Merge tag 'kvm-x86-hyperv-6.8' of https://github.com/kvm-x86/linux into HEAD

KVM x86 Hyper-V changes for 6.8:

 - Guard KVM-on-HyperV's range-based TLB flush hooks with an #ifdef on
   CONFIG_HYPERV as a minor optimization, and to self-document the code.

 - Add CONFIG_KVM_HYPERV to allow disabling KVM support for HyperV "emulation"
   at build time.

Author: bonzini

arch/x86/include/asm/kvm-x86-ops.h

@@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags)
 KVM_X86_OP(get_if_flag)
 KVM_X86_OP(flush_tlb_all)
 KVM_X86_OP(flush_tlb_current)
+#if IS_ENABLED(CONFIG_HYPERV)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
+#endif
 KVM_X86_OP(flush_tlb_gva)
 KVM_X86_OP(flush_tlb_guest)
 KVM_X86_OP(vcpu_pre_run)

arch/x86/include/asm/kvm_host.h

@@ -937,8 +937,10 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
+#ifdef CONFIG_KVM_HYPERV
 	bool hyperv_enabled;
 	struct kvm_vcpu_hv *hyperv;
+#endif
 #ifdef CONFIG_KVM_XEN
 	struct kvm_vcpu_xen xen;
 #endif
@@ -1095,6 +1097,7 @@ enum hv_tsc_page_status {
 	HV_TSC_PAGE_BROKEN,
 };
 
+#ifdef CONFIG_KVM_HYPERV
 /* Hyper-V emulation context */
 struct kvm_hv {
 	struct mutex hv_lock;
@@ -1125,9 +1128,9 @@ struct kvm_hv {
 	 */
 	unsigned int synic_auto_eoi_used;
 
-	struct hv_partition_assist_pg *hv_pa_pg;
 	struct kvm_hv_syndbg hv_syndbg;
 };
+#endif
 
 struct msr_bitmap_range {
 	u32 flags;
@@ -1136,6 +1139,7 @@ struct msr_bitmap_range {
 	unsigned long *bitmap;
 };
 
+#ifdef CONFIG_KVM_XEN
 /* Xen emulation context */
 struct kvm_xen {
 	struct mutex xen_lock;
@@ -1147,6 +1151,7 @@ struct kvm_xen {
 	struct idr evtchn_ports;
 	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 };
+#endif
 
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
@@ -1348,8 +1353,13 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_hv hyperv;
+#endif
+
+#ifdef CONFIG_KVM_XEN
 	struct kvm_xen xen;
+#endif
 
 	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
@@ -1442,6 +1452,7 @@ struct kvm_arch {
 #if IS_ENABLED(CONFIG_HYPERV)
 	hpa_t	hv_root_tdp;
 	spinlock_t hv_root_tdp_lock;
+	struct hv_partition_assist_pg *hv_pa_pg;
 #endif
 	/*
 	 * VM-scope maximum vCPU ID. Used to determine the size of structures
@@ -1614,9 +1625,11 @@ struct kvm_x86_ops {
 
 	void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
 	void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
+#if IS_ENABLED(CONFIG_HYPERV)
 	int  (*flush_remote_tlbs)(struct kvm *kvm);
 	int  (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
 					gfn_t nr_pages);
+#endif
 
 	/*
 	 * Flush any TLB entries associated with the given GVA.
@@ -1825,6 +1838,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
 #define __KVM_HAVE_ARCH_VM_FREE
 void kvm_arch_free_vm(struct kvm *kvm);
 
+#if IS_ENABLED(CONFIG_HYPERV)
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
 static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
@@ -1836,6 +1850,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 }
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
+						   u64 nr_pages)
+{
+	if (!kvm_x86_ops.flush_remote_tlbs_range)
+		return -EOPNOTSUPP;
+
+	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+}
+#endif /* CONFIG_HYPERV */
 
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)

arch/x86/kvm/Kconfig

@@ -138,6 +138,20 @@ config KVM_SMM
 
 	  If unsure, say Y.
 
+config KVM_HYPERV
+	bool "Support for Microsoft Hyper-V emulation"
+	depends on KVM
+	default y
+	help
+	  Provides KVM support for emulating Microsoft Hyper-V.  This allows KVM
+	  to expose a subset of the paravirtualized interfaces defined in the
+	  Hyper-V Hypervisor Top-Level Functional Specification (TLFS):
+	  https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+	  These interfaces are required for the correct and performant functioning
+	  of Windows and Hyper-V guests on KVM.
+
+	  If unsure, say "Y".
+
 config KVM_XEN
 	bool "Support for Xen hypercall interface"
 	depends on KVM

arch/x86/kvm/Makefile

@@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \
+			   debugfs.o mmu/mmu.o mmu/page_track.o \
 			   mmu/spte.o
 
