From patchwork Sat Jan 13 18:17:28 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dan Williams X-Patchwork-Id: 124424 Delivered-To: patch@linaro.org Received: by 10.46.64.148 with SMTP id r20csp183768lje; Sat, 13 Jan 2018 10:25:52 -0800 (PST) X-Google-Smtp-Source: ACJfBotrW2ynSmiet7UVPgDRpK4bXP+a8tplrmQdTrXK5gb8Y/5kEH3/pUcf9mQPotlcZqxYw9ur X-Received: by 10.159.246.5 with SMTP id b5mr30019871pls.208.1515867952307; Sat, 13 Jan 2018 10:25:52 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1515867952; cv=none; d=google.com; s=arc-20160816; b=RA2V7lsbyblwWDjSi35MiNSjK8yxqT49yDjGvoXYXXzl0ucy7RfZbPzmReHUef80AQ d9EFb3HWlrHwCqPVIufs9cxgQ2veU0ozX2JPH2d3do+aU2k3flY43I9Hm8WMW8NiSUj9 Or7EqDr0AbI8kIbFQsirX3RLf0JYt7ppjaOnYecpXyrt/52AAAdKYHlSOeo8uu/8V4D1 3Z/OJvJTEYTEXZzj0Vz+Fg6ZAK5QPlhX+N1P+BztHoaLsAszS2Ii9+VqfDtXgdOpUkXV SOOpbLPAEiEuRX41fJEsM2TetsWzlBQgnkkMmn7OshVU4laBGM9vPRHdRoJDHl/ACW// ldDQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:cc:to:from :subject:arc-authentication-results; bh=EAZY0HkeiG8K9SnKfC9v522m7/gHkQA/0dv079DtOdI=; b=qsuA3tQ2qL/yXn1QWRaLbeabSY79DTuNovOLdW57DkRw8dROb5yhFcOa4kV3OGy7kE QWqVtaK/zaJBihaa/NOTT7kpHjC79yBsCEC0lN56D8lvhQ72AmQw9zAF0M8D6BqlydD4 ShN+60qL3w78zGsjeydN49Vuf6FpNzDqQwaY2JNZKzlggavTDSolVBsVMosjkjxou2JA 4ruHS/Jshq0h/upcEmE7rxJASZ9vNBstUTiUbNBI9yCteksZA7g1NPBVzg3dsn5YO15C Zuov12dPo3iTmbHRR+NG4B7lqUKP3vjNL5KMPFX9Mvrwu48rrz/h2Wn2+Me6yQOrTgmQ zwzQ== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id c23si6589700pli.135.2018.01.13.10.25.51; Sat, 13 Jan 2018 10:25:52 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754289AbeAMSZs (ORCPT + 28 others); Sat, 13 Jan 2018 13:25:48 -0500 Received: from mga01.intel.com ([192.55.52.88]:18429 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751475AbeAMSZo (ORCPT ); Sat, 13 Jan 2018 13:25:44 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga007.fm.intel.com ([10.253.24.52]) by fmsmga101.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 13 Jan 2018 10:25:42 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.46,354,1511856000"; d="scan'208";a="9514797" Received: from dwillia2-desk3.jf.intel.com (HELO dwillia2-desk3.amr.corp.intel.com) ([10.54.39.16]) by fmsmga007.fm.intel.com with ESMTP; 13 Jan 2018 10:25:42 -0800 Subject: [PATCH v3 1/9] Documentation: document array_ptr From: Dan Williams To: linux-kernel@vger.kernel.org Cc: Mark Rutland , linux-arch@vger.kernel.org, kernel-hardening@lists.openwall.com, Peter Zijlstra , gregkh@linuxfoundation.org, Jonathan Corbet , Will Deacon , tglx@linutronix.de, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@linux.intel.com Date: Sat, 13 Jan 2018 10:17:28 -0800 Message-ID: <151586744826.5820.2041500357568068352.stgit@dwillia2-desk3.amr.corp.intel.com> In-Reply-To: <151586744180.5820.13215059696964205856.stgit@dwillia2-desk3.amr.corp.intel.com> References: <151586744180.5820.13215059696964205856.stgit@dwillia2-desk3.amr.corp.intel.com> User-Agent: StGit/0.17.1-9-g687f MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Mark Rutland Document the rationale and usage of the new array_ptr() helper. Signed-off-by: Mark Rutland Signed-off-by: Will Deacon Cc: Dan Williams Cc: Jonathan Corbet Cc: Peter Zijlstra Signed-off-by: Dan Williams --- Documentation/speculation.txt | 143 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 143 insertions(+) create mode 100644 Documentation/speculation.txt diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt new file mode 100644 index 000000000000..1e59d1d9eaf4 --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,143 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int idx) + { + if (idx >= MAX_ARRAY_ELEMS) + return 0; + else + return array[idx]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP , #MAX_ARRAY_ELEMS + B.LT less + MOV , #0 + RET + less: + LDR , [, ] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[idx], even if idx >= MAX_ARRAY_ELEMS. This value +will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may result +in sensitive information being leaked. Consider the following code, building +on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int idx) + { + int val1, val2, + + val1 = load_array(arr1, idx); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value of an +out-of-bounds address, while the second call will influence microarchitectural +state dependent on this value. This may provide an arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are respected +even under speculation. Architectures which are affected by speculation-based +side-channels are expected to implement these primitives. + +The array_ptr() helper in can be used to prevent +information from being leaked via side-channels. + +A call to array_ptr(arr, idx, sz) returns a sanitized pointer to +arr[idx] only if idx falls in the [0, sz) interval. When idx < 0 or idx > sz, +NULL is returned. Additionally, array_ptr() an out-of-bounds poitner is +not propagated to code which is speculatively executed. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int idx) + { + int *elem; + + elem = array_ptr(array, idx, MAX_ARRAY_ELEMS); + if (elem) + return *elem; + else + return 0; + } + +This can also be used in situations where multiple fields on a structure are +accessed: + + struct foo array[SIZE]; + int a, b; + + void do_thing(int idx) + { + struct foo *elem; + + elem = array_ptr(array, idx, SIZE); + if (elem) { + a = elem->field_a; + b = elem->field_b; + } + } + +It is imperative that the returned pointer is used. Pointers which are +generated separately are subject to a number of potential CPU and compiler +optimizations, and may still be used speculatively. For example, this means +that the following sequence is unsafe: + + struct foo array[SIZE]; + int a, b; + + void do_thing(int idx) + { + if (array_ptr(array, idx, SIZE) != NULL) { + // unsafe as wrong pointer is used + a = array[idx].field_a; + b = array[idx].field_b; + } + } + +Similarly, it is unsafe to compare the returned pointer with other pointers, +as this may permit the compiler to substitute one pointer with another, +permitting speculation. For example, the following sequence is unsafe: + + struct foo array[SIZE]; + int a, b; + + void do_thing(int idx) + { + struct foo *elem = array_ptr(array, idx, size); + + // unsafe due to pointer substitution + if (elem == &array[idx]) { + a = elem->field_a; + b = elem->field_b; + } + } +