spectre-meltdown-checker/spectre-meltdown-checker.sh

4813 lines
172 KiB
Bash
Raw Normal View History

2018-01-07 15:00:59 +01:00
#! /bin/sh
# SPDX-License-Identifier: GPL-3.0-only
#
2018-01-07 15:00:59 +01:00
# Spectre & Meltdown checker
2018-01-09 09:21:42 +01:00
#
# Check for the latest version at:
# https://github.com/speed47/spectre-meltdown-checker
# git clone https://github.com/speed47/spectre-meltdown-checker.git
# or wget https://meltdown.ovh -O spectre-meltdown-checker.sh
# or curl -L https://meltdown.ovh -o spectre-meltdown-checker.sh
2018-01-09 09:21:42 +01:00
#
2018-01-07 16:22:30 +01:00
# Stephane Lesimple
2018-01-09 09:21:42 +01:00
#
2019-05-15 09:57:28 +02:00
VERSION='0.41'
2018-01-07 15:00:59 +01:00
trap 'exit_cleanup' EXIT
trap '_warn "interrupted, cleaning up..."; exit_cleanup; exit 1' INT
exit_cleanup()
{
# cleanup the temp decompressed config & kernel image
[ -n "$dumped_config" ] && [ -f "$dumped_config" ] && rm -f "$dumped_config"
[ -n "$kerneltmp" ] && [ -f "$kerneltmp" ] && rm -f "$kerneltmp"
[ -n "$kerneltmp2" ] && [ -f "$kerneltmp2" ] && rm -f "$kerneltmp2"
[ -n "$mcedb_tmp" ] && [ -f "$mcedb_tmp" ] && rm -f "$mcedb_tmp"
[ "$mounted_debugfs" = 1 ] && umount /sys/kernel/debug 2>/dev/null
[ "$mounted_procfs" = 1 ] && umount "$procfs" 2>/dev/null
[ "$insmod_cpuid" = 1 ] && rmmod cpuid 2>/dev/null
[ "$insmod_msr" = 1 ] && rmmod msr 2>/dev/null
[ "$kldload_cpuctl" = 1 ] && kldunload cpuctl 2>/dev/null
[ "$kldload_vmm" = 1 ] && kldunload vmm 2>/dev/null
}
# if we were git clone'd, adjust VERSION
2019-05-05 18:34:09 +02:00
if [ -d "$(dirname "$0")/.git" ] && command -v git >/dev/null 2>&1; then
describe=$(git -C "$(dirname "$0")" describe --tags --dirty 2>/dev/null)
[ -n "$describe" ] && VERSION=$(echo "$describe" | sed -e s/^v//)
fi
2018-01-08 20:50:42 +01:00
show_usage()
{
# shellcheck disable=SC2086
2018-01-08 20:50:42 +01:00
cat <<EOF
Usage:
Live mode: $(basename $0) [options] [--live]
Offline mode: $(basename $0) [options] [--kernel <kernel_file>] [--config <kernel_config>] [--map <kernel_map_file>]
2018-01-09 10:32:51 +01:00
Modes:
2018-01-08 20:50:42 +01:00
Two modes are available.
First mode is the "live" mode (default), it does its best to find information about the currently running kernel.
2018-01-12 11:46:36 +01:00
To run under this mode, just start the script without any option (you can also use --live explicitly)
2018-01-08 20:50:42 +01:00
Second mode is the "offline" mode, where you can inspect a non-running kernel.
You'll need to specify the location of the kernel file, config and System.map files:
2018-01-08 20:50:42 +01:00
2018-03-25 12:27:40 +02:00
--kernel kernel_file specify a (possibly compressed) Linux or BSD kernel file
--config kernel_config specify a kernel config file (Linux only)
--map kernel_map_file specify a kernel System.map file (Linux only)
2018-01-08 20:50:42 +01:00
2018-01-09 10:32:51 +01:00
Options:
2018-03-25 12:27:40 +02:00
--no-color don't use color codes
--verbose, -v increase verbosity level, possibly several times
--explain produce an additional human-readable explanation of actions to take to mitigate a vulnerability
--paranoid require IBPB to deem Variant 2 as mitigated
also require SMT disabled + unconditional L1D flush to deem Foreshadow-NG VMM as mitigated
also require SMT disabled to deem MDS vulnerabilities mitigated
2018-03-25 12:27:40 +02:00
--no-sysfs don't use the /sys interface even if present [Linux]
--sysfs-only only use the /sys interface, don't run our own checks [Linux]
--coreos special mode for CoreOS (use an ephemeral toolbox to inspect kernel) [Linux]
--arch-prefix PREFIX specify a prefix for cross-inspecting a kernel of a different arch, for example "aarch64-linux-gnu-",
so that invoked tools will be prefixed with this (i.e. aarch64-linux-gnu-objdump)
--batch text produce machine readable output, this is the default if --batch is specified alone
--batch short produce only one line with the vulnerabilities separated by spaces
2018-03-25 12:27:40 +02:00
--batch json produce JSON output formatted for Puppet, Ansible, Chef...
