(sb, ngroups - 1);
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
......@@ -189,9 +188,6 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* when a file system is mounted (see ext4_fill_super).
*/
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
/**
* ext4_get_group_desc() -- load group descriptor from disk
* @sb: super block
......@@ -210,10 +206,8 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= ngroups) {
ext4_error(sb, "ext4_get_group_desc",
"block_group >= groups_count - "
"block_group = %u, groups_count = %u",
block_group, ngroups);
ext4_error(sb, "block_group >= groups_count - block_group = %u,"
" groups_count = %u", block_group, ngroups);
return NULL;
}
......@@ -221,8 +215,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
ext4_error(sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
ext4_error(sb, "Group descriptor not loaded - "
"block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
return NULL;
......@@ -282,9 +275,7 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
return 1;
err_out:
ext4_error(sb, __func__,
"Invalid block bitmap - "
"block_group = %d, block = %llu",
ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
block_group, bitmap_blk);
return 0;
}
......@@ -311,8 +302,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, __func__,
"Cannot read block bitmap - "
ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
......@@ -354,8 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
ext4_error(sb, __func__,
"Cannot read block bitmap - "
ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
......@@ -419,8 +408,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
ext4_error(sb, __func__,
"Adding blocks in system zones - "
ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
......@@ -453,8 +441,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
ext4_error(sb, __func__,
"bit already cleared for block %llu",
ext4_error(sb, "bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
......
......@@ -205,14 +205,14 @@ void ext4_release_system_zone(struct super_block *sb)
entry = rb_entry(n, struct ext4_system_zone, node);
kmem_cache_free(ext4_system_zone_cachep, entry);
if (!parent)
EXT4_SB(sb)->system_blks.rb_node = NULL;
EXT4_SB(sb)->system_blks = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
parent->rb_right = NULL;
n = parent;
}
EXT4_SB(sb)->system_blks.rb_node = NULL;
EXT4_SB(sb)->system_blks = RB_ROOT;
}
/*
......
......@@ -83,10 +83,12 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
error_msg = "inode out of bounds";
if (error_msg != NULL)
ext4_error(dir->i_sb, function,
"bad entry in directory #%lu: %s - "
"offset=%u, inode=%u, rec_len=%d, name_len=%d",
dir->i_ino, error_msg, offset,
__ext4_error(dir->i_sb, function,
"bad entry in directory #%lu: %s - block=%llu"
"offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
dir->i_ino, error_msg,
(unsigned long long) bh->b_blocknr,
(unsigned) (offset%bh->b_size), offset,
le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
......@@ -150,7 +152,7 @@ static int ext4_readdir(struct file *filp,
*/
if (!bh) {
if (!dir_has_error) {
ext4_error(sb, __func__, "directory #%lu "
ext4_error(sb, "directory #%lu "
"contains a hole at offset %Lu",
inode->i_ino,
(unsigned long long) filp->f_pos);
......@@ -303,7 +305,7 @@ static void free_rb_tree_fname(struct rb_root *root)
kfree(old);
}
if (!parent)
root->rb_node = NULL;
*root = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
......
......@@ -53,6 +53,12 @@
#define ext4_debug(f, a...) do {} while (0)
#endif
#define EXT4_ERROR_INODE(inode, fmt, a...) \
ext4_error_inode(__func__, (inode), (fmt), ## a);
#define EXT4_ERROR_FILE(file, fmt, a...) \
ext4_error_file(__func__, (file), (fmt), ## a);
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
......@@ -133,14 +139,14 @@ struct mpage_da_data {
int pages_written;
int retval;
};
#define DIO_AIO_UNWRITTEN 0x1
#define EXT4_IO_UNWRITTEN 0x1
typedef struct ext4_io_end {
struct list_head list; /* per-file finished AIO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
int error; /* I/O error code */
ext4_lblk_t offset; /* offset in the file */
size_t size; /* size of the extent */
struct page *page; /* page struct for buffer write */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
} ext4_io_end_t;
......@@ -284,10 +290,12 @@ struct flex_groups {
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */
#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
......@@ -313,17 +321,6 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
return flags & EXT4_OTHER_FLMASK;
}
/*
* Inode dynamic state flags
*/
#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */
#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */
#define EXT4_STATE_DIO_UNWRITTEN 0x00000040 /* need convert on dio done*/
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
__u32 group; /* Group number for this data */
......@@ -364,19 +361,20 @@ struct ext4_new_group_data {
/* caller is from the direct IO path, request to creation of an
unitialized extents if not allocated, split the uninitialized
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_DIO 0x0008
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_DIO_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after direct IO complete */
#define EXT4_GET_BLOCKS_DIO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_DIO_CREATE_EXT)
/*
* Flags used by ext4_free_blocks
*/
#define EXT4_FREE_BLOCKS_METADATA 0x0001
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
/*
* ioctl commands
......@@ -630,7 +628,7 @@ struct ext4_inode_info {
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
__u32 i_state; /* Dynamic state flags for ext4 */
unsigned long i_state_flags; /* Dynamic state flags */
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
......@@ -708,8 +706,9 @@ struct ext4_inode_info {
qsize_t i_reserved_quota;
#endif
/* completed async DIOs that might need unwritten extents handling */
struct list_head i_aio_dio_complete_list;
/* completed IOs that might need unwritten extents handling */
struct list_head i_completed_io_list;
spinlock_t i_completed_io_lock;
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
......@@ -760,6 +759,7 @@ struct ext4_inode_info {
#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_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#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 */
......@@ -1050,6 +1050,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
/*
* Inode dynamic state flags
*/
enum {
EXT4_STATE_JDATA, /* journaled data exists */
EXT4_STATE_NEW, /* inode is newly created */
EXT4_STATE_XATTR, /* has in-inode xattrs */
EXT4_STATE_NO_EXPAND, /* No space for expansion */
EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
};
static inline int ext4_test_inode_state(struct inode *inode, int bit)
{
return test_bit(bit, &EXT4_I(inode)->i_state_flags);
}
static inline void ext4_set_inode_state(struct inode *inode, int bit)
{
set_bit(bit, &EXT4_I(inode)->i_state_flags);
}
static inline void ext4_clear_inode_state(struct inode *inode, int bit)
{
clear_bit(bit, &EXT4_I(inode)->i_state_flags);
}
#else
/* Assume that user mode programs are passing in an ext4fs superblock, not
* a kernel struct super_block. This will allow us to call the feature-test
......@@ -1126,6 +1154,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
......@@ -1439,7 +1469,7 @@ extern int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int flush_aio_dio_completed_IO(struct inode *inode);
extern int flush_completed_IO(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
/* ioctl.c */
......@@ -1465,13 +1495,20 @@ extern int ext4_group_extend(struct super_block *sb,
ext4_fsblk_t n_blocks_count);
/* super.c */
extern void ext4_error(struct super_block *, const char *, const char *, ...)
