[PATCH Part2 RFC v3 24/37] KVM: X86: Add kvm_x86_ops to get the max page level for the TDP

[Brijesh Singh]

When running an SEV-SNP VM, the sPA used to index the RMP entry is
obtained through the TDP translation (gva->gpa->spa). The TDP 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.

To keep the TDP and RMP page level's in sync, the KVM fault handle
kvm_handle_page_fault() will call get_tdp_max_page_level() to get
the maximum allowed page level so that it can limit the TDP level.

In the case of SEV-SNP guest, the get_tdp_max_page_level() will consult
the RMP table to compute the maximum allowed page level for a given
GPA.

Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/mmu/mmu.c          |  6 ++++--
 arch/x86/kvm/svm/sev.c          | 20 ++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/vmx/vmx.c          |  8 ++++++++
 6 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 188110ab2c02..cd2e19e1d323 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1384,6 +1384,7 @@ struct kvm_x86_ops {
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
+	int (*get_tdp_max_page_level)(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0144c40d09c7..7991ffae7b31 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3781,11 +3781,13 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
 				u32 error_code, bool prefault)
 {
+	int max_level = kvm_x86_ops.get_tdp_max_page_level(vcpu, gpa, PG_LEVEL_2M);
+
 	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
 
 	/* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
 	return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault,
-				 PG_LEVEL_2M, false);
+				 max_level, false);
 }
 
 int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
@@ -3826,7 +3828,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 {
 	int max_level;
 
-	for (max_level = KVM_MAX_HUGEPAGE_LEVEL;
+	for (max_level = kvm_x86_ops.get_tdp_max_page_level(vcpu, gpa, KVM_MAX_HUGEPAGE_LEVEL);
 	     max_level > PG_LEVEL_4K;
 	     max_level--) {
 		int page_num = KVM_PAGES_PER_HPAGE(max_level);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 856a6cf99a61..6b0c230c5f37 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3184,3 +3184,23 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 
 	return pfn_to_page(pfn);
 }
+
+int sev_get_tdp_max_page_level(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level)
+{
+	struct rmpentry *e;
+	kvm_pfn_t pfn;
+	int level;
+
+	if (!sev_snp_guest(vcpu->kvm))
+		return max_level;
+
+	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
+	if (is_error_noslot_pfn(pfn))
+		return max_level;
+
+	e = snp_lookup_page_in_rmptable(pfn_to_page(pfn), &level);
+	if (unlikely(!e))
+		return max_level;
+
+	return min_t(uint32_t, level, max_level);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a7adf6ca1713..2632eae52aa3 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4576,6 +4576,7 @@ 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,
+	.get_tdp_max_page_level = sev_get_tdp_max_page_level,
 };
 
 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 bc5582b44356..32abcbd774d0 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -568,6 +568,7 @@ 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);
+int sev_get_tdp_max_page_level(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level);
 
 /* vmenter.S */
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4bceb5ca3a89..fbc9034edf16 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7612,6 +7612,12 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
+
+static int vmx_get_tdp_max_page_level(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level)
+{
+	return max_level;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hardware_unsetup = hardware_unsetup,
 
@@ -7742,6 +7748,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+
+	.get_tdp_max_page_level = vmx_get_tdp_max_page_level,
 };
 
 static __init void vmx_setup_user_return_msrs(void)
-- 
2.17.1