#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((inode), __func__, __LINE__, 0, (fmt), ## a)
+
+#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \
+ ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
+
+#define EXT4_ERROR_FILE(file, block, fmt, a...) \
+ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
+
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
/* data type for block group number */
typedef unsigned int ext4_group_t;
+/*
+ * 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
+ */
/* prefer goal again. length */
#define EXT4_MB_HINT_MERGE 0x0001
};
/*
+ * 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
+ */
+struct mpage_da_data {
+ struct inode *inode;
+ sector_t b_blocknr; /* start block number of extent */
+ size_t b_size; /* size of extent */
+ unsigned long b_state; /* state of the extent */
+ unsigned long first_page, next_page; /* extent of pages */
+ struct writeback_control *wbc;
+ int io_done;
+ int pages_written;
+ int retval;
+};
+
+/*
+ * Flags for ext4_io_end->flags
+ */
+#define EXT4_IO_END_UNWRITTEN 0x0001
+#define EXT4_IO_END_ERROR 0x0002
+
+struct ext4_io_page {
+ struct page *p_page;
+ atomic_t p_count;
+};
+
+#define MAX_IO_PAGES 128
+
+typedef struct ext4_io_end {
+ struct list_head list; /* per-file finished IO list */
+ struct inode *inode; /* file being written to */
+ unsigned int flag; /* unwritten or not */
+ 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 */
+ struct kiocb *iocb; /* iocb struct for AIO */
+ int result; /* error value for AIO */
+ int num_io_pages;
+ struct ext4_io_page *pages[MAX_IO_PAGES];
+} ext4_io_end_t;
+
+struct ext4_io_submit {
+ int io_op;
+ struct bio *io_bio;
+ ext4_io_end_t *io_end;
+ struct ext4_io_page *io_page;
+ sector_t io_next_block;
+};
+
+/*
* Special inodes numbers
*/
#define EXT4_BAD_INO 1 /* Bad blocks inode */
#define EXT4_MIN_BLOCK_SIZE 1024
#define EXT4_MAX_BLOCK_SIZE 65536
#define EXT4_MIN_BLOCK_LOG_SIZE 10
+#define EXT4_MAX_BLOCK_LOG_SIZE 16
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
#else
#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_EXT_MIGRATE 0x00100000 /* Inode is migrating */
+#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 */
+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;
};
/*
- * Flags used by ext4_get_blocks()
+ * Flags used by ext4_map_blocks()
*/
/* Allocate any needed blocks and/or convert an unitialized
extent to be an initialized ext4 */
#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
- /* Call ext4_da_update_reserve_space() after successfully
- allocating the blocks */
-#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008
+ /* 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_PRE_IO 0x0008
+#define EXT4_GET_BLOCKS_CONVERT 0x0010
+#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)
+/*
+ * 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
-
-
-/*
- * Mount options
- */
-struct ext4_mount_options {
- unsigned long s_mount_opt;
- 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];
#endif
-};
+
+/* Max physical block we can address w/o extents */
+#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
/*
* Structure of an inode on the disk
__u64 len; /* block length to be moved */
__u64 moved_len; /* moved block length */
};
-#define MAX_DEFRAG_SIZE ((1UL<<31) - 1)
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
- time->tv_sec >> 32 : 0) |
- ((time->tv_nsec << 2) & EXT4_NSEC_MASK));
+ (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
+ ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
}
static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
if (sizeof(time->tv_sec) > 4)
time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
<< 32;
- time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> 2;
+ time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
}
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
ext4_decode_extra_time(&(inode)->xtime, \
raw_inode->xtime ## _extra); \
+ else \
+ (inode)->xtime.tv_nsec = 0; \
} while (0)
#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
+ else \
+ (einode)->xtime.tv_nsec = 0; \
} while (0)
#define i_disk_version osd1.linux1.l_i_version
/*
* storage for cached extent
+ * If ec_len == 0, then the cache is invalid.