extern void __ext4_error(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
#define ext4_error(sb, message...) __ext4_error(sb, __func__, ## message)
extern void ext4_error_inode(const char *, struct inode *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_error_file(const char *, struct file *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void __ext4_std_error(struct super_block *, const char *, int);
extern void ext4_abort(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_warning(struct super_block *, const char *, const char *, ...)
extern void __ext4_warning(struct super_block *, const char *,
const char *, ...)
__attribute__ ((format (printf, 3, 4)));
#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, ## message)
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
......@@ -1744,7 +1781,7 @@ 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_convert_unwritten_extents(struct inode *inode, loff_t offset,
loff_t len);
ssize_t len);
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int flags);
......@@ -1756,6 +1793,15 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 len, __u64 *moved_len);
/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
/*
* Add new method to test wether block and inode bitmaps are properly
* initialized. With uninit_bg reading the block from disk is not enough
......@@ -1773,6 +1819,8 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
......@@ -125,14 +125,14 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
ext4_journal_abort_handle(where, __func__, bh,
handle, err);
} else {
if (inode && bh)
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
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__,
ext4_error(inode->i_sb,
"IO error syncing inode, "
"inode=%lu, block=%llu",
inode->i_ino,
......
......@@ -304,4 +304,28 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return 0;
}
/*
* This function controls whether or not we should try to go down the
* dioread_nolock code paths, which makes it safe to avoid taking
* i_mutex for direct I/O reads. This only works for extent-based
* files, and it doesn't work for nobh or if data journaling is
* enabled, since the dioread_nolock code uses b_private to pass
* information back to the I/O completion handler, and this conflicts
* with the jbd's use of b_private.
*/
static inline int ext4_should_dioread_nolock(struct inode *inode)
{
if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
return 0;
if (test_opt(inode->i_sb, NOBH))
return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
return 0;
if (ext4_should_journal_data(inode))
return 0;
return 1;
}
#endif /* _EXT4_JBD2_H */
This diff is collapsed.
......@@ -35,9 +35,9 @@
*/
static int ext4_release_file(struct inode *inode, struct file *filp)
{
if (EXT4_I(inode)->i_state & EXT4_STATE_DA_ALLOC_CLOSE) {
if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
EXT4_I(inode)->i_state &= ~EXT4_STATE_DA_ALLOC_CLOSE;
ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
......
......@@ -63,7 +63,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_aio_dio_completed_IO(inode);
ret = flush_completed_IO(inode);
if (ret < 0)
return ret;
......
......@@ -76,8 +76,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, __func__, "Checksum bad for group %u",
block_group);
ext4_error(sb, "Checksum bad for group %u", block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
......@@ -111,8 +110,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_inode_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, __func__,
"Cannot read inode bitmap - "
ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
......@@ -153,8 +151,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
ext4_error(sb, __func__,
"Cannot read inode bitmap - "
ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
......@@ -229,8 +226,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error(sb, "ext4_free_inode",
"reserved or nonexistent inode %lu", ino);
ext4_error(sb, "reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
......@@ -248,8 +244,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit, bitmap_bh->b_data);
if (!cleared)
ext4_error(sb, "ext4_free_inode",
"bit already cleared for inode %lu", ino);
ext4_error(sb, "bit already cleared for inode %lu", ino);
else {
gdp = ext4_get_group_desc(sb, block_group, &bh2);
......@@ -736,8 +731,7 @@ static int ext4_claim_inode(struct super_block *sb,
if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
ino > EXT4_INODES_PER_GROUP(sb)) {
ext4_unlock_group(sb, group);
ext4_error(sb, __func__,
"reserved inode or inode > inodes count - "
ext4_error(sb, "reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
return 1;
......@@ -904,7 +898,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
BUFFER_TRACE(inode_bitmap_bh,
"call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle,
inode,
NULL,
inode_bitmap_bh);
if (err)
goto fail;
......@@ -1029,7 +1023,8 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state = EXT4_STATE_NEW;
ei->i_state_flags = 0;
ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
......@@ -1098,8 +1093,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
ext4_warning(sb, __func__,
"bad orphan ino %lu! e2fsck was run?", ino);
ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
goto error;
}
......@@ -1107,8 +1101,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (!bitmap_bh) {
ext4_warning(sb, __func__,
"inode bitmap error for orphan %lu", ino);
ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
goto error;
}
......@@ -1140,8 +1133,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
err = PTR_ERR(inode);
inode = NULL;
bad_orphan:
ext4_warning(sb, __func__,
"bad orphan inode %lu! e2fsck was run?", ino);
ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
bit, (unsigned long long)bitmap_bh->b_blocknr,
ext4_test_bit(bit, bitmap_bh->b_data));
......
This diff is collapsed.