--batch nrpe produce machine readable output formatted for NRPE
--batch prometheus produce output for consumption by prometheus-node-exporter
--variant VARIANT specify which variant you'd like to check, by default all variants are checked
VARIANT can be one of 1, 2, 3, 3a, 4, l1tf, msbds, mfbds, mlpds, mdsum
2018-03-25 12:27:40 +02:00
can be specified multiple times (e.g. --variant 2 --variant 3)
--cve [cve1,cve2,...] specify which CVE you'd like to check, by default all supported CVEs are checked
--hw-only only check for CPU information, don't check for any variant
--no-hw skip CPU information and checks, if you're inspecting a kernel not to be run on this host
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
--vmm [auto,yes,no] override the detection of the presence of a hypervisor (for CVE-2018-3646), default: auto
--update-mcedb update our local copy of the CPU microcodes versions database (from the awesome MCExtractor project)
--update-builtin-mcedb same as --update-mcedb but update builtin DB inside the script itself
2018-01-09 10:32:51 +01:00
Return codes:
0 (not vulnerable), 2 (vulnerable), 3 (unknown), 255 (error)
2018-01-12 19:10:44 +01:00
2018-01-09 18:52:21 +01:00
IMPORTANT:
A false sense of security is worse than no security at all.
Please use the --disclaimer option to understand exactly what this script does.
EOF
}
show_disclaimer()
{
cat <<EOF
Disclaimer:
This tool does its best to determine whether your system is immune (or has proper mitigations in place) for the
collectively named "speculative execution" vulnerabilities. It doesn't attempt to run any kind of exploit, and can't guarantee
that your system is secure, but rather helps you verifying whether your system has the known correct mitigations in place.
However, some mitigations could also exist in your kernel that this script doesn't know (yet) how to detect, or it might
falsely detect mitigations that in the end don't work as expected (for example, on backported or modified kernels).
Your system exposure also depends on your CPU. As of now, AMD and ARM processors are marked as immune to some or all of these
vulnerabilities (except some specific ARM models). All Intel processors manufactured since circa 1995 are thought to be vulnerable,
except some specific/old models, such as some early Atoms. Whatever processor one uses, one might seek more information
from the manufacturer of that processor and/or of the device in which it runs.
2018-01-09 18:52:21 +01:00
The nature of the discovered vulnerabilities being quite new, the landscape of vulnerable processors can be expected
to change over time, which is why this script makes the assumption that all CPUs are vulnerable, except if the manufacturer
2018-01-12 11:46:36 +01:00
explicitly stated otherwise in a verifiable public announcement.
2018-01-09 18:52:21 +01:00
Please also note that for Spectre vulnerabilities, all software can possibly be exploited, this tool only verifies that the
kernel (which is the core of the system) you're using has the proper protections in place. Verifying all the other software
is out of the scope of this tool. As a general measure, ensure you always have the most up to date stable versions of all
the software you use, especially for those who are exposed to the world, such as network daemons and browsers.
2018-01-09 18:52:21 +01:00
This tool has been released in the hope that it'll be useful, but don't use it to jump to conclusions about your security.
