/* * NOTE! When we get the inode, we're the only people * that have access to it, and as such there are no * race conditions we have to worry about. The inode * is not on the hash-lists, and it cannot be reached * through the filesystem because the directory entry * has been deleted earlier. * * HOWEVER: we must make sure that we get no aliases, * which means that we have to call "clear_inode()" * _before_ we mark the inode not in use in the inode * bitmaps. Otherwise a newly created file might use * the same inode number (not actually the same pointer * though), and then we'd have two inodes sharing the * same inode number and space on the harddisk. */ void ext4_free_inode (handle_t *handle, struct inode * inode) { struct super_block * sb = inode->i_sb; int is_directory; unsigned long ino; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; unsigned long block_group; unsigned long bit; struct ext4_group_desc * gdp; struct ext4_super_block * es; struct ext4_sb_info *sbi; int fatal = 0, err; if (atomic_read(&inode->i_count) > 1) { printk ("ext4_free_inode: inode has count=%d\n", atomic_read(&inode->i_count)); return; } if (inode->i_nlink) { printk ("ext4_free_inode: inode has nlink=%d\n", inode->i_nlink); return; } if (!sb) { printk("ext4_free_inode: inode on nonexistent device\n"); return; } sbi = EXT4_SB(sb); ino = inode->i_ino; ext4_debug ("freeing inode %lu\n", ino); /* * Note: we must free any quota before locking the superblock, * as writing the quota to disk may need the lock as well. */ DQUOT_INIT(inode); ext4_xattr_delete_inode(handle, inode); DQUOT_FREE_INODE(inode); DQUOT_DROP(inode); is_directory = S_ISDIR(inode->i_mode); /* Do this BEFORE marking the inode not in use or returning an error */ clear_inode (inode); es = EXT4_SB(sb)->s_es; if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext4_error (sb, "ext4_free_inode", "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = read_inode_bitmap(sb, block_group); if (!bitmap_bh) goto error_return; BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext4_journal_get_write_access(handle, bitmap_bh); if (fatal) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), bit, bitmap_bh->b_data)) ext4_error (sb, "ext4_free_inode", "bit already cleared for inode %lu", ino); else { gdp = ext4_get_group_desc (sb, block_group, &bh2); BUFFER_TRACE(bh2, "get_write_access"); fatal = ext4_journal_get_write_access(handle, bh2); if (fatal) goto error_return; if (gdp) { spin_lock(sb_bgl_lock(sbi, block_group)); gdp->bg_free_inodes_count = cpu_to_le16( le16_to_cpu(gdp->bg_free_inodes_count) + 1); if (is_directory) gdp->bg_used_dirs_count = cpu_to_le16( le16_to_cpu(gdp->bg_used_dirs_count) - 1); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); } BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bh2); if (!fatal) fatal = err; } BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bitmap_bh); if (!fatal) fatal = err; sb->s_dirt = 1; error_return: brelse(bitmap_bh); ext4_std_error(sb, fatal); }
/** * ext4_add_groupblocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physcial block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap. We ask the * mballoc to reload the buddy after this by setting group * EXT4_GROUP_INFO_NEED_INIT_BIT flag */ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh = NULL; struct buffer_head *gd_bh; ext4_group_t block_group; ext4_grpblk_t bit; unsigned long i; struct ext4_group_desc *desc; struct ext4_super_block *es; struct ext4_sb_info *sbi; int err = 0, ret; ext4_grpblk_t blocks_freed; struct ext4_group_info *grp; sbi = EXT4_SB(sb); es = sbi->s_es; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); ext4_get_group_no_and_offset(sb, block, &block_group, &bit); grp = ext4_get_group_info(sb, block_group); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) { goto error_return; } bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (!bitmap_bh) goto error_return; desc = ext4_get_group_desc(sb, block_group, &gd_bh); if (!desc) goto error_return; if (in_range(ext4_block_bitmap(sb, desc), block, count) || in_range(ext4_inode_bitmap(sb, desc), block, count) || in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, desc), sbi->s_itb_per_group)) { ext4_error(sb, __func__, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); goto error_return; } /* * We are about to add blocks to the bitmap, * so we need undo access. */ BUFFER_TRACE(bitmap_bh, "getting undo access"); err = ext4_journal_get_undo_access(handle, bitmap_bh); if (err) goto error_return; /* * We are about to modify some metadata. Call the journal APIs * to unshare ->b_data if a currently-committing transaction is * using it */ BUFFER_TRACE(gd_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gd_bh); if (err) goto error_return; /* * make sure we don't allow a parallel init on other groups in the * same buddy cache */ down_write(&grp->alloc_sem); for (i = 0, blocks_freed = 0; i < count; i++) { BUFFER_TRACE(bitmap_bh, "clear bit"); if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i, bitmap_bh->b_data)) { ext4_error(sb, __func__, "bit already cleared for block %llu", (ext4_fsblk_t)(block + i)); BUFFER_TRACE(bitmap_bh, "bit already cleared"); } else { blocks_freed++; } } spin_lock(sb_bgl_lock(sbi, block_group)); le16_add_cpu(&desc->bg_free_blocks_count, blocks_freed); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); spin_lock(sb_bgl_lock(sbi, flex_group)); sbi->s_flex_groups[flex_group].free_blocks += blocks_freed; spin_unlock(sb_bgl_lock(sbi, flex_group)); } /* * request to reload the buddy with the * new bitmap information */ set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); ext4_mb_update_group_info(grp, blocks_freed); up_write(&grp->alloc_sem); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_journal_dirty_metadata(handle, bitmap_bh); /* And the group descriptor block */ BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); ret = ext4_journal_dirty_metadata(handle, gd_bh); if (!err) err = ret; sb->s_dirt = 1; error_return: brelse(bitmap_bh); ext4_std_error(sb, err); return; }
/* * 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); }