......@@ -92,6 +92,15 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
flags &= ~EXT4_EXTENTS_FL;
}
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
......@@ -249,7 +258,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (me.moved_len > 0)
file_remove_suid(donor_filp);
if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fput(donor_filp);
......
......@@ -441,10 +441,9 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
for (i = 0; i < count; i++) {
if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
ext4_fsblk_t blocknr;
blocknr = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb);
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += first + i;
blocknr +=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
ext4_grp_locked_error(sb, e4b->bd_group,
__func__, "double-free of inode"
" %lu's block %llu(bit %u in group %u)",
......@@ -1255,10 +1254,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
if (!mb_test_bit(block, EXT4_MB_BITMAP(e4b))) {
ext4_fsblk_t blocknr;
blocknr = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb);
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += block;
blocknr +=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
ext4_grp_locked_error(sb, e4b->bd_group,
__func__, "double-free of inode"
" %lu's block %llu(bit %u in group %u)",
......@@ -1631,7 +1629,6 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
int max;
int err;
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_super_block *es = sbi->s_es;
struct ext4_free_extent ex;
if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
......@@ -1648,8 +1645,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
ext4_fsblk_t start;
start = (e4b->bd_group * EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) +
ex.fe_start + le32_to_cpu(es->s_first_data_block);
start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) +
ex.fe_start;
/* use do_div to get remainder (would be 64-bit modulo) */
if (do_div(start, sbi->s_stripe) == 0) {
ac->ac_found++;
......@@ -1803,8 +1800,8 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
BUG_ON(sbi->s_stripe == 0);
/* find first stripe-aligned block in group */
first_group_block = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb)
+ le32_to_cpu(sbi->s_es->s_first_data_block);
first_group_block = ext4_group_first_block_no(sb, e4b->bd_group);
a = first_group_block + sbi->s_stripe - 1;
do_div(a, sbi->s_stripe);
i = (a * sbi->s_stripe) - first_group_block;
......@@ -2256,7 +2253,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root.rb_node = NULL;
meta_group_info[i]->bb_free_root = RB_ROOT;
#ifdef DOUBLE_CHECK
{
......@@ -2560,12 +2557,9 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
ext4_unlock_group(sb, entry->group);
if (test_opt(sb, DISCARD)) {
ext4_fsblk_t discard_block;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
discard_block = (ext4_fsblk_t)entry->group *
EXT4_BLOCKS_PER_GROUP(sb)
+ entry->start_blk
+ le32_to_cpu(es->s_first_data_block);
discard_block = entry->start_blk +
ext4_group_first_block_no(sb, entry->group);
trace_ext4_discard_blocks(sb,
(unsigned long long)discard_block,
entry->count);
......@@ -2703,14 +2697,11 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (err)
goto out_err;
block = ac->ac_b_ex.fe_group * EXT4_BLOCKS_PER_GROUP(sb)
+ ac->ac_b_ex.fe_start
+ le32_to_cpu(es->s_first_data_block);
block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
len = ac->ac_b_ex.fe_len;
if (!ext4_data_block_valid(sbi, block, len)) {
ext4_error(sb, __func__,
"Allocating blocks %llu-%llu which overlap "
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata\n", block, block+len);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
......@@ -3161,9 +3152,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
/* The max size of hash table is PREALLOC_TB_SIZE */
order = PREALLOC_TB_SIZE - 1;
goal_block = ac->ac_g_ex.fe_group * EXT4_BLOCKS_PER_GROUP(ac->ac_sb) +
ac->ac_g_ex.fe_start +
le32_to_cpu(EXT4_SB(ac->ac_sb)->s_es->s_first_data_block);
goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex);
/*
* search for the prealloc space that is having
* minimal distance from the goal block.
......@@ -3526,8 +3515,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
if (bit >= end)
break;
next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit +
le32_to_cpu(sbi->s_es->s_first_data_block);
start = ext4_group_first_block_no(sb, group) + bit;
mb_debug(1, " free preallocated %u/%u in group %u\n",
(unsigned) start, (unsigned) next - bit,
(unsigned) group);
......@@ -3623,15 +3611,13 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
"bitmap for %u", group);
ext4_error(sb, "Error reading block bitmap for %u", group);
return 0;
}
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
ext4_error(sb, __func__, "Error in loading buddy "
"information for %u", group);
ext4_error(sb, "Error loading buddy information for %u", group);
put_bh(bitmap_bh);
return 0;
}
......@@ -3804,15 +3790,15 @@ void ext4_discard_preallocations(struct inode *inode)
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
ext4_error(sb, __func__, "Error in loading buddy "
"information for %u", group);
ext4_error(sb, "Error loading buddy information for %u",
group);
continue;
}
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
"bitmap for %u", group);
ext4_error(sb, "Error reading block bitmap for %u",
group);
ext4_mb_release_desc(&e4b);
continue;
}
......@@ -3938,7 +3924,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
/* don't use group allocation for large files */
size = max(size, isize);
if (size >= sbi->s_mb_stream_request) {
if (size > sbi->s_mb_stream_request) {
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
return;
}
......@@ -4077,8 +4063,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
if (ext4_mb_load_buddy(sb, group, &e4b)) {
ext4_error(sb, __func__, "Error in loading buddy "
"information for %u", group);
ext4_error(sb, "Error loading buddy information for %u",
group);
continue;
}
ext4_lock_group(sb, group);
......@@ -4476,10 +4462,10 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
sbi = EXT4_SB(sb);
es = EXT4_SB(sb)->s_es;
if (!ext4_data_block_valid(sbi, block, count)) {
ext4_error(sb, __func__,
"Freeing blocks not in datazone - "
"block = %llu, count = %lu", block, count);
if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
!ext4_data_block_valid(sbi, block, count)) {
ext4_error(sb, "Freeing blocks not in datazone - "
"block = %llu, count = %lu", block, count);
goto error_return;
}
......@@ -4547,8 +4533,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
in_range(block + count - 1, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, __func__,
"Freeing blocks in system zone - "
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
/* err = 0. ext4_std_error should be a no op */
goto error_return;
......
