linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: alex.shi@linaro.org (Alex Shi)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 27/29] arm64: Force KPTI to be disabled on Cavium ThunderX
Date: Wed, 28 Feb 2018 11:56:49 +0800	[thread overview]
Message-ID: <1519790211-16582-28-git-send-email-alex.shi@linaro.org> (raw)
In-Reply-To: <1519790211-16582-1-git-send-email-alex.shi@linaro.org>

From: Marc Zyngier <marc.zyngier@arm.com>

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 <marc.zyngier@arm.com>
[will: Update comment]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	using old function read_system_reg/cpus_have_cap to replace
	read_sanitised_ftr_reg/cpus_have_const_cap in
	arch/arm64/kernel/cpufeature.c
---
 arch/arm64/kernel/cpufeature.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0fba610..760c851 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -753,12 +753,23 @@ static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 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;
 	}
 
-- 
2.7.4

  parent reply	other threads:[~2018-02-28  3:56 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-28  3:56 [PATCH 0/29] arm meltdown fix backporting review for lts 4.9 Alex Shi
2018-02-28  3:56 ` [PATCH 01/29] arm64: mm: Use non-global mappings for kernel space Alex Shi
2018-02-28 12:08   ` Greg KH
2018-03-01 11:53     ` Alex Shi
2018-02-28  3:56 ` [PATCH 02/29] arm64: mm: Move ASID from TTBR0 to TTBR1 Alex Shi
2018-02-28  3:56 ` [PATCH 03/29] arm64: mm: Allocate ASIDs in pairs Alex Shi
2018-02-28  3:56 ` [PATCH 04/29] arm64: mm: Add arm64_kernel_unmapped_at_el0 helper Alex Shi
2018-02-28  3:56 ` [PATCH 05/29] arm64: mm: Invalidate both kernel and user ASIDs when performing TLBI Alex Shi
2018-02-28  3:56 ` [PATCH 06/29] arm64: factor out entry stack manipulation Alex Shi
2018-02-28  3:56 ` [PATCH 07/29] arm64: entry.S: move SError handling into a C function for future expansion Alex Shi
2018-02-28  3:56 ` [PATCH 08/29] module: extend 'rodata=off' boot cmdline parameter to module mappings Alex Shi
2018-02-28  3:56 ` [PATCH 09/29] arm64: entry: Add exception trampoline page for exceptions from EL0 Alex Shi
2018-02-28  3:56 ` [PATCH 10/29] arm64: mm: Map entry trampoline into trampoline and kernel page tables Alex Shi
2018-02-28  3:56 ` [PATCH 11/29] arm64: entry: Explicitly pass exception level to kernel_ventry macro Alex Shi
2018-02-28  3:56 ` [PATCH 12/29] arm64: entry: Hook up entry trampoline to exception vectors Alex Shi
2018-02-28  3:56 ` [PATCH 13/29] arm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks Alex Shi
2018-02-28  3:56 ` [PATCH 14/29] arm64: entry: Add fake CPU feature for unmapping the kernel at EL0 Alex Shi
2018-02-28  3:56 ` [PATCH 15/29] arm64: kaslr: Put kernel vectors address in separate data page Alex Shi
2018-02-28  3:56 ` [PATCH 16/29] arm64: use RET instruction for exiting the trampoline Alex Shi
2018-02-28  3:56 ` [PATCH 17/29] arm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0 Alex Shi
2018-02-28  3:56 ` [PATCH 18/29] arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry Alex Shi
2018-02-28  3:56 ` [PATCH 19/29] arm64: Take into account ID_AA64PFR0_EL1.CSV3 Alex Shi
2018-02-28  3:56 ` [PATCH 20/29] arm64: Allow checking of a CPU-local erratum Alex Shi
2018-02-28  3:56 ` [PATCH 21/29] arm64: capabilities: Handle duplicate entries for a capability Alex Shi
2018-02-28  3:56 ` [PATCH 22/29] arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75 Alex Shi
2018-02-28  3:56 ` [PATCH 23/29] arm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs Alex Shi
2018-02-28  3:56 ` [PATCH 24/29] arm64: Turn on KPTI only on CPUs that need it Alex Shi
2018-02-28  3:56 ` [PATCH 25/29] arm64: kpti: Make use of nG dependent on arm64_kernel_unmapped_at_el0() Alex Shi
2018-02-28  3:56 ` [PATCH 26/29] arm64: kpti: Add ->enable callback to remap swapper using nG mappings Alex Shi
2018-02-28  3:56 ` Alex Shi [this message]
2018-02-28  3:56 ` [PATCH 28/29] arm64: entry: Reword comment about post_ttbr_update_workaround Alex Shi
2018-02-28  3:56 ` [PATCH 29/29] arm64: idmap: Use "awx" flags for .idmap.text .pushsection directives Alex Shi
2018-02-28  4:02 ` [PATCH 0/29] arm meltdown fix backporting review for lts 4.9 Alex Shi
2018-03-01 15:24 ` Greg KH
2018-03-02  9:14   ` Alex Shi
2018-03-02 10:32     ` Marc Zyngier
2018-03-02 16:54     ` Greg KH
2018-03-05 12:46       ` Mark Brown
2018-03-05 13:08         ` Greg KH
2018-03-06 14:26           ` Mark Brown
2018-03-06 17:25             ` Greg KH
2018-03-06 21:31               ` Mark Brown
2018-03-13 10:03                 ` Greg KH
2018-03-07  4:43               ` Alex Shi
2018-03-07  3:27           ` Alex Shi
2018-03-07 18:24       ` Ard Biesheuvel
2018-03-13 10:04         ` Greg KH
2018-03-13 10:13           ` Ard Biesheuvel
2018-03-13 10:38             ` Greg KH
2018-03-13 13:01               ` Ard Biesheuvel
2018-03-13 13:25                 ` Greg KH

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1519790211-16582-28-git-send-email-alex.shi@linaro.org \
    --to=alex.shi@linaro.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).