KVM: x86: Add support for "protected VMs" that can utilize private memory

Add a new x86 VM type, KVM_X86_SW_PROTECTED_VM, to serve as a development
and testing vehicle for Confidential (CoCo) VMs, and potentially to even
become a "real" product in the distant future, e.g. a la pKVM.

The private memory support in KVM x86 is aimed at AMD's SEV-SNP and
Intel's TDX, but those technologies are extremely complex (understatement),
difficult to debug, don't support running as nested guests, and require
hardware that's isn't universally accessible.  I.e. relying SEV-SNP or TDX
for maintaining guest private memory isn't a realistic option.

At the very least, KVM_X86_SW_PROTECTED_VM will enable a variety of
selftests for guest_memfd and private memory support without requiring
unique hardware.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20231027182217.3615211-24-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 40 insertions, 7 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 75ab0da06e64..a565a2e70f30 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1255,6 +1255,7 @@ enum kvm_apicv_inhibit {
 };
 
 struct kvm_arch {
+	unsigned long vm_type;
 	unsigned long n_used_mmu_pages;
 	unsigned long n_requested_mmu_pages;
 	unsigned long n_max_mmu_pages;
@@ -2089,6 +2090,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
 void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 		       int tdp_max_root_level, int tdp_huge_page_level);
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
 static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
@@ -2137,14 +2144,10 @@ enum {
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
 # define KVM_MAX_NR_ADDRESS_SPACES	2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
-
-static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
-{
-	return KVM_MAX_NR_ADDRESS_SPACES;
-}
-
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index e61383674c75..c1716e83d176 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -77,6 +77,18 @@ config KVM_WERROR
 
 	  If in doubt, say "N".
 
+config KVM_SW_PROTECTED_VM
+	bool "Enable support for KVM software-protected VMs"
+	depends on EXPERT
+	depends on X86_64
+	select KVM_GENERIC_PRIVATE_MEM
+	help
+	  Enable support for KVM software-protected VMs.  Currently "protected"
+	  means the VM can be backed with memory provided by
+	  KVM_CREATE_GUEST_MEMFD.
+
+	  If unsure, say "N".
+
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 86c7cb692786..b66a7d47e0e4 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -297,6 +297,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
+		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
 	};
 	int r;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f521c97f5c64..6d0772b47041 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4548,6 +4548,13 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool kvm_is_vm_type_supported(unsigned long type)
+{
+	return type == KVM_X86_DEFAULT_VM ||
+	       (type == KVM_X86_SW_PROTECTED_VM &&
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -4739,6 +4746,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_X86_NOTIFY_VMEXIT:
 		r = kvm_caps.has_notify_vmexit;
 		break;
+	case KVM_CAP_VM_TYPES:
+		r = BIT(KVM_X86_DEFAULT_VM);
+		if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
+			r |= BIT(KVM_X86_SW_PROTECTED_VM);
+		break;
 	default:
 		break;
 	}
@@ -12436,9 +12448,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	int ret;
 	unsigned long flags;
 
-	if (type)
+	if (!kvm_is_vm_type_supported(type))
 		return -EINVAL;
 
+	kvm->arch.vm_type = type;
+
 	ret = kvm_page_track_init(kvm);
 	if (ret)
 		goto out;