[PATCH v4 29/30] x86/kvm: Obtain TSC frequency from CPUID if present

[David Woodhouse <dwmw2@xxxxxxxxxxxxx>]

From: David Woodhouse <dwmw@xxxxxxxxxxxx>

In https://lore.kernel.org/all/1222881242.9381.17.camel@alok-dev1/
a proposal was made for generic CPUID conventions across hypervisors.
It was mostly shot down in flames, but the leaf at 0x40000010
containing timing information didn't die.

It's used by XNU and FreeBSD guests under all hypervisors to determine
the TSC frequency, and also exposed by the EC2 Nitro hypervisor and
VMware. Use it under KVM to obtain the TSC frequency more accurately,
instead of reverse-calculating the frequency from the mul/shift values
in the KVM clock.

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
---
 arch/x86/include/asm/kvm_para.h      |  1 +
 arch/x86/include/uapi/asm/kvm_para.h | 11 +++++++++++
 arch/x86/kernel/kvm.c                | 10 ++++++++++
 arch/x86/kernel/kvmclock.c           |  7 ++++++-
 4 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 4a47c16e2df8..03fa1228fcf2 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -121,6 +121,7 @@ static inline long kvm_sev_hypercall3(unsigned int nr, 
unsigned long p1,
 void kvmclock_init(void);
 void kvmclock_disable(void);
 bool kvm_para_available(void);
+unsigned int kvm_para_tsc_khz(void);
 unsigned int kvm_arch_para_features(void);
 unsigned int kvm_arch_para_hints(void);
 void kvm_async_pf_task_wait_schedule(u32 token);
diff --git a/arch/x86/include/uapi/asm/kvm_para.h 
b/arch/x86/include/uapi/asm/kvm_para.h
index a1efa7907a0b..dc0d036fe678 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -44,6 +44,17 @@
  */
 #define KVM_FEATURE_CLOCKSOURCE_STABLE_BIT     24
 
+/*
+ * In https://lore.kernel.org/all/1222881242.9381.17.camel@alok-dev1/
+ * VMware proposed a timing information leaf providing the TSC and
+ * local APIC timer frequencies:
+ *
+ *  # EAX: (Virtual) TSC frequency in kHz.
+ *  # EBX: (Virtual) Bus (local apic timer) frequency in kHz.
+ *  # ECX, EDX: RESERVED (reserved fields are set to zero).
+ */
+#define KVM_CPUID_TIMING_INFO  0x40000010
+
 #define MSR_KVM_WALL_CLOCK  0x11
 #define MSR_KVM_SYSTEM_TIME 0x12
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 29226d112029..60375165b66c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -910,6 +910,16 @@ bool kvm_para_available(void)
 }
 EXPORT_SYMBOL_GPL(kvm_para_available);
 
+unsigned int kvm_para_tsc_khz(void)
+{
+       u32 base = kvm_cpuid_base();
+
+       if (base && cpuid_eax(base) >= (base | KVM_CPUID_TIMING_INFO))
+               return cpuid_eax(base | KVM_CPUID_TIMING_INFO);
+
+       return 0;
+}
+
 unsigned int kvm_arch_para_features(void)
 {
        return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index b5991d53fc0e..74aca22dc726 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -118,7 +118,12 @@ static inline void kvm_sched_clock_init(bool stable)
 static unsigned long kvm_get_tsc_khz(void)
 {
        setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-       return pvclock_tsc_khz(this_cpu_pvti());
+
+       /*
+        * If KVM advertises the frequency directly in CPUID, use that
+        * instead of reverse-calculating it from the KVM clock data.
+        */
+       return kvm_para_tsc_khz() ? : pvclock_tsc_khz(this_cpu_pvti());
 }
 
 static void __init kvm_get_preset_lpj(void)
-- 
2.51.0