nEPT: Add nEPT violation/misconfigration support

Inject nEPT fault to L1 guest. This patch is original from Xinhao.

Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Jun Nakajima <jun.nakajima@intel.com>
Signed-off-by: Xinhao Xu <xinhao.xu@intel.com>
Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -286,6 +286,7 @@ struct kvm_mmu {
 	u64 *pae_root;
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
+	u64 bad_mt_xwr;
 
 	/*
 	 * Bitmap: bit set = last pte in walk
@@ -512,6 +513,9 @@ struct kvm_vcpu_arch {
 	 * instruction.
 	 */
 	bool write_fault_to_shadow_pgtable;
+
+	/* set at EPT violation at this point */
+	unsigned long exit_qualification;
 };
 
 struct kvm_lpage_info {

arch/x86/kvm/mmu.c

@@ -3519,6 +3519,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 
+	context->bad_mt_xwr = 0;
+
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
 	switch (context->root_level) {
@@ -3574,7 +3576,40 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *context, bool execonly)
+{
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+	int pte;
+
+	context->rsvd_bits_mask[0][3] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
+	context->rsvd_bits_mask[0][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+
+	/* large page */
+	context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+	context->rsvd_bits_mask[1][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
+	context->rsvd_bits_mask[1][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
+	context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+	for (pte = 0; pte < 64; pte++) {
+		int rwx_bits = pte & 7;
+		int mt = pte >> 3;
+		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
+				rwx_bits == 0x2 || rwx_bits == 0x6 ||
+				(rwx_bits == 0x4 && !execonly))
+			context->bad_mt_xwr |= (1ull << pte);
+	}
+}
+
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3592,12 +3627,16 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu
 			w = bit & ACC_WRITE_MASK;
 			u = bit & ACC_USER_MASK;
 
-			/* Not really needed: !nx will cause pte.nx to fault */
+			if (!ept) {
-			x |= !mmu->nx;
+				/* Not really needed: !nx will cause pte.nx to fault */
-			/* Allow supervisor writes if !cr0.wp */
+				x |= !mmu->nx;
-			w |= !is_write_protection(vcpu) && !uf;
+				/* Allow supervisor writes if !cr0.wp */
-			/* Disallow supervisor fetches of user code if cr4.smep */
+				w |= !is_write_protection(vcpu) && !uf;
-			x &= !(smep && u && !uf);
+				/* Disallow supervisor fetches of user code if cr4.smep */
+				x &= !(smep && u && !uf);
+			} else
+				/* Not really needed: no U/S accesses on ept  */
+				u = 1;
 
 			fault = (ff && !x) || (uf && !u) || (wf && !w);
 			map |= fault << bit;
@@ -3632,7 +3671,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->root_level = level;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
@@ -3662,7 +3701,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->root_level = PT32_ROOT_LEVEL;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
@@ -3724,7 +3763,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	return 0;
@@ -3803,7 +3842,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
-	update_permission_bitmask(vcpu, g_context);
+	update_permission_bitmask(vcpu, g_context, false);
 	update_last_pte_bitmap(vcpu, g_context);
 
 	return 0;

arch/x86/kvm/paging_tmpl.h

@@ -129,10 +129,10 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
 
 static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
 {
-	int bit7;
+	int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
 
-	bit7 = (gpte >> 7) & 1;
+	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
+		((mmu->bad_mt_xwr & (1ull << low6)) != 0);
 }
 
 static inline int FNAME(is_present_gpte)(unsigned long pte)
@@ -386,6 +386,25 @@ error:
 	walker->fault.vector = PF_VECTOR;
 	walker->fault.error_code_valid = true;
 	walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+	/*
+	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+	 * misconfiguration requires to be injected. The detection is
+	 * done by is_rsvd_bits_set() above.
+	 *
+	 * We set up the value of exit_qualification to inject:
+	 * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation
+	 * [5:3] - Calculated by the page walk of the guest EPT page tables
+	 * [7:8] - Derived from [7:8] of real exit_qualification
+	 *
+	 * The other bits are set to 0.
+	 */
+	if (!(errcode & PFERR_RSVD_MASK)) {
+		vcpu->arch.exit_qualification &= 0x187;
+		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+	}
+#endif
 	walker->fault.address = addr;
 	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
 

arch/x86/kvm/vmx.c

@@ -5317,9 +5317,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 
 	/* It is a write fault? */
 	error_code = exit_qualification & (1U << 1);
+	/* It is a fetch fault? */
+	error_code |= (exit_qualification & (1U << 2)) << 2;
 	/* ept page table is present? */
 	error_code |= (exit_qualification >> 3) & 0x1;
 
+	vcpu->arch.exit_qualification = exit_qualification;
+
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
@@ -7348,6 +7352,21 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 		entry->ecx |= bit(X86_FEATURE_VMX);
 }
 
+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);
+
+	if (fault->error_code & PFERR_RSVD_MASK)
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+	else
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+	vmcs12->exit_qualification = vcpu->arch.exit_qualification;
+	vmcs12->guest_physical_address = fault->address;
+}
+
 /*
  * 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