diff options
Diffstat (limited to 'fs/ext4')
| -rw-r--r-- | fs/ext4/Makefile | 2 | ||||
| -rw-r--r-- | fs/ext4/acl.c | 64 | ||||
| -rw-r--r-- | fs/ext4/acl.h | 4 | ||||
| -rw-r--r-- | fs/ext4/ext4.h | 57 | ||||
| -rw-r--r-- | fs/ext4/ext4_extents.h | 4 | ||||
| -rw-r--r-- | fs/ext4/ext4_jbd2.c | 4 | ||||
| -rw-r--r-- | fs/ext4/ext4_jbd2.h | 6 | ||||
| -rw-r--r-- | fs/ext4/extents.c | 5 | ||||
| -rw-r--r-- | fs/ext4/file.c | 36 | ||||
| -rw-r--r-- | fs/ext4/fsync.c | 8 | ||||
| -rw-r--r-- | fs/ext4/ialloc.c | 48 | ||||
| -rw-r--r-- | fs/ext4/inode.c | 655 | ||||
| -rw-r--r-- | fs/ext4/ioctl.c | 57 | ||||
| -rw-r--r-- | fs/ext4/mballoc.c | 125 | ||||
| -rw-r--r-- | fs/ext4/mballoc.h | 1 | ||||
| -rw-r--r-- | fs/ext4/migrate.c | 8 | ||||
| -rw-r--r-- | fs/ext4/move_extent.c | 1320 | ||||
| -rw-r--r-- | fs/ext4/namei.c | 10 | ||||
| -rw-r--r-- | fs/ext4/resize.c | 2 | ||||
| -rw-r--r-- | fs/ext4/super.c | 46 |
20 files changed, 1818 insertions, 644 deletions
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 8a34710ecf4..8867b2a1e5f 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o migrate.o mballoc.o block_validity.o + ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 647e0d65a28..f6d8967149c 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -126,30 +126,6 @@ fail: return ERR_PTR(-EINVAL); } -static inline struct posix_acl * -ext4_iget_acl(struct inode *inode, struct posix_acl **i_acl) -{ - struct posix_acl *acl = EXT4_ACL_NOT_CACHED; - - spin_lock(&inode->i_lock); - if (*i_acl != EXT4_ACL_NOT_CACHED) - acl = posix_acl_dup(*i_acl); - spin_unlock(&inode->i_lock); - - return acl; -} - -static inline void -ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != EXT4_ACL_NOT_CACHED) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - /* * Inode operation get_posix_acl(). * @@ -158,7 +134,6 @@ ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl, static struct posix_acl * ext4_get_acl(struct inode *inode, int type) { - struct ext4_inode_info *ei = EXT4_I(inode); int name_index; char *value = NULL; struct posix_acl *acl; @@ -167,23 +142,19 @@ ext4_get_acl(struct inode *inode, int type) if (!test_opt(inode->i_sb, POSIX_ACL)) return NULL; + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + switch (type) { case ACL_TYPE_ACCESS: - acl = ext4_iget_acl(inode, &ei->i_acl); - if (acl != EXT4_ACL_NOT_CACHED) - return acl; name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; break; - case ACL_TYPE_DEFAULT: - acl = ext4_iget_acl(inode, &ei->i_default_acl); - if (acl != EXT4_ACL_NOT_CACHED) - return acl; name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; break; - default: - return ERR_PTR(-EINVAL); + BUG(); } retval = ext4_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { @@ -200,17 +171,9 @@ ext4_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) { - switch (type) { - case ACL_TYPE_ACCESS: - ext4_iset_acl(inode, &ei->i_acl, acl); - break; + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext4_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return acl; } @@ -223,7 +186,6 @@ static int ext4_set_acl(handle_t *handle, struct inode *inode, int type, struct posix_acl *acl) { - struct ext4_inode_info *ei = EXT4_I(inode); int name_index; void *value = NULL; size_t size = 0; @@ -268,17 +230,9 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type, value, size, 0); kfree(value); - if (!error) { - switch (type) { - case ACL_TYPE_ACCESS: - ext4_iset_acl(inode, &ei->i_acl, acl); - break; + if (!error) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext4_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return error; } diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index cb45257a246..949789d2bba 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -53,10 +53,6 @@ static inline int ext4_acl_count(size_t size) #ifdef CONFIG_EXT4_FS_POSIX_ACL -/* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl - if the ACL has not been cached */ -#define EXT4_ACL_NOT_CACHED ((void *)-1) - /* acl.c */ extern int ext4_permission(struct inode *, int); extern int ext4_acl_chmod(struct inode *); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cc7d5edc38c..9714db393ef 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -93,20 +93,20 @@ typedef unsigned int ext4_group_t; struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; + /* how many blocks we want to allocate */ + unsigned int len; /* logical block in target inode */ ext4_lblk_t logical; - /* phys. target (a hint) */ - ext4_fsblk_t goal; /* the closest logical allocated block to the left */ ext4_lblk_t lleft; - /* phys. block for ^^^ */ - ext4_fsblk_t pleft; /* the closest logical allocated block to the right */ ext4_lblk_t lright; - /* phys. block for ^^^ */ + /* phys. target (a hint) */ + ext4_fsblk_t goal; + /* phys. block for the closest logical allocated block to the left */ + ext4_fsblk_t pleft; + /* phys. block for the closest logical allocated block to the right */ ext4_fsblk_t pright; - /* how many blocks we want to allocate */ - unsigned int len; /* flags. see above EXT4_MB_HINT_* */ unsigned int flags; }; @@ -352,6 +352,7 @@ struct ext4_new_group_data { /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ #define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) +#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent) /* * ioctl commands in 32 bit emulation @@ -447,6 +448,15 @@ struct ext4_inode { __le32 i_version_hi; /* high 32 bits for 64-bit version */ }; +struct move_extent { + __u32 reserved; /* should be zero */ + __u32 donor_fd; /* donor file descriptor */ + __u64 orig_start; /* logical start offset in block for orig */ + __u64 donor_start; /* logical start offset in block for donor */ + __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) @@ -585,10 +595,6 @@ struct ext4_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_EXT4_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif struct list_head i_orphan; /* unlinked but open inodes */ @@ -674,7 +680,6 @@ struct ext4_inode_info { #define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ #define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ #define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ -#define EXT4_MOUNT_ABORT 0x00200 /* Fatal error detected */ #define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ #define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ #define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ @@ -696,17 +701,10 @@ struct ext4_inode_info { #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ -/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ -#ifndef _LINUX_EXT2_FS_H #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt #define set_opt(o, opt) o |= EXT4_MOUNT_##opt #define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ EXT4_MOUNT_##opt) -#else -#define EXT2_MOUNT_NOLOAD EXT4_MOUNT_NOLOAD -#define EXT2_MOUNT_ABORT EXT4_MOUNT_ABORT -#define EXT2_MOUNT_DATA_FLAGS EXT4_MOUNT_DATA_FLAGS -#endif #define ext4_set_bit ext2_set_bit #define ext4_set_bit_atomic ext2_set_bit_atomic @@ -824,6 +822,13 @@ struct ext4_super_block { }; #ifdef __KERNEL__ + +/* + * run-time mount flags + */ +#define EXT4_MF_MNTDIR_SAMPLED 0x0001 +#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ + /* * fourth extended-fs super-block data in memory */ @@ -842,7 +847,8 @@ struct ext4_sb_info { struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ struct buffer_head **s_group_desc; - unsigned long s_mount_opt; + unsigned int s_mount_opt; + unsigned int s_mount_flags; ext4_fsblk_t s_sb_block; uid_t s_resuid; gid_t s_resgid; @@ -853,6 +859,7 @@ struct ext4_sb_info { int s_inode_size; int s_first_ino; unsigned int s_inode_readahead_blks; + unsigned int s_inode_goal; spinlock_t s_next_gen_lock; u32 s_next_generation; u32 s_hash_seed[4]; @@ -1305,7 +1312,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo); /* ialloc.c */ -extern struct inode * ext4_new_inode(handle_t *, struct inode *, int); +extern struct inode *ext4_new_inode(handle_t *, struct inode *, int, + const struct qstr *qstr, __u32 goal); extern void ext4_free_inode(handle_t *, struct inode *); extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); @@ -1329,7 +1337,7 @@ extern void ext4_discard_preallocations(struct inode *); extern int __init init_ext4_mballoc(void); extern void exit_ext4_mballoc(void); extern void ext4_mb_free_blocks(handle_t *, struct inode *, - unsigned long, unsigned long, int, unsigned long *); + 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, @@ -1647,6 +1655,11 @@ extern int ext4_get_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, int flags); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); +/* move_extent.c */ +extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, + __u64 start_orig, __u64 start_donor, + __u64 len, __u64 *moved_len); + /* * Add new method to test wether block and inode bitmaps are properly diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index f0c3ec85bd4..20a84105a10 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -221,12 +221,16 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *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 *); extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t); extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); +extern int ext4_can_extents_be_merged(struct inode *inode, + struct ext4_extent *ex1, + struct ext4_extent *ex2); extern int ext4_ext_try_to_merge(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index ad13a84644e..eb27fd0f2ee 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -43,6 +43,8 @@ int __ext4_journal_forget(const char *where, handle_t *handle, ext4_journal_abort_handle(where, __func__, bh, handle, err); } + else + brelse(bh); return err; } @@ -57,6 +59,8 @@ int __ext4_journal_revoke(const char *where, handle_t *handle, ext4_journal_abort_handle(where, __func__, bh, handle, err); } + else + brelse(bh); return err; } diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index be2f426f680..139fb8cb87e 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -131,9 +131,11 @@ int __ext4_journal_get_undo_access(const char *where, handle_t *handle, int __ext4_journal_get_write_access(const char *where, handle_t *handle, struct buffer_head *bh); +/* When called with an invalid handle, this will still do a put on the BH */ int __ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh); +/* When called with an invalid handle, this will still do a put on the BH */ int __ext4_journal_revoke(const char *where, handle_t *handle, ext4_fsblk_t blocknr, struct buffer_head *bh); @@ -281,10 +283,10 @@ static inline int ext4_should_order_data(struct inode *inode) static inline int ext4_should_writeback_data(struct inode *inode) { - if (EXT4_JOURNAL(inode) == NULL) - return 0; if (!S_ISREG(inode->i_mode)) return 0; + if (EXT4_JOURNAL(inode) == NULL) + return 1; if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) return 0; if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2593f748c3a..73ebfb44ad7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -49,7 +49,7 @@ * ext_pblock: * combine low and high parts of physical block number into ext4_fsblk_t */ -static ext4_fsblk_t ext_pblock(struct ext4_extent *ex) +ext4_fsblk_t ext_pblock(struct ext4_extent *ex) { ext4_fsblk_t block; @@ -1417,7 +1417,7 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, return err; } -static int +int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { @@ -1977,6 +1977,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); + return ret; } } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 588af8c7724..3f1873fef1c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -21,6 +21,8 @@ #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> +#include <linux/mount.h> +#include <linux/path.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" @@ -145,6 +147,38 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +static int ext4_file_open(struct inode * inode, struct file * filp) +{ + struct super_block *sb = inode->i_sb; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct vfsmount *mnt = filp->f_path.mnt; + struct path path; + char buf[64], *cp; + + if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) && + !