diff options
| author | Pawan Gupta <pawan.kumar.gupta@linux.intel.com> | 2026-07-08 11:40:14 -0700 |
|---|---|---|
| committer | Borislav Petkov (AMD) <bp@alien8.de> | 2026-07-20 10:04:45 -0700 |
| commit | a4c714fe9746bf5a434bb798b26ebba278b798c1 (patch) | |
| tree | 64c70f028cd57a5fd60b3fca023b44b0737f270a /tools/lib/python | |
| parent | 3eaa50e1e255ec261c757b9eea811ef3bac10d1e (diff) | |
x86/bugs: Don't use cpu-type matching in cpu_vuln_blacklist
Thomas Gleixner pointed out that cpu-type is a per-CPU property while hybrid
is a system property; conflating the two in the CPU matching infrastructure is
wrong. Currently, on a hybrid system x86_match_cpu() matches any cpu-type.
This works if the intent is to find the possibility of a cpu-type in a system.
But fails if matching for the cpu-type of a given CPU.
Borislav posted a cleanup here:
https://lore.kernel.org/all/20260703193222.GFakgORjvxwnZTPRnI@fat_crate.local
To make way for the cleanup stop matching cpu-type in cpu_vuln_blacklist.
RFDS is the only user, so drop the VULNBL_INTEL_TYPE entries and fold their
RFDS bit into the base Alder Lake (0x97) and Raptor Lake (0xB7) blacklist
entries. For now open-code cpu-type check in vulnerable_to_rfds(). In the
future, if more vulnerabilities need cpu-type matching a helper can be added.
No functional change intended.
Fixes: 722fa0dba74f ("x86/rfds: Exclude P-only parts from the RFDS affected list")
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://patch.msgid.link/20260708-cpu-type-vuln-v1-1-85c1d3c704db@linux.intel.com
Diffstat (limited to 'tools/lib/python')
0 files changed, 0 insertions, 0 deletions
