#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif
/*
* The fourth extended filesystem constants/structures
#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;
typedef unsigned int ext4_group_t;
/*
- * Flags used in mballoc's allocation_context flags field.
+ * Flags used in mballoc's allocation_context flags field.
*
* Also used to show what's going on for debugging purposes when the
* flag field is exported via the traceport interface
unsigned int flags;
};
+/*
+ * Logical to physical block mapping, used by ext4_map_blocks()
+ *
+ * This structure is used to pass requests into ext4_map_blocks() as
+ * well as to store the information returned by ext4_map_blocks(). It
+ * takes less room on the stack than a struct buffer_head.
+ */
+#define EXT4_MAP_NEW (1 << BH_New)
+#define EXT4_MAP_MAPPED (1 << BH_Mapped)
+#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
+#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
+#define EXT4_MAP_UNINIT (1 << BH_Uninit)
+#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
+ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+ EXT4_MAP_UNINIT)
+
+struct ext4_map_blocks {
+ ext4_fsblk_t m_pblk;
+ ext4_lblk_t m_lblk;
+ unsigned int m_len;
+ unsigned int m_flags;
+};
+
/*
* For delayed allocation tracking
*/
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;
#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 |\
}
/*
- * Inode dynamic state flags
+ * Inode flags used for atomic set/get
*/
-#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*/
+enum {
+ EXT4_INODE_SECRM = 0, /* Secure deletion */
+ EXT4_INODE_UNRM = 1, /* Undelete */
+ EXT4_INODE_COMPR = 2, /* Compress file */
+ EXT4_INODE_SYNC = 3, /* Synchronous updates */
+ EXT4_INODE_IMMUTABLE = 4, /* Immutable file */
+ EXT4_INODE_APPEND = 5, /* writes to file may only append */
+ EXT4_INODE_NODUMP = 6, /* do not dump file */
+ EXT4_INODE_NOATIME = 7, /* do not update atime */
+/* Reserved for compression usage... */
+ EXT4_INODE_DIRTY = 8,
+ EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
+ EXT4_INODE_NOCOMPR = 10, /* Don't compress */
+ EXT4_INODE_ECOMPR = 11, /* Compression error */
+/* End compression flags --- maybe not all used */
+ EXT4_INODE_INDEX = 12, /* hash-indexed directory */
+ EXT4_INODE_IMAGIC = 13, /* AFS directory */
+ EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */
+ EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */
+ EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */
+ EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/
+ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */
+ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */
+ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
+ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
+ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
+};
+
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
+ printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
+ EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
+
+/*
+ * Since it's pretty easy to mix up bit numbers and hex values, and we
+ * can't do a compile-time test for ENUM values, we use a run-time
+ * test to make sure that EXT4_XXX_FL is consistent with respect to
+ * EXT4_INODE_XXX. If all is well the printk and BUG_ON will all drop
+ * out so it won't cost any extra space in the compiled kernel image.
+ * But it's important that these values are the same, since we are
+ * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
+ * must be consistent with the values of FS_XXX_FL defined in
+ * include/linux/fs.h and the on-disk values found in ext2, ext3, and
+ * ext4 filesystems, and of course the values defined in e2fsprogs.
+ *
+ * It's not paranoia if the Murphy's Law really *is* out to get you. :-)
+ */
+static inline void ext4_check_flag_values(void)
+{
+ CHECK_FLAG_VALUE(SECRM);
+ CHECK_FLAG_VALUE(UNRM);
+ CHECK_FLAG_VALUE(COMPR);
+ CHECK_FLAG_VALUE(SYNC);
+ CHECK_FLAG_VALUE(IMMUTABLE);
+ CHECK_FLAG_VALUE(APPEND);
+ CHECK_FLAG_VALUE(NODUMP);
+ CHECK_FLAG_VALUE(NOATIME);
+ CHECK_FLAG_VALUE(DIRTY);
+ CHECK_FLAG_VALUE(COMPRBLK);
+ CHECK_FLAG_VALUE(NOCOMPR);
+ CHECK_FLAG_VALUE(ECOMPR);
+ CHECK_FLAG_VALUE(INDEX);
+ CHECK_FLAG_VALUE(IMAGIC);
+ CHECK_FLAG_VALUE(JOURNAL_DATA);
+ CHECK_FLAG_VALUE(NOTAIL);
+ CHECK_FLAG_VALUE(DIRSYNC);
+ CHECK_FLAG_VALUE(TOPDIR);
+ CHECK_FLAG_VALUE(HUGE_FILE);
+ CHECK_FLAG_VALUE(EXTENTS);
+ CHECK_FLAG_VALUE(EA_INODE);
+ CHECK_FLAG_VALUE(EOFBLOCKS);
+ CHECK_FLAG_VALUE(RESERVED);
+}
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
__u16 unused;
};
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+struct compat_ext4_new_group_input {
+ u32 group;
+ compat_u64 block_bitmap;
+ compat_u64 inode_bitmap;
+ compat_u64 inode_table;
+ u32 blocks_count;
+ u16 reserved_blocks;
+ u16 unused;
+};
+#endif
+
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
__u32 group;
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path,
- so set the magic i_delalloc_reserve_flag after taking the
+ so set the magic i_delalloc_reserve_flag after taking the
inode allocation semaphore for */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* 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
#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12)
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
#ifdef CONFIG_JBD2_DEBUG
#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
+#endif
/*
*/
struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
- __u32 i_flags;
- ext4_fsblk_t i_file_acl;
__u32 i_dtime;
+ ext4_fsblk_t i_file_acl;
/*
* i_block_group is the number of the block group which contains
* 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 */
+ unsigned long i_flags;
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
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;
#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 */
atomic_t s_lock_busy;
/* locality groups */
- struct ext4_locality_group *s_locality_groups;
+ struct ext4_locality_group __percpu *s_locality_groups;
/* for write statistics */
unsigned long s_sectors_written_start;
(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*/
+ EXT4_STATE_NEWENTRY, /* File just added to dir */
+};
+
+#define EXT4_INODE_BIT_FNS(name, field) \
+static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
+{ \
+ return test_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
+{ \
+ set_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{ \
+ clear_bit(bit, &EXT4_I(inode)->i_##field); \
+}
+
+EXT4_INODE_BIT_FNS(flag, flags)
+EXT4_INODE_BIT_FNS(state, 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
#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| \
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
EXT4_FEATURE_COMPAT_DIR_INDEX) && \
- (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
+ ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
/* fsync.c */
-extern int ext4_sync_file(struct file *, struct dentry *, int);
+extern int ext4_sync_file(struct file *, int);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
struct buffer_head *bh_result, int create);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
-extern int ext4_write_inode(struct inode *, int);
+extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
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 */
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,
ext4_grpblk_t bb_first_free; /* first free block */
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
+ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
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 int max_blocks,
- struct buffer_head *bh_result, int flags);
+extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags);
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_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len);
+ ssize_t len);
+extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags);
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int flags);
__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
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 */