diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/Kconfig | 11 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 2 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 145 | ||||
-rw-r--r-- | fs/ext4/ext4_extents.h | 11 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 9 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 6 | ||||
-rw-r--r-- | fs/ext4/extents.c | 556 | ||||
-rw-r--r-- | fs/ext4/file.c | 2 | ||||
-rw-r--r-- | fs/ext4/fsync.c | 18 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 2 | ||||
-rw-r--r-- | fs/ext4/inode.c | 676 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 7 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 726 | ||||
-rw-r--r-- | fs/ext4/mballoc.h | 57 | ||||
-rw-r--r-- | fs/ext4/migrate.c | 24 | ||||
-rw-r--r-- | fs/ext4/move_extent.c | 354 | ||||
-rw-r--r-- | fs/ext4/namei.c | 25 | ||||
-rw-r--r-- | fs/ext4/resize.c | 7 | ||||
-rw-r--r-- | fs/ext4/super.c | 258 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 15 |
20 files changed, 1885 insertions, 1026 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 418b6f3b0ae8..d5c0ea2e8f2d 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -37,7 +37,7 @@ config EXT4DEV_COMPAT To enable backwards compatibility so that systems that are still expecting to mount ext4 filesystems using ext4dev, - chose Y here. This feature will go away by 2.6.31, so + choose Y here. This feature will go away by 2.6.31, so please arrange to get your userspace programs fixed! config EXT4_FS_XATTR @@ -77,3 +77,12 @@ config EXT4_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. + +config EXT4_DEBUG + bool "EXT4 debugging support" + depends on EXT4_FS + help + Enables run-time debugging support for the ext4 filesystem. + + If you select Y here, then you will be able to turn on debugging + with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug" diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e2126d70dff5..1d0418980f8d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -478,7 +478,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, * new bitmap information */ set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); - ext4_mb_update_group_info(grp, blocks_freed); + grp->bb_free += blocks_freed; up_write(&grp->alloc_sem); /* We dirtied the bitmap block */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9714db393efe..984ca0cb38c3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -65,29 +65,37 @@ typedef __u32 ext4_lblk_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 1 +#define EXT4_MB_HINT_MERGE 0x0001 /* blocks already reserved */ -#define EXT4_MB_HINT_RESERVED 2 +#define EXT4_MB_HINT_RESERVED 0x0002 /* metadata is being allocated */ -#define EXT4_MB_HINT_METADATA 4 +#define EXT4_MB_HINT_METADATA 0x0004 /* first blocks in the file */ -#define EXT4_MB_HINT_FIRST 8 +#define EXT4_MB_HINT_FIRST 0x0008 /* search for the best chunk */ -#define EXT4_MB_HINT_BEST 16 +#define EXT4_MB_HINT_BEST 0x0010 /* data is being allocated */ -#define EXT4_MB_HINT_DATA 32 +#define EXT4_MB_HINT_DATA 0x0020 /* don't preallocate (for tails) */ -#define EXT4_MB_HINT_NOPREALLOC 64 +#define EXT4_MB_HINT_NOPREALLOC 0x0040 /* allocate for locality group */ -#define EXT4_MB_HINT_GROUP_ALLOC 128 +#define EXT4_MB_HINT_GROUP_ALLOC 0x0080 /* allocate goal blocks or none */ -#define EXT4_MB_HINT_GOAL_ONLY 256 +#define EXT4_MB_HINT_GOAL_ONLY 0x0100 /* goal is meaningful */ -#define EXT4_MB_HINT_TRY_GOAL 512 +#define EXT4_MB_HINT_TRY_GOAL 0x0200 /* blocks already pre-reserved by delayed allocation */ -#define EXT4_MB_DELALLOC_RESERVED 1024 +#define EXT4_MB_DELALLOC_RESERVED 0x0400 +/* We are doing stream allocation */ +#define EXT4_MB_STREAM_ALLOC 0x0800 struct ext4_allocation_request { @@ -112,6 +120,31 @@ struct ext4_allocation_request { }; /* + * 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; +}; +#define DIO_AIO_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 work_struct work; /* data work queue */ +} ext4_io_end_t; + +/* * Special inodes numbers */ #define EXT4_BAD_INO 1 /* Bad blocks inode */ @@ -251,7 +284,6 @@ 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_EXT_MIGRATE 0x00100000 /* Inode is migrating */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ @@ -289,6 +321,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) #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 */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { @@ -330,7 +363,16 @@ struct ext4_new_group_data { /* 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_DIO 0x0010 +#define EXT4_GET_BLOCKS_CONVERT 0x0020 +#define EXT4_GET_BLOCKS_DIO_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\ + 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) /* * ioctl commands @@ -386,6 +428,9 @@ struct ext4_mount_options { #endif }; +/* Max physical block we can addres w/o extents */ +#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF + /* * Structure of an inode on the disk */ @@ -456,7 +501,6 @@ struct move_extent { __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) @@ -481,8 +525,8 @@ struct move_extent { 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) @@ -490,7 +534,7 @@ 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) \ @@ -653,6 +697,11 @@ struct ext4_inode_info { __u16 i_extra_isize; spinlock_t i_block_reservation_lock; + + /* completed async DIOs that might need unwritten extents handling */ + struct list_head i_aio_dio_complete_list; + /* current io_end structure for async DIO write*/ + ext4_io_end_t *cur_aio_dio; }; /* @@ -694,7 +743,6 @@ 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_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_DELALLOC 0x8000000 /* Delalloc support */ @@ -841,6 +889,7 @@ struct ext4_sb_info { 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 */ @@ -923,18 +972,11 @@ struct ext4_sb_info { 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 */ @@ -950,6 +992,7 @@ struct ext4_sb_info { atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; + atomic_t s_lock_busy; /* locality groups */ struct ext4_locality_group *s_locality_groups; @@ -960,6 +1003,9 @@ struct ext4_sb_info { unsigned int s_log_groups_per_flex; struct flex_groups *s_flex_groups; + + /* workqueue for dio unwritten */ + struct workqueue_struct *dio_unwritten_wq; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1340,8 +1386,6 @@ extern void ext4_mb_free_blocks(handle_t *, struct inode *, ext4_fsblk_t, unsigned long, int, unsigned long *); 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); @@ -1367,6 +1411,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern int ext4_can_truncate(struct inode *inode); extern void ext4_truncate(struct inode *); +extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks); extern void ext4_set_inode_flags(struct inode *); extern void ext4_get_inode_flags(struct ext4_inode_info *); extern int ext4_alloc_da_blocks(struct inode *inode); @@ -1378,7 +1423,7 @@ 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); /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); @@ -1575,15 +1620,18 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) 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 */ 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 @@ -1591,15 +1639,42 @@ struct ext4_group_info { #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +#define EXT4_MAX_CONTENTION 8 +#define EXT4_CONTENTION_THRESHOLD 2 + static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb, ext4_group_t group) { return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group); } +/* + * Returns true if the filesystem is busy enough that attempts to + * access the block group locks has run into contention. + */ +static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi) +{ + return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD); +} + static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { - spin_lock(ext4_group_lock_ptr(sb, group)); + spinlock_t *lock = ext4_group_lock_ptr(sb, group); + if (spin_trylock(lock)) + /* + * We're able to grab the lock right away, so drop the + * lock contention counter. + */ + atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0); + else { + /* + * The lock is busy, so bump the contention counter, + * and then wait on the spin lock. + */ + atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1, + EXT4_MAX_CONTENTION); + spin_lock(lock); + } } static inline void ext4_unlock_group(struct super_block *sb, @@ -1650,6 +1725,8 @@ 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); extern int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, unsigned int max_blocks, struct buffer_head *bh, int flags); diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 20a84105a10b..2ca686454e87 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -43,8 +43,7 @@ #define CHECK_BINSEARCH__ /* - * If EXT_DEBUG is defined you can use the 'extdebug' mount option - * to get lots of info about what's going on. + * Turn on EXT_DEBUG to get lots of info about extents operations. */ #define EXT_DEBUG__ #ifdef EXT_DEBUG @@ -138,6 +137,7 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_BREAK 1 #define EXT_REPEAT 2 +/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */ #define EXT_MAX_BLOCK 0xffffffff /* @@ -220,6 +220,11 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); } +static inline void ext4_ext_mark_initialized(struct ext4_extent *ext) +{ + ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext)); +} + extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks); extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex); extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *); @@ -235,7 +240,7 @@ extern int ext4_ext_try_to_merge(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *); extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *); -extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); +extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int); extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t, ext_prepare_callback, void *); extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index eb27fd0f2ee8..6a9409920dee 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -44,7 +44,7 @@ int __ext4_journal_forget(const char *where, handle_t *handle, handle, err); } else - brelse(bh); + bforget(bh); return err; } @@ -60,7 +60,7 @@ int __ext4_journal_revoke(const char *where, handle_t *handle, handle, err); } else - brelse(bh); + bforget(bh); return err; } @@ -89,7 +89,10 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle, ext4_journal_abort_handle(where, __func__, bh, handle, err); } else { - mark_buffer_dirty(bh); + if (inode && bh) + 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)) { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 139fb8cb87e4..a2865980342f 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -161,11 +161,13 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle, handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, handle_t *handle); -#define EXT4_NOJOURNAL_HANDLE ((handle_t *) 0x1) +#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) +/* Note: Do not use this for NULL handles. This is only to determine if + * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { - if (handle == EXT4_NOJOURNAL_HANDLE) + if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 73ebfb44ad75..10539e364283 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -93,7 +93,9 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } -static int ext4_ext_journal_restart(handle_t *handle, int needed) +static int ext4_ext_truncate_extend_restart(handle_t *handle, + struct inode *inode, + int needed) { int err; @@ -104,7 +106,14 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed) err = ext4_journal_extend(handle, needed); if (err <= 0) return err; - return ext4_journal_restart(handle, needed); + err = ext4_truncate_restart_trans(handle, inode, needed); + /* + * We have dropped i_data_sem so someone might have cached again + * an extent we are going to truncate. + */ + ext4_ext_invalidate_cache(inode); + + return err; } /* @@ -220,57 +229,65 @@ ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, return newblock; } -static int ext4_ext_space_block(struct inode *inode) +static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 6) - size = 6; + if (size > 6) + size = 6; #endif + } return size; } -static int ext4_ext_space_block_idx(struct inode *inode) +static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 5) - size = 5; + if (size > 5) + size = 5; #endif + } return size; } -static int ext4_ext_space_root(struct inode *inode) +static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 3) - size = 3; + if (size > 3) + size = 3; #endif + } return size; } -static int ext4_ext_space_root_idx(struct inode *inode) +static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 4) - size = 4; + if (size > 4) + size = 4; #endif + } return size; } @@ -284,9 +301,9 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks) int lcap, icap, rcap, leafs, idxs, num; int newextents = blocks; - rcap = ext4_ext_space_root_idx(inode); - lcap = ext4_ext_space_block(inode); - icap = ext4_ext_space_block_idx(inode); + rcap = ext4_ext_space_root_idx(inode, 0); + lcap = ext4_ext_space_block(inode, 0); + icap = ext4_ext_space_block_idx(inode, 0); /* number of new leaf blocks needed */ num = leafs = (newextents + lcap - 1) / lcap; @@ -311,14 +328,14 @@ ext4_ext_max_entries(struct inode *inode, int depth) if (depth == ext_depth(inode)) { if (depth == 0) - max = ext4_ext_space_root(inode); + max = ext4_ext_space_root(inode, 1); else - max = ext4_ext_space_root_idx(inode); + max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) - max = ext4_ext_space_block(inode); + max = ext4_ext_space_block(inode, 1); else - max = ext4_ext_space_block_idx(inode); + max = ext4_ext_space_block_idx(inode, 1); } return max; @@ -437,8 +454,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), idx_pblock(path->p_idx)); } else if (path->p_ext) { - ext_debug(" %d:%d:%llu ", + ext_debug(" %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), + ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext_pblock(path->p_ext)); } else @@ -460,8 +478,11 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); + ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino); + for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { - ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block), + ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), ext4_ext_get_actual_len(ex), ext_pblock(ex)); } ext_debug("\n"); @@ -580,9 +601,10 @@ ext4_ext_binsearch(struct inode *inode, } path->p_ext = l - 1; - ext_debug(" -> %d:%llu:%d ", + ext_debug(" -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext_pblock(path->p_ext), + ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH @@ -612,7 +634,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; - eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode)); + eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); ext4_mark_inode_dirty(handle, inode); ext4_ext_invalidate_cache(inode); return 0; @@ -701,7 +723,7 @@ err: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ -static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, +int ext4_ext_insert_index(handle_t *handle, struct inode *inode, struct ext4_ext_path *curp, int logical, ext4_fsblk_t ptr) { @@ -837,7 +859,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh = ext_block_hdr(bh); neh->eh_entries = 0; - neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; ex = EXT_FIRST_EXTENT(neh); @@ -850,9 +872,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, path[depth].p_ext++; while (path[depth].p_ext <= EXT_MAX_EXTENT(path[depth].p_hdr)) { - ext_debug("move %d:%llu:%d in new leaf %llu\n", + ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(path[depth].p_ext->ee_block), ext_pblock(path[depth].p_ext), + ext4_ext_is_uninitialized(path[depth].p_ext), ext4_ext_get_actual_len(path[depth].p_ext), newblock); /*memmove(ex++, path[depth].p_ext++, @@ -912,7 +935,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; - neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; @@ -1037,9 +1060,9 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) - neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else - neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1054,7 +1077,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, goto out; curp->p_hdr->eh_magic = EXT4_EXT_MAGIC; - curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode)); + curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); curp->p_hdr->eh_entries = cpu_to_le16(1); curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr); @@ -1563,7 +1586,7 @@ out: */ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent *newext) + struct ext4_extent *newext, int flag) { struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; @@ -1579,10 +1602,13 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, BUG_ON(path[depth].p_hdr == NULL); /* try to insert block into found extent and return */ - if (ex && ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append %d block to %d:%d (from %llu)\n", + if (ex && (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT) + && ext4_can_extents_be_merged(inode, ex, newext)) { + ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n", + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), ext4_ext_get_actual_len(ex), ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -1651,9 +1677,10 @@ has_space: if (!nearex) { /* there is no extent in this leaf, create first one */ - ext_debug("first extent in the leaf: %d:%llu:%d\n", + ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); } else if (le32_to_cpu(newext->ee_block) @@ -1663,10 +1690,11 @@ has_space: len = EXT_MAX_EXTENT(eh) - nearex; len = (len - 1) * sizeof(struct ext4_extent); len = len < 0 ? 0 : len; - ext_debug("insert %d:%llu:%d after: nearest 0x%p, " + ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 2, nearex + 1, len); @@ -1676,10 +1704,11 @@ has_space: BUG_ON(newext->ee_block == nearex->ee_block); len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent); len = len < 0 ? 0 : len; - ext_debug("insert %d:%llu:%d before: nearest 0x%p, " + ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 1, nearex, len); @@ -1694,7 +1723,8 @@ has_space: merge: /* try to merge extents to the right */ - ext4_ext_try_to_merge(inode, path, nearex); + if (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT) + ext4_ext_try_to_merge(inode, path, nearex); /* try to merge extents to the left */ @@ -2094,7 +2124,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, else uninitialized = 0; - ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); + ext_debug("remove ext %u:[%d]%d\n", ex_ee_block, + uninitialized, ex_ee_len); path[depth].p_ext = ex; a = ex_ee_block > start ? ex_ee_block : start; @@ -2138,7 +2169,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, } credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); - err = ext4_ext_journal_restart(handle, credits); + err = ext4_ext_truncate_extend_restart(handle, inode, credits); if (err) goto out; @@ -2327,7 +2358,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start) if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = - cpu_to_le16(ext4_ext_space_root(inode)); + cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } @@ -2349,6 +2380,7 @@ void ext4_ext_init(struct super_block *sb) */ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { +#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled"); #ifdef AGGRESSIVE_TEST printk(", aggressive tests"); @@ -2360,6 +2392,7 @@ void ext4_ext_init(struct super_block *sb) printk(", stats"); #endif printk("\n"); +#endif #ifdef EXTENTS_STATS spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); EXT4_SB(sb)->s_ext_min = 1 << 30; @@ -2461,7 +2494,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) } #define EXT4_EXT_ZERO_LEN 7 - /* * This function is called by ext4_ext_get_blocks() if someone tries to write * to an uninitialized extent. It may result in splitting the uninitialized @@ -2554,7 +2586,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ex3->ee_block = cpu_to_le32(iblock); ext4_ext_store_pblock(ex3, newblock); ex3->ee_len = cpu_to_le16(allocated); - err = ext4_ext_insert_extent(handle, inode, path, ex3); + err = ext4_ext_insert_extent(handle, inode, path, + ex3, 0); if (err == -ENOSPC) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) @@ -2610,7 +2643,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ext4_ext_store_pblock(ex3, newblock + max_blocks); ex3->ee_len = cpu_to_le16(allocated - max_blocks); ext4_ext_mark_uninitialized(ex3); - err = ext4_ext_insert_extent(handle, inode, path, ex3); + err = ext4_ext_insert_extent(handle, inode, path, ex3, 0); if (err == -ENOSPC) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) @@ -2728,7 +2761,191 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, err = ext4_ext_dirty(handle, inode, path + depth); goto out; insert: - err = ext4_ext_insert_extent(handle, inode, path, &newex); + err = ext4_ext_insert_extent(handle, inode, path, &newex, 0); + if (err == -ENOSPC) { + err = ext4_ext_zeroout(inode, &orig_ex); + if (err) + goto fix_extent_len; + /* update the extent length and mark as initialized */ + ex->ee_block = orig_ex.ee_block; + ex->ee_len = orig_ex.ee_len; + ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_dirty(handle, inode, path + depth); + /* zero out the first half */ + return allocated; + } else if (err) + goto fix_extent_len; +out: + ext4_ext_show_leaf(inode, path); + return err ? err : allocated; + +fix_extent_len: + ex->ee_block = orig_ex.ee_block; + ex->ee_len = orig_ex.ee_len; + ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_mark_uninitialized(ex); + ext4_ext_dirty(handle, inode, path + depth); + return err; +} + +/* + * This function is called by ext4_ext_get_blocks() from + * ext4_get_blocks_dio_write() when DIO to write + * to an uninitialized extent. + * + * Writing to an uninitized extent may result in splitting the uninitialized + * extent into multiple /intialized unintialized extents (up to three) + * There are three possibilities: + * a> There is no split required: Entire extent should be uninitialized + * b> Splits in two extents: Write is happening at either end of the extent + * c> Splits in three extents: Somone is writing in middle of the extent + * + * One of more index blocks maybe needed if the extent tree grow after + * the unintialized extent split. To prevent ENOSPC occur at the IO + * complete, we need to split the uninitialized extent before DIO submit + * the IO. The uninitilized extent called at this time will be split + * into three uninitialized extent(at most). After IO complete, the part + * being filled will be convert to initialized by the end_io callback function + * via ext4_convert_unwritten_extents(). + */ +static int ext4_split_unwritten_extents(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t iblock, + unsigned int max_blocks, + int flags) +{ + struct ext4_extent *ex, newex, orig_ex; + struct ext4_extent *ex1 = NULL; + struct ext4_extent *ex2 = NULL; + struct ext4_extent *ex3 = NULL; + struct ext4_extent_header *eh; + ext4_lblk_t ee_block; + unsigned int allocated, ee_len, depth; + ext4_fsblk_t newblock; + int err = 0; + int ret = 0; + + ext_debug("ext4_split_unwritten_extents: inode %lu," + "iblock %llu, max_blocks %u\n", inode->i_ino, + (unsigned long long)iblock, max_blocks); + depth = ext_depth(inode); + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); + allocated = ee_len - (iblock - ee_block); + newblock = iblock - ee_block + ext_pblock(ex); + ex2 = ex; + orig_ex.ee_block = ex->ee_block; + orig_ex.ee_len = cpu_to_le16(ee_len); + ext4_ext_store_pblock(&orig_ex, ext_pblock(ex)); + + /* + * if the entire unintialized extent length less than + * the size of extent to write, there is no need to split + * uninitialized extent + */ + if (allocated <= max_blocks) + return ret; + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + /* ex1: ee_block to iblock - 1 : uninitialized */ + if (iblock > ee_block) { + ex1 = ex; + ex1->ee_len = cpu_to_le16(iblock - ee_block); + ext4_ext_mark_uninitialized(ex1); + ex2 = &newex; + } + /* + * for sanity, update the length of the ex2 extent before + * we insert ex3, if ex1 is NULL. This is to avoid temporary + * overlap of blocks. + */ + if (!ex1 && allocated > max_blocks) + ex2->ee_len = cpu_to_le16(max_blocks); + /* ex3: to ee_block + ee_len : uninitialised */ + if (allocated > max_blocks) { + unsigned int newdepth; + ex3 = &newex; + ex3->ee_block = cpu_to_le32(iblock + max_blocks); + ext4_ext_store_pblock(ex3, newblock + max_blocks); + ex3->ee_len = cpu_to_le16(allocated - max_blocks); + ext4_ext_mark_uninitialized(ex3); + err = ext4_ext_insert_extent(handle, inode, path, ex3, flags); + if (err == -ENOSPC) { + err = ext4_ext_zeroout(inode, &orig_ex); + if (err) + goto fix_extent_len; + /* update the extent length and mark as initialized */ + ex->ee_block = orig_ex.ee_block; + ex->ee_len = orig_ex.ee_len; + ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_dirty(handle, inode, path + depth); + /* zeroed the full extent */ + /* blocks available from iblock */ + return allocated; + + } else if (err) + goto fix_extent_len; + /* + * The depth, and hence eh & ex might change + * as part of the insert above. + */ + newdepth = ext_depth(inode); + /* + * update the extent length after successful insert of the + * split extent + */ + orig_ex.ee_len = cpu_to_le16(ee_len - + ext4_ext_get_actual_len(ex3)); + depth = newdepth; + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, iblock, path); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out; + } + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + if (ex2 != &newex) + ex2 = ex; + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + + allocated = max_blocks; + } + /* + * If there was a change of depth as part of the + * insertion of ex3 above, we need to update the length + * of the ex1 extent again here + */ + if (ex1 && ex1 != ex) { + ex1 = ex; + ex1->ee_len = cpu_to_le16(iblock - ee_block); + ext4_ext_mark_uninitialized(ex1); + ex2 = &newex; + } + /* + * ex2: iblock to iblock + maxblocks-1 : to be direct IO written, + * uninitialised still. + */ + ex2->ee_block = cpu_to_le32(iblock); + ext4_ext_store_pblock(ex2, newblock); + ex2->ee_len = cpu_to_le16(allocated); + ext4_ext_mark_uninitialized(ex2); + if (ex2 != ex) + goto insert; + /* Mark modified extent as dirty */ + err = ext4_ext_dirty(handle, inode, path + depth); + ext_debug("out here\n"); + goto out; +insert: + err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err == -ENOSPC) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) @@ -2743,6 +2960,7 @@ insert: } else if (err) goto fix_extent_len; out: + ext4_ext_show_leaf(inode, path); return err ? err : allocated; fix_extent_len: @@ -2753,7 +2971,141 @@ fix_extent_len: ext4_ext_dirty(handle, inode, path + depth); return err; } +static int ext4_convert_unwritten_extents_dio(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path) +{ + struct ext4_extent *ex; + struct ext4_extent_header *eh; + int depth; + int err = 0; + int ret = 0; + + depth = ext_depth(inode); + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + /* first mark the extent as initialized */ + ext4_ext_mark_initialized(ex); + + /* + * We have to see if it can be merged with the extent + * on the left. + */ + if (ex > EXT_FIRST_EXTENT(eh)) { + /* + * To merge left, pass "ex - 1" to try_to_merge(), + * since it merges towards right _only_. + */ + ret = ext4_ext_try_to_merge(inode, path, ex - 1); + if (ret) { + err = ext4_ext_correct_indexes(handle, inode, path); + if (err) + goto out; + depth = ext_depth(inode); + ex--; + } + } + /* + * Try to Merge towards right. + */ + ret = ext4_ext_try_to_merge(inode, path, ex); + if (ret) { + err = ext4_ext_correct_indexes(handle, inode, path); + if (err) + goto out; + depth = ext_depth(inode); + } + /* Mark modified extent as dirty */ + err = ext4_ext_dirty(handle, inode, path + depth); +out: + ext4_ext_show_leaf(inode, path); + return err; +} + +static int +ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, + ext4_lblk_t iblock, unsigned int max_blocks, + struct ext4_ext_path *path, int flags, + unsigned int allocated, struct buffer_head *bh_result, + ext4_fsblk_t newblock) +{ + int ret = 0; + int err = 0; + ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; + + ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical" + "block %llu, max_blocks %u, flags %d, allocated %u", + inode->i_ino, (unsigned long long)iblock, max_blocks, + flags, allocated); + ext4_ext_show_leaf(inode, path); + + /* DIO get_block() before submit the IO, split the extent */ + if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) { + ret = ext4_split_unwritten_extents(handle, + inode, path, iblock, + max_blocks, flags); + /* flag the io_end struct that we need convert when IO done */ + if (io) + io->flag = DIO_AIO_UNWRITTEN; + goto out; + } + /* DIO end_io complete, convert the filled extent to written */ + if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) { + ret = ext4_convert_unwritten_extents_dio(handle, inode, + path); + goto out2; + } + /* buffered IO case */ + /* + * repeat fallocate creation request + * we already have an unwritten extent + */ + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) + goto map_out; + + /* buffered READ or buffered write_begin() lookup */ + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { + /* + * We have blocks reserved already. We + * return allocated blocks so that delalloc + * won't do block reservation for us. But + * the buffer head will be unmapped so that + * a read from the block returns 0s. + */ + set_buffer_unwritten(bh_result); + goto out1; + } + /* buffered write, writepage time, convert*/ + ret = ext4_ext_convert_to_initialized(handle, inode, + path, iblock, + max_blocks); +out: + if (ret <= 0) { + err = ret; + goto out2; + } else + allocated = ret; + set_buffer_new(bh_result); +map_out: + set_buffer_mapped(bh_result); +out1: + if (allocated > max_blocks) + allocated = max_blocks; + ext4_ext_show_leaf(inode, path); + bh_result->b_bdev = inode->i_sb->s_bdev; + bh_result->b_blocknr = newblock; +out2: + if (path) { + ext4_ext_drop_refs(path); + kfree(path); + } + return err ? err : allocated; +} /* * Block allocation/map/preallocation routine for extents based files * @@ -2784,9 +3136,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; + ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; __clear_bit(BH_New, &bh_result->b_state); - ext_debug("blocks %u/%u requested for inode %u\n", + ext_debug("blocks %u/%u requested for inode %lu\n", iblock, max_blocks, inode->i_ino); /* check in cache */ @@ -2849,7 +3202,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = iblock - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (iblock - ee_block); - ext_debug("%u fit into %lu:%d -> %llu\n", iblock, + ext_debug("%u fit into %u:%d -> %llu\n", iblock, ee_block, ee_len, newblock); /* Do not put uninitialized extent in the cache */ @@ -2859,33 +3212,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, EXT4_EXT_CACHE_EXTENT); goto out; } - if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) - goto out; - if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - if (allocated > max_blocks) - allocated = max_blocks; - /* - * We have blocks reserved already. We - * return allocated blocks so that delalloc - * won't do block reservation for us. But - * the buffer head will be unmapped so that - * a read from the block returns 0s. - */ - set_buffer_unwritten(bh_result); - bh_result->b_bdev = inode->i_sb->s_bdev; - bh_result->b_blocknr = newblock; - goto out2; - } - - ret = ext4_ext_convert_to_initialized(handle, inode, - path, iblock, - max_blocks); - if (ret <= 0) { - err = ret; - goto out2; - } else - allocated = ret; - goto outnew; + ret = ext4_ext_handle_uninitialized_extents(handle, + inode, iblock, max_blocks, path, + flags, allocated, bh_result, newblock); + return ret; } } @@ -2950,15 +3280,27 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out2; - ext_debug("allocate new block: goal %llu, found %llu/%lu\n", + ext_debug("allocate new block: goal %llu, found %llu/%u\n", ar.goal, newblock, allocated); /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(ar.len); - if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) /* Mark uninitialized */ + /* Mark uninitialized */ + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){ ext4_ext_mark_uninitialized(&newex); - err = ext4_ext_insert_extent(handle, inode, path, &newex); + /* + * io_end structure was created for every async + * direct IO write to the middle of the file. + * To avoid unecessary convertion for every aio dio rewrite + * to the mid of file, here we flag the IO that is really + * need the convertion. + * + */ + if (io && flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) + io->flag = DIO_AIO_UNWRITTEN; + } + err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err) { /* free data blocks we just allocated */ /* not a good idea to call discard here directly, @@ -2972,7 +3314,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* previous routine could use block we allocated */ newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); -outnew: set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ @@ -3171,6 +3512,63 @@ retry: } /* + * This function convert a range of blocks to written extents + * The caller of this function will pass the start offset and the size. + * all unwritten extents within this range will be converted to + * written extents. + * + * This function is called from the direct IO end io call back + * function, to convert the fallocated extents after IO is completed. + */ +int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + ext4_lblk_t block; + unsigned int max_blocks; + int ret = 0; + int ret2 = 0; + struct buffer_head map_bh; + unsigned int credits, blkbits = inode->i_blkbits; + + block = offset >> blkbits; + /* + * We can't just convert len to max_blocks because + * If blocksize = 4096 offset = 3072 and len = 2048 + */ + max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) + - block; + /* + * credits to insert 1 extent into extent tree + */ + credits = ext4_chunk_trans_blocks(inode, max_blocks); + while (ret >= 0 && ret < max_blocks) { + block = block + ret; + max_blocks = max_blocks - ret; + handle = ext4_journal_start(inode, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + break; + } + map_bh.b_state = 0; + ret = ext4_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_GET_BLOCKS_DIO_CONVERT_EXT); + if (ret <= 0) { + WARN_ON(ret <= 0); + printk(KERN_ERR "%s: ext4_ext_get_blocks " + "returned error inode#%lu, block=%u, " + "max_blocks=%u", __func__, + inode->i_ino, block, max_blocks); + } + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + if (ret <= 0 || ret2 ) + break; + } + return ret > 0 ? ret2 : ret; +} +/* * Callback function called for each extent to gather FIEMAP information. */ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5ca3eca70a1e..9630583cef28 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -81,7 +81,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, return generic_file_aio_write(iocb, iov, nr_segs, pos); } -static struct vm_operations_struct ext4_file_vm_ops = { +static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 83cf6415f599..2b1531266ee2 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -44,18 +44,23 @@ * * What we do is just kick off a commit and wait on it. This will snapshot the * inode to disk. + * + * i_mutex lock is held when entering and exiting this function */ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) { struct inode *inode = dentry->d_inode; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - int ret = 0; + int err, ret = 0; J_ASSERT(ext4_journal_current_handle() == NULL); trace_ext4_sync_file(file, dentry, datasync); + ret = flush_aio_dio_completed_IO(inode); + if (ret < 0) + goto out; /* * data=writeback: * The caller's filemap_fdatawrite()/wait will sync the data. @@ -79,6 +84,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) goto out; } + if (!journal) + ret = sync_mapping_buffers(inode->i_mapping); + if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; @@ -91,10 +99,12 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, /* sys_fsync did this */ }; - ret = sync_inode(inode, &wbc); - if (journal && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + err = sync_inode(inode, &wbc); + if (ret == 0) + ret = err; } out: + if (journal && (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(inode->i_sb->s_bdev, NULL); return ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 29e6dc7299b8..f3624ead4f6c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1189,7 +1189,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", - i, ext4_free_inodes_count(sb, gdp), x); + (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f9c642b22efa..ec367bce7215 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,6 +37,7 @@ #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> +#include <linux/workqueue.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -192,11 +193,24 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode) * so before we call here everything must be consistently dirtied against * this transaction. */ -static int ext4_journal_test_restart(handle_t *handle, struct inode *inode) + int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, + int nblocks) { + int ret; + + /* + * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this + * moment, get_block can be called only for blocks inside i_size since + * page cache has been already dropped and writes are blocked by + * i_mutex. So we can safely drop the i_data_sem here. + */ BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); - return ext4_journal_restart(handle, blocks_for_truncate(inode)); + up_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_journal_restart(handle, blocks_for_truncate(inode)); + down_write(&EXT4_I(inode)->i_data_sem); + + return ret; } /* @@ -341,9 +355,7 @@ static int ext4_block_to_path(struct inode *inode, int n = 0; int final = 0; - if (i_block < 0) { - ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0"); - } else if (i_block < direct_blocks) { + if (i_block < direct_blocks) { offsets[n++] = i_block; final = direct_blocks; } else if ((i_block -= direct_blocks) < indirect_blocks) { @@ -551,15 +563,21 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * * Normally this function find the preferred place for block allocation, * returns it. + * Because this is only used for non-extent files, we limit the block nr + * to 32 bits. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, Indirect *partial) { + ext4_fsblk_t goal; + /* * XXX need to get goal block from mballoc's data structures */ - return ext4_find_near(inode, partial); + goal = ext4_find_near(inode, partial); + goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; + return goal; } /** @@ -640,6 +658,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, if (*err) goto failed_out; + BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS); + target -= count; /* allocate blocks for indirect blocks */ while (index < indirect_blks && count) { @@ -674,6 +694,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, ar.flags = EXT4_MB_HINT_DATA; current_block = ext4_mb_new_blocks(handle, &ar, err); + BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS); if (*err && (target == blks)) { /* @@ -762,8 +783,9 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, bh); if (err) { + /* Don't brelse(bh) here; it's done in + * ext4_journal_forget() below */ unlock_buffer(bh); - brelse(bh); goto failed; } @@ -1109,22 +1131,79 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) ext4_discard_preallocations(inode); } -static int check_block_validity(struct inode *inode, sector_t logical, - sector_t phys, int len) +static int check_block_validity(struct inode *inode, const char *msg, + sector_t logical, sector_t phys, int len) { if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) { - ext4_error(inode->i_sb, "check_block_validity", + ext4_error(inode->i_sb, msg, "inode #%lu logical block %llu mapped to %llu " "(size %d)", inode->i_ino, (unsigned long long) logical, (unsigned long long) phys, len); - WARN_ON(1); return -EIO; } return 0; } /* + * Return the number of dirty pages in the given inode starting at + * page frame idx. + */ +static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, + unsigned int max_pages) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t index; + struct pagevec pvec; + pgoff_t num = 0; + int i, nr_pages, done = 0; + + if (max_pages == 0) + return 0; + pagevec_init(&pvec, 0); + while (!done) { + index = idx; + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + (pgoff_t)PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + struct buffer_head *bh, *head; + + lock_page(page); + if (unlikely(page->mapping != mapping) || + !PageDirty(page) || + PageWriteback(page) || + page->index != idx) { + done = 1; + unlock_page(page); + break; + } + head = page_buffers(page); + bh = head; + do { + if (!buffer_delay(bh) && + !buffer_unwritten(bh)) { + done = 1; + break; + } + } while ((bh = bh->b_this_page) != head); + unlock_page(page); + if (done) + break; + idx++; + num++; + if (num >= max_pages) + break; + } + pagevec_release(&pvec); + } + return num; +} + +/* * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * @@ -1155,6 +1234,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, clear_buffer_mapped(bh); clear_buffer_unwritten(bh); + ext_debug("ext4_get_blocks(): inode %lu, flag %d, max_blocks %u," + "logical block %lu\n", inode->i_ino, flags, max_blocks, + (unsigned long)block); /* * Try to see if we can get the block without requesting a new * file system block. @@ -1170,8 +1252,8 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && buffer_mapped(bh)) { - int ret = check_block_validity(inode, block, - bh->b_blocknr, retval); + int ret = check_block_validity(inode, "file system corruption", + block, bh->b_blocknr, retval); if (ret != 0) return ret; } @@ -1235,8 +1317,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, * i_data's format changing. Force the migrate * to fail by clearing migrate flags */ - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags & - ~EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE; } } @@ -1252,8 +1333,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && buffer_mapped(bh)) { - int ret = check_block_validity(inode, block, - bh->b_blocknr, retval); + int ret = check_block_validity(inode, "file system " + "corruption after allocation", + block, bh->b_blocknr, retval); if (ret != 0) return ret; } @@ -1776,11 +1858,11 @@ repeat: if (ext4_claim_free_blocks(sbi, total)) { spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + vfs_dq_release_reservation_block(inode, total); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; } - vfs_dq_release_reservation_block(inode, total); return -ENOSPC; } EXT4_I(inode)->i_reserved_data_blocks += nrblocks; @@ -1863,18 +1945,6 @@ static void ext4_da_page_release_reservation(struct page *page, * Delayed allocation stuff */ -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; -}; - /* * mpage_da_submit_io - walks through extent of pages and try to write * them with writepage() call back @@ -2084,18 +2154,18 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - printk(KERN_EMERG "Total free blocks count %lld\n", - ext4_count_free_blocks(inode->i_sb)); - printk(KERN_EMERG "Free/Dirty block details\n"); - printk(KERN_EMERG "free_blocks=%lld\n", - (long long)percpu_counter_sum(&sbi->s_freeblocks_counter)); - printk(KERN_EMERG "dirty_blocks=%lld\n", - (long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter)); - printk(KERN_EMERG "Block reservation details\n"); - printk(KERN_EMERG "i_reserved_data_blocks=%u\n", - EXT4_I(inode)->i_reserved_data_blocks); - printk(KERN_EMERG "i_reserved_meta_blocks=%u\n", - EXT4_I(inode)->i_reserved_meta_blocks); + printk(KERN_CRIT "Total free blocks count %lld\n", + ext4_count_free_blocks(inode->i_sb)); + printk(KERN_CRIT "Free/Dirty block details\n"); + printk(KERN_CRIT "free_blocks=%lld\n", + (long long) percpu_counter_sum(&sbi->s_freeblocks_counter)); + printk(KERN_CRIT "dirty_blocks=%lld\n", + (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + printk(KERN_CRIT "Block reservation details\n"); + printk(KERN_CRIT "i_reserved_data_blocks=%u\n", + EXT4_I(inode)->i_reserved_data_blocks); + printk(KERN_CRIT "i_reserved_meta_blocks=%u\n", + EXT4_I(inode)->i_reserved_meta_blocks); return; } @@ -2181,14 +2251,14 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) * writepage and writepages will again try to write * the same. */ - printk(KERN_EMERG "%s block allocation failed for inode %lu " - "at logical offset %llu with max blocks " - "%zd with error %d\n", - __func__, mpd->inode->i_ino, - (unsigned long long)next, - mpd->b_size >> mpd->inode->i_blkbits, err); - printk(KERN_EMERG "This should not happen.!! " - "Data will be lost\n"); + ext4_msg(mpd->inode->i_sb, KERN_CRIT, + "delayed block allocation failed for inode %lu at " + "logical offset %llu with max blocks %zd with " + "error %d\n", mpd->inode->i_ino, + (unsigned long long) next, + mpd->b_size >> mpd->inode->i_blkbits, err); + printk(KERN_CRIT "This should not happen!! " + "Data will be lost\n"); if (err == -ENOSPC) { ext4_print_free_blocks(mpd->inode); } @@ -2329,7 +2399,7 @@ static int __mpage_da_writepage(struct page *page, /* * Rest of the page in the page_vec * redirty then and skip then. We will - * try to to write them again after + * try to write them again after * starting a new transaction */ redirty_page_for_writepage(wbc, page); @@ -2735,8 +2805,11 @@ static int ext4_da_writepages(struct address_space *mapping, int no_nrwrite_index_update; int pages_written = 0; long pages_skipped; + unsigned int max_pages; int range_cyclic, cycled = 1, io_done = 0; - int needed_blocks, ret = 0, nr_to_writebump = 0; + int needed_blocks, ret = 0; + long desired_nr_to_write, nr_to_writebump = 0; + loff_t range_start = wbc->range_start; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); trace_ext4_da_writepages(inode, wbc); @@ -2762,16 +2835,6 @@ static int ext4_da_writepages(struct address_space *mapping, if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) return -EROFS; - /* - * Make sure nr_to_write is >= sbi->s_mb_stream_request - * This make sure small files blocks are allocated in - * single attempt. This ensure that small files - * get less fragmented. - */ - if (wbc->nr_to_write < sbi->s_mb_stream_request) { - nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write; - wbc->nr_to_write = sbi->s_mb_stream_request; - } if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; @@ -2786,6 +2849,36 @@ static int ext4_da_writepages(struct address_space *mapping, } else index = wbc->range_start >> PAGE_CACHE_SHIFT; + /* + * This works around two forms of stupidity. The first is in + * the writeback code, which caps the maximum number of pages + * written to be 1024 pages. This is wrong on multiple + * levels; different architectues have a different page size, + * which changes the maximum amount of data which gets + * written. Secondly, 4 megabytes is way too small. XFS + * forces this value to be 16 megabytes by multiplying + * nr_to_write parameter by four, and then relies on its + * allocator to allocate larger extents to make them + * contiguous. Unfortunately this brings us to the second + * stupidity, which is that ext4's mballoc code only allocates + * at most 2048 blocks. So we force contiguous writes up to + * the number of dirty blocks in the inode, or + * sbi->max_writeback_mb_bump whichever is smaller. + */ + max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT); + if (!range_cyclic && range_whole) + desired_nr_to_write = wbc->nr_to_write * 8; + else + desired_nr_to_write = ext4_num_dirty_pages(inode, index, + max_pages); + if (desired_nr_to_write > max_pages) + desired_nr_to_write = max_pages; + + if (wbc->nr_to_write < desired_nr_to_write) { + nr_to_writebump = desired_nr_to_write - wbc->nr_to_write; + wbc->nr_to_write = desired_nr_to_write; + } + mpd.wbc = wbc; mpd.inode = mapping->host; @@ -2813,10 +2906,9 @@ retry: handle = ext4_journal_start(inode, needed_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - printk(KERN_CRIT "%s: jbd2_start: " + ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: " "%ld pages, ino %lu; err %d\n", __func__, wbc->nr_to_write, inode->i_ino, ret); - dump_stack(); goto out_writepages; } @@ -2850,6 +2942,7 @@ retry: mpd.io_done = 1; ret = MPAGE_DA_EXTENT_TAIL; } + trace_ext4_da_write_pages(inode, &mpd); wbc->nr_to_write -= mpd.pages_written; ext4_journal_stop(handle); @@ -2887,9 +2980,10 @@ retry: goto retry; } if (pages_skipped != wbc->pages_skipped) - printk(KERN_EMERG "This should not happen leaving %s " - "with nr_to_write = %ld ret = %d\n", - __func__, wbc->nr_to_write, ret); + ext4_msg(inode->i_sb, KERN_CRIT, + "This should not happen leaving %s " + "with nr_to_write = %ld ret = %d\n", + __func__, wbc->nr_to_write, ret); /* Update index */ index += pages_written; @@ -2904,7 +2998,9 @@ retry: out_writepages: if (!no_nrwrite_index_update) wbc->no_nrwrite_index_update = 0; - wbc->nr_to_write -= nr_to_writebump; + if (wbc->nr_to_write > nr_to_writebump) + wbc->nr_to_write -= nr_to_writebump; + wbc->range_start = range_start; trace_ext4_da_writepages_result(inode, wbc, ret, pages_written); return ret; } @@ -3117,6 +3213,8 @@ out: */ int ext4_alloc_da_blocks(struct inode *inode) { + trace_ext4_alloc_da_blocks(inode); + if (!EXT4_I(inode)->i_reserved_data_blocks && !EXT4_I(inode)->i_reserved_meta_blocks) return 0; @@ -3259,6 +3357,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait) } /* + * O_DIRECT for ext3 (or indirect map) based files + * * If the O_DIRECT write will extend the file then add this inode to the * orphan list. So recovery will truncate it back to the original size * if the machine crashes during the write. @@ -3267,7 +3367,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) * crashes then stale disk data _may_ be exposed inside the file. But current * VFS code falls back into buffered path in that case so we are safe. */ -static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, +static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) { @@ -3341,6 +3441,359 @@ out: return ret; } +/* Maximum number of blocks we map for direct IO at once. */ + +static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + handle_t *handle = NULL; + int ret = 0; + unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + int dio_credits; + + ext4_debug("ext4_get_block_dio_write: inode %lu, create flag %d\n", + inode->i_ino, create); + /* + * DIO VFS code passes create = 0 flag for write to + * the middle of file. It does this to avoid block + * allocation for holes, to prevent expose stale data + * out when there is parallel buffered read (which does + * not hold the i_mutex lock) while direct IO write has + * not completed. DIO request on holes finally falls back + * to buffered IO for this reason. + * + * For ext4 extent based file, since we support fallocate, + * new allocated extent as uninitialized, for holes, we + * could fallocate blocks for holes, thus parallel + * buffered IO read will zero out the page when read on + * a hole while parallel DIO write to the hole has not completed. + * + * when we come here, we know it's a direct IO write to + * to the middle of file (<i_size) + * so it's safe to override the create flag from VFS. + */ + create = EXT4_GET_BLOCKS_DIO_CREATE_EXT; + + if (max_blocks > DIO_MAX_BLOCKS) + max_blocks = DIO_MAX_BLOCKS; + dio_credits = ext4_chunk_trans_blocks(inode, max_blocks); + handle = ext4_journal_start(inode, dio_credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, + create); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; + } + ext4_journal_stop(handle); +out: + return ret; +} + +static void ext4_free_io_end(ext4_io_end_t *io) +{ + BUG_ON(!io); + iput(io->inode); + kfree(io); +} +static void dump_aio_dio_list(struct inode * inode) +{ +#ifdef EXT4_DEBUG + struct list_head *cur, *before, *after; + ext4_io_end_t *io, *io0, *io1; + + if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){ + ext4_debug("inode %lu aio dio list is empty\n", inode->i_ino); + return; + } + + ext4_debug("Dump inode %lu aio_dio_completed_IO list \n", inode->i_ino); + list_for_each_entry(io, &EXT4_I(inode)->i_aio_dio_complete_list, list){ + cur = &io->list; + before = cur->prev; + io0 = container_of(before, ext4_io_end_t, list); + after = cur->next; + io1 = container_of(after, ext4_io_end_t, list); + + ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", + io, inode->i_ino, io0, io1); + } +#endif +} + +/* + * check a range of space and convert unwritten extents to written. + */ +static int ext4_end_aio_dio_nolock(ext4_io_end_t *io) +{ + struct inode *inode = io->inode; + loff_t offset = io->offset; + size_t size = io->size; + int ret = 0; + + ext4_debug("end_aio_dio_onlock: io 0x%p from inode %lu,list->next 0x%p," + "list->prev 0x%p\n", + io, inode->i_ino, io->list.next, io->list.prev); + + if (list_empty(&io->list)) + return ret; + + if (io->flag != DIO_AIO_UNWRITTEN) + return ret; + + if (offset + size <= i_size_read(inode)) + ret = ext4_convert_unwritten_extents(inode, offset, size); + + if (ret < 0) { + printk(KERN_EMERG "%s: failed to convert unwritten" + "extents to written extents, error is %d" + " io is still on inode %lu aio dio list\n", + __func__, ret, inode->i_ino); + return ret; + } + + /* clear the DIO AIO unwritten flag */ + io->flag = 0; + return ret; +} +/* + * work on completed aio dio IO, to convert unwritten extents to extents + */ +static void ext4_end_aio_dio_work(struct work_struct *work) +{ + ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); + struct inode *inode = io->inode; + int ret = 0; + + mutex_lock(&inode->i_mutex); + ret = ext4_end_aio_dio_nolock(io); + if (ret >= 0) { + if (!list_empty(&io->list)) + list_del_init(&io->list); + ext4_free_io_end(io); + } + mutex_unlock(&inode->i_mutex); +} +/* + * This function is called from ext4_sync_file(). + * + * When AIO DIO IO is completed, the work to convert unwritten + * extents to written is queued on workqueue but may not get immediately + * scheduled. When fsync is called, we need to ensure the + * conversion is complete before fsync returns. + * The inode keeps track of a list of completed AIO from DIO path + * that might needs to do the conversion. This function walks through + * the list and convert the related unwritten extents to written. + */ +int flush_aio_dio_completed_IO(struct inode *inode) +{ + ext4_io_end_t *io; + int ret = 0; + int ret2 = 0; + + if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)) + return ret; + + dump_aio_dio_list(inode); + while (!list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){ + io = list_entry(EXT4_I(inode)->i_aio_dio_complete_list.next, + ext4_io_end_t, list); + /* + * Calling ext4_end_aio_dio_nolock() to convert completed + * IO to written. + * + * When ext4_sync_file() is called, run_queue() may already + * about to flush the work corresponding to this io structure. + * It will be upset if it founds the io structure related + * to the work-to-be schedule is freed. + * + * Thus we need to keep the io structure still valid here after + * convertion finished. The io structure has a flag to + * avoid double converting from both fsync and background work + * queue work. + */ + ret = ext4_end_aio_dio_nolock(io); + if (ret < 0) + ret2 = ret; + else + list_del_init(&io->list); + } + return (ret2 < 0) ? ret2 : 0; +} + +static ext4_io_end_t *ext4_init_io_end (struct inode *inode) +{ + ext4_io_end_t *io = NULL; + + io = kmalloc(sizeof(*io), GFP_NOFS); + + if (io) { + igrab(inode); + io->inode = inode; + io->flag = 0; + io->offset = 0; + io->size = 0; + io->error = 0; + INIT_WORK(&io->work, ext4_end_aio_dio_work); + INIT_LIST_HEAD(&io->list); + } + + return io; +} + +static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, + ssize_t size, void *private) +{ + ext4_io_end_t *io_end = iocb->private; + struct workqueue_struct *wq; + + ext_debug("ext4_end_io_dio(): io_end 0x%p" + "for inode %lu, iocb 0x%p, offset %llu, size %llu\n", + iocb->private, io_end->inode->i_ino, iocb, offset, + size); + /* if not async direct IO or dio with 0 bytes write, just return */ + if (!io_end || !size) + return; + + /* if not aio dio with unwritten extents, just free io and return */ + if (io_end->flag != DIO_AIO_UNWRITTEN){ + ext4_free_io_end(io_end); + iocb->private = NULL; + return; + } + + io_end->offset = offset; + io_end->size = size; + wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; + + /* queue the work to convert unwritten extents to written */ + queue_work(wq, &io_end->work); + + /* Add the io_end to per-inode completed aio dio list*/ + list_add_tail(&io_end->list, + &EXT4_I(io_end->inode)->i_aio_dio_complete_list); + iocb->private = NULL; +} +/* + * For ext4 extent files, ext4 will do direct-io write to holes, + * preallocated extents, and those write extend the file, no need to + * fall back to buffered IO. + * + * For holes, we fallocate those blocks, mark them as unintialized + * If those blocks were preallocated, we mark sure they are splited, but + * still keep the range to write as unintialized. + * + * The unwrritten extents will be converted to written when DIO is completed. + * For async direct IO, since the IO may still pending when return, we + * set up an end_io call back function, which will do the convertion + * when async direct IO completed. + * + * If the O_DIRECT write will extend the file then add this inode to the + * orphan list. So recovery will truncate it back to the original size + * if the machine crashes during the write. + * + */ +static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + size_t count = iov_length(iov, nr_segs); + + loff_t final_size = offset + count; + if (rw == WRITE && final_size <= inode->i_size) { + /* + * We could direct write to holes and fallocate. + * + * Allocated blocks to fill the hole are marked as uninitialized + * to prevent paralel buffered read to expose the stale data + * before DIO complete the data IO. + * + * As to previously fallocated extents, ext4 get_block + * will just simply mark the buffer mapped but still + * keep the extents uninitialized. + * + * for non AIO case, we will convert those unwritten extents + * to written after return back from blockdev_direct_IO. + * + * for async DIO, the conversion needs to be defered when + * the IO is completed. The ext4 end_io callback function + * will be called to take care of the conversion work. + * Here for async case, we allocate an io_end structure to + * hook to the iocb. + */ + iocb->private = NULL; + EXT4_I(inode)->cur_aio_dio = NULL; + if (!is_sync_kiocb(iocb)) { + iocb->private = ext4_init_io_end(inode); + if (!iocb->private) + return -ENOMEM; + /* + * we save the io structure for current async + * direct IO, so that later ext4_get_blocks() + * could flag the io structure whether there + * is a unwritten extents needs to be converted + * when IO is completed. + */ + EXT4_I(inode)->cur_aio_dio = iocb->private; + } + + ret = blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block_dio_write, + ext4_end_io_dio); + if (iocb->private) + EXT4_I(inode)->cur_aio_dio = NULL; + /* + * The io_end structure takes a reference to the inode, + * that structure needs to be destroyed and the + * reference to the inode need to be dropped, when IO is + * complete, even with 0 byte write, or failed. + * + * In the successful AIO DIO case, the io_end structure will be + * desctroyed and the reference to the inode will be dropped + * after the end_io call back function is called. + * + * In the case there is 0 byte write, or error case, since + * VFS direct IO won't invoke the end_io call back function, + * we need to free the end_io structure here. + */ + if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { + ext4_free_io_end(iocb->private); + iocb->private = NULL; + } else if (ret > 0) + /* + * for non AIO case, since the IO is already + * completed, we could do the convertion right here + */ + ret = ext4_convert_unwritten_extents(inode, + offset, ret); + return ret; + } + + /* for write the the end of file case, we fall back to old way */ + return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); +} + +static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); + + return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); +} + /* * Pages can be marked dirty completely asynchronously from ext4's journalling * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do @@ -3373,6 +3826,7 @@ static const struct address_space_operations ext4_ordered_aops = { .direct_IO = ext4_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; static const struct address_space_operations ext4_writeback_aops = { @@ -3388,6 +3842,7 @@ static const struct address_space_operations ext4_writeback_aops = { .direct_IO = ext4_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; static const struct address_space_operations ext4_journalled_aops = { @@ -3402,6 +3857,7 @@ static const struct address_space_operations ext4_journalled_aops = { .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; static const struct address_space_operations ext4_da_aops = { @@ -3418,6 +3874,7 @@ static const struct address_space_operations ext4_da_aops = { .direct_IO = ext4_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; void ext4_set_aops(struct inode *inode) @@ -3659,7 +4116,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode, ext4_handle_dirty_metadata(handle, inode, bh); } ext4_mark_inode_dirty(handle, inode); - ext4_journal_test_restart(handle, inode); + ext4_truncate_restart_trans(handle, inode, + blocks_for_truncate(inode)); if (bh) { BUFFER_TRACE(bh, "retaking write access"); ext4_journal_get_write_access(handle, bh); @@ -3870,7 +4328,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, return; if (try_to_extend_transaction(handle, inode)) { ext4_mark_inode_dirty(handle, inode); - ext4_journal_test_restart(handle, inode); + ext4_truncate_restart_trans(handle, inode, + blocks_for_truncate(inode)); } ext4_free_blocks(handle, inode, nr, 1, 1); @@ -3958,8 +4417,7 @@ void ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return; - if (ei->i_disksize && inode->i_size == 0 && - !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) + if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE; if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { @@ -4581,8 +5039,7 @@ static int ext4_do_update_inode(handle_t *handle, if (ext4_inode_blocks_set(handle, raw_inode, ei)) goto out_brelse; raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); - /* clear the migrate flag in the raw_inode */ - raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE); + raw_inode->i_flags = cpu_to_le32(ei->i_flags); if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_HURD)) raw_inode->i_file_acl_high = @@ -4684,19 +5141,40 @@ out_brelse: */ int ext4_write_inode(struct inode *inode, int wait) { + int err; + if (current->flags & PF_MEMALLOC) return 0; - if (ext4_journal_current_handle()) { - jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); - dump_stack(); - return -EIO; - } + if (EXT4_SB(inode->i_sb)->s_journal) { + if (ext4_journal_current_handle()) { + jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); + dump_stack(); + return -EIO; + } - if (!wait) - return 0; + if (!wait) + return 0; - return ext4_force_commit(inode->i_sb); + err = ext4_force_commit(inode->i_sb); + } else { + struct ext4_iloc iloc; + + err = ext4_get_inode_loc(inode, &iloc); + if (err) + return err; + if (wait) + sync_dirty_buffer(iloc.bh); + if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { + ext4_error(inode->i_sb, __func__, + "IO error syncing inode, " + "inode=%lu, block=%llu", + inode->i_ino, + (unsigned long long)iloc.bh->b_blocknr); + err = -EIO; + } + } + return err; } /* @@ -5137,24 +5615,13 @@ void ext4_dirty_inode(struct inode *inode) handle_t *current_handle = ext4_journal_current_handle(); handle_t *handle; - if (!ext4_handle_valid(current_handle)) { - ext4_mark_inode_dirty(current_handle, inode); - return; - } - handle = ext4_journal_start(inode, 2); if (IS_ERR(handle)) goto out; - if (current_handle && - current_handle->h_transaction != handle->h_transaction) { - /* This task has a transaction open against a different fs */ - printk(KERN_EMERG "%s: transactions do not match!\n", - __func__); - } else { - jbd_debug(5, "marking dirty. outer handle=%p\n", - current_handle); - ext4_mark_inode_dirty(handle, inode); - } + + jbd_debug(5, "marking dirty. outer handle=%p\n", current_handle); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); out: return; @@ -5281,12 +5748,21 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) else len = PAGE_CACHE_SIZE; + lock_page(page); + /* + * return if we have all the buffers mapped. This avoid + * the need to call write_begin/write_end which does a + * journal_start/journal_stop which can block and take + * long time + */ if (page_has_buffers(page)) { - /* return if we have all the buffers mapped */ if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped)) + ext4_bh_unmapped)) { + unlock_page(page); goto out_unlock; + } } + unlock_page(page); /* * OK, we need to fill the hole... Do write_begin write_end * to do block allocation/reservation.We are not holding diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 7050a9cd04a4..c1cdf613e725 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -243,10 +243,9 @@ setversion_out: me.donor_start, me.len, &me.moved_len); fput(donor_filp); - if (!err) - if (copy_to_user((struct move_extent *)arg, - &me, sizeof(me))) - return -EFAULT; + if (copy_to_user((struct move_extent *)arg, &me, sizeof(me))) + return -EFAULT; + return err; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cd258463e2a9..bba12824defa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -22,6 +22,7 @@ */ #include "mballoc.h" +#include <linux/debugfs.h> #include <trace/events/ext4.h> /* @@ -622,13 +623,13 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, /* FIXME!! need more doc */ static void ext4_mb_mark_free_simple(struct super_block *sb, - void *buddy, unsigned first, int len, + void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned short min; - unsigned short max; - unsigned short chunk; + ext4_grpblk_t min; + ext4_grpblk_t max; + ext4_grpblk_t chunk; unsigned short border; BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb)); @@ -662,10 +663,10 @@ void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); - unsigned short max = EXT4_BLOCKS_PER_GROUP(sb); - unsigned short i = 0; - unsigned short first; - unsigned short len; + ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb); + ext4_grpblk_t i = 0; + ext4_grpblk_t first; + ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); @@ -743,7 +744,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) char *data; char *bitmap; - mb_debug("init page %lu\n", page->index); + mb_debug(1, "init page %lu\n", page->index); inode = page->mapping->host; sb = inode->i_sb; @@ -822,7 +823,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) set_bitmap_uptodate(bh[i]); bh[i]->b_end_io = end_buffer_read_sync; submit_bh(READ, bh[i]); - mb_debug("read bitmap for group %u\n", first_group + i); + mb_debug(1, "read bitmap for group %u\n", first_group + i); } /* wait for I/O completion */ @@ -862,12 +863,13 @@ static int ext4_mb_init_cache(struct page *page, char *incore) if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); - mb_debug("put buddy for group %u in page %lu/%x\n", + mb_debug(1, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); grinfo = ext4_get_group_info(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, - sizeof(unsigned short)*(sb->s_blocksize_bits+2)); + sizeof(*grinfo->bb_counters) * + (sb->s_blocksize_bits+2)); /* * incore got set to the group block bitmap below */ @@ -878,7 +880,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) } else { /* this is block of bitmap */ BUG_ON(incore != NULL); - mb_debug("put bitmap for group %u in page %lu/%x\n", + mb_debug(1, "put bitmap for group %u in page %lu/%x\n", group, page->index, i * blocksize); /* see comments in ext4_mb_put_pa() */ @@ -908,6 +910,100 @@ out: return err; } +static noinline_for_stack +int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) +{ + + int ret = 0; + void *bitmap; + int blocks_per_page; + int block, pnum, poff; + int num_grp_locked = 0; + struct ext4_group_info *this_grp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct inode *inode = sbi->s_buddy_cache; + struct page *page = NULL, *bitmap_page = NULL; + + mb_debug(1, "init group %u\n", group); + blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + this_grp = ext4_get_group_info(sb, group); + /* + * This ensures that we don't reinit the buddy cache + * page which map to the group from which we are already + * allocating. If we are looking at the buddy cache we would + * have taken a reference using ext4_mb_load_buddy and that + * would have taken the alloc_sem lock. + */ + num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group); + if (!EXT4_MB_GRP_NEED_INIT(this_grp)) { + /* + * somebody initialized the group + * return without doing anything + */ + ret = 0; + goto err; + } + /* + * the buddy cache inode stores the block bitmap + * and buddy information in consecutive blocks. + * So for each group we need two blocks. + */ + block = group * 2; + pnum = block / blocks_per_page; + poff = block % blocks_per_page; + page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + if (page) { + BUG_ON(page->mapping != inode->i_mapping); + ret = ext4_mb_init_cache(page, NULL); + if (ret) { + unlock_page(page); + goto err; + } + unlock_page(page); + } + if (page == NULL || !PageUptodate(page)) { + ret = -EIO; + goto err; + } + mark_page_accessed(page); + bitmap_page = page; + bitmap = page_address(page) + (poff * sb->s_blocksize); + + /* init buddy cache */ + block++; + pnum = block / blocks_per_page; + poff = block % blocks_per_page; + page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + if (page == bitmap_page) { + /* + * If both the bitmap and buddy are in + * the same page we don't need to force + * init the buddy + */ + unlock_page(page); + } else if (page) { + BUG_ON(page->mapping != inode->i_mapping); + ret = ext4_mb_init_cache(page, bitmap); + if (ret) { + unlock_page(page); + goto err; + } + unlock_page(page); + } + if (page == NULL || !PageUptodate(page)) { + ret = -EIO; + goto err; + } + mark_page_accessed(page); +err: + ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked); + if (bitmap_page) + page_cache_release(bitmap_page); + if (page) + page_cache_release(page); + return ret; +} + static noinline_for_stack int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) @@ -922,7 +1018,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; - mb_debug("load group %u\n", group); + mb_debug(1, "load group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); @@ -941,8 +1037,26 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, * groups mapped by the page is blocked * till we are done with allocation */ +repeat_load_buddy: down_read(e4b->alloc_semp); + if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { + /* we need to check for group need init flag + * with alloc_semp held so that we can be sure + * that new blocks didn't get added to the group + * when we are loading the buddy cache + */ + up_read(e4b->alloc_semp); + /* + * we need full data about the group + * to make a good selection + */ + ret = ext4_mb_init_group(sb, group); + if (ret) + return ret; + goto repeat_load_buddy; + } + /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. @@ -1360,7 +1474,7 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, ac->alloc_semp = e4b->alloc_semp; e4b->alloc_semp = NULL; /* store last allocated for subsequent stream allocation */ - if ((ac->ac_flags & EXT4_MB_HINT_DATA)) { + if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; @@ -1837,97 +1951,6 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb, } -static noinline_for_stack -int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) -{ - - int ret; - void *bitmap; - int blocks_per_page; - int block, pnum, poff; - int num_grp_locked = 0; - struct ext4_group_info *this_grp; - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct inode *inode = sbi->s_buddy_cache; - struct page *page = NULL, *bitmap_page = NULL; - - mb_debug("init group %lu\n", group); - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; - this_grp = ext4_get_group_info(sb, group); - /* - * This ensures we don't add group - * to this buddy cache via resize - */ - num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group); - if (!EXT4_MB_GRP_NEED_INIT(this_grp)) { - /* - * somebody initialized the group - * return without doing anything - */ - ret = 0; - goto err; - } - /* - * the buddy cache inode stores the block bitmap - * and buddy information in consecutive blocks. - * So for each group we need two blocks. - */ - block = group * 2; - pnum = block / blocks_per_page; - poff = block % blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); - if (page) { - BUG_ON(page->mapping != inode->i_mapping); - ret = ext4_mb_init_cache(page, NULL); - if (ret) { - unlock_page(page); - goto err; - } - unlock_page(page); - } - if (page == NULL || !PageUptodate(page)) { - ret = -EIO; - goto err; - } - mark_page_accessed(page); - bitmap_page = page; - bitmap = page_address(page) + (poff * sb->s_blocksize); - - /* init buddy cache */ - block++; - pnum = block / blocks_per_page; - poff = block % blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); - if (page == bitmap_page) { - /* - * If both the bitmap and buddy are in - * the same page we don't need to force - * init the buddy - */ - unlock_page(page); - } else if (page) { - BUG_ON(page->mapping != inode->i_mapping); - ret = ext4_mb_init_cache(page, bitmap); - if (ret) { - unlock_page(page); - goto err; - } - unlock_page(page); - } - if (page == NULL || !PageUptodate(page)) { - ret = -EIO; - goto err; - } - mark_page_accessed(page); -err: - ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked); - if (bitmap_page) - page_cache_release(bitmap_page); - if (page) - page_cache_release(page); - return ret; -} - static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { @@ -1938,11 +1961,14 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; - loff_t size, isize; sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(sb); + /* non-extent files are limited to low blocks/groups */ + if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL)) + ngroups = sbi->s_blockfile_groups; + BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ @@ -1974,20 +2000,16 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) } bsbits = ac->ac_sb->s_blocksize_bits; - /* if stream allocation is enabled, use global goal */ - size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len; - isize = i_size_read(ac->ac_inode) >> bsbits; - if (size < isize) - size = isize; - if (size < sbi->s_mb_stream_request && - (ac->ac_flags & EXT4_MB_HINT_DATA)) { + /* if stream allocation is enabled, use global goal */ + if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } + /* Let's just scan groups to find more-less suitable blocks */ cr = ac->ac_2order ? 0 : 1; /* @@ -2015,27 +2037,6 @@ repeat: if (grp->bb_free == 0) continue; - /* - * if the group is already init we check whether it is - * a good group and if not we don't load the buddy - */ - if (EXT4_MB_GRP_NEED_INIT(grp)) { - /* - * we need full data about the group - * to make a good selection - */ - err = ext4_mb_init_group(sb, group); - if (err) - goto out; - } - - /* - * If the particular group doesn't satisfy our - * criteria we continue with the next group - */ - if (!ext4_mb_good_group(ac, group, cr)) - continue; - err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; @@ -2095,207 +2096,6 @@ out: return err; } -#ifdef EXT4_MB_HISTORY -struct ext4_mb_proc_session { - struct ext4_mb_history *history; - struct super_block *sb; - int start; - int max; -}; - -static void *ext4_mb_history_skip_empty(struct ext4_mb_proc_session *s, - struct ext4_mb_history *hs, - int first) -{ - if (hs == s->history + s->max) - hs = s->history; - if (!first && hs == s->history + s->start) - return NULL; - while (hs->orig.fe_len == 0) { - hs++; - if (hs == s->history + s->max) - hs = s->history; - if (hs == s->history + s->start) - return NULL; - } - return hs; -} - -static void *ext4_mb_seq_history_start(struct seq_file *seq, loff_t *pos) -{ - struct ext4_mb_proc_session *s = seq->private; - struct ext4_mb_history *hs; - int l = *pos; - - if (l == 0) - return SEQ_START_TOKEN; - hs = ext4_mb_history_skip_empty(s, s->history + s->start, 1); - if (!hs) - return NULL; - while (--l && (hs = ext4_mb_history_skip_empty(s, ++hs, 0)) != NULL); - return hs; -} - -static void *ext4_mb_seq_history_next(struct seq_file *seq, void *v, - loff_t *pos) -{ - struct ext4_mb_proc_session *s = seq->private; - struct ext4_mb_history *hs = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ext4_mb_history_skip_empty(s, s->history + s->start, 1); - else - return ext4_mb_history_skip_empty(s, ++hs, 0); -} - -static int ext4_mb_seq_history_show(struct seq_file *seq, void *v) -{ - char buf[25], buf2[25], buf3[25], *fmt; - struct ext4_mb_history *hs = v; - - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-5s %-8s %-23s %-23s %-23s %-5s " - "%-5s %-2s %-5s %-5s %-5s %-6s\n", - "pid", "inode", "original", "goal", "result", "found", - "grps", "cr", "flags", "merge", "tail", "broken"); - return 0; - } - - if (hs->op == EXT4_MB_HISTORY_ALLOC) { - fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u " - "%-5u %-5s %-5u %-6u\n"; - sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len, - hs->result.fe_logical); - sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group, - hs->orig.fe_start, hs->orig.fe_len, - hs->orig.fe_logical); - sprintf(buf3, "%u/%d/%u@%u", hs->goal.fe_group, - hs->goal.fe_start, hs->goal.fe_len, - hs->goal.fe_logical); - seq_printf(seq, fmt, hs->pid, hs->ino, buf, buf3, buf2, - hs->found, hs->groups, hs->cr, hs->flags, - hs->merged ? "M" : "", hs->tail, - hs->buddy ? 1 << hs->buddy : 0); - } else if (hs->op == EXT4_MB_HISTORY_PREALLOC) { - fmt = "%-5u %-8u %-23s %-23s %-23s\n"; - sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len, - hs->result.fe_logical); - sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group, - hs->orig.fe_start, hs->orig.fe_len, - hs->orig.fe_logical); - seq_printf(seq, fmt, hs->pid, hs->ino, buf, "", buf2); - } else if (hs->op == EXT4_MB_HISTORY_DISCARD) { - sprintf(buf2, "%u/%d/%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len); - seq_printf(seq, "%-5u %-8u %-23s discard\n", - hs->pid, hs->ino, buf2); - } else if (hs->op == EXT4_MB_HISTORY_FREE) { - sprintf(buf2, "%u/%d/%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len); - seq_printf(seq, "%-5u %-8u %-23s free\n", - hs->pid, hs->ino, buf2); - } - return 0; -} - -static void ext4_mb_seq_history_stop(struct seq_file *seq, void *v) -{ -} - -static struct seq_operations ext4_mb_seq_history_ops = { - .start = ext4_mb_seq_history_start, - .next = ext4_mb_seq_history_next, - .stop = ext4_mb_seq_history_stop, - .show = ext4_mb_seq_history_show, -}; - -static int ext4_mb_seq_history_open(struct inode *inode, struct file *file) -{ - struct super_block *sb = PDE(inode)->data; - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_mb_proc_session *s; - int rc; - int size; - - if (unlikely(sbi->s_mb_history == NULL)) - return -ENOMEM; - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return -ENOMEM; - s->sb = sb; - size = sizeof(struct ext4_mb_history) * sbi->s_mb_history_max; - s->history = kmalloc(size, GFP_KERNEL); - if (s->history == NULL) { - kfree(s); - return -ENOMEM; - } - - spin_lock(&sbi->s_mb_history_lock); - memcpy(s->history, sbi->s_mb_history, size); - s->max = sbi->s_mb_history_max; - s->start = sbi->s_mb_history_cur % s->max; - spin_unlock(&sbi->s_mb_history_lock); - - rc = seq_open(file, &ext4_mb_seq_history_ops); - if (rc == 0) { - struct seq_file *m = (struct seq_file *)file->private_data; - m->private = s; - } else { - kfree(s->history); - kfree(s); - } - return rc; - -} - -static int ext4_mb_seq_history_release(struct inode *inode, struct file *file) -{ - struct seq_file *seq = (struct seq_file *)file->private_data; - struct ext4_mb_proc_session *s = seq->private; - kfree(s->history); - kfree(s); - return seq_release(inode, file); -} - -static ssize_t ext4_mb_seq_history_write(struct file *file, - const char __user *buffer, - size_t count, loff_t *ppos) -{ - struct seq_file *seq = (struct seq_file *)file->private_data; - struct ext4_mb_proc_session *s = seq->private; - struct super_block *sb = s->sb; - char str[32]; - int value; - - if (count >= sizeof(str)) { - printk(KERN_ERR "EXT4-fs: %s string too long, max %u bytes\n", - "mb_history", (int)sizeof(str)); - return -EOVERFLOW; - } - - if (copy_from_user(str, buffer, count)) - return -EFAULT; - - value = simple_strtol(str, NULL, 0); - if (value < 0) - return -ERANGE; - EXT4_SB(sb)->s_mb_history_filter = value; - - return count; -} - -static struct file_operations ext4_mb_seq_history_fops = { - .owner = THIS_MODULE, - .open = ext4_mb_seq_history_open, - .read = seq_read, - .write = ext4_mb_seq_history_write, - .llseek = seq_lseek, - .release = ext4_mb_seq_history_release, -}; - static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = seq->private; @@ -2328,7 +2128,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct ext4_buddy e4b; struct sg { struct ext4_group_info info; - unsigned short counters[16]; + ext4_grpblk_t counters[16]; } sg; group--; @@ -2366,7 +2166,7 @@ static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } -static struct seq_operations ext4_mb_seq_groups_ops = { +static const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, @@ -2387,7 +2187,7 @@ static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file) } -static struct file_operations ext4_mb_seq_groups_fops = { +static const struct file_operations ext4_mb_seq_groups_fops = { .owner = THIS_MODULE, .open = ext4_mb_seq_groups_open, .read = seq_read, @@ -2395,82 +2195,6 @@ static struct file_operations ext4_mb_seq_groups_fops = { .release = seq_release, }; -static void ext4_mb_history_release(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - - if (sbi->s_proc != NULL) { - remove_proc_entry("mb_groups", sbi->s_proc); - if (sbi->s_mb_history_max) - remove_proc_entry("mb_history", sbi->s_proc); - } - kfree(sbi->s_mb_history); -} - -static void ext4_mb_history_init(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - int i; - - if (sbi->s_proc != NULL) { - if (sbi->s_mb_history_max) - proc_create_data("mb_history", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_history_fops, sb); - proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_groups_fops, sb); - } - - sbi->s_mb_history_cur = 0; - spin_lock_init(&sbi->s_mb_history_lock); - i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history); - sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL; - /* if we can't allocate history, then we simple won't use it */ -} - -static noinline_for_stack void -ext4_mb_store_history(struct ext4_allocation_context *ac) -{ - struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - struct ext4_mb_history h; - - if (sbi->s_mb_history == NULL) - return; - - if (!(ac->ac_op & sbi->s_mb_history_filter)) - return; - - h.op = ac->ac_op; - h.pid = current->pid; - h.ino = ac->ac_inode ? ac->ac_inode->i_ino : 0; - h.orig = ac->ac_o_ex; - h.result = ac->ac_b_ex; - h.flags = ac->ac_flags; - h.found = ac->ac_found; - h.groups = ac->ac_groups_scanned; - h.cr = ac->ac_criteria; - h.tail = ac->ac_tail; - h.buddy = ac->ac_buddy; - h.merged = 0; - if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) { - if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && - ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) - h.merged = 1; - h.goal = ac->ac_g_ex; - h.result = ac->ac_f_ex; - } - - spin_lock(&sbi->s_mb_history_lock); - memcpy(sbi->s_mb_history + sbi->s_mb_history_cur, &h, sizeof(h)); - if (++sbi->s_mb_history_cur >= sbi->s_mb_history_max) - sbi->s_mb_history_cur = 0; - spin_unlock(&sbi->s_mb_history_lock); -} - -#else -#define ext4_mb_history_release(sb) -#define ext4_mb_history_init(sb) -#endif - /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, @@ -2532,7 +2256,7 @@ 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_node = NULL; #ifdef DOUBLE_CHECK { @@ -2558,26 +2282,15 @@ exit_meta_group_info: return -ENOMEM; } /* ext4_mb_add_groupinfo */ -/* - * Update an existing group. - * This function is used for online resize - */ -void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add) -{ - grp->bb_free += add; -} - static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; - int metalen; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int num_meta_group_infos; int num_meta_group_infos_max; int array_size; - struct ext4_group_info **meta_group_info; struct ext4_group_desc *desc; /* This is the number of blocks used by GDT */ @@ -2622,22 +2335,6 @@ static int ext4_mb_init_backend(struct super_block *sb) goto err_freesgi; } EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; - - metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); - for (i = 0; i < num_meta_group_infos; i++) { - if ((i + 1) == num_meta_group_infos) - metalen = sizeof(*meta_group_info) * - (ngroups - - (i << EXT4_DESC_PER_BLOCK_BITS(sb))); - meta_group_info = kmalloc(metalen, GFP_KERNEL); - if (meta_group_info == NULL) { - printk(KERN_ERR "EXT4-fs: can't allocate mem for a " - "buddy group\n"); - goto err_freemeta; - } - sbi->s_group_info[i] = meta_group_info; - } - for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { @@ -2655,7 +2352,6 @@ err_freebuddy: while (i-- > 0) kfree(ext4_get_group_info(sb, i)); i = num_meta_group_infos; -err_freemeta: while (i-- > 0) kfree(sbi->s_group_info[i]); iput(sbi->s_buddy_cache); @@ -2672,14 +2368,14 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) unsigned max; int ret; - i = (sb->s_blocksize_bits + 2) * sizeof(unsigned short); + i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { return -ENOMEM; } - i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int); + i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { kfree(sbi->s_mb_offsets); @@ -2717,7 +2413,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; - sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT; sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC; sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); @@ -2735,12 +2430,12 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) spin_lock_init(&lg->lg_prealloc_lock); } - ext4_mb_history_init(sb); + if (sbi->s_proc) + proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, + &ext4_mb_seq_groups_fops, sb); if (sbi->s_journal) sbi->s_journal->j_commit_callback = release_blocks_on_commit; - - printk(KERN_INFO "EXT4-fs: mballoc enabled\n"); return 0; } @@ -2758,7 +2453,7 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) kmem_cache_free(ext4_pspace_cachep, pa); } if (count) - mb_debug("mballoc: %u PAs left\n", count); + mb_debug(1, "mballoc: %u PAs left\n", count); } @@ -2817,7 +2512,8 @@ int ext4_mb_release(struct super_block *sb) } free_percpu(sbi->s_locality_groups); - ext4_mb_history_release(sb); + if (sbi->s_proc) + remove_proc_entry("mb_groups", sbi->s_proc); return 0; } @@ -2839,7 +2535,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) list_for_each_safe(l, ltmp, &txn->t_private_list) { entry = list_entry(l, struct ext4_free_data, list); - mb_debug("gonna free %u blocks in group %u (0x%p):", + mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->count, entry->group, entry); err = ext4_mb_load_buddy(sb, entry->group, &e4b); @@ -2874,9 +2570,43 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) ext4_mb_release_desc(&e4b); } - mb_debug("freed %u blocks in %u structures\n", count, count2); + mb_debug(1, "freed %u blocks in %u structures\n", count, count2); +} + +#ifdef CONFIG_EXT4_DEBUG +u8 mb_enable_debug __read_mostly; + +static struct dentry *debugfs_dir; +static struct dentry *debugfs_debug; + +static void __init ext4_create_debugfs_entry(void) +{ + debugfs_dir = debugfs_create_dir("ext4", NULL); + if (debugfs_dir) + debugfs_debug = debugfs_create_u8("mballoc-debug", + S_IRUGO | S_IWUSR, + debugfs_dir, + &mb_enable_debug); +} + +static void ext4_remove_debugfs_entry(void) +{ + debugfs_remove(debugfs_debug); + debugfs_remove(debugfs_dir); } +#else + +static void __init ext4_create_debugfs_entry(void) +{ +} + +static void ext4_remove_debugfs_entry(void) +{ +} + +#endif + int __init init_ext4_mballoc(void) { ext4_pspace_cachep = @@ -2904,6 +2634,7 @@ int __init init_ext4_mballoc(void) kmem_cache_destroy(ext4_ac_cachep); return -ENOMEM; } + ext4_create_debugfs_entry(); return 0; } @@ -2917,6 +2648,7 @@ void exit_ext4_mballoc(void) kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); + ext4_remove_debugfs_entry(); } @@ -3061,7 +2793,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe; else ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; - mb_debug("#%u: goal %u blocks for locality group\n", + mb_debug(1, "#%u: goal %u blocks for locality group\n", current->pid, ac->ac_g_ex.fe_len); } @@ -3180,23 +2912,18 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end || ac->ac_o_ex.fe_logical < pa->pa_lstart)); - /* skip PA normalized request doesn't overlap with */ - if (pa->pa_lstart >= end) { - spin_unlock(&pa->pa_lock); - continue; - } - if (pa_end <= start) { + /* skip PAs this normalized request doesn't overlap with */ + if (pa->pa_lstart >= end || pa_end <= start) { spin_unlock(&pa->pa_lock); continue; } BUG_ON(pa->pa_lstart <= start && pa_end >= end); + /* adjust start or end to be adjacent to this pa */ if (pa_end <= ac->ac_o_ex.fe_logical) { BUG_ON(pa_end < start); start = pa_end; - } - - if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { + } else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { BUG_ON(pa->pa_lstart > end); end = pa->pa_lstart; } @@ -3251,7 +2978,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - mb_debug("goal: %u(was %u) blocks at %u\n", (unsigned) size, + mb_debug(1, "goal: %u(was %u) blocks at %u\n", (unsigned) size, (unsigned) orig_size, (unsigned) start); } @@ -3272,7 +2999,10 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) atomic_inc(&sbi->s_bal_breaks); } - ext4_mb_store_history(ac); + if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) + trace_ext4_mballoc_alloc(ac); + else + trace_ext4_mballoc_prealloc(ac); } /* @@ -3300,7 +3030,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(pa->pa_free < len); pa->pa_free -= len; - mb_debug("use %llu/%u from inode pa %p\n", start, len, pa); + mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa); } /* @@ -3324,7 +3054,7 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ - mb_debug("use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); + mb_debug(1, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); } /* @@ -3382,6 +3112,11 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len) continue; + /* non-extent files can't have physical blocks past 2^32 */ + if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) && + pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS) + continue; + /* found preallocated blocks, use them */ spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free) { @@ -3503,7 +3238,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, preallocated += len; count++; } - mb_debug("prellocated %u for group %u\n", preallocated, group); + mb_debug(1, "prellocated %u for group %u\n", preallocated, group); } static void ext4_mb_pa_callback(struct rcu_head *head) @@ -3638,7 +3373,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; - mb_debug("new inode pa %p: %llu/%u for %u\n", pa, + mb_debug(1, "new inode pa %p: %llu/%u for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); @@ -3698,7 +3433,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; - mb_debug("new group pa %p: %llu/%u for %u\n", pa, + mb_debug(1, "new group pa %p: %llu/%u for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); @@ -3767,7 +3502,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, if (ac) { ac->ac_sb = sb; ac->ac_inode = pa->pa_inode; - ac->ac_op = EXT4_MB_HISTORY_DISCARD; } while (bit < end) { @@ -3777,7 +3511,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, 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); - mb_debug(" free preallocated %u/%u in group %u\n", + mb_debug(1, " free preallocated %u/%u in group %u\n", (unsigned) start, (unsigned) next - bit, (unsigned) group); free += next - bit; @@ -3787,7 +3521,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = next - bit; ac->ac_b_ex.fe_logical = 0; - ext4_mb_store_history(ac); + trace_ext4_mballoc_discard(ac); } trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit, @@ -3822,9 +3556,6 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ext4_group_t group; ext4_grpblk_t bit; - if (ac) - ac->ac_op = EXT4_MB_HISTORY_DISCARD; - trace_ext4_mb_release_group_pa(ac, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); @@ -3839,7 +3570,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = pa->pa_len; ac->ac_b_ex.fe_logical = 0; - ext4_mb_store_history(ac); + trace_ext4_mballoc_discard(ac); } return 0; @@ -3868,7 +3599,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int busy = 0; int free = 0; - mb_debug("discard preallocation for group %u\n", group); + mb_debug(1, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) return 0; @@ -3992,7 +3723,7 @@ void ext4_discard_preallocations(struct inode *inode) return; } - mb_debug("discard preallocation for inode %lu\n", inode->i_ino); + mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode); INIT_LIST_HEAD(&list); @@ -4097,7 +3828,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode, { BUG_ON(!list_empty(&EXT4_I(inode)->i_prealloc_list)); } -#ifdef MB_DEBUG +#ifdef CONFIG_EXT4_DEBUG static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; @@ -4139,14 +3870,14 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); - printk(KERN_ERR "PA:%lu:%d:%u \n", i, - start, pa->pa_len); + printk(KERN_ERR "PA:%u:%d:%u \n", i, + start, pa->pa_len); } ext4_unlock_group(sb, i); if (grp->bb_free == 0) continue; - printk(KERN_ERR "%lu: %d/%d \n", + printk(KERN_ERR "%u: %d/%d \n", i, grp->bb_free, grp->bb_fragments); } printk(KERN_ERR "\n"); @@ -4174,16 +3905,26 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; + if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + return; + size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len; - isize = i_size_read(ac->ac_inode) >> bsbits; - size = max(size, isize); + isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) + >> bsbits; - /* don't use group allocation for large files */ - if (size >= sbi->s_mb_stream_request) + if ((size == isize) && + !ext4_fs_is_busy(sbi) && + (atomic_read(&ac->ac_inode->i_writecount) == 0)) { + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; + } - if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + /* don't use group allocation for large files */ + size = max(size, isize); + if (size >= sbi->s_mb_stream_request) { + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; + } BUG_ON(ac->ac_lg != NULL); /* @@ -4246,7 +3987,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); - mb_debug("init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, " + mb_debug(1, "init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, @@ -4268,7 +4009,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_prealloc_space *pa, *tmp; struct ext4_allocation_context *ac; - mb_debug("discard locality group preallocation\n"); + mb_debug(1, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); @@ -4720,7 +4461,6 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode, ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); if (ac) { - ac->ac_op = EXT4_MB_HISTORY_FREE; ac->ac_inode = inode; ac->ac_sb = sb; } @@ -4787,7 +4527,7 @@ do_more: ac->ac_b_ex.fe_group = block_group; ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = count; - ext4_mb_store_history(ac); + trace_ext4_mballoc_free(ac); } err = ext4_mb_load_buddy(sb, block_group, &e4b); diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index c96bb19f58f9..0ca811061bc7 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -37,25 +37,23 @@ /* */ -#define MB_DEBUG__ -#ifdef MB_DEBUG -#define mb_debug(fmt, a...) printk(fmt, ##a) +#ifdef CONFIG_EXT4_DEBUG +extern u8 mb_enable_debug; + +#define mb_debug(n, fmt, a...) \ + do { \ + if ((n) <= mb_enable_debug) { \ + printk(KERN_DEBUG "(%s, %d): %s: ", \ + __FILE__, __LINE__, __func__); \ + printk(fmt, ## a); \ + } \ + } while (0) #else -#define mb_debug(fmt, a...) +#define mb_debug(n, fmt, a...) #endif -/* - * with EXT4_MB_HISTORY mballoc stores last N allocations in memory - * and you can monitor it in /proc/fs/ext4/<dev>/mb_history - */ -#define EXT4_MB_HISTORY #define EXT4_MB_HISTORY_ALLOC 1 /* allocation */ #define EXT4_MB_HISTORY_PREALLOC 2 /* preallocated blocks used */ -#define EXT4_MB_HISTORY_DISCARD 4 /* preallocation discarded */ -#define EXT4_MB_HISTORY_FREE 8 /* free */ - -#define EXT4_MB_HISTORY_DEFAULT (EXT4_MB_HISTORY_ALLOC | \ - EXT4_MB_HISTORY_PREALLOC) /* * How long mballoc can look for a best extent (in found extents) @@ -76,7 +74,7 @@ * with 'ext4_mb_stats' allocator will collect stats that will be * shown at umount. The collecting costs though! */ -#define MB_DEFAULT_STATS 1 +#define MB_DEFAULT_STATS 0 /* * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served @@ -128,8 +126,8 @@ struct ext4_prealloc_space { unsigned pa_deleted; ext4_fsblk_t pa_pstart; /* phys. block */ ext4_lblk_t pa_lstart; /* log. block */ - unsigned short pa_len; /* len of preallocated chunk */ - unsigned short pa_free; /* how many blocks are free */ + ext4_grpblk_t pa_len; /* len of preallocated chunk */ + ext4_grpblk_t pa_free; /* how many blocks are free */ unsigned short pa_type; /* pa type. inode or group */ spinlock_t *pa_obj_lock; struct inode *pa_inode; /* hack, for history only */ @@ -144,7 +142,7 @@ struct ext4_free_extent { ext4_lblk_t fe_logical; ext4_grpblk_t fe_start; ext4_group_t fe_group; - int fe_len; + ext4_grpblk_t fe_len; }; /* @@ -209,22 +207,6 @@ struct ext4_allocation_context { #define AC_STATUS_FOUND 2 #define AC_STATUS_BREAK 3 -struct ext4_mb_history { - struct ext4_free_extent orig; /* orig allocation */ - struct ext4_free_extent goal; /* goal allocation */ - struct ext4_free_extent result; /* result allocation */ - unsigned pid; - unsigned ino; - __u16 found; /* how many extents have been found */ - __u16 groups; /* how many groups have been scanned */ - __u16 tail; /* what tail broke some buddy */ - __u16 buddy; /* buddy the tail ^^^ broke */ - __u16 flags; - __u8 cr:3; /* which phase the result extent was found at */ - __u8 op:4; - __u8 merged:1; -}; - struct ext4_buddy { struct page *bd_buddy_page; void *bd_buddy; @@ -239,13 +221,6 @@ struct ext4_buddy { #define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap) #define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy) -#ifndef EXT4_MB_HISTORY -static inline void ext4_mb_store_history(struct ext4_allocation_context *ac) -{ - return; -} -#endif - #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, diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 313a50b39741..a93d5b80f3e2 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -75,7 +75,7 @@ static int finish_range(handle_t *handle, struct inode *inode, goto err_out; } } - retval = ext4_ext_insert_extent(handle, inode, path, &newext); + retval = ext4_ext_insert_extent(handle, inode, path, &newext, 0); err_out: if (path) { ext4_ext_drop_refs(path); @@ -353,17 +353,16 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, down_write(&EXT4_I(inode)->i_data_sem); /* - * if EXT4_EXT_MIGRATE is cleared a block allocation + * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation * happened after we started the migrate. We need to * fail the migrate */ - if (!(EXT4_I(inode)->i_flags & EXT4_EXT_MIGRATE)) { + if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) { retval = -EAGAIN; up_write(&EXT4_I(inode)->i_data_sem); goto err_out; } else - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags & - ~EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE; /* * We have the extent map build with the tmp inode. * Now copy the i_data across @@ -517,14 +516,15 @@ int ext4_ext_migrate(struct inode *inode) * when we add extents we extent the journal */ /* - * Even though we take i_mutex we can still cause block allocation - * via mmap write to holes. If we have allocated new blocks we fail - * migrate. New block allocation will clear EXT4_EXT_MIGRATE flag. - * The flag is updated with i_data_sem held to prevent racing with - * block allocation. + * Even though we take i_mutex we can still cause block + * allocation via mmap write to holes. If we have allocated + * new blocks we fail migrate. New block allocation will + * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated + * with i_data_sem held to prevent racing with block + * allocation. */ down_read((&EXT4_I(inode)->i_data_sem)); - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags | EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE; up_read((&EXT4_I(inode)->i_data_sem)); handle = ext4_journal_start(inode, 1); @@ -618,7 +618,7 @@ err_out: tmp_inode->i_nlink = 0; ext4_journal_stop(handle); - + unlock_new_inode(tmp_inode); iput(tmp_inode); return retval; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index bbf2dd9404dc..25b6b1457360 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -19,14 +19,31 @@ #include "ext4_extents.h" #include "ext4.h" -#define get_ext_path(path, inode, block, ret) \ - do { \ - path = ext4_ext_find_extent(inode, block, path); \ - if (IS_ERR(path)) { \ - ret = PTR_ERR(path); \ - path = NULL; \ - } \ - } while (0) +/** + * get_ext_path - Find an extent path for designated logical block number. + * + * @inode: an inode which is searched + * @lblock: logical block number to find an extent path + * @path: pointer to an extent path pointer (for output) + * + * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value + * on failure. + */ +static inline int +get_ext_path(struct inode *inode, ext4_lblk_t lblock, + struct ext4_ext_path **path) +{ + int ret = 0; + + *path = ext4_ext_find_extent(inode, lblock, *path); + if (IS_ERR(*path)) { + ret = PTR_ERR(*path); + *path = NULL; + } else if ((*path)[ext_depth(inode)].p_ext == NULL) + ret = -ENODATA; + + return ret; +} /** * copy_extent_status - Copy the extent's initialization status @@ -113,6 +130,31 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, } /** + * mext_check_null_inode - NULL check for two inodes + * + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. + */ +static int +mext_check_null_inode(struct inode *inode1, struct inode *inode2, + const char *function) +{ + int ret = 0; + + if (inode1 == NULL) { + 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, + "Both inodes should not be NULL: " + "inode1 %lu inode2 NULL", inode1->i_ino); + ret = -EIO; + } + return ret; +} + +/** * mext_double_down_read - Acquire two inodes' read semaphore * * @orig_inode: original inode structure @@ -124,8 +166,6 @@ mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode) { struct inode *first = orig_inode, *second = donor_inode; - BUG_ON(orig_inode == NULL || donor_inode == NULL); - /* * Use the inode number to provide the stable locking order instead * of its address, because the C language doesn't guarantee you can @@ -152,8 +192,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) { struct inode *first = orig_inode, *second = donor_inode; - BUG_ON(orig_inode == NULL || donor_inode == NULL); - /* * Use the inode number to provide the stable locking order instead * of its address, because the C language doesn't guarantee you can @@ -178,8 +216,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) static void mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) { - BUG_ON(orig_inode == NULL || donor_inode == NULL); - up_read(&EXT4_I(orig_inode)->i_data_sem); up_read(&EXT4_I(donor_inode)->i_data_sem); } @@ -194,8 +230,6 @@ mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) static void mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode) { - BUG_ON(orig_inode == NULL || donor_inode == NULL); - up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); } @@ -283,23 +317,23 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, } if (new_flag) { - get_ext_path(orig_path, orig_inode, eblock, err); - if (orig_path == NULL) + err = get_ext_path(orig_inode, eblock, &orig_path); + if (err) goto out; if (ext4_ext_insert_extent(handle, orig_inode, - orig_path, new_ext)) + orig_path, new_ext, 0)) goto out; } if (end_flag) { - get_ext_path(orig_path, orig_inode, - le32_to_cpu(end_ext->ee_block) - 1, err); - if (orig_path == NULL) + err = get_ext_path(orig_inode, + le32_to_cpu(end_ext->ee_block) - 1, &orig_path); + if (err) goto out; if (ext4_ext_insert_extent(handle, orig_inode, - orig_path, end_ext)) + orig_path, end_ext, 0)) goto out; } out: @@ -519,7 +553,15 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, * oext |-----------| * new_ext |-------| */ - BUG_ON(le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end); + if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) { + ext4_error(orig_inode->i_sb, __func__, + "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), + oext_alen); + ret = -EIO; + goto out; + } /* * Case: new_ext is smaller than original extent @@ -543,6 +585,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, ret = mext_insert_extents(handle, orig_inode, orig_path, o_start, o_end, &start_ext, &new_ext, &end_ext); +out: return ret; } @@ -554,8 +597,10 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, * @orig_off: block offset of original inode * @donor_off: block offset of donor inode * @max_count: the maximun length of extents + * + * Return 0 on success, or a negative error value on failure. */ -static void +static int mext_calc_swap_extents(struct ext4_extent *tmp_dext, struct ext4_extent *tmp_oext, ext4_lblk_t orig_off, ext4_lblk_t donor_off, @@ -564,6 +609,19 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, ext4_lblk_t diff, orig_diff; struct ext4_extent dext_old, oext_old; + BUG_ON(orig_off != donor_off); + + /* original and donor extents have to cover the same block offset */ + if (orig_off < le32_to_cpu(tmp_oext->ee_block) || + le32_to_cpu(tmp_oext->ee_block) + + ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off) + return -ENODATA; + + if (orig_off < le32_to_cpu(tmp_dext->ee_block) || + le32_to_cpu(tmp_dext->ee_block) + + ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off) + return -ENODATA; + dext_old = *tmp_dext; oext_old = *tmp_oext; @@ -591,6 +649,8 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, copy_extent_status(&oext_old, tmp_dext); copy_extent_status(&dext_old, tmp_oext); + + return 0; } /** @@ -631,13 +691,13 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, mext_double_down_write(orig_inode, donor_inode); /* Get the original extent for the block "orig_off" */ - get_ext_path(orig_path, orig_inode, orig_off, err); - if (orig_path == NULL) + err = get_ext_path(orig_inode, orig_off, &orig_path); + if (err) goto out; /* Get the donor extent for the head */ - get_ext_path(donor_path, donor_inode, donor_off, err); - if (donor_path == NULL) + err = get_ext_path(donor_inode, donor_off, &donor_path); + if (err) goto out; depth = ext_depth(orig_inode); oext = orig_path[depth].p_ext; @@ -647,13 +707,28 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, dext = donor_path[depth].p_ext; tmp_dext = *dext; - mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, donor_off, count); + if (err) + goto out; /* Loop for the donor extents */ while (1) { /* The extent for donor must be found. */ - BUG_ON(!dext || donor_off != le32_to_cpu(tmp_dext.ee_block)); + if (!dext) { + ext4_error(donor_inode->i_sb, __func__, + "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__, + "Donor offset(%u) and the first block of donor " + "extent(%u) should be equal", + donor_off, + le32_to_cpu(tmp_dext.ee_block)); + err = -EIO; + goto out; + } /* Set donor extent to orig extent */ err = mext_leaf_block(handle, orig_inode, @@ -678,8 +753,8 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (orig_path) ext4_ext_drop_refs(orig_path); - get_ext_path(orig_path, orig_inode, orig_off, err); - if (orig_path == NULL) + err = get_ext_path(orig_inode, orig_off, &orig_path); + if (err) goto out; depth = ext_depth(orig_inode); oext = orig_path[depth].p_ext; @@ -692,9 +767,8 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (donor_path) ext4_ext_drop_refs(donor_path); - get_ext_path(donor_path, donor_inode, - donor_off, err); - if (donor_path == NULL) + err = get_ext_path(donor_inode, donor_off, &donor_path); + if (err) goto out; depth = ext_depth(donor_inode); dext = donor_path[depth].p_ext; @@ -705,9 +779,10 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, } tmp_dext = *dext; - mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, - count - replaced_count); + err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, count - replaced_count); + if (err) + goto out; } out: @@ -740,7 +815,7 @@ out: * on success, or a negative error value on failure. */ static int -move_extent_par_page(struct file *o_filp, struct inode *donor_inode, +move_extent_per_page(struct file *o_filp, struct inode *donor_inode, pgoff_t orig_page_offset, int data_offset_in_page, int block_len_in_page, int uninit) { @@ -871,6 +946,7 @@ out: if (PageLocked(page)) unlock_page(page); page_cache_release(page); + ext4_journal_stop(handle); } out2: ext4_journal_stop(handle); @@ -897,6 +973,10 @@ mext_check_arguments(struct inode *orig_inode, struct inode *donor_inode, __u64 orig_start, __u64 donor_start, __u64 *len, __u64 moved_len) { + ext4_lblk_t orig_blocks, donor_blocks; + 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 " @@ -921,14 +1001,6 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - /* orig and donor should be different file */ - if (orig_inode->i_ino == donor_inode->i_ino) { - ext4_debug("ext4 move extent: The argument files should not " - "be same file [ino:orig %lu, donor %lu]\n", - orig_inode->i_ino, donor_inode->i_ino); - return -EINVAL; - } - /* Ext4 move extent supports only extent based file */ if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) { ext4_debug("ext4 move extent: orig file is not extents " @@ -960,54 +1032,58 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - if ((orig_start > MAX_DEFRAG_SIZE) || - (donor_start > MAX_DEFRAG_SIZE) || - (*len > MAX_DEFRAG_SIZE) || - (orig_start + *len > MAX_DEFRAG_SIZE)) { - ext4_debug("ext4 move extent: Can't handle over [%lu] blocks " - "[ino:orig %lu, donor %lu]\n", MAX_DEFRAG_SIZE, + if ((orig_start > EXT_MAX_BLOCK) || + (donor_start > EXT_MAX_BLOCK) || + (*len > EXT_MAX_BLOCK) || + (orig_start + *len > EXT_MAX_BLOCK)) { + ext4_debug("ext4 move extent: Can't handle over [%u] blocks " + "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if (orig_inode->i_size > donor_inode->i_size) { - if (orig_start >= donor_inode->i_size) { + donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits; + /* TODO: eliminate this artificial restriction */ + if (orig_start >= donor_blocks) { ext4_debug("ext4 move extent: orig start offset " - "[%llu] should be less than donor file size " - "[%lld] [ino:orig %lu, donor_inode %lu]\n", - orig_start, donor_inode->i_size, + "[%llu] should be less than donor file blocks " + "[%u] [ino:orig %lu, donor %lu]\n", + orig_start, donor_blocks, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_start + *len > donor_inode->i_size) { + /* TODO: eliminate this artificial restriction */ + if (orig_start + *len > donor_blocks) { ext4_debug("ext4 move extent: End offset [%llu] should " - "be less than donor file size [%lld]." - "So adjust length from %llu to %lld " + "be less than donor file blocks [%u]." + "So adjust length from %llu to %llu " "[ino:orig %lu, donor %lu]\n", - orig_start + *len, donor_inode->i_size, - *len, donor_inode->i_size - orig_start, + orig_start + *len, donor_blocks, + *len, donor_blocks - orig_start, orig_inode->i_ino, donor_inode->i_ino); - *len = donor_inode->i_size - orig_start; + *len = donor_blocks - orig_start; } } else { - if (orig_start >= orig_inode->i_size) { + orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits; + if (orig_start >= orig_blocks) { ext4_debug("ext4 move extent: start offset [%llu] " - "should be less than original file size " - "[%lld] [inode:orig %lu, donor %lu]\n", - orig_start, orig_inode->i_size, + "should be less than original file blocks " + "[%u] [ino:orig %lu, donor %lu]\n", + orig_start, orig_blocks, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_start + *len > orig_inode->i_size) { + if (orig_start + *len > orig_blocks) { ext4_debug("ext4 move extent: Adjust length " - "from %llu to %lld. Because it should be " - "less than original file size " + "from %llu to %llu. Because it should be " + "less than original file blocks " "[ino:orig %lu, donor %lu]\n", - *len, orig_inode->i_size - orig_start, + *len, orig_blocks - orig_start, orig_inode->i_ino, donor_inode->i_ino); - *len = orig_inode->i_size - orig_start; + *len = orig_blocks - orig_start; } } @@ -1027,18 +1103,23 @@ mext_check_arguments(struct inode *orig_inode, * @inode1: the inode structure * @inode2: the inode structure * - * Lock two inodes' i_mutex by i_ino order. This function is moved from - * fs/inode.c. + * Lock two inodes' i_mutex by i_ino order. + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static void +static int mext_inode_double_lock(struct inode *inode1, struct inode *inode2) { - if (inode1 == NULL || inode2 == NULL || inode1 == inode2) { - if (inode1) - mutex_lock(&inode1->i_mutex); - else if (inode2) - mutex_lock(&inode2->i_mutex); - return; + int ret = 0; + + BUG_ON(inode1 == NULL && inode2 == NULL); + + ret = mext_check_null_inode(inode1, inode2, __func__); + if (ret < 0) + goto out; + + if (inode1 == inode2) { + mutex_lock(&inode1->i_mutex); + goto out; } if (inode1->i_ino < inode2->i_ino) { @@ -1048,6 +1129,9 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); } + +out: + return ret; } /** @@ -1056,17 +1140,28 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) * @inode1: the inode that is released first * @inode2: the inode that is released second * - * This function is moved from fs/inode.c. + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static void +static int mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) { + int ret = 0; + + BUG_ON(inode1 == NULL && inode2 == NULL); + + ret = mext_check_null_inode(inode1, inode2, __func__); + if (ret < 0) + goto out; + if (inode1) mutex_unlock(&inode1->i_mutex); if (inode2 && inode2 != inode1) mutex_unlock(&inode2->i_mutex); + +out: + return ret; } /** @@ -1123,70 +1218,84 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0; ext4_lblk_t rest_blocks; pgoff_t orig_page_offset = 0, seq_end_page; - int ret, depth, last_extent = 0; + int ret1, ret2, depth, last_extent = 0; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; int data_offset_in_page; int block_len_in_page; int uninit; + /* orig and donor should be different file */ + if (orig_inode->i_ino == donor_inode->i_ino) { + ext4_debug("ext4 move extent: The argument files should not " + "be same file [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + /* protect orig and donor against a truncate */ - mext_inode_double_lock(orig_inode, donor_inode); + ret1 = mext_inode_double_lock(orig_inode, donor_inode); + if (ret1 < 0) + return ret1; mext_double_down_read(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ - ret = mext_check_arguments(orig_inode, donor_inode, orig_start, + ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len, *moved_len); mext_double_up_read(orig_inode, donor_inode); - if (ret) - goto out2; + if (ret1) + goto out; file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; block_end = block_start + len - 1; if (file_end < block_end) len -= block_end - file_end; - get_ext_path(orig_path, orig_inode, block_start, ret); - if (orig_path == NULL) - goto out2; + ret1 = get_ext_path(orig_inode, block_start, &orig_path); + if (ret1) + goto out; /* Get path structure to check the hole */ - get_ext_path(holecheck_path, orig_inode, block_start, ret); - if (holecheck_path == NULL) + ret1 = get_ext_path(orig_inode, block_start, &holecheck_path); + if (ret1) goto out; depth = ext_depth(orig_inode); ext_cur = holecheck_path[depth].p_ext; - if (ext_cur == NULL) { - ret = -EINVAL; - goto out; - } /* - * Get proper extent whose ee_block is beyond block_start - * if block_start was within the hole. + * Get proper starting location of block replacement if block_start was + * within the hole. */ if (le32_to_cpu(ext_cur->ee_block) + ext4_ext_get_actual_len(ext_cur) - 1 < block_start) { + /* + * The hole exists between extents or the tail of + * original file. + */ last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; goto out; } last_extent = mext_next_extent(orig_inode, orig_path, &ext_dummy); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; goto out; } - } - seq_start = block_start; + seq_start = le32_to_cpu(ext_cur->ee_block); + } else if (le32_to_cpu(ext_cur->ee_block) > block_start) + /* The hole exists at the beginning of original file. */ + seq_start = le32_to_cpu(ext_cur->ee_block); + else + seq_start = block_start; /* No blocks within the specified range. */ if (le32_to_cpu(ext_cur->ee_block) > block_end) { ext4_debug("ext4 move extent: The specified range of file " "may be the hole\n"); - ret = -EINVAL; + ret1 = -EINVAL; goto out; } @@ -1206,7 +1315,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; break; } add_blocks = ext4_ext_get_actual_len(ext_cur); @@ -1258,16 +1367,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, while (orig_page_offset <= seq_end_page) { /* Swap original branches with new branches */ - ret = move_extent_par_page(o_filp, donor_inode, + ret1 = move_extent_per_page(o_filp, donor_inode, orig_page_offset, data_offset_in_page, block_len_in_page, uninit); - if (ret < 0) + if (ret1 < 0) goto out; orig_page_offset++; /* Count how many blocks we have exchanged */ *moved_len += block_len_in_page; - BUG_ON(*moved_len > len); + if (*moved_len > len) { + ext4_error(orig_inode->i_sb, __func__, + "We replaced blocks too much! " + "sum of replaced: %llu requested: %llu", + *moved_len, len); + ret1 = -EIO; + goto out; + } data_offset_in_page = 0; rest_blocks -= block_len_in_page; @@ -1280,17 +1396,16 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, /* Decrease buffer counter */ if (holecheck_path) ext4_ext_drop_refs(holecheck_path); - get_ext_path(holecheck_path, orig_inode, - seq_start, ret); - if (holecheck_path == NULL) + ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path); + if (ret1) break; depth = holecheck_path->p_depth; /* Decrease buffer counter */ if (orig_path) ext4_ext_drop_refs(orig_path); - get_ext_path(orig_path, orig_inode, seq_start, ret); - if (orig_path == NULL) + ret1 = get_ext_path(orig_inode, seq_start, &orig_path); + if (ret1) break; ext_cur = holecheck_path[depth].p_ext; @@ -1307,14 +1422,13 @@ out: ext4_ext_drop_refs(holecheck_path); kfree(holecheck_path); } -out2: - mext_inode_double_unlock(orig_inode, donor_inode); - if (ret) - return ret; + ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - /* All of the specified blocks must be exchanged in succeed */ - BUG_ON(*moved_len != len); + if (ret1) + return ret1; + else if (ret2) + return ret2; return 0; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 114abe5d2c1d..7c8fe80bacdd 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1518,8 +1518,12 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) - return make_indexed_dir(handle, dentry, inode, bh); + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + retval = make_indexed_dir(handle, dentry, inode, bh); + if (retval == -ENOSPC) + brelse(bh); + return retval; + } brelse(bh); } bh = ext4_append(handle, dir, &block, &retval); @@ -1528,7 +1532,10 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, de = (struct ext4_dir_entry_2 *) bh->b_data; de->inode = 0; de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize); - return add_dirent_to_buf(handle, dentry, inode, de, bh); + retval = add_dirent_to_buf(handle, dentry, inode, de, bh); + if (retval == -ENOSPC) + brelse(bh); + return retval; } /* @@ -1590,9 +1597,9 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, goto cleanup; node2 = (struct dx_node *)(bh2->b_data); entries2 = node2->entries; + memset(&node2->fake, 0, sizeof(struct fake_dirent)); node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize, sb->s_blocksize); - node2->fake.inode = 0; BUFFER_TRACE(frame->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, frame->bh); if (err) @@ -1657,7 +1664,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, if (!de) goto cleanup; err = add_dirent_to_buf(handle, dentry, inode, de, bh); - bh = NULL; + if (err != -ENOSPC) + bh = NULL; goto cleanup; journal_error: @@ -2068,7 +2076,8 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) struct ext4_iloc iloc; int err = 0; - if (!ext4_handle_valid(handle)) + /* ext4_handle_valid() assumes a valid handle_t pointer */ + if (handle && !ext4_handle_valid(handle)) return 0; mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock); @@ -2310,7 +2319,7 @@ static int ext4_link(struct dentry *old_dentry, struct inode *inode = old_dentry->d_inode; int err, retries = 0; - if (EXT4_DIR_LINK_MAX(inode)) + if (inode->i_nlink >= EXT4_LINK_MAX) return -EMLINK; /* @@ -2413,7 +2422,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; retval = -EMLINK; if (!new_inode && new_dir != old_dir && - new_dir->i_nlink >= EXT4_LINK_MAX) + EXT4_DIR_LINK_MAX(new_dir)) goto end_rename; } if (!new_bh) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 68b0351fc647..3cfc343c41b5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -746,7 +746,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) struct inode *inode = NULL; handle_t *handle; int gdb_off, gdb_num; - int num_grp_locked = 0; int err, err2; gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb); @@ -856,7 +855,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * using the new disk blocks. */ - num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, input->group); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)((char *)primary->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -875,10 +873,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * descriptor */ err = ext4_mb_add_groupinfo(sb, input->group, gdp); - if (err) { - ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked); + if (err) goto exit_journal; - } /* * Make the new blocks and inodes valid next. We do this before @@ -920,7 +916,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) /* Update the global fs size fields */ sbi->s_groups_count++; - ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked); ext4_handle_dirty_metadata(handle, NULL, primary); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8f4f079e6b9a..12e726a7073f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -45,17 +45,11 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include "mballoc.h" #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> -static int default_mb_history_length = 1000; - -module_param_named(default_mb_history_length, default_mb_history_length, - int, 0644); -MODULE_PARM_DESC(default_mb_history_length, - "Default number of entries saved for mb_history"); - struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; @@ -188,6 +182,36 @@ void ext4_itable_unused_set(struct super_block *sb, bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } + +/* Just increment the non-pointer handle value */ +static handle_t *ext4_get_nojournal(void) +{ + handle_t *handle = current->journal_info; + unsigned long ref_cnt = (unsigned long)handle; + + BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT); + + ref_cnt++; + handle = (handle_t *)ref_cnt; + + current->journal_info = handle; + return handle; +} + + +/* Decrement the non-pointer handle value */ +static void ext4_put_nojournal(handle_t *handle) +{ + unsigned long ref_cnt = (unsigned long)handle; + + BUG_ON(ref_cnt == 0); + + ref_cnt--; + handle = (handle_t *)ref_cnt; + + current->journal_info = handle; +} + /* * Wrappers for jbd2_journal_start/end. * @@ -214,11 +238,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) } return jbd2_journal_start(journal, nblocks); } - /* - * We're not journaling, return the appropriate indication. - */ - current->journal_info = EXT4_NOJOURNAL_HANDLE; - return current->journal_info; + return ext4_get_nojournal(); } /* @@ -234,11 +254,7 @@ int __ext4_journal_stop(const char *where, handle_t *handle) int rc; if (!ext4_handle_valid(handle)) { - /* - * Do this here since we don't call jbd2_journal_stop() in - * no-journal mode. - */ - current->journal_info = NULL; + ext4_put_nojournal(handle); return 0; } sb = handle->h_transaction->t_journal->j_private; @@ -344,7 +360,8 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, errstr = "Out of memory"; break; case -EROFS: - if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT) + if (!sb || (EXT4_SB(sb)->s_journal && + EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; @@ -578,6 +595,9 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + flush_workqueue(sbi->dio_unwritten_wq); + destroy_workqueue(sbi->dio_unwritten_wq); + lock_super(sb); lock_kernel(); if (sb->s_dirt) @@ -682,6 +702,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_allocated_meta_blocks = 0; ei->i_delalloc_reserved_flag = 0; spin_lock_init(&(ei->i_block_reservation_lock)); + INIT_LIST_HEAD(&ei->i_aio_dio_complete_list); + ei->cur_aio_dio = NULL; return &ei->vfs_inode; } @@ -962,7 +984,7 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); -static struct dquot_operations ext4_quota_operations = { +static const struct dquot_operations ext4_quota_operations = { .initialize = dquot_initialize, .drop = dquot_drop, .alloc_space = dquot_alloc_space, @@ -983,7 +1005,7 @@ static struct dquot_operations ext4_quota_operations = { .destroy_dquot = dquot_destroy, }; -static struct quotactl_ops ext4_qctl_operations = { +static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = vfs_quota_off, .quota_sync = vfs_quota_sync, @@ -1050,7 +1072,7 @@ enum { Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length, + Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, @@ -1097,7 +1119,6 @@ static const match_table_t tokens = { {Opt_data_writeback, "data=writeback"}, {Opt_data_err_abort, "data_err=abort"}, {Opt_data_err_ignore, "data_err=ignore"}, - {Opt_mb_history_length, "mb_history_length=%u"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, @@ -1279,11 +1300,9 @@ static int parse_options(char *options, struct super_block *sb, *journal_devnum = option; break; case Opt_journal_checksum: - set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); - break; + break; /* Kept for backwards compatibility */ case Opt_journal_async_commit: set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT); - set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); break; case Opt_noload: set_opt(sbi->s_mount_opt, NOLOAD); @@ -1340,13 +1359,6 @@ static int parse_options(char *options, struct super_block *sb, case Opt_data_err_ignore: clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT); break; - case Opt_mb_history_length: - if (match_int(&args[0], &option)) - return 0; - if (option < 0) - return 0; - sbi->s_mb_history_max = option; - break; #ifdef CONFIG_QUOTA case Opt_usrjquota: qtype = USRQUOTA; @@ -1646,13 +1658,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt); - if (EXT4_SB(sb)->s_journal) { - ext4_msg(sb, KERN_INFO, "%s journal on %s", - EXT4_SB(sb)->s_journal->j_inode ? "internal" : - "external", EXT4_SB(sb)->s_journal->j_devname); - } else { - ext4_msg(sb, KERN_INFO, "no journal"); - } return res; } @@ -1695,12 +1700,12 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_set(&sbi->s_flex_groups[flex_group].free_inodes, - ext4_free_inodes_count(sb, gdp)); - atomic_set(&sbi->s_flex_groups[flex_group].free_blocks, - ext4_free_blks_count(sb, gdp)); - atomic_set(&sbi->s_flex_groups[flex_group].used_dirs, - ext4_used_dirs_count(sb, gdp)); + atomic_add(ext4_free_inodes_count(sb, gdp), + &sbi->s_flex_groups[flex_group].free_inodes); + atomic_add(ext4_free_blks_count(sb, gdp), + &sbi->s_flex_groups[flex_group].free_blocks); + atomic_add(ext4_used_dirs_count(sb, gdp), + &sbi->s_flex_groups[flex_group].used_dirs); } return 1; @@ -2197,6 +2202,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump); static struct attribute *ext4_attrs[] = { ATTR_LIST(delayed_allocation_blocks), @@ -2210,6 +2216,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_order2_req), ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), + ATTR_LIST(max_writeback_mb_bump), NULL, }; @@ -2253,6 +2260,49 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +/* + * Check whether this filesystem can be mounted based on + * the features present and the RDONLY/RDWR mount requested. + * Returns 1 if this filesystem can be mounted as requested, + * 0 if it cannot be. + */ +static int ext4_feature_set_ok(struct super_block *sb, int readonly) +{ + if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) { + ext4_msg(sb, KERN_ERR, + "Couldn't mount because of " + "unsupported optional features (%x)", + (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & + ~EXT4_FEATURE_INCOMPAT_SUPP)); + return 0; + } + + if (readonly) + return 1; + + /* Check that feature set is OK for a read-write mount */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) { + ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " + "unsupported optional features (%x)", + (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & + ~EXT4_FEATURE_RO_COMPAT_SUPP)); + return 0; + } + /* + * Large file size enabled file system can only be mounted + * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF + */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + if (sizeof(blkcnt_t) < sizeof(u64)) { + ext4_msg(sb, KERN_ERR, "Filesystem with huge files " + "cannot be mounted RDWR without " + "CONFIG_LBDAF"); + return 0; + } + } + return 1; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) @@ -2274,7 +2324,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) unsigned int db_count; unsigned int i; int needs_recovery, has_huge_files; - int features; __u64 blocks_count; int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; @@ -2371,7 +2420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; - sbi->s_mb_history_max = default_mb_history_length; set_opt(sbi->s_mount_opt, BARRIER); @@ -2401,39 +2449,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ - features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP); - if (features) { - ext4_msg(sb, KERN_ERR, - "Couldn't mount because of " - "unsupported optional features (%x)", - (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & - ~EXT4_FEATURE_INCOMPAT_SUPP)); + if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY))) goto failed_mount; - } - features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP); - if (!(sb->s_flags & MS_RDONLY) && features) { - ext4_msg(sb, KERN_ERR, - "Couldn't mount RDWR because of " - "unsupported optional features (%x)", - (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & - ~EXT4_FEATURE_RO_COMPAT_SUPP)); - goto failed_mount; - } - has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE); - if (has_huge_files) { - /* - * Large file size enabled file system can only be - * mount if kernel is build with CONFIG_LBDAF - */ - if (sizeof(root->i_blocks) < sizeof(u64) && - !(sb->s_flags & MS_RDONLY)) { - ext4_msg(sb, KERN_ERR, "Filesystem with huge " - "files cannot be mounted read-write " - "without CONFIG_LBDAF"); - goto failed_mount; - } - } + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); if (blocksize < EXT4_MIN_BLOCK_SIZE || @@ -2469,6 +2487,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } + has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_HUGE_FILE); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); @@ -2549,12 +2569,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (ext4_blocks_count(es) > - (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + /* + * Test whether we have more sectors than will fit in sector_t, + * and whether the max offset is addressable by the page cache. + */ + if ((ext4_blocks_count(es) > + (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) || + (ext4_blocks_count(es) > + (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) { ext4_msg(sb, KERN_ERR, "filesystem" - " too large to mount safely"); + " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); + ret = -EFBIG; goto failed_mount; } @@ -2595,6 +2622,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } sbi->s_groups_count = blocks_count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), @@ -2656,6 +2685,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sbi->s_stripe = ext4_get_stripe_size(sbi); + sbi->s_max_writeback_mb_bump = 128; /* * set up enough so that it can read an inode @@ -2729,20 +2759,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount4; } - if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, + jbd2_journal_set_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + jbd2_journal_set_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else if (test_opt(sb, JOURNAL_CHECKSUM)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); + else jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else { - jbd2_journal_clear_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ @@ -2781,6 +2805,12 @@ no_journal: clear_opt(sbi->s_mount_opt, NOBH); } } + EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten"); + if (!EXT4_SB(sb)->dio_unwritten_wq) { + printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); + goto failed_mount_wq; + } + /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. @@ -2832,12 +2862,12 @@ no_journal: "available"); } - if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + if (test_opt(sb, DELALLOC) && + (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - " "requested data journaling mode"); clear_opt(sbi->s_mount_opt, DELALLOC); - } else if (test_opt(sb, DELALLOC)) - ext4_msg(sb, KERN_INFO, "delayed allocation enabled"); + } err = ext4_setup_system_zone(sb); if (err) { @@ -2893,6 +2923,8 @@ cantfind_ext4: failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); + destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq); +failed_mount_wq: ext4_release_system_zone(sb); if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -3147,9 +3179,7 @@ static int ext4_load_journal(struct super_block *sb, return -EINVAL; } - if (journal->j_flags & JBD2_BARRIER) - ext4_msg(sb, KERN_INFO, "barriers enabled"); - else + if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { @@ -3208,7 +3238,18 @@ static int ext4_commit_super(struct super_block *sb, int sync) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } - es->s_wtime = cpu_to_le32(get_seconds()); + /* + * If the file system is mounted read-only, don't update the + * superblock write time. This avoids updating the superblock + * write time when we are mounting the root file system + * read/only but we need to replay the journal; at that point, + * for people who are east of GMT and who make their clock + * tick in localtime for Windows bug-for-bug compatibility, + * the clock is set in the future, and this will cause e2fsck + * to complain and force a full file system check. + */ + if (!(sb->s_flags & MS_RDONLY)) + es->s_wtime = cpu_to_le32(get_seconds()); es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - @@ -3333,11 +3374,13 @@ static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; + struct ext4_sb_info *sbi = EXT4_SB(sb); trace_ext4_sync_fs(sb, wait); - if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { + flush_workqueue(sbi->dio_unwritten_wq); + if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) - jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target); + jbd2_log_wait_commit(sbi->s_journal, target); } return ret; } @@ -3477,18 +3520,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); } else { - int ret; - if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, - ~EXT4_FEATURE_RO_COMPAT_SUPP))) { - ext4_msg(sb, KERN_WARNING, "couldn't " - "remount RDWR because of unsupported " - "optional features (%x)", - (le32_to_cpu(sbi->s_es->s_feature_ro_compat) & - ~EXT4_FEATURE_RO_COMPAT_SUPP)); + /* Make sure we can mount this feature set readwrite */ + if (!ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } - /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 62b31c246994..fed5b01d7a8d 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -810,12 +810,23 @@ inserted: get_bh(new_bh); } else { /* We need to allocate a new block */ - ext4_fsblk_t goal = ext4_group_first_block_no(sb, + ext4_fsblk_t goal, block; + + goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); - ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode, + + /* non-extent files can't have physical blocks past 2^32 */ + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; + + block = ext4_new_meta_blocks(handle, inode, goal, NULL, &error); if (error) goto cleanup; + + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); + ea_idebug(inode, "creating block %d", block); new_bh = sb_getblk(sb, block); |