From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id C51D3C0044C for ; Wed, 7 Nov 2018 23:15:19 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 72EAD2086C for ; Wed, 7 Nov 2018 23:15:19 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 72EAD2086C Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727963AbeKHIry (ORCPT ); Thu, 8 Nov 2018 03:47:54 -0500 Received: from mga12.intel.com ([192.55.52.136]:19827 "EHLO mga12.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727068AbeKHIry (ORCPT ); Thu, 8 Nov 2018 03:47:54 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 07 Nov 2018 15:15:13 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,477,1534834800"; d="scan'208";a="277994037" Received: from schen9-desk.jf.intel.com (HELO [10.54.74.144]) ([10.54.74.144]) by fmsmga005.fm.intel.com with ESMTP; 07 Nov 2018 15:15:13 -0800 Subject: Re: [Patch v4 17/18] x86/speculation: Update SPEC_CTRL MSRs of remote CPUs To: Waiman Long , Thomas Gleixner Cc: Jiri Kosina , Tom Lendacky , Ingo Molnar , Peter Zijlstra , Josh Poimboeuf , Andrea Arcangeli , David Woodhouse , Andi Kleen , Dave Hansen , Casey Schaufler , Asit Mallick , Arjan van de Ven , Jon Masters , LKML , x86@kernel.org, Kees Cook References: <81398b26-e1c3-aac3-b44a-2a0982ae74e0@linux.intel.com> From: Tim Chen Openpgp: preference=signencrypt Autocrypt: addr=tim.c.chen@linux.intel.com; prefer-encrypt=mutual; keydata= xsFNBE6ONugBEAC1c8laQ2QrezbYFetwrzD0v8rOqanj5X1jkySQr3hm/rqVcDJudcfdSMv0 BNCCjt2dofFxVfRL0G8eQR4qoSgzDGDzoFva3NjTJ/34TlK9MMouLY7X5x3sXdZtrV4zhKGv 3Rt2osfARdH3QDoTUHujhQxlcPk7cwjTXe4o3aHIFbcIBUmxhqPaz3AMfdCqbhd7uWe9MAZX 7M9vk6PboyO4PgZRAs5lWRoD4ZfROtSViX49KEkO7BDClacVsODITpiaWtZVDxkYUX/D9OxG AkxmqrCxZxxZHDQos1SnS08aKD0QITm/LWQtwx1y0P4GGMXRlIAQE4rK69BDvzSaLB45ppOw AO7kw8aR3eu/sW8p016dx34bUFFTwbILJFvazpvRImdjmZGcTcvRd8QgmhNV5INyGwtfA8sn L4V13aZNZA9eWd+iuB8qZfoFiyAeHNWzLX/Moi8hB7LxFuEGnvbxYByRS83jsxjH2Bd49bTi XOsAY/YyGj6gl8KkjSbKOkj0IRy28nLisFdGBvgeQrvaLaA06VexptmrLjp1Qtyesw6zIJeP oHUImJltjPjFvyfkuIPfVIB87kukpB78bhSRA5mC365LsLRl+nrX7SauEo8b7MX0qbW9pg0f wsiyCCK0ioTTm4IWL2wiDB7PeiJSsViBORNKoxA093B42BWFJQARAQABzTRUaW0gQ2hlbiAo d29yayByZWxhdGVkKSA8dGltLmMuY2hlbkBsaW51eC5pbnRlbC5jb20+wsF+BBMBAgAoAhsD BgsJCAcDAgYVCAIJCgsEFgIDAQIeAQIXgAUCWfPBPgUJDyfxUQAKCRCiZ7WKota4SReFEACa 5ruzJM/hXJguHJY8i95rxHfLOgE7QoDgsR2aK2C1BSu84StTcT9BMikndQ0em28mpd1zROCs FvJ8Dzpp923699FU7s70+bFG9zIWtAOLWt2QyIMYImILzKkzkyLZo2RTcLNdUWS5fkAtjspQ QPg29W+kcbX1NhB6WDdbvk2HNeZoDh4A5ucOzKjEPqbSFIbw2Wt3RUmXxezjH1NzZG3fMkEN cT7JezYhUxvi2PrJlD+mo26q2/PQmFgF49tneRJXmYyie5o2+ClfFVO9I6Rd1k7hS9uXQLg3 udpnDKobNYZ7/+O5+ucp0Y/MwzTfBYmtJ5fBjUTi2L1RMDJee8WqCNY1VU6cQ8MD4KstxUp2 bxlSRAYaDtNa1Omr61E7BA1Cc2E3cIt/O1mMfudWUjCND8qrAtEnugqKjk5tJJZzmzIKSHPY