[PATCH RFC v7 41/64] KVM: X86: Keep the NPT and RMP page level in sync

[Michael Roth]

From: Brijesh Singh <brijesh.singh@xxxxxxx>

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.

Co-developed-by: Michael Roth <michael.roth@xxxxxxx>
Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
Signed-off-by: Jarkko Sakkinen <jarkko@xxxxxxxxxxx>
Signed-off-by: Ashish Kalra <Ashish.Kalra@xxxxxxx>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  2 +
 arch/x86/kvm/mmu/mmu.c             | 12 +++++-
 arch/x86/kvm/svm/sev.c             | 66 ++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c             |  2 +
 arch/x86/kvm/svm/svm.h             |  1 +
 6 files changed, 83 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index e0015926cdf4..61e31b622fce 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -136,6 +136,7 @@ KVM_X86_OP_OPTIONAL_RET0(private_mem_enabled);
 KVM_X86_OP_OPTIONAL_RET0(fault_is_private);
 KVM_X86_OP_OPTIONAL_RET0(update_mem_attr)
 KVM_X86_OP_OPTIONAL(invalidate_restricted_mem)
+KVM_X86_OP_OPTIONAL(rmp_page_level_adjust)
 
 #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 e2529415f28b..b126c6ac7ce4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1724,6 +1724,8 @@ struct kvm_x86_ops {
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
 
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
+
+	void (*rmp_page_level_adjust)(struct kvm *kvm, gfn_t gfn, int *level);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2713632e5061..25db83021500 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3053,6 +3053,11 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 
 out:
 	local_irq_restore(flags);
+
+	/* 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, gfn, &level);
+
 	return level;
 }
 
@@ -3070,8 +3075,13 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
-	if (is_private)
+	pr_debug("%s: gfn: %llx max_level: %d max_huge_page_level: %d\n",
+		 __func__, gfn, max_level, max_huge_page_level);
+	if (kvm_slot_can_be_private(slot) && is_private) {
+		if (kvm_x86_ops.rmp_page_level_adjust)
+			static_call(kvm_x86_rmp_page_level_adjust)(kvm, gfn, &max_level);
 		return max_level;
+	}
 
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6f901545bed9..443c5c8aaaf3 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3710,6 +3710,72 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 	return p;
 }
 
+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, gfn_t gfn, int *level)
+{
+	struct kvm_memory_slot *slot;
+	int ret, order, assigned;
+	int rmp_level = 1;
+	kvm_pfn_t pfn;
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!kvm_slot_can_be_private(slot))
+		return;
+
+	ret = kvm_restricted_mem_get_pfn(slot, gfn, &pfn, &order);
+	if (ret) {
+		pr_warn_ratelimited("Failed to adjust RMP page level, unable to obtain private PFN, rc: %d\n",
+				    ret);
+		*level = PG_LEVEL_4K;
+		return;
+	}
+
+	/* If there's an error retrieving RMP entry, stick with 4K mappings */
+	assigned = snp_lookup_rmpentry(pfn, &rmp_level);
+	if (unlikely(assigned < 0))
+		goto out_adjust;
+
+	if (!assigned) {
+		kvm_pfn_t huge_pfn;
+
+		/*
+		 * If all the pages are shared then no need to keep the RMP
+		 * and NPT in sync.
+		 */
+		huge_pfn = pfn & ~(PTRS_PER_PMD - 1);
+		if (is_pfn_range_shared(huge_pfn, huge_pfn + PTRS_PER_PMD))
+			goto out;
+	}
+
+	/*
+	 * 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))
+		goto out;
+
+out_adjust:
+	/* Adjust the level to keep the NPT and RMP in sync */
+	*level = min_t(size_t, *level, rmp_level);
+out:
+	put_page(pfn_to_page(pfn));
+	pr_debug("%s: GFN: 0x%llx, level: %d, rmp_level: %d, ret: %d\n",
+		 __func__, gfn, *level, rmp_level, ret);
+}
+
 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 013f811c733c..2dfa150bcb09 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4843,6 +4843,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
 
 	.fault_is_private = sev_fault_is_private,
+
+	.rmp_page_level_adjust = sev_rmp_page_level_adjust,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 17200c1ad20e..ae733188cf87 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -698,6 +698,7 @@ 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);
+void sev_rmp_page_level_adjust(struct kvm *kvm, gfn_t gfn, int *level);
 
 int sev_fault_is_private(struct kvm *kvm, gpa_t gpa, u64 error_code, bool *private_fault);
 
-- 
2.25.1