Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760263AbcDEVdU (ORCPT ); Tue, 5 Apr 2016 17:33:20 -0400 Received: from mail-pf0-f181.google.com ([209.85.192.181]:35671 "EHLO mail-pf0-f181.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760228AbcDEVdR (ORCPT ); Tue, 5 Apr 2016 17:33:17 -0400 Date: Tue, 5 Apr 2016 14:33:14 -0700 (PDT) From: Hugh Dickins X-X-Sender: hugh@eggly.anvils To: Andrew Morton cc: "Kirill A. Shutemov" , Andrea Arcangeli , Andres Lagar-Cavilla , Yang Shi , Ning Qu , Ralf Baechle , Martin Schwidefsky , David Miller , Ingo Molnar , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH 12/31] huge tmpfs: extend get_user_pages_fast to shmem pmd In-Reply-To: Message-ID: References: User-Agent: Alpine 2.11 (LSU 23 2013-08-11) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4743 Lines: 170 The arch-specific get_user_pages_fast() has a gup_huge_pmd() designed to optimize the refcounting on anonymous THP and hugetlbfs pages, with one atomic addition to compound head's common refcount. That optimization must be avoided on huge tmpfs team pages, which use normal separate page refcounting. We could combine the PageTeam and PageCompound cases into a single simple loop, but would lose the compound optimization that way. One cannot go through these functions without wondering why some arches (x86, mips) like to SetPageReferenced, while the rest do not: an x86 optimization that missed being propagated to the other architectures? No, see commit 8ee53820edfd ("thp: mmu_notifier_test_young"): it's a KVM GRU EPT thing, maybe not useful beyond x86. I've just followed the established practice in each architecture. Signed-off-by: Hugh Dickins --- Cc'ed to arch maintainers as an FYI: this patch is not expected to go into the tree in the next few weeks, and depends upon a PageTeam definition not yet available outside this huge tmpfs patchset. Please refer to linux-mm or linux-kernel for more context. arch/mips/mm/gup.c | 15 ++++++++++++++- arch/s390/mm/gup.c | 19 ++++++++++++++++++- arch/sparc/mm/gup.c | 19 ++++++++++++++++++- arch/x86/mm/gup.c | 15 ++++++++++++++- mm/gup.c | 19 ++++++++++++++++++- 5 files changed, 82 insertions(+), 5 deletions(-) --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -81,9 +81,22 @@ static int gup_huge_pmd(pmd_t pmd, unsig VM_BUG_ON(pte_special(pte)); VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - refs = 0; head = pte_page(pte); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + + if (PageTeam(head)) { + /* Handle a huge tmpfs team with normal refcounting. */ + do { + get_page(page); + SetPageReferenced(page); + pages[*nr] = page; + (*nr)++; + page++; + } while (addr += PAGE_SIZE, addr != end); + return 1; + } + + refs = 0; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -66,9 +66,26 @@ static inline int gup_huge_pmd(pmd_t *pm return 0; VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT)); - refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + + if (PageTeam(head)) { + /* Handle a huge tmpfs team with normal refcounting. */ + do { + if (!page_cache_get_speculative(page)) + return 0; + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) { + put_page(page); + return 0; + } + pages[*nr] = page; + (*nr)++; + page++; + } while (addr += PAGE_SIZE, addr != end); + return 1; + } + + refs = 0; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -77,9 +77,26 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd if (write && !pmd_write(pmd)) return 0; - refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + + if (PageTeam(head)) { + /* Handle a huge tmpfs team with normal refcounting. */ + do { + if (!page_cache_get_speculative(page)) + return 0; + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) { + put_page(page); + return 0; + } + pages[*nr] = page; + (*nr)++; + page++; + } while (addr += PAGE_SIZE, addr != end); + return 1; + } + + refs = 0; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -196,9 +196,22 @@ static noinline int gup_huge_pmd(pmd_t p /* hugepages are never "special" */ VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + + if (PageTeam(head)) { + /* Handle a huge tmpfs team with normal refcounting. */ + do { + get_page(page); + SetPageReferenced(page); + pages[*nr] = page; + (*nr)++; + page++; + } while (addr += PAGE_SIZE, addr != end); + return 1; + } + + refs = 0; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; --- a/mm/gup.c +++ b/mm/gup.c @@ -1247,9 +1247,26 @@ static int gup_huge_pmd(pmd_t orig, pmd_ if (write && !pmd_write(orig)) return 0; - refs = 0; head = pmd_page(orig); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + + if (PageTeam(head)) { + /* Handle a huge tmpfs team with normal refcounting. */ + do { + if (!page_cache_get_speculative(page)) + return 0; + if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { + put_page(page); + return 0; + } + pages[*nr] = page; + (*nr)++; + page++; + } while (addr += PAGE_SIZE, addr != end); + return 1; + } + + refs = 0; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page;