diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 114727cdcaed1841bc97d5ecf64afe86144bbbdf..de91c20fb080018108967c45abc7c6bb6bb76f6b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1267,8 +1267,22 @@ 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 (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1277,15 +1291,23 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * paging, too. * * If TDP is enabled, use the raw bare metal MAXPHYADDR as - * reductions to the HPAs do not affect GPAs. + * reductions to the HPAs do not 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). */ if (!tdp_enabled) { phys_as = boot_cpu_data.x86_phys_bits; + g_phys_as = 0; } else { 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); 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.h b/arch/x86/kvm/mmu.h index fb31db031470c64c0b3844a60d0876bf09e25102..51cc34a7042118c3f1269456340902169fca421c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -101,6 +101,8 @@ 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/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 61be1227e87abfa86e9c1827793629f39e2320c8..1abee3f522d293bef3578d6e5af4d303ce85fec8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5181,6 +5181,11 @@ 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) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 25bc61dac5fbe69bcc62195dde70ef53f56868b0..490a0a7efb3c4b7c7d389708a0d82d2127d44558 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -272,6 +272,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31) #define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7) #define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15) +#define X86_PROPERTY_GUEST_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) #define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index d8288374078e4b3ce888bed569c7e59192d43e7c..5a035bc2b9c1c0829ee23696b6d22b194565ee2a 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1248,9 +1248,20 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ unsigned long ht_gfn, max_gfn, max_pfn; - uint8_t maxphyaddr; + uint8_t maxphyaddr, guest_maxphyaddr; - max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; + /* + * Use "guest MAXPHYADDR" from KVM if it's available. Guest MAXPHYADDR + * enumerates the max _mappable_ GPA, which can be less than the raw + * MAXPHYADDR, e.g. if MAXPHYADDR=52, KVM is using TDP, and the CPU + * doesn't support 5-level TDP. + */ + guest_maxphyaddr = kvm_cpu_property(X86_PROPERTY_GUEST_MAX_PHY_ADDR); + guest_maxphyaddr = guest_maxphyaddr ?: vm->pa_bits; + TEST_ASSERT(guest_maxphyaddr <= vm->pa_bits, + "Guest MAXPHYADDR should never be greater than raw MAXPHYADDR"); + + max_gfn = (1ULL << (guest_maxphyaddr - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ if (!host_cpu_is_amd)