dCiJtOBQaVAYYchXF2hwOKhpFS43V4FdWLlM1CnFXsmbk48hGbiA8XHU85JBCXmG0i4qUlKn x2ilChvq4A102ahnlGbEmFaSwxuqR/5lhai6lOkwHXDFUT6jblaSs24L3MTn/vXtvwaLEEKh SPzNaj7yFvEhrJoLiZmDm0SZuPbQ+wrmPWUbzyf5te2Oq0JyrHTQJoQqn+CwGqwF/JaUq60f VuUD3T0icgsfljsOA4apyH7kyfxXGP0hOM7BTQROjjboARAAx+LxKhznLH0RFvuBEGTcntrC 3S0tpYmVsuWbdWr2ZL9VqZmXh6UWb0K7w7OpPNW1FiaWtVLnG1nuMmBJhE5jpYsi+yU8sbMA 5BEiQn2hUo0k5eww5/oiyNI9H7vql9h628JhYd9T1CcDMghTNOKfCPNGzQ8Js33cFnszqL4I N9jh+qdg5FnMHs/+oBNtlvNjD1dQdM6gm8WLhFttXNPn7nRUPuLQxTqbuoPgoTmxUxR3/M5A KDjntKEdYZziBYfQJkvfLJdnRZnuHvXhO2EU1/7bAhdz7nULZktw9j1Sp9zRYfKRnQdIvXXa jHkOn3N41n0zjoKV1J1KpAH3UcVfOmnTj+u6iVMW5dkxLo07CddJDaayXtCBSmmd90OG0Odx cq9VaIu/DOQJ8OZU3JORiuuq40jlFsF1fy7nZSvQFsJlSmHkb+cDMZDc1yk0ko65girmNjMF hsAdVYfVsqS1TJrnengBgbPgesYO5eY0Tm3+0pa07EkONsxnzyWJDn4fh/eA6IEUo2JrOrex O6cRBNv9dwrUfJbMgzFeKdoyq/Zwe9QmdStkFpoh9036iWsj6Nt58NhXP8WDHOfBg9o86z9O VMZMC2Q0r6pGm7L0yHmPiixrxWdW0dGKvTHu/DH/ORUrjBYYeMsCc4jWoUt4Xq49LX98KDGN dhkZDGwKnAUAEQEAAcLBZQQYAQIADwIbDAUCVEAL2AUJC1VvawAKCRCiZ7WKota4SWWrD/9L 4H3kHUR9qPTfSpwFBV0+PspkpMQmRQ9cQauIRXL+qIqCYfx48Jz/WZkq47COhY4d1tAvX4qv lviIoCwShAHhVkxD2rWFpa6Yang7cyPDjS6sNChsZ9aTAP0zX4LLHN8ub5LwCcU9JA4Avwdy NDSeeSeqNq9QOvVd2bDmyHxgVv4zRgLTNPH28hXAnDODy0wCJWg53PWvlp35XfWdIsC0ZAPK vgA1Bh+FYYKfT8Uzj8J/SYH+chmeYMt+8Y+FZa+NybivWJg6+UaJ2fCTuKCc7TgqLneBudox izWQMnBso0tHOT6+ju+L+ewPWc0OrJdKJeadrE2T1E949vMup5jG0lJLeSpBNmELODNL0xz6 Erjs/pwX7cYGKUbJfBaQcC9frPfpWfSqnK5X+12HFDxAxquXKC4ejBJOhbo3xx0sziiPTC3m 4LvLkEa9evQNtMvRcnWY5qIC4YdT5waC0stYNpyCiBXpYArKYCmlra3xpgAe0MRL94PHU4UW yxxdxRubFYna9LeNcWL7C0w2ngg1jd0tjRjLnimrOL8rSVUzwjNSQOV37tWTueTr40M/SfjU B6bifflZQpeSY8IpqzKqB0vvxo2xD0rU7JqUh7rW8U6rg2JEzVgYiHS4cf/vJMHuauHAjH7a ys7DYlLhlOVo3o0jOor4xuZPrWbSp4w51sLBZQQYAQIADwIbDAUCWfPBJQUJDyfxOAAKCRCi Z7WKota4SZKQD/wLu3j8kgATic+wF3ekngjwPcW3JhbQJeHxUZwsb9OgVMHumlrZHGoltKQu FfAhG/sOfuAh5f7QMzzA1M+2JD1Q6lr74vUHNBu+xBFMgZstE6hpkKmn0pNZ5JS3iZRVRLBx dWw63DYr0GM80vmbHjAhwxoF2PsO2/PkWTc68+pFyl3Dy0heZSJii81hkzh8FnF8CaMH0VXu MJoWyuYgnC058hHj0QqXvlNx9LzMtmrsskTmPvwqXTgG/dTEfTkQ4RfX3enrBy55cg9tMc88 BEQ/0/JV1bCDwyWXKRpz6FsHbICGQ4G9TTD4pS5QJ+oRQccMjfiDM3rFTcG1RYP2lHXjSm9c 0VnimpQBz3LarrdHJilmTHbAWf5KLmtWfYXHrlncnhnCtw2nfwBBdy8cQW4tUyniSVRLOwGm eJziyuPJ5SVVZcil2oN5/o7js7BYAeAV/WVF2Sk/blnXaaObIYIVqnDhV4N0oUz1KXq1Leem Uvjo5rljmmhOBdgl6D0scXCWICbuuWN9eW2fZl38hBSI3M0MX0jnV2e+0FY+76iNmKadpTDw gY3OaQAZ/UlJVI+pRV4JtRrajtpo9Vb38SBPXwp9moWmwVQyIdFUXjCTQARvxjRsUoPVu9oA SCd9W74oOgrqC1hadvVU867d07PlWksfYwCeYP4bs+4GSLzI1w== Message-ID: <2aff26cb-e85e-29c5-cc85-eb12480f03fc@linux.intel.com> Date: Wed, 7 Nov 2018 15:15:12 -0800 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.1.