1 files changed, 67 insertions, 40 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index a8e7bc04d9bf..aa78b6f38dfe 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,6 +7,7 @@
 #include <asm/debugreg.h>
 #include <asm/mmu_context.h>
 
+#include "x86.h"
 #include "cpuid.h"
 #include "hyperv.h"
 #include "mmu.h"
@@ -16,7 +17,6 @@
 #include "sgx.h"
 #include "trace.h"
 #include "vmx.h"
-#include "x86.h"
 #include "smm.h"
 
 static bool __read_mostly enable_shadow_vmcs = 1;
@@ -231,11 +231,8 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (nested_vmx_is_evmptr12_valid(vmx)) {
-		kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
-		vmx->nested.hv_evmcs = NULL;
-	}
-
+	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map);
+	vmx->nested.hv_evmcs = NULL;
 	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
 
 	if (hv_vcpu) {
@@ -317,6 +314,16 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	vcpu->arch.regs_dirty = 0;
 }
 
+static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map);
+	vmx->nested.pi_desc = NULL;
+}
+
 /*
  * Free whatever needs to be freed from vmx->nested when L1 goes down, or
  * just stops using VMX.
@@ -349,15 +356,8 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.cached_vmcs12 = NULL;
 	kfree(vmx->nested.cached_shadow_vmcs12);
 	vmx->nested.cached_shadow_vmcs12 = NULL;
-	/*
-	 * Unpin physical memory we referred to in the vmcs02.  The APIC access
-	 * page's backing page (yeah, confusing) shouldn't actually be accessed,
-	 * and if it is written, the contents are irrelevant.
-	 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
-	vmx->nested.pi_desc = NULL;
+
+	nested_put_vmcs12_pages(vcpu);
 
 	kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
 
@@ -624,7 +624,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
-	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
+	struct kvm_host_map map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
 	if (!cpu_has_vmx_msr_bitmap() ||
@@ -647,10 +647,10 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 			return true;
 	}
 
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
+	if (kvm_vcpu_map_readonly(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), &map))
 		return false;
 
-	msr_bitmap_l1 = (unsigned long *)map->hva;
+	msr_bitmap_l1 = (unsigned long *)map.hva;
 
 	/*
 	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
@@ -714,7 +714,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_FLUSH_CMD, MSR_TYPE_W);
 
-	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
+	kvm_vcpu_unmap(vcpu, &map);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
 
@@ -1197,11 +1197,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);
 
 	/*
-	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
-	 * full TLB flush from the guest's perspective.  This is required even
-	 * if VPID is disabled in the host as KVM may need to synchronize the
-	 * MMU in response to the guest TLB flush.
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host, and so architecturally, linear and combined
+	 * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit.  KVM
+	 * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2,
+	 * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01.  This
+	 * is required if VPID is disabled in KVM, as a TLB flush (there are no
+	 * VPIDs) still occurs from L1's perspective, and KVM may need to
+	 * synchronize the MMU in response to the guest TLB flush.
 	 *
 	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
 	 * EPT is a special snowflake, as guest-physical mappings aren't
@@ -2315,6 +2318,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
 
+	/*
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host.  Emulate this behavior by using vpid01 for L2
+	 * if VPID is disabled in vmcs12.  Note, if VPID is disabled, VM-Enter
+	 * and VM-Exit are architecturally required to flush VPID=0, but *only*
+	 * VPID=0.  I.e. using vpid02 would be ok (so long as KVM emulates the
+	 * required flushes), but doing so would cause KVM to over-flush.  E.g.
+	 * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled,
+	 * and then runs L2 X again, then KVM can and should retain TLB entries
+	 * for VPID12=1.
+	 */
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
 			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
@@ -2996,6 +3010,17 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12)
+{
+	/*
+	 * Check that the given linear address is canonical after a VM exit
+	 * from L2, based on HOST_CR4.LA57 value that will be loaded for L1.
+	 */
+	u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48;
+
+	return !__is_canonical_address(la, l1_address_bits_on_exit);
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -3006,8 +3031,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
 		return -EINVAL;
 
-	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
+	if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
+	    CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
 		return -EINVAL;
 
 	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
@@ -3041,12 +3066,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
 		return -EINVAL;
 
-	if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
+	if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) ||
+	    CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12)))
 		return -EINVAL;
 
 	/*
@@ -3164,7 +3189,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
-	    (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
+	    (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
 	     CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
 		return -EINVAL;
 
@@ -5013,11 +5038,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx_update_cpu_dirty_logging(vcpu);
 	}
 
-	/* Unpin physical memory we referred to in vmcs02 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
-	vmx->nested.pi_desc = NULL;
+	nested_put_vmcs12_pages(vcpu);
 
 	if (vmx->nested.reload_vmcs01_apic_access_page) {
 		vmx->nested.reload_vmcs01_apic_access_page = false;
@@ -5153,7 +5174,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 		 * non-canonical form. This is the only check on the memory
 		 * destination for long mode!
 		 */
-		exn = is_noncanonical_address(*ret, vcpu);
+		exn = is_noncanonical_address(*ret, vcpu, 0);
 	} else {
 		/*
 		 * When not in long mode, the virtual/linear address is
@@ -5950,6 +5971,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 
+	/*
+	 * Always flush the effective vpid02, i.e. never flush the current VPID
+	 * and never explicitly flush vpid01.  INVVPID targets a VPID, not a
+	 * VMCS, and so whether or not the current vmcs12 has VPID enabled is
+	 * irrelevant (and there may not be a loaded vmcs12).
+	 */
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
@@ -5958,7 +5985,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		 * invalidation.
 		 */
 		if (!operand.vpid ||
-		    is_noncanonical_address(operand.gla, vcpu))
+		    is_noncanonical_invlpg_address(operand.gla, vcpu))
 			return nested_vmx_fail(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		vpid_sync_vcpu_addr(vpid02, operand.gla);