From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-15.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 39EA2C433E0 for ; Wed, 24 Feb 2021 20:03:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 0451A64F26 for ; Wed, 24 Feb 2021 20:03:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235279AbhBXUDQ (ORCPT ); Wed, 24 Feb 2021 15:03:16 -0500 Received: from mail.kernel.org ([198.145.29.99]:55482 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235278AbhBXUCh (ORCPT ); Wed, 24 Feb 2021 15:02:37 -0500 Received: by mail.kernel.org (Postfix) with ESMTPSA id C29BB64F0E; Wed, 24 Feb 2021 20:01:59 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1614196920; bh=aCK0dNgwGkv90of6nPlfiG1AVyeLOiO5Ok0TXQU0XMc=; h=Date:From:To:Subject:In-Reply-To:From; b=D5IzzQK/qajMCdfut204yMk9o/QPSWaK/gcOBWiYEh3t7WQPbYAF0ht3XjcaJ5LMm cb46X6COJ+VNPBrQZq1j6OVsKgLKYaYn0OBbK+Asxkq2GjuNqRCq0iN2U6sXFDmQI7 1550nZBo0PmZlZafnawguYrx7VerSdxv1e/nyCKM= Date: Wed, 24 Feb 2021 12:01:59 -0800 From: Andrew Morton To: akpm@linux-foundation.org, hch@lst.de, kent.overstreet@gmail.com, linmiaohe@huawei.com, linux-mm@kvack.org, mm-commits@vger.kernel.org, torvalds@linux-foundation.org, willy@infradead.org Subject: [patch 033/173] mm/filemap: use head pages in generic_file_buffered_read Message-ID: <20210224200159.h_ITNzOVN%akpm@linux-foundation.org> In-Reply-To: <20210224115824.1e289a6895087f10c41dd8d6@linux-foundation.org> User-Agent: s-nail v14.8.16 Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org From: "Matthew Wilcox (Oracle)" Subject: mm/filemap: use head pages in generic_file_buffered_read Add filemap_get_read_batch() which returns the head pages which represent a contiguous array of bytes in the file. It also stops when encountering a page marked as Readahead or !Uptodate (but does return that page) so it can be handled appropriately by filemap_get_pages(). That lets us remove the loop in filemap_get_pages() and check only the last page. Link: https://lkml.kernel.org/r/20210122160140.223228-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Kent Overstreet Reviewed-by: Christoph Hellwig Cc: Miaohe Lin Signed-off-by: Andrew Morton --- mm/filemap.c | 122 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 85 insertions(+), 37 deletions(-) --- a/mm/filemap.c~mm-filemap-use-head-pages-in-generic_file_buffered_read +++ a/mm/filemap.c @@ -2178,6 +2178,51 @@ static int lock_page_for_iocb(struct kio return lock_page_killable(page); } +/* + * filemap_get_read_batch - Get a batch of pages for read + * + * Get a batch of pages which represent a contiguous range of bytes + * in the file. No tail pages will be returned. If @index is in the + * middle of a THP, the entire THP will be returned. The last page in + * the batch may have Readahead set or be not Uptodate so that the + * caller can take the appropriate action. + */ +static void filemap_get_read_batch(struct address_space *mapping, + pgoff_t index, pgoff_t max, struct pagevec *pvec) +{ + XA_STATE(xas, &mapping->i_pages, index); + struct page *head; + + rcu_read_lock(); + for (head = xas_load(&xas); head; head = xas_next(&xas)) { + if (xas_retry(&xas, head)) + continue; + if (xas.xa_index > max || xa_is_value(head)) + break; + if (!page_cache_get_speculative(head)) + goto retry; + + /* Has the page moved or been split? */ + if (unlikely(head != xas_reload(&xas))) + goto put_page; + + if (!pagevec_add(pvec, head)) + break; + if (!PageUptodate(head)) + break; + if (PageReadahead(head)) + break; + xas.xa_index = head->index + thp_nr_pages(head) - 1; + xas.xa_offset = (xas.xa_index >> xas.xa_shift) & XA_CHUNK_MASK; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); + } + rcu_read_unlock(); +} + static struct page *filemap_read_page(struct kiocb *iocb, struct file *filp, struct address_space *mapping, struct page *page) { @@ -2331,15 +2376,15 @@ static int filemap_get_pages(struct kioc struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; - pgoff_t last_index = (iocb->ki_pos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; - unsigned