From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx> At allocation time, put the pages in the cache unless we're using ->readpages. Add the readahead_for_each() iterator for the benefit of the ->readpage fallback. This iterator supports huge pages, even though none of the filesystems to be converted do yet. Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> --- include/linux/pagemap.h | 24 ++++++++++++++++++++++++ mm/readahead.c | 34 +++++++++++++++++----------------- 2 files changed, 41 insertions(+), 17 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 982ecda2d4a2..3613154e79e4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -639,8 +639,32 @@ struct readahead_control { /* private: use the readahead_* accessors instead */ pgoff_t _start; unsigned int _nr_pages; + unsigned int _batch_count; }; +static inline struct page *readahead_page(struct readahead_control *rac) +{ + struct page *page; + + if (!rac->_nr_pages) + return NULL; + + page = xa_load(&rac->mapping->i_pages, rac->_start); + VM_BUG_ON_PAGE(!PageLocked(page), page); + rac->_batch_count = hpage_nr_pages(page); + + return page; +} + +static inline void readahead_next(struct readahead_control *rac) +{ + rac->_nr_pages -= rac->_batch_count; + rac->_start += rac->_batch_count; +} + +#define readahead_for_each(rac, page) \ + for (; (page = readahead_page(rac)); readahead_next(rac)) + /* The number of pages in this readahead block */ static inline unsigned int readahead_count(struct readahead_control *rac) { diff --git a/mm/readahead.c b/mm/readahead.c index 74791b96013f..7663de534734 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -113,12 +113,11 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, EXPORT_SYMBOL(read_cache_pages); -static void read_pages(struct readahead_control *rac, struct list_head *pages, - gfp_t gfp) +static void read_pages(struct readahead_control *rac, struct list_head *pages) { const struct address_space_operations *aops = rac->mapping->a_ops; + struct page *page; struct blk_plug plug; - unsigned page_idx; blk_start_plug(&plug); @@ -127,19 +126,13 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, readahead_count(rac)); /* Clean up the remaining pages */ put_pages_list(pages); - goto out; - } - - for (page_idx = 0; page_idx < readahead_count(rac); page_idx++) { - struct page *page = lru_to_page(pages); - list_del(&page->lru); - if (!add_to_page_cache_lru(page, rac->mapping, page->index, - gfp)) + } else { + readahead_for_each(rac, page) { aops->readpage(rac->file, page); - put_page(page); + put_page(page); + } } -out: blk_finish_plug(&plug); } @@ -159,6 +152,7 @@ void __do_page_cache_readahead(struct address_space *mapping, int page_idx; loff_t isize = i_size_read(inode); gfp_t gfp_mask = readahead_gfp_mask(mapping); + bool use_list = mapping->a_ops->readpages; struct readahead_control rac = { .mapping = mapping, .file = filp, @@ -196,8 +190,14 @@ void __do_page_cache_readahead(struct address_space *mapping, page = __page_cache_alloc(gfp_mask); if (!page) break; - page->index = offset; - list_add(&page->lru, &page_pool); + if (use_list) { + page->index = offset; + list_add(&page->lru, &page_pool); + } else if (add_to_page_cache_lru(page, mapping, offset, + gfp_mask) < 0) { + put_page(page); + goto read; + } if (page_idx == nr_to_read - lookahead_size) SetPageReadahead(page); rac._nr_pages++; @@ -205,7 +205,7 @@ void __do_page_cache_readahead(struct address_space *mapping, continue; read: if (readahead_count(&rac)) - read_pages(&rac, &page_pool, gfp_mask); + read_pages(&rac, &page_pool); rac._nr_pages = 0; rac._start = ++offset; } @@ -216,7 +216,7 @@ void __do_page_cache_readahead(struct address_space *mapping, * will then handle the error. */ if (readahead_count(&rac)) - read_pages(&rac, &page_pool, gfp_mask); + read_pages(&rac, &page_pool); BUG_ON(!list_empty(&page_pool)); } -- 2.25.0