From 12a1dc374259e82efd19b930bfaf50ecb5ba9800 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 21 Jul 2025 14:56:50 -0700 Subject: [PATCH 13/23] KVM: x86/mmu: Extend guest_memfd's max mapping level to shared mappings Rework kvm_mmu_max_mapping_level() to consult guest_memfd for all mappings, not just private mappings, so that hugepage support plays nice with the upcoming support for backing non-private memory with guest_memfd. In addition to getting the max order from guest_memfd for gmem-only memslots, update TDX's hook to effectively ignore shared mappings, as TDX's restrictions on page size only apply to Secure EPT mappings. Do nothing for SNP, as RMP restrictions apply to both private and shared memory. Suggested-by: Ackerley Tng Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu/mmu.c | 12 +++++++----- arch/x86/kvm/svm/sev.c | 2 +- arch/x86/kvm/svm/svm.h | 4 ++-- arch/x86/kvm/vmx/main.c | 7 ++++--- arch/x86/kvm/vmx/tdx.c | 5 ++++- arch/x86/kvm/vmx/x86_ops.h | 2 +- 7 files changed, 20 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1569520e84d2..ae36973f48a6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1907,7 +1907,7 @@ struct kvm_x86_ops { void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); - int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn); + int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); }; struct kvm_x86_nested_ops { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1ff7582d5fae..2d1894ed1623 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3275,8 +3275,9 @@ static u8 kvm_max_level_for_order(int order) return PG_LEVEL_4K; } -static u8 kvm_max_private_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, - const struct kvm_memory_slot *slot, gfn_t gfn) +static u8 kvm_gmem_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, + const struct kvm_memory_slot *slot, gfn_t gfn, + bool is_private) { struct page *page; kvm_pfn_t pfn; @@ -3305,7 +3306,7 @@ static u8 kvm_max_private_mapping_level(struct kvm *kvm, struct kvm_page_fault * return max_level; return min(max_level, - kvm_x86_call(gmem_max_mapping_level)(kvm, pfn)); + kvm_x86_call(gmem_max_mapping_level)(kvm, pfn, is_private)); } int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, @@ -3335,8 +3336,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; - if (is_private) - host_level = kvm_max_private_mapping_level(kvm, fault, slot, gfn); + if (is_private || kvm_memslot_is_gmem_only(slot)) + host_level = kvm_gmem_max_mapping_level(kvm, fault, slot, gfn, + is_private); else host_level = host_pfn_mapping_level(kvm, gfn, slot); return min(host_level, max_level); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 81974ae2bc8c..c28cf72aa7aa 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -4906,7 +4906,7 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) } } -int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) { int level, rc; bool assigned; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index bd7445e0b521..118266bfa46b 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -787,7 +787,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code); void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu); int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); -int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); +int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu); void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa); #else @@ -816,7 +816,7 @@ static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, in return 0; } static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {} -static inline int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +static inline int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) { return 0; } diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 0c5b66edbf49..1deeca587b39 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -871,10 +871,11 @@ static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp) return tdx_vcpu_ioctl(vcpu, argp); } -static int vt_gmem_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +static int vt_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, + bool is_private) { if (is_td(kvm)) - return tdx_gmem_gmem_max_mapping_level(kvm, pfn); + return tdx_gmem_max_mapping_level(kvm, pfn, is_private); return 0; } @@ -1044,7 +1045,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl), .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl), - .gmem_max_mapping_level = vt_op_tdx_only(gmem_gmem_max_mapping_level) + .gmem_max_mapping_level = vt_op_tdx_only(gmem_max_mapping_level) }; struct kvm_x86_init_ops vt_init_ops __initdata = { diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index d867a210eba0..4a1f2c4bdb66 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -3322,8 +3322,11 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) return ret; } -int tdx_gmem_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +int tdx_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) { + if (!is_private) + return 0; + return PG_LEVEL_4K; } diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 26c6de3d775c..520d12c304d3 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -163,7 +163,7 @@ int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, void tdx_flush_tlb_current(struct kvm_vcpu *vcpu); void tdx_flush_tlb_all(struct kvm_vcpu *vcpu); void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); -int tdx_gmem_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); +int tdx_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); #endif #endif /* __KVM_X86_VMX_X86_OPS_H */ -- 2.50.0.727.gbf7dc18ff4-goog