static int ext4_group_used_meta_blocks(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { ext4_fsblk_t tmp; struct ext4_sb_info *sbi = EXT4_SB(sb); /* block bitmap, inode bitmap, and inode table blocks */ int used_blocks = sbi->s_itb_per_group + 2; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) used_blocks--; if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) used_blocks--; tmp = ext4_inode_table(sb, gdp); for (; tmp < ext4_inode_table(sb, gdp) + sbi->s_itb_per_group; tmp++) { if (!ext4_block_in_group(sb, tmp, block_group)) used_blocks -= 1; } } return used_blocks; }
static unsigned char get_dtype(struct super_block *sb, int filetype) { if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || (filetype >= EXT4_FT_MAX)) return DT_UNKNOWN; return (ext4_filetype_table[filetype]); }
/* * Migrate a simple extent-based inode to use the i_blocks[] array */ int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; ext4_fsblk_t blk; handle_t *handle; int ret; if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_INCOMPAT_EXTENTS) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) return -EOPNOTSUPP; handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); if (ret) goto errout; eh = ext_inode_hdr(inode); ex = EXT_FIRST_EXTENT(eh); if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS || eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) { ret = -EOPNOTSUPP; goto errout; } if (eh->eh_entries == 0) blk = len = 0; else { len = le16_to_cpu(ex->ee_len); blk = ext4_ext_pblock(ex); if (len > EXT4_NDIR_BLOCKS) { ret = -EOPNOTSUPP; goto errout; } } ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); memset(ei->i_data, 0, sizeof(ei->i_data)); for (i=0; i < len; i++) ei->i_data[i] = cpu_to_le32(blk++); ext4_mark_inode_dirty(handle, inode); errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); return ret; }
static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, ext4_group_t group) { if (!ext4_bg_has_super(sb, group)) return 0; if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG)) return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); else return EXT4_SB(sb)->s_gdb_count; }
static int ext4_valid_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, unsigned int block_group, struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; ext4_fsblk_t bitmap_blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { /* with FLEX_BG, the inode/block bitmaps and itable * blocks may not be in the group at all * so the bitmap validation will be skipped for those groups * or it has to also read the block group where the bitmaps * are located to verify they are set. */ return 1; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ bitmap_blk = ext4_block_bitmap(sb, desc); offset = bitmap_blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ goto err_out; /* check whether the inode bitmap block number is set */ bitmap_blk = ext4_inode_bitmap(sb, desc); offset = bitmap_blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ goto err_out; /* check whether the inode table block number is set */ bitmap_blk = ext4_inode_table(sb, desc); offset = bitmap_blk - group_first_block; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, offset + EXT4_SB(sb)->s_itb_per_group, offset); if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group) /* good bitmap for inode tables */ return 1; err_out: ext4_error(sb, __func__, "Invalid block bitmap - " "block_group = %d, block = %llu", block_group, bitmap_blk); return 0; }
/** * ext4_bg_num_gdb - number of blocks used by the group table in group * @sb: superblock for filesystem * @group: group number to check * * Return the number of blocks used by the group descriptor table * (primary or backup) in this group. In the future there may be a * different number of descriptor blocks in each group. */ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) { unsigned long first_meta_bg = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) || metagroup < first_meta_bg) return ext4_bg_num_gdb_nometa(sb, group); return ext4_bg_num_gdb_meta(sb,group); }
/** * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other * important fields of the inodes. * * @sb: the super block of the filesystem * @inode: the inode to swap with EXT4_BOOT_LOADER_INO * */ static long swap_inode_boot_loader(struct super_block *sb, struct inode *inode) { handle_t *handle; int err; struct inode *inode_bl; struct ext4_inode_info *ei_bl; struct ext4_sb_info *sbi = EXT4_SB(sb); if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) { err = -EINVAL; goto swap_boot_out; } if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto swap_boot_out; } inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO); if (IS_ERR(inode_bl)) { err = PTR_ERR(inode_bl); goto swap_boot_out; } ei_bl = EXT4_I(inode_bl); filemap_flush(inode->i_mapping); filemap_flush(inode_bl->i_mapping); /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); truncate_inode_pages(&inode->i_data, 0); truncate_inode_pages(&inode_bl->i_data, 0); /* Wait for all existing dio workers */ ext4_inode_block_unlocked_dio(inode); ext4_inode_block_unlocked_dio(inode_bl); inode_dio_wait(inode); inode_dio_wait(inode_bl); handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; goto journal_err_out; } /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); if (inode_bl->i_nlink == 0) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); i_gid_write(inode_bl, 0); inode_bl->i_flags = 0; ei_bl->i_flags = 0; inode_bl->i_version = 1; i_size_write(inode_bl, 0); inode_bl->i_mode = S_IFREG; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode_bl); } else memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); } swap_inode_data(inode, inode_bl); inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode); spin_lock(&sbi->s_next_gen_lock); inode->i_generation = sbi->s_next_generation++; inode_bl->i_generation = sbi->s_next_generation++; spin_unlock(&sbi->s_next_gen_lock); ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { ext4_warning(inode->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); } else { err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { ext4_warning(inode_bl->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode_bl->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); } } ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); journal_err_out: ext4_inode_resume_unlocked_dio(inode); ext4_inode_resume_unlocked_dio(inode_bl); unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); swap_boot_out: return err; }
/* Initializes an uninitialized block bitmap if given, and returns the * number of blocks free in the group. */ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) { int bit, bit_max; ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned free_blocks, group_blocks; struct ext4_sb_info *sbi = EXT4_SB(sb); if (bh) { J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { ext4_error(sb, __func__, "Checksum bad for group %u", block_group); ext4_free_blks_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); return 0; } memset(bh->b_data, 0, sb->s_blocksize); } /* Check for superblock and gdt backups in this group */ bit_max = ext4_bg_has_super(sb, block_group); if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) || block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) * sbi->s_desc_per_block) { if (bit_max) { bit_max += ext4_bg_num_gdb(sb, block_group); bit_max += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); } } else { /* For META_BG_BLOCK_GROUPS */ bit_max += ext4_bg_num_gdb(sb, block_group); } if (block_group == ngroups - 1) { /* * Even though mke2fs always initialize first and last group * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need * to make sure we calculate the right free blocks */ group_blocks = ext4_blocks_count(sbi->s_es) - le32_to_cpu(sbi->s_es->s_first_data_block) - (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1)); } else { group_blocks = EXT4_BLOCKS_PER_GROUP(sb); } free_blocks = group_blocks - bit_max; if (bh) { ext4_fsblk_t start, tmp; int flex_bg = 0; for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); start = ext4_group_first_block_no(sb, block_group); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) flex_bg = 1; /* Set bits for block and inode bitmaps, and inode table */ tmp = ext4_block_bitmap(sb, gdp); if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(tmp - start, bh->b_data); tmp = ext4_inode_bitmap(sb, gdp); if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(tmp - start, bh->b_data); tmp = ext4_inode_table(sb, gdp); for (; tmp < ext4_inode_table(sb, gdp) + sbi->s_itb_per_group; tmp++) { if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(tmp - start, bh->b_data); } /* * Also if the number of blocks within the group is * less than the blocksize * 8 ( which is the size * of bitmap ), set rest of the block bitmap to 1 */ mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data); } return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp); }
