Re: [PATCH v5 7/7] kvm, mem-hotplug: Unpin and remove nested_vmx->apic_access_page.

[Paolo Bonzini <pbonzini@redhat.com>]

Il 11/09/2014 07:38, Tang Chen ha scritto:
> Just like we removed kvm_arch->apic_access_page, nested_vmx->apic_access_page
> becomes useless for the same reason. This patch removes nested_vmx->apic_access_page,
> and use gfn_to_page() to pin it in memory when we need it, and unpin it after then.
> 
> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
> ---
>  arch/x86/kvm/vmx.c | 31 +++++++++----------------------
>  1 file changed, 9 insertions(+), 22 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 058c373..4aa73cb 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -374,11 +374,6 @@ struct nested_vmx {
>  	u64 vmcs01_tsc_offset;
>  	/* L2 must run next, and mustn't decide to exit to L1. */
>  	bool nested_run_pending;
> -	/*
> -	 * Guest pages referred to in vmcs02 with host-physical pointers, so
> -	 * we must keep them pinned while L2 runs.
> -	 */
> -	struct page *apic_access_page;
>  	u64 msr_ia32_feature_control;
>  
>  	struct hrtimer preemption_timer;
> @@ -6154,11 +6149,6 @@ static void free_nested(struct vcpu_vmx *vmx)
>  	nested_release_vmcs12(vmx);
>  	if (enable_shadow_vmcs)
>  		free_vmcs(vmx->nested.current_shadow_vmcs);
> -	/* Unpin physical memory we referred to in current vmcs02 */
> -	if (vmx->nested.apic_access_page) {
> -		nested_release_page(vmx->nested.apic_access_page);
> -		vmx->nested.apic_access_page = 0;
> -	}
>  
>  	nested_free_all_saved_vmcss(vmx);
>  }
> @@ -7983,28 +7973,31 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
>  			exec_control |= vmcs12->secondary_vm_exec_control;
>  
>  		if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) {
> +			struct page *page;
>  			/*
>  			 * Translate L1 physical address to host physical
>  			 * address for vmcs02. Keep the page pinned, so this
>  			 * physical address remains valid. We keep a reference
>  			 * to it so we can release it later.
>  			 */
> -			if (vmx->nested.apic_access_page) /* shouldn't happen */
> -				nested_release_page(vmx->nested.apic_access_page);
> -			vmx->nested.apic_access_page =
> -				nested_get_page(vcpu, vmcs12->apic_access_addr);
> +			page = nested_get_page(vcpu, vmcs12->apic_access_addr);
>  			/*
>  			 * If translation failed, no matter: This feature asks
>  			 * to exit when accessing the given address, and if it
>  			 * can never be accessed, this feature won't do
>  			 * anything anyway.
>  			 */
> -			if (!vmx->nested.apic_access_page)
> +			if (!page)
>  				exec_control &=
>  				  ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
>  			else
>  				vmcs_write64(APIC_ACCESS_ADDR,
> -				  page_to_phys(vmx->nested.apic_access_page));
> +					     page_to_phys(page));
> +			/*
> +			 * Do not pin nested vm's apic access page in memory so
> +			 * that memory hotplug process is able to migrate it.
> +			 */
> +			put_page(page);
>  		} else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) {
>  			struct page *page = gfn_to_page(vmx->vcpu.kvm,
>  				APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
> @@ -8807,12 +8800,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
>  	/* This is needed for same reason as it was needed in prepare_vmcs02 */
>  	vmx->host_rsp = 0;
>  
> -	/* Unpin physical memory we referred to in vmcs02 */
> -	if (vmx->nested.apic_access_page) {
> -		nested_release_page(vmx->nested.apic_access_page);
> -		vmx->nested.apic_access_page = 0;
> -	}
> -
>  	/*
>  	 * Do not call kvm_reload_apic_access_page() because we are now
>  	 * running, mmu_notifier will force to reload the page's hpa for L2
> 

This patch is not against the latest KVM tree.  The call to
nested_get_page is now in nested_get_vmcs12_pages, and you have to
handle virtual_apic_page in a similar manner.

Paolo