From 6f5c9600621b4efb5c61b482d767432eb1ad3a9c Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Wed, 13 Mar 2024 13:58:42 +0100 Subject: KVM: x86: Don't advertise guest.MAXPHYADDR as host.MAXPHYADDR in CPUID Drop KVM's propagation of GuestPhysBits (CPUID leaf 80000008, EAX[23:16]) to HostPhysBits (same leaf, EAX[7:0]) when advertising the address widths to userspace via KVM_GET_SUPPORTED_CPUID. Per AMD, GuestPhysBits is intended for software use, and physical CPUs do not set that field. I.e. GuestPhysBits will be non-zero if and only if KVM is running as a nested hypervisor, and in that case, GuestPhysBits is NOT guaranteed to capture the CPU's effective MAXPHYADDR when running with TDP enabled. E.g. KVM will soon use GuestPhysBits to communicate the CPU's maximum *addressable* guest physical address, which would result in KVM under- reporting PhysBits when running as an L1 on a CPU with MAXPHYADDR=52, but without 5-level paging. Signed-off-by: Gerd Hoffmann Cc: stable@vger.kernel.org Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20240313125844.912415-2-kraxel@redhat.com [sean: rewrite changelog with --verbose, Cc stable@] Signed-off-by: Sean Christopherson --- arch/x86/kvm/cpuid.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'arch/x86/kvm/cpuid.c') diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bfc0bfcb2bc6..d1cbb14f8553 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1231,9 +1231,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1241,16 +1240,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) - g_phys_as = phys_as; + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + } else { + phys_as = entry->eax & 0xff; + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); -- cgit From b628cb523c65420031b310050a3733aa7fbe2e88 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Wed, 13 Mar 2024 13:58:43 +0100 Subject: KVM: x86: Advertise max mappable GPA in CPUID.0x80000008.GuestPhysBits Use the GuestPhysBits field in CPUID.0x80000008 to communicate the max mappable GPA to userspace, i.e. the max GPA that is addressable by the CPU itself. Typically this is identical to the max effective GPA, except in the case where the CPU supports MAXPHYADDR > 48 but does not support 5-level TDP (the CPU consults bits 51:48 of the GPA only when walking the fifth level TDP page table entry). Enumerating the max mappable GPA via CPUID will allow guest firmware to map resources like PCI bars in the highest possible address space, while ensuring that the GPA is addressable by the CPU. Without precise knowledge about the max mappable GPA, the guest must assume that 5-level paging is unsupported and thus restrict its mappings to the lower 48 bits. Advertise the max mappable GPA via KVM_GET_SUPPORTED_CPUID as userspace doesn't have easy access to whether or not 5-level paging is supported, and to play nice with userspace VMMs that reflect the supported CPUID directly into the guest. AMD's 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 above. Real hardware always returns zero. Leave GuestPhysBits as '0' when TDP is disabled in order to comply with the APM's statement that GuestPhysBits "applies only to guest using nested paging". As above, guest firmware will likely create suboptimal mappings, but that is a very minor issue and not a functional concern. Signed-off-by: Gerd Hoffmann Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20240313125844.912415-3-kraxel@redhat.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- arch/x86/kvm/cpuid.c | 28 +++++++++++++++++++++++++--- arch/x86/kvm/mmu.h | 2 ++ arch/x86/kvm/mmu/mmu.c | 5 +++++ 3 files changed, 32 insertions(+), 3 deletions(-) (limited to 'arch/x86/kvm/cpuid.c') diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d1cbb14f8553..1c5583addc90 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1231,8 +1231,22 @@ 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 @@ -1241,15 +1255,23 @@ 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 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/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 992e651540e8..db3a26eb7b75 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5322,6 +5322,11 @@ 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) -- cgit