Provide a function, readahead_expand(), that expands the set of pages specified by a readahead_control object to encompass a revised area with a proposed size and length. The proposed area must include all of the old area and may be expanded yet more by this function so that the edges align on (transparent huge) page boundaries as allocated. The expansion will be cut short if a page already exists in either of the areas being expanded into. Note that any expansion made in such a case is not rolled back. This will be used by fscache so that reads can be expanded to cache granule boundaries, thereby allowing whole granules to be stored in the cache, but there are other potential users also. Changes: - Moved the declaration of readahead_expand() to a better place[1]. Suggested-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Signed-off-by: David Howells <dhowells@xxxxxxxxxx> cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx> cc: Christoph Hellwig <hch@xxxxxx> cc: linux-mm@xxxxxxxxx cc: linux-cachefs@xxxxxxxxxx cc: linux-afs@xxxxxxxxxxxxxxxxxxx cc: linux-nfs@xxxxxxxxxxxxxxx cc: linux-cifs@xxxxxxxxxxxxxxx cc: ceph-devel@xxxxxxxxxxxxxxx cc: v9fs-developer@xxxxxxxxxxxxxxxxxxxxx cc: linux-fsdevel@xxxxxxxxxxxxxxx Link: https://lore.kernel.org/r/20210217161358.GM2858050@xxxxxxxxxxxxxxxxxxxx/ [1] Link: https://lore.kernel.org/r/159974633888.2094769.8326206446358128373.stgit@xxxxxxxxxxxxxxxxxxxxxx/ Link: https://lore.kernel.org/r/160588479816.3465195.553952688795241765.stgit@xxxxxxxxxxxxxxxxxxxxxx/ # rfc Link: https://lore.kernel.org/r/161118131787.1232039.4863969952441067985.stgit@xxxxxxxxxxxxxxxxxxxxxx/ # rfc Link: https://lore.kernel.org/r/161161028670.2537118.13831420617039766044.stgit@xxxxxxxxxxxxxxxxxxxxxx/ # v2 Link: https://lore.kernel.org/r/161340389201.1303470.14353807284546854878.stgit@xxxxxxxxxxxxxxxxxxxxxx/ # v3 Link: https://lore.kernel.org/r/161539530488.286939.18085961677838089157.stgit@xxxxxxxxxxxxxxxxxxxxxx/ # v4 --- include/linux/pagemap.h | 2 + mm/readahead.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index da5c38864037..5c14a9365aae 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -837,6 +837,8 @@ void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct file_ra_state *, struct page *, unsigned long req_count); +void readahead_expand(struct readahead_control *ractl, + loff_t new_start, size_t new_len); /** * page_cache_sync_readahead - generic file readahead diff --git a/mm/readahead.c b/mm/readahead.c index c5b0457415be..4446dada0bc2 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -638,3 +638,73 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } + +/** + * readahead_expand - Expand a readahead request + * @ractl: The request to be expanded + * @new_start: The revised start + * @new_len: The revised size of the request + * + * Attempt to expand a readahead request outwards from the current size to the + * specified size by inserting locked pages before and after the current window + * to increase the size to the new window. This may involve the insertion of + * THPs, in which case the window may get expanded even beyond what was + * requested. + * + * The algorithm will stop if it encounters a conflicting page already in the + * pagecache and leave a smaller expansion than requested. + * + * The caller must check for this by examining the revised @ractl object for a + * different expansion than was requested. + */ +void readahead_expand(struct readahead_control *ractl, + loff_t new_start, size_t new_len) +{ + struct address_space *mapping = ractl->mapping; + pgoff_t new_index, new_nr_pages; + gfp_t gfp_mask = readahead_gfp_mask(mapping); + + new_index = new_start / PAGE_SIZE; + + /* Expand the leading edge downwards */ + while (ractl->_index > new_index) { + unsigned long index = ractl->_index - 1; + struct page *page = xa_load(&mapping->i_pages, index); + + if (page && !xa_is_value(page)) + return; /* Page apparently present */ + + page = __page_cache_alloc(gfp_mask); + if (!page) + return; + if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) { + put_page(page); + return; + } + + ractl->_nr_pages++; + ractl->_index = page->index; + } + + new_len += new_start - readahead_pos(ractl); + new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); + + /* Expand the trailing edge upwards */ + while (ractl->_nr_pages < new_nr_pages) { + unsigned long index = ractl->_index + ractl->_nr_pages; + struct page *page = xa_load(&mapping->i_pages, index); + + if (page && !xa_is_value(page)) + return; /* Page apparently present */ + + page = __page_cache_alloc(gfp_mask); + if (!page) + return; + if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) { + put_page(page); + return; + } + ractl->_nr_pages++; + } +} +EXPORT_SYMBOL(readahead_expand);
