KVM: SEV: Make AVIC backing, VMSA and VMCB memory allocation SNP safe

Implement a workaround for an SNP erratum where the CPU will incorrectly
signal an RMP violation #PF if a hugepage (2MB or 1GB) collides with the
RMP entry of a VMCB, VMSA or AVIC backing page.

When SEV-SNP is globally enabled, the CPU marks the VMCB, VMSA, and AVIC
backing pages as "in-use" via a reserved bit in the corresponding RMP
entry after a successful VMRUN. This is done for _all_ VMs, not just
SNP-Active VMs.

If the hypervisor accesses an in-use page through a writable
translation, the CPU will throw an RMP violation #PF. On early SNP
hardware, if an in-use page is 2MB-aligned and software accesses any
part of the associated 2MB region with a hugepage, the CPU will
incorrectly treat the entire 2MB region as in-use and signal a an RMP
violation #PF.

To avoid this, the recommendation is to not use a 2MB-aligned page for
the VMCB, VMSA or AVIC pages. Add a generic allocator that will ensure
that the page returned is not 2MB-aligned and is safe to be used when
SEV-SNP is enabled. Also implement similar handling for the VMCB/VMSA
pages of nested guests.

  [ mdr: Squash in nested guest handling from Ashish, commit msg fixups. ]

Reported-by: Alper Gun <alpergun@google.com> # for nested VMSA case
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Marc Orr <marcorr@google.com>
Signed-off-by: Marc Orr <marcorr@google.com>
Co-developed-by: Ashish Kalra <ashish.kalra@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20240126041126.1927228-22-michael.roth@amd.com

arch/x86/include/asm/kvm-x86-ops.h

@@ -138,6 +138,7 @@ KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
+KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL

arch/x86/include/asm/kvm_host.h

@@ -1794,6 +1794,7 @@ struct kvm_x86_ops {
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
 
 	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
+	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/lapic.c

@@ -2815,6 +2815,9 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 
 	vcpu->arch.apic = apic;
 
+	if (kvm_x86_ops.alloc_apic_backing_page)
+		apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu);
+	else
 		apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!apic->regs) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",

arch/x86/kvm/svm/nested.c

@@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm)
 	if (svm->nested.initialized)
 		return 0;
 
-	vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	vmcb02_page = snp_safe_alloc_page(&svm->vcpu);
 	if (!vmcb02_page)
 		return -ENOMEM;
 	svm->nested.vmcb02.ptr = page_address(vmcb02_page);

arch/x86/kvm/svm/sev.c

@@ -3163,3 +3163,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 
 	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
 }
+
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
+{
+	unsigned long pfn;
+	struct page *p;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+
+	/*
+	 * Allocate an SNP-safe page to workaround the SNP erratum where
+	 * the CPU will incorrectly signal an RMP violation #PF if a
+	 * hugepage (2MB or 1GB) collides with the RMP entry of a
+	 * 2MB-aligned VMCB, VMSA, or AVIC backing page.
+	 *
+	 * Allocate one extra page, choose a page which is not
+	 * 2MB-aligned, and free the other.
+	 */
+	p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+	if (!p)
+		return NULL;
+
+	split_page(p, 1);
+
+	pfn = page_to_pfn(p);
+	if (IS_ALIGNED(pfn, PTRS_PER_PMD))
+		__free_page(p++);
+	else
+		__free_page(p + 1);
+
+	return p;
+}

arch/x86/kvm/svm/svm.c

@@ -703,7 +703,7 @@ static int svm_cpu_init(int cpu)
 	int ret = -ENOMEM;
 
 	memset(sd, 0, sizeof(struct svm_cpu_data));
-	sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	sd->save_area = snp_safe_alloc_page(NULL);
 	if (!sd->save_area)
 		return ret;
 
@@ -1421,7 +1421,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 	svm = to_svm(vcpu);
 
 	err = -ENOMEM;
-	vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	vmcb01_page = snp_safe_alloc_page(vcpu);
 	if (!vmcb01_page)
 		goto out;
 
@@ -1430,7 +1430,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 		 * SEV-ES guests require a separate VMSA page used to contain
 		 * the encrypted register state of the guest.
 		 */
-		vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		vmsa_page = snp_safe_alloc_page(vcpu);
 		if (!vmsa_page)
 			goto error_free_vmcb_page;
 
@@ -4900,6 +4900,16 @@ static int svm_vm_init(struct kvm *kvm)
 	return 0;
 }
 
+static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
+{
+	struct page *page = snp_safe_alloc_page(vcpu);
+
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
 static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -5031,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
+	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
 };
 
 /*

arch/x86/kvm/svm/svm.h

@@ -694,6 +694,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm);
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa);
 void sev_es_unmap_ghcb(struct vcpu_svm *svm);
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
 
 /* vmenter.S */