From 37be6c80947b946a1cdb4a931f6fba1fc880b956 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 25 May 2019 18:34:24 +0800 Subject: [PATCH] iov_iter: optimize page_copy_sane() commit 6daef95b8c914866a46247232a048447fff97279 upstream. Avoid cache line miss dereferencing struct page if we can. page_copy_sane() mostly deals with order-0 pages. Extra cache line miss is visible on TCP recvmsg() calls dealing with GRO packets (typically 45 page frags are attached to one skb). Bringing the 45 struct pages into cpu cache while copying the data is not free, since the freeing of the skb (and associated page frags put_page()) can happen after cache lines have been evicted. Signed-off-by: Eric Dumazet Cc: Al Viro Signed-off-by: Al Viro Cc: Matthew Wilcox Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yang Yingliang --- lib/iov_iter.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 2b4fe3f10904..d51bd7283243 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -817,8 +817,21 @@ EXPORT_SYMBOL(_copy_from_iter_full_nocache); static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { - struct page *head = compound_head(page); - size_t v = n + offset + page_address(page) - page_address(head); + struct page *head; + size_t v = n + offset; + + /* + * The general case needs to access the page order in order + * to compute the page size. + * However, we mostly deal with order-0 pages and thus can + * avoid a possible cache line miss for requests that fit all + * page orders. + */ + if (n <= v && v <= PAGE_SIZE) + return true; + + head = compound_head(page); + v += (page - head) << PAGE_SHIFT; if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head)))) return true; -- GitLab