KVM: X86: Delegate tsc-offset calculation to architecture code

With TSC scaling in SVM the tsc-offset needs to be
calculated differently. This patch propagates this
calculation into the architecture specific modules so that
this complexity can be handled there.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -609,6 +609,8 @@ struct kvm_x86_ops {
 	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
+	u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
+
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 
 	int (*check_intercept)(struct kvm_vcpu *vcpu,

arch/x86/kvm/svm.c

@@ -943,6 +943,15 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
+static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
+{
+	u64 tsc;
+
+	tsc = svm_scale_tsc(vcpu, native_read_tsc());
+
+	return target_tsc - tsc;
+}
+
 static void init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -4194,6 +4203,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_tsc_khz = svm_set_tsc_khz,
 	.write_tsc_offset = svm_write_tsc_offset,
 	.adjust_tsc_offset = svm_adjust_tsc_offset,
+	.compute_tsc_offset = svm_compute_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
 

arch/x86/kvm/vmx.c

@@ -1184,6 +1184,11 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
 	vmcs_write64(TSC_OFFSET, offset + adjustment);
 }
 
+static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
+{
+	return target_tsc - native_read_tsc();
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -4510,6 +4515,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.set_tsc_khz = vmx_set_tsc_khz,
 	.write_tsc_offset = vmx_write_tsc_offset,
 	.adjust_tsc_offset = vmx_adjust_tsc_offset,
+	.compute_tsc_offset = vmx_compute_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
 

arch/x86/kvm/x86.c

@@ -977,7 +977,7 @@ static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu)
 		return __this_cpu_read(cpu_tsc_khz);
 }
 
-static inline u64 nsec_to_cycles(u64 nsec)
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 {
 	u64 ret;
 
@@ -985,7 +985,7 @@ static inline u64 nsec_to_cycles(u64 nsec)
 	if (kvm_tsc_changes_freq())
 		printk_once(KERN_WARNING
 		 "kvm: unreliable cycle conversion on adjustable rate TSC\n");
-	ret = nsec * __this_cpu_read(cpu_tsc_khz);
+	ret = nsec * vcpu_tsc_khz(vcpu);
 	do_div(ret, USEC_PER_SEC);
 	return ret;
 }
@@ -1015,7 +1015,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 	s64 sdiff;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
-	offset = data - native_read_tsc();
+	offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
 	ns = get_kernel_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 	sdiff = data - kvm->arch.last_tsc_write;
@@ -1031,13 +1031,13 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 	 * In that case, for a reliable TSC, we can match TSC offsets,
 	 * or make a best guest using elapsed value.
 	 */
-	if (sdiff < nsec_to_cycles(5ULL * NSEC_PER_SEC) &&
+	if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) &&
 	    elapsed < 5ULL * NSEC_PER_SEC) {
 		if (!check_tsc_unstable()) {
 			offset = kvm->arch.last_tsc_offset;
 			pr_debug("kvm: matched tsc offset for %llu\n", data);
 		} else {
-			u64 delta = nsec_to_cycles(elapsed);
+			u64 delta = nsec_to_cycles(vcpu, elapsed);
 			offset += delta;
 			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}