[PATCH RFC v7 35/64] KVM: SVM: Make AVIC backing, VMSA and VMCB memory allocation SNP safe

From: Michael Roth <michael.roth@amd.com>
To: <kvm@vger.kernel.org>
Cc: <linux-coco@lists.linux.dev>, <linux-mm@kvack.org>,
	<linux-crypto@vger.kernel.org>, <x86@kernel.org>,
	<linux-kernel@vger.kernel.org>, <tglx@linutronix.de>,
	<mingo@redhat.com>, <jroedel@suse.de>, <thomas.lendacky@amd.com>,
	<hpa@zytor.com>, <ardb@kernel.org>, <pbonzini@redhat.com>,
	<seanjc@google.com>, <vkuznets@redhat.com>,
	<wanpengli@tencent.com>, <jmattson@google.com>, <luto@kernel.org>,
	<dave.hansen@linux.intel.com>, <slp@redhat.com>,
	<pgonda@google.com>, <peterz@infradead.org>,
	<srinivas.pandruvada@linux.intel.com>, <rientjes@google.com>,
	<dovmurik@linux.ibm.com>, <tobin@ibm.com>, <bp@alien8.de>,
	<vbabka@suse.cz>, <kirill@shutemov.name>, <ak@linux.intel.com>,
	<tony.luck@intel.com>, <marcorr@google.com>,
	<sathyanarayanan.kuppuswamy@linux.intel.com>,
	<alpergun@google.com>, <dgilbert@redhat.com>, <jarkko@kernel.org>,
	<ashish.kalra@amd.com>, <harald@profian.com>,
	Brijesh Singh <brijesh.singh@amd.com>
Subject: [PATCH RFC v7 35/64] KVM: SVM: Make AVIC backing, VMSA and VMCB memory allocation SNP safe
Date: Wed, 14 Dec 2022 13:40:27 -0600	[thread overview]
Message-ID: <20221214194056.161492-36-michael.roth@amd.com> (raw)
In-Reply-To: <20221214194056.161492-1-michael.roth@amd.com>

From: Brijesh Singh <brijesh.singh@amd.com>

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" in the RMP 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. 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.

Co-developed-by: Marc Orr <marcorr@google.com>
Signed-off-by: Marc Orr <marcorr@google.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  2 ++
 arch/x86/kvm/lapic.c               |  5 ++++-
 arch/x86/kvm/svm/sev.c             | 33 ++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c             | 15 ++++++++++++--
 arch/x86/kvm/svm/svm.h             |  1 +
 6 files changed, 54 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index c71df44b0f02..e0015926cdf4 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -131,6 +131,7 @@ KVM_X86_OP(msr_filter_changed)
 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(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(private_mem_enabled);
 KVM_X86_OP_OPTIONAL_RET0(fault_is_private);
 KVM_X86_OP_OPTIONAL_RET0(update_mem_attr)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9ef8d73455d9..e2529415f28b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1722,6 +1722,8 @@ struct kvm_x86_ops {
 	 * Returns vCPU specific APICv inhibit reasons
 	 */
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+	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 1bb63746e991..8500d1d54664 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2581,7 +2581,10 @@ 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/sev.c b/arch/x86/kvm/svm/sev.c
index 82ff96b4f04a..0e93b536dc34 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3234,6 +3234,39 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 	}
 }
 
+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;
+}
+
 int sev_fault_is_private(struct kvm *kvm, gpa_t gpa, u64 error_code, bool *private_fault)
 {
 	gfn_t gfn = gpa_to_gfn(gpa);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index fc7885869f7e..013f811c733c 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1360,7 +1360,7 @@ 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;
 
@@ -1369,7 +1369,7 @@ 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;
 
@@ -4694,6 +4694,16 @@ 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 int svm_private_mem_enabled(struct kvm *kvm)
 {
 	if (sev_guest(kvm))
@@ -4830,6 +4840,7 @@ 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,
 
 	.fault_is_private = sev_fault_is_private,
 };
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 1f3098dff3d5..ea9844546e8a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -684,6 +684,7 @@ 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);
 
 int sev_fault_is_private(struct kvm *kvm, gpa_t gpa, u64 error_code, bool *private_fault);
 
-- 
2.25.1