int nr = min_t(unsigned long, last_index - index, PAGEVEC_SIZE); - int i, j, err = 0; + pgoff_t last_index; + int err = 0; + last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE); find_page: if (fatal_signal_pending(current)) return -EINTR; - pvec->nr = find_get_pages_contig(mapping, index, nr, pvec->pages); + filemap_get_read_batch(mapping, index, last_index, pvec); if (pvec->nr) goto got_pages; @@ -2348,29 +2393,30 @@ find_page: page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); - pvec->nr = find_get_pages_contig(mapping, index, nr, pvec->pages); + filemap_get_read_batch(mapping, index, last_index, pvec); if (pvec->nr) goto got_pages; pvec->pages[0] = filemap_create_page(iocb, iter); err = PTR_ERR_OR_ZERO(pvec->pages[0]); - if (!IS_ERR_OR_NULL(pvec->pages[0])) - pvec->nr = 1; + if (IS_ERR_OR_NULL(pvec->pages[0])) + goto err; + pvec->nr = 1; + return 0; got_pages: - for (i = 0; i < pvec->nr; i++) { - struct page *page = pvec->pages[i]; - pgoff_t pg_index = index + i; + { + struct page *page = pvec->pages[pvec->nr - 1]; + pgoff_t pg_index = page->index; loff_t pg_pos = max(iocb->ki_pos, (loff_t) pg_index << PAGE_SHIFT); loff_t pg_count = iocb->ki_pos + iter->count - pg_pos; if (PageReadahead(page)) { if (iocb->ki_flags & IOCB_NOIO) { - for (j = i; j < pvec->nr; j++) - put_page(pvec->pages[j]); - pvec->nr = i; + put_page(page); + pvec->nr--; err = -EAGAIN; - break; + goto err; } page_cache_async_readahead(mapping, ra, filp, page, pg_index, last_index - pg_index); @@ -2378,26 +2424,23 @@ got_pages: if (!PageUptodate(page)) { if ((iocb->ki_flags & IOCB_NOWAIT) || - ((iocb->ki_flags & IOCB_WAITQ) && i)) { - for (j = i; j < pvec->nr; j++) - put_page(pvec->pages[j]); - pvec->nr = i; + ((iocb->ki_flags & IOCB_WAITQ) && pvec->nr > 1)) { + put_page(page); + pvec->nr--; err = -EAGAIN; - break; + goto err; } page = filemap_update_page(iocb, filp, iter, page, pg_pos, pg_count); if (IS_ERR_OR_NULL(page)) { - for (j = i + 1; j < pvec->nr; j++) - put_page(pvec->pages[j]); - pvec->nr = i; + pvec->nr--; err = PTR_ERR_OR_ZERO(page); - break; } } } +err: if (likely(pvec->nr)) return 0; if (err) @@ -2442,6 +2485,7 @@ ssize_t generic_file_buffered_read(struc return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + pagevec_init(&pvec); do { cond_resched(); @@ -2469,13 +2513,8 @@ ssize_t generic_file_buffered_read(struc isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_pages; - end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); - while ((iocb->ki_pos >> PAGE_SHIFT) + pvec.nr > - (end_offset + PAGE_SIZE - 1) >> PAGE_SHIFT) - put_page(pvec.pages[--pvec.nr]); - /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: @@ -2489,24 +2528,32 @@ ssize_t generic_file_buffered_read(struc if (iocb->ki_pos >> PAGE_SHIFT != ra->prev_pos >> PAGE_SHIFT) mark_page_accessed(pvec.pages[0]); - for (i = 1; i < pagevec_count(&pvec); i++) - mark_page_accessed(pvec.pages[i]); for (i = 0; i < pagevec_count(&pvec); i++) { - unsigned int offset = iocb->ki_pos & ~PAGE_MASK; - unsigned int bytes = min_t(loff_t, end_offset - iocb->ki_pos, - PAGE_SIZE - offset); - unsigned int copied; + struct page *page = pvec.pages[i]; + size_t page_size = thp_size(page); + size_t offset = iocb->ki_pos & (page_size - 1); + size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, + page_size - offset); + size_t copied; + if (end_offset < page_offset(page)) + break; + if (i > 0) + mark_page_accessed(page); /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ - if (writably_mapped) - flush_dcache_page(pvec.pages[i]); + if (writably_mapped) { + int j; + + for (j = 0; j < thp_nr_pages(page); j++) + flush_dcache_page(page + j); + } - copied = copy_page_to_iter(pvec.pages[i], offset, bytes, iter); + copied = copy_page_to_iter(page, offset, bytes, iter); written += copied; iocb->ki_pos += copied; @@ -2520,6 +2567,7 @@ ssize_t generic_file_buffered_read(struc put_pages: for (i = 0; i < pagevec_count(&pvec); i++) put_page(pvec.pages[i]); + pagevec_reinit(&pvec); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); _