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; + } + } + From patchwork Sat Jan 13 18:17:34 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dan Williams X-Patchwork-Id: 124425 Delivered-To: patch@linaro.org Received: by 10.46.64.148 with SMTP id r20csp183772lje; Sat, 13 Jan 2018 10:25:54 -0800 (PST) X-Google-Smtp-Source: ACJfBovTvU31NSWH8lHITKmStM5VyclKfUa1kPH+TXfZj+AWvqHiFA6IPLG8z6mb7oWnJIOtGWSG X-Received: by 10.84.131.74 with SMTP id 68mr4353372pld.276.1515867954209; Sat, 13 Jan 2018 10:25:54 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1515867954; cv=none; d=google.com; s=arc-20160816; b=mgRjQmBUNzSW1JiHcgUcRQbWx0Qi8oQvEihBIAHoQuM5qWJ0qwvW4br+NIXemP4sjz s9nZ8Lt2qtL8mBNMZadCTJDeGlwdVz1cczt9jXuaU4BE71wbCR2hrhdqyOLf1ez+99O1 ctYkbx6FpJvE178442I0foqWzT3BS6lgdy7MTCYbkr+ZalwQEWm71aoWKZUdbZjcmixi 02zdmqNQiq7KdpHZPDN2aT4pZ98F3s1zykraaqC4dwIvtr+4GFWcZfWOjhEZFLsgdi7U Yfg9tPi6mA3HHg6SjNHBgppCjre6YBrt5pv9Q3rDWtMQD6BVVun3ZuOkuK+4EcRbfKFE QkDA== 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=wFn1bJYf9vgHH8VwGPizYnG7j7lYqtvoZghpJo0jL9U=; b=twHBgn2IDG+5THRH8BGlw2sCBYUulDW4tT2k9bObULMIJ4/QPh5RJJmUsill/aqW5F VJOkKNSQz4G8juzLGrpTVkGQN0Cy7o6HwYi+nGKcoGG+uLGxIlms3A+BcbIik75rgEWP roSRmYcouO30tQk3eOMtIXPxLPeqlVVLj91V5K4ZFY6AdDVZ3FXhGHWlQNdBfZttGEhr nJK8MuQ8nQx++f25GpdHZkaaUnpIfxOyUS4VNysyAOAJflQeNz0btTvJbp3vaPHTPoSu Zn3eUgtGqCkknhKNmRnAwCZKHHsngRsbxh3DtPZ+DDzUoY6NiiJSjYEeDo9PQWlzl87B mvRg== 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.135.2018.01.13.10.25.53; Sat, 13 Jan 2018 10:25:54 -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 S1754455AbeAMSZw (ORCPT + 28 others); Sat, 13 Jan 2018 13:25:52 -0500 Received: from mga11.intel.com ([192.55.52.93]:26623 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751475AbeAMSZt (ORCPT ); Sat, 13 Jan 2018 13:25:49 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga102.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 13 Jan 2018 10:25:48 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.46,354,1511856000"; d="scan'208";a="19110113" Received: from dwillia2-desk3.jf.intel.com (HELO dwillia2-desk3.amr.corp.intel.com) ([10.54.39.16]) by FMSMGA003.fm.intel.com with ESMTP; 13 Jan 2018 10:25:48 -0800 Subject: [PATCH v3 2/9] arm64: implement ifence_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 , Catalin Marinas , Will Deacon , gregkh@linuxfoundation.org, tglx@linutronix.de, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@linux.intel.com Date: Sat, 13 Jan 2018 10:17:34 -0800 Message-ID: <151586745407.5820.16345523612044599487.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 This patch implements ifence_array_ptr() for arm64, using an LDR+CSEL+CSDB sequence to inhibit speculative use of the returned value. Signed-off-by: Mark Rutland Signed-off-by: Will Deacon Cc: Catalin Marinas Cc: Peter Zijlstra Signed-off-by: Dan Williams --- arch/arm64/include/asm/barrier.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 77651c49ef44..74ffcddb26e6 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -40,6 +40,30 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) +#define ifence_array_ptr(arr, idx, sz) \ +({ \ + typeof(&(arr)[0]) __nap_arr = (arr); \ + typeof(idx) __nap_idx = (idx); \ + typeof(sz) __nap_sz = (sz); \ + \ + unsigned long __nap_ptr = (unsigned long)__nap_arr + \ + sizeof(__nap_arr[0]) * idx; \ + \ + asm volatile( \ + " cmp %[i], %[s]\n" \ + " b.cs 1f\n" \ + " ldr %[p], %[pp]\n" \ + "1: csel %[p], %[p], xzr, cc\n" \ + " hint #0x14 // CSDB\n" \ + : [p] "=&r" (__nap_ptr) \ + : [pp] "m" (__nap_ptr), \ + [i] "r" ((unsigned long)__nap_idx), \ + [s] "r" ((unsigned long)__nap_sz) \ + : "cc"); \ + \ + (typeof(&(__nap_arr)[0]))__nap_ptr; \ +}) + #define __smp_mb() dmb(ish) #define __smp_rmb() dmb(ishld) #define __smp_wmb() dmb(ishst) From patchwork Sat Jan 13 18:17:40 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dan Williams X-Patchwork-Id: 124426 Delivered-To: patch@linaro.org Received: by 10.46.64.148 with SMTP id r20csp183795lje; Sat, 13 Jan 2018 10:26:02 -0800 (PST) X-Google-Smtp-Source: ACJfBot/idAIUbishx9YX0NZtuvqjmoPlIbyGMS/JZYhg7ivr71LtWgZ3jrM8xu4V4yZvbBNIKWh X-Received: by 10.159.230.16 with SMTP id u16mr15185107plq.401.1515867962462; Sat, 13 Jan 2018 10:26:02 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1515867962; cv=none; d=google.com; s=arc-20160816; b=KdYPazhvoDHX/eLaQNC1PbmZMLg99+WfGRtXSncTbBTbRyP+j+LK49ThJn23lkYVYU 2auVfBxU6ryMyfIxpJhMcrHb9APb5sazgQDbZsEBp3/Zy7qIYrWRC0ZcPp3Urtl1SFZa jUh9uo7HZY5oZEIqYxTpT6SbnkZBo2EmWAD88MPw2WeVccQA81rg5vZfhQyKd9s7jJn6 +JTYRafhGe3bu14D0ZTQ58DP3S8+nNIOw3zgJus50gKGzwOPD9te3M7A8LZm+qy0Fu0n l9A9KCXPGFhqAPG7F73NiB1a8f9+5yjZHDWCcFi3qA5T2IZQgGgV/XyYBvieCuKSWMhe wK7g== 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=7heKRSmbm1Mik3I27Nwqvw1y/PuUZqBJeKZO72FALwc=; b=kNwk1fMtGvYKnDk3S2R0OJqZC1OCf4hzziHVHlykmD/AkU1cEpNv47PZ1qWoDqwQ4c SZFhq89EQaV7zw866/1wOu//1oapqgWYe4UDnzoryxElR1pYGU+Kw6Nu2PVpZrhxrYHK /mR5QXjJa2Z+Axan0Tccnmq/X5hD4Yid24tyjABS5K8CYQyV59yJU1ilznv6QxlFKMz0 nGEyE0M0WsIyePKK3uwvFxkeqOfFsfIbLIy8cFRUxSe3VlT681uu5NfcZN9RqE9L69dB x7Um71Z5AuRbvlgL7s94yb2IG5LCprgtEPKeEnPH+ZLqLBNfnbO4OLfdKtBTAvPAj9wQ 2S3g== 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 r59si5226108plb.314.2018.01.13.10.26.02; Sat, 13 Jan 2018 10:26:02 -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 S1754862AbeAMSZ7 (ORCPT + 28 others); Sat, 13 Jan 2018 13:25:59 -0500 Received: from mga12.intel.com ([192.55.52.136]:52578 "EHLO mga12.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754485AbeAMSZz (ORCPT ); Sat, 13 Jan 2018 13:25:55 -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; 13 Jan 2018 10:25:54 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.46,354,1511856000"; d="scan'208";a="194788599" Received: from dwillia2-desk3.jf.intel.com (HELO dwillia2-desk3.amr.corp.intel.com) ([10.54.39.16]) by fmsmga005.fm.intel.com with ESMTP; 13 Jan 2018 10:25:54 -0800 Subject: [PATCH v3 3/9] arm: implement ifence_array_ptr() From: Dan Williams To: linux-kernel@vger.kernel.org Cc: Mark Rutland , linux-arch@vger.kernel.org, kernel-hardening@lists.openwall.com, gregkh@linuxfoundation.org, Russell King , tglx@linutronix.de, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@linux.intel.com Date: Sat, 13 Jan 2018 10:17:40 -0800 Message-ID: <151586745989.5820.17196364421122234994.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 This patch implements ifence_array_ptr() for arm, using an LDR+MOVCS+CSDB sequence to inhibit speculative use of the returned value. Cc: Russell King Signed-off-by: Mark Rutland Signed-off-by: Dan Williams --- arch/arm/include/asm/barrier.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index 40f5c410fd8c..919235ed6e68 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -59,6 +59,30 @@ extern void arm_heavy_mb(void); #define dma_wmb() barrier() #endif +#define ifence_array_ptr(arr, idx, sz) \ +({ \ + typeof(&(arr)[0]) __nap_arr = (arr); \ + typeof(idx) __nap_idx = (idx); \ + typeof(sz) __nap_sz = (sz); \ + \ + unsigned long __nap_ptr = (unsigned long)__nap_arr + \ + sizeof(__nap_arr[0]) * idx; \ + \ + asm volatile( \ + " cmp %[i], %[s]\n" \ + " bcs 1f\n" \ + " ldr %[p], %[pp]\n" \ + "1: movcs %[p], #0\n" \ + " .inst 0xe320f018 @ CSDB\n" \ + : [p] "=&r" (__nap_ptr) \ + : [pp] "m" (__nap_ptr), \ + [i] "r" ((unsigned long)__nap_idx), \ + [s] "r" ((unsigned long)__nap_sz) \ + : "cc"); \ + \ + (typeof(&(__nap_arr)[0]))__nap_ptr; \ +}) + #define __smp_mb() dmb(ish) #define __smp_rmb() __smp_mb() #define __smp_wmb() dmb(ishst)