KVM: x86: Expose TSC offset controls to userspace

To date, VMM-directed TSC synchronization and migration has been a bit
messy. KVM has some baked-in heuristics around TSC writes to infer if
the VMM is attempting to synchronize. This is problematic, as it depends
on host userspace writing to the guest's TSC within 1 second of the last
write.

A much cleaner approach to configuring the guest's views of the TSC is to
simply migrate the TSC offset for every vCPU. Offsets are idempotent,
and thus not subject to change depending on when the VMM actually
reads/writes values from/to KVM. The VMM can then read the TSC once with
KVM_GET_CLOCK to capture a (realtime, host_tsc) pair at the instant when
the guest is paused.

Cc: David Matlack <dmatlack@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210916181538.968978-8-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 121 insertions, 0 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 68ac06fef4fa..88f0326c184a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1095,6 +1095,7 @@ struct kvm_arch {
 	u64 last_tsc_nsec;
 	u64 last_tsc_write;
 	u32 last_tsc_khz;
+	u64 last_tsc_offset;
 	u64 cur_tsc_nsec;
 	u64 cur_tsc_write;
 	u64 cur_tsc_offset;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 2ef1f6513c68..5a776a08f78c 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -504,4 +504,8 @@ struct kvm_pmu_event_filter {
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
+/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
+#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
+#define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c74a44f2a38c..afdc5d186c50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2454,6 +2454,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 	kvm->arch.last_tsc_nsec = ns;
 	kvm->arch.last_tsc_write = tsc;
 	kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
+	kvm->arch.last_tsc_offset = offset;
 
 	vcpu->arch.last_guest_tsc = tsc;
 
@@ -4054,6 +4055,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
 	case KVM_CAP_SREGS2:
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
+	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
@@ -4918,6 +4920,115 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int r;
+
+	switch (attr->attr) {
+	case KVM_VCPU_TSC_OFFSET:
+		r = 0;
+		break;
+	default:
+		r = -ENXIO;
+	}
+
+	return r;
+}
+
+static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr;
+	int r;
+
+	if ((u64)(unsigned long)uaddr != attr->addr)
+		return -EFAULT;
+
+	switch (attr->attr) {
+	case KVM_VCPU_TSC_OFFSET:
+		r = -EFAULT;
+		if (put_user(vcpu->arch.l1_tsc_offset, uaddr))
+			break;
+		r = 0;
+		break;
+	default:
+		r = -ENXIO;
+	}
+
+	return r;
+}
+
+static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr;
+	struct kvm *kvm = vcpu->kvm;
+	int r;
+
+	if ((u64)(unsigned long)uaddr != attr->addr)
+		return -EFAULT;
+
+	switch (attr->attr) {
+	case KVM_VCPU_TSC_OFFSET: {
+		u64 offset, tsc, ns;
+		unsigned long flags;
+		bool matched;
+
+		r = -EFAULT;
+		if (get_user(offset, uaddr))
+			break;
+
+		raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
+
+		matched = (vcpu->arch.virtual_tsc_khz &&
+			   kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz &&
+			   kvm->arch.last_tsc_offset == offset);
+
+		tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset;
+		ns = get_kvmclock_base_ns();
+
+		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched);
+		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+
+		r = 0;
+		break;
+	}
+	default:
+		r = -ENXIO;
+	}
+
+	return r;
+}
+
+static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu,
+				      unsigned int ioctl,
+				      void __user *argp)
+{
+	struct kvm_device_attr attr;
+	int r;
+
+	if (copy_from_user(&attr, argp, sizeof(attr)))
+		return -EFAULT;
+
+	if (attr.group != KVM_VCPU_TSC_CTRL)
+		return -ENXIO;
+
+	switch (ioctl) {
+	case KVM_HAS_DEVICE_ATTR:
+		r = kvm_arch_tsc_has_attr(vcpu, &attr);
+		break;
+	case KVM_GET_DEVICE_ATTR:
+		r = kvm_arch_tsc_get_attr(vcpu, &attr);
+		break;
+	case KVM_SET_DEVICE_ATTR:
+		r = kvm_arch_tsc_set_attr(vcpu, &attr);
+		break;
+	}
+
+	return r;
+}
+
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				     struct kvm_enable_cap *cap)
 {
@@ -5372,6 +5483,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = __set_sregs2(vcpu, u.sregs2);
 		break;
 	}
+	case KVM_HAS_DEVICE_ATTR:
+	case KVM_GET_DEVICE_ATTR:
+	case KVM_SET_DEVICE_ATTR:
+		r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp);
+		break;
 	default:
 		r = -EINVAL;
 	}