X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?p=kvmfornfv.git;a=blobdiff_plain;f=kernel%2Ffs%2Fext4%2Finode.c;h=06bda0361e7ce80dcecdf2245b4922e0af8cffd3;hp=966c614822cc1ea338540082f00218418756c183;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hpb=f93b97fd65072de626c074dbe099a1fff05ce060 diff --git a/kernel/fs/ext4/inode.c b/kernel/fs/ext4/inode.c index 966c61482..06bda0361 100644 --- a/kernel/fs/ext4/inode.c +++ b/kernel/fs/ext4/inode.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -377,7 +378,7 @@ static int __check_block_validity(struct inode *inode, const char *func, "lblock %lu mapped to illegal pblock " "(length %d)", (unsigned long) map->m_lblk, map->m_len); - return -EIO; + return -EFSCORRUPTED; } return 0; } @@ -479,7 +480,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, /* We can handle the block number less than EXT_MAX_BLOCKS */ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) - return -EIO; + return -EFSCORRUPTED; /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { @@ -656,16 +657,32 @@ has_zeroout: return retval; } -static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate) +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) { - struct inode *inode = bh->b_assoc_map->host; - /* XXX: breaks on 32-bit > 16GB. Is that even supported? */ - loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits; - int err; - if (!uptodate) + unsigned long old_state; + unsigned long new_state; + + flags &= EXT4_MAP_FLAGS; + + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_page) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; return; - WARN_ON(!buffer_unwritten(bh)); - err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size); + } + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + do { + old_state = READ_ONCE(bh->b_state); + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely( + cmpxchg(&bh->b_state, old_state, new_state) != old_state)); } /* Maximum number of blocks we map for direct IO at once. */ @@ -704,11 +721,16 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_io_end_t *io_end = ext4_inode_aio(inode); map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; - if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) { + ext4_update_bh_state(bh, map.m_flags); + if (IS_DAX(inode) && buffer_unwritten(bh)) { + /* + * dgc: I suspect unwritten conversion on ext4+DAX is + * fundamentally broken here when there are concurrent + * read/write in progress on this inode. + */ + WARN_ON_ONCE(io_end); bh->b_assoc_map = inode->i_mapping; bh->b_private = (void *)(unsigned long)iblock; - bh->b_end_io = ext4_end_io_unwritten; } if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); @@ -731,18 +753,18 @@ int ext4_get_block(struct inode *inode, sector_t iblock, * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, - ext4_lblk_t block, int create) + ext4_lblk_t block, int map_flags) { struct ext4_map_blocks map; struct buffer_head *bh; + int create = map_flags & EXT4_GET_BLOCKS_CREATE; int err; J_ASSERT(handle != NULL || create == 0); map.m_lblk = block; map.m_len = 1; - err = ext4_map_blocks(handle, inode, &map, - create ? EXT4_GET_BLOCKS_CREATE : 0); + err = ext4_map_blocks(handle, inode, &map, map_flags); if (err == 0) return create ? ERR_PTR(-ENOSPC) : NULL; @@ -788,11 +810,11 @@ errout: } struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, - ext4_lblk_t block, int create) + ext4_lblk_t block, int map_flags) { struct buffer_head *bh; - bh = ext4_getblk(handle, inode, block, create); + bh = ext4_getblk(handle, inode, block, map_flags); if (IS_ERR(bh)) return bh; if (!bh || buffer_uptodate(bh)) @@ -971,7 +993,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, if (unlikely(err)) page_zero_new_buffers(page, from, to); else if (decrypt) - err = ext4_decrypt_one(inode, page); + err = ext4_decrypt(page); return err; } #endif @@ -1187,6 +1209,38 @@ errout: return ret ? ret : copied; } +/* + * This is a private version of page_zero_new_buffers() which doesn't + * set the buffer to be dirty, since in data=journalled mode we need + * to call ext4_handle_dirty_metadata() instead. + */ +static void zero_new_buffers(struct page *page, unsigned from, unsigned to) +{ + unsigned int block_start = 0, block_end; + struct buffer_head *head, *bh; + + bh = head = page_buffers(page); + do { + block_end = block_start + bh->b_size; + if (buffer_new(bh)) { + if (block_end > from && block_start < to) { + if (!PageUptodate(page)) { + unsigned start, size; + + start = max(from, block_start); + size = min(to, block_end) - start; + + zero_user(page, start, size); + set_buffer_uptodate(bh); + } + clear_buffer_new(bh); + } + } + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); +} + static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -1213,7 +1267,7 @@ static int ext4_journalled_write_end(struct file *file, if (copied < len) { if (!PageUptodate(page)) copied = 0; - page_zero_new_buffers(page, from+copied, to); + zero_new_buffers(page, from+copied, to); } ret = ext4_walk_page_buffers(handle, page_buffers(page), from, @@ -1261,13 +1315,12 @@ static int ext4_journalled_write_end(struct