[PATCH v3] x86/cpuid: expose AVX512_4VNNIW and AVX512_4FMAPS features to kvm guest
From: He Chen
Date: Fri Nov 04 2016 - 03:09:59 EST
The spec can be found in Intel Software Developer Manual or in
Instruction Set Extensions Programming Reference.
Signed-off-by: Luwei Kang <luwei.kang@xxxxxxxxx>
Signed-off-by: He Chen <he.chen@xxxxxxxxxxxxxxx>
---
Changes in v3:
* add a helper in scattered.c to get scattered leaf.
Changes in v2:
* add new macros for new AVX512 scattered features.
* add a cpuid_count_edx function to processor.h
---
arch/x86/events/intel/pt.c | 7 ------
arch/x86/include/asm/processor.h | 9 +++++++
arch/x86/kernel/cpu/scattered.c | 52 +++++++++++++++++++++++++++-------------
arch/x86/kvm/cpuid.c | 14 ++++++++++-
4 files changed, 57 insertions(+), 25 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index c5047b8..5b4b972 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);
static struct pt_pmu pt_pmu;
-enum cpuid_regs {
- CR_EAX = 0,
- CR_ECX,
- CR_EDX,
- CR_EBX
-};
-
/*
* Capabilities of Intel PT hardware, such as number of address bits or
* supported output schemes, are cached and exported to userspace as "caps"
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf..47978b7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -137,6 +137,13 @@ struct cpuinfo_x86 {
u32 microcode;
};
+enum cpuid_regs_idx {
+ CR_EAX = 0,
+ CR_ECX,
+ CR_EDX,
+ CR_EBX
+};
+
#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
#define X86_VENDOR_AMD 2
@@ -178,6 +185,8 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+ unsigned int sub_leaf, enum cpuid_regs_idx reg);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 1db8dc4..ca3c605 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,11 +17,17 @@ struct cpuid_bit {
u32 sub_leaf;
};
-enum cpuid_regs {
- CR_EAX = 0,
- CR_ECX,
- CR_EDX,
- CR_EBX
+/* Please keep the leaf sorted. */
+static const struct cpuid_bit cpuid_bits[] = {
+ { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
+ { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_INTEL_PT, CR_EBX, 25, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 },
+ { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
+ { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 },
+ { X86_FEATURE_PROC_FEEDBACK, CR_EDX, 11, 0x80000007, 0 },
+ { 0, 0, 0, 0, 0 }
};
void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
@@ -30,18 +36,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
u32 regs[4];
const struct cpuid_bit *cb;
- static const struct cpuid_bit cpuid_bits[] = {
- { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 },
- { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
- { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
- { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
- { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 },
- { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 },
- { 0, 0, 0, 0, 0 }
- };
-
for (cb = cpuid_bits; cb->feature; cb++) {
/* Verify that the level is valid */
@@ -57,3 +51,27 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
set_cpu_cap(c, cb->feature);
}
}
+
+u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
+ enum cpuid_regs_idx reg)
+{
+ u32 cpuid_val = 0;
+ const struct cpuid_bit *cb;
+
+ for (cb = cpuid_bits; cb->feature; cb++) {
+
+ if (level > cb->level)
+ continue;
+
+ if (level < cb->level)
+ break;
+
+ if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
+ if (cpu_has(&boot_cpu_data, cb->feature))
+ cpuid_val |= BIT(cb->bit);
+ }
+ }
+
+ return cpuid_val;
+}
+EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index afa7bbb..1f63011 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,7 @@
#include <linux/export.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <asm/processor.h>
#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */
#include <asm/user.h>
#include <asm/fpu/xstate.h>
@@ -65,6 +66,11 @@ u64 kvm_supported_xcr0(void)
#define F(x) bit(X86_FEATURE_##x)
+/* These are scattered features in cpufeatures.h. */
+#define KVM_CPUID_BIT_AVX512_4VNNIW 2
+#define KVM_CPUID_BIT_AVX512_4FMAPS 3
+#define KF(x) bit(KVM_CPUID_BIT_##x)
+
int kvm_update_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
@@ -376,6 +382,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.ecx*/
const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/;
+ /* cpuid 7.0.edx*/
+ const u32 kvm_cpuid_7_0_edx_x86_features =
+ KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS);
+
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -458,12 +468,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* PKU is not yet implemented for shadow paging. */
if (!tdp_enabled)
entry->ecx &= ~F(PKU);
+ entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+ entry->edx &= get_scattered_cpuid_leaf(7, 0, CR_EDX);
} else {
entry->ebx = 0;
entry->ecx = 0;
+ entry->edx = 0;
}
entry->eax = 0;
- entry->edx = 0;
break;
}
case 9:
--
2.7.4