[PATCH Part2 v5 28/45] KVM: X86: Keep the NPT and RMP page level in sync

[Brijesh Singh]

When running an SEV-SNP VM, the sPA used to index the RMP entry is
obtained through the NPT translation (gva->gpa->spa). The NPT page
level is checked against the page level programmed in the RMP entry.
If the page level does not match, then it will cause a nested page
fault with the RMP bit set to indicate the RMP violation.

Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  2 ++
 arch/x86/kvm/mmu/mmu.c             |  5 ++++
 arch/x86/kvm/svm/sev.c             | 46 ++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c             |  1 +
 arch/x86/kvm/svm/svm.h             |  1 +
 6 files changed, 56 insertions(+)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 36a9c23a4b27..371756c7f8f4 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -123,6 +123,7 @@ KVM_X86_OP_NULL(migrate_timers)
 KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP_NULL(complete_emulated_msr)
 KVM_X86_OP(alloc_apic_backing_page)
+KVM_X86_OP_NULL(rmp_page_level_adjust)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_NULL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5ad6255ff5d5..109e80167f11 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1453,7 +1453,9 @@ struct kvm_x86_ops {
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
+	void (*rmp_page_level_adjust)(struct kvm *kvm, kvm_pfn_t pfn, int *level);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 66f7f5bc3482..f9aaf6e1e51e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -43,6 +43,7 @@
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
 #include <linux/kthread.h>
+#include <linux/sev.h>
 
 #include <asm/page.h>
 #include <asm/memtype.h>
@@ -2818,6 +2819,10 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 	if (unlikely(!pte))
 		return PG_LEVEL_4K;
 
+	/* Adjust the page level based on the SEV-SNP RMP page level. */
+	if (kvm_x86_ops.rmp_page_level_adjust)
+		static_call(kvm_x86_rmp_page_level_adjust)(kvm, pfn, &level);
+
 	return level;
 }
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 248096a5c307..2ad186d7e7b0 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3231,3 +3231,49 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 
 	return pfn_to_page(pfn);
 }
+
+static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)
+{
+	int level;
+
+	while (end > start) {
+		if (snp_lookup_rmpentry(start, &level) != 0)
+			return false;
+		start++;
+	}
+
+	return true;
+}
+
+void sev_rmp_page_level_adjust(struct kvm *kvm, kvm_pfn_t pfn, int *level)
+{
+	int rmp_level, assigned;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return;
+
+	assigned = snp_lookup_rmpentry(pfn, &rmp_level);
+	if (unlikely(assigned < 0))
+		return;
+
+	if (!assigned) {
+		/*
+		 * If all the pages are shared then no need to keep the RMP
+		 * and NPT in sync.
+		 */
+		pfn = pfn & ~(PTRS_PER_PMD - 1);
+		if (is_pfn_range_shared(pfn, pfn + PTRS_PER_PMD))
+			return;
+	}
+
+	/*
+	 * The hardware installs 2MB TLB entries to access to 1GB pages,
+	 * therefore allow NPT to use 1GB pages when pfn was added as 2MB
+	 * in the RMP table.
+	 */
+	if (rmp_level == PG_LEVEL_2M && (*level == PG_LEVEL_1G))
+		return;
+
+	/* Adjust the level to keep the NPT and RMP in sync */
+	*level = min_t(size_t, *level, rmp_level);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 058eea8353c9..0c8510ad63f1 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4679,6 +4679,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
+	.rmp_page_level_adjust = sev_rmp_page_level_adjust,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 85417c44812d..27c0c7b265b8 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -589,6 +589,7 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu);
 void sev_es_unmap_ghcb(struct vcpu_svm *svm);
 struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
+void sev_rmp_page_level_adjust(struct kvm *kvm, kvm_pfn_t pfn, int *level);
 
 /* vmenter.S */
 
-- 
2.17.1