(sb->s_flags & MS_RDONLY))) { + sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; + /* + * Sample where the filesystem has been mounted and + * store it in the superblock for sysadmin convenience + * when trying to sort through large numbers of block + * devices or filesystem images. + */ + memset(buf, 0, sizeof(buf)); + path.mnt = mnt->mnt_parent; + path.dentry = mnt->mnt_mountpoint; + path_get(&path); + cp = d_path(&path, buf, sizeof(buf)); + path_put(&path); + if (!IS_ERR(cp)) { + memcpy(sbi->s_es->s_last_mounted, cp, + sizeof(sbi->s_es->s_last_mounted)); + sb->s_dirt = 1; + } + } + return generic_file_open(inode, filp); +} + const struct file_operations ext4_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, @@ -156,7 +190,7 @@ const struct file_operations ext4_file_operations = { .compat_ioctl = ext4_compat_ioctl, #endif .mmap = ext4_file_mmap, - .open = generic_file_open, + .open = ext4_file_open, .release = ext4_release_file, .fsync = ext4_sync_file, .splice_read = generic_file_splice_read, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 5afe4370840..83cf6415f59 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -28,10 +28,12 @@ #include <linux/writeback.h> #include <linux/jbd2.h> #include <linux/blkdev.h> -#include <linux/marker.h> + #include "ext4.h" #include "ext4_jbd2.h" +#include <trace/events/ext4.h> + /* * akpm: A new design for ext4_sync_file(). * @@ -52,9 +54,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) J_ASSERT(ext4_journal_current_handle() == NULL); - trace_mark(ext4_sync_file, "dev %s datasync %d ino %ld parent %ld", - inode->i_sb->s_id, datasync, inode->i_ino, - dentry->d_parent->d_inode->i_ino); + trace_ext4_sync_file(file, dentry, datasync); /* * data=writeback: diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 3743bd849bc..29e6dc7299b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -23,11 +23,14 @@ #include <linux/bitops.h> #include <linux/blkdev.h> #include <asm/byteorder.h> + #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include <trace/events/ext4.h> + /* * ialloc.c contains the inodes allocation and deallocation routines */ @@ -208,11 +211,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) ino = inode->i_ino; ext4_debug("freeing inode %lu\n", ino); - trace_mark(ext4_free_inode, - "dev %s ino %lu mode %d uid %lu gid %lu bocks %llu", - sb->s_id, inode->i_ino, inode->i_mode, - (unsigned long) inode->i_uid, (unsigned long) inode->i_gid, - (unsigned long long) inode->i_blocks); + trace_ext4_free_inode(inode); /* * Note: we must free any quota before locking the superblock, @@ -471,7 +470,8 @@ void get_orlov_stats(struct super_block *sb, ext4_group_t g, */ static int find_group_orlov(struct super_block *sb, struct inode *parent, - ext4_group_t *group, int mode) + ext4_group_t *group, int mode, + const struct qstr *qstr) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -486,6 +486,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, struct ext4_group_desc *desc; struct orlov_stats stats; int flex_size = ext4_flex_bg_size(sbi); + struct dx_hash_info hinfo; ngroups = real_ngroups; if (flex_size > 1) { @@ -507,7 +508,13 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, int best_ndir = inodes_per_group; int ret = -1; - get_random_bytes(&grp, sizeof(grp)); + if (qstr) { + hinfo.hash_version = DX_HASH_HALF_MD4; + hinfo.seed = sbi->s_hash_seed; + ext4fs_dirhash(qstr->name, qstr->len, &hinfo); + grp = hinfo.hash; + } else + get_random_bytes(&grp, sizeof(grp)); parent_group = (unsigned)grp % ngroups; for (i = 0; i < ngroups; i++) { g = (parent_group + i) % ngroups; @@ -650,7 +657,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, *group = parent_group + flex_size; if (*group > ngroups) *group = 0; - return find_group_orlov(sb, parent, group, mode); + return find_group_orlov(sb, parent, group, mode, 0); } /* @@ -791,7 +798,8 @@ err_ret: * For other inodes, search forward from the parent directory's block * group to find a free inode. */ -struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) +struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, + const struct qstr *qstr, __u32 goal) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; @@ -815,14 +823,23 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) sb = dir->i_sb; ngroups = ext4_get_groups_count(sb); - trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id, - dir->i_ino, mode); + trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); sbi = EXT4_SB(sb); + if (!goal) + goal = sbi->s_inode_goal; + + if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) { + group = (goal - 1) / EXT4_INODES_PER_GROUP(sb); + ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb); + ret2 = 0; + goto got_group; + } + if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) { ret2 = find_group_flex(sb, dir, &group); if (ret2 == -1) { @@ -841,7 +858,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) if (test_opt(sb, OLDALLOC)) ret2 = find_group_dir(sb, dir, &group); else - ret2 = find_group_orlov(sb, dir, &group, mode); + ret2 = find_group_orlov(sb, dir, &group, mode, qstr); } else ret2 = find_group_other(sb, dir, &group, mode); @@ -851,7 +868,7 @@ got_group: if (ret2 == -1) goto out; - for (i = 0; i < ngroups; i++) { + for (i = 0; i < ngroups; i++, ino = 0) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); @@ -863,8 +880,6 @@ got_group: if (!inode_bitmap_bh) goto fail; - ino = 0; - repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) inode_bitmap_bh->b_data, @@ -1047,8 +1062,7 @@ got: } ext4_debug("allocating inode %lu\n", inode->i_ino); - trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d", - sb->s_id, inode->i_ino, dir->i_ino, mode); + trace_ext4_allocate_inode(inode, dir, mode); goto really_out; fail: ext4_std_error(sb, err); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 875db944b22..f9c642b22ef 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,11 +37,14 @@ #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> + #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "ext4_extents.h" +#include <trace/events/ext4.h> + #define MPAGE_DA_EXTENT_TAIL 0x01 static inline int ext4_begin_ordered_truncate(struct inode *inode, @@ -75,22 +78,20 @@ static int ext4_inode_is_fast_symlink(struct inode *inode) * but there may still be a record of it in the journal, and that record * still needs to be revoked. * - * If the handle isn't valid we're not journaling so there's nothing to do. + * If the handle isn't valid we're not journaling, but we still need to + * call into ext4_journal_revoke() to put the buffer head. */ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t blocknr) + struct buffer_head *bh, ext4_fsblk_t blocknr) { int err; - if (!ext4_handle_valid(handle)) - return 0; - might_sleep(); BUFFER_TRACE(bh, "enter"); jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, " - "data mode %lx\n", + "data mode %x\n", bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); @@ -329,8 +330,8 @@ static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) */ static int ext4_block_to_path(struct inode *inode, - ext4_lblk_t i_block, - ext4_lblk_t offsets[4], int *boundary) + ext4_lblk_t i_block, + ext4_lblk_t offsets[4], int *boundary) { int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb); int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb); @@ -362,9 +363,9 @@ static int ext4_block_to_path(struct inode *inode, final = ptrs; } else { ext4_warning(inode->i_sb, "ext4_block_to_path", - "block %lu > max in inode %lu", - i_block + direct_blocks + - indirect_blocks + double_blocks, inode->i_ino); + "block %lu > max in inode %lu", + i_block + direct_blocks + + indirect_blocks + double_blocks, inode->i_ino); } if (boundary) *boundary = final - 1 - (i_block & (ptrs - 1)); @@ -379,25 +380,25 @@ static int __ext4_check_blockref(const char *function, struct inode *inode, while (bref < p+max) { blk = le32_to_cpu(*bref++); - if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), + if (blk && + unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), blk, 1))) { ext4_error(inode->i_sb, function, "invalid block reference %u " "in inode #%lu", blk, inode->i_ino); - return -EIO; - } - } - return 0; + return -EIO; + } + } + return 0; } #define ext4_check_indirect_blockref(inode, bh) \ - __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data, \ + __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data, \ EXT4_ADDR_PER_BLOCK((inode)->i_sb)) #define ext4_check_inode_blockref(inode) \ - __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data, \ + __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data, \ EXT4_NDIR_BLOCKS) /** @@ -447,7 +448,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, bh = sb_getblk(sb, le32_to_cpu(p->key)); if (unlikely(!bh)) goto failure; - + if (!bh_uptodate_or_lock(bh)) { if (bh_submit_read(bh) < 0) { put_bh(bh); @@ -459,7 +460,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, goto failure; } } - + add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets); /* Reader: end */ if (!p->key) @@ -552,7 +553,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * returns it. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, - Indirect *partial) + Indirect *partial) { /* * XXX need to get goal block from mballoc's data structures @@ -574,7 +575,7 @@ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, * direct and indirect blocks. */ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, - int blocks_to_boundary) + int blocks_to_boundary) { unsigned int count = 0; @@ -610,9 +611,9 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, * direct blocks */ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, ext4_fsblk_t goal, - int indirect_blks, int blks, - ext4_fsblk_t new_blocks[4], int *err) + ext4_lblk_t iblock, ext4_fsblk_t goal, + int indirect_blks, int blks, + ext4_fsblk_t new_blocks[4], int *err) { struct ext4_allocation_request ar; int target, i; @@ -683,10 +684,10 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, } if (!*err) { if (target == blks) { - /* - * save the new block number - * for the first direct block - */ + /* + * save the new block number + * for the first direct block + */ new_blocks[index] = current_block; } blk_allocated += ar.len; @@ -728,9 +729,9 @@ failed_out: * as described above and return 0. */ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, int indirect_blks, - int *blks, ext4_fsblk_t goal, - ext4_lblk_t *offsets, Indirect *branch) + ext4_lblk_t iblock, int indirect_blks, + int *blks, ext4_fsblk_t goal, + ext4_lblk_t *offsets, Indirect *branch) { int blocksize = inode->i_sb->s_blocksize; int i, n = 0; @@ -777,7 +778,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, * the chain to point to the new allocated * data blocks numbers */ - for (i=1; i < num; i++) + for (i = 1; i < num; i++) *(branch[n].p + i) = cpu_to_le32(++current_block); } BUFFER_TRACE(bh, "marking uptodate"); @@ -820,7 +821,8 @@ failed: * chain to new block and return 0. */ static int ext4_splice_branch(handle_t *handle, struct inode *inode, - ext4_lblk_t block, Indirect *where, int num, int blks) + ext4_lblk_t block, Indirect *where, int num, + int blks) { int i; int err = 0; @@ -852,10 +854,6 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, } /* We are done with atomic stuff, now do the rest of housekeeping */ - - inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - /* had we spliced it onto indirect block? */ if (where->bh) { /* @@ -874,8 +872,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, } else { /* * OK, we spliced it into the inode itself on a direct block. - * Inode was dirtied above. */ + ext4_mark_inode_dirty(handle, inode); jbd_debug(5, "splicing direct\n"); } return err; @@ -921,9 +919,9 @@ err_out: * blocks. */ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, unsigned int maxblocks, - struct buffer_head *bh_result, - int flags) + ext4_lblk_t iblock, unsigned int maxblocks, + struct buffer_head *bh_result, + int flags) { int err = -EIO; ext4_lblk_t offsets[4]; @@ -939,7 +937,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, iblock, offsets, - &blocks_to_boundary); + &blocks_to_boundary); if (depth == 0) goto out; @@ -987,8 +985,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, * Block out ext4_truncate while we alter the tree */ err = ext4_alloc_branch(handle, inode, iblock, indirect_blks, - &count, goal, - offsets + (partial - chain), partial); + &count, goal, + offsets + (partial - chain), partial); /* * The ext4_splice_branch call will free and forget any buffers @@ -999,8 +997,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, */ if (!err) err = ext4_splice_branch(handle, inode, iblock, - partial, indirect_blks, count); - else + partial, indirect_blks, count); + else goto cleanup; set_buffer_new(bh_result); @@ -1172,7 +1170,7 @@ 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, + int ret = check_block_validity(inode, block, bh->b_blocknr, retval); if (ret != 0) return ret; @@ -1254,7 +1252,7 @@ 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, + int ret = check_block_validity(inode, block, bh->b_blocknr, retval); if (ret != 0) return ret; @@ -1405,8 +1403,7 @@ static int walk_page_buffers(handle_t *handle, for (bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); - block_start = block_end, bh = next) - { + block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { @@ -1447,7 +1444,7 @@ static int walk_page_buffers(handle_t *handle, * write. */ static int do_journal_get_write_access(handle_t *handle, - struct buffer_head *bh) + struct buffer_head *bh) { if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; @@ -1455,27 +1452,24 @@ static int do_journal_get_write_access(handle_t *handle, } static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; handle_t *handle; int retries = 0; struct page *page; - pgoff_t index; + pgoff_t index; unsigned from, to; - trace_mark(ext4_write_begin, - "dev %s ino %lu pos %llu len %u flags %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, flags); + trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason */ needed_blocks = ext4_writepage_trans_blocks(inode) + 1; - index = pos >> PAGE_CACHE_SHIFT; + index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; @@ -1517,14 +1511,14 @@ retry: * Add inode to orphan list in case we crash before * truncate finishes */ - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); - /* - * If vmtruncate failed early the inode might + ext4_truncate(inode); + /* + * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. @@ -1550,9 +1544,9 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh) } static int ext4_generic_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { int i_size_changed = 0; struct inode *inode = mapping->host; @@ -1603,25 +1597,22 @@ static int ext4_generic_write_end(struct file *file, * buffers are managed internally. */ static int ext4_ordered_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; - trace_mark(ext4_ordered_write_end, - "dev %s ino %lu pos %llu len %u copied %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, copied); + trace_ext4_ordered_write_end(inode, pos, len, copied); ret = ext4_jbd2_file_inode(handle, inode); if (ret == 0) { ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1635,9 +1626,9 @@ static int ext4_ordered_write_end(struct file *file, ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); - /* - * If vmtruncate failed early the inode might still be + ext4_truncate(inode); + /* + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -1650,22 +1641,19 @@ static int ext4_ordered_write_end(struct file *file, } static int ext4_writeback_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; - trace_mark(ext4_writeback_write_end, - "dev %s ino %lu pos %llu len %u copied %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, copied); + trace_ext4_writeback_write_end(inode, pos, len, copied); ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1680,9 +1668,9 @@ static int ext4_writeback_write_end(struct file *file, ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); - /* - * If vmtruncate failed early the inode might still be + ext4_truncate(inode); + /* + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -1694,9 +1682,9 @@ static int ext4_writeback_write_end(struct file *file, } static int ext4_journalled_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; @@ -1705,10 +1693,7 @@ static int ext4_journalled_write_end(struct file *file, unsigned from, to; loff_t new_i_size; - trace_mark(ext4_journalled_write_end, - "dev %s ino %lu pos %llu len %u copied %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, copied); + trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; @@ -1735,7 +1720,7 @@ static int ext4_journalled_write_end(struct file *file, unlock_page(page); page_cache_release(page); - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1746,9 +1731,9 @@ static int ext4_journalled_write_end(struct file *file, if (!ret) ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); - /* - * If vmtruncate failed early the inode might still be + ext4_truncate(inode); + /* + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -1854,7 +1839,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free) } static void ext4_da_page_release_reservation(struct page *page, - unsigned long offset) + unsigned long offset) { int to_release = 0; struct buffer_head *head, *bh; @@ -2318,15 +2303,9 @@ flush_it: return; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) { - /* - * unmapped buffer is possible for holes. - * delay buffer is possible with delayed allocation. - * We also need to consider unwritten buffer as unmapped. - */ - return (!buffer_mapped(bh) || buffer_delay(bh) || - buffer_unwritten(bh)) && buffer_dirty(bh); + return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } /* @@ -2411,9 +2390,9 @@ static int __mpage_da_writepage(struct page *page, * We need to try to allocate * unmapped blocks in the same page. * Otherwise we won't make progress - * with the page in ext4_da_writepage + * with the page in ext4_writepage */ - if (ext4_bh_unmapped_or_delay(NULL, bh)) { + if (ext4_bh_delay_or_unwritten(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); @@ -2530,7 +2509,6 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, * so call get_block_wrap with create = 0 */ ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); - BUG_ON(create && ret == 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -2538,15 +2516,102 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, return ret; } +static int bget_one(handle_t *handle, struct buffer_head *bh) +{ + get_bh(bh); + return 0; +} + +static int bput_one(handle_t *handle, struct buffer_head *bh) +{ + put_bh(bh); + return 0; +} + +static int __ext4_journalled_writepage(struct page *page, + struct writeback_control *wbc, + unsigned int len) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + struct buffer_head *page_bufs; + handle_t *handle = NULL; + int ret = 0; + int err; + + page_bufs = page_buffers(page); + BUG_ON(!page_bufs); + walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); + /* As soon as we unlock the page, it can go away, but we have + * references to buffers so we are safe */ + unlock_page(page); + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, + do_journal_get_write_access); + + err = walk_page_buffers(handle, page_bufs, 0, len, NULL, + write_end_fn); + if (ret == 0) + ret = err; + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + + walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); + EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; +out: + return ret; +} + /* + * Note that we don't need to start a transaction unless we're journaling data + * because we should have holes filled from ext4_page_mkwrite(). We even don't + * need to file the inode to the transaction's list in ordered mode because if + * we are writing back data added by write(), the inode is already there and if + * we are writing back data modified via mmap(), noone guarantees in which + * transaction the data will hit the disk. In case we are journaling data, we + * cannot start transaction directly because transaction start ranks above page + * lock so we have to do some magic. + * * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) * - shrink_page_list via pdflush (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) + * + * We don't do any block allocation in this function. If we have page with + * multiple blocks we need to write those buffer_heads that are mapped. This + * is important for mmaped based write. So if we do with blocksize 1K + * truncate(f, 1024); + * a = mmap(f, 0, 4096); + * a[0] = 'a'; + * truncate(f, 4096); + * we have in the page first buffer_head mapped via page_mkwrite call back + * but other bufer_heads would be unmapped but dirty(dirty done via the + * do_wp_page). So writepage should write the first block. If we modify + * the mmap area beyond 1024 we will again get a page_fault and the + * page_mkwrite callback will do the block allocation and mark the + * buffer_heads mapped. + * + * We redirty the page if we have any buffer_heads that is either delay or + * unwritten in the page. + * + * We can get recursively called as show below. + * + * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> + * ext4_writepage() + * + * But since we don't do any block allocation we should not deadlock. + * Page also have the dirty flag cleared so we don't get recurive page_lock. */ -static int ext4_da_writepage(struct page *page, - struct writeback_control *wbc) +static int ext4_writepage(struct page *page, + struct writeback_control *wbc) { int ret = 0; loff_t size; @@ -2554,9 +2619,7 @@ static int ext4_da_writepage(struct page *page, struct buffer_head *page_bufs; struct inode *inode = page->mapping->host; - trace_mark(ext4_da_writepage, - "dev %s ino %lu page_index %lu", - inode->i_sb->s_id, inode->i_ino, page->index); + trace_ext4_writepage(inode, page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; @@ -2566,7 +2629,7 @@ static int ext4_da_writepage(struct page *page, if (page_has_buffers(page)) { page_bufs = page_buffers(page); if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_unmapped_or_delay)) { + ext4_bh_delay_or_unwritten)) { /* * We don't want to do block allocation * So redirty the page and return @@ -2593,13 +2656,13 @@ static int ext4_da_writepage(struct page *page, * all are mapped and non delay. We don't want to * do block allocation here. */ - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, + ret = block_prepare_write(page, 0, len, noalloc_get_block_write); if (!ret) { page_bufs = page_buffers(page); /* check whether all are mapped and non delay */ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_unmapped_or_delay)) { + ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; @@ -2615,7 +2678,16 @@ static int ext4_da_writepage(struct page *page, return 0; } /* now mark the buffer_heads as dirty and uptodate */ - block_commit_write(page, 0, PAGE_CACHE_SIZE); + block_commit_write(page, 0, len); + } + + if (PageChecked(page) && ext4_should_journal_data(inode)) { + /* + * It's mmapped pagecache. Add buffers and journal it. There + * doesn't seem much point in redirtying the page here. + */ + ClearPageChecked(page); + return __ext4_journalled_writepage(page, wbc, len); } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) @@ -2667,19 +2739,7 @@ static int ext4_da_writepages(struct address_space *mapping, int needed_blocks, ret = 0, nr_to_writebump = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); - trace_mark(ext4_da_writepages, - "dev %s ino %lu nr_t_write %ld " - "pages_skipped %ld range_start %llu " - "range_end %llu nonblocking %d " - "for_kupdate %d for_reclaim %d " - "for_writepages %d range_cyclic %d", - inode->i_sb->s_id, inode->i_ino, - wbc->nr_to_write, wbc->pages_skipped, - (unsigned long long) wbc->range_start, - (unsigned long long) wbc->range_end, - wbc->nonblocking, wbc->for_kupdate, - wbc->for_reclaim, wbc->for_writepages, - wbc->range_cyclic); + trace_ext4_da_writepages(inode, wbc); /* * No pages to write? This is mainly a kludge to avoid starting @@ -2693,13 +2753,13 @@ static int ext4_da_writepages(struct address_space *mapping, * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test - * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because + * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_da_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ - if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT)) + if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) return -EROFS; /* @@ -2845,14 +2905,7 @@ out_writepages: if (!no_nrwrite_index_update) wbc->no_nrwrite_index_update = 0; wbc->nr_to_write -= nr_to_writebump; - trace_mark(ext4_da_writepage_result, - "dev %s ino %lu ret %d pages_written %d " - "pages_skipped %ld congestion %d " - "more_io %d no_nrwrite_index_update %d", - inode->i_sb->s_id, inode->i_ino, ret, - pages_written, wbc->pages_skipped, - wbc->encountered_congestion, wbc->more_io, - wbc->no_nrwrite_index_update); + trace_ext4_da_writepages_result(inode, wbc, ret, pages_written); return ret; } @@ -2884,8 +2937,8 @@ static int ext4_nonda_switch(struct super_block *sb) } static int ext4_da_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { int ret, retries = 0; struct page *page; @@ -2904,11 +2957,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, len, flags, pagep, fsdata); } *fsdata = (void *)0; - - trace_mark(ext4_da_write_begin, - "dev %s ino %lu pos %llu len %u flags %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, flags); + trace_ext4_da_write_begin(inode, pos, len, flags); retry: /* * With delayed allocation, we don't log the i_disksize update @@ -2945,7 +2994,7 @@ retry: * i_size_read because we hold i_mutex. */ if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -2959,7 +3008,7 @@ out: * when write to the end of file but not require block allocation */ static int ext4_da_should_update_i_disksize(struct page *page, - unsigned long offset) + unsigned long offset) { struct buffer_head *bh; struct inode *inode = page->mapping->host; @@ -2978,9 +3027,9 @@ static int ext4_da_should_update_i_disksize(struct page *page, } static int ext4_da_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { struct inode *inode = mapping->host; int ret = 0, ret2; @@ -3001,10 +3050,7 @@ static int ext4_da_write_end(struct file *file, } } - trace_mark(ext4_da_write_end, - "dev %s ino %lu pos %llu len %u copied %u", - inode->i_sb->s_id, inode->i_ino, - (unsigned long long) pos, len, copied); + trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_CACHE_SIZE - 1); end = start + copied - 1; @@ -3081,7 +3127,7 @@ int ext4_alloc_da_blocks(struct inode *inode) * not strictly speaking necessary (and for users of * laptop_mode, not even desirable). However, to do otherwise * would require replicating code paths in: - * + * * ext4_da_writepages() -> * write_cache_pages() ---> (via passed in callback function) * __mpage_da_writepage() --> @@ -3101,7 +3147,7 @@ int ext4_alloc_da_blocks(struct inode *inode) * write out the pages, but rather only collect contiguous * logical block extents, call the multi-block allocator, and * then update the buffer heads with the block allocations. - * + * * For now, though, we'll cheat by calling filemap_flush(), * which will map the blocks, and start the I/O, but not * actually wait for the I/O to complete. @@ -3171,226 +3217,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, ext4_get_block); } -static int bget_one(handle_t *handle, struct buffer_head *bh) -{ - get_bh(bh); - return 0; -} - -static int bput_one(handle_t *handle, struct buffer_head *bh) -{ - put_bh(bh); - return 0; -} - -/* - * Note that we don't need to start a transaction unless we're journaling data - * because we should have holes filled from ext4_page_mkwrite(). We even don't - * need to file the inode to the transaction's list in ordered mode because if - * we are writing back data added by write(), the inode is already there and if - * we are writing back data modified via mmap(), noone guarantees in which - * transaction the data will hit the disk. In case we are journaling data, we - * cannot start transaction directly because transaction start ranks above page - * lock so we have to do some magic. - * - * In all journaling modes block_write_full_page() will start the I/O. - * - * Problem: - * - * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> - * ext4_writepage() - * - * Similar for: - * - * ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ... - * - * Same applies to ext4_get_block(). We will deadlock on various things like - * lock_journal and i_data_sem - * - * Setting PF_MEMALLOC here doesn't work - too many internal memory - * allocations fail. - * - * 16May01: If we're reentered then journal_current_handle() will be - * non-zero. We simply *return*. - * - * 1 July 2001: @@@ FIXME: - * In journalled data mode, a data buffer may be metadata against the - * current transaction. But the same file is part of a shared mapping - * and someone does a writepage() on it. - * - * We will move the buffer onto the async_data list, but *after* it has - * been dirtied. So there's a small window where we have dirty data on - * BJ_Metadata. - * - * Note that this only applies to the last partial page in the file. The - * bit which block_write_full_page() uses prepare/commit for. (That's - * broken code anyway: it's wrong for msync()). - * - * It's a rare case: affects the final partial page, for journalled data - * where the file is subject to bith write() and writepage() in the same - * transction. To fix it we'll need a custom block_write_full_page(). - * We'll probably need that anyway for journalling writepage() output. - * - * We don't honour synchronous mounts for writepage(). That would be - * disastrous. Any write() or metadata operation will sync the fs for - * us. - * - */ -static int __ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - - if (test_opt(inode->i_sb, NOBH)) - return nobh_writepage(page, noalloc_get_block_write, wbc); - else - return block_write_full_page(page, noalloc_get_block_write, - wbc); -} - -static int ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - loff_t size = i_size_read(inode); - loff_t len; - - trace_mark(ext4_normal_writepage, - "dev %s ino %lu page_index %lu", - inode->i_sb->s_id, inode->i_ino, page->index); - J_ASSERT(PageLocked(page)); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - - if (page_has_buffers(page)) { - /* if page has buffers it should all be mapped - * and allocated. If there are not buffers attached - * to the page we know the page is dirty but it lost - * buffers. That means that at some moment in time - * after write_begin() / write_end() has been called - * all buffers have been clean and thus they must have been - * written at least once. So they are all mapped and we can - * happily proceed with mapping them and writing the page. - */ - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); - } - - if (!ext4_journal_current_handle()) - return __ext4_normal_writepage(page, wbc); - - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - -static int __ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; - struct buffer_head *page_bufs; - handle_t *handle = NULL; - int ret = 0; - int err; - - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - noalloc_get_block_write); - if (ret != 0) - goto out_unlock; - - page_bufs = page_buffers(page); - walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, - bget_one); - /* As soon as we unlock the page, it can go away, but we have - * references to buffers so we are safe */ - unlock_page(page); - - handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - - ret = walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, do_journal_get_write_access); - - err = walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, write_end_fn); - if (ret == 0) - ret = err; - err = ext4_journal_stop(handle); - if (!ret) - ret = err; - - walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, bput_one); - EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; - goto out; - -out_unlock: - unlock_page(page); -out: - return ret; -} - -static int ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - loff_t size = i_size_read(inode); - loff_t len; - - trace_mark(ext4_journalled_writepage, - "dev %s ino %lu page_index %lu", - inode->i_sb->s_id, inode->i_ino, page->index); - J_ASSERT(PageLocked(page)); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - - if (page_has_buffers(page)) { - /* if page has buffers it should all be mapped - * and allocated. If there are not buffers attached - * to the page we know the page is dirty but it lost - * buffers. That means that at some moment in time - * after write_begin() / write_end() has been called - * all buffers have been clean and thus they must have been - * written at least once. So they are all mapped and we can - * happily proceed with mapping them and writing the page. - */ - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); - } - - if (ext4_journal_current_handle()) - goto no_write; - - if (PageChecked(page)) { - /* - * It's mmapped pagecache. Add buffers and journal it. There - * doesn't seem much point in redirtying the page here. - */ - ClearPageChecked(page); - return __ext4_journalled_writepage(page, wbc); - } else { - /* - * It may be a page full of checkpoint-mode buffers. We don't - * really know unless we go poke around in the buffer_heads. - * But block_write_full_page will do the right thing. - */ - return block_write_full_page(page, noalloc_get_block_write, - wbc); - } -no_write: - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - static int ext4_readpage(struct file *file, struct page *page) { return mpage_readpage(page, ext4_get_block); @@ -3442,8 +3268,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait) * 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, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -3537,7 +3363,7 @@ static int ext4_journalled_set_page_dirty(struct page *page) static const struct address_space_operations ext4_ordered_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_ordered_write_end, @@ -3552,7 +3378,7 @@ static const struct address_space_operations ext4_ordered_aops = { static const struct address_space_operations ext4_writeback_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_writeback_write_end, @@ -3567,7 +3393,7 @@ static const struct address_space_operations ext4_writeback_aops = { static const struct address_space_operations ext4_journalled_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_journalled_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, @@ -3581,7 +3407,7 @@ static const struct address_space_operations ext4_journalled_aops = { static const struct address_space_operations ext4_da_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_da_writepage, + .writepage = ext4_writepage, .writepages = ext4_da_writepages, .sync_page = block_sync_page, .write_begin = ext4_da_write_begin, @@ -3628,7 +3454,8 @@ int ext4_block_truncate_page(handle_t *handle, struct page *page; int err = 0; - page = grab_cache_page(mapping, from >> PAGE_CACHE_SHIFT); + page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, + mapping_gfp_mask(mapping) & ~__GFP_FS); if (!page) return -EINVAL; @@ -3763,7 +3590,8 @@ static inline int all_zeroes(__le32 *p, __le32 *q) * (no partially truncated stuff there). */ static Indirect *ext4_find_shared(struct inode *inode, int depth, - ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top) + ext4_lblk_t offsets[4], Indirect chain[4], + __le32 *top) { Indirect *partial, *p; int k, err; @@ -3819,8 +3647,10 @@ no_top: * than `count' because there can be holes in there. */ static void ext4_clear_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t block_to_free, - unsigned long count, __le32 *first, __le32 *last) + struct buffer_head *bh, + ext4_fsblk_t block_to_free, + unsigned long count, __le32 *first, + __le32 *last) { __le32 *p; if (try_to_extend_transaction(handle, inode)) { @@ -3837,10 +3667,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode, } /* - * Any buffers which are on the journal will be in memory. We find - * them on the hash table so jbd2_journal_revoke() will run jbd2_journal_forget() - * on them. We've already detached each block from the file, so - * bforget() in jbd2_journal_forget() should be safe. + * Any buffers which are on the journal will be in memory. We + * find them on the hash table so jbd2_journal_revoke() will + * run jbd2_journal_forget() on them. We've already detached + * each block from the file, so bforget() in + * jbd2_journal_forget() should be safe. * * AKPM: turn on bforget in jbd2_journal_forget()!!! */ @@ -4212,7 +4043,7 @@ void ext4_truncate(struct inode *inode) (__le32*)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); BUFFER_TRACE(partial->bh, "call brelse"); - brelse (partial->bh); + brelse(partial->bh); partial--; } do_indirects: @@ -4453,8 +4284,9 @@ void ext4_get_inode_flags(struct ext4_inode_info *ei) if (flags & S_DIRSYNC) ei->i_flags |= EXT4_DIRSYNC_FL; } + static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, - struct ext4_inode_info *ei) + struct ext4_inode_info *ei) { blkcnt_t i_blocks ; struct inode *inode = &(ei->vfs_inode); @@ -4493,10 +4325,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT4_I(inode); -#ifdef CONFIG_EXT4_FS_POSIX_ACL - ei->i_acl = EXT4_ACL_NOT_CACHED; - ei->i_default_acl = EXT4_ACL_NOT_CACHED; -#endif ret = __ext4_get_inode_loc(inode, &iloc, 0); if (ret < 0) @@ -4569,7 +4397,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) - ei->i_state |= EXT4_STATE_XATTR; + ei->i_state |= EXT4_STATE_XATTR; } } else ei->i_extra_isize = 0; @@ -4588,7 +4416,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ret = 0; if (ei->i_file_acl && - ((ei->i_file_acl < + ((ei->i_file_acl < (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + EXT4_SB(sb)->s_gdb_count)) || (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) { @@ -4603,15 +4431,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) !ext4_inode_is_fast_symlink(inode))) /* Validate extent which is part of inode */ ret = ext4_ext_check_inode(inode); - } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || (S_ISLNK(inode->i_mode) && !ext4_inode_is_fast_symlink(inode))) { - /* Validate block references which are part of inode */ + /* Validate block references which are part of inode */ ret = ext4_check_inode_blockref(inode); } if (ret) { - brelse(bh); - goto bad_inode; + brelse(bh); + goto bad_inode; } if (S_ISREG(inode->i_mode)) { @@ -4642,7 +4470,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } else { brelse(bh); ret = -EIO; - ext4_error(inode->i_sb, __func__, + ext4_error(inode->i_sb, __func__, "bogus i_mode (%o) for inode=%lu", inode->i_mode, inode->i_ino); goto bad_inode; @@ -4795,8 +4623,9 @@ static int ext4_do_update_inode(handle_t *handle, cpu_to_le32(new_encode_dev(inode->i_rdev)); raw_inode->i_block[2] = 0; } - } else for (block = 0; block < EXT4_N_BLOCKS; block++) - raw_inode->i_block[block] = ei->i_data[block]; + } else + for (block = 0; block < EXT4_N_BLOCKS; block++) + raw_inode->i_block[block] = ei->i_data[block]; raw_inode->i_disk_version = cpu_to_le32(inode->i_version); if (ei->i_extra_isize) { @@ -5150,7 +4979,7 @@ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) * Give this, we know that the caller already has write access to iloc->bh. */ int ext4_mark_iloc_dirty(handle_t *handle, - struct inode *inode, struct ext4_iloc *iloc) + struct inode *inode, struct ext4_iloc *iloc) { int err = 0; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 91e75f7a9e7..7050a9cd04a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -12,8 +12,8 @@ #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> -#include <linux/smp_lock.h> #include <linux/mount.h> +#include <linux/file.h> #include <asm/uaccess.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -191,7 +191,7 @@ setversion_out: case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; struct super_block *sb = inode->i_sb; - int err, err2; + int err, err2=0; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -204,19 +204,56 @@ setversion_out: return err; err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); - jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); - jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + if (EXT4_SB(sb)->s_journal) { + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + } if (err == 0) err = err2; mnt_drop_write(filp->f_path.mnt); return err; } + + case EXT4_IOC_MOVE_EXT: { + struct move_extent me; + struct file *donor_filp; + int err; + + if (copy_from_user(&me, + (struct move_extent __user *)arg, sizeof(me))) + return -EFAULT; + + donor_filp = fget(me.donor_fd); + if (!donor_filp) + return -EBADF; + + if (!capable(CAP_DAC_OVERRIDE)) { + if ((current->real_cred->fsuid != inode->i_uid) || + !(inode->i_mode & S_IRUSR) || + !(donor_filp->f_dentry->d_inode->i_mode & + S_IRUSR)) { + fput(donor_filp); + return -EACCES; + } + } + + err = ext4_move_extents(filp, donor_filp, me.orig_start, + 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; + return err; + } + case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; struct super_block *sb = inode->i_sb; - int err, err2; + int err, err2=0; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -230,9 +267,11 @@ setversion_out: return err; err = ext4_group_add(sb, &input); - jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); - jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + if (EXT4_SB(sb)->s_journal) { + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + } if (err == 0) err = err2; mnt_drop_write(filp->f_path.mnt); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index ed8482e22c0..cd258463e2a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -22,6 +22,8 @@ */ #include "mballoc.h" +#include <trace/events/ext4.h> + /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() @@ -340,8 +342,6 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); static void release_blocks_on_commit(journal_t *journal, transaction_t *txn); - - static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 @@ -657,7 +657,8 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_generate_buddy(struct super_block *sb, +static noinline_for_stack +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); @@ -1480,7 +1481,8 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, ext4_mb_check_limits(ac, e4b, 0); } -static int ext4_mb_try_best_found(struct ext4_allocation_context *ac, +static noinline_for_stack +int ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; @@ -1507,7 +1509,8 @@ static int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return 0; } -static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, +static noinline_for_stack +int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; @@ -1566,7 +1569,8 @@ static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ -static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1609,7 +1613,8 @@ static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ -static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1668,7 +1673,8 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, * we try to find stripe-aligned chunks for stripe-size requests * XXX should do so at least for multiples of stripe size as well */ -static void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1831,7 +1837,8 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb, } -static int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) +static noinline_for_stack +int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) { int ret; @@ -2859,9 +2866,8 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb) + entry->start_blk + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); - trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u", - sb->s_id, (unsigned long long) discard_block, - entry->count); + trace_ext4_discard_blocks(sb, (unsigned long long)discard_block, + entry->count); sb_issue_discard(sb, discard_block, entry->count); kmem_cache_free(ext4_free_ext_cachep, entry); @@ -2903,7 +2909,11 @@ int __init init_ext4_mballoc(void) void exit_ext4_mballoc(void) { - /* XXX: synchronize_rcu(); */ + /* + * Wait for completion of call_rcu()'s on ext4_pspace_cachep + * before destroying the slab cache. + */ + rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); @@ -3458,7 +3468,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ -static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, +static noinline_for_stack +void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); @@ -3629,10 +3640,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) mb_debug("new inode pa %p: %llu/%u for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); - trace_mark(ext4_mb_new_inode_pa, - "dev %s ino %lu pstart %llu len %u lstart %u", - sb->s_id, ac->ac_inode->i_ino, - pa->pa_pstart, pa->pa_len, pa->pa_lstart); + trace_ext4_mb_new_inode_pa(ac, pa); ext4_mb_use_inode_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); @@ -3691,9 +3699,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) pa->pa_type = MB_GROUP_PA; mb_debug("new group pa %p: %llu/%u for %u\n", pa, - pa->pa_pstart, pa->pa_len, pa->pa_lstart); - trace_mark(ext4_mb_new_group_pa, "dev %s pstart %llu len %u lstart %u", - sb->s_id, pa->pa_pstart, pa->pa_len, pa->pa_lstart); + pa->pa_pstart, pa->pa_len, pa->pa_lstart); + trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); @@ -3783,10 +3790,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, ext4_mb_store_history(ac); } - trace_mark(ext4_mb_release_inode_pa, - "dev %s ino %lu block %llu count %u", - sb->s_id, pa->pa_inode->i_ino, grp_blk_start + bit, - next - bit); + trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit, + next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } @@ -3820,8 +3825,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, if (ac) ac->ac_op = EXT4_MB_HISTORY_DISCARD; - trace_mark(ext4_mb_release_group_pa, "dev %s pstart %llu len %d", - sb->s_id, pa->pa_pstart, pa->pa_len); + 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); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); @@ -3889,6 +3893,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, INIT_LIST_HEAD(&list); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); + if (ac) + ac->ac_sb = sb; repeat: ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, @@ -3987,12 +3993,15 @@ void ext4_discard_preallocations(struct inode *inode) } mb_debug("discard preallocation for inode %lu\n", inode->i_ino); - trace_mark(ext4_discard_preallocations, "dev %s ino %lu", sb->s_id, - inode->i_ino); + trace_ext4_discard_preallocations(inode); INIT_LIST_HEAD(&list); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); + if (ac) { + ac->ac_sb = sb; + ac->ac_inode = inode; + } repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); @@ -4218,14 +4227,9 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ + memset(ac, 0, sizeof(struct ext4_allocation_context)); ac->ac_b_ex.fe_logical = ar->logical; - ac->ac_b_ex.fe_group = 0; - ac->ac_b_ex.fe_start = 0; - ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; - ac->ac_groups_scanned = 0; - ac->ac_ex_scanned = 0; - ac->ac_found = 0; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ar->logical; @@ -4236,15 +4240,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ac->ac_g_ex.fe_group = group; ac->ac_g_ex.fe_start = block; ac->ac_g_ex.fe_len = len; - ac->ac_f_ex.fe_len = 0; ac->ac_flags = ar->flags; - ac->ac_2order = 0; - ac->ac_criteria = 0; - ac->ac_pa = NULL; - ac->ac_bitmap_page = NULL; - ac->ac_buddy_page = NULL; - ac->alloc_semp = NULL; - ac->ac_lg = NULL; /* we have to define context: we'll we work with a file or * locality group. this is a policy, actually */ @@ -4276,6 +4272,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, INIT_LIST_HEAD(&discard_list); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); + if (ac) + ac->ac_sb = sb; spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], @@ -4445,8 +4443,7 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) int ret; int freed = 0; - trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d", - sb->s_id, needed); + trace_ext4_mb_discard_preallocations(sb, needed); for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, needed); freed += ret; @@ -4475,17 +4472,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, sb = ar->inode->i_sb; sbi = EXT4_SB(sb); - trace_mark(ext4_request_blocks, "dev %s flags %u len %u ino %lu " - "lblk %llu goal %llu lleft %llu lright %llu " - "pleft %llu pright %llu ", - sb->s_id, ar->flags, ar->len, - ar->inode ? ar->inode->i_ino : 0, - (unsigned long long) ar->logical, - (unsigned long long) ar->goal, - (unsigned long long) ar->lleft, - (unsigned long long) ar->lright, - (unsigned long long) ar->pleft, - (unsigned long long) ar->pright); + trace_ext4_request_blocks(ar); /* * For delayed allocation, we could skip the ENOSPC and @@ -4594,18 +4581,7 @@ out3: reserv_blks); } - trace_mark(ext4_allocate_blocks, - "dev %s block %llu flags %u len %u ino %lu " - "logical %llu goal %llu lleft %llu lright %llu " - "pleft %llu pright %llu ", - sb->s_id, (unsigned long long) block, - ar->flags, ar->len, ar->inode ? ar->inode->i_ino : 0, - (unsigned long long) ar->logical, - (unsigned long long) ar->goal, - (unsigned long long) ar->lleft, - (unsigned long long) ar->lright, - (unsigned long long) ar->pleft, - (unsigned long long) ar->pright); + trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } @@ -4709,7 +4685,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * Main entry point into mballoc to free blocks */ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode, - unsigned long block, unsigned long count, + ext4_fsblk_t block, unsigned long count, int metadata, unsigned long *freed) { struct buffer_head *bitmap_bh = NULL; @@ -4735,15 +4711,12 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode, block + count > ext4_blocks_count(es)) { ext4_error(sb, __func__, "Freeing blocks not in datazone - " - "block = %lu, count = %lu", block, count); + "block = %llu, count = %lu", block, count); goto error_return; } - ext4_debug("freeing block %lu\n", block); - trace_mark(ext4_free_blocks, - "dev %s block %llu count %lu metadata %d ino %lu", - sb->s_id, (unsigned long long) block, count, metadata, - inode ? inode->i_ino : 0); + ext4_debug("freeing block %llu\n", block); + trace_ext4_free_blocks(inode, block, count, metadata); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); if (ac) { @@ -4784,7 +4757,7 @@ do_more: ext4_error(sb, __func__, "Freeing blocks in system zone - " - "Block = %lu, count = %lu", block, count); + "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_return; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 75e34f69215..c96bb19f58f 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -19,7 +19,6 @@ #include <linux/seq_file.h> #include <linux/version.h> #include <linux/blkdev.h> -#include <linux/marker.h> #include <linux/mutex.h> #include "ext4_jbd2.h" #include "ext4.h" diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index fe64d9f7985..313a50b3974 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -458,6 +458,7 @@ int ext4_ext_migrate(struct inode *inode) struct inode *tmp_inode = NULL; struct list_blocks_struct lb; unsigned long max_entries; + __u32 goal; /* * If the filesystem does not support extents, or the inode @@ -483,9 +484,10 @@ int ext4_ext_migrate(struct inode *inode) retval = PTR_ERR(handle); return retval; } - tmp_inode = ext4_new_inode(handle, - inode->i_sb->s_root->d_inode, - S_IFREG); + goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * + EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; + tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, + S_IFREG, 0, goal); if (IS_ERR(tmp_inode)) { retval = -ENOMEM; ext4_journal_stop(handle); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c new file mode 100644 index 00000000000..bbf2dd9404d --- /dev/null +++ b/fs/ext4/move_extent.c @@ -0,0 +1,1320 @@ +/* + * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd. + * Written by Takashi Sato <t-sato@yk.jp.nec.com> + * Akira Fujita <a-fujita@rs.jp.nec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/fs.h> +#include <linux/quotaops.h> +#include "ext4_jbd2.h" +#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) + +/** + * copy_extent_status - Copy the extent's initialization status + * + * @src: an extent for getting initialize status + * @dest: an extent to be set the status + */ +static void +copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest) +{ + if (ext4_ext_is_uninitialized(src)) + ext4_ext_mark_uninitialized(dest); + else + dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest)); +} + +/** + * mext_next_extent - Search for the next extent and set it to "extent" + * + * @inode: inode which is searched + * @path: this will obtain data for the next extent + * @extent: pointer to the next extent we have just gotten + * + * Search the next extent in the array of ext4_ext_path structure (@path) + * and set it to ext4_extent structure (@extent). In addition, the member of + * @path (->p_ext) also points the next extent. Return 0 on success, 1 if + * ext4_ext_path structure refers to the last extent, or a negative error + * value on failure. + */ +static int +mext_next_extent(struct inode *inode, struct ext4_ext_path *path, + struct ext4_extent **extent) +{ + int ppos, leaf_ppos = path->p_depth; + + ppos = leaf_ppos; + if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) { + /* leaf block */ + *extent = ++path[ppos].p_ext; + return 0; + } + + while (--ppos >= 0) { + if (EXT_LAST_INDEX(path[ppos].p_hdr) > + path[ppos].p_idx) { + int cur_ppos = ppos; + + /* index block */ + path[ppos].p_idx++; + path[ppos].p_block = idx_pblock(path[ppos].p_idx); + if (path[ppos+1].p_bh) + brelse(path[ppos+1].p_bh); + path[ppos+1].p_bh = + sb_bread(inode->i_sb, path[ppos].p_block); + if (!path[ppos+1].p_bh) + return -EIO; + path[ppos+1].p_hdr = + ext_block_hdr(path[ppos+1].p_bh); + + /* Halfway index block */ + while (++cur_ppos < leaf_ppos) { + path[cur_ppos].p_idx = + EXT_FIRST_INDEX(path[cur_ppos].p_hdr); + path[cur_ppos].p_block = + idx_pblock(path[cur_ppos].p_idx); + if (path[cur_ppos+1].p_bh) + brelse(path[cur_ppos+1].p_bh); + path[cur_ppos+1].p_bh = sb_bread(inode->i_sb, + path[cur_ppos].p_block); + if (!path[cur_ppos+1].p_bh) + return -EIO; + path[cur_ppos+1].p_hdr = + ext_block_hdr(path[cur_ppos+1].p_bh); + } + + /* leaf block */ + path[leaf_ppos].p_ext = *extent = + EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr); + return 0; + } + } + /* We found the last extent */ + return 1; +} + +/** + * mext_double_down_read - Acquire two inodes' read semaphore + * + * @orig_inode: original inode structure + * @donor_inode: donor inode structure + * Acquire read semaphore of the two inodes (orig and donor) by i_ino order. + */ +static void +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 + * compare pointers that don't come from the same array. + */ + if (donor_inode->i_ino < orig_inode->i_ino) { + first = donor_inode; + second = orig_inode; + } + + down_read(&EXT4_I(first)->i_data_sem); + down_read(&EXT4_I(second)->i_data_sem); +} + +/** + * mext_double_down_write - Acquire two inodes' write semaphore + * + * @orig_inode: original inode structure + * @donor_inode: donor inode structure + * Acquire write semaphore of the two inodes (orig and donor) by i_ino order. + */ +static void +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 + * compare pointers that don't come from the same array. + */ + if (donor_inode->i_ino < orig_inode->i_ino) { + first = donor_inode; + second = orig_inode; + } + + down_write(&EXT4_I(first)->i_data_sem); + down_write(&EXT4_I(second)->i_data_sem); +} + +/** + * mext_double_up_read - Release two inodes' read semaphore + * + * @orig_inode: original inode structure to be released its lock first + * @donor_inode: donor inode structure to be released its lock second + * Release read semaphore of two inodes (orig and donor). + */ +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); +} + +/** + * mext_double_up_write - Release two inodes' write semaphore + * + * @orig_inode: original inode structure to be released its lock first + * @donor_inode: donor inode structure to be released its lock second + * Release write semaphore of two inodes (orig and donor). + */ +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); +} + +/** + * mext_insert_across_blocks - Insert extents across leaf block + * + * @handle: journal handle + * @orig_inode: original inode + * @o_start: first original extent to be changed + * @o_end: last original extent to be changed + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * + * Allocate a new leaf block and insert extents into it. Return 0 on success, + * or a negative error value on failure. + */ +static int +mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, + struct ext4_extent *o_start, struct ext4_extent *o_end, + struct ext4_extent *start_ext, struct ext4_extent *new_ext, + struct ext4_extent *end_ext) +{ + struct ext4_ext_path *orig_path = NULL; + ext4_lblk_t eblock = 0; + int new_flag = 0; + int end_flag = 0; + int err = 0; + + if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) { + if (o_start == o_end) { + + /* start_ext new_ext end_ext + * donor |---------|-----------|--------| + * orig |------------------------------| + */ + end_flag = 1; + } else { + + /* start_ext new_ext end_ext + * donor |---------|----------|---------| + * orig |---------------|--------------| + */ + o_end->ee_block = end_ext->ee_block; + o_end->ee_len = end_ext->ee_len; + ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + } + + o_start->ee_len = start_ext->ee_len; + new_flag = 1; + + } else if (start_ext->ee_len && new_ext->ee_len && + !end_ext->ee_len && o_start == o_end) { + + /* start_ext new_ext + * donor |--------------|---------------| + * orig |------------------------------| + */ + o_start->ee_len = start_ext->ee_len; + new_flag = 1; + + } else if (!start_ext->ee_len && new_ext->ee_len && + end_ext->ee_len && o_start == o_end) { + + /* new_ext end_ext + * donor |--------------|---------------| + * orig |------------------------------| + */ + o_end->ee_block = end_ext->ee_block; + o_end->ee_len = end_ext->ee_len; + ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + + /* + * Set 0 to the extent block if new_ext was + * the first block. + */ + if (new_ext->ee_block) + eblock = le32_to_cpu(new_ext->ee_block); + + new_flag = 1; + } else { + ext4_debug("ext4 move extent: Unexpected insert case\n"); + return -EIO; + } + + if (new_flag) { + get_ext_path(orig_path, orig_inode, eblock, err); + if (orig_path == NULL) + goto out; + + if (ext4_ext_insert_extent(handle, orig_inode, + orig_path, new_ext)) + 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) + goto out; + + if (ext4_ext_insert_extent(handle, orig_inode, + orig_path, end_ext)) + goto out; + } +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + + return err; + +} + +/** + * mext_insert_inside_block - Insert new extent to the extent block + * + * @o_start: first original extent to be moved + * @o_end: last original extent to be moved + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * @eh: extent header of target leaf block + * @range_to_move: used to decide how to insert extent + * + * Insert extents into the leaf block. The extent (@o_start) is overwritten + * by inserted extents. + */ +static void +mext_insert_inside_block(struct ext4_extent *o_start, + struct ext4_extent *o_end, + struct ext4_extent *start_ext, + struct ext4_extent *new_ext, + struct ext4_extent *end_ext, + struct ext4_extent_header *eh, + int range_to_move) +{ + int i = 0; + unsigned long len; + + /* Move the existing extents */ + if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) { + len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) - + (unsigned long)(o_end + 1); + memmove(o_end + 1 + range_to_move, o_end + 1, len); + } + + /* Insert start entry */ + if (start_ext->ee_len) + o_start[i++].ee_len = start_ext->ee_len; + + /* Insert new entry */ + if (new_ext->ee_len) { + o_start[i] = *new_ext; + ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext)); + } + + /* Insert end entry */ + if (end_ext->ee_len) + o_start[i] = *end_ext; + + /* Increment the total entries counter on the extent block */ + le16_add_cpu(&eh->eh_entries, range_to_move); +} + +/** + * mext_insert_extents - Insert new extent + * + * @handle: journal handle + * @orig_inode: original inode + * @orig_path: path indicates first extent to be changed + * @o_start: first original extent to be changed + * @o_end: last original extent to be changed + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * + * Call the function to insert extents. If we cannot add more extents into + * the leaf block, we call mext_insert_across_blocks() to create a + * new leaf block. Otherwise call mext_insert_inside_block(). Return 0 + * on success, or a negative error value on failure. + */ +static int +mext_insert_extents(handle_t *handle, struct inode *orig_inode, + struct ext4_ext_path *orig_path, + struct ext4_extent *o_start, + struct ext4_extent *o_end, + struct ext4_extent *start_ext, + struct ext4_extent *new_ext, + struct ext4_extent *end_ext) +{ + struct ext4_extent_header *eh; + unsigned long need_slots, slots_range; + int range_to_move, depth, ret; + + /* + * The extents need to be inserted + * start_extent + new_extent + end_extent. + */ + need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) + + (new_ext->ee_len ? 1 : 0); + + /* The number of slots between start and end */ + slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1) + / sizeof(struct ext4_extent); + + /* Range to move the end of extent */ + range_to_move = need_slots - slots_range; + depth = orig_path->p_depth; + orig_path += depth; + eh = orig_path->p_hdr; + + if (depth) { + /* Register to journal */ + ret = ext4_journal_get_write_access(handle, orig_path->p_bh); + if (ret) + return ret; + } + + /* Expansion */ + if (range_to_move > 0 && + (range_to_move > le16_to_cpu(eh->eh_max) + - le16_to_cpu(eh->eh_entries))) { + + ret = mext_insert_across_blocks(handle, orig_inode, o_start, + o_end, start_ext, new_ext, end_ext); + if (ret < 0) + return ret; + } else + mext_insert_inside_block(o_start, o_end, start_ext, new_ext, + end_ext, eh, range_to_move); + + if (depth) { + ret = ext4_handle_dirty_metadata(handle, orig_inode, + orig_path->p_bh); + if (ret) + return ret; + } else { + ret = ext4_mark_inode_dirty(handle, orig_inode); + if (ret < 0) + return ret; + } + + return 0; +} + +/** + * mext_leaf_block - Move one leaf extent block into the inode. + * + * @handle: journal handle + * @orig_inode: original inode + * @orig_path: path indicates first extent to be changed + * @dext: donor extent + * @from: start offset on the target file + * + * In order to insert extents into the leaf block, we must divide the extent + * in the leaf block into three extents. The one is located to be inserted + * extents, and the others are located around it. + * + * Therefore, this function creates structures to save extents of the leaf + * block, and inserts extents by calling mext_insert_extents() with + * created extents. Return 0 on success, or a negative error value on failure. + */ +static int +mext_leaf_block(handle_t *handle, struct inode *orig_inode, + struct ext4_ext_path *orig_path, struct ext4_extent *dext, + ext4_lblk_t *from) +{ + struct ext4_extent *oext, *o_start, *o_end, *prev_ext; + struct ext4_extent new_ext, start_ext, end_ext; + ext4_lblk_t new_ext_end; + ext4_fsblk_t new_phys_end; + int oext_alen, new_ext_alen, end_ext_alen; + int depth = ext_depth(orig_inode); + int ret; + + o_start = o_end = oext = orig_path[depth].p_ext; + oext_alen = ext4_ext_get_actual_len(oext); + start_ext.ee_len = end_ext.ee_len = 0; + + new_ext.ee_block = cpu_to_le32(*from); + ext4_ext_store_pblock(&new_ext, ext_pblock(dext)); + new_ext.ee_len = dext->ee_len; + new_ext_alen = ext4_ext_get_actual_len(&new_ext); + new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1; + new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1; + + /* + * Case: original extent is first + * oext |--------| + * new_ext |--| + * start_ext |--| + */ + if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) && + le32_to_cpu(new_ext.ee_block) < + le32_to_cpu(oext->ee_block) + oext_alen) { + start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) - + le32_to_cpu(oext->ee_block)); + copy_extent_status(oext, &start_ext); + } else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) { + prev_ext = oext - 1; + /* + * We can merge new_ext into previous extent, + * if these are contiguous and same extent type. + */ + if (ext4_can_extents_be_merged(orig_inode, prev_ext, + &new_ext)) { + o_start = prev_ext; + start_ext.ee_len = cpu_to_le16( + ext4_ext_get_actual_len(prev_ext) + + new_ext_alen); + copy_extent_status(prev_ext, &start_ext); + new_ext.ee_len = 0; + } + } + + /* + * Case: new_ext_end must be less than oext + * oext |-----------| + * new_ext |-------| + */ + BUG_ON(le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end); + + /* + * Case: new_ext is smaller than original extent + * oext |---------------| + * new_ext |-----------| + * end_ext |---| + */ + if (le32_to_cpu(oext->ee_block) <= new_ext_end && + new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) { + end_ext.ee_len = + cpu_to_le16(le32_to_cpu(oext->ee_block) + + oext_alen - 1 - new_ext_end); + copy_extent_status(oext, &end_ext); + end_ext_alen = ext4_ext_get_actual_len(&end_ext); + ext4_ext_store_pblock(&end_ext, + (ext_pblock(o_end) + oext_alen - end_ext_alen)); + end_ext.ee_block = + cpu_to_le32(le32_to_cpu(o_end->ee_block) + + oext_alen - end_ext_alen); + } + + ret = mext_insert_extents(handle, orig_inode, orig_path, o_start, + o_end, &start_ext, &new_ext, &end_ext); + return ret; +} + +/** + * mext_calc_swap_extents - Calculate extents for extent swapping. + * + * @tmp_dext: the extent that will belong to the original inode + * @tmp_oext: the extent that will belong to the donor inode + * @orig_off: block offset of original inode + * @donor_off: block offset of donor inode + * @max_count: the maximun length of extents + */ +static void +mext_calc_swap_extents(struct ext4_extent *tmp_dext, + struct ext4_extent *tmp_oext, + ext4_lblk_t orig_off, ext4_lblk_t donor_off, + ext4_lblk_t max_count) +{ + ext4_lblk_t diff, orig_diff; + struct ext4_extent dext_old, oext_old; + + dext_old = *tmp_dext; + oext_old = *tmp_oext; + + /* When tmp_dext is too large, pick up the target range. */ + diff = donor_off - le32_to_cpu(tmp_dext->ee_block); + + ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff); + tmp_dext->ee_block = + cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff); + tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff); + + if (max_count < ext4_ext_get_actual_len(tmp_dext)) + tmp_dext->ee_len = cpu_to_le16(max_count); + + orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block); + ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff); + + /* Adjust extent length if donor extent is larger than orig */ + if (ext4_ext_get_actual_len(tmp_dext) > + ext4_ext_get_actual_len(tmp_oext) - orig_diff) + tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) - + orig_diff); + + tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext)); + + copy_extent_status(&oext_old, tmp_dext); + copy_extent_status(&dext_old, tmp_oext); +} + +/** + * mext_replace_branches - Replace original extents with new extents + * + * @handle: journal handle + * @orig_inode: original inode + * @donor_inode: donor inode + * @from: block offset of orig_inode + * @count: block count to be replaced + * + * Replace original inode extents and donor inode extents page by page. + * We implement this replacement in the following three steps: + * 1. Save the block information of original and donor inodes into + * dummy extents. + * 2. Change the block information of original inode to point at the + * donor inode blocks. + * 3. Change the block information of donor inode to point at the saved + * original inode blocks in the dummy extents. + * + * Return 0 on success, or a negative error value on failure. + */ +static int +mext_replace_branches(handle_t *handle, struct inode *orig_inode, + struct inode *donor_inode, ext4_lblk_t from, + ext4_lblk_t count) +{ + struct ext4_ext_path *orig_path = NULL; + struct ext4_ext_path *donor_path = NULL; + struct ext4_extent *oext, *dext; + struct ext4_extent tmp_dext, tmp_oext; + ext4_lblk_t orig_off = from, donor_off = from; + int err = 0; + int depth; + int replaced_count = 0; + int dext_alen; + + 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) + goto out; + + /* Get the donor extent for the head */ + get_ext_path(donor_path, donor_inode, donor_off, err); + if (donor_path == NULL) + goto out; + depth = ext_depth(orig_inode); + oext = orig_path[depth].p_ext; + tmp_oext = *oext; + + depth = ext_depth(donor_inode); + dext = donor_path[depth].p_ext; + tmp_dext = *dext; + + mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, count); + + /* 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)); + + /* Set donor extent to orig extent */ + err = mext_leaf_block(handle, orig_inode, + orig_path, &tmp_dext, &orig_off); + if (err < 0) + goto out; + + /* Set orig extent to donor extent */ + err = mext_leaf_block(handle, donor_inode, + donor_path, &tmp_oext, &donor_off); + if (err < 0) + goto out; + + dext_alen = ext4_ext_get_actual_len(&tmp_dext); + replaced_count += dext_alen; + donor_off += dext_alen; + orig_off += dext_alen; + + /* Already moved the expected blocks */ + if (replaced_count >= count) + break; + + if (orig_path) + ext4_ext_drop_refs(orig_path); + get_ext_path(orig_path, orig_inode, orig_off, err); + if (orig_path == NULL) + goto out; + depth = ext_depth(orig_inode); + oext = orig_path[depth].p_ext; + if (le32_to_cpu(oext->ee_block) + + ext4_ext_get_actual_len(oext) <= orig_off) { + err = 0; + goto out; + } + tmp_oext = *oext; + + if (donor_path) + ext4_ext_drop_refs(donor_path); + get_ext_path(donor_path, donor_inode, + donor_off, err); + if (donor_path == NULL) + goto out; + depth = ext_depth(donor_inode); + dext = donor_path[depth].p_ext; + if (le32_to_cpu(dext->ee_block) + + ext4_ext_get_actual_len(dext) <= donor_off) { + err = 0; + goto out; + } + tmp_dext = *dext; + + mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, + count - replaced_count); + } + +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + if (donor_path) { + ext4_ext_drop_refs(donor_path); + kfree(donor_path); + } + + mext_double_up_write(orig_inode, donor_inode); + return err; +} + +/** + * move_extent_per_page - Move extent data per page + * + * @o_filp: file structure of original file + * @donor_inode: donor inode + * @orig_page_offset: page index on original file + * @data_offset_in_page: block index where data swapping starts + * @block_len_in_page: the number of blocks to be swapped + * @uninit: orig extent is uninitialized or not + * + * Save the data in original inode blocks and replace original inode extents + * with donor inode extents by calling mext_replace_branches(). + * Finally, write out the saved data in new original inode blocks. Return 0 + * on success, or a negative error value on failure. + */ +static int +move_extent_par_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) +{ + struct inode *orig_inode = o_filp->f_dentry->d_inode; + struct address_space *mapping = orig_inode->i_mapping; + struct buffer_head *bh; + struct page *page = NULL; + const struct address_space_operations *a_ops = mapping->a_ops; + handle_t *handle; + ext4_lblk_t orig_blk_offset; + long long offs = orig_page_offset << PAGE_CACHE_SHIFT; + unsigned long blocksize = orig_inode->i_sb->s_blocksize; + unsigned int w_flags = 0; + unsigned int tmp_data_len, data_len; + void *fsdata; + int ret, i, jblocks; + int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + + /* + * It needs twice the amount of ordinary journal buffers because + * inode and donor_inode may change each different metadata blocks. + */ + jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; + handle = ext4_journal_start(orig_inode, jblocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + + if (segment_eq(get_fs(), KERNEL_DS)) + w_flags |= AOP_FLAG_UNINTERRUPTIBLE; + + orig_blk_offset = orig_page_offset * blocks_per_page + + data_offset_in_page; + + /* + * If orig extent is uninitialized one, + * it's not necessary force the page into memory + * and then force it to be written out again. + * Just swap data blocks between orig and donor. + */ + if (uninit) { + ret = mext_replace_branches(handle, orig_inode, + donor_inode, orig_blk_offset, + block_len_in_page); + + /* Clear the inode cache not to refer to the old data */ + ext4_ext_invalidate_cache(orig_inode); + ext4_ext_invalidate_cache(donor_inode); + goto out2; + } + + offs = (long long)orig_blk_offset << orig_inode->i_blkbits; + + /* Calculate data_len */ + if ((orig_blk_offset + block_len_in_page - 1) == + ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { + /* Replace the last block */ + tmp_data_len = orig_inode->i_size & (blocksize - 1); + /* + * If data_len equal zero, it shows data_len is multiples of + * blocksize. So we set appropriate value. + */ + if (tmp_data_len == 0) + tmp_data_len = blocksize; + + data_len = tmp_data_len + + ((block_len_in_page - 1) << orig_inode->i_blkbits); + } else { + data_len = block_len_in_page << orig_inode->i_blkbits; + } + + ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags, + &page, &fsdata); + if (unlikely(ret < 0)) + goto out; + + if (!PageUptodate(page)) { + mapping->a_ops->readpage(o_filp, page); + lock_page(page); + } + + /* + * try_to_release_page() doesn't call releasepage in writeback mode. + * We should care about the order of writing to the same file + * by multiple move extent processes. + * It needs to call wait_on_page_writeback() to wait for the + * writeback of the page. + */ + if (PageWriteback(page)) + wait_on_page_writeback(page); + + /* Release old bh and drop refs */ + try_to_release_page(page, 0); + + ret = mext_replace_branches(handle, orig_inode, donor_inode, + orig_blk_offset, block_len_in_page); + if (ret < 0) + goto out; + + /* Clear the inode cache not to refer to the old data */ + ext4_ext_invalidate_cache(orig_inode); + ext4_ext_invalidate_cache(donor_inode); + + if (!page_has_buffers(page)) + create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); + + bh = page_buffers(page); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + + for (i = 0; i < block_len_in_page; i++) { + ret = ext4_get_block(orig_inode, + (sector_t)(orig_blk_offset + i), bh, 0); + if (ret < 0) + goto out; + + if (bh->b_this_page != NULL) + bh = bh->b_this_page; + } + + ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len, + page, fsdata); + page = NULL; + +out: + if (unlikely(page)) { + if (PageLocked(page)) + unlock_page(page); + page_cache_release(page); + } +out2: + ext4_journal_stop(handle); + + return ret < 0 ? ret : 0; +} + +/** + * mext_check_argumants - Check whether move extent can be done + * + * @orig_inode: original inode + * @donor_inode: donor inode + * @orig_start: logical start offset in block for orig + * @donor_start: logical start offset in block for donor + * @len: the number of blocks to be moved + * @moved_len: moved block length + * + * Check the arguments of ext4_move_extents() whether the files can be + * exchanged with each other. + * Return 0 on success, or a negative error value on failure. + */ +static int +mext_check_arguments(struct inode *orig_inode, + struct inode *donor_inode, __u64 orig_start, + __u64 donor_start, __u64 *len, __u64 moved_len) +{ + /* Regular file check */ + if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) { + ext4_debug("ext4 move extent: The argument files should be " + "regular file [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* Ext4 move extent does not support swapfile */ + if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { + ext4_debug("ext4 move extent: The argument files should " + "not be swapfile [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* Files should be in the same ext4 FS */ + if (orig_inode->i_sb != donor_inode->i_sb) { + ext4_debug("ext4 move extent: The argument files " + "should be in same FS [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + 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 " + "based file [ino:orig %lu]\n", orig_inode->i_ino); + return -EOPNOTSUPP; + } else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) { + ext4_debug("ext4 move extent: donor file is not extents " + "based file [ino:donor %lu]\n", donor_inode->i_ino); + return -EOPNOTSUPP; + } + + if ((!orig_inode->i_size) || (!donor_inode->i_size)) { + ext4_debug("ext4 move extent: File size is 0 byte\n"); + return -EINVAL; + } + + /* Start offset should be same */ + if (orig_start != donor_start) { + ext4_debug("ext4 move extent: orig and donor's start " + "offset are not same [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (moved_len) { + ext4_debug("ext4 move extent: moved_len should be 0 " + "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, + donor_inode->i_ino); + 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, + 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) { + 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, + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (orig_start + *len > donor_inode->i_size) { + ext4_debug("ext4 move extent: End offset [%llu] should " + "be less than donor file size [%lld]." + "So adjust length from %llu to %lld " + "[ino:orig %lu, donor %lu]\n", + orig_start + *len, donor_inode->i_size, + *len, donor_inode->i_size - orig_start, + orig_inode->i_ino, donor_inode->i_ino); + *len = donor_inode->i_size - orig_start; + } + } else { + if (orig_start >= orig_inode->i_size) { + 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, + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (orig_start + *len > orig_inode->i_size) { + ext4_debug("ext4 move extent: Adjust length " + "from %llu to %lld. Because it should be " + "less than original file size " + "[ino:orig %lu, donor %lu]\n", + *len, orig_inode->i_size - orig_start, + orig_inode->i_ino, donor_inode->i_ino); + *len = orig_inode->i_size - orig_start; + } + } + + if (!*len) { + ext4_debug("ext4 move extent: len shoudld not be 0 " + "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, + donor_inode->i_ino); + return -EINVAL; + } + + return 0; +} + +/** + * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 + * + * @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. + */ +static void +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; + } + + if (inode1->i_ino < inode2->i_ino) { + mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); + } +} + +/** + * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 + * + * @inode1: the inode that is released first + * @inode2: the inode that is released second + * + * This function is moved from fs/inode.c. + */ + +static void +mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) +{ + if (inode1) + mutex_unlock(&inode1->i_mutex); + + if (inode2 && inode2 != inode1) + mutex_unlock(&inode2->i_mutex); +} + +/** + * ext4_move_extents - Exchange the specified range of a file + * + * @o_filp: file structure of the original file + * @d_filp: file structure of the donor file + * @orig_start: start offset in block for orig + * @donor_start: start offset in block for donor + * @len: the number of blocks to be moved + * @moved_len: moved block length + * + * This function returns 0 and moved block length is set in moved_len + * if succeed, otherwise returns error value. + * + * Note: ext4_move_extents() proceeds the following order. + * 1:ext4_move_extents() calculates the last block number of moving extent + * function by the start block number (orig_start) and the number of blocks + * to be moved (len) specified as arguments. + * If the {orig, donor}_start points a hole, the extent's start offset + * pointed by ext_cur (current extent), holecheck_path, orig_path are set + * after hole behind. + * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent + * or the ext_cur exceeds the block_end which is last logical block number. + * 3:To get the length of continues area, call mext_next_extent() + * specified with the ext_cur (initial value is holecheck_path) re-cursive, + * until find un-continuous extent, the start logical block number exceeds + * the block_end or the extent points to the last extent. + * 4:Exchange the original inode data with donor inode data + * from orig_page_offset to seq_end_page. + * The start indexes of data are specified as arguments. + * That of the original inode is orig_page_offset, + * and the donor inode is also orig_page_offset + * (To easily handle blocksize != pagesize case, the offset for the + * donor inode is block unit). + * 5:Update holecheck_path and orig_path to points a next proceeding extent, + * then returns to step 2. + * 6:Release holecheck_path, orig_path and set the len to moved_len + * which shows the number of moved blocks. + * The moved_len is useful for the command to calculate the file offset + * for starting next move extent ioctl. + * 7:Return 0 on success, or a negative error value on failure. + */ +int +ext4_move_extents(struct file *o_filp, struct file *d_filp, + __u64 orig_start, __u64 donor_start, __u64 len, + __u64 *moved_len) +{ + struct inode *orig_inode = o_filp->f_dentry->d_inode; + struct inode *donor_inode = d_filp->f_dentry->d_inode; + struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL; + struct ext4_extent *ext_prev, *ext_cur, *ext_dummy; + ext4_lblk_t block_start = orig_start; + 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 blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + int data_offset_in_page; + int block_len_in_page; + int uninit; + + /* protect orig and donor against a truncate */ + mext_inode_double_lock(orig_inode, donor_inode); + + 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, + donor_start, &len, *moved_len); + mext_double_up_read(orig_inode, donor_inode); + if (ret) + goto out2; + + 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; + + /* Get path structure to check the hole */ + get_ext_path(holecheck_path, orig_inode, block_start, ret); + if (holecheck_path == NULL) + 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. + */ + if (le32_to_cpu(ext_cur->ee_block) + + ext4_ext_get_actual_len(ext_cur) - 1 < block_start) { + last_extent = mext_next_extent(orig_inode, + holecheck_path, &ext_cur); + if (last_extent < 0) { + ret = last_extent; + goto out; + } + last_extent = mext_next_extent(orig_inode, orig_path, + &ext_dummy); + if (last_extent < 0) { + ret = last_extent; + goto out; + } + } + 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; + goto out; + } + + /* Adjust start blocks */ + add_blocks = min(le32_to_cpu(ext_cur->ee_block) + + ext4_ext_get_actual_len(ext_cur), block_end + 1) - + max(le32_to_cpu(ext_cur->ee_block), block_start); + + while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { + seq_blocks += add_blocks; + + /* Adjust tail blocks */ + if (seq_start + seq_blocks - 1 > block_end) + seq_blocks = block_end - seq_start + 1; + + ext_prev = ext_cur; + last_extent = mext_next_extent(orig_inode, holecheck_path, + &ext_cur); + if (last_extent < 0) { + ret = last_extent; + break; + } + add_blocks = ext4_ext_get_actual_len(ext_cur); + + /* + * Extend the length of contiguous block (seq_blocks) + * if extents are contiguous. + */ + if (ext4_can_extents_be_merged(orig_inode, + ext_prev, ext_cur) && + block_end >= le32_to_cpu(ext_cur->ee_block) && + !last_extent) + continue; + + /* Is original extent is uninitialized */ + uninit = ext4_ext_is_uninitialized(ext_prev); + + data_offset_in_page = seq_start % blocks_per_page; + + /* + * Calculate data blocks count that should be swapped + * at the first page. + */ + if (data_offset_in_page + seq_blocks > blocks_per_page) { + /* Swapped blocks are across pages */ + block_len_in_page = + blocks_per_page - data_offset_in_page; + } else { + /* Swapped blocks are in a page */ + block_len_in_page = seq_blocks; + } + + orig_page_offset = seq_start >> + (PAGE_CACHE_SHIFT - orig_inode->i_blkbits); + seq_end_page = (seq_start + seq_blocks - 1) >> + (PAGE_CACHE_SHIFT - orig_inode->i_blkbits); + seq_start = le32_to_cpu(ext_cur->ee_block); + rest_blocks = seq_blocks; + + /* Discard preallocations of two inodes */ + down_write(&EXT4_I(orig_inode)->i_data_sem); + ext4_discard_preallocations(orig_inode); + up_write(&EXT4_I(orig_inode)->i_data_sem); + + down_write(&EXT4_I(donor_inode)->i_data_sem); + ext4_discard_preallocations(donor_inode); + up_write(&EXT4_I(donor_inode)->i_data_sem); + + while (orig_page_offset <= seq_end_page) { + + /* Swap original branches with new branches */ + ret = move_extent_par_page(o_filp, donor_inode, + orig_page_offset, + data_offset_in_page, + block_len_in_page, uninit); + if (ret < 0) + goto out; + orig_page_offset++; + /* Count how many blocks we have exchanged */ + *moved_len += block_len_in_page; + BUG_ON(*moved_len > len); + + data_offset_in_page = 0; + rest_blocks -= block_len_in_page; + if (rest_blocks > blocks_per_page) + block_len_in_page = blocks_per_page; + else + block_len_in_page = rest_blocks; + } + + /* 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) + 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) + break; + + ext_cur = holecheck_path[depth].p_ext; + add_blocks = ext4_ext_get_actual_len(ext_cur); + seq_blocks = 0; + + } +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + if (holecheck_path) { + ext4_ext_drop_refs(holecheck_path); + kfree(holecheck_path); + } +out2: + mext_inode_double_unlock(orig_inode, donor_inode); + + if (ret) + return ret; + + /* All of the specified blocks must be exchanged in succeed */ + BUG_ON(*moved_len != len); + + return 0; +} diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 07eb6649e4f..de04013d16f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1782,7 +1782,7 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode (handle, dir, mode); + inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0); err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; @@ -1816,7 +1816,7 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode(handle, dir, mode); + inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0); err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); @@ -1853,7 +1853,8 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode(handle, dir, S_IFDIR | mode); + inode = ext4_new_inode(handle, dir, S_IFDIR | mode, + &dentry->d_name, 0); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_stop; @@ -2264,7 +2265,8 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO); + inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO, + &dentry->d_name, 0); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_stop; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 27eb289eea3..68b0351fc64 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1002,7 +1002,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, " too large to resize to %llu blocks safely\n", sb->s_id, n_blocks_count); if (sizeof(sector_t) < 8) - ext4_warning(sb, __func__, "CONFIG_LBD not enabled"); + ext4_warning(sb, __func__, "CONFIG_LBDAF not enabled"); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 012c4251397..8f4f079e6b9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -37,7 +37,6 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/ctype.h> -#include <linux/marker.h> #include <linux/log2.h> #include <linux/crc16.h> #include <asm/uaccess.h> @@ -47,6 +46,9 @@ #include "xattr.h" #include "acl.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, @@ -301,7 +303,7 @@ static void ext4_handle_error(struct super_block *sb) if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; - EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; + EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; if (journal) jbd2_journal_abort(journal, -EIO); } @@ -414,7 +416,7 @@ void ext4_abort(struct super_block *sb, const char *function, ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; sb->s_flags |= MS_RDONLY; - EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; + EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); } @@ -664,10 +666,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) if (!ei) return NULL; -#ifdef CONFIG_EXT4_FS_POSIX_ACL - ei->i_acl = EXT4_ACL_NOT_CACHED; - ei->i_default_acl = EXT4_ACL_NOT_CACHED; -#endif ei->vfs_inode.i_version = 1; ei->vfs_inode.i_data.writeback_index = 0; memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); @@ -733,18 +731,6 @@ static void destroy_inodecache(void) static void ext4_clear_inode(struct inode *inode) { -#ifdef CONFIG_EXT4_FS_POSIX_ACL - if (EXT4_I(inode)->i_acl && - EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) { - posix_acl_release(EXT4_I(inode)->i_acl); - EXT4_I(inode)->i_acl = EXT4_ACL_NOT_CACHED; - } - if (EXT4_I(inode)->i_default_acl && - EXT4_I(inode)->i_default_acl != EXT4_ACL_NOT_CACHED) { - posix_acl_release(EXT4_I(inode)->i_default_acl); - EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED; - } -#endif ext4_discard_preallocations(inode); if (EXT4_JOURNAL(inode)) jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal, @@ -1474,7 +1460,7 @@ set_qf_format: break; #endif case Opt_abort: - set_opt(sbi->s_mount_opt, ABORT); + sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; break; case Opt_nobarrier: clear_opt(sbi->s_mount_opt, BARRIER); @@ -1653,7 +1639,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, ext4_commit_super(sb, 1); if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " - "bpg=%lu, ipg=%lu, mo=%04lx]\n", + "bpg=%lu, ipg=%lu, mo=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), @@ -1957,7 +1943,7 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) /* small i_blocks in vfs inode? */ if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { /* - * CONFIG_LBD is not enabled implies the inode + * CONFIG_LBDAF is not enabled implies the inode * i_block represent total blocks in 512 bytes * 32 == size of vfs inode i_blocks * 8 */ @@ -2000,7 +1986,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { /* - * !has_huge_files or CONFIG_LBD not enabled implies that + * !has_huge_files or CONFIG_LBDAF not enabled implies that * the inode i_block field represents total file blocks in * 2^32 512-byte sectors == size of vfs inode i_blocks * 8 */ @@ -2204,6 +2190,7 @@ EXT4_RO_ATTR(session_write_kbytes); EXT4_RO_ATTR(lifetime_write_kbytes); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show, inode_readahead_blks_store, s_inode_readahead_blks); +EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); @@ -2216,6 +2203,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(session_write_kbytes), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(inode_readahead_blks), + ATTR_LIST(inode_goal), ATTR_LIST(mb_stats), ATTR_LIST(mb_max_to_scan), ATTR_LIST(mb_min_to_scan), @@ -2436,13 +2424,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (has_huge_files) { /* * Large file size enabled file system can only be - * mount if kernel is build with CONFIG_LBD + * 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_LBD"); + "without CONFIG_LBDAF"); goto failed_mount; } } @@ -2566,7 +2554,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely"); if (sizeof(sector_t) < 8) - ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled"); + ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); goto failed_mount; } @@ -3346,7 +3334,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) int ret = 0; tid_t target; - trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait); + trace_ext4_sync_fs(sb, wait); if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { if (wait) jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target); @@ -3450,7 +3438,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) + if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, __func__, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | @@ -3465,7 +3453,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) || n_blocks_count > ext4_blocks_count(es)) { - if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) { + if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; goto restore_opts; } |