From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759561AbbCDG0A (ORCPT ); Wed, 4 Mar 2015 01:26:00 -0500 Received: from mail-wg0-f50.google.com ([74.125.82.50]:34120 "EHLO mail-wg0-f50.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759016AbbCDGZ5 (ORCPT ); Wed, 4 Mar 2015 01:25:57 -0500 Date: Wed, 4 Mar 2015 07:25:52 +0100 From: Ingo Molnar To: Borislav Petkov Cc: X86 ML , Andy Lutomirski , LKML , Linus Torvalds Subject: Re: [PATCH v2 07/15] x86/lib/copy_user_64.S: Convert to ALTERNATIVE_2 Message-ID: <20150304062552.GA16111@gmail.com> References: <1424776497-3180-1-git-send-email-bp@alien8.de> <1424776497-3180-8-git-send-email-bp@alien8.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1424776497-3180-8-git-send-email-bp@alien8.de> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Borislav Petkov wrote: > From: Borislav Petkov > > Use the asm macro and drop the locally grown version. > @@ -73,9 +49,11 @@ ENTRY(_copy_to_user) > jc bad_to_user > cmpq TI_addr_limit(%rax),%rcx > ja bad_to_user > + ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \ > + "jmp copy_user_generic_string", \ > + X86_FEATURE_REP_GOOD, \ > + "jmp copy_user_enhanced_fast_string", \ > + X86_FEATURE_ERMS Btw., as a future optimization, wouldn't it be useful to patch this function at its first instruction, i.e. to have three fully functional copy_user_generic_ variants and choose to jmp to one of them in the first instruction of the original function? The advantage would be two-fold: 1) right now: smart microarchitectures that are able to optimize jump-after-jump (and jump-after-call) targets in their branch target cache can do so in this case, reducing the overhead of the patching, possibly close to zero in the cached case. 2) in the future: we could actually do a (limited) re-link of the kernel during bootup, and patch up the original copy_to_user call sites directly to one of the three variants. Alternatives patching done at the symbol level. Does current tooling allow something like this already? Thanks, Ingo