From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx> Subject: mm: add page_cache_readahead_unbounded ext4 and f2fs have duplicated the guts of the readahead code so they can read past i_size. Instead, separate out the guts of the readahead code so they can call it directly. Link: http://lkml.kernel.org/r/20200414150233.24495-14-willy@xxxxxxxxxxxxx Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Reviewed-by: Christoph Hellwig <hch@xxxxxx> Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx> Reviewed-by: Eric Biggers <ebiggers@xxxxxxxxxx> Tested-by: Eric Biggers <ebiggers@xxxxxxxxxx> Cc: Chao Yu <yuchao0@xxxxxxxxxx> Cc: Cong Wang <xiyou.wangcong@xxxxxxxxx> Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx> Cc: Dave Chinner <dchinner@xxxxxxxxxx> Cc: Gao Xiang <gaoxiang25@xxxxxxxxxx> Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx> Cc: John Hubbard <jhubbard@xxxxxxxxxx> Cc: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx> Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Zi Yan <ziy@xxxxxxxxxx> Cc: Johannes Thumshirn <johannes.thumshirn@xxxxxxx> Cc: Miklos Szeredi <mszeredi@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/ext4/verity.c | 35 +------------------ fs/f2fs/data.c | 2 - fs/f2fs/f2fs.h | 3 - fs/f2fs/verity.c | 35 +------------------ include/linux/pagemap.h | 3 + mm/readahead.c | 68 ++++++++++++++++++++++++++------------ 6 files changed, 55 insertions(+), 91 deletions(-) --- a/fs/ext4/verity.c~mm-add-page_cache_readahead_unbounded +++ a/fs/ext4/verity.c @@ -342,37 +342,6 @@ static int ext4_get_verity_descriptor(st return desc_size; } -/* - * Prefetch some pages from the file's Merkle tree. - * - * This is basically a stripped-down version of __do_page_cache_readahead() - * which works on pages past i_size. - */ -static void ext4_merkle_tree_readahead(struct address_space *mapping, - pgoff_t start_index, unsigned long count) -{ - LIST_HEAD(pages); - unsigned int nr_pages = 0; - struct page *page; - pgoff_t index; - struct blk_plug plug; - - for (index = start_index; index < start_index + count; index++) { - page = xa_load(&mapping->i_pages, index); - if (!page || xa_is_value(page)) { - page = __page_cache_alloc(readahead_gfp_mask(mapping)); - if (!page) - break; - page->index = index; - list_add(&page->lru, &pages); - nr_pages++; - } - } - blk_start_plug(&plug); - ext4_mpage_readpages(mapping, &pages, NULL, nr_pages, true); - blk_finish_plug(&plug); -} - static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) @@ -386,8 +355,8 @@ static struct page *ext4_read_merkle_tre if (page) put_page(page); else if (num_ra_pages > 1) - ext4_merkle_tree_readahead(inode->i_mapping, index, - num_ra_pages); + page_cache_readahead_unbounded(inode->i_mapping, NULL, + index, num_ra_pages, 0); page = read_mapping_page(inode->i_mapping, index, NULL); } return page; --- a/fs/f2fs/data.c~mm-add-page_cache_readahead_unbounded +++ a/fs/f2fs/data.c @@ -2177,7 +2177,7 @@ out: * use ->readpage() or do the necessary surgery to decouple ->readpages() * from read-ahead. */ -int f2fs_mpage_readpages(struct address_space *mapping, +static int f2fs_mpage_readpages(struct address_space *mapping, struct list_head *pages, struct page *page, unsigned nr_pages, bool is_readahead) { --- a/fs/f2fs/f2fs.h~mm-add-page_cache_readahead_unbounded +++ a/fs/f2fs/f2fs.h @@ -3373,9 +3373,6 @@ int f2fs_reserve_new_block(struct dnode_ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index); int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from); int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); -int f2fs_mpage_readpages(struct address_space *mapping, - struct list_head *pages, struct page *page, - unsigned nr_pages, bool is_readahead); struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, int op_flags, bool for_write); struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index); --- a/fs/f2fs/verity.c~mm-add-page_cache_readahead_unbounded +++ a/fs/f2fs/verity.c @@ -222,37 +222,6 @@ static int f2fs_get_verity_descriptor(st return size; } -/* - * Prefetch some pages from the file's Merkle tree. - * - * This is basically a stripped-down version of __do_page_cache_readahead() - * which works on pages past i_size. - */ -static void f2fs_merkle_tree_readahead(struct address_space *mapping, - pgoff_t start_index, unsigned long count) -{ - LIST_HEAD(pages); - unsigned int nr_pages = 0; - struct page *page; - pgoff_t index; - struct blk_plug plug; - - for (index = start_index; index < start_index + count; index++) { - page = xa_load(&mapping->i_pages, index); - if (!page || xa_is_value(page)) { - page = __page_cache_alloc(readahead_gfp_mask(mapping)); - if (!page) - break; - page->index = index; - list_add(&page->lru, &pages); - nr_pages++; - } - } - blk_start_plug(&plug); - f2fs_mpage_readpages(mapping, &pages, NULL, nr_pages, true); - blk_finish_plug(&plug); -} - static struct page *f2fs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) @@ -266,8 +235,8 @@ static struct page *f2fs_read_merkle_tre if (page) put_page(page); else if (num_ra_pages > 1) - f2fs_merkle_tree_readahead(inode->i_mapping, index, - num_ra_pages); + page_cache_readahead_unbounded(inode->i_mapping, NULL, + index, num_ra_pages, 0); page = read_mapping_page(inode->i_mapping, index, NULL); } return page; --- a/include/linux/pagemap.h~mm-add-page_cache_readahead_unbounded +++ a/include/linux/pagemap.h @@ -625,6 +625,9 @@ void page_cache_sync_readahead(struct ad void page_cache_async_readahead(struct address_space *, struct file_ra_state *, struct file *, struct page *, pgoff_t index, unsigned long req_count); +void page_cache_readahead_unbounded(struct address_space *, struct file *, + pgoff_t index, unsigned long nr_to_read, + unsigned long lookahead_count); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: --- a/mm/readahead.c~mm-add-page_cache_readahead_unbounded +++ a/mm/readahead.c @@ -156,37 +156,34 @@ out: rac->_index++; } -/* - * __do_page_cache_readahead() actually reads a chunk of disk. It allocates - * the pages first, then submits them for I/O. This avoids the very bad - * behaviour which would occur if page allocations are causing VM writeback. - * We really don't want to intermingle reads and writes like that. +/** + * page_cache_readahead_unbounded - Start unchecked readahead. + * @mapping: File address space. + * @file: This instance of the open file; used for authentication. + * @index: First page index to read. + * @nr_to_read: The number of pages to read. + * @lookahead_size: Where to start the next readahead. + * + * This function is for filesystems to call when they want to start + * readahead beyond a file's stated i_size. This is almost certainly + * not the function you want to call. Use page_cache_async_readahead() + * or page_cache_sync_readahead() instead. + * + * Context: File is referenced by caller. Mutexes may be held by caller. + * May sleep, but will not reenter filesystem to reclaim memory. */ -void __do_page_cache_readahead(struct address_space *mapping, - struct file *filp, pgoff_t index, unsigned long nr_to_read, +void page_cache_readahead_unbounded(struct address_space *mapping, + struct file *file, pgoff_t index, unsigned long nr_to_read, unsigned long lookahead_size) { - struct inode *inode = mapping->host; LIST_HEAD(page_pool); - loff_t isize = i_size_read(inode); gfp_t gfp_mask = readahead_gfp_mask(mapping); struct readahead_control rac = { .mapping = mapping, - .file = filp, + .file = file, ._index = index, }; unsigned long i; - pgoff_t end_index; /* The last page we want to read */ - - if (isize == 0) - return; - - end_index = (isize - 1) >> PAGE_SHIFT; - if (index > end_index) - return; - /* Don't read past the page containing the last byte of the file */ - if (nr_to_read > end_index - index) - nr_to_read = end_index - index + 1; /* * Preallocate as many pages as we will need. @@ -230,6 +227,35 @@ void __do_page_cache_readahead(struct ad */ read_pages(&rac, &page_pool, false); } +EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded); + +/* + * __do_page_cache_readahead() actually reads a chunk of disk. It allocates + * the pages first, then submits them for I/O. This avoids the very bad + * behaviour which would occur if page allocations are causing VM writeback. + * We really don't want to intermingle reads and writes like that. + */ +void __do_page_cache_readahead(struct address_space *mapping, + struct file *file, pgoff_t index, unsigned long nr_to_read, + unsigned long lookahead_size) +{ + struct inode *inode = mapping->host; + loff_t isize = i_size_read(inode); + pgoff_t end_index; /* The last page we want to read */ + + if (isize == 0) + return; + + end_index = (isize - 1) >> PAGE_SHIFT; + if (index > end_index) + return; + /* Don't read past the page containing the last byte of the file */ + if (nr_to_read > end_index - index) + nr_to_read = end_index - index + 1; + + page_cache_readahead_unbounded(mapping, file, index, nr_to_read, + lookahead_size); +} /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much _