......@@ -220,16 +220,9 @@ struct ext4_buddy {
#define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap)
#define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy)
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
{
ext4_fsblk_t block;
block = (ext4_fsblk_t) fex->fe_group * EXT4_BLOCKS_PER_GROUP(sb)
+ fex->fe_start
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
return block;
return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
}
#endif
......@@ -365,12 +365,12 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
* happened after we started the migrate. We need to
* fail the migrate
*/
if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) {
if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
......@@ -503,14 +503,10 @@ int ext4_ext_migrate(struct inode *inode)
}
i_size_write(tmp_inode, i_size_read(inode));
/*
* We don't want the inode to be reclaimed
* if we got interrupted in between. We have
* this tmp inode carrying reference to the
* data blocks of the original file. We set
* the i_nlink to zero at the last stage after
* switching the original file to extent format
* Set the i_nlink to zero so it will be deleted later
* when we drop inode reference.
*/
tmp_inode->i_nlink = 1;
tmp_inode->i_nlink = 0;
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
......@@ -533,10 +529,20 @@ int ext4_ext_migrate(struct inode *inode)
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE;
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
/*
* It is impossible to update on-disk structures without
* a handle, so just rollback in-core changes and live other
* work to orphan_list_cleanup()
*/
ext4_orphan_del(NULL, tmp_inode);
retval = PTR_ERR(handle);
goto out;
}
ei = EXT4_I(inode);
i_data = ei->i_data;
......@@ -618,15 +624,8 @@ int ext4_ext_migrate(struct inode *inode)
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
/*
* Set the i_nlink to zero so that
* generic_drop_inode really deletes the
* inode
*/
tmp_inode->i_nlink = 0;
ext4_journal_stop(handle);
out:
unlock_new_inode(tmp_inode);
iput(tmp_inode);
......
......@@ -152,12 +152,12 @@ mext_check_null_inode(struct inode *inode1, struct inode *inode2,
int ret = 0;
if (inode1 == NULL) {
ext4_error(inode2->i_sb, function,
__ext4_error(inode2->i_sb, function,
"Both inodes should not be NULL: "
"inode1 NULL inode2 %lu", inode2->i_ino);
ret = -EIO;
} else if (inode2 == NULL) {
ext4_error(inode1->i_sb, function,
__ext4_error(inode1->i_sb, function,
"Both inodes should not be NULL: "
"inode1 %lu inode2 NULL", inode1->i_ino);
ret = -EIO;
......@@ -252,6 +252,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
}
o_start->ee_len = start_ext->ee_len;
eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (start_ext->ee_len && new_ext->ee_len &&
......@@ -262,6 +263,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
* orig |------------------------------|
*/
o_start->ee_len = start_ext->ee_len;
eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (!start_ext->ee_len && new_ext->ee_len &&
......@@ -475,7 +477,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
struct ext4_extent new_ext, start_ext, end_ext;
ext4_lblk_t new_ext_end;
ext4_fsblk_t new_phys_end;
int oext_alen, new_ext_alen, end_ext_alen;
int depth = ext_depth(orig_inode);
int ret;
......@@ -489,7 +490,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
new_ext.ee_len = dext->ee_len;
new_ext_alen = ext4_ext_get_actual_len(&new_ext);
new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1;
/*
* Case: original extent is first
......@@ -502,6 +502,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
le32_to_cpu(oext->ee_block) + oext_alen) {
start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
le32_to_cpu(oext->ee_block));
start_ext.ee_block = oext->ee_block;
copy_extent_status(oext, &start_ext);
} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
prev_ext = oext - 1;
......@@ -515,6 +516,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
start_ext.ee_len = cpu_to_le16(
ext4_ext_get_actual_len(prev_ext) +
new_ext_alen);
start_ext.ee_block = oext->ee_block;
copy_extent_status(prev_ext, &start_ext);
new_ext.ee_len = 0;
}
......@@ -526,7 +528,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
* new_ext |-------|
*/
if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
ext4_error(orig_inode->i_sb, __func__,
ext4_error(orig_inode->i_sb,
"new_ext_end(%u) should be less than or equal to "
"oext->ee_block(%u) + oext_alen(%d) - 1",
new_ext_end, le32_to_cpu(oext->ee_block),
......@@ -689,12 +691,12 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
while (1) {
/* The extent for donor must be found. */
if (!dext) {
ext4_error(donor_inode->i_sb, __func__,
ext4_error(donor_inode->i_sb,
"The extent for donor must be found");
*err = -EIO;
goto out;
} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
ext4_error(donor_inode->i_sb, __func__,
ext4_error(donor_inode->i_sb,
"Donor offset(%u) and the first block of donor "
"extent(%u) should be equal",
donor_off,
......@@ -928,7 +930,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
}
/**
* mext_check_argumants - Check whether move extent can be done
* mext_check_arguments - Check whether move extent can be done
*
* @orig_inode: original inode
* @donor_inode: donor inode
......@@ -949,14 +951,6 @@ mext_check_arguments(struct inode *orig_inode,
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;
/* Regular file check */
if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
ext4_debug("ext4 move extent: The argument files should be "
"regular file [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
ext4_debug("ext4 move extent: suid or sgid is set"
" to donor file [ino:orig %lu, donor %lu]\n",
......@@ -1204,6 +1198,14 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
return -EINVAL;
}
/* Regular file check */
if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
ext4_debug("ext4 move extent: The argument files should be "
"regular file [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
/* Protect orig and donor inodes against a truncate */
ret1 = mext_inode_double_lock(orig_inode, donor_inode);
if (ret1 < 0)
......@@ -1351,7 +1353,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
if (ret1 < 0)
break;
if (*moved_len > len) {
ext4_error(orig_inode->i_sb, __func__,
ext4_error(orig_inode->i_sb,
"We replaced blocks too much! "
"sum of replaced: %llu requested: %llu",
*moved_len, len);
......
......@@ -383,8 +383,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
if (root->info.hash_version != DX_HASH_TEA &&
root->info.hash_version != DX_HASH_HALF_MD4 &&
root->info.hash_version != DX_HASH_LEGACY) {
ext4_warning(dir->i_sb, __func__,
"Unrecognised inode hash code %d",
ext4_warning(dir->i_sb, "Unrecognised inode hash code %d",
root->info.hash_version);
brelse(bh);
*err = ERR_BAD_DX_DIR;
......@@ -399,8 +398,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
hash = hinfo->hash;
if (root->info.unused_flags & 1) {
ext4_warning(dir->i_sb, __func__,
"Unimplemented inode hash flags: %#06x",
ext4_warning(dir->i_sb, "Unimplemented inode hash flags: %#06x",
root->info.unused_flags);
brelse(bh);
*err = ERR_BAD_DX_DIR;
......@@ -408,8 +406,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
}
if ((indirect = root->info.indirect_levels) > 1) {
ext4_warning(dir->i_sb, __func__,
"Unimplemented inode hash depth: %#06x",
ext4_warning(dir->i_sb, "Unimplemented inode hash depth: %#06x",
root->info.indirect_levels);
brelse(bh);
*err = ERR_BAD_DX_DIR;
......@@ -421,8 +418,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
if (dx_get_limit(entries) != dx_root_limit(dir,
root->info.info_length)) {
ext4_warning(dir->i_sb, __func__,
"dx entry: limit != root limit");
ext4_warning(dir->i_sb, "dx entry: limit != root limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
goto fail;
......@@ -433,7 +429,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
{
count = dx_get_count(entries);
if (!count || count > dx_get_limit(entries)) {
ext4_warning(dir->i_sb, __func__,
ext4_warning(dir->i_sb,
"dx entry: no count or count > limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
......@@ -478,7 +474,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
goto fail2;
at = entries = ((struct dx_node *) bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit (dir)) {
ext4_warning(dir->i_sb, __func__,
ext4_warning(dir->i_sb,
"dx entry: limit != node limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
......@@ -494,7 +490,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
}
fail:
if (*err == ERR_BAD_DX_DIR)
ext4_warning(dir->i_sb, __func__,
ext4_warning(dir->i_sb,
"Corrupt dir inode %ld, running e2fsck is "
"recommended.", dir->i_ino);
return NULL;
......@@ -947,9 +943,8 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
/* read error, skip block & hope for the best */
ext4_error(sb, __func__, "reading directory #%lu "
"offset %lu", dir->i_ino,
(unsigned long)block);
ext4_error(sb, "reading directory #%lu offset %lu",
dir->i_ino, (unsigned long)block);
brelse(bh);
goto next;
}
......@@ -1041,7 +1036,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
retval = ext4_htree_next_block(dir, hash, frame,
frames, NULL);
if (retval < 0) {
ext4_warning(sb, __func__,
ext4_warning(sb,
"error reading index page in directory #%lu",
dir->i_ino);
*err = retval;
......@@ -1071,14 +1066,13 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
__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: %u", ino);
ext4_error(dir->i_sb, "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
inode = ext4_iget(dir->i_sb, ino);
if (unlikely(IS_ERR(inode))) {
if (PTR_ERR(inode) == -ESTALE) {
ext4_error(dir->i_sb, __func__,
ext4_error(dir->i_sb,
"deleted inode referenced: %u",
ino);
return ERR_PTR(-EIO);
......@@ -1110,7 +1104,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
brelse(bh);
if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
ext4_error(child->d_inode->i_sb, "ext4_get_parent",
ext4_error(child->d_inode->i_sb,
"bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
......@@ -1410,7 +1404,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
de = (struct ext4_dir_entry_2 *)((char *)fde +
ext4_rec_len_from_disk(fde->rec_len, blocksize));
if ((char *) de >= (((char *) root) + blocksize)) {
ext4_error(dir->i_sb, __func__,
ext4_error(dir->i_sb,
"invalid rec_len for '..' in inode %lu",
dir->i_ino);
brelse(bh);
......@@ -1575,8 +1569,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (levels && (dx_get_count(frames->entries) ==
dx_get_limit(frames->entries))) {
ext4_warning(sb, __func__,
"Directory index full!");
ext4_warning(sb, "Directory index full!");
err = -ENOSPC;
goto cleanup;
}
......@@ -1916,11 +1909,11 @@ static int empty_dir(struct inode *inode)
if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
!(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
if (err)
ext4_error(inode->i_sb, __func__,
ext4_error(inode->i_sb,
"error %d reading directory #%lu offset 0",
err, inode->i_ino);
else
ext4_warning(inode->i_sb, __func__,
ext4_warning(inode->i_sb,
"bad directory (dir #%lu) - no data block",
inode->i_ino);
return 1;
......@@ -1931,7 +1924,7 @@ static int empty_dir(struct inode *inode)
!le32_to_cpu(de1->inode) ||
strcmp(".", de->name) ||
strcmp("..", de1->name)) {
ext4_warning(inode->i_sb, "empty_dir",
ext4_warning(inode->i_sb,
"bad directory (dir #%lu) - no `.' or `..'",
inode->i_ino);
brelse(bh);
......@@ -1949,7 +1942,7 @@ static int empty_dir(struct inode *inode)
offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
if (!bh) {
if (err)
ext4_error(sb, __func__,
ext4_error(sb,
"error %d reading directory"
" #%lu offset %u",
err, inode->i_ino, offset);
......@@ -2020,11 +2013,18 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_unlock;
/*
* Due to previous errors inode may be already a part of on-disk
* orphan list. If so skip on-disk list modification.
