[PATCH 03/11] nEPT: MMU context for nested EPT

[Jun Nakajima <jun.nakajima@intel.com>]

KVM's existing shadow MMU code already supports nested TDP. To use it, we
need to set up a new "MMU context" for nested EPT, and create a few callbacks
for it (nested_ept_*()). This context should also use the EPT versions of
the page table access functions (defined in the previous patch).
Then, we need to switch back and forth between this nested context and the
regular MMU context when switching between L1 and L2 (when L1 runs this L2
with EPT).

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Jun Nakajima <jun.nakajima@intel.com>
Signed-off-by: Xinhao Xu <xinhao.xu@intel.com>
---
 arch/x86/kvm/mmu.c | 38 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu.h |  1 +
 arch/x86/kvm/vmx.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cb9c6fd..99bfc5e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3644,6 +3644,44 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
+int kvm_init_shadow_EPT_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
+{
+	ASSERT(vcpu);
+	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+
+	context->nx = is_nx(vcpu); /* TODO: ? */
+	context->new_cr3 = paging_new_cr3;
+	context->page_fault = EPT_page_fault;
+	context->gva_to_gpa = EPT_gva_to_gpa;
+	context->sync_page = EPT_sync_page;
+	context->invlpg = EPT_invlpg;
+	context->update_pte = EPT_update_pte;
+	context->free = paging_free;
+	context->root_level = context->shadow_root_level;
+	context->root_hpa = INVALID_PAGE;
+	context->direct_map = false;
+
+	/* TODO: reset_rsvds_bits_mask() is not built for EPT, we need
+	   something different.
+	 */
+	reset_rsvds_bits_mask(vcpu, context);
+
+
+	/* TODO: I copied these from kvm_init_shadow_mmu, I don't know why
+	   they are done, or why they write to vcpu->arch.mmu and not context
+	 */
+	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
+	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
+	vcpu->arch.mmu.base_role.smep_andnot_wp =
+		kvm_read_cr4_bits(vcpu, X86_CR4_SMEP) &&
+		!is_write_protection(vcpu);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_EPT_mmu);
+
 static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
 	int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 6987108..19dd5ab 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -54,6 +54,7 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+int kvm_init_shadow_EPT_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9e0ec9d..6ab53ca 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -918,6 +918,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
+}
+
 static inline bool is_exception(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -6873,6 +6878,46 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 		entry->ecx |= bit(X86_FEATURE_VMX);
 }
 
+/* Callbacks for nested_ept_init_mmu_context: */
+
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+{
+	/* return the page table to be shadowed - in our case, EPT12 */
+	return get_vmcs12(vcpu)->ept_pointer;
+}
+
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+	struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12;
+	nested_vmx_vmexit(vcpu);
+	vmcs12 = get_vmcs12(vcpu);
+	/*
+	 * Note no need to set vmcs12->vm_exit_reason as it is already copied
+	 * from vmcs02 in nested_vmx_vmexit() above, i.e., EPT_VIOLATION.
+	 */
+	vmcs12->exit_qualification = fault->error_code;
+	vmcs12->guest_physical_address = fault->address;
+}
+
+static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+	int r = kvm_init_shadow_EPT_mmu(vcpu, &vcpu->arch.mmu);
+
+	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
+	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
+	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+
+	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
+
+	return r;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7090,6 +7135,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmx_flush_tlb(vcpu);
 	}
 
+	if (nested_cpu_has_ept(vmcs12)) {
+		kvm_mmu_unload(vcpu);
+		nested_ept_init_mmu_context(vcpu);
+	}
+
 	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->guest_ia32_efer;
 	if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
@@ -7420,7 +7470,8 @@ void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	/* shadow page tables on either EPT or shadow page tables */
+	if (nested_cpu_has_ept(vmcs12))
+		nested_ept_uninit_mmu_context(vcpu);
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
 
-- 
1.8.2.1.610.g562af5b