-ifdef CONFIG_HYPERV
-kvm-y			+= kvm_onhyperv.o
-endif
-
 kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
 kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
-			   vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
+			   vmx/nested.o vmx/posted_intr.o
+
 kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
+kvm-intel-$(CONFIG_KVM_HYPERV)	+= vmx/hyperv.o vmx/hyperv_evmcs.o
 
 kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
-			   svm/sev.o svm/hyperv.o
+			   svm/sev.o
+kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
 
 ifdef CONFIG_HYPERV
+kvm-y			+= kvm_onhyperv.o
+kvm-intel-y		+= vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o
 kvm-amd-y		+= svm/svm_onhyperv.o
 endif
 

arch/x86/kvm/cpuid.c

@@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_cpuid_entry2 *entry;
 
 	entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE,
 				  KVM_CPUID_INDEX_NOT_SIGNIFICANT);
 	return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX;
+#else
+	return false;
+#endif
 }
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -433,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 		return 0;
 	}
 
+#ifdef CONFIG_KVM_HYPERV
 	if (kvm_cpuid_has_hyperv(e2, nent)) {
 		r = kvm_hv_vcpu_init(vcpu);
 		if (r)
 			return r;
 	}
+#endif
 
 	r = kvm_check_cpuid(vcpu, e2, nent);
 	if (r)

arch/x86/kvm/hyperv.h

@@ -24,6 +24,8 @@
 #include <linux/kvm_host.h>
 #include "x86.h"
 
+#ifdef CONFIG_KVM_HYPERV
+
 /* "Hv#1" signature */
 #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
 
@@ -105,6 +107,17 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap);
+}
+
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) &&
+	       test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap);
+}
+
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
@@ -236,6 +249,76 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
 	return kvm_hv_get_assist_page(vcpu);
 }
 
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu,
+						     bool tdp_enabled)
+{
+	/*
+	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+	 * L2's VP_ID upon request from the guest. Make sure we check for
+	 * pending entries in the right FIFO upon L1/L2 transition as these
+	 * requests are put by other vCPUs asynchronously.
+	 */
+	if (to_hv_vcpu(vcpu) && tdp_enabled)
+		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+}
+
 int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
+					 struct pvclock_vcpu_time_info *hv_clock) {}
+static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_init_vm(struct kvm *kvm) {}
+static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
+static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	return HV_STATUS_ACCESS_DENIED;
+}
+static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {}
+static inline void kvm_hv_free_pa_page(struct kvm *kvm) {}
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {}
+static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {}
+static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
+{
+	return vcpu->vcpu_idx;
+}
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {}
+#endif /* CONFIG_KVM_HYPERV */
 
-#endif
+#endif /* __ARCH_X86_KVM_HYPERV_H__ */

arch/x86/kvm/irq.c

@@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.nr;
 
+#ifdef CONFIG_KVM_XEN
 	if (kvm_xen_has_interrupt(v))
 		return v->kvm->arch.xen.upcall_vector;
+#endif
 
 	if (irqchip_split(v->kvm)) {
 		int vector = v->arch.pending_external_vector;

arch/x86/kvm/irq_comm.c

@@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
 
-
+#ifdef CONFIG_KVM_HYPERV
 static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 		    struct kvm *kvm, int irq_source_id, int level,
 		    bool line_status)
@@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 
 	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
 }
+#endif
 
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
@@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	int r;
 
 	switch (e->type) {
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
 				       line_status);
+#endif
 
 	case KVM_IRQ_ROUTING_MSI:
 		if (kvm_msi_route_invalid(kvm, e))
@@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		if (kvm_msi_route_invalid(kvm, e))
 			return -EINVAL;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		e->set = kvm_hv_set_sint;
 		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
 		e->hv_sint.sint = ue->u.hv_sint.sint;
 		break;
+#endif
 #ifdef CONFIG_KVM_XEN
 	case KVM_IRQ_ROUTING_XEN_EVTCHN:
 		return kvm_xen_setup_evtchn(kvm, e, ue);
@@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
+#ifdef CONFIG_KVM_HYPERV
 	kvm_hv_irq_routing_update(kvm);
+#endif
 }

arch/x86/kvm/kvm_onhyperv.h

@@ -10,6 +10,26 @@
 int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages);
 int hv_flush_remote_tlbs(struct kvm *kvm);
 void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp);
+static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Partition assist page is something which Hyper-V running in L0
+	 * requires from KVM running in L1 before direct TLB flush for L2
+	 * guests can be enabled. KVM doesn't currently use the page but to
+	 * comply with TLFS it still needs to be allocated. For now, this
+	 * is a single page shared among all vCPUs.
+	 */
+	struct hv_partition_assist_pg **p_hv_pa_pg =
+		&vcpu->kvm->arch.hv_pa_pg;
+
+	if (!*p_hv_pa_pg)
+		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+
+	if (!*p_hv_pa_pg)
+		return INVALID_PAGE;
+
+	return __pa(*p_hv_pa_pg);
+}
 #else /* !CONFIG_HYPERV */
 static inline int hv_flush_remote_tlbs(struct kvm *kvm)
 {