diff --git a/Documentation/ABI/testing/sysfs-fs-ext4 b/Documentation/ABI/testing/sysfs-fs-ext4 index 4e79074de282..5fb709997d96 100644 --- a/Documentation/ABI/testing/sysfs-fs-ext4 +++ b/Documentation/ABI/testing/sysfs-fs-ext4 @@ -79,3 +79,13 @@ Description: This file is read-only and shows the number of kilobytes of data that have been written to this filesystem since it was mounted. + +What: /sys/fs/ext4//inode_goal +Date: June 2008 +Contact: "Theodore Ts'o" +Description: + Tuning parameter which (if non-zero) controls the goal + inode used by the inode allocator in p0reference to + all other allocation hueristics. This is intended for + debugging use only, and should be 0 on production + systems. diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 608fdba97b72..7be02ac5fa36 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -235,6 +235,10 @@ minixdf Make 'df' act like Minix. debug Extra debugging information is sent to syslog. +abort Simulate the effects of calling ext4_abort() for + debugging purposes. This is normally used while + remounting a filesystem which is already mounted. + errors=remount-ro Remount the filesystem read-only on an error. errors=continue Keep going on a filesystem error. errors=panic Panic and halt the machine if an error occurs. diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 8a34710ecf40..8867b2a1e5fe 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/ext4.h b/fs/ext4/ext4.h index cc7d5edc38c9..17b9998680e3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -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) @@ -674,7 +684,6 @@ 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 +705,10 @@ 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 +826,13 @@ 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 +851,8 @@ 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 +863,7 @@ 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 +1316,8 @@ 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 +1341,7 @@ 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 +1659,11 @@ 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 f0c3ec85bd48..20a84105a10b 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/extents.c b/fs/ext4/extents.c index 2593f748c3a4..50322a09bd01 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) { diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 588af8c77246..3f1873fef1c6 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #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 5afe4370840b..83cf6415f599 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -28,10 +28,12 @@ #include #include #include -#include + #include "ext4.h" #include "ext4_jbd2.h" +#include + /* * 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 3743bd849bce..2f645732e3b7 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -23,11 +23,14 @@ #include #include #include + #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include + /* * 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 875db944b22f..7c17ae275af4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,11 +37,14 @@ #include #include #include + #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "ext4_extents.h" +#include + #define MPAGE_DA_EXTENT_TAIL 0x01 static inline int ext4_begin_ordered_truncate(struct inode *inode, @@ -78,7 +81,7 @@ static int ext4_inode_is_fast_symlink(struct inode *inode) * If the handle isn't valid we're not journaling so there's nothing to do. */ 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; @@ -90,7 +93,7 @@ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, 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 +332,8 @@ 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 +365,9 @@ 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 +382,25 @@ 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 +450,7 @@ 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 +462,7 @@ 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 +555,7 @@ 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 +577,7 @@ 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 +613,9 @@ 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 +686,10 @@ 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 +731,9 @@ 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 +780,7 @@ 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 +823,8 @@ 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 +856,6 @@ 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 +874,8 @@ 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 +921,9 @@ 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 +939,7 @@ 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 +987,8 @@ 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 +999,8 @@ 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 +1172,7 @@ 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 +1254,7 @@ 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 +1405,7 @@ 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 +1446,7 @@ 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 +1454,24 @@ 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; @@ -1523,7 +1519,7 @@ retry: ext4_journal_stop(handle); if (pos + len > inode->i_size) { vmtruncate(inode, inode->i_size); - /* + /* * If vmtruncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the @@ -1550,9 +1546,9 @@ 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; @@ -1603,18 +1599,15 @@ 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) { @@ -1636,7 +1629,7 @@ static int ext4_ordered_write_end(struct file *file, if (pos + len > inode->i_size) { vmtruncate(inode, inode->i_size); - /* + /* * If vmtruncate 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. @@ -1650,18 +1643,15 @@ 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; @@ -1681,7 +1671,7 @@ static int ext4_writeback_write_end(struct file *file, if (pos + len > inode->i_size) { vmtruncate(inode, inode->i_size); - /* + /* * If vmtruncate 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 +1684,9 @@ 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 +1695,7 @@ 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; @@ -1747,7 +1734,7 @@ static int ext4_journalled_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 * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. @@ -1854,7 +1841,7 @@ 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; @@ -2554,9 +2541,7 @@ 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_da_writepage(inode, page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; @@ -2667,19 +2652,7 @@ 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 +2666,13 @@ 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 +2818,7 @@ 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 +2850,8 @@ 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 +2870,7 @@ 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 @@ -2959,7 +2921,7 @@ 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 +2940,9 @@ 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 +2963,7 @@ 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 +3040,7 @@ 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 +3060,7 @@ 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. @@ -3237,7 +3196,7 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) * */ static int __ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) + struct writeback_control *wbc) { struct inode *inode = page->mapping->host; @@ -3249,15 +3208,13 @@ static int __ext4_normal_writepage(struct page *page, } static int ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) + 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); + trace_ext4_normal_writepage(inode, page); J_ASSERT(PageLocked(page)); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; @@ -3287,7 +3244,7 @@ static int ext4_normal_writepage(struct page *page, } static int __ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) + struct writeback_control *wbc) { struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; @@ -3337,15 +3294,13 @@ out: } static int ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) + 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); + trace_ext4_journalled_writepage(inode, page); J_ASSERT(PageLocked(page)); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; @@ -3442,8 +3397,8 @@ 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; @@ -3763,7 +3718,8 @@ 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 +3775,10 @@ 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 +3795,11 @@ 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 +4171,7 @@ 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 +4412,9 @@ 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); @@ -4569,7 +4529,7 @@ 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 +4548,7 @@ 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 +4563,15 @@ 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 +4602,7 @@ 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 +4755,9 @@ 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 +5111,7 @@ 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 91e75f7a9e73..bb415408fdb6 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "ext4_jbd2.h" #include "ext4.h" @@ -213,6 +214,41 @@ setversion_out: 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; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index ed8482e22c0e..519a0a686d94 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -22,6 +22,8 @@ */ #include "mballoc.h" +#include + /* * 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 @@ -2859,9 +2859,8 @@ 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); @@ -3629,10 +3628,7 @@ 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 +3687,8 @@ 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 +3778,8 @@ 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 +3813,7 @@ 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 +3881,8 @@ 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 +3981,15 @@ 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); @@ -4276,6 +4273,8 @@ 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 +4444,7 @@ 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 +4473,7 @@ 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 @@ -4521,7 +4509,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); - if (!ac) { + if (ac) { + ac->ac_sb = sb; + ac->ac_inode = ar->inode; + } else { ar->len = 0; *errp = -ENOMEM; goto out1; @@ -4594,18 +4585,7 @@ 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 +4689,7 @@ 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 +4715,12 @@ 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 +4761,7 @@ 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 75e34f69215b..c96bb19f58f9 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -19,7 +19,6 @@ #include #include #include -#include #include #include "ext4_jbd2.h" #include "ext4.h" diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index fe64d9f79852..313a50b39741 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 000000000000..bbf2dd9404dc --- /dev/null +++ b/fs/ext4/move_extent.c @@ -0,0 +1,1320 @@ +/* + * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd. + * Written by Takashi Sato + * Akira Fujita + * + * 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 +#include +#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 07eb6649e4fa..de04013d16ff 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/super.c b/fs/ext4/super.c index 012c4251397e..23013d303f81 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -47,6 +46,9 @@ #include "xattr.h" #include "acl.h" +#define CREATE_TRACE_POINTS +#include + 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); } @@ -1474,7 +1476,7 @@ 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 +1655,7 @@ 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), @@ -2204,6 +2206,7 @@ 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 +2219,7 @@ 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), @@ -3346,7 +3350,7 @@ 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 +3454,7 @@ 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 +3469,7 @@ 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; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 17159cacbd9e..5d70b3e6d49b 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -20,9 +20,9 @@ #include #include #include -#include #include #include +#include /* * Unlink a buffer from a transaction checkpoint list. @@ -358,8 +358,7 @@ int jbd2_log_do_checkpoint(journal_t *journal) * journal straight away. */ result = jbd2_cleanup_journal_tail(journal); - trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d", - journal->j_devname, result); + trace_jbd2_checkpoint(journal, result); jbd_debug(1, "cleanup_journal_tail returned %d\n", result); if (result <= 0) return result; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 0b7d3b8226fd..7b4088b2364d 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -26,6 +25,7 @@ #include #include #include +#include /* * Default IO end handler for temporary BJ_IO buffer_heads. @@ -253,6 +253,7 @@ static int journal_submit_data_buffers(journal_t *journal, * block allocation with delalloc. We need to write * only allocated blocks here. */ + trace_jbd2_submit_inode_data(jinode->i_vfs_inode); err = journal_submit_inode_data_buffers(mapping); if (!ret) ret = err; @@ -394,8 +395,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) commit_transaction = journal->j_running_transaction; J_ASSERT(commit_transaction->t_state == T_RUNNING); - trace_mark(jbd2_start_commit, "dev %s transaction %d", - journal->j_devname, commit_transaction->t_tid); + trace_jbd2_start_commit(journal, commit_transaction); jbd_debug(1, "JBD: starting commit of transaction %d\n", commit_transaction->t_tid); @@ -409,6 +409,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ if (commit_transaction->t_synchronous_commit) write_op = WRITE_SYNC_PLUG; + trace_jbd2_commit_locking(journal, commit_transaction); stats.u.run.rs_wait = commit_transaction->t_max_wait; stats.u.run.rs_locked = jiffies; stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start, @@ -484,6 +485,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_switch_revoke_table(journal); + trace_jbd2_commit_flushing(journal, commit_transaction); stats.u.run.rs_flushing = jiffies; stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked, stats.u.run.rs_flushing); @@ -520,6 +522,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) commit_transaction->t_state = T_COMMIT; spin_unlock(&journal->j_state_lock); + trace_jbd2_commit_logging(journal, commit_transaction); stats.u.run.rs_logging = jiffies; stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing, stats.u.run.rs_logging); @@ -1054,9 +1057,7 @@ restart_loop: if (journal->j_commit_callback) journal->j_commit_callback(journal, commit_transaction); - trace_mark(jbd2_end_commit, "dev %s transaction %d head %d", - journal->j_devname, commit_transaction->t_tid, - journal->j_tail_sequence); + trace_jbd2_end_commit(journal, commit_transaction); jbd_debug(1, "JBD: commit %d complete, head %d\n", journal->j_commit_sequence, journal->j_tail_sequence); if (to_free) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 62be7d294ec2..18bfd5dab642 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -38,6 +38,10 @@ #include #include #include +#include + +#define CREATE_TRACE_POINTS +#include #include #include @@ -2377,6 +2381,71 @@ static void __exit journal_exit(void) jbd2_journal_destroy_caches(); } +/* + * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 + * tracing infrastructure to map a dev_t to a device name. + * + * The caller should use rcu_read_lock() in order to make sure the + * device name stays valid until its done with it. We use + * rcu_read_lock() as well to make sure we're safe in case the caller + * gets sloppy, and because rcu_read_lock() is cheap and can be safely + * nested. + */ +struct devname_cache { + struct rcu_head rcu; + dev_t device; + char devname[BDEVNAME_SIZE]; +}; +#define CACHE_SIZE_BITS 6 +static struct devname_cache *devcache[1 << CACHE_SIZE_BITS]; +static DEFINE_SPINLOCK(devname_cache_lock); + +static void free_devcache(struct rcu_head *rcu) +{ + kfree(rcu); +} + +const char *jbd2_dev_to_name(dev_t device) +{ + int i = hash_32(device, CACHE_SIZE_BITS); + char *ret; + struct block_device *bd; + + rcu_read_lock(); + if (devcache[i] && devcache[i]->device == device) { + ret = devcache[i]->devname; + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); + + spin_lock(&devname_cache_lock); + if (devcache[i]) { + if (devcache[i]->device == device) { + ret = devcache[i]->devname; + spin_unlock(&devname_cache_lock); + return ret; + } + call_rcu(&devcache[i]->rcu, free_devcache); + } + devcache[i] = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); + if (!devcache[i]) { + spin_unlock(&devname_cache_lock); + return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ + } + devcache[i]->device = device; + bd = bdget(device); + if (bd) { + bdevname(bd, devcache[i]->devname); + bdput(bd); + } else + __bdevname(device, devcache[i]->devname); + ret = devcache[i]->devname; + spin_unlock(&devname_cache_lock); + return ret; +} +EXPORT_SYMBOL(jbd2_dev_to_name); + MODULE_LICENSE("GPL"); module_init(journal_init); module_exit(journal_exit); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 996ffda06bf3..494501edba6b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1547,36 +1547,6 @@ out: return; } -/* - * jbd2_journal_try_to_free_buffers() could race with - * jbd2_journal_commit_transaction(). The later might still hold the - * reference count to the buffers when inspecting them on - * t_syncdata_list or t_locked_list. - * - * jbd2_journal_try_to_free_buffers() will call this function to - * wait for the current transaction to finish syncing data buffers, before - * try to free that buffer. - * - * Called with journal->j_state_lock hold. - */ -static void jbd2_journal_wait_for_transaction_sync_data(journal_t *journal) -{ - transaction_t *transaction; - tid_t tid; - - spin_lock(&journal->j_state_lock); - transaction = journal->j_committing_transaction; - - if (!transaction) { - spin_unlock(&journal->j_state_lock); - return; - } - - tid = transaction->t_tid; - spin_unlock(&journal->j_state_lock); - jbd2_log_wait_commit(journal, tid); -} - /** * int jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation @@ -1649,25 +1619,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, ret = try_to_free_buffers(page); - /* - * There are a number of places where jbd2_journal_try_to_free_buffers() - * could race with jbd2_journal_commit_transaction(), the later still - * holds the reference to the buffers to free while processing them. - * try_to_free_buffers() failed to free those buffers. Some of the - * caller of releasepage() request page buffers to be dropped, otherwise - * treat the fail-to-free as errors (such as generic_file_direct_IO()) - * - * So, if the caller of try_to_release_page() wants the synchronous - * behaviour(i.e make sure buffers are dropped upon return), - * let's wait for the current transaction to finish flush of - * dirty data buffers, then try to free those buffers again, - * with the journal locked. - */ - if (ret == 0 && (gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)) { - jbd2_journal_wait_for_transaction_sync_data(journal); - ret = try_to_free_buffers(page); - } - busy: return ret; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index cc02393bfce8..d97eb652d6ca 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1315,6 +1315,12 @@ extern int jbd_blocks_per_page(struct inode *inode); #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) +/* + * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 + * tracing infrastructure to map a dev_t to a device name. + */ +extern const char *jbd2_dev_to_name(dev_t device); + #endif /* __KERNEL__ */ #endif /* _LINUX_JBD2_H */ diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h new file mode 100644 index 000000000000..acf4cc9cd36d --- /dev/null +++ b/include/trace/events/ext4.h @@ -0,0 +1,719 @@ +#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_EXT4_H + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ext4 + +#include +#include "../../../fs/ext4/ext4.h" +#include "../../../fs/ext4/mballoc.h" +#include + +TRACE_EVENT(ext4_free_inode, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( umode_t, mode ) + __field( uid_t, uid ) + __field( gid_t, gid ) + __field( blkcnt_t, blocks ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->mode = inode->i_mode; + __entry->uid = inode->i_uid; + __entry->gid = inode->i_gid; + __entry->blocks = inode->i_blocks; + ), + + TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode, + __entry->uid, __entry->gid, __entry->blocks) +); + +TRACE_EVENT(ext4_request_inode, + TP_PROTO(struct inode *dir, int mode), + + TP_ARGS(dir, mode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, dir ) + __field( umode_t, mode ) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = dir->i_ino; + __entry->mode = mode; + ), + + TP_printk("dev %s dir %lu mode %d", + jbd2_dev_to_name(__entry->dev), __entry->dir, __entry->mode) +); + +TRACE_EVENT(ext4_allocate_inode, + TP_PROTO(struct inode *inode, struct inode *dir, int mode), + + TP_ARGS(inode, dir, mode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( ino_t, dir ) + __field( umode_t, mode ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->dir = dir->i_ino; + __entry->mode = mode; + ), + + TP_printk("dev %s ino %lu dir %lu mode %d", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->dir, __entry->mode) +); + +TRACE_EVENT(ext4_write_begin, + + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int flags), + + TP_ARGS(inode, pos, len, flags), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, flags ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->flags = flags; + ), + + TP_printk("dev %s ino %lu pos %llu len %u flags %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->flags) +); + +TRACE_EVENT(ext4_ordered_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), + + TP_ARGS(inode, pos, len, copied), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, copied ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->copied = copied; + ), + + TP_printk("dev %s ino %lu pos %llu len %u copied %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->copied) +); + +TRACE_EVENT(ext4_writeback_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), + + TP_ARGS(inode, pos, len, copied), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, copied ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->copied = copied; + ), + + TP_printk("dev %s ino %lu pos %llu len %u copied %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->copied) +); + +TRACE_EVENT(ext4_journalled_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), + TP_ARGS(inode, pos, len, copied), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, copied ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->copied = copied; + ), + + TP_printk("dev %s ino %lu pos %llu len %u copied %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->copied) +); + +TRACE_EVENT(ext4_da_writepage, + TP_PROTO(struct inode *inode, struct page *page), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( pgoff_t, index ) + + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->index = page->index; + ), + + TP_printk("dev %s ino %lu page_index %lu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) +); + +TRACE_EVENT(ext4_da_writepages, + TP_PROTO(struct inode *inode, struct writeback_control *wbc), + + TP_ARGS(inode, wbc), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( long, nr_to_write ) + __field( long, pages_skipped ) + __field( loff_t, range_start ) + __field( loff_t, range_end ) + __field( char, nonblocking ) + __field( char, for_kupdate ) + __field( char, for_reclaim ) + __field( char, for_writepages ) + __field( char, range_cyclic ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nr_to_write = wbc->nr_to_write; + __entry->pages_skipped = wbc->pages_skipped; + __entry->range_start = wbc->range_start; + __entry->range_end = wbc->range_end; + __entry->nonblocking = wbc->nonblocking; + __entry->for_kupdate = wbc->for_kupdate; + __entry->for_reclaim = wbc->for_reclaim; + __entry->for_writepages = wbc->for_writepages; + __entry->range_cyclic = wbc->range_cyclic; + ), + + TP_printk("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", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write, + __entry->pages_skipped, __entry->range_start, + __entry->range_end, __entry->nonblocking, + __entry->for_kupdate, __entry->for_reclaim, + __entry->for_writepages, __entry->range_cyclic) +); + +TRACE_EVENT(ext4_da_writepages_result, + TP_PROTO(struct inode *inode, struct writeback_control *wbc, + int ret, int pages_written), + + TP_ARGS(inode, wbc, ret, pages_written), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( int, ret ) + __field( int, pages_written ) + __field( long, pages_skipped ) + __field( char, encountered_congestion ) + __field( char, more_io ) + __field( char, no_nrwrite_index_update ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->ret = ret; + __entry->pages_written = pages_written; + __entry->pages_skipped = wbc->pages_skipped; + __entry->encountered_congestion = wbc->encountered_congestion; + __entry->more_io = wbc->more_io; + __entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update; + ), + + TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->ret, + __entry->pages_written, __entry->pages_skipped, + __entry->encountered_congestion, __entry->more_io, + __entry->no_nrwrite_index_update) +); + +TRACE_EVENT(ext4_da_write_begin, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int flags), + + TP_ARGS(inode, pos, len, flags), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, flags ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->flags = flags; + ), + + TP_printk("dev %s ino %lu pos %llu len %u flags %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->flags) +); + +TRACE_EVENT(ext4_da_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), + + TP_ARGS(inode, pos, len, copied), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, pos ) + __field( unsigned int, len ) + __field( unsigned int, copied ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->len = len; + __entry->copied = copied; + ), + + TP_printk("dev %s ino %lu pos %llu len %u copied %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, + __entry->copied) +); + +TRACE_EVENT(ext4_normal_writepage, + TP_PROTO(struct inode *inode, struct page *page), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( pgoff_t, index ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->index = page->index; + ), + + TP_printk("dev %s ino %lu page_index %lu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) +); + +TRACE_EVENT(ext4_journalled_writepage, + TP_PROTO(struct inode *inode, struct page *page), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( pgoff_t, index ) + + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->index = page->index; + ), + + TP_printk("dev %s ino %lu page_index %lu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) +); + +TRACE_EVENT(ext4_discard_blocks, + TP_PROTO(struct super_block *sb, unsigned long long blk, + unsigned long long count), + + TP_ARGS(sb, blk, count), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u64, blk ) + __field( __u64, count ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->blk = blk; + __entry->count = count; + ), + + TP_printk("dev %s blk %llu count %llu", + jbd2_dev_to_name(__entry->dev), __entry->blk, __entry->count) +); + +TRACE_EVENT(ext4_mb_new_inode_pa, + TP_PROTO(struct ext4_allocation_context *ac, + struct ext4_prealloc_space *pa), + + TP_ARGS(ac, pa), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, pa_pstart ) + __field( __u32, pa_len ) + __field( __u64, pa_lstart ) + + ), + + TP_fast_assign( + __entry->dev = ac->ac_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->pa_pstart = pa->pa_pstart; + __entry->pa_len = pa->pa_len; + __entry->pa_lstart = pa->pa_lstart; + ), + + TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart, + __entry->pa_len, __entry->pa_lstart) +); + +TRACE_EVENT(ext4_mb_new_group_pa, + TP_PROTO(struct ext4_allocation_context *ac, + struct ext4_prealloc_space *pa), + + TP_ARGS(ac, pa), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, pa_pstart ) + __field( __u32, pa_len ) + __field( __u64, pa_lstart ) + + ), + + TP_fast_assign( + __entry->dev = ac->ac_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->pa_pstart = pa->pa_pstart; + __entry->pa_len = pa->pa_len; + __entry->pa_lstart = pa->pa_lstart; + ), + + TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart, + __entry->pa_len, __entry->pa_lstart) +); + +TRACE_EVENT(ext4_mb_release_inode_pa, + TP_PROTO(struct ext4_allocation_context *ac, + struct ext4_prealloc_space *pa, + unsigned long long block, unsigned int count), + + TP_ARGS(ac, pa, block, count), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, block ) + __field( __u32, count ) + + ), + + TP_fast_assign( + __entry->dev = ac->ac_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->block = block; + __entry->count = count; + ), + + TP_printk("dev %s ino %lu block %llu count %u", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block, + __entry->count) +); + +TRACE_EVENT(ext4_mb_release_group_pa, + TP_PROTO(struct ext4_allocation_context *ac, + struct ext4_prealloc_space *pa), + + TP_ARGS(ac, pa), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, pa_pstart ) + __field( __u32, pa_len ) + + ), + + TP_fast_assign( + __entry->dev = ac->ac_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->pa_pstart = pa->pa_pstart; + __entry->pa_len = pa->pa_len; + ), + + TP_printk("dev %s pstart %llu len %u", + jbd2_dev_to_name(__entry->dev), __entry->pa_pstart, __entry->pa_len) +); + +TRACE_EVENT(ext4_discard_preallocations, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + ), + + TP_printk("dev %s ino %lu", + jbd2_dev_to_name(__entry->dev), __entry->ino) +); + +TRACE_EVENT(ext4_mb_discard_preallocations, + TP_PROTO(struct super_block *sb, int needed), + + TP_ARGS(sb, needed), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, needed ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->needed = needed; + ), + + TP_printk("dev %s needed %d", + jbd2_dev_to_name(__entry->dev), __entry->needed) +); + +TRACE_EVENT(ext4_request_blocks, + TP_PROTO(struct ext4_allocation_request *ar), + + TP_ARGS(ar), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, flags ) + __field( unsigned int, len ) + __field( __u64, logical ) + __field( __u64, goal ) + __field( __u64, lleft ) + __field( __u64, lright ) + __field( __u64, pleft ) + __field( __u64, pright ) + ), + + TP_fast_assign( + __entry->dev = ar->inode->i_sb->s_dev; + __entry->ino = ar->inode->i_ino; + __entry->flags = ar->flags; + __entry->len = ar->len; + __entry->logical = ar->logical; + __entry->goal = ar->goal; + __entry->lleft = ar->lleft; + __entry->lright = ar->lright; + __entry->pleft = ar->pleft; + __entry->pright = ar->pright; + ), + + TP_printk("dev %s ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags, + __entry->len, + (unsigned long long) __entry->logical, + (unsigned long long) __entry->goal, + (unsigned long long) __entry->lleft, + (unsigned long long) __entry->lright, + (unsigned long long) __entry->pleft, + (unsigned long long) __entry->pright) +); + +TRACE_EVENT(ext4_allocate_blocks, + TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block), + + TP_ARGS(ar, block), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, block ) + __field( unsigned int, flags ) + __field( unsigned int, len ) + __field( __u64, logical ) + __field( __u64, goal ) + __field( __u64, lleft ) + __field( __u64, lright ) + __field( __u64, pleft ) + __field( __u64, pright ) + ), + + TP_fast_assign( + __entry->dev = ar->inode->i_sb->s_dev; + __entry->ino = ar->inode->i_ino; + __entry->block = block; + __entry->flags = ar->flags; + __entry->len = ar->len; + __entry->logical = ar->logical; + __entry->goal = ar->goal; + __entry->lleft = ar->lleft; + __entry->lright = ar->lright; + __entry->pleft = ar->pleft; + __entry->pright = ar->pright; + ), + + TP_printk("dev %s ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags, + __entry->len, __entry->block, + (unsigned long long) __entry->logical, + (unsigned long long) __entry->goal, + (unsigned long long) __entry->lleft, + (unsigned long long) __entry->lright, + (unsigned long long) __entry->pleft, + (unsigned long long) __entry->pright) +); + +TRACE_EVENT(ext4_free_blocks, + TP_PROTO(struct inode *inode, __u64 block, unsigned long count, + int metadata), + + TP_ARGS(inode, block, count, metadata), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, block ) + __field( unsigned long, count ) + __field( int, metadata ) + + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->block = block; + __entry->count = count; + __entry->metadata = metadata; + ), + + TP_printk("dev %s ino %lu block %llu count %lu metadata %d", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block, + __entry->count, __entry->metadata) +); + +TRACE_EVENT(ext4_sync_file, + TP_PROTO(struct file *file, struct dentry *dentry, int datasync), + + TP_ARGS(file, dentry, datasync), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( ino_t, parent ) + __field( int, datasync ) + ), + + TP_fast_assign( + __entry->dev = dentry->d_inode->i_sb->s_dev; + __entry->ino = dentry->d_inode->i_ino; + __entry->datasync = datasync; + __entry->parent = dentry->d_parent->d_inode->i_ino; + ), + + TP_printk("dev %s ino %ld parent %ld datasync %d ", + jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->parent, + __entry->datasync) +); + +TRACE_EVENT(ext4_sync_fs, + TP_PROTO(struct super_block *sb, int wait), + + TP_ARGS(sb, wait), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, wait ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->wait = wait; + ), + + TP_printk("dev %s wait %d", jbd2_dev_to_name(__entry->dev), + __entry->wait) +); + +#endif /* _TRACE_EXT4_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h new file mode 100644 index 000000000000..845b0b4b48fd --- /dev/null +++ b/include/trace/events/jbd2.h @@ -0,0 +1,168 @@ +#if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_JBD2_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM jbd2 + +TRACE_EVENT(jbd2_checkpoint, + + TP_PROTO(journal_t *journal, int result), + + TP_ARGS(journal, result), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, result ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->result = result; + ), + + TP_printk("dev %s result %d", + jbd2_dev_to_name(__entry->dev), __entry->result) +); + +TRACE_EVENT(jbd2_start_commit, + + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), + + TP_ARGS(journal, commit_transaction), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( char, sync_commit ) + __field( int, transaction ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->sync_commit = commit_transaction->t_synchronous_commit; + __entry->transaction = commit_transaction->t_tid; + ), + + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) +); + +TRACE_EVENT(jbd2_commit_locking, + + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), + + TP_ARGS(journal, commit_transaction), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( char, sync_commit ) + __field( int, transaction ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->sync_commit = commit_transaction->t_synchronous_commit; + __entry->transaction = commit_transaction->t_tid; + ), + + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) +); + +TRACE_EVENT(jbd2_commit_flushing, + + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), + + TP_ARGS(journal, commit_transaction), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( char, sync_commit ) + __field( int, transaction ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->sync_commit = commit_transaction->t_synchronous_commit; + __entry->transaction = commit_transaction->t_tid; + ), + + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) +); + +TRACE_EVENT(jbd2_commit_logging, + + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), + + TP_ARGS(journal, commit_transaction), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( char, sync_commit ) + __field( int, transaction ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->sync_commit = commit_transaction->t_synchronous_commit; + __entry->transaction = commit_transaction->t_tid; + ), + + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) +); + +TRACE_EVENT(jbd2_end_commit, + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), + + TP_ARGS(journal, commit_transaction), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( char, sync_commit ) + __field( int, transaction ) + __field( int, head ) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->sync_commit = commit_transaction->t_synchronous_commit; + __entry->transaction = commit_transaction->t_tid; + __entry->head = journal->j_tail_sequence; + ), + + TP_printk("dev %s transaction %d sync %d head %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit, __entry->head) +); + +TRACE_EVENT(jbd2_submit_inode_data, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + ), + + TP_printk("dev %s ino %lu", + jbd2_dev_to_name(__entry->dev), __entry->ino) +); + +#endif /* _TRACE_JBD2_H */ + +/* This part must be outside protection */ +#include