Re: [PATCH] x86/srso: Correct the mitigation status when SMT is disabled

[Josh Poimboeuf]

On Tue, Aug 15, 2023 at 11:57:24AM +0200, Borislav Petkov wrote:
> --- a/arch/x86/kernel/cpu/bugs.c
> +++ b/arch/x86/kernel/cpu/bugs.c
> @@ -2417,8 +2417,7 @@ static void __init srso_select_mitigation(void)
>  		 * Zen1/2 with SMT off aren't vulnerable after the right
>  		 * IBPB microcode has been applied.
>  		 */
> -		if ((boot_cpu_data.x86 < 0x19) &&
> -		    (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) {
> +		if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
>  			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
>  			return;
>  		}
> @@ -2698,8 +2697,12 @@ static ssize_t retbleed_show_state(char *buf)
>  
>  static ssize_t srso_show_state(char *buf)
>  {
> -	if (boot_cpu_has(X86_FEATURE_SRSO_NO))
> -		return sysfs_emit(buf, "Not affected\n");
> +	if (boot_cpu_has(X86_FEATURE_SRSO_NO)) {
> +		if (sched_smt_active())
> +			return sysfs_emit(buf, "Not affected\n");
> +		else
> +			return sysfs_emit(buf, "Mitigation: SMT disabled\n");
> +	}

AFAICT, nowhere in the spec does it say the SRSO_NO bit won't get set by
future (fixed) HW.  In fact I'd expect it will, similar to other *_NO
flags.

Regardless, here SRSO_NO seems to mean two different things: "reported
safe by host (or HW)" and "not reported safe on Zen1/2 with SMT not
possible".

Also, in this code, the SRSO_NO+SMT combo doesn't seem logically
possible, as srso_show_state() only gets called if X86_BUG_SRSO is set,
which only happens if SRSO_NO is not set by the HW/host in the first
place.  So here, if boot_cpu_has(X86_FEATURE_SRSO_NO), it means SRSO_NO
was manually set by srso_select_mitigation(), and SMT can't possibly be
enabled.

Instead of piggybacking on SRSO_NO, which is confusing, why not just add
a new mitigation type, like:

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6c04aef4b63b..c925b98f5a15 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2343,6 +2343,7 @@ early_param("l1tf", l1tf_cmdline);
 enum srso_mitigation {
 	SRSO_MITIGATION_NONE,
 	SRSO_MITIGATION_MICROCODE,
+	SRSO_MITIGATION_SMT,
 	SRSO_MITIGATION_SAFE_RET,
 	SRSO_MITIGATION_IBPB,
 	SRSO_MITIGATION_IBPB_ON_VMEXIT,
@@ -2359,6 +2360,7 @@ enum srso_mitigation_cmd {
 static const char * const srso_strings[] = {
 	[SRSO_MITIGATION_NONE]           = "Vulnerable",
 	[SRSO_MITIGATION_MICROCODE]      = "Mitigation: microcode",
+	[SRSO_MITIGATION_SMT]		 = "Mitigation: SMT disabled",
 	[SRSO_MITIGATION_SAFE_RET]	 = "Mitigation: safe RET",
 	[SRSO_MITIGATION_IBPB]		 = "Mitigation: IBPB",
 	[SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only"
@@ -2407,19 +2409,15 @@ static void __init srso_select_mitigation(void)
 		pr_warn("IBPB-extending microcode not applied!\n");
 		pr_warn(SRSO_NOTICE);
 	} else {
-		/*
-		 * Enable the synthetic (even if in a real CPUID leaf)
-		 * flags for guests.
-		 */
+		/* Enable the synthetic flag, as HW doesn't set it. */
 		setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
 
 		/*
 		 * Zen1/2 with SMT off aren't vulnerable after the right
 		 * IBPB microcode has been applied.
 		 */
-		if ((boot_cpu_data.x86 < 0x19) &&
-		    (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) {
-			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
+		if ((boot_cpu_data.x86 < 0x19) && !cpu_smt_possible()) {
+			srso_mitigation = SRSO_MITIGATION_SMT;
 			return;
 		}
 	}
@@ -2698,9 +2696,6 @@ static ssize_t retbleed_show_state(char *buf)
 
 static ssize_t srso_show_state(char *buf)
 {
-	if (boot_cpu_has(X86_FEATURE_SRSO_NO))
-		return sysfs_emit(buf, "Not affected\n");
-
 	return sysfs_emit(buf, "%s%s\n",
 			  srso_strings[srso_mitigation],
 			  (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));