Re: [PATCH v3 2/2] kvm/cpuid: set proper GuestPhysBits in CPUID.0x80000008

[Tao Su]

On Mon, Mar 11, 2024 at 11:41:17AM +0100, Gerd Hoffmann wrote:
> The AMD APM (3.35) defines GuestPhysBits (EAX[23:16]) as:
> 
>   Maximum guest physical address size in bits.  This number applies
>   only to guests using nested paging.  When this field is zero, refer
>   to the PhysAddrSize field for the maximum guest physical address size.
> 
> Tom Lendacky confirmed that the purpose of GuestPhysBits is software use
> and KVM can use it as described below.  Hardware always returns zero
> here.
> 
> Use the GuestPhysBits field to communicate the max addressable GPA to
> the guest.  Typically this is identical to the max effective GPA, except
> in case the CPU supports MAXPHYADDR > 48 but does not support 5-level
> TDP.
> 
> GuestPhysBits is set only in case TDP is enabled, otherwise it is left
> at zero.
> 
> GuestPhysBits will be used by the guest firmware to make sure resources
> like PCI bars are mapped into the addressable GPA.
> 
> Signed-off-by: Gerd Hoffmann <kraxel@xxxxxxxxxx>
> ---
>  arch/x86/kvm/mmu.h     |  2 ++
>  arch/x86/kvm/cpuid.c   | 31 +++++++++++++++++++++++++++++--
>  arch/x86/kvm/mmu/mmu.c |  5 +++++
>  3 files changed, 36 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
> index 60f21bb4c27b..b410a227c601 100644
> --- a/arch/x86/kvm/mmu.h
> +++ b/arch/x86/kvm/mmu.h
> @@ -100,6 +100,8 @@ static inline u8 kvm_get_shadow_phys_bits(void)
>  	return boot_cpu_data.x86_phys_bits;
>  }
>  
> +u8 kvm_mmu_get_max_tdp_level(void);
> +
>  void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
>  void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
>  void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index c638b5fb2144..cd627dead9ce 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -1221,8 +1221,22 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
>  		entry->eax = entry->ebx = entry->ecx = 0;
>  		break;
>  	case 0x80000008: {
> +		/*
> +		 * GuestPhysAddrSize (EAX[23:16]) is intended for software
> +		 * use.
> +		 *
> +		 * KVM's ABI is to report the effective MAXPHYADDR for the
> +		 * guest in PhysAddrSize (phys_as), and the maximum
> +		 * *addressable* GPA in GuestPhysAddrSize (g_phys_as).
> +		 *
> +		 * GuestPhysAddrSize is valid if and only if TDP is enabled,
> +		 * in which case the max GPA that can be addressed by KVM may
> +		 * be less than the max GPA that can be legally generated by
> +		 * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't
> +		 * support 5-level TDP.
> +		 */
>  		unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U);
> -		unsigned int phys_as;
> +		unsigned int phys_as, g_phys_as;
>  
>  		if (!tdp_enabled) {
>  			/*
> @@ -1232,11 +1246,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
>  			 * for memory encryption affect shadow paging, too.
>  			 */
>  			phys_as = boot_cpu_data.x86_phys_bits;
> +			g_phys_as = 0;
>  		} else {
> +			/*
> +			 * If TDP is enabled, the effective guest MAXPHYADDR
> +			 * is the same as the raw bare metal MAXPHYADDR, as
> +			 * reductions to HPAs don't affect GPAs.  The max
> +			 * addressable GPA is the same as the max effective
> +			 * GPA, except that it's capped at 48 bits if 5-level
> +			 * TDP isn't supported (hardware processes bits 51:48
> +			 * only when walking the fifth level page table).
> +			 */
>  			phys_as = entry->eax & 0xff;
> +			g_phys_as = phys_as;
> +			if (kvm_mmu_get_max_tdp_level() < 5)
> +				g_phys_as = min(g_phys_as, 48);
>  		}
>  
> -		entry->eax = phys_as | (virt_as << 8);
> +		entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16);

When g_phys_as==phys_as, I would suggest advertising g_phys_as==0,
otherwise application can easily know whether it is in a VM, I’m
concerned this could be abused by application.

>  		entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
>  		entry->edx = 0;
>  		cpuid_entry_override(entry, CPUID_8000_0008_EBX);
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 2d6cdeab1f8a..ffd32400fd8c 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -5267,6 +5267,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
>  	return max_tdp_level;
>  }
>  
> +u8 kvm_mmu_get_max_tdp_level(void)
> +{
> +	return tdp_root_level ? tdp_root_level : max_tdp_level;
> +}
> +
>  static union kvm_mmu_page_role
>  kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
>  				union kvm_cpu_role cpu_role)
> -- 
> 2.44.0
> 
>