KVM: x86: Introduce KVM_REQ_TLB_FLUSH_CURRENT to flush current ASID

Add KVM_REQ_TLB_FLUSH_CURRENT to allow optimized TLB flushing of VMX's
EPTP/VPID contexts[*] from the KVM MMU and/or in a deferred manner, e.g.
to flush L2's context during nested VM-Enter.

Convert KVM_REQ_TLB_FLUSH to KVM_REQ_TLB_FLUSH_CURRENT in flows where
the flush is directly associated with vCPU-scoped instruction emulation,
i.e. MOV CR3 and INVPCID.

Add a comment in vmx_vcpu_load_vmcs() above its KVM_REQ_TLB_FLUSH to
make it clear that it deliberately requests a flush of all contexts.

Service any pending flush request on nested VM-Exit as it's possible a
nested VM-Exit could occur after requesting a flush for L2.  Add the
same logic for nested VM-Enter even though it's _extremely_ unlikely
for flush to be pending on nested VM-Enter, but theoretically possible
(in the future) due to RSM (SMM) emulation.

[*] Intel also has an Address Space Identifier (ASID) concept, e.g.
    EPTP+VPID+PCID == ASID, it's just not documented in the SDM because
    the rules of invalidation are different based on which piece of the
    ASID is being changed, i.e. whether the EPTP, VPID, or PCID context
    must be invalidated.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200320212833.3507-25-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -83,8 +83,9 @@
 #define KVM_REQ_GET_VMCS12_PAGES	KVM_ARCH_REQ(24)
 #define KVM_REQ_APICV_UPDATE \
 	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
 #define KVM_REQ_HV_TLB_FLUSH \
-	KVM_ARCH_REQ_FLAGS(26, KVM_REQUEST_NO_WAKEUP)
+	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -1104,6 +1105,7 @@ struct kvm_x86_ops {
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 	void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
+	void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
 	int  (*tlb_remote_flush)(struct kvm *kvm);
 	int  (*tlb_remote_flush_with_range)(struct kvm *kvm,
 			struct kvm_tlb_range *range);

arch/x86/kvm/svm/svm.c

@@ -3945,6 +3945,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_rflags = svm_set_rflags,
 
 	.tlb_flush_all = svm_flush_tlb,
+	.tlb_flush_current = svm_flush_tlb,
 	.tlb_flush_gva = svm_flush_tlb_gva,
 	.tlb_flush_guest = svm_flush_tlb,
 

arch/x86/kvm/vmx/nested.c

@@ -3208,6 +3208,9 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	u32 exit_reason = EXIT_REASON_INVALID_STATE;
 	u32 exit_qual;
 
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
 	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
@@ -4274,6 +4277,10 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+	/* Service the TLB flush request for L2 before switching to L1. */
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
 	leave_guest_mode(vcpu);
 
 	if (nested_cpu_has_preemption_timer(vmcs12))

arch/x86/kvm/vmx/vmx.c

@@ -1338,6 +1338,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
 		void *gdt = get_current_gdt_ro();
 		unsigned long sysenter_esp;
 
+		/*
+		 * Flush all EPTP/VPID contexts, the new pCPU may have stale
+		 * TLB entries from its previous association with the vCPU.
+		 */
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 
 		/*
@@ -5468,7 +5472,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 
 		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
 			kvm_mmu_sync_roots(vcpu);
-			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 
 		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
@@ -7764,6 +7768,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.set_rflags = vmx_set_rflags,
 
 	.tlb_flush_all = vmx_flush_tlb_all,
+	.tlb_flush_current = vmx_flush_tlb_current,
 	.tlb_flush_gva = vmx_flush_tlb_gva,
 	.tlb_flush_guest = vmx_flush_tlb_guest,
 

arch/x86/kvm/x86.c

@@ -1019,7 +1019,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
 		if (!skip_tlb_flush) {
 			kvm_mmu_sync_roots(vcpu);
-			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 		return 0;
 	}
@@ -8222,10 +8222,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu))
 			kvm_mmu_load_pgd(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
 			kvm_vcpu_flush_tlb_all(vcpu);
+
+			/* Flushing all ASIDs flushes the current ASID... */
+			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+		}
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+			kvm_vcpu_flush_tlb_current(vcpu);
 		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu))
 			kvm_vcpu_flush_tlb_guest(vcpu);
+
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;

arch/x86/kvm/x86.h

@@ -125,6 +125,12 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	kvm_x86_ops.tlb_flush_current(vcpu);
+}
+
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);