+ * If ec_start == 0, then the cache represents a gap (null mapping)
*/
struct ext4_ext_cache {
ext4_fsblk_t ec_start;
ext4_lblk_t ec_block;
__u32 ec_len; /* must be 32bit to return holes */
- __u32 ec_type;
};
/*
*/
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 */
+ ext4_lblk_t i_dir_start_lookup;
+#if (BITS_PER_LONG < 64)
+ unsigned long i_state_flags; /* Dynamic state flags */
+#endif
+ unsigned long i_flags;
- ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
/*
* Extended attributes can be read independently of the main file
*/
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
- struct jbd2_inode jinode;
+ struct jbd2_inode *jinode;
struct ext4_ext_cache i_cached_extent;
/*
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
- unsigned short i_delalloc_reserved_flag;
+ ext4_lblk_t i_da_metadata_calc_last_lblock;
+ int i_da_metadata_calc_len;
/* on-disk additional length */
__u16 i_extra_isize;
+#ifdef CONFIG_QUOTA
+ /* quota space reservation, managed internally by quota code */
+ qsize_t i_reserved_quota;
+#endif
+
+ /* completed IOs that might need unwritten extents handling */
+ struct list_head i_completed_io_list;
+ spinlock_t i_completed_io_lock;
+ atomic_t i_ioend_count; /* Number of outstanding io_end structs */
+ /* current io_end structure for async DIO write*/
+ ext4_io_end_t *cur_aio_dio;
+ atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
+
spinlock_t i_block_reservation_lock;
+
+ /*
+ * Transactions that contain inode's metadata needed to complete
+ * fsync and fdatasync, respectively.
+ */
+ tid_t i_sync_tid;
+ tid_t i_datasync_tid;
};
/*
#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */
#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */
-#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */
#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 */
+#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
+#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
+#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
-#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt
-#define set_opt(o, opt) o |= EXT4_MOUNT_##opt
+#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
+ ~EXT4_MOUNT_##opt
+#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
+ EXT4_MOUNT_##opt
#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \
EXT4_MOUNT_##opt)
+#define clear_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 &= \
+ ~EXT4_MOUNT2_##opt
+#define set_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 |= \
+ EXT4_MOUNT2_##opt
+#define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \
+ EXT4_MOUNT2_##opt)
+
#define ext4_set_bit ext2_set_bit
#define ext4_set_bit_atomic ext2_set_bit_atomic
#define ext4_clear_bit ext2_clear_bit
__le32 s_last_orphan; /* start of list of inodes to delete */
__le32 s_hash_seed[4]; /* HTREE hash seed */
__u8 s_def_hash_version; /* Default hash version to use */
- __u8 s_reserved_char_pad;
+ __u8 s_jnl_backup_type;
__le16 s_desc_size; /* size of group descriptor */
/*100*/ __le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
__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;
+ __u8 s_reserved_char_pad;
__le16 s_reserved_pad;
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
- __u32 s_reserved[160]; /* Padding to the end of the block */
+ __le32 s_snapshot_inum; /* Inode number of active snapshot */
+ __le32 s_snapshot_id; /* sequential ID of active snapshot */
+ __le64 s_snapshot_r_blocks_count; /* reserved blocks for active
+ snapshot's future use */
+ __le32 s_snapshot_list; /* inode number of the head of the
+ on-disk snapshot list */
+#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
+ __le32 s_error_count; /* number of fs errors */
+ __le32 s_first_error_time; /* first time an error happened */
+ __le32 s_first_error_ino; /* inode involved in first error */
+ __le64 s_first_error_block; /* block involved of first error */
+ __u8 s_first_error_func[32]; /* function where the error happened */
+ __le32 s_first_error_line; /* line number where error happened */
+ __le32 s_last_error_time; /* most recent time of an error */
+ __le32 s_last_error_ino; /* inode involved in last error */
+ __le32 s_last_error_line; /* line number where error happened */
+ __le64 s_last_error_block; /* block involved of last error */
+ __u8 s_last_error_func[32]; /* function where the error happened */
+#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
+ __u8 s_mount_opts[64];