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = filp->f_dentry->d_inode; struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); unsigned int flags; ext4_debug("cmd = %u, arg = %lu\n", cmd, arg); switch (cmd) { case EXT4_IOC_GETFLAGS: ext4_get_inode_flags(ei); flags = ei->i_flags & EXT4_FL_USER_VISIBLE; return put_user(flags, (int __user *) arg); case EXT4_IOC_SETFLAGS: { handle_t *handle = NULL; int err, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags; unsigned int jflag; if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) return -EFAULT; err = mnt_want_write_file(filp); if (err) return err; flags = ext4_mask_flags(inode->i_mode, flags); err = -EPERM; mutex_lock(&inode->i_mutex); /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) goto flags_out; oldflags = ei->i_flags; /* The JOURNAL_DATA flag is modifiable only by root */ jflag = flags & EXT4_JOURNAL_DATA_FL; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. * * This test looks nicer. Thanks to Pauline Middelink */ if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) { if (!capable(CAP_LINUX_IMMUTABLE)) goto flags_out; } /* * The JOURNAL_DATA flag can only be changed by * the relevant capability. */ if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } if (oldflags & EXT4_EXTENTS_FL) { /* We don't support clearning extent flags */ if (!(flags & EXT4_EXTENTS_FL)) { err = -EOPNOTSUPP; goto flags_out; } } else if (flags & EXT4_EXTENTS_FL) { /* migrate the file */ migrate = 1; flags &= ~EXT4_EXTENTS_FL; } if (flags & EXT4_EOFBLOCKS_FL) { /* we don't support adding EOFBLOCKS flag */ if (!(oldflags & EXT4_EOFBLOCKS_FL)) { err = -EOPNOTSUPP; goto flags_out; } } else if (oldflags & EXT4_EOFBLOCKS_FL) ext4_truncate(inode); handle = ext4_journal_start(inode, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto flags_out; } if (IS_SYNC(inode)) ext4_handle_sync(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto flags_err; flags = flags & EXT4_FL_USER_MODIFIABLE; flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE; ei->i_flags = flags; ext4_set_inode_flags(inode); inode->i_ctime = ext4_current_time(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); flags_err: ext4_journal_stop(handle); if (err) goto flags_out; if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) err = ext4_change_inode_journal_flag(inode, jflag); if (err) goto flags_out; if (migrate) err = ext4_ext_migrate(inode); flags_out: mutex_unlock(&inode->i_mutex); mnt_drop_write_file(filp); return err; } case EXT4_IOC_GETVERSION: case EXT4_IOC_GETVERSION_OLD: return put_user(inode->i_generation, (int __user *) arg); case EXT4_IOC_SETVERSION: case EXT4_IOC_SETVERSION_OLD: { handle_t *handle; struct ext4_iloc iloc; __u32 generation; int err; if (!inode_owner_or_capable(inode)) return -EPERM; err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { err = -EFAULT; goto setversion_out; } mutex_lock(&inode->i_mutex); handle = ext4_journal_start(inode, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto unlock_out; } err = ext4_reserve_inode_write(handle, inode, &iloc); if (err == 0) { inode->i_ctime = ext4_current_time(inode); inode->i_generation = generation; err = ext4_mark_iloc_dirty(handle, inode, &iloc); } ext4_journal_stop(handle); unlock_out: mutex_unlock(&inode->i_mutex); setversion_out: mnt_drop_write_file(filp); return err; } case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (get_user(n_blocks_count, (__u32 __user *)arg)) { err = -EFAULT; goto group_extend_out; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_extend_out; } err = mnt_want_write_file(filp); if (err) goto group_extend_out; err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); group_extend_out: ext4_resize_end(sb); return err; } case EXT4_IOC_MOVE_EXT: { struct move_extent me; struct file *donor_filp; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&me, (struct move_extent __user *)arg, sizeof(me))) return -EFAULT; me.moved_len = 0; donor_filp = fget(me.donor_fd); if (!donor_filp) return -EBADF; if (!(donor_filp->f_mode & FMODE_WRITE)) { err = -EBADF; goto mext_out; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); return -EOPNOTSUPP; } err = mnt_want_write_file(filp); if (err) goto mext_out; err = ext4_move_extents(filp, donor_filp, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); mnt_drop_write(filp->f_path.mnt); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) err = -EFAULT; mext_out: fput(donor_filp); return err; } case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, sizeof(input))) { err = -EFAULT; goto group_add_out; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_add_out; } err = mnt_want_write_file(filp); if (err) goto group_add_out; err = ext4_group_add(sb, &input); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); group_add_out: ext4_resize_end(sb); return err; } case EXT4_IOC_MIGRATE: { int err; if (!inode_owner_or_capable(inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; /* * inode_mutex prevent write and truncate on the file. * Read still goes through. We take i_data_sem in * ext4_ext_swap_inode_data before we switch the * inode format to prevent read. */ mutex_lock(&(inode->i_mutex)); err = ext4_ext_migrate(inode); mutex_unlock(&(inode->i_mutex)); mnt_drop_write_file(filp); return err; } case EXT4_IOC_ALLOC_DA_BLKS: { int err; if (!inode_owner_or_capable(inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; err = ext4_alloc_da_blocks(inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; struct super_block *sb = inode->i_sb; int err = 0, err2 = 0; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "Online resizing not (yet) supported with bigalloc"); return -EOPNOTSUPP; } if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG)) { ext4_msg(sb, KERN_ERR, "Online resizing not (yet) supported with meta_bg"); return -EOPNOTSUPP; } if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } if (n_blocks_count > MAX_32_NUM && !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "File system only supports 32-bit block numbers"); return -EOPNOTSUPP; } err = ext4_resize_begin(sb); if (err) return err; err = mnt_want_write(filp->f_path.mnt); if (err) goto resizefs_out; err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write(filp->f_path.mnt); resizefs_out: ext4_resize_end(sb); return err; } case FIDTRIM: case FITRIM: { struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!blk_queue_discard(q)) return -EOPNOTSUPP; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "FITRIM not supported with bigalloc"); return -EOPNOTSUPP; } if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q)) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; range.minlen = max((unsigned int)range.minlen, q->limits.discard_granularity); ret = ext4_trim_fs(sb, &range, flags); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } case FS_IOC_INVAL_MAPPING: { return invalidate_mapping_pages(inode->i_mapping, 0, -1); } default: return -ENOTTY; } }
/* * Migrate a simple extent-based inode to use the i_blocks[] array */ int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; ext4_lblk_t start, end; ext4_fsblk_t blk; handle_t *handle; int ret; if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_INCOMPAT_EXTENTS) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) return -EOPNOTSUPP; /* * In order to get correct extent info, force all delayed allocation * blocks to be allocated, otherwise delayed allocation blocks may not * be reflected and bypass the checks on extent header. */ if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); if (ret) goto errout; eh = ext_inode_hdr(inode); ex = EXT_FIRST_EXTENT(eh); if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS || eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) { ret = -EOPNOTSUPP; goto errout; } if (eh->eh_entries == 0) blk = len = start = end = 0; else { len = le16_to_cpu(ex->ee_len); blk = ext4_ext_pblock(ex); start = le32_to_cpu(ex->ee_block); end = start + len - 1; if (end >= EXT4_NDIR_BLOCKS) { ret = -EOPNOTSUPP; goto errout; } } ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); memset(ei->i_data, 0, sizeof(ei->i_data)); for (i = start; i <= end; i++) ei->i_data[i] = cpu_to_le32(blk++); ext4_mark_inode_dirty(handle, inode); errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); return ret; }
int ext4_ext_migrate(struct inode *inode) { handle_t *handle; int retval = 0, i; __le32 *i_data; struct ext4_inode_info *ei; struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; __u32 goal; uid_t owner[2]; /* * If the filesystem does not support extents, or the inode * already is extent-based, error out. */ if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_INCOMPAT_EXTENTS) || (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) /* * don't migrate fast symlink */ return retval; /* * Worst case we can touch the allocation bitmaps, a bgd * block, and a block to link in the orphan list. We do need * need to worry about credits for modifying the quota inode. */ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); return retval; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; owner[0] = i_uid_read(inode); owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG, NULL, goal, owner); if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); return retval; } i_size_write(tmp_inode, i_size_read(inode)); /* * Set the i_nlink to zero so it will be deleted later * when we drop inode reference. */ clear_nlink(tmp_inode); ext4_ext_tree_init(handle, tmp_inode); ext4_orphan_add(handle, tmp_inode); ext4_journal_stop(handle); /* * start with one credit accounted for * superblock modification. * * For the tmp_inode we already have committed the * trascation that created the inode. Later as and * when we add extents we extent the journal */ /* * Even though we take i_mutex we can still cause block * allocation via mmap write to holes. If we have allocated * new blocks we fail migrate. New block allocation will * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated * with i_data_sem held to prevent racing with block * allocation. */ down_read((&EXT4_I(inode)->i_data_sem)); ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE); up_read((&EXT4_I(inode)->i_data_sem)); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { /* * It is impossible to update on-disk structures without * a handle, so just rollback in-core changes and live other * work to orphan_list_cleanup() */ ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); goto out; } ei = EXT4_I(inode); i_data = ei->i_data; memset(&lb, 0, sizeof(lb)); /* 32 bit block address 4 bytes */ max_entries = inode->i_sb->s_blocksize >> 2; for (i = 0; i < EXT4_NDIR_BLOCKS; i++) { if (i_data[i]) { retval = update_extent_range(handle, tmp_inode, le32_to_cpu(i_data[i]), &lb); if (retval) goto err_out; } else lb.curr_block++; } if (i_data[EXT4_IND_BLOCK]) { retval = update_ind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb); if (retval) goto err_out; } else lb.curr_block += max_entries; if (i_data[EXT4_DIND_BLOCK]) { retval = update_dind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb); if (retval) goto err_out; } else lb.curr_block += max_entries * max_entries; if (i_data[EXT4_TIND_BLOCK]) { retval = update_tind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb); if (retval) goto err_out; } /* * Build the last extent */ retval = finish_range(handle, tmp_inode, &lb); err_out: if (retval) /* * Failure case delete the extent information with the * tmp_inode */ free_ext_block(handle, tmp_inode); else { retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode); if (retval) /* * if we fail to swap inode data free the extent * details of the tmp inode */ free_ext_block(handle, tmp_inode); } /* We mark the tmp_inode dirty via ext4_ext_tree_init. */ if (ext4_journal_extend(handle, 1) != 0) ext4_journal_restart(handle, 1); /* * Mark the tmp_inode as of size zero */ i_size_write(tmp_inode, 0); /* * set the i_blocks count to zero * so that the ext4_delete_inode does the * right job * * We don't need to take the i_lock because * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); ext4_journal_stop(handle); out: unlock_new_inode(tmp_inode); iput(tmp_inode); return retval; }
int ext4_ext_migrate(struct inode *inode) { handle_t *handle; int retval = 0, i; __le32 *i_data; ext4_lblk_t blk_count = 0; struct ext4_inode_info *ei; 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 * already is extent-based, error out. */ if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_INCOMPAT_EXTENTS) || (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) /* * don't migrate fast symlink */ return retval; handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) + 1); if (IS_ERR(handle)) { retval = PTR_ERR(handle); return retval; } 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); return retval; } i_size_write(tmp_inode, i_size_read(inode)); /* * We don't want the inode to be reclaimed * if we got interrupted in between. We have * this tmp inode carrying reference to the * data blocks of the original file. We set * the i_nlink to zero at the last stage after * switching the original file to extent format */ tmp_inode->i_nlink = 1; ext4_ext_tree_init(handle, tmp_inode); ext4_orphan_add(handle, tmp_inode); ext4_journal_stop(handle); /* * start