[PATCH v5 05/34] KVM: SVM: Add support for the SEV-ES VMSA

[Tom Lendacky <thomas.lendacky@amd.com>]

From: Tom Lendacky <thomas.lendacky@amd.com>

Allocate a page during vCPU creation to be used as the encrypted VM save
area (VMSA) for the SEV-ES guest. Provide a flag in the kvm_vcpu_arch
structure that indicates whether the guest state is protected.

When freeing a VMSA page that has been encrypted, the cache contents must
be flushed using the MSR_AMD64_VM_PAGE_FLUSH before freeing the page.

[ i386 build warnings ]
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
 arch/x86/include/asm/kvm_host.h |  3 ++
 arch/x86/kvm/svm/sev.c          | 67 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          | 24 +++++++++++-
 arch/x86/kvm/svm/svm.h          |  5 +++
 4 files changed, 97 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f002cdb13a0b..8cf6b0493d49 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -805,6 +805,9 @@ struct kvm_vcpu_arch {
 		 */
 		bool enforce;
 	} pv_cpuid;
+
+	/* Protected Guests */
+	bool guest_state_protected;
 };
 
 struct kvm_lpage_info {
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 9bf5e9dadff5..fb4a411f7550 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -14,6 +14,7 @@
 #include <linux/psp-sev.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/processor.h>
 
 #include "x86.h"
 #include "svm.h"
@@ -1190,6 +1191,72 @@ void sev_hardware_teardown(void)
 	sev_flush_asids();
 }
 
+/*
+ * Pages used by hardware to hold guest encrypted state must be flushed before
+ * returning them to the system.
+ */
+static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
+				   unsigned long len)
+{
+	/*
+	 * If hardware enforced cache coherency for encrypted mappings of the
+	 * same physical page is supported, nothing to do.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SME_COHERENT))
+		return;
+
+	/*
+	 * If the VM Page Flush MSR is supported, use it to flush the page
+	 * (using the page virtual address and the guest ASID).
+	 */
+	if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) {
+		struct kvm_sev_info *sev;
+		unsigned long va_start;
+		u64 start, stop;
+
+		/* Align start and stop to page boundaries. */
+		va_start = (unsigned long)va;
+		start = (u64)va_start & PAGE_MASK;
+		stop = PAGE_ALIGN((u64)va_start + len);
+
+		if (start < stop) {
+			sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+
+			while (start < stop) {
+				wrmsrl(MSR_AMD64_VM_PAGE_FLUSH,
+				       start | sev->asid);
+
+				start += PAGE_SIZE;
+			}
+
+			return;
+		}
+
+		WARN(1, "Address overflow, using WBINVD\n");
+	}
+
+	/*
+	 * Hardware should always have one of the above features,
+	 * but if not, use WBINVD and issue a warning.
+	 */
+	WARN_ONCE(1, "Using WBINVD to flush guest memory\n");
+	wbinvd_on_all_cpus();
+}
+
+void sev_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm;
+
+	if (!sev_es_guest(vcpu->kvm))
+		return;
+
+	svm = to_svm(vcpu);
+
+	if (vcpu->arch.guest_state_protected)
+		sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
+	__free_page(virt_to_page(svm->vmsa));
+}
+
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a1ea30c98629..cd4c9884e5a8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1289,6 +1289,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
 	struct page *vmcb_page;
+	struct page *vmsa_page = NULL;
 	int err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
@@ -1299,9 +1300,19 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	if (!vmcb_page)
 		goto out;
 
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		/*
+		 * 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);
+		if (!vmsa_page)
+			goto error_free_vmcb_page;
+	}
+
 	err = avic_init_vcpu(svm);
 	if (err)
-		goto error_free_vmcb_page;
+		goto error_free_vmsa_page;
 
 	/* We initialize this flag to true to make sure that the is_running
 	 * bit would be set the first time the vcpu is loaded.
@@ -1311,12 +1322,16 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm)
-		goto error_free_vmcb_page;
+		goto error_free_vmsa_page;
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
 	svm->vmcb = page_address(vmcb_page);
 	svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
+
+	if (vmsa_page)
+		svm->vmsa = page_address(vmsa_page);
+
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
@@ -1325,6 +1340,9 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 
 	return 0;
 
+error_free_vmsa_page:
+	if (vmsa_page)
+		__free_page(vmsa_page);
 error_free_vmcb_page:
 	__free_page(vmcb_page);
 out:
@@ -1352,6 +1370,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 
 	svm_free_nested(svm);
 
+	sev_free_vcpu(vcpu);
+
 	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 56d950df82e5..80a359f3cf20 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -168,6 +168,10 @@ struct vcpu_svm {
 		DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
 		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
 	} shadow_msr_intercept;
+
+	/* SEV-ES support */
+	struct vmcb_save_area *vmsa;
+	struct ghcb *ghcb;
 };
 
 struct svm_cpu_data {
@@ -513,5 +517,6 @@ int svm_unregister_enc_region(struct kvm *kvm,
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 void __init sev_hardware_setup(void);
 void sev_hardware_teardown(void);
+void sev_free_vcpu(struct kvm_vcpu *vcpu);
 
 #endif
-- 
2.28.0