Messages in this thread | | | Date | Wed, 9 Aug 2023 16:43:35 +0200 | From | Peter Zijlstra <> | Subject | Re: [RFC][PATCH 11/17] x86/cpu: Remove all SRSO interface nonsense |
| |
On Wed, Aug 09, 2023 at 10:05:30AM -0400, Josh Poimboeuf wrote: > On Wed, Aug 09, 2023 at 09:12:29AM +0200, Peter Zijlstra wrote: > > @@ -2607,26 +2447,26 @@ static ssize_t srbds_show_state(char *bu > > static ssize_t retbleed_show_state(char *buf) > > { > > if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || > > + retbleed_mitigation == RETBLEED_MITIGATION_UNRET_SRSO || > > + retbleed_mitigation == RETBLEED_MITIGATION_UNRET_SRSO_ALIAS || > > retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { > > These retbleed_show_state() changes probably belong in that other patch > which adds the retbleed= cmdline options.
Ah yes, lost hunk that. Let me move it there.
> > + > > if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && > > boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) > > return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); > > > > - return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], > > + return sysfs_emit(buf, "%s; SMT %s%s\n", retbleed_strings[retbleed_mitigation], > > !sched_smt_active() ? "disabled" : > > spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || > > spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? > > - "enabled with STIBP protection" : "vulnerable"); > > - } > > + "enabled with STIBP protection" : "vulnerable", > > + cpu_has_ibpb_brtype_microcode() ? "" : ", no SRSO microcode"); > > Hm? What does missing microcode have to do with SMT?
semi-colon then, instead of comma ?
| |