static int orangefs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { int page_idx; int ret; gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n"); for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page; page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); if (!add_to_page_cache(page, mapping, page->index, readahead_gfp_mask(mapping))) { ret = read_one_page(page); gossip_debug(GOSSIP_INODE_DEBUG, "failure adding page to cache, read_one_page returned: %d\n", ret); } else { put_page(page); } } BUG_ON(!list_empty(pages)); return 0; }
/** * mpage_readpages - populate an address space with some pages & start reads against them * @mapping: the address_space * @pages: The address of a list_head which contains the target pages. These * pages have their ->index populated and are otherwise uninitialised. * The page at @pages->prev has the lowest file offset, and reads should be * issued in @pages->prev to @pages->next order. * @nr_pages: The number of pages at *@pages * @get_block: The filesystem's block mapper function. * * This function walks the pages and the blocks within each page, building and * emitting large BIOs. * * If anything unusual happens, such as: * * - encountering a page which has buffers * - encountering a page which has a non-hole after a hole * - encountering a page with non-contiguous blocks * * then this code just gives up and calls the buffer_head-based read function. * It does handle a page which has holes at the end - that is a common case: * the end-of-file on blocksize < PAGE_SIZE setups. * * BH_Boundary explanation: * * There is a problem. The mpage read code assembles several pages, gets all * their disk mappings, and then submits them all. That's fine, but obtaining * the disk mappings may require I/O. Reads of indirect blocks, for example. * * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be * submitted in the following order: * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16 * * because the indirect block has to be read to get the mappings of blocks * 13,14,15,16. Obviously, this impacts performance. * * So what we do it to allow the filesystem's get_block() function to set * BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block * after this one will require I/O against a block which is probably close to * this one. So you should push what I/O you have currently accumulated. * * This all causes the disk requests to be issued in the correct order. */ int mpage_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, get_block_t get_block) { struct bio *bio = NULL; unsigned page_idx; sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; gfp_t gfp = readahead_gfp_mask(mapping); map_bh.b_state = 0; map_bh.b_size = 0; for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = lru_to_page(pages); prefetchw(&page->flags); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) { bio = do_mpage_readpage(bio, page, nr_pages - page_idx, &last_block_in_bio, &map_bh, &first_logical_block, get_block, gfp); } put_page(page); } BUG_ON(!list_empty(pages)); if (bio) mpage_bio_submit(REQ_OP_READ, 0, bio); return 0; }
int ext4_mpage_readpages(struct address_space *mapping, struct list_head *pages, struct page *page, unsigned nr_pages, bool is_readahead) { struct bio *bio = NULL; sector_t last_block_in_bio = 0; struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocks_per_page = PAGE_SIZE >> blkbits; const unsigned blocksize = 1 << blkbits; sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; sector_t blocks[MAX_BUF_PER_PAGE]; unsigned page_block; struct block_device *bdev = inode->i_sb->s_bdev; int length; unsigned relative_block = 0; struct ext4_map_blocks map; map.m_pblk = 0; map.m_lblk = 0; map.m_len = 0; map.m_flags = 0; for (; nr_pages; nr_pages--) { int fully_mapped = 1; unsigned first_hole = blocks_per_page; prefetchw(&page->flags); if (pages) { page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, readahead_gfp_mask(mapping))) goto next_page; } if (page_has_buffers(page)) goto confused; block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; if (last_block > last_block_in_file) last_block = last_block_in_file; page_block = 0; /* * Map blocks using the previous result first. */ if ((map.m_flags & EXT4_MAP_MAPPED) && block_in_file > map.m_lblk && block_in_file < (map.m_lblk + map.m_len)) { unsigned map_offset = block_in_file - map.m_lblk; unsigned last = map.m_len - map_offset; for (relative_block = 0; ; relative_block++) { if (relative_block == last) { /* needed? */ map.m_flags &= ~EXT4_MAP_MAPPED; break; } if (page_block == blocks_per_page) break; blocks[page_block] = map.m_pblk + map_offset + relative_block; page_block++; block_in_file++; } } /* * Then do more ext4_map_blocks() calls until we are * done with this page. */ while (page_block < blocks_per_page) { if (block_in_file < last_block) { map.m_lblk = block_in_file; map.m_len = last_block - block_in_file; if (ext4_map_blocks(NULL, inode, &map, 0) < 0) { set_error_page: SetPageError(page); zero_user_segment(page, 0, PAGE_SIZE); unlock_page(page); goto next_page; } } if ((map.m_flags & EXT4_MAP_MAPPED) == 0) { fully_mapped = 0; if (first_hole == blocks_per_page) first_hole = page_block; page_block++; block_in_file++; continue; } if (first_hole != blocks_per_page) goto confused; /* hole -> non-hole */ /* Contiguous blocks? */ if (page_block && blocks[page_block-1] != map.m_pblk-1) goto confused; for (relative_block = 0; ; relative_block++) { if (relative_block == map.m_len) { /* needed? */ map.m_flags &= ~EXT4_MAP_MAPPED; break; } else if (page_block == blocks_per_page) break; blocks[page_block] = map.m_pblk+relative_block; page_block++; block_in_file++; } } if (first_hole != blocks_per_page) { zero_user_segment(page, first_hole << blkbits, PAGE_SIZE); if (first_hole == 0) { SetPageUptodate(page); unlock_page(page); goto next_page; } } else if (fully_mapped) { SetPageMappedToDisk(page); } if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) && cleancache_get_page(page) == 0) { SetPageUptodate(page); goto confused; } /* * This page will go to BIO. Do we need to send this * BIO off first? */ if (bio && (last_block_in_bio != blocks[0] - 1)) { submit_and_realloc: submit_bio(bio); bio = NULL; } if (bio == NULL) { struct fscrypt_ctx *ctx = NULL; if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { ctx = fscrypt_get_ctx(inode, GFP_NOFS); if (IS_ERR(ctx)) goto set_error_page; } bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); if (!bio) { if (ctx) fscrypt_release_ctx(ctx); goto set_error_page; } bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); bio->bi_end_io = mpage_end_io; bio->bi_private = ctx; bio_set_op_attrs(bio, REQ_OP_READ, is_readahead ? REQ_RAHEAD : 0); } length = first_hole << blkbits; if (bio_add_page(bio, page, length, 0) < length) goto submit_and_realloc; if (((map.m_flags & EXT4_MAP_BOUNDARY) && (relative_block == map.m_len)) || (first_hole != blocks_per_page)) { submit_bio(bio); bio = NULL; } else last_block_in_bio = blocks[blocks_per_page - 1]; goto next_page; confused: if (bio) { submit_bio(bio); bio = NULL; } if (!PageUptodate(page)) block_read_full_page(page, ext4_get_block); else unlock_page(page); next_page: if (pages) put_page(page); } BUG_ON(pages && !list_empty(pages)); if (bio) submit_bio(bio); return 0; }