with one credit accounted for * superblock modification. * * For the tmp_inode we already have commited the * trascation that created the inode. Later as and * when we add extents we extent the journal */ /* * Even though we take i_mutex we can still cause block * allocation via mmap write to holes. If we have allocated * new blocks we fail migrate. New block allocation will * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated * with i_data_sem held to prevent racing with block * allocation. */ down_read((&EXT4_I(inode)->i_data_sem)); EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE; up_read((&EXT4_I(inode)->i_data_sem)); handle = ext4_journal_start(inode, 1); ei = EXT4_I(inode); i_data = ei->i_data; memset(&lb, 0, sizeof(lb)); /* 32 bit block address 4 bytes */ max_entries = inode->i_sb->s_blocksize >> 2; for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) { if (i_data[i]) { retval = update_extent_range(handle, tmp_inode, le32_to_cpu(i_data[i]), blk_count, &lb); if (retval) goto err_out; } } if (i_data[EXT4_IND_BLOCK]) { retval = update_ind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_IND_BLOCK]), &blk_count, &lb); if (retval) goto err_out; } else blk_count += max_entries; if (i_data[EXT4_DIND_BLOCK]) { retval = update_dind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &blk_count, &lb); if (retval) goto err_out; } else blk_count += max_entries * max_entries; if (i_data[EXT4_TIND_BLOCK]) { retval = update_tind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &blk_count, &lb); if (retval) goto err_out; } /* * Build the last extent */ retval = finish_range(handle, tmp_inode, &lb); err_out: if (retval) /* * Failure case delete the extent information with the * tmp_inode */ free_ext_block(handle, tmp_inode); else { retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode); if (retval) /* * if we fail to swap inode data free the extent * details of the tmp inode */ free_ext_block(handle, tmp_inode); } /* We mark the tmp_inode dirty via ext4_ext_tree_init. */ if (ext4_journal_extend(handle, 1) != 0) ext4_journal_restart(handle, 1); /* * Mark the tmp_inode as of size zero */ i_size_write(tmp_inode, 0); /* * set the i_blocks count to zero * so that the ext4_delete_inode does the * right job * * We don't need to take the i_lock because * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); /* * Set the i_nlink to zero so that * generic_drop_inode really deletes the * inode */ tmp_inode->i_nlink = 0; ext4_journal_stop(handle); unlock_new_inode(tmp_inode); iput(tmp_inode); return retval; }
static int ext4_destroy_inline_data_nolock(handle_t *handle, struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_xattr_ibody_find is = { .s = { .not_found = 0, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, .value = NULL, .value_len = 0, }; int error; if (!ei->i_inline_off) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; error = ext4_journal_get_write_access(handle, is.iloc.bh); if (error) goto out; error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); if (error) goto out; memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } } ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); EXT4_I(inode)->i_inline_off = 0; EXT4_I(inode)->i_inline_size = 0; ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); out: brelse(is.iloc.bh); if (error == -ENODATA) error = 0; return error; } static int ext4_read_inline_page(struct inode *inode, struct page *page) { void *kaddr; int ret = 0; size_t len; struct ext4_iloc iloc; BUG_ON(!PageLocked(page)); BUG_ON(!ext4_has_inline_data(inode)); BUG_ON(page->index); if (!EXT4_I(inode)->i_inline_off) { ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.", inode->i_ino); goto out; } ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); kaddr = kmap_atomic(page); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); flush_dcache_page(page); kunmap_atomic(kaddr); zero_user_segment(page, len, PAGE_CACHE_SIZE); SetPageUptodate(page); brelse(iloc.bh); out: return ret; }
/* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both * free space and a low directory-to-inode ratio; if that fails, then of * the groups with above-average free space, that group with the fewest * directories already is chosen. * * 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 super_block *sb; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; int group; unsigned long ino = 0; struct inode * inode; struct ext4_group_desc * gdp = NULL; struct ext4_super_block * es; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; int err = 0; struct inode *ret; int i; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); sb = dir->i_sb; inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); sbi = EXT4_SB(sb); es = sbi->s_es; if (S_ISDIR(mode)) { if (test_opt (sb, OLDALLOC)) group = find_group_dir(sb, dir); else group = find_group_orlov(sb, dir); } else group = find_group_other(sb, dir); err = -ENOSPC; if (group == -1) goto out; for (i = 0; i < sbi->s_groups_count; i++) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &bh2); if (!gdp) goto fail; brelse(bitmap_bh); bitmap_bh = read_inode_bitmap(sb, group); if (!bitmap_bh) goto fail; ino = 0; repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino); if (ino < EXT4_INODES_PER_GROUP(sb)) { BUFFER_TRACE(bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto fail; if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group), ino, bitmap_bh->b_data)) { /* we won it */ BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bitmap_bh); if (err) goto fail; goto got; } /* we lost it */ jbd2_journal_release_buffer(handle, bitmap_bh); if (++ino < EXT4_INODES_PER_GROUP(sb)) goto repeat_in_this_group; } /* * This case is possible in concurrent environment. It is very * rare. We cannot repeat the find_group_xxx() call because * that will simply return the same blockgroup, because the * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ if (++group == sbi->s_groups_count) group = 0; } err = -ENOSPC; goto out; got: ino += group * EXT4_INODES_PER_GROUP(sb) + 1; if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext4_error (sb, "ext4_new_inode", "reserved inode or inode > inodes count - " "block_group = %d, inode=%lu", group, ino); err = -EIO; goto fail; } BUFFER_TRACE(bh2, "get_write_access"); err = ext4_journal_get_write_access(handle, bh2); if (err) goto fail; spin_lock(sb_bgl_lock(sbi, group)); gdp->bg_free_inodes_count = cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1); if (S_ISDIR(mode)) { gdp->bg_used_dirs_count = cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1); } spin_unlock(sb_bgl_lock(sbi, group)); BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bh2); if (err) goto fail; percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); sb->s_dirt = 1; inode->i_uid = current->fsuid; if (test_opt (sb, GRPID)) inode->i_gid = dir->i_gid; else if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; if (S_ISDIR(mode)) mode |= S_ISGID; } else inode->i_gid = current->fsgid; inode->i_mode = mode; inode->i_ino = ino; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = ext4_current_time(inode); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; ei->i_disksize = 0; ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL; if (S_ISLNK(mode)) ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL); /* dirsync only applies to directories */ if (!S_ISDIR(mode)) ei->i_flags &= ~EXT4_DIRSYNC_FL; #ifdef EXT4_FRAGMENTS ei->i_faddr = 0; ei->i_frag_no = 0; ei->i_frag_size = 0; #endif ei->i_file_acl = 0; ei->i_dir_acl = 0; ei->i_dtime = 0; ei->i_block_alloc_info = NULL; ei->i_block_group = group; ext4_set_inode_flags(inode); if (IS_DIRSYNC(inode)) handle->h_sync = 1; insert_inode_hash(inode); spin_lock(&sbi->s_next_gen_lock); inode->i_generation = sbi->s_next_generation++; spin_unlock(&sbi->s_next_gen_lock); ei->i_state = EXT4_STATE_NEW; ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; ret = inode; if(DQUOT_ALLOC_INODE(inode)) { err = -EDQUOT; goto fail_drop; } err = ext4_init_acl(handle, inode, dir); if (err) goto fail_free_drop; err = ext4_init_security(handle,inode, dir); if (err) goto fail_free_drop; err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_std_error(sb, err); goto fail_free_drop; } if (test_opt(sb, EXTENTS)) { EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; ext4_ext_tree_init(handle, inode); if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto fail; EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS); BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); } } ext4_debug("allocating inode %lu\n", inode->i_ino); goto really_out; fail: ext4_std_error(sb, err); out: iput(inode); ret = ERR_PTR(err); really_out: brelse(bitmap_bh); return ret; fail_free_drop: DQUOT_FREE_INODE(inode); fail_drop: DQUOT_DROP(inode); inode->i_flags |= S_NOQUOTA; inode->i_nlink = 0; iput(inode); brelse(bitmap_bh); return ERR_PTR(err); }