file *file, } /* - * Reserve a single cluster located at lblock + * Reserve space for a single cluster */ -static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +static int ext4_da_reserve_space(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - unsigned int md_needed; int ret; /* @@ -1279,25 +1332,14 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) if (ret) return ret; - /* - * recalculate the amount of metadata blocks to reserve - * in order to allocate nrblocks - * worse case is one extent per block - */ spin_lock(&ei->i_block_reservation_lock); - /* - * ext4_calc_metadata_amount() has side effects, which we have - * to be prepared undo if we fail to claim space. - */ - md_needed = 0; - trace_ext4_da_reserve_space(inode, 0); - if (ext4_claim_free_clusters(sbi, 1, 0)) { spin_unlock(&ei->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } ei->i_reserved_data_blocks++; + trace_ext4_da_reserve_space(inode); spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ @@ -1575,9 +1617,9 @@ add_delayed: * then we don't need to reserve it again. However we still need * to reserve metadata for every block we're going to write. */ - if (EXT4_SB(inode->i_sb)->s_cluster_ratio <= 1 || + if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 || !ext4_find_delalloc_cluster(inode, map->m_lblk)) { - ret = ext4_da_reserve_space(inode, iblock); + ret = ext4_da_reserve_space(inode); if (ret) { /* not enough space to reserve */ retval = ret; @@ -1655,7 +1697,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked @@ -1833,11 +1875,22 @@ static int ext4_writepage(struct page *page, * the page. But we may reach here when we do a journal commit via * journal_submit_inode_data_buffers() and in that case we must write * allocated buffers to achieve data=ordered mode guarantees. + * + * Also, if there is only one buffer per page (the fs block + * size == the page size), if one buffer needs block + * allocation or needs to modify the extent tree to clear the + * unwritten flag, we know that the page can't be written at + * all, so we might as well refuse the write immediately. + * Unfortunately if the block size != page size, we can't as + * easily detect this case using ext4_walk_page_buffers(), but + * for the extremely common case, this is an optimization that + * skips a useless round trip through ext4_bio_write_page(). */ if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); - if (current->flags & PF_MEMALLOC) { + if ((current->flags & PF_MEMALLOC) || + (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here @@ -2617,8 +2670,7 @@ static int ext4_nonda_switch(struct super_block *sb) /* We always reserve for an inode update; the superblock could be there too */ static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) { - if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + if (likely(ext4_has_feature_large_file(inode->i_sb))) return 1; if (pos + len <= 0x7fffffffULL) @@ -3039,6 +3091,17 @@ static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_NO_LOCK); } +int ext4_get_block_dax(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT; + if (create) + flags |= EXT4_GET_BLOCKS_CREATE; + ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n", + inode->i_ino, create); + return _ext4_get_block(inode, iblock, bh_result, flags); +} + static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private) { @@ -3351,7 +3414,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, int err = 0; page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; @@ -3400,7 +3463,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, /* We expect the key to be set. */ BUG_ON(!ext4_has_encryption_key(inode)); BUG_ON(blocksize != PAGE_CACHE_SIZE); - WARN_ON_ONCE(ext4_decrypt_one(inode, page)); + WARN_ON_ONCE(ext4_decrypt(page)); } } if (ext4_should_journal_data(inode)) { @@ -3827,7 +3890,7 @@ static int __ext4_get_inode_loc(struct inode *inode, iloc->bh = NULL; if (!ext4_valid_inum(sb, inode->i_ino)) - return -EIO; + return -EFSCORRUPTED; iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb); gdp = ext4_get_group_desc(sb, iloc->block_group, NULL); @@ -4013,8 +4076,7 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct inode *inode = &(ei->vfs_inode); struct super_block *sb = inode->i_sb; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + if (ext4_has_feature_huge_file(sb)) { /* we are using combined 48 bit field */ i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 | le32_to_cpu(raw_inode->i_blocks_lo); @@ -4075,7 +4137,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)", EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); - ret = -EIO; + ret = -EFSCORRUPTED; goto bad_inode; } } else @@ -4095,7 +4157,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { EXT4_ERROR_INODE(inode, "checksum invalid"); - ret = -EIO; + ret = -EFSBADCRC; goto bad_inode; } @@ -4137,7 +4199,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_flags = le32_to_cpu(raw_inode->i_flags); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) + if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; inode->i_size = ext4_isize(raw_inode); @@ -4210,7 +4272,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { EXT4_ERROR_INODE(inode, "bad extended attribute block %llu", ei->i_file_acl); - ret = -EIO; + ret = -EFSCORRUPTED; goto bad_inode; } else if (!ext4_has_inline_data(inode)) { if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { @@ -4237,8 +4299,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext4_inode_is_fast_symlink(inode) && - !ext4_encrypted_inode(inode)) { + if (ext4_encrypted_inode(inode)) { + inode->i_op = &ext4_encrypted_symlink_inode_operations; + ext4_set_aops(inode); + } else if (ext4_inode_is_fast_symlink(inode)) { + inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); @@ -4258,7 +4323,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } else if (ino == EXT4_BOOT_LOADER_INO) { make_bad_inode(inode); } else { - ret = -EIO; + ret = -EFSCORRUPTED; EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); goto bad_inode; } @@ -4276,7 +4341,7 @@ bad_inode: struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) { if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); return ext4_iget(sb, ino); } @@ -4298,7 +4363,7 @@ static int ext4_inode_blocks_set(handle_t *handle, ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); return 0; } - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) + if (!ext4_has_feature_huge_file(sb)) return -EFBIG; if (i_blocks <= 0xffffffffffffULL) { @@ -4459,8 +4524,7 @@ static int ext4_do_update_inode(handle_t *handle, need_datasync = 1; } if (ei->i_disksize > 0x7fffffffULL) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE) || + if (!ext4_has_feature_large_file(sb) || EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) set_large_file = 1; @@ -4509,8 +4573,7 @@ static int ext4_do_update_inode(handle_t *handle, if (err) goto out_brelse; ext4_update_dynamic_rev(sb); - EXT4_SET_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE); + ext4_set_feature_large_file(sb); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); } @@ -4677,8 +4740,11 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (error) return error; - if (is_quota_modification(inode, attr)) - dquot_initialize(inode); + if (is_quota_modification(inode, attr)) { + error = dquot_initialize(inode); + if (error) + return error; + } if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; @@ -4707,8 +4773,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_journal_stop(handle); } - if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { + if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; + loff_t oldsize = inode->i_size; + int shrink = (attr->ia_size <= inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4716,27 +4784,37 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_size > sbi->s_bitmap_maxbytes) return -EFBIG; } + if (!S_ISREG(inode->i_mode)) + return -EINVAL; if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size) inode_inc_iversion(inode); - if (S_ISREG(inode->i_mode) && + if (ext4_should_order_data(inode) && (attr->ia_size < inode->i_size)) { - if (ext4_should_order_data(inode)) { - error = ext4_begin_ordered_truncate(inode, + error = ext4_begin_ordered_truncate(inode, attr->ia_size); - if (error) - goto err_out; - } + if (error) + goto err_out; + } + if (attr->ia_size != inode->i_size) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto err_out; } - if (ext4_handle_valid(handle)) { + if (ext4_handle_valid(handle) && shrink) { error = ext4_orphan_add(handle, inode); orphan = 1; } + /* + * Update c/mtime on truncate up, ext4_truncate() will + * update c/mtime in shrink case below + */ + if (!shrink) { + inode->i_mtime = ext4_current_time(inode); + inode->i_ctime = inode->i_mtime; + } down_write(&EXT4_I(inode)->i_data_sem); EXT4_I(inode)->i_disksize = attr->ia_size; rc = ext4_mark_inode_dirty(handle, inode); @@ -4752,15 +4830,13 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) { - ext4_orphan_del(NULL, inode); + if (orphan) + ext4_orphan_del(NULL, inode); goto err_out; } - } else { - loff_t oldsize = inode->i_size; - - i_size_write(inode, attr->ia_size); - pagecache_isize_extended(inode, oldsize, inode->i_size); } + if (!shrink) + pagecache_isize_extended(inode, oldsize, inode->i_size); /* * Blocks are going to be removed from the inode. Wait @@ -4780,13 +4856,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) * in data=journal mode to make pages freeable. */ truncate_pagecache(inode, inode->i_size); + if (shrink) + ext4_truncate(inode); } - /* - * We want to call ext4_truncate() even if attr->ia_size == - * inode->i_size for cases like truncation of fallocated space - */ - if (attr->ia_valid & ATTR_SIZE) - ext4_truncate(inode); if (!rc) { setattr_copy(inode, attr); @@ -5239,7 +5311,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = __block_page_mkwrite(vma, vmf, + ret = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); } while (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); @@ -5286,7 +5358,7 @@ retry_alloc: ret = VM_FAULT_SIGBUS; goto out; } - ret = __block_page_mkwrite(vma, vmf, get_block); + ret = block_page_mkwrite(vma, vmf, get_block); if (!ret && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {