KVM: nVMX/nSVM: Fix bug which sets vcpu->arch.tsc_offset to L1 tsc_offset

Since commit e79f245 ("X86/KVM: Properly update 'tsc_offset' to
represent the running guest"), vcpu->arch.tsc_offset meaning was
changed to always reflect the tsc_offset value set on active VMCS.
Regardless if vCPU is currently running L1 or L2.

However, above mentioned commit failed to also change
kvm_vcpu_write_tsc_offset() to set vcpu->arch.tsc_offset correctly.
This is because vmx_write_tsc_offset() could set the tsc_offset value
in active VMCS to given offset parameter *plus vmcs12->tsc_offset*.
However, kvm_vcpu_write_tsc_offset() just sets vcpu->arch.tsc_offset
to given offset parameter. Without taking into account the possible
addition of vmcs12->tsc_offset. (Same is true for SVM case).

Fix this issue by changing kvm_x86_ops->write_tsc_offset() to return
actually set tsc_offset in active VMCS and modify
kvm_vcpu_write_tsc_offset() to set returned value in
vcpu->arch.tsc_offset.
In addition, rename write_tsc_offset() callback to write_l1_tsc_offset()
to make it clear that it is meant to set L1 TSC offset.

Fixes: e79f245 ("X86/KVM: Properly update 'tsc_offset' to represent the running guest")
Reviewed-by: Liran Alon <[email protected]>
Reviewed-by: Mihai Carabas <[email protected]>
Reviewed-by: Krish Sadhukhan <[email protected]>
Signed-off-by: Leonid Shatz <[email protected]>
Cc: [email protected]
Signed-off-by: Paolo Bonzini <[email protected]>

Author: Leonid Shatz

arch/x86/include/asm/kvm_host.h

@@ -1094,7 +1094,8 @@ struct kvm_x86_ops {
 	bool (*has_wbinvd_exit)(void);
 
 	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
-	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+	/* Returns actual tsc_offset set in active VMCS */
+	u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 

arch/x86/kvm/svm.c

@@ -1446,7 +1446,7 @@ static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 	return vcpu->arch.tsc_offset;
 }
 
-static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;
@@ -1464,6 +1464,7 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
+	return svm->vmcb->control.tsc_offset;
 }
 
 static void avic_init_vmcb(struct vcpu_svm *svm)
@@ -7152,7 +7153,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
 	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
-	.write_tsc_offset = svm_write_tsc_offset,
+	.write_l1_tsc_offset = svm_write_l1_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
 

arch/x86/kvm/vmx.c

@@ -3464,29 +3464,26 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 	return vcpu->arch.tsc_offset;
 }
 
-/*
- * writes 'offset' into guest's timestamp counter offset register
- */
-static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
+	u64 active_offset = offset;
 	if (is_guest_mode(vcpu)) {
 		/*
 		 * We're here if L1 chose not to trap WRMSR to TSC. According
 		 * to the spec, this should set L1's TSC; The offset that L1
 		 * set for L2 remains unchanged, and still needs to be added
 		 * to the newly set TSC to get L2's TSC.
 		 */
-		struct vmcs12 *vmcs12;
-		/* recalculate vmcs02.TSC_OFFSET: */
-		vmcs12 = get_vmcs12(vcpu);
-		vmcs_write64(TSC_OFFSET, offset +
-			(nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ?
-			 vmcs12->tsc_offset : 0));
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING))
+			active_offset += vmcs12->tsc_offset;
 	} else {
 		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
 					   vmcs_read64(TSC_OFFSET), offset);
-		vmcs_write64(TSC_OFFSET, offset);
 	}
+
+	vmcs_write64(TSC_OFFSET, active_offset);
+	return active_offset;
 }
 
 /*
@@ -15074,7 +15071,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
 	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
-	.write_tsc_offset = vmx_write_tsc_offset,
+	.write_l1_tsc_offset = vmx_write_l1_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
 

arch/x86/kvm/x86.c

@@ -1665,8 +1665,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
 static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
-	kvm_x86_ops->write_tsc_offset(vcpu, offset);
-	vcpu->arch.tsc_offset = offset;
+	vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset);
 }
 
 static inline bool kvm_check_tsc_unstable(void)
@@ -1794,7 +1793,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
 					   s64 adjustment)
 {
-	kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment);
+	u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+	kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment);
 }
 
 static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)