[PATCH 2/3] x86/bugs: Fix BHI retpoline check

Josh Poimboeuf posted 3 patches 1 year, 8 months ago
[PATCH 2/3] x86/bugs: Fix BHI retpoline check
Posted by Josh Poimboeuf 1 year, 8 months ago
Confusingly, X86_FEATURE_RETPOLINE doesn't mean retpolines are enabled,
as it also includes the original "AMD retpoline" which isn't a retpoline
at all.

Also replace cpu_feature_enabled() with boot_cpu_has() because this is
before alternatives are patched and cpu_feature_enabled()'s fallback
path is slower than plain old boot_cpu_has().

Fixes: ec9404e40e8f ("x86/bhi: Add BHI mitigation knob")
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 arch/x86/kernel/cpu/bugs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index dcb97cc2758f..e827613c9e39 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1652,7 +1652,8 @@ static void __init bhi_select_mitigation(void)
 		return;
 
 	/* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+	if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+	    !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
 		spec_ctrl_disable_kernel_rrsba();
 		if (rrsba_disabled)
 			return;
@@ -2833,11 +2834,13 @@ static const char *spectre_bhi_state(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_BHI))
 		return "; BHI: Not affected";
-	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
 		return "; BHI: BHI_DIS_S";
-	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
 		return "; BHI: SW loop, KVM: SW loop";
-	else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && rrsba_disabled)
+	else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+		 !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
+		 rrsba_disabled)
 		return "; BHI: Retpoline";
 	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
 		return "; BHI: Vulnerable, KVM: SW loop";
-- 
2.44.0
Re: [PATCH 2/3] x86/bugs: Fix BHI retpoline check
Posted by Pawan Gupta 1 year, 8 months ago
On Fri, Apr 12, 2024 at 11:10:33AM -0700, Josh Poimboeuf wrote:
> Confusingly, X86_FEATURE_RETPOLINE doesn't mean retpolines are enabled,
> as it also includes the original "AMD retpoline" which isn't a retpoline
> at all.
> 
> Also replace cpu_feature_enabled() with boot_cpu_has() because this is
> before alternatives are patched and cpu_feature_enabled()'s fallback
> path is slower than plain old boot_cpu_has().
> 
> Fixes: ec9404e40e8f ("x86/bhi: Add BHI mitigation knob")
> Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>

Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>