1. Patchew
  2. linux
  3. [PATCH v6 0/7] x86/cpu, kvm: Support AMD Automatic IBRS
  4. View patch

[PATCH v6 3/7] x86/cpu, kvm: Move the LFENCE_RDTSC / LFENCE always serializing feature

Kim Phillips posted 7 patches 2 years, 8 months ago
There is a newer version of this series
[PATCH v6 3/7] x86/cpu, kvm: Move the LFENCE_RDTSC / LFENCE always serializing feature
Posted by Kim Phillips 2 years, 8 months ago 
The LFENCE_RDTSC / LFENCE always serializing feature was a scattered bit
and open-coded for KVM in __do_cpuid_func().  Add it to its newly added
CPUID leaf 0x80000021 EAX proper, and propagate it in kvm_set_cpu_caps()
instead.

Also drop the bit description comments now it's more self-describing.

Whilst there, switch to using the more efficient cpu_feature_enabled()
instead of static_cpu_has().

Signed-off-by: Kim Phillips <kim.phillips@amd.com>
---
 arch/x86/include/asm/cpufeatures.h | 3 ++-
 arch/x86/kvm/cpuid.c               | 9 ++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0cd7b4afd528..79da8e492c0f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -97,7 +97,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
@@ -428,6 +428,7 @@
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" AMD No Nested Data Breakpoints */
+#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 69e433e4e9ff..88c970046c10 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -742,8 +742,10 @@ void kvm_set_cpu_caps(void)
 		F(SME_COHERENT));
 
 	kvm_cpu_cap_mask(CPUID_8000_0021_EAX,
-		F(NO_NESTED_DATA_BP)
+		F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC)
 	);
+	if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
+		kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC);
 
 	kvm_cpu_cap_mask(CPUID_C000_0001_EDX,
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
@@ -1229,7 +1231,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		cpuid_entry_override(entry, CPUID_8000_0021_EAX);
 		/*
 		 * Pass down these bits:
-		 *    EAX      2      LAS, LFENCE always serializing
 		 *    EAX      6      NSCB, Null selector clear base
 		 *
 		 * Other defined bits are for MSRs that KVM does not expose:
@@ -1239,10 +1240,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		 * KVM doesn't support SMM_CTL.
 		 *   EAX       9     SMM_CTL MSR is not supported
 		 */
-		entry->eax &= BIT(2) | BIT(6);
+		entry->eax &= BIT(6);
 		entry->eax |= BIT(9);
-		if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC))
-			entry->eax |= BIT(2);
 		if (!static_cpu_has_bug(X86_BUG_NULL_SEG))
 			entry->eax |= BIT(6);
 		break;
-- 
2.34.1
Re: [PATCH v6 3/7] x86/cpu, kvm: Move the LFENCE_RDTSC / LFENCE always serializing feature
Posted by Borislav Petkov 2 years, 8 months ago 
On Tue, Jan 10, 2023 at 04:46:39PM -0600, Kim Phillips wrote:
> The LFENCE_RDTSC / LFENCE always serializing feature was a scattered bit
> and open-coded for KVM in __do_cpuid_func().  Add it to its newly added
> CPUID leaf 0x80000021 EAX proper, and propagate it in kvm_set_cpu_caps()
> instead.
> 
> Also drop the bit description comments now it's more self-describing.
> 
> Whilst there, switch to using the more efficient cpu_feature_enabled()
> instead of static_cpu_has().
> 
> Signed-off-by: Kim Phillips <kim.phillips@amd.com>
> ---
>  arch/x86/include/asm/cpufeatures.h | 3 ++-
>  arch/x86/kvm/cpuid.c               | 9 ++++-----
>  2 files changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
> index 0cd7b4afd528..79da8e492c0f 100644
> --- a/arch/x86/include/asm/cpufeatures.h
> +++ b/arch/x86/include/asm/cpufeatures.h
> @@ -97,7 +97,7 @@
>  #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
>  #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
>  #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
> -#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
> +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
>  #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
>  #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
>  #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
> @@ -428,6 +428,7 @@
>  
>  /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
>  #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" AMD No Nested Data Breakpoints */
> +#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */

Hmm, a synthetic bit which gets replaced with a vendor one and then the other
vendors set it too. I don't see why that cannot work but we probably should be
careful here.

dhansen, am I missing an angle?

Also, X86_FEATURE_LFENCE_RDTSC gets set in init_amd() along with setting
DE_CFG[1]. I think you should check the new flag here first and avoid the
setting if that flag is set. Just for good measure - not that it changes
anything but still, it is cheap to do.

Thx.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette
Re: [PATCH v6 3/7] x86/cpu, kvm: Move the LFENCE_RDTSC / LFENCE always serializing feature
Posted by Dave Hansen 2 years, 8 months ago 
On 1/16/23 10:13, Borislav Petkov wrote:
>>  /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
>>  #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" AMD No Nested Data Breakpoints */
>> +#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
> Hmm, a synthetic bit which gets replaced with a vendor one and then the other
> vendors set it too. I don't see why that cannot work but we probably should be
> careful here.
> 
> dhansen, am I missing an angle?

I don't think so.

I'd be surprised if we don't have a _few_ other cases like this around,
but nothing is coming to mind.  Either way, it doesn't seem problematic.
Re: [PATCH v6 3/7] x86/cpu, kvm: Move the LFENCE_RDTSC / LFENCE always serializing feature
Posted by Borislav Petkov 2 years, 8 months ago 
On Mon, Jan 16, 2023 at 01:15:29PM -0800, Dave Hansen wrote:
> I don't think so.
> 
> I'd be surprised if we don't have a _few_ other cases like this around,
> but nothing is coming to mind.  Either way, it doesn't seem problematic.

Yeah, probably. The cases I remember are the other way around - we map
vendor-specific flags to synthetic ones...

Anyway, thanks for checking!

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.