*/
if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
(le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
goto mem_insert;
/* 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_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
......@@ -2037,6 +2037,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
*
* This is safe: on error we're going to ignore the orphan list
* anyway on the next recovery. */
mem_insert:
if (!err)
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
......@@ -2096,7 +2097,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
......@@ -2163,7 +2164,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
if (retval)
goto end_rmdir;
if (!EXT4_DIR_LINK_EMPTY(inode))
ext4_warning(inode->i_sb, "ext4_rmdir",
ext4_warning(inode->i_sb,
"empty directory has too many links (%d)",
inode->i_nlink);
inode->i_version++;
......@@ -2215,7 +2216,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
goto end_unlink;
if (!inode->i_nlink) {
ext4_warning(inode->i_sb, "ext4_unlink",
ext4_warning(inode->i_sb,
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
inode->i_nlink = 1;
......@@ -2462,7 +2463,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
if (retval) {
ext4_warning(old_dir->i_sb, "ext4_rename",
ext4_warning(old_dir->i_sb,
"Deleting old file (%lu), %d, error=%d",
old_dir->i_ino, old_dir->i_nlink, retval);
}
......
This diff is collapsed.
This diff is collapsed.
......@@ -227,7 +227,8 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(bh)) {
bad_block: ext4_error(inode->i_sb, __func__,
bad_block:
ext4_error(inode->i_sb,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
error = -EIO;
......@@ -267,7 +268,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
void *end;
int error;
if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return -ENODATA;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
......@@ -371,7 +372,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(bh)) {
ext4_error(inode->i_sb, __func__,
ext4_error(inode->i_sb,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
error = -EIO;
......@@ -396,7 +397,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
void *end;
int error;
if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return 0;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
......@@ -665,9 +666,8 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
atomic_read(&(bs->bh->b_count)),
le32_to_cpu(BHDR(bs->bh)->h_refcount));
if (ext4_xattr_check_block(bs->bh)) {
ext4_error(sb, __func__,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
ext4_error(sb, "inode %lu: bad block %llu",
inode->i_ino, EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
......@@ -880,9 +880,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
goto cleanup;
bad_block:
ext4_error(inode->i_sb, __func__,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
ext4_error(inode->i_sb, "inode %lu: bad block %llu",
inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
#undef header
......@@ -908,7 +907,7 @@ ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
is->s.base = is->s.first = IFIRST(header);
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
error = ext4_xattr_check_names(IFIRST(header), is->s.end);
if (error)
return error;
......@@ -940,10 +939,10 @@ ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
EXT4_I(inode)->i_state |= EXT4_STATE_XATTR;
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
} else {
header->h_magic = cpu_to_le32(0);
EXT4_I(inode)->i_state &= ~EXT4_STATE_XATTR;
ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
}
return 0;
}
......@@ -986,8 +985,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (strlen(name) > 255)
return -ERANGE;
down_write(&EXT4_I(inode)->xattr_sem);
no_expand = EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND;
EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
......@@ -997,10 +996,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (error)
goto cleanup;
if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
EXT4_I(inode)->i_state &= ~EXT4_STATE_NEW;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
}
error = ext4_xattr_ibody_find(inode, &i, &is);
......@@ -1052,7 +1051,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = ext4_current_time(inode);
if (!value)
EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
......@@ -1067,7 +1066,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
brelse(is.iloc.bh);
brelse(bs.bh);
if (no_expand == 0)
EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
......@@ -1195,9 +1194,8 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
if (!bh)
goto cleanup;
if (ext4_xattr_check_block(bh)) {
ext4_error(inode->i_sb, __func__,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
ext4_error(inode->i_sb, "inode %lu: bad block %llu",
inode->i_ino, EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
......@@ -1302,6 +1300,8 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
/* Remove the chosen entry from the inode */
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto cleanup;
entry = IFIRST(header);
if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
......@@ -1372,16 +1372,14 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
goto cleanup;
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh) {
ext4_error(inode->i_sb, __func__,
"inode %lu: block %llu read error", inode->i_ino,
EXT4_I(inode)->i_file_acl);
ext4_error(inode->i_sb, "inode %lu: block %llu read error",
inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
}
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1)) {
ext4_error(inode->i_sb, __func__,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
ext4_error(inode->i_sb, "inode %lu: bad block %llu",
inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
}
ext4_xattr_release_block(handle, inode, bh);
......@@ -1506,7 +1504,7 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
}
bh = sb_bread(inode->i_sb, ce->e_block);
if (!bh) {
ext4_error(inode->i_sb, __func__,
ext4_error(inode->i_sb,
"inode %lu: block %lu read error",
inode->i_ino, (unsigned long) ce->e_block);
} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
......
......@@ -507,6 +507,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
if (blocknr < journal->j_tail)
freed = freed + journal->j_last - journal->j_first;
trace_jbd2_cleanup_journal_tail(journal, first_tid, blocknr, freed);
jbd_debug(1,
"Cleaning journal tail from %d to %d (offset %lu), "
"freeing %lu\n",
......
......@@ -883,8 +883,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
spin_unlock(&journal->j_list_lock);
bh = jh2bh(jh);
jbd_lock_bh_state(bh);
J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
jh->b_transaction == journal->j_running_transaction);
J_ASSERT_JH(jh, jh->b_transaction == commit_transaction);
/*
* If there is undo-protected committed data against
......@@ -930,12 +929,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* A buffer which has been freed while still being
* journaled by a previous transaction may end up still
* being dirty here, but we want to avoid writing back
* that buffer in the future now that the last use has
* been committed. That's not only a performance gain,
* it also stops aliasing problems if the buffer is left
* behind for writeback and gets reallocated for another
* that buffer in the future after the "add to orphan"
* operation been committed, That's not only a performance
* gain, it also stops aliasing problems if the buffer is
* left behind for writeback and gets reallocated for another
* use in a different page. */
if (buffer_freed(bh)) {
if (buffer_freed(bh) && !jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
}
......
