Patch "arm64: Force KPTI to be disabled on Cavium ThunderX" has been added to the 4.9-stable tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This is a note to let you know that I've just added the patch titled

    arm64: Force KPTI to be disabled on Cavium ThunderX

to the 4.9-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     arm64-force-kpti-to-be-disabled-on-cavium-thunderx.patch
and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.


>From foo@baz Thu Apr  5 21:39:28 CEST 2018
From: Mark Rutland <mark.rutland@xxxxxxx>
Date: Tue,  3 Apr 2018 12:09:21 +0100
Subject: arm64: Force KPTI to be disabled on Cavium ThunderX
To: stable@xxxxxxxxxxxxxxx
Cc: mark.brown@xxxxxxxxxx, ard.biesheuvel@xxxxxxxxxx, marc.zyngier@xxxxxxx, will.deacon@xxxxxxx
Message-ID: <20180403110923.43575-26-mark.rutland@xxxxxxx>

From: Marc Zyngier <marc.zyngier@xxxxxxx>

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@xxxxxxx>
[will: Update comment]
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
[Alex: use cpus_have_cap as cpus_have_const_cap doesn't exist in v4.9]
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxx> [v4.9 backport]
Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx> [v4.9 backport]
Tested-by: Will Deacon <will.deacon@xxxxxxx>
Tested-by: Greg Hackmann <ghackmann@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 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;
 	}
 


Patches currently in stable-queue which might be from mark.rutland@xxxxxxx are

queue-4.9/arm64-mm-add-arm64_kernel_unmapped_at_el0-helper.patch
queue-4.9/arm64-entry-reword-comment-about-post_ttbr_update_workaround.patch
queue-4.9/arm64-kaslr-put-kernel-vectors-address-in-separate-data-page.patch
queue-4.9/arm64-turn-on-kpti-only-on-cpus-that-need-it.patch
queue-4.9/arm64-force-kpti-to-be-disabled-on-cavium-thunderx.patch
queue-4.9/arm64-mm-allocate-asids-in-pairs.patch
queue-4.9/arm64-tls-avoid-unconditional-zeroing-of-tpidrro_el0-for-native-tasks.patch
queue-4.9/arm64-use-ret-instruction-for-exiting-the-trampoline.patch
queue-4.9/arm64-entry-explicitly-pass-exception-level-to-kernel_ventry-macro.patch
queue-4.9/arm64-kpti-make-use-of-ng-dependent-on-arm64_kernel_unmapped_at_el0.patch
queue-4.9/arm64-mm-use-non-global-mappings-for-kernel-space.patch
queue-4.9/arm64-capabilities-handle-duplicate-entries-for-a-capability.patch
queue-4.9/arm64-entry-hook-up-entry-trampoline-to-exception-vectors.patch
queue-4.9/arm64-mm-invalidate-both-kernel-and-user-asids-when-performing-tlbi.patch
queue-4.9/arm64-mm-map-entry-trampoline-into-trampoline-and-kernel-page-tables.patch
queue-4.9/module-extend-rodata-off-boot-cmdline-parameter-to-module-mappings.patch
queue-4.9/arm64-kconfig-reword-unmap_kernel_at_el0-kconfig-entry.patch
queue-4.9/arm64-mm-move-asid-from-ttbr0-to-ttbr1.patch
queue-4.9/arm64-allow-checking-of-a-cpu-local-erratum.patch
queue-4.9/arm64-take-into-account-id_aa64pfr0_el1.csv3.patch
queue-4.9/arm64-kconfig-add-config_unmap_kernel_at_el0.patch
queue-4.9/arm64-idmap-use-awx-flags-for-.idmap.text-.pushsection-directives.patch
queue-4.9/arm64-factor-out-entry-stack-manipulation.patch
queue-4.9/arm64-entry-add-exception-trampoline-page-for-exceptions-from-el0.patch
queue-4.9/arm64-kpti-add-enable-callback-to-remap-swapper-using-ng-mappings.patch
queue-4.9/arm64-entry-add-fake-cpu-feature-for-unmapping-the-kernel-at-el0.patch
queue-4.9/arm64-cputype-add-midr-values-for-cavium-thunderx2-cpus.patch



[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]