Merge branch 'kvm-older-features' into HEAD

Merge branch for features that did not make it into 5.18:

* New ioctls to get/set TSC frequency for a whole VM

* Allow userspace to opt out of hypercall patching

Nested virtualization improvements for AMD:

* Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
  nested vGIF)

* Allow AVIC to co-exist with a nested guest running

* Fixes for LBR virtualizations when a nested guest is running,
  and nested LBR virtualization support

* PAUSE filtering for nested hypervisors

Guest support:

* Decoupling of vcpu_is_preempted from PV spinlocks
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -982,12 +982,22 @@ memory.
 	__u8 pad2[30];
   };
 
-If the KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag is returned from the
-KVM_CAP_XEN_HVM check, it may be set in the flags field of this ioctl.
-This requests KVM to generate the contents of the hypercall page
-automatically; hypercalls will be intercepted and passed to userspace
-through KVM_EXIT_XEN.  In this case, all of the blob size and address
-fields must be zero.
+If certain flags are returned from the KVM_CAP_XEN_HVM check, they may
+be set in the flags field of this ioctl:
+
+The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate
+the contents of the hypercall page automatically; hypercalls will be
+intercepted and passed to userspace through KVM_EXIT_XEN.  In this
+ase, all of the blob size and address fields must be zero.
+
+The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace
+will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event
+channel interrupts rather than manipulating the guest's shared_info
+structures directly. This, in turn, may allow KVM to enable features
+such as intercepting the SCHEDOP_poll hypercall to accelerate PV
+spinlock operation for the guest. Userspace may still use the ioctl
+to deliver events if it was advertised, even if userspace does not
+send this indication that it will always do so
 
 No other flags are currently valid in the struct kvm_xen_hvm_config.
 
@@ -1887,22 +1897,25 @@ the future.
 4.55 KVM_SET_TSC_KHZ
 --------------------
 
-:Capability: KVM_CAP_TSC_CONTROL
+:Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL
 :Architectures: x86
-:Type: vcpu ioctl
+:Type: vcpu ioctl / vm ioctl
 :Parameters: virtual tsc_khz
 :Returns: 0 on success, -1 on error
 
 Specifies the tsc frequency for the virtual machine. The unit of the
 frequency is KHz.
 
+If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also
+be used as a vm ioctl to set the initial tsc frequency of subsequently
+created vCPUs.
 
 4.56 KVM_GET_TSC_KHZ
 --------------------
 
-:Capability: KVM_CAP_GET_TSC_KHZ
+:Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL
 :Architectures: x86
-:Type: vcpu ioctl
+:Type: vcpu ioctl / vm ioctl
 :Parameters: none
 :Returns: virtual tsc-khz on success, negative value on error
 
@@ -5216,7 +5229,25 @@ have deterministic behavior.
 		struct {
 			__u64 gfn;
 		} shared_info;
-		__u64 pad[4];
+		struct {
+			__u32 send_port;
+			__u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+			__u32 flags;
+			union {
+				struct {
+					__u32 port;
+					__u32 vcpu;
+					__u32 priority;
+				} port;
+				struct {
+					__u32 port; /* Zero for eventfd */
+					__s32 fd;
+				} eventfd;
+				__u32 padding[4];
+			} deliver;
+		} evtchn;
+		__u32 xen_version;
+		__u64 pad[8];
 	} u;
   };
 
@@ -5247,6 +5278,30 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO
 
 KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
   Sets the exception vector used to deliver Xen event channel upcalls.
+  This is the HVM-wide vector injected directly by the hypervisor
+  (not through the local APIC), typically configured by a guest via
+  HVM_PARAM_CALLBACK_IRQ.
+
+KVM_XEN_ATTR_TYPE_EVTCHN
+  This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+  support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
+  an outbound port number for interception of EVTCHNOP_send requests
+  from the guest. A given sending port number may be directed back
+  to a specified vCPU (by APIC ID) / port / priority on the guest,
+  or to trigger events on an eventfd. The vCPU and priority can be
+  changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call,
+  but other fields cannot change for a given sending port. A port
+  mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags
+  field.
+
+KVM_XEN_ATTR_TYPE_XEN_VERSION
+  This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+  support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
+  the 32-bit version code returned to the guest when it invokes the
+  XENVER_version call; typically (XEN_MAJOR << 16 | XEN_MINOR). PV
+  Xen guests will often use this to as a dummy hypercall to trigger
+  event channel delivery, so responding within the kernel without
+  exiting to userspace is beneficial.
 
 4.127 KVM_XEN_HVM_GET_ATTR
 --------------------------
@@ -5258,7 +5313,8 @@ KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
 :Returns: 0 on success, < 0 on error
 
 Allows Xen VM attributes to be read. For the structure and types,
-see KVM_XEN_HVM_SET_ATTR above.
+see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_ATTR_TYPE_EVTCHN
+attribute cannot be read.
 
 4.128 KVM_XEN_VCPU_SET_ATTR
 ---------------------------
@@ -5285,6 +5341,13 @@ see KVM_XEN_HVM_SET_ATTR above.
 			__u64 time_blocked;
 			__u64 time_offline;
 		} runstate;
+		__u32 vcpu_id;
+		struct {
+			__u32 port;
+			__u32 priority;
+			__u64 expires_ns;
+		} timer;
+		__u8 vector;
 	} u;
   };
 
@@ -5326,6 +5389,27 @@ KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST
   or RUNSTATE_offline) to set the current accounted state as of the
   adjusted state_entry_time.
 
+KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID
+  This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+  support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the Xen
+  vCPU ID of the given vCPU, to allow timer-related VCPU operations to
+  be intercepted by KVM.
+
+KVM_XEN_VCPU_ATTR_TYPE_TIMER
+  This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+  support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
+  event channel port/priority for the VIRQ_TIMER of the vCPU, as well
+  as allowing a pending timer to