Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756886AbeAINEu (ORCPT + 1 other); Tue, 9 Jan 2018 08:04:50 -0500 Received: from wtarreau.pck.nerim.net ([62.212.114.60]:39152 "EHLO 1wt.eu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751165AbeAINEt (ORCPT ); Tue, 9 Jan 2018 08:04:49 -0500 From: Willy Tarreau To: linux-kernel@vger.kernel.org, x86@kernel.org Cc: Willy Tarreau , Andy Lutomirski , Borislav Petkov , Brian Gerst , Dave Hansen , Ingo Molnar , Linus Torvalds , Peter Zijlstra , Thomas Gleixner , Josh Poimboeuf , "H. Peter Anvin" , Greg Kroah-Hartman , Kees Cook Subject: [RFC PATCH v2 6/6] x86/entry/pti: don't switch PGD on when pti_disable is set Date: Tue, 9 Jan 2018 13:56:20 +0100 Message-Id: <1515502580-12261-7-git-send-email-w@1wt.eu> X-Mailer: git-send-email 2.8.0.rc2.1.gbe9624a In-Reply-To: <1515502580-12261-1-git-send-email-w@1wt.eu> References: <1515502580-12261-1-git-send-email-w@1wt.eu> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: When a syscall returns to userspace with pti_disable set, it means the current mm is configured to disable page table isolation (PTI). In this case, returns from kernel to user will not switch the CR3, leaving it to the kernel one which already maps both user and kernel pages. This avoids a TLB flush, and saves another one on next entry. Thanks to these changes, haproxy running under KVM went back from 12700 conn/s (without PCID) or 19700 (with PCID) to 23100 once loaded after calling prctl(), indicating that PTI has no measurable impact on this workload. Signed-off-by: Willy Tarreau Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Ingo Molnar Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Josh Poimboeuf Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: Kees Cook v2: - use pti_disable instead of task flag --- arch/x86/entry/calling.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 2c0d3b5..5361a10 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -229,6 +229,11 @@ .macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + + /* The "pti_disable" mm attribute is mirrored into this per-cpu var */ + cmpb $0, PER_CPU_VAR(pti_disable) + jne .Lend_\@ + mov %cr3, \scratch_reg ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID -- 1.7.12.1