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 11/07/2018 10:33 AM, Waiman Long wrote: > On 11/06/2018 07:18 PM, Tim Chen wrote: >> Thomas, >> >>>>> 2) Add _TIF_UPDATE_SPEC_CTRL to the SYSCALL_EXIT_WORK_FLAGS and handle it >>>>> in the slow work path. >>>> There can be tasks that don't do any syscalls, and it seems like we can >>>> have MSRs getting out of sync? >>> Setting the TIF flag directly in a remote task is wrong. It needs to be >>> handled when the _TIF_UPDATE_SPEC_CTRL is evaluated, i.e. the information >>> needs to be stored process wide e.g. in task->mm. >>> >>> But yes, if the remote task runs in user space forever, it won't >>> help. Though the point is that dumpable is usually set when the process >>> starts, so it's probably mostly a theoretical issue. >>> >> I took a crack to implement what you suggested to update >> remote task's flag and remote SPEC_CTRL MSR on the syscall exit slow path. >> >> This looks reasobale? >> >> Tim >> >> >> ------------ >> >> diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c >> index 3b2490b..614594a 100644 >> --- a/arch/x86/entry/common.c >> +++ b/arch/x86/entry/common.c >> @@ -216,7 +216,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) >> >> #define SYSCALL_EXIT_WORK_FLAGS \ >> (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ >> - _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) >> + _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | _TIF_UPDATE_SPEC_CTRL) >> >> static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) >> { >> @@ -227,6 +227,8 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) >> if (cached_flags & _TIF_SYSCALL_TRACEPOINT) >> trace_sys_exit(regs, regs->ax); >> >> + if (cached_flags & _TIF_UPDATE_SPEC_CTRL) >> + spec_ctrl_do_pending_update(); >> /* >> * If TIF_SYSCALL_EMU is set, we only get here because of >> * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). >> diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h >> index c59a6c4..f124597 100644 >> --- a/arch/x86/include/asm/nospec-branch.h >> +++ b/arch/x86/include/asm/nospec-branch.h >> @@ -276,6 +276,8 @@ static inline void indirect_branch_prediction_barrier(void) >> alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); >> } >> >> +void spec_ctrl_do_pending_update(void); >> + >> /* The Intel SPEC CTRL MSR base value cache */ >> extern u64 x86_spec_ctrl_base; >> >> diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h >> index 4f6a7a9..b78db59 100644 >> --- a/arch/x86/include/asm/thread_info.h >> +++ b/arch/x86/include/asm/thread_info.h >> @@ -97,6 +97,7 @@ struct thread_info { >> #define TIF_USER_RETURN_NOTIFY 14 /* Notify kernel of userspace return */ >> #define TIF_PATCH_PENDING 15 /* Pending live patching update */ >> #define TIF_FSCHECK 16 /* Check FS is USER_DS on return */ >> +#define TIF_UPDATE_SPEC_CTRL 17 /* Pending update of speculation control */ >> >> /* Task status */ >> #define TIF_UPROBE 18 /* Breakpointed or singlestepping */ >> @@ -131,6 +132,7 @@ struct thread_info { >> #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) >> #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) >> #define _TIF_FSCHECK (1 << TIF_FSCHECK) >> +#define _TIF_UPDATE_SPEC_CTRL (1 << TIF_UPDATE_SPEC_CTRL) >> >> #define _TIF_UPROBE (1 << TIF_UPROBE) >> #define _TIF_MEMDIE (1 << TIF_MEMDIE) >> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c >> index 4c15c86..d82d3f8 100644 >> --- a/arch/x86/kernel/cpu/bugs.c >> +++ b/arch/x86/kernel/cpu/bugs.c >> @@ -14,6 +14,8 @@ >> #include >> #include >> #include >> +#include >> +#include >> >> #include >> #include >> @@ -770,6 +772,69 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) >> return 0; >> } >> >> +static void set_task_stibp(struct task_struct *tsk, bool stibp_on) >> +{ >> + bool update = false; >> + >> + if (stibp_on) >> + update = !test_and_set_tsk_thread_flag(tsk, TIF_STIBP); >> + else >> + update = test_and_clear_tsk_thread_flag(tsk, TIF_STIBP); >> + >> + if (tsk == current && update) >> + speculation_ctrl_update_current(); >> +} >> + >> +void spec_ctrl_do_pending_update(void) >> +{ >> + if (!static_branch_unlikely(&spectre_v2_app_lite)) >> + return; >> + >> + if (!current->mm) >> + return; >> + >> + if (get_dumpable(current->mm) != SUID_DUMP_USER) >> + set_tsk_thread_flag(current, TIF_STIBP); >> + else >> + clear_tsk_thread_flag(current, TIF_STIBP); >> + >> + clear_tsk_thread_flag(current, TIF_UPDATE_SPEC_CTRL); >> + speculation_ctrl_update_current(); >> +} >> + >> +int arch_update_spec_ctrl_restriction(struct task_struct *task) >> +{ >> + unsigned long flags; >> + struct task_struct *t; >> + bool stibp_on = false; >> + >> + if (!static_branch_unlikely(&spectre_v2_app_lite)) >> + return 0; >> + >> + if (!task->mm) >> + return -EINVAL; >> + >> + if (!lock_task_sighand(task, &flags)) >> + return -ESRCH; >> + >> + if (get_dumpable(task->mm) != SUID_DUMP_USER) >> + stibp_on = true; >> + >> + for_each_thread(task, t) { >> + if (task_cpu(task) == smp_processor_id()) >> + set_task_stibp(task, stibp_on); > > I think "t" is the iterator, not "task". BTW, a thread is on the same > CPU doesn't mean it is running. Should you just check "(t == current)" here? Ah yes, should be t. t==current is checked in set_task_stibp. Tim > >> + else if (test_tsk_thread_flag(task, TIF_STIBP) != stibp_on) >> + set_tsk_thread_flag(task, TIF_UPDATE_SPEC_CTRL); >> + } >> + >> + unlock_task_sighand(task, &flags); >> + return 0; >> +} >> + >> int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, >> unsigned long ctrl) >> { > > Cheers, > Longman >