Stéphane Lesimple
b262c40541
fix: remove spurious character after an else statement
2018-07-25 21:55:50 +02:00
Stéphane Lesimple
cc2910fbbc
fix: read_cpuid: don't use iflag=skip_bytes for compat with old dd versions
...
This closes #215 #199 #193
2018-07-23 09:12:30 +02:00
manish jaggi
30c4a1f6d2
arm64: cavium: Add CPU Implementer Cavium ( #216 )
...
This patch adds 0x43 check for cavium implementor id in function
parse_cpu_details. Also adds that Cavium Soc is not vulnerable to variant 3/3a
Signed-off-by: Manish Jaggi <manish.jagg@cavium.com>
2018-07-22 19:06:19 +02:00
Stéphane Lesimple
cf06636a3f
fix: prometheus output: use printf for proper \n interpretation ( #204 )
2018-06-21 23:35:51 +02:00
Stéphane Lesimple
60077c8d12
fix(arm): rewrite vuln logic from latest arm statement for Cortex A8 to A76
2018-06-21 23:24:18 +02:00
Rob Gill
c181978d7c
fix(arm): Updated arm cortex status ( #209 )
...
* Cortex A8 Vulnerable
Arm Cortex A8 is vulnerable to variants 1 & 2 (https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability )
Part number is 0xc08 (https://developer.arm.com/docs/ddi0344/b/system-control-coprocessor/system-control-coprocessorregisters/c0-main-id-register )
False negative reported by @V10lator in #206
* ARM Cortex A12 Vulnerable to 1&2
https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
* A76 vulnerable to variant 4
All arch 8 cortex A57-A76 are vulnerable to variant 4.
https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
* Whitelist variant4 nonvuln Arms
* ARM Cortex Whitelist & Cumulative Blacklist
Applies all information about vulnerabilities of ARM Cortex processors (from https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability ).
Whitelist & blacklist approach, using both vulnerable and non vulnerable status for each identified CPU, with vulnerabilities tracked cumulatively for multi CPU systems.
2018-06-16 12:14:39 +02:00
Jan
9a6406a9a2
chore: add docker support ( #203 )
2018-06-14 20:25:35 +02:00
Rob Gill
5962d20ba7
fix(variant4): whitelist from common.c::cpu_no_spec_store_bypass ( #202 )
...
* variant4 from common.c::cpu_no_spec_store_bypass
Variant 4 - Add function to 'whitelist' the hand-full of CPUs unaffected by speculative store bypass.
This would allow improved determination of variant 4 status ( #189 ) of immune CPUs while waiting for the 4.17/stable patches to be backported to distro kernels.
Source of cpu list : https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/kernel/cpu/common.c#n945 )
Modeled after is_cpu_specex_free()
* amd families fix
amd families are reported by parse_cpu_details() in decimal
* remove duplicates
Only list processors which speculate and are immune to variant 4.
Avoids duplication with non-speculating CPUs listed in is_cpu_specex_free()
2018-05-27 15:14:29 +02:00
Rob Gill
17a3488505
fix(help): add missing references to variants 3a & 4 ( #201 )
2018-05-24 16:35:57 +02:00
Stéphane Lesimple
e54e8b3e84
chore: remove warning in README, fix display indentation
2018-05-24 16:32:53 +02:00
Stéphane Lesimple
39c778e3ac
fix(amd): AMD families 0x15-0x17 non-arch MSRs are a valid way to control SSB
2018-05-23 23:08:07 +02:00
Stéphane Lesimple
2cde6e4649
feat(ssbd): add detection of proper CPUID bits on AMD
2018-05-23 22:50:52 +02:00
Stéphane Lesimple
f4d51e7e53
fix(variant4): add another detection way for Red Hat kernel
2018-05-23 22:47:54 +02:00
Stéphane Lesimple
85d46b2799
feat(variant4): add more detailed explanations
2018-05-23 21:08:58 +02:00
Stéphane Lesimple
61e02abd0c
feat(variant3a): detect up to date microcode
2018-05-23 21:08:08 +02:00
Stéphane Lesimple
114756fab7
fix(amd): not vulnerable to variant3a
2018-05-23 20:38:43 +02:00
Rob Gill
ea75969eb7
fix(help): Update variant options in usage message ( #200 )
2018-05-22 15:54:25 +02:00
Stéphane Lesimple
ca391cbfc9
fix(variant2): correctly detect IBRS/IBPB in SLES kernels
2018-05-22 12:06:46 +02:00
Stéphane Lesimple
68af5c5f92
feat(variant4): detect SSBD-aware kernel
2018-05-22 12:05:46 +02:00
Stéphane Lesimple
19be8f79eb
doc: update README with some info about variant3 and variant4
2018-05-22 09:43:29 +02:00
Stéphane Lesimple
f75cc0bb6f
feat(variant4): add sysfs mitigation hint and some explanation about the vuln
2018-05-22 09:39:11 +02:00
Stéphane Lesimple
f33d65ff71
feat(variant3a): add information about microcode-sufficient mitigation
2018-05-22 09:38:29 +02:00
Stéphane Lesimple
725eaa8bf5
feat(arm): adjust vulnerable ARM CPUs for variant3a and variant4
2018-05-22 09:19:29 +02:00
Stéphane Lesimple
c6ee0358d1
feat(variant4): report SSB_NO CPUs as not vulnerable
2018-05-22 09:18:30 +02:00
Stéphane Lesimple
22d0b203da
fix(ssb_no): rename ssbd_no to ssb_no and fix shift
2018-05-22 00:38:31 +02:00
Stéphane Lesimple
3062a8416a
fix(msg): add missing words
2018-05-22 00:10:08 +02:00
Stéphane Lesimple
6a4318addf
feat(variant3a/4): initial support for 2 new CVEs
2018-05-22 00:06:56 +02:00
Stéphane Lesimple
c19986188f
fix(variant2): adjust detection for SLES kernels
2018-05-19 09:53:12 +02:00
Rob Gill
7e4899bcb8
ibrs can't be enabled on no ibrs cpu ( #195 )
...
* ibrs can't be enabled on no ibrs cpu
If the cpu is identified, and does not support SPEC_CTRL or IBRS, then ibrs can't be enabled, even if supported by the kernel.
Instead of reporting IBRS enabled and active UNKNOWN, report IBRS enabled and active NO.
2018-05-17 15:39:48 +02:00
rrobgill
5cc77741af
Update spectre-meltdown-checker.sh
2018-05-05 13:00:44 +02:00
rrobgill
1c0f6d9580
cpuid and msr module check
...
This adds a check before loading the cpuid and msr modules under linux, ensuring they are not unloaded in exit_cleanup() if they were initially present.
2018-05-05 13:00:44 +02:00
Onno Zweers
4acd0f647a
Suggestion to change VM to a CPU with IBRS capability
2018-04-20 20:35:12 +02:00
Stéphane Lesimple
fb52dbe7bf
set master branch to v0.37+
2018-04-20 20:34:42 +02:00
Stéphane Lesimple
edebe4dcd4
bump to v0.37
2018-04-18 23:51:45 +02:00
Stéphane Lesimple
83ea78f523
fix: arm: also detect variant 1 mitigation when using native objdump
2018-04-17 18:50:32 +02:00
Stéphane Lesimple
602b68d493
fix(spectrev2): explain that retpoline is possible for Skylake+ if there is RSB filling, even if IBRS is still better
2018-04-16 09:27:28 +02:00
Stéphane Lesimple
97bccaa0d7
feat: rephrase IBPB warning when only retpoline is enabled in non-paranoid mode
2018-04-16 09:13:25 +02:00
Stéphane Lesimple
68e619b0d3
feat: show RSB filling capability for non-Skylake in verbose mode
2018-04-16 09:08:25 +02:00
Stéphane Lesimple
a6f4475cee
feat: make IBRS_FW blue instead of green
2018-04-16 09:07:54 +02:00
Stéphane Lesimple
223f5028df
feat: add --paranoid to choose whether we require IBPB
2018-04-15 23:05:30 +02:00
Stéphane Lesimple
c0108b9690
fix(spectre2): don't explain how to fix when NOT VULNERABLE
2018-04-15 20:55:55 +02:00
Stéphane Lesimple
a3016134bd
feat: make RSB filling support mandatory for Skylake+ CPUs
2018-04-15 20:55:31 +02:00
Stéphane Lesimple
59d85b39c9
feat: detect RSB filling capability in the kernel
2018-04-15 20:55:01 +02:00
Stéphane Lesimple
baaefb0c31
fix: remove shellcheck warnings
2018-04-11 22:24:03 +02:00
Igor Lubashev
d452aca03a
fix: invalid bash syntax when ibpb_enabled or ibrs_enabled are empty
2018-04-11 10:29:42 +02:00
Stéphane Lesimple
10b8d94724
feat: detect latest Red Hat kernels' RO ibpb_enabled knob
2018-04-10 22:51:45 +02:00
Stéphane Lesimple
8606e60ef7
refactor: no longer display the retoline-aware compiler test when we can't tell for sure
2018-04-10 22:51:45 +02:00
Stéphane Lesimple
6a48251647
fix: regression in 51aeae25, when retpoline & ibpb are enabled
2018-04-10 22:51:45 +02:00
Stéphane Lesimple
f4bf5e95ec
fix: typos
2018-04-10 22:51:45 +02:00
Stéphane Lesimple
60eac1ad43
feat: also do PTI performance check with (inv)pcid for BSD
2018-04-10 22:51:45 +02:00
