From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1948151AbcBRUYs (ORCPT ); Thu, 18 Feb 2016 15:24:48 -0500 Received: from terminus.zytor.com ([198.137.202.10]:47157 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1947059AbcBRUYp (ORCPT ); Thu, 18 Feb 2016 15:24:45 -0500 Date: Thu, 18 Feb 2016 12:23:19 -0800 From: tip-bot for Dave Hansen Message-ID: Cc: hpa@zytor.com, torvalds@linux-foundation.org, dave@sr71.net, dave.hansen@linux.intel.com, peterz@infradead.org, luto@amacapital.net, brgerst@gmail.com, bp@alien8.de, riel@redhat.com, mingo@kernel.org, akpm@linux-foundation.org, dvlasenk@redhat.com, linux-kernel@vger.kernel.org, tglx@linutronix.de Reply-To: tglx@linutronix.de, linux-kernel@vger.kernel.org, dvlasenk@redhat.com, akpm@linux-foundation.org, mingo@kernel.org, bp@alien8.de, riel@redhat.com, luto@amacapital.net, brgerst@gmail.com, peterz@infradead.org, dave.hansen@linux.intel.com, dave@sr71.net, hpa@zytor.com, torvalds@linux-foundation.org In-Reply-To: <20160212210222.EBB63D8C@viggo.jf.intel.com> References: <20160212210222.EBB63D8C@viggo.jf.intel.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:mm/pkeys] x86/mm/pkeys: Optimize fault handling in access_error() Git-Commit-ID: 07f146f53e8de826e4afa3a88ea65bdb13c24959 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 07f146f53e8de826e4afa3a88ea65bdb13c24959 Gitweb: http://git.kernel.org/tip/07f146f53e8de826e4afa3a88ea65bdb13c24959 Author: Dave Hansen AuthorDate: Fri, 12 Feb 2016 13:02:22 -0800 Committer: Ingo Molnar CommitDate: Thu, 18 Feb 2016 19:46:28 +0100 x86/mm/pkeys: Optimize fault handling in access_error() We might not strictly have to make modifictions to access_error() to check the VMA here. If we do not, we will do this: 1. app sets VMA pkey to K 2. app touches a !present page 3. do_page_fault(), allocates and maps page, sets pte.pkey=K 4. return to userspace 5. touch instruction reexecutes, but triggers PF_PK 6. do PKEY signal What happens with this patch applied: 1. app sets VMA pkey to K 2. app touches a !present page 3. do_page_fault() notices that K is inaccessible 4. do PKEY signal We basically skip the fault that does an allocation. So what this lets us do is protect areas from even being *populated* unless it is accessible according to protection keys. That seems handy to me and makes protection keys work more like an mprotect()'d mapping. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210222.EBB63D8C@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 319331a..68ecdff 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -900,10 +900,16 @@ bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { + /* This code is always called on the current mm */ + bool foreign = false; + if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; if (error_code & PF_PK) return true; + /* this checks permission keys on the VMA: */ + if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), foreign)) + return true; return false; } @@ -1091,6 +1097,8 @@ int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { + /* This is only called for the current mm, so: */ + bool foreign = false; /* * Access or read was blocked by protection keys. We do * this check before any others because we do not want @@ -1099,6 +1107,13 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) */ if (error_code & PF_PK) return 1; + /* + * Make sure to check the VMA so that we do not perform + * faults just to hit a PF_PK as soon as we fill in a + * page. + */ + if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), foreign)) + return 1; if (error_code & PF_WRITE) { /* write, present and write, not present: */