+ __le32 s_reserved[112]; /* Padding to the end of the block */
};
+#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
+
#ifdef __KERNEL__
/*
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
ext4_group_t s_groups_count; /* Number of groups in the fs */
+ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
struct buffer_head **s_group_desc;
unsigned int s_mount_opt;
+ unsigned int s_mount_opt2;
unsigned int s_mount_flags;
ext4_fsblk_t s_sb_block;
uid_t s_resuid;
struct completion s_kobj_unregister;
/* Journaling */
- struct inode *s_journal_inode;
struct journal_s *s_journal;
struct list_head s_orphan;
struct mutex s_orphan_lock;
/* for buddy allocator */
struct ext4_group_info ***s_group_info;
struct inode *s_buddy_cache;
- long s_blocks_reserved;
- spinlock_t s_reserve_lock;
spinlock_t s_md_lock;
- tid_t s_last_transaction;
unsigned short *s_mb_offsets;
unsigned int *s_mb_maxs;
unsigned int s_mb_stats;
unsigned int s_mb_order2_reqs;
unsigned int s_mb_group_prealloc;
+ unsigned int s_max_writeback_mb_bump;
/* where last allocation was done - for stream allocation */
unsigned long s_mb_last_group;
unsigned long s_mb_last_start;
- /* history to debug policy */
- struct ext4_mb_history *s_mb_history;
- int s_mb_history_cur;
- int s_mb_history_max;
- int s_mb_history_num;
- spinlock_t s_mb_history_lock;
- int s_mb_history_filter;
-
/* stats for buddy allocator */
- spinlock_t s_mb_pa_lock;
atomic_t s_bal_reqs; /* number of reqs with len > 1 */
atomic_t s_bal_success; /* we found long enough chunks */
atomic_t s_bal_allocated; /* in blocks */
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;
unsigned int s_log_groups_per_flex;
struct flex_groups *s_flex_groups;
+
+ /* workqueue for dio unwritten */
+ struct workqueue_struct *dio_unwritten_wq;
+
+ /* timer for periodic error stats printing */
+ struct timer_list s_err_report;
+
+ /* Lazy inode table initialization info */
+ struct ext4_li_request *s_li_request;
+ /* Wait multiplier for lazy initialization thread */
+ unsigned int s_li_wait_mult;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
(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 */
+ EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */
+};
+
+#define EXT4_INODE_BIT_FNS(name, field, offset) \
+static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
+{ \
+ return test_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
+{ \
+ set_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{ \
+ clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
+}
+
+EXT4_INODE_BIT_FNS(flag, flags, 0)
+#if (BITS_PER_LONG < 64)
+EXT4_INODE_BIT_FNS(state, state_flags, 0)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+ (ei)->i_state_flags = 0;
+}
+#else
+EXT4_INODE_BIT_FNS(state, flags, 32)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+ /* We depend on the fact that callers will set i_flags */
+}
+#endif
#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 EXT4_DEFM_JMODE_DATA 0x0020
#define EXT4_DEFM_JMODE_ORDERED 0x0040
#define EXT4_DEFM_JMODE_WBACK 0x0060
+#define EXT4_DEFM_NOBARRIER 0x0100
+#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
+#define EXT4_DEFM_DISCARD 0x0400
+#define EXT4_DEFM_NODELALLOC 0x0800
/*
* Default journal batch times
#define EXT4_MAX_REC_LEN ((1<<16)-1)
/*
+ * If we ever get support for fs block sizes > page_size, we'll need
+ * to remove the #if statements in the next two functions...
+ */
+static inline unsigned int
+ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
+{
+ unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+ if (len == EXT4_MAX_REC_LEN || len == 0)
+ return blocksize;
+ return (len & 65532) | ((len & 3) << 16);
+#else
+ return len;
+#endif
+}
+
+static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
+{
+ if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
+ BUG();
+#if (PAGE_CACHE_SIZE >= 65536)
+ if (len < 65536)
+ return cpu_to_le16(len);
+ if (len == blocksize) {
+ if (blocksize == 65536)
+ return cpu_to_le16(EXT4_MAX_REC_LEN);
+ else
+ return cpu_to_le16(0);
+ }
+ return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
+#else
+ return cpu_to_le16(len);
+#endif
+}
+
+/*
* Hash Tree Directory indexing
* (c) Daniel Phillips, 2001
*/
#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)
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
-extern struct proc_dir_entry *ext4_proc_root;
+/*
+ * Timeout and state flag for lazy initialization inode thread.
