Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754434AbdCFOEk (ORCPT ); Mon, 6 Mar 2017 09:04:40 -0500 Received: from mga11.intel.com ([192.55.52.93]:57264 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754189AbdCFOA2 (ORCPT ); Mon, 6 Mar 2017 09:00:28 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.35,253,1484035200"; d="scan'208";a="1105321940" From: "Kirill A. Shutemov" To: Linus Torvalds , Andrew Morton , x86@kernel.org, Thomas Gleixner , Ingo Molnar , Arnd Bergmann , "H. Peter Anvin" Cc: Andi Kleen , Dave Hansen , Andy Lutomirski , linux-arch@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, "Kirill A. Shutemov" Subject: [PATCHv4 10/33] x86/gup: add 5-level paging support Date: Mon, 6 Mar 2017 16:53:34 +0300 Message-Id: <20170306135357.3124-11-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170306135357.3124-1-kirill.shutemov@linux.intel.com> References: <20170306135357.3124-1-kirill.shutemov@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2667 Lines: 87 It's simply extension for one more page table level. Signed-off-by: Kirill A. Shutemov --- arch/x86/mm/gup.c | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 99c7805a9693..eb407cf0f6d3 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -76,9 +76,9 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) } /* - * 'pteval' can come from a pte, pmd or pud. We only check + * 'pteval' can come from a pte, pmd, pud or p4d. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 3 types. + * same value on all 4 types. */ static inline int pte_allows_gup(unsigned long pteval, int write) { @@ -290,13 +290,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = *pudp; @@ -315,6 +315,27 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = *p4dp; + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_large(p4d)); + if (!gup_pud_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except its IRQ-safe in that it won't fall * back to the regular GUP. @@ -363,7 +384,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); @@ -435,7 +456,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) goto slow; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) goto slow; } while (pgdp++, addr = next, addr != end); local_irq_enable(); -- 2.11.0