[PATCH RFC v9 26/51] KVM: SVM: Make AVIC backing, VMSA and VMCB memory allocation SNP safe

[Michael Roth]

From: Brijesh Singh <brijesh.singh@xxxxxxx>

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 hupage, the CPU will
incorrectly treat the entire 2mb region as in-use and signal a spurious
RMP violation #PF.

The recommended is to not use the hugepage for the VMCB, VMSA or
AVIC backing page for similar reasons. Add a generic allocator that will
ensure that the page returns is not hugepage (2mb or 1gb) and is safe to
be used when SEV-SNP is enabled. Also implement similar handling for the
VMCB/VMSA pages of nested guests.

Co-developed-by: Marc Orr <marcorr@xxxxxxxxxx>
Signed-off-by: Marc Orr <marcorr@xxxxxxxxxx>
Reported-by: Alper Gun <alpergun@xxxxxxxxxx> # for nested VMSA case
Co-developed-by: Ashish Kalra <ashish.kalra@xxxxxxx>
Signed-off-by: Ashish Kalra <ashish.kalra@xxxxxxx>
Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
[mdr: squash in nested guest handling from Ashish]
Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/lapic.c               |  5 ++++-
 arch/x86/kvm/svm/nested.c          |  2 +-
 arch/x86/kvm/svm/sev.c             | 33 ++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c             | 17 ++++++++++++---
 arch/x86/kvm/svm/svm.h             |  1 +
 7 files changed, 55 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 48f043de2ec0..28456b497198 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -135,6 +135,7 @@ KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
 KVM_X86_OP_OPTIONAL(gmem_invalidate)
+KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c26f76641121..8d2bb3ff66a2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1743,6 +1743,7 @@ struct kvm_x86_ops {
 	int (*gmem_prepare)(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    kvm_pfn_t pfn, gfn_t gfn, u8 *max_level);
 	void (*gmem_invalidate)(struct kvm *kvm, kvm_pfn_t start, kvm_pfn_t end);
+	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e542cf285b51..94311938651a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2769,7 +2769,10 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 
 	vcpu->arch.apic = apic;
 
-	apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+	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",
 		       vcpu->vcpu_id);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 96936ddf1b3c..fb981c8b82c4 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1185,7 +1185,7 @@ 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);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2bceb0060880..69b57e8f0a7f 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3104,3 +3104,36 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 		break;
 	}
 }
+
+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 VMCB, VMSA
+	 * or AVIC backing page. The recommeded workaround is to not use the
+	 * hugepage.
+	 *
+	 * Allocate one extra page, use 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;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index eb308c9994f9..065167b42f90 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -668,7 +668,7 @@ 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;
 
@@ -1381,7 +1381,7 @@ 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;
 
@@ -1390,7 +1390,7 @@ 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;
 
@@ -4770,6 +4770,16 @@ 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,
 
@@ -4900,6 +4910,7 @@ 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,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 1ab117daebd9..e45b54e95495 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -741,6 +741,7 @@ 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 */
 
-- 
2.25.1