+ */
+#define EXT4_DEF_LI_WAIT_MULT 10
+#define EXT4_DEF_LI_MAX_START_DELAY 5
+#define EXT4_LAZYINIT_QUIT 0x0001
+#define EXT4_LAZYINIT_RUNNING 0x0002
+
+/*
+ * Lazy inode table initialization info
+ */
+struct ext4_lazy_init {
+ unsigned long li_state;
+ wait_queue_head_t li_wait_task;
+ struct task_struct *li_task;
+ struct list_head li_request_list;
+ struct mutex li_list_mtx;
+};
+
+struct ext4_li_request {
+ struct super_block *lr_super;
+ struct ext4_sb_info *lr_sbi;
+ ext4_group_t lr_next_group;
+ struct list_head lr_request;
+ unsigned long lr_next_sched;
+ unsigned long lr_timeout;
+};
+
+struct ext4_features {
+ struct kobject f_kobj;
+ struct completion f_kobj_unregister;
+};
/*
* Function prototypes
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern 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_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 *);
ext4_init_block_bitmap(sb, NULL, group, desc)
/* dir.c */
-extern int ext4_check_dir_entry(const char *, struct inode *,
- struct ext4_dir_entry_2 *,
- struct buffer_head *, unsigned int);
+extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
+ struct file *,
+ struct ext4_dir_entry_2 *,
+ struct buffer_head *, unsigned int);
+#define ext4_check_dir_entry(dir, filp, de, bh, offset) \
+ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
+ (de), (bh), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
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);
+extern int ext4_flush_completed_IO(struct inode *);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
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 ext4_init_inode_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern int ext4_init_inode_table(struct super_block *sb,
+ ext4_group_t group, int barrier);
/* mballoc.c */
extern long ext4_mb_stats;
struct ext4_allocation_request *, int *);
extern int ext4_mb_reserve_blocks(struct super_block *, int);
extern void ext4_discard_preallocations(struct inode *);
-extern int __init init_ext4_mballoc(void);
-extern void exit_ext4_mballoc(void);
-extern void ext4_mb_free_blocks(handle_t *, struct inode *,
- ext4_fsblk_t, unsigned long, int, unsigned long *);
+extern int __init ext4_init_mballoc(void);
+extern void ext4_exit_mballoc(void);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags);
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);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+
/* inode.c */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t blocknr);
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
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);
-extern void ext4_delete_inode(struct inode *);
+extern void ext4_evict_inode(struct inode *);
+extern void ext4_clear_inode(struct inode *);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
-extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
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 qsize_t *ext4_get_reserved_space(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
extern int ext4_ext_migrate(struct inode *);
/* namei.c */
-extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize);
-extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize);
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void ext4_error(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void __ext4_std_error(struct super_block *, const char *, int);
-extern void ext4_abort(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
+extern void __ext4_error(struct super_block *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
+ __LINE__, ## message)
+extern void ext4_error_inode(struct inode *, const char *, unsigned int,
+ ext4_fsblk_t, const char *, ...)
+ __attribute__ ((format (printf, 5, 6)));
+extern void ext4_error_file(struct file *, const char *, unsigned int,
+ ext4_fsblk_t, const char *, ...)
+ __attribute__ ((format (printf, 5, 6)));
+extern void __ext4_std_error(struct super_block *, const char *,
+ unsigned int, int);
+extern void __ext4_abort(struct super_block *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
+ __LINE__, ## message)
+extern void __ext4_warning(struct super_block *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
+ __LINE__, ## 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,
- const char *, const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern void __ext4_grp_locked_error(const char *, unsigned int, \
+ struct super_block *, ext4_group_t, \
+ unsigned long, ext4_fsblk_t, \
+ const char *, ...)
+ __attribute__ ((format (printf, 7, 8)));
+#define ext4_grp_locked_error(sb, grp, message...) \
+ __ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
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);
#define ext4_std_error(sb, errno) \
do { \
if ((errno)) \
- __ext4_std_error((sb), __func__, (errno)); \
+ __ext4_std_error((sb), __func__, __LINE__, (errno)); \
} while (0)
#ifdef CONFIG_SMP
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;
+ 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;
#endif
struct rw_semaphore alloc_sem;
- unsigned short bb_counters[];
+ ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
+ * regions, index is order.
+ * bb_counters[3] = 5 means
+ * 5 free 8-block regions. */
};
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
spin_unlock(ext4_group_lock_ptr(sb, group));
}
+static inline void ext4_mark_super_dirty(struct super_block *sb)
+{
+ if (EXT4_SB(sb)->s_journal == NULL)
+ sb->s_dirt =1;
+}
+
/*
* Inodes and files operations
*/
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
+extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
-extern int __init init_ext4_system_zone(void);
-extern void exit_ext4_system_zone(void);
+extern int __init ext4_init_system_zone(void);
+extern void ext4_exit_system_zone(void);
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
ext4_fsblk_t start_blk,
unsigned int count);
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,
+extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
loff_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);
+extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
+ ssize_t len);
+extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
/* move_extent.c */
__u64 start_orig, __u64 start_donor,
__u64 len, __u64 *moved_len);
+/* page-io.c */
+extern int __init ext4_init_pageio(void);
+extern void ext4_exit_pageio(void);
+extern void ext4_ioend_wait(struct inode *);
+extern void ext4_free_io_end(ext4_io_end_t *io);
+extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern int ext4_end_io_nolock(ext4_io_end_t *io);
+extern void ext4_io_submit(struct ext4_io_submit *io);
+extern int ext4_bio_write_page(struct ext4_io_submit *io,
+ struct page *page,
+ int len,
+ struct writeback_control *wbc);
+
+/* 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
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
+#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ 37
+#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
projects / linux-flexiantxendom0-natty.git / blobdiff