Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754813AbcCaC20 (ORCPT ); Wed, 30 Mar 2016 22:28:26 -0400 Received: from TYO201.gate.nec.co.jp ([210.143.35.51]:59689 "EHLO tyo201.gate.nec.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750704AbcCaC2Z convert rfc822-to-8bit (ORCPT ); Wed, 30 Mar 2016 22:28:25 -0400 From: Naoya Horiguchi To: Mike Kravetz CC: Ingo Molnar , "linux-mm@kvack.org" , "linux-kernel@vger.kernel.org" , "x86@kernel.org" , Hugh Dickins , "Hillf Danton" , "Kirill A. Shutemov" , David Rientjes , "Dave Hansen" , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , "Catalin Marinas" , Will Deacon , "Steve Capper" , Andrew Morton Subject: Re: [RFC PATCH 2/2] x86/hugetlb: Attempt PUD_SIZE mapping alignment if PMD sharing enabled Thread-Topic: [RFC PATCH 2/2] x86/hugetlb: Attempt PUD_SIZE mapping alignment if PMD sharing enabled Thread-Index: AQHRiVglaJ7rMpcmDE+CwX9efSA/iJ9vgj8AgACOl4CAAi8vgA== Date: Thu, 31 Mar 2016 02:26:56 +0000 Message-ID: <20160331022655.GA24293@hori1.linux.bs1.fc.nec.co.jp> References: <1459213970-17957-1-git-send-email-mike.kravetz@oracle.com> <1459213970-17957-3-git-send-email-mike.kravetz@oracle.com> <20160329083510.GA27941@gmail.com> <56FAB5DB.8070003@oracle.com> In-Reply-To: <56FAB5DB.8070003@oracle.com> Accept-Language: ja-JP, en-US Content-Language: ja-JP X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.128.101.30] Content-Type: text/plain; charset="iso-2022-jp" Content-ID: <9F368A9A34165248A39CDDA955E4A1B4@gisp.nec.co.jp> Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3328 Lines: 84 On Tue, Mar 29, 2016 at 10:05:31AM -0700, Mike Kravetz wrote: > On 03/29/2016 01:35 AM, Ingo Molnar wrote: > > > > * Mike Kravetz wrote: > > > >> When creating a hugetlb mapping, attempt PUD_SIZE alignment if the > >> following conditions are met: > >> - Address passed to mmap or shmat is NULL > >> - The mapping is flaged as shared > >> - The mapping is at least PUD_SIZE in length > >> If a PUD_SIZE aligned mapping can not be created, then fall back to a > >> huge page size mapping. > >> > >> Signed-off-by: Mike Kravetz > >> --- > >> arch/x86/mm/hugetlbpage.c | 64 ++++++++++++++++++++++++++++++++++++++++++++--- > >> 1 file changed, 61 insertions(+), 3 deletions(-) > >> > >> diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c > >> index 42982b2..4f53af5 100644 > >> --- a/arch/x86/mm/hugetlbpage.c > >> +++ b/arch/x86/mm/hugetlbpage.c > >> @@ -78,14 +78,39 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, > >> { > >> struct hstate *h = hstate_file(file); > >> struct vm_unmapped_area_info info; > >> + bool pud_size_align = false; > >> + unsigned long ret_addr; > >> + > >> + /* > >> + * If PMD sharing is enabled, align to PUD_SIZE to facilitate > >> + * sharing. Only attempt alignment if no address was passed in, > >> + * flags indicate sharing and size is big enough. > >> + */ > >> + if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && > >> + !addr && flags & MAP_SHARED && len >= PUD_SIZE) > >> + pud_size_align = true; > >> > >> info.flags = 0; > >> info.length = len; > >> info.low_limit = current->mm->mmap_legacy_base; > >> info.high_limit = TASK_SIZE; > >> - info.align_mask = PAGE_MASK & ~huge_page_mask(h); > >> + if (pud_size_align) > >> + info.align_mask = PAGE_MASK & (PUD_SIZE - 1); > >> + else > >> + info.align_mask = PAGE_MASK & ~huge_page_mask(h); > >> info.align_offset = 0; > >> - return vm_unmapped_area(&info); > >> + ret_addr = vm_unmapped_area(&info); > >> + > >> + /* > >> + * If failed with PUD_SIZE alignment, try again with huge page > >> + * size alignment. > >> + */ > >> + if ((ret_addr & ~PAGE_MASK) && pud_size_align) { > >> + info.align_mask = PAGE_MASK & ~huge_page_mask(h); > >> + ret_addr = vm_unmapped_area(&info); > >> + } > > > > So AFAICS 'ret_addr' is either page aligned, or is an error code. Wouldn't it be a > > lot easier to read to say: > > > > if ((long)ret_addr > 0 && pud_size_align) { > > info.align_mask = PAGE_MASK & ~huge_page_mask(h); > > ret_addr = vm_unmapped_area(&info); > > } > > > > return ret_addr; > > > > to make it clear that it's about error handling, not some alignment > > requirement/restriction? > > Yes, I agree that is easier to read. However, it assumes that process > virtual addresses can never evaluate to a negative long value. This may > be the case for x86_64 today. But, there are other architectures where > this is not the case. I know this is x86 specific code, but might it be > possible that x86 virtual addresses could be negative longs in the future? > > It appears that all callers of vm_unmapped_area() are using the page aligned > check to determine error. I would prefer to do the same, and can add > comments to make that more clear. IS_ERR_VALUE() might be helpful?