2018-01-08 20:50:42 +01:00
EOF
}
os=$(uname -s)
# parse options
opt_kernel=''
opt_config=''
opt_map=''
opt_live_explicit=0
opt_live=1
opt_no_color=0
opt_batch=0
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
opt_batch_format='text'
opt_verbose=1
opt_cve_list=''
opt_cve_all=1
opt_no_sysfs=0
opt_sysfs_only=0
opt_coreos=0
opt_arch_prefix=''
opt_hw_only=0
opt_no_hw=0
opt_vmm=-1
opt_explain=0
opt_paranoid=0
2018-01-10 12:57:45 +01:00
global_critical=0
global_unknown=0
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
nrpe_vuln=''
supported_cve_list='CVE-2017-5753 CVE-2017-5715 CVE-2017-5754 CVE-2018-3640 CVE-2018-3639 CVE-2018-3615 CVE-2018-3620 CVE-2018-3646 CVE-2018-12126 CVE-2018-12130 CVE-2018-12127 CVE-2019-11091'
# find a sane command to print colored messages, we prefer `printf` over `echo`
# because `printf` behavior is more standard across Linux/BSD
# we'll try to avoid using shell builtins that might not take options
echo_cmd_type='echo'
2019-05-05 18:34:09 +02:00
# ignore SC2230 here because `which` ignores builtins while `command -v` doesn't, and
# we don't want builtins here. Even if `which` is not installed, we'll fallback to the
# `echo` builtin anyway, so this is safe.
# shellcheck disable=SC2230
if command -v printf >/dev/null 2>&1; then
echo_cmd=$(command -v printf)
echo_cmd_type='printf'
elif which echo >/dev/null 2>&1; then
echo_cmd=$(which echo)
else
# maybe the `which` command is broken?
[ -x /bin/echo ] && echo_cmd=/bin/echo
# for Android
[ -x /system/bin/echo ] && echo_cmd=/system/bin/echo
fi
# still empty? fallback to builtin
[ -z "$echo_cmd" ] && echo_cmd='echo'
2018-01-09 10:32:51 +01:00
__echo()
{
opt="$1"
shift
_msg="$*"
2018-01-09 10:32:51 +01:00
if [ "$opt_no_color" = 1 ] ; then
# strip ANSI color codes
# some sed versions (i.e. toybox) can't seem to handle
# \033 aka \x1B correctly, so do it for them.
if [ "$echo_cmd_type" = printf ]; then
_interpret_chars=''
else
_interpret_chars='-e'
fi
_ctrlchar=$($echo_cmd $_interpret_chars "\033")
_msg=$($echo_cmd $_interpret_chars "$_msg" | sed -r "s/$_ctrlchar\[([0-9][0-9]?(;[0-9][0-9]?)?)?m//g")
fi
if [ "$echo_cmd_type" = printf ]; then
if [ "$opt" = "-n" ]; then
$echo_cmd "$_msg"
else
$echo_cmd "$_msg\n"
fi
else
# shellcheck disable=SC2086
$echo_cmd $opt -e "$_msg"
2018-01-09 10:32:51 +01:00
fi
}
_echo()
{
if [ "$opt_verbose" -ge "$1" ]; then
shift
__echo '' "$*"
fi
2018-01-09 10:32:51 +01:00
}
_echo_nol()
{
if [ "$opt_verbose" -ge "$1" ]; then
shift
__echo -n "$*"
fi
}
_warn()
{
_echo 0 "\033[31m$*\033[0m" >&2
}
_info()
{
_echo 1 "$*"
}
_info_nol()
{
_echo_nol 1 "$*"
}
_verbose()
{
_echo 2 "$*"
2018-01-09 10:32:51 +01:00
}
_verbose_nol()
{
_echo_nol 2 "$*"
}
_debug()
{
_echo 3 "\033[34m(debug) $*\033[0m"
}
explain()
{
if [ "$opt_explain" = 1 ] ; then
_info ''
_info "> \033[41m\033[30mHow to fix:\033[0m $*"
fi
}
cve2name()
{
case "$1" in
CVE-2017-5753) echo "Spectre Variant 1, bounds check bypass";;
CVE-2017-5715) echo "Spectre Variant 2, branch target injection";;
CVE-2017-5754) echo "Variant 3, Meltdown, rogue data cache load";;
CVE-2018-3640) echo "Variant 3a, rogue system register read";;
CVE-2018-3639) echo "Variant 4, speculative store bypass";;
CVE-2018-3615) echo "Foreshadow (SGX), L1 terminal fault";;
CVE-2018-3620) echo "Foreshadow-NG (OS), L1 terminal fault";;
