Re: [PATCH 1/2] X86/KVM: Properly update 'tsc_offset' to represent the running guest

[Raslan, KarimAllah]

On Fri, 2018-04-13 at 13:23 +0200, Paolo Bonzini wrote:
> From: KarimAllah Ahmed <karahmed@xxxxxxxxx>
> 
> Update 'tsc_offset' on vmenty/vmexit of L2 guests to ensure that it always
> captures the TSC_OFFSET of the running guest whether it is the L1 or L2
> guest.
> 
> Cc: Jim Mattson <jmattson@xxxxxxxxxx>
> Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
> Cc: kvm@xxxxxxxxxxxxxxx
> Cc: linux-kernel@xxxxxxxxxxxxxxx
> Suggested-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> Signed-off-by: KarimAllah Ahmed <karahmed@xxxxxxxxx>
> [AMD changes, fix update_ia32_tsc_adjust_msr. - Paolo]
> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> ---
>  arch/x86/include/asm/kvm_host.h |  1 +
>  arch/x86/kvm/svm.c              | 17 ++++++++++++++++-
>  arch/x86/kvm/vmx.c              | 25 ++++++++++++++++++++-----
>  arch/x86/kvm/x86.c              |  6 ++++--
>  4 files changed, 41 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 949c977bc4c9..c25775fad4ed 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1013,6 +1013,7 @@ 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);
>  
>  	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index b3ebc8ad6891..ea7c6d29aca5 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c

Thank you for adding the AMD bits, I did not have a machine to test the
AMD bits on so I left it untouched :)

> @@ -1424,12 +1424,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
>  	seg->base = 0;
>  }
>  
> +static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_svm *svm = to_svm(vcpu);
> +
> +	if (is_guest_mode(vcpu))
> +		return svm->nested.hsave->control.tsc_offset;
> +
> +	return vcpu->arch.tsc_offset;
> +}
> +
>  static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
>  {
>  	struct vcpu_svm *svm = to_svm(vcpu);
>  	u64 g_tsc_offset = 0;
>  
>  	if (is_guest_mode(vcpu)) {
> +		/* Write L1's TSC offset.  */
>  		g_tsc_offset = svm->vmcb->control.tsc_offset -
>  			       svm->nested.hsave->control.tsc_offset;
>  		svm->nested.hsave->control.tsc_offset = offset;
> @@ -3323,6 +3334,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
>  	/* Restore the original control entries */
>  	copy_vmcb_control_area(vmcb, hsave);
>  
> +	vcpu->arch.tsc_offset = svm->vmcb->control.tsc_offset;
>  	kvm_clear_exception_queue(&svm->vcpu);
>  	kvm_clear_interrupt_queue(&svm->vcpu);
>  
> @@ -3483,10 +3495,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
>  	/* We don't want to see VMMCALLs from a nested guest */
>  	clr_intercept(svm, INTERCEPT_VMMCALL);
>  
> +	vcpu->arch.tsc_offset += nested_vmcb->control.tsc_offset;
> +	svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset;
> +
>  	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
>  	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
>  	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
> -	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
>  	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
>  	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
>  
> @@ -7102,6 +7116,7 @@ static int svm_unregister_enc_region(struct kvm *kvm,
>  
>  	.has_wbinvd_exit = svm_has_wbinvd_exit,
>  
> +	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
>  	.write_tsc_offset = svm_write_tsc_offset,
>  
>  	.set_tdp_cr3 = set_tdp_cr3,
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index a13c603bdefb..6553419202ee 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -2874,6 +2874,17 @@ static void setup_msrs(struct vcpu_vmx *vmx)
>  		vmx_update_msr_bitmap(&vmx->vcpu);
>  }
>  
> +static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
> +{
> +	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
> +
> +	if (is_guest_mode(vcpu) &&
> +	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
> +		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
> +
> +	return vcpu->arch.tsc_offset;
> +}
> +
>  /*
>   * reads and returns guest's timestamp counter "register"
>   * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
> @@ -11175,11 +11186,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
>  		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
>  	}
>  
> -	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
> -		vmcs_write64(TSC_OFFSET,
> -			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
> -	else
> -		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
> +	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
> +
>  	if (kvm_has_tsc_control)
>  		decache_tsc_multiplier(vmx);
>  
> @@ -11489,6 +11497,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
>  	if (enable_shadow_vmcs)
>  		copy_shadow_to_vmcs12(vmx);
>  
> +	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
> +		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
> +
>  	/*
>  	 * The nested entry process starts with enforcing various prerequisites
>  	 * on vmcs12 as required by the Intel SDM, and act appropriately when
> @@ -12035,6 +12046,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
>  
>  	leave_guest_mode(vcpu);
>  
> +	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
> +		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
> +
>  	if (likely(!vmx->fail)) {
>  		if (exit_reason == -1)
>  			sync_vmcs12(vcpu, vmcs12);
> @@ -12725,6 +12739,7 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
>  
>  	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
>  
> +	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
>  	.write_tsc_offset = vmx_write_tsc_offset,
>  
>  	.set_tdp_cr3 = vmx_set_cr3,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 0334b250e102..3f3fba58c960 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1490,7 +1490,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
>  
>  static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
>  {
> -	u64 curr_offset = vcpu->arch.tsc_offset;
> +	u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);

I might be missing something but is this really strictly needed or is
it really a bug?

I can seeÂupdate_ia32_tsc_adjust_msrÂcalled fromÂkvm_write_tsc onlyÂ
which is called from a)Âvmx_set_msr or b)Âkvm_arch_vcpu_postcreate.
The adjust_msr would only be called if !host_initiated. So onlyÂ
vmx_set_msr which is coming from an L1 write (or a restore but that
would not be !host_initiated). So the only that tsc_adjust is called is
!is_guest_mode.

>  	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
>  }
>  
> @@ -1532,7 +1532,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
>  
>  u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
>  {
> -	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
> +	u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
> +
> +	return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
>  }
>  EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
>  
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B