NTSTATUS Ext2DoExtentExpand( IN PEXT2_IRP_CONTEXT IrpContext, IN PEXT2_VCB Vcb, IN PEXT2_MCB Mcb, IN ULONG Index, IN OUT PULONG Block, IN OUT PULONG Number ) { EXT4_EXTENT_HEADER *eh; struct buffer_head bh_got; int rc, flags; if (IsMcbDirectory(Mcb) || IrpContext->MajorFunction == IRP_MJ_WRITE) { flags = EXT4_GET_BLOCKS_IO_CONVERT_EXT; } else { flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; } memset(&bh_got, 0, sizeof(struct buffer_head)); eh = get_ext4_header(&Mcb->Inode); if (eh->eh_magic != EXT4_EXT_MAGIC) { ext4_ext_tree_init(IrpContext, NULL, &Mcb->Inode); } if ((rc = ext4_ext_get_blocks( IrpContext, NULL, &Mcb->Inode, Index, *Number, &bh_got, 1, flags)) < 0) { DEBUG(DL_ERR, ("Expand Block insufficient resources, Number: %u," " err: %d\n", *Number, rc)); DbgBreak(); return Ext2WinntError(rc); } if (Number) *Number = rc ? rc : 1; if (Block) *Block = (ULONG)bh_got.b_blocknr; Ext2SaveInode(IrpContext, Vcb, &Mcb->Inode); return STATUS_SUCCESS; }
/** * 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; }
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; BUFFER_TRACE(is.iloc.bh, "get_write_access"); 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_feature_extents(inode->i_sb)) { 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; }
NTSTATUS Ext2MapExtent( IN PEXT2_IRP_CONTEXT IrpContext, IN PEXT2_VCB Vcb, IN PEXT2_MCB Mcb, IN ULONG Index, IN BOOLEAN Alloc, OUT PULONG Block, OUT PULONG Number ) { EXT4_EXTENT_HEADER *eh; struct buffer_head bh_got; int flags, rc; ULONG max_blocks = 0; memset(&bh_got, 0, sizeof(struct buffer_head)); eh = get_ext4_header(&Mcb->Inode); if (eh->eh_magic != EXT4_EXT_MAGIC) { if (Alloc) { /* now initialize inode extent root node */ ext4_ext_tree_init(IrpContext, NULL, &Mcb->Inode); } else { /* return empty-mapping when inode extent isn't initialized */ if (Block) *Block = 0; if (Number) { LONGLONG _len = _len = Mcb->Inode.i_size; if (Mcb->Fcb) _len = Mcb->Fcb->Header.AllocationSize.QuadPart; *Number = (ULONG)((_len + BLOCK_SIZE - 1) >> BLOCK_BITS); } return STATUS_SUCCESS; } } /* IrpContext is NULL when called during journal initialization */ if (IsMcbDirectory(Mcb) || IrpContext == NULL || IrpContext->MajorFunction == IRP_MJ_WRITE || !Alloc){ flags = EXT4_GET_BLOCKS_IO_CONVERT_EXT; max_blocks = EXT_INIT_MAX_LEN; } else { flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; max_blocks = EXT_UNWRITTEN_MAX_LEN; } if ((rc = ext4_ext_get_blocks( IrpContext, NULL, &Mcb->Inode, Index, max_blocks, &bh_got, Alloc, flags)) < 0) { DEBUG(DL_ERR, ("Block insufficient resources, err: %d\n", rc)); return Ext2WinntError(rc); } if (Alloc) Ext2SaveInode(IrpContext, Vcb, &Mcb->Inode); if (Number) *Number = rc ? rc : 1; if (Block) *Block = (ULONG)bh_got.b_blocknr; return STATUS_SUCCESS; }
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; }
/* * 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); }
int ext4_ext_migrate(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg) { 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; if (!test_opt(inode->i_sb, EXTENTS)) /* * if mounted with noextents we don't allow the migrate */ return -EINVAL; if ((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 + 2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb) + 1); if (IS_ERR(handle)) { retval = PTR_ERR(handle); goto err_out; } tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG); if (IS_ERR(tmp_inode)) { retval = -ENOMEM; ext4_journal_stop(handle); tmp_inode = NULL; goto err_out; } 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 */ /* * 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)); 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); /* 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); mutex_unlock(&(inode->i_mutex)); if (tmp_inode) iput(tmp_inode); return retval; }
/** * 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; qsize_t size, size_bl, diff; blkcnt_t blocks; unsigned short bytes; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) || ext4_has_inline_data(inode)) { err = -EINVAL; goto journal_err_out; } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; } down_write(&EXT4_I(inode)->i_mmap_sem); err = filemap_write_and_wait(inode->i_mapping); if (err) goto err_out; err = filemap_write_and_wait(inode_bl->i_mapping); if (err) goto err_out; /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); truncate_inode_pages(&inode->i_data, 0); truncate_inode_pages(&inode_bl->i_data, 0); handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; goto 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_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { 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)); } err = dquot_initialize(inode); if (err) goto err_out1; size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes; size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes; diff = size - size_bl; swap_inode_data(inode, inode_bl); inode->i_ctime = inode_bl->i_ctime = current_time(inode); inode->i_generation = prandom_u32(); inode_bl->i_generation = prandom_u32(); reset_inode_seed(inode); reset_inode_seed(inode_bl); ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { /* No need to update quota information. */ 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); ext4_mark_inode_dirty(handle, inode); goto err_out1; } blocks = inode_bl->i_blocks; bytes = inode_bl->i_bytes; inode_bl->i_blocks = inode->i_blocks; inode_bl->i_bytes = inode->i_bytes; err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode_bl->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode_bl->i_ino, err); goto revert; } /* Bootloader inode should not be counted into quota information. */ if (diff > 0) dquot_free_space(inode, diff); else err = dquot_alloc_space(inode, -1 * diff); if (err < 0) { revert: /* Revert all changes: */ inode_bl->i_blocks = blocks; inode_bl->i_bytes = bytes; swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); ext4_mark_inode_dirty(handle, inode_bl); } err_out1: ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); err_out: up_write(&EXT4_I(inode)->i_mmap_sem); journal_err_out: unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); return err; }