From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763138AbdEWNJz (ORCPT ); Tue, 23 May 2017 09:09:55 -0400 Received: from mail-lf0-f53.google.com ([209.85.215.53]:36167 "EHLO mail-lf0-f53.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763086AbdEWNJu (ORCPT ); Tue, 23 May 2017 09:09:50 -0400 Date: Tue, 23 May 2017 16:09:47 +0300 From: "Kirill A. Shutemov" To: Punit Agrawal Cc: akpm@linux-foundation.org, Will Deacon , linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, catalin.marinas@arm.com, n-horiguchi@ah.jp.nec.com, kirill.shutemov@linux.intel.com, mike.kravetz@oracle.com, steve.capper@arm.com, mark.rutland@arm.com, hillf.zj@alibaba-inc.com, linux-arch@vger.kernel.org, aneesh.kumar@linux.vnet.ibm.com Subject: Re: [PATCH v3 1/6] mm, gup: Remove broken VM_BUG_ON_PAGE compound check for hugepages Message-ID: <20170523130947.cv3bbjxa2l4ifj55@node.shutemov.name> References: <20170522133604.11392-1-punit.agrawal@arm.com> <20170522133604.11392-2-punit.agrawal@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170522133604.11392-2-punit.agrawal@arm.com> User-Agent: NeoMutt/20170428 (1.8.2) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, May 22, 2017 at 02:35:59PM +0100, Punit Agrawal wrote: > From: Will Deacon > > When operating on hugepages with DEBUG_VM enabled, the GUP code checks the > compound head for each tail page prior to calling page_cache_add_speculative. > This is broken, because on the fast-GUP path (where we don't hold any page > table locks) we can be racing with a concurrent invocation of > split_huge_page_to_list. > > split_huge_page_to_list deals with this race by using page_ref_freeze to > freeze the page and force concurrent GUPs to fail whilst the component > pages are modified. This modification includes clearing the compound_head > field for the tail pages, so checking this prior to a successful call > to page_cache_add_speculative can lead to false positives: In fact, > page_cache_add_speculative *already* has this check once the page refcount > has been successfully updated, so we can simply remove the broken calls > to VM_BUG_ON_PAGE. > > Cc: "Kirill A. Shutemov" > Cc: Aneesh Kumar K.V > Signed-off-by: Will Deacon > Acked-by: Steve Capper > Signed-off-by: Punit Agrawal Looks reasonable to me: Acked-by: Kirill A. Shutemov -- Kirill A. Shutemov From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Kirill A. Shutemov" Subject: Re: [PATCH v3 1/6] mm, gup: Remove broken VM_BUG_ON_PAGE compound check for hugepages Date: Tue, 23 May 2017 16:09:47 +0300 Message-ID: <20170523130947.cv3bbjxa2l4ifj55@node.shutemov.name> References: <20170522133604.11392-1-punit.agrawal@arm.com> <20170522133604.11392-2-punit.agrawal@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20170522133604.11392-2-punit.agrawal@arm.com> Sender: owner-linux-mm@kvack.org To: Punit Agrawal Cc: akpm@linux-foundation.org, Will Deacon , linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, catalin.marinas@arm.com, n-horiguchi@ah.jp.nec.com, kirill.shutemov@linux.intel.com, mike.kravetz@oracle.com, steve.capper@arm.com, mark.rutland@arm.com, hillf.zj@alibaba-inc.com, linux-arch@vger.kernel.org, aneesh.kumar@linux.vnet.ibm.com List-Id: linux-arch.vger.kernel.org On Mon, May 22, 2017 at 02:35:59PM +0100, Punit Agrawal wrote: > From: Will Deacon > > When operating on hugepages with DEBUG_VM enabled, the GUP code checks the > compound head for each tail page prior to calling page_cache_add_speculative. > This is broken, because on the fast-GUP path (where we don't hold any page > table locks) we can be racing with a concurrent invocation of > split_huge_page_to_list. > > split_huge_page_to_list deals with this race by using page_ref_freeze to > freeze the page and force concurrent GUPs to fail whilst the component > pages are modified. This modification includes clearing the compound_head > field for the tail pages, so checking this prior to a successful call > to page_cache_add_speculative can lead to false positives: In fact, > page_cache_add_speculative *already* has this check once the page refcount > has been successfully updated, so we can simply remove the broken calls > to VM_BUG_ON_PAGE. > > Cc: "Kirill A. Shutemov" > Cc: Aneesh Kumar K.V > Signed-off-by: Will Deacon > Acked-by: Steve Capper > Signed-off-by: Punit Agrawal Looks reasonable to me: Acked-by: Kirill A. Shutemov -- Kirill A. Shutemov -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 From: kirill@shutemov.name (Kirill A. Shutemov) Date: Tue, 23 May 2017 16:09:47 +0300 Subject: [PATCH v3 1/6] mm, gup: Remove broken VM_BUG_ON_PAGE compound check for hugepages In-Reply-To: <20170522133604.11392-2-punit.agrawal@arm.com> References: <20170522133604.11392-1-punit.agrawal@arm.com> <20170522133604.11392-2-punit.agrawal@arm.com> Message-ID: <20170523130947.cv3bbjxa2l4ifj55@node.shutemov.name> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Mon, May 22, 2017 at 02:35:59PM +0100, Punit Agrawal wrote: > From: Will Deacon > > When operating on hugepages with DEBUG_VM enabled, the GUP code checks the > compound head for each tail page prior to calling page_cache_add_speculative. > This is broken, because on the fast-GUP path (where we don't hold any page > table locks) we can be racing with a concurrent invocation of > split_huge_page_to_list. > > split_huge_page_to_list deals with this race by using page_ref_freeze to > freeze the page and force concurrent GUPs to fail whilst the component > pages are modified. This modification includes clearing the compound_head > field for the tail pages, so checking this prior to a successful call > to page_cache_add_speculative can lead to false positives: In fact, > page_cache_add_speculative *already* has this check once the page refcount > has been successfully updated, so we can simply remove the broken calls > to VM_BUG_ON_PAGE. > > Cc: "Kirill A. Shutemov" > Cc: Aneesh Kumar K.V > Signed-off-by: Will Deacon > Acked-by: Steve Capper > Signed-off-by: Punit Agrawal Looks reasonable to me: Acked-by: Kirill A. Shutemov -- Kirill A. Shutemov