CVE-2018-3646) echo "Foreshadow-NG (VMM), L1 terminal fault";;
CVE-2018-12126) echo "Fallout, microarchitectural store buffer data sampling (MSBDS)";;
CVE-2018-12130) echo "ZombieLoad, microarchitectural fill buffer data sampling (MFBDS)";;
CVE-2018-12127) echo "RIDL, microarchitectural load port data sampling (MLPDS)";;
CVE-2019-11091) echo "RIDL, microarchitectural data sampling uncacheable memory (MDSUM)";;
*) echo "$0: error: invalid CVE '$1' passed to cve2name()" >&2; exit 255;;
esac
}
is_cpu_vulnerable_cached=0
_is_cpu_vulnerable_cached()
{
# shellcheck disable=SC2086
case "$1" in
CVE-2017-5753) return $variant1;;
CVE-2017-5715) return $variant2;;
CVE-2017-5754) return $variant3;;
CVE-2018-3640) return $variant3a;;
CVE-2018-3639) return $variant4;;
CVE-2018-3615) return $variantl1tf_sgx;;
CVE-2018-3620) return $variantl1tf;;
CVE-2018-3646) return $variantl1tf;;
CVE-2018-12126) return $variant_msbds;;
CVE-2018-12130) return $variant_mfbds;;
CVE-2018-12127) return $variant_mlpds;;
CVE-2019-11091) return $variant_mdsum;;
*) echo "$0: error: invalid variant '$1' passed to is_cpu_vulnerable()" >&2; exit 255;;
esac
}
2018-01-09 13:11:48 +01:00
is_cpu_vulnerable()
{
# param: one of the $supported_cve_list items
# returns 0 if vulnerable, 1 if not vulnerable
# (note that in shell, a return of 0 is success)
# by default, everything is vulnerable, we work in a "whitelist" logic here.
# usage: is_cpu_vulnerable CVE-xxxx-yyyy && do something if vulnerable
if [ "$is_cpu_vulnerable_cached" = 1 ]; then
_is_cpu_vulnerable_cached "$1"
return $?
fi
variant1=''
variant2=''
variant3=''
variant3a=''
variant4=''
2018-08-15 11:59:23 +02:00
variantl1tf=''
variant_msbds=''
variant_mfbds=''
variant_mlpds=''
variant_mdsum=''
if is_cpu_mds_free; then
[ -z "$variant_msbds" ] && variant_msbds=immune
[ -z "$variant_mfbds" ] && variant_mfbds=immune
[ -z "$variant_mlpds" ] && variant_mlpds=immune
[ -z "$variant_mdsum" ] && variant_mdsum=immune
_debug "is_cpu_vulnerable: cpu not affected by Microarchitectural Data Sampling"
fi
if is_cpu_specex_free; then
variant1=immune
variant2=immune
variant3=immune
variant3a=immune
variant4=immune
2018-08-15 11:59:23 +02:00
variantl1tf=immune
variant_msbds=immune
variant_mfbds=immune
variant_mlpds=immune
variant_mdsum=immune
elif is_intel; then
# Intel
# https://github.com/crozone/SpectrePoC/issues/1 ^F E5200 => spectre 2 not vulnerable
# https://github.com/paboldin/meltdown-exploit/issues/19 ^F E5200 => meltdown vulnerable
# model name : Pentium(R) Dual-Core CPU E5200 @ 2.50GHz
if grep -qE '^model name.+ Pentium\(R\) Dual-Core[[:space:]]+CPU[[:space:]]+E[0-9]{4}K? ' "$procfs/cpuinfo"; then
variant1=vuln
[ -z "$variant2" ] && variant2=immune
variant3=vuln
fi
if [ "$capabilities_rdcl_no" = 1 ]; then
# capability bit for future Intel processor that will explicitly state
# that they're not vulnerable to Meltdown
# this var is set in check_cpu()
2018-08-15 11:59:23 +02:00
[ -z "$variant3" ] && variant3=immune
[ -z "$variantl1tf" ] && variantl1tf=immune
_debug "is_cpu_vulnerable: RDCL_NO is set so not vuln to meltdown nor l1tf"
fi
if [ "$capabilities_ssb_no" = 1 ]; then
# capability bit for future Intel processor that will explicitly state
# that they're not vulnerable to Variant 4
# this var is set in check_cpu()
2018-08-15 11:59:23 +02:00
[ -z "$variant4" ] && variant4=immune
_debug "is_cpu_vulnerable: SSB_NO is set so not vuln to variant4"
fi
if is_cpu_ssb_free; then
[ -z "$variant4" ] && variant4=immune
_debug "is_cpu_vulnerable: cpu not affected by speculative store bypass so not vuln to variant4"
fi
2018-08-15 11:59:23 +02:00
# variant 4a for xeon phi
if [ "$cpu_family" = 6 ]; then
if [ "$cpu_model" = "$INTEL_FAM6_XEON_PHI_KNL" ] || [ "$cpu_model" = "$INTEL_FAM6_XEON_PHI_KNM" ]; then
_debug "is_cpu_vulnerable: xeon phi immune to variant 3a"
[ -z "$variant3a" ] && variant3a=immune
fi
fi
# L1TF (RDCL_NO already checked above)
if [ "$cpu_family" = 6 ]; then
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
if [ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL_TABLET" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_BONNELL" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_BONNELL_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SILVERMONT" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SILVERMONT_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SILVERMONT_X" ] || \
2018-08-15 11:59:23 +02:00
[ "$cpu_model" = "$INTEL_FAM6_ATOM_AIRMONT" ] || \
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
[ "$cpu_model" = "$INTEL_FAM6_ATOM_AIRMONT_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT_X" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT_PLUS" ] || \
2018-08-15 11:59:23 +02:00
[ "$cpu_model" = "$INTEL_FAM6_XEON_PHI_KNL" ] || \
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
[ "$cpu_model" = "$INTEL_FAM6_XEON_PHI_KNM" ]; then
2018-08-15 11:59:23 +02:00
_debug "is_cpu_vulnerable: intel family 6 but model known to be immune"
[ -z "$variantl1tf" ] && variantl1tf=immune
else
_debug "is_cpu_vulnerable: intel family 6 is vuln"
[ -z "$variantl1tf" ] && variantl1tf=vuln
2018-08-15 11:59:23 +02:00
fi
elif [ "$cpu_family" -lt 6 ]; then
_debug "is_cpu_vulnerable: intel family < 6 is immune"
[ -z "$variantl1tf" ] && variantl1tf=immune
fi
elif is_amd || is_hygon; then
# AMD revised their statement about variant2 => vulnerable
# https://www.amd.com/en/corporate/speculative-execution
variant1=vuln
variant2=vuln
2018-05-23 20:38:43 +02:00
[ -z "$variant3" ] && variant3=immune
# https://www.amd.com/en/corporate/security-updates
# "We have not identified any AMD x86 products susceptible to the Variant 3a vulnerability in our analysis to-date."
[ -z "$variant3a" ] && variant3a=immune
if is_cpu_ssb_free; then
[ -z "$variant4" ] && variant4=immune
_debug "is_cpu_vulnerable: cpu not affected by speculative store bypass so not vuln to variant4"
fi
2018-08-15 11:59:23 +02:00
variantl1tf=immune
elif [ "$cpu_vendor" = CAVIUM ]; then
variant3=immune
variant3a=immune
2018-08-15 11:59:23 +02:00
variantl1tf=immune
elif [ "$cpu_vendor" = ARM ]; then
2018-01-09 13:11:48 +01:00
# ARM
# reference: https://developer.arm.com/support/security-update
# some devices (phones or other) have several ARMs and as such different part numbers,
# an example is "bigLITTLE". we shouldn't rely on the first CPU only, so we check the whole list
i=0
for cpupart in $cpu_part_list
do
i=$(( i + 1 ))
# do NOT quote $cpu_arch_list below
# shellcheck disable=SC2086
cpuarch=$(echo $cpu_arch_list | awk '{ print $'$i' }')
_debug "checking cpu$i: <$cpupart> <$cpuarch>"
# some kernels report AArch64 instead of 8
[ "$cpuarch" = "AArch64" ] && cpuarch=8
if [ -n "$cpupart" ] && [ -n "$cpuarch" ]; then
# Cortex-R7 and Cortex-R8 are real-time and only used in medical devices or such
# I can't find their CPU part number, but it's probably not that useful anyway
# model R7 R8 A8 A9 A12 A15 A17 A57 A72 A73 A75 A76
# part ? ? c08 c09 c0d c0f c0e d07 d08 d09 d0a d0b?
# arch 7? 7? 7 7 7 7 7 8 8 8 8 8
#
# Whitelist identified non-vulnerable processors, use vulnerability information from
# https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
#
# Maintain cumulative check of vulnerabilities -
# if at least one of the cpu is vulnerable, then the system is vulnerable
if [ "$cpuarch" = 7 ] && echo "$cpupart" | grep -q -w -e 0xc08 -e 0xc09 -e 0xc0d -e 0xc0e; then
variant1=vuln
variant2=vuln
[ -z "$variant3" ] && variant3=immune
[ -z "$variant3a" ] && variant3a=immune
[ -z "$variant4" ] && variant4=immune
_debug "checking cpu$i: armv7 A8/A9/A12/A17 non vulnerable to variants 3, 3a & 4"
elif [ "$cpuarch" = 7 ] && echo "$cpupart" | grep -q -w -e 0xc0f; then
variant1=vuln
variant2=vuln
[ -z "$variant3" ] && variant3=immune
variant3a=vuln
[ -z "$variant4" ] && variant4=immune
_debug "checking cpu$i: armv7 A15 non vulnerable to variants 3 & 4"
elif [ "$cpuarch" = 8 ] && echo "$cpupart" | grep -q -w -e 0xd07 -e 0xd08; then
variant1=vuln
variant2=vuln
[ -z "$variant3" ] && variant3=immune
variant3a=vuln
variant4=vuln
_debug "checking cpu$i: armv8 A57/A72 non vulnerable to variants 3"
elif [ "$cpuarch" = 8 ] && echo "$cpupart" | grep -q -w -e 0xd09; then
variant1=vuln
variant2=vuln
[ -z "$variant3" ] && variant3=immune
[ -z "$variant3a" ] && variant3a=immune
variant4=vuln
_debug "checking cpu$i: armv8 A73 non vulnerable to variants 3 & 3a"
elif [ "$cpuarch" = 8 ] && echo "$cpupart" | grep -q -w -e 0xd0a; then
variant1=vuln
variant2=vuln
variant3=vuln
[ -z "$variant3a" ] && variant3a=immune
variant4=vuln
_debug "checking cpu$i: armv8 A75 non vulnerable to variant 3a"
elif [ "$cpuarch" = 8 ] && echo "$cpupart" | grep -q -w -e 0xd0b; then
variant1=vuln
[ -z "$variant2" ] && variant2=immune
[ -z "$variant3" ] && variant3=immune
[ -z "$variant3a" ] && variant3a=immune
variant4=vuln
_debug "checking cpu$i: armv8 A76 non vulnerable to variant 2, 3 & 3a"
2019-05-05 18:34:09 +02:00
elif [ "$cpuarch" -le 7 ] || { [ "$cpuarch" = 8 ] && [ $(( cpupart )) -lt $(( 0xd07 )) ]; } ; then
[ -z "$variant1" ] && variant1=immune
[ -z "$variant2" ] && variant2=immune
[ -z "$variant3" ] && variant3=immune
[ -z "$variant3a" ] && variant3a=immune
[ -z "$variant4" ] && variant4=immune
_debug "checking cpu$i: arm arch$cpuarch, all immune (v7 or v8 and model < 0xd07)"
else
variant1=vuln
variant2=vuln
variant3=vuln
variant3a=vuln
variant4=vuln
_debug "checking cpu$i: arm unknown arch$cpuarch part$cpupart, considering vuln"
fi
2018-01-09 13:11:48 +01:00
fi
_debug "is_cpu_vulnerable: for cpu$i and so far, we have <$variant1> <$variant2> <$variant3> <$variant3a> <$variant4>"
done
2018-08-15 11:59:23 +02:00
variantl1tf=immune
fi
_debug "is_cpu_vulnerable: temp results are <$variant1> <$variant2> <$variant3> <$variant3a> <$variant4> <$variantl1tf>"
[ "$variant1" = "immune" ] && variant1=1 || variant1=0
[ "$variant2" = "immune" ] && variant2=1 || variant2=0
[ "$variant3" = "immune" ] && variant3=1 || variant3=0
[ "$variant3a" = "immune" ] && variant3a=1 || variant3a=0
[ "$variant4" = "immune" ] && variant4=1 || variant4=0
[ "$variantl1tf" = "immune" ] && variantl1tf=1 || variantl1tf=0
[ "$variant_msbds" = "immune" ] && variant_msbds=1 || variant_msbds=0
[ "$variant_mfbds" = "immune" ] && variant_mfbds=1 || variant_mfbds=0
[ "$variant_mlpds" = "immune" ] && variant_mlpds=1 || variant_mlpds=0
[ "$variant_mdsum" = "immune" ] && variant_mdsum=1 || variant_mdsum=0
variantl1tf_sgx="$variantl1tf"
# even if we are vulnerable to L1TF, if there's no SGX, we're safe for the original foreshadow
[ "$cpuid_sgx" = 0 ] && variantl1tf_sgx=1
_debug "is_cpu_vulnerable: final results are <$variant1> <$variant2> <$variant3> <$variant3a> <$variant4> <$variantl1tf> <$variantl1tf_sgx>"
is_cpu_vulnerable_cached=1
_is_cpu_vulnerable_cached "$1"
return $?
2018-01-09 13:11:48 +01:00
}
is_cpu_specex_free()
{
# return true (0) if the CPU doesn't do speculative execution, false (1) if it does.
# if it's not in the list we know, return false (1).
# source: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/kernel/cpu/common.c#n882
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
# { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL, X86_FEATURE_ANY },
# { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_TABLET, X86_FEATURE_ANY },
# { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL_MID, X86_FEATURE_ANY },
# { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_MID, X86_FEATURE_ANY },
# { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL, X86_FEATURE_ANY },
# { X86_VENDOR_CENTAUR, 5 },
# { X86_VENDOR_INTEL, 5 },
# { X86_VENDOR_NSC, 5 },
# { X86_VENDOR_ANY, 4 },
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
2018-02-02 11:10:36 +01:00
parse_cpu_details
if is_intel; then
if [ "$cpu_family" = 6 ]; then
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
if [ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL_TABLET" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_BONNELL_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_SALTWELL_MID" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_BONNELL" ]; then
return 0
fi
elif [ "$cpu_family" = 5 ]; then
return 0
fi
fi
[ "$cpu_family" = 4 ] && return 0
return 1
}
is_cpu_mds_free()
{
# return true (0) if the CPU isn't affected by microarchitectural data sampling, false (1) if it does.
# if it's not in the list we know, return false (1).
# source: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/kernel/cpu/common.c
#VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF),
#VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF),
#VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF),
#/* AMD Family 0xf - 0x12 */
#VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
#VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
#VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
#VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
#/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
#VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
#VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
parse_cpu_details
if is_intel; then
if [ "$cpu_family" = 6 ]; then
if [ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT_X" ] || \
[ "$cpu_model" = "$INTEL_FAM6_ATOM_GOLDMONT_PLUS" ]; then
return 0
fi
fi
fi
# official statement from AMD says none of their CPUs are vulnerable
# https://www.amd.com/en/corporate/product-security
# https://www.amd.com/system/files/documents/security-whitepaper.pdf
if is_amd; then
return 0
elif is_hygon; then
return 0
elif [ "$cpu_vendor" = CAVIUM ]; then
return 0
elif [ "$cpu_vendor" = ARM ]; then
return 0
fi
return 1
}
is_cpu_ssb_free()
{
# return true (0) if the CPU isn't affected by speculative store bypass, false (1) if it does.
# if it's not in the list we know, return false (1).
# source1: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/kernel/cpu/common.c#n945
# source2: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/tree/arch/x86/kernel/cpu/common.c
# Only list CPUs that speculate but are immune, to avoid duplication of cpus listed in is_cpu_specex_free()
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
#{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
#{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
Improved hypervisor detection (#259) * Code consistency ``` opt_batch_format="text" ``` replaced by ``` opt_batch_format='text' ``` ```nrpe_vuln='"" ``` replaced by ``` nrpe_vuln='' ``` , as used by other parse options Redundant ``` ! -z ``` replaced by ``` -n ```, as used elsewhere Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Improved hypervisor detection Tests for presence of hypervisor flag in /proc/cpuino Tests for evidence of hypervisor in dmesg Signed-off-by: Rob Gill <rrobgill@protonmail.com> * formatting fix Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Set $l1d_mode to -1 in cases where cpu/vulnerabilities/l1tf is not available (prevents invalid number error when evaluating [ "$l1d_mode" -ge 1 ]) Signed-off-by: Rob Gill <rrobgill@protonmail.com> * Update Intel Atom 6 cpu names to align with kernel Update processor names of atom 6 family processors to align with those from kernel as of October 2018. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/arch/x86/include/asm/intel-family.h?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Update list of known immune processors from https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/arch/x86/kernel/cpu/common.c?id=f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e * Fix unset $l1d_mode Another instance of unset l1d_mode causing error "./spectre-meltdown-checker.sh: 3867: [: Illegal number:" * chore: update readme with brief summary of L1tfs L1tf mitigation and impact details from https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html and https://blogs.oracle.com/oraclesecurity/intel-l1tf * typo
2018-12-10 19:33:07 +01:00
#{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X },
#{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID },