From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org ([140.211.169.12]:32884 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932231AbeDFNhe (ORCPT ); Fri, 6 Apr 2018 09:37:34 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org, stable@vger.kernel.org Cc: Greg Kroah-Hartman , Marc Zyngier , Will Deacon , Catalin Marinas , Greg Hackmann , Alex Shi , Mark Rutland Subject: [PATCH 4.9 074/102] arm64: Force KPTI to be disabled on Cavium ThunderX Date: Fri, 6 Apr 2018 15:23:55 +0200 Message-Id: <20180406084341.914967207@linuxfoundation.org> In-Reply-To: <20180406084331.507038179@linuxfoundation.org> References: <20180406084331.507038179@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: stable-owner@vger.kernel.org List-ID: 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Marc Zyngier commit 6dc52b15c4a4 upstream. Cavium ThunderX's erratum 27456 results in a corruption of icache entries that are loaded from memory that is mapped as non-global (i.e. ASID-tagged). As KPTI is based on memory being mapped non-global, let's prevent it from kicking in if this erratum is detected. Signed-off-by: Marc Zyngier [will: Update comment] Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas [Alex: use cpus_have_cap as cpus_have_const_cap doesn't exist in v4.9] Signed-off-by: Alex Shi [v4.9 backport] Signed-off-by: Mark Rutland [v4.9 backport] Tested-by: Will Deacon Tested-by: Greg Hackmann Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/cpufeature.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -753,12 +753,23 @@ static int __kpti_forced; /* 0: not forc static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, int __unused) { + char const *str = "command line option"; u64 pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1); - /* Forced on command line? */ + /* + * For reasons that aren't entirely clear, enabling KPTI on Cavium + * ThunderX leads to apparent I-cache corruption of kernel text, which + * ends as well as you might imagine. Don't even try. + */ + if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_27456)) { + str = "ARM64_WORKAROUND_CAVIUM_27456"; + __kpti_forced = -1; + } + + /* Forced? */ if (__kpti_forced) { - pr_info_once("kernel page table isolation forced %s by command line option\n", - __kpti_forced > 0 ? "ON" : "OFF"); + pr_info_once("kernel page table isolation forced %s by %s\n", + __kpti_forced > 0 ? "ON" : "OFF", str); return __kpti_forced > 0; }