......@@ -39,6 +39,8 @@
#include <linux/seq_file.h>
#include <linux/math64.h>
#include <linux/hash.h>
#include <linux/log2.h>
#include <linux/vmalloc.h>
#define CREATE_TRACE_POINTS
#include <trace/events/jbd2.h>
......@@ -93,6 +95,7 @@ EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);
/*
* Helper function used to manage commit timeouts
......@@ -1248,6 +1251,13 @@ int jbd2_journal_load(journal_t *journal)
}
}
/*
* Create a slab for this blocksize
*/
err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize));
if (err)
return err;
/* Let the recovery code check whether it needs to recover any
* data from the journal. */
if (jbd2_journal_recover(journal))
......@@ -1806,6 +1816,127 @@ size_t journal_tag_bytes(journal_t *journal)
return JBD2_TAG_SIZE32;
}
/*
* JBD memory management
*
* These functions are used to allocate block-sized chunks of memory
* used for making copies of buffer_head data. Very often it will be
* page-sized chunks of data, but sometimes it will be in
* sub-page-size chunks. (For example, 16k pages on Power systems
* with a 4k block file system.) For blocks smaller than a page, we
* use a SLAB allocator. There are slab caches for each block size,
* which are allocated at mount time, if necessary, and we only free
* (all of) the slab caches when/if the jbd2 module is unloaded. For
* this reason we don't need to a mutex to protect access to
* jbd2_slab[] allocating or releasing memory; only in
* jbd2_journal_create_slab().
*/
#define JBD2_MAX_SLABS 8
static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS];
static DECLARE_MUTEX(jbd2_slab_create_sem);
static const char *jbd2_slab_names[JBD2_MAX_SLABS] = {
"jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k",
"jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k"
};
static void jbd2_journal_destroy_slabs(void)
{
int i;
for (i = 0; i < JBD2_MAX_SLABS; i++) {
if (jbd2_slab[i])
kmem_cache_destroy(jbd2_slab[i]);
jbd2_slab[i] = NULL;
}
}
static int jbd2_journal_create_slab(size_t size)
{
int i = order_base_2(size) - 10;
size_t slab_size;
if (size == PAGE_SIZE)
return 0;
if (i >= JBD2_MAX_SLABS)
return -EINVAL;
if (unlikely(i < 0))
i = 0;
down(&jbd2_slab_create_sem);
if (jbd2_slab[i]) {
up(&jbd2_slab_create_sem);
return 0; /* Already created */
}
slab_size = 1 << (i+10);
jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size,
slab_size, 0, NULL);
up(&jbd2_slab_create_sem);
if (!jbd2_slab[i]) {
printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n");
return -ENOMEM;
}
return 0;
}
static struct kmem_cache *get_slab(size_t size)
{
int i = order_base_2(size) - 10;
BUG_ON(i >= JBD2_MAX_SLABS);
if (unlikely(i < 0))
i = 0;
BUG_ON(jbd2_slab[i] == 0);
return jbd2_slab[i];
}
void *jbd2_alloc(size_t size, gfp_t flags)
{
void *ptr;
BUG_ON(size & (size-1)); /* Must be a power of 2 */
flags |= __GFP_REPEAT;
if (size == PAGE_SIZE)
ptr = (void *)__get_free_pages(flags, 0);
else if (size > PAGE_SIZE) {
int order = get_order(size);
if (order < 3)
ptr = (void *)__get_free_pages(flags, order);
else
ptr = vmalloc(size);
} else
ptr = kmem_cache_alloc(get_slab(size), flags);
/* Check alignment; SLUB has gotten this wrong in the past,
* and this can lead to user data corruption! */
BUG_ON(((unsigned long) ptr) & (size-1));
return ptr;
}
void jbd2_free(void *ptr, size_t size)
{
if (size == PAGE_SIZE) {
free_pages((unsigned long)ptr, 0);
return;
}
if (size > PAGE_SIZE) {
int order = get_order(size);
if (order < 3)
free_pages((unsigned long)ptr, order);
else
vfree(ptr);
return;
}
kmem_cache_free(get_slab(size), ptr);
};
/*
* Journal_head storage management
*/
......@@ -2204,6 +2335,7 @@ static void jbd2_journal_destroy_caches(void)
jbd2_journal_destroy_revoke_caches();
jbd2_journal_destroy_jbd2_journal_head_cache();
jbd2_journal_destroy_handle_cache();
jbd2_journal_destroy_slabs();
}
static int __init journal_init(void)
......
......@@ -1727,6 +1727,21 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
if (!jh)
goto zap_buffer_no_jh;
/*
* We cannot remove the buffer from checkpoint lists until the
* transaction adding inode to orphan list (let's call it T)
* is committed. Otherwise if the transaction changing the
* buffer would be cleaned from the journal before T is
* committed, a crash will cause that the correct contents of
* the buffer will be lost. On the other hand we have to
* clear the buffer dirty bit at latest at the moment when the
* transaction marking the buffer as freed in the filesystem
* structures is committed because from that moment on the
* buffer can be reallocated and used by a different page.
* Since the block hasn't been freed yet but the inode has
* already been added to orphan list, it is safe for us to add
* the buffer to BJ_Forget list of the newest transaction.
*/
transaction = jh->b_transaction;
if (transaction == NULL) {
/* First case: not on any transaction. If it
......@@ -1783,16 +1798,15 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
} else if (transaction == journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "on committing transaction");
/*
* If it is committing, we simply cannot touch it. We
* can remove it's next_transaction pointer from the
* running transaction if that is set, but nothing
* else. */
* The buffer is committing, we simply cannot touch
* it. So we just set j_next_transaction to the
* running transaction (if there is one) and mark
* buffer as freed so that commit code knows it should
* clear dirty bits when it is done with the buffer.
*/
set_buffer_freed(bh);
if (jh->b_next_transaction) {
J_ASSERT(jh->b_next_transaction ==
journal->j_running_transaction);
jh->b_next_transaction = NULL;
}
if (journal->j_running_transaction && buffer_jbddirty(bh))
jh->b_next_transaction = journal->j_running_transaction;
jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
......@@ -1969,7 +1983,7 @@ void jbd2_journal_file_buffer(struct journal_head *jh,
*/
void __jbd2_journal_refile_buffer(struct journal_head *jh)
{
int was_dirty;
int was_dirty, jlist;
struct buffer_head *bh = jh2bh(jh);
J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
......@@ -1991,8 +2005,13 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
__jbd2_journal_temp_unlink_buffer(jh);
jh->b_transaction = jh->b_next_transaction;
jh->b_next_transaction = NULL;
__jbd2_journal_file_buffer(jh, jh->b_transaction,
jh->b_modified ? BJ_Metadata : BJ_Reserved);
if (buffer_freed(bh))
jlist = BJ_Forget;
else if (jh->b_modified)
jlist = BJ_Metadata;
else
jlist = BJ_Reserved;
__jbd2_journal_file_buffer(jh, jh->b_transaction, jlist);
J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING);
if (was_dirty)
......
......@@ -69,15 +69,8 @@ extern u8 jbd2_journal_enable_debug;
#define jbd_debug(f, a...) /**/
#endif
static inline void *jbd2_alloc(size_t size, gfp_t flags)
{
return (void *)__get_free_pages(flags, get_order(size));
}
static inline void jbd2_free(void *ptr, size_t size)
{
free_pages((unsigned long)ptr, get_order(size));
};
extern void *jbd2_alloc(size_t size, gfp_t flags);
extern void jbd2_free(void *ptr, size_t size);
#define JBD2_MIN_JOURNAL_BLOCKS 1024
......
......@@ -874,6 +874,107 @@ TRACE_EVENT(ext4_forget,
__entry->mode, __entry->is_metadata, __entry->block)
);
TRACE_EVENT(ext4_da_update_reserve_space,
TP_PROTO(struct inode *inode, int used_blocks),
TP_ARGS(inode, used_blocks),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( umode_t, mode )
__field( __u64, i_blocks )
__field( int, used_blocks )
__field( int, reserved_data_blocks )
__field( int, reserved_meta_blocks )
__field( int, allocated_meta_blocks )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->mode = inode->i_mode;
__entry->i_blocks = inode->i_blocks;
__entry->used_blocks = used_blocks;
__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
),
TP_printk("dev %s ino %lu mode 0%o i_blocks %llu used_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
__entry->mode, (unsigned long long) __entry->i_blocks,
__entry->used_blocks, __entry->reserved_data_blocks,
__entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
);
TRACE_EVENT(ext4_da_reserve_space,
TP_PROTO(struct inode *inode, int md_needed),
TP_ARGS(inode, md_needed),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( umode_t, mode )
__field( __u64, i_blocks )
__field( int, md_needed )
__field( int, reserved_data_blocks )
__field( int, reserved_meta_blocks )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->mode = inode->i_mode;
__entry->i_blocks = inode->i_blocks;
__entry->md_needed = md_needed;
__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
),
TP_printk("dev %s ino %lu mode 0%o i_blocks %llu md_needed %d reserved_data_blocks %d reserved_meta_blocks %d",
jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
__entry->mode, (unsigned long long) __entry->i_blocks,
__entry->md_needed, __entry->reserved_data_blocks,
__entry->reserved_meta_blocks)
);
TRACE_EVENT(ext4_da_release_space,
TP_PROTO(struct inode *inode, int freed_blocks),
TP_ARGS(inode, freed_blocks),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( umode_t, mode )
__field( __u64, i_blocks )
__field( int, freed_blocks )
__field( int, reserved_data_blocks )
__field( int, reserved_meta_blocks )
__field( int, allocated_meta_blocks )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->mode = inode->i_mode;
__entry->i_blocks = inode->i_blocks;
__entry->freed_blocks = freed_blocks;
__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
),
TP_printk("dev %s ino %lu mode 0%o i_blocks %llu freed_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
__entry->mode, (unsigned long long) __entry->i_blocks,
__entry->freed_blocks, __entry->reserved_data_blocks,
__entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
);
#endif /* _TRACE_EXT4_H */
/* This part must be outside protection */
......
......@@ -199,6 +199,34 @@ TRACE_EVENT(jbd2_checkpoint_stats,
__entry->forced_to_close, __entry->written, __entry->dropped)
);
TRACE_EVENT(jbd2_cleanup_journal_tail,
TP_PROTO(journal_t *journal, tid_t first_tid,
unsigned long block_nr, unsigned long freed),
TP_ARGS(journal, first_tid, block_nr, freed),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( tid_t, tail_sequence )
__field( tid_t, first_tid )
__field(unsigned long, block_nr )
__field(unsigned long, freed )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
__entry->tail_sequence = journal->j_tail_sequence;
__entry->first_tid = first_tid;
__entry->block_nr = block_nr;
__entry->freed = freed;
),
TP_printk("dev %s from %u to %u offset %lu freed %lu",
jbd2_dev_to_name(__entry->dev), __entry->tail_sequence,
__entry->first_tid, __entry->block_nr, __entry->freed)
);
#endif /* _TRACE_JBD2_H */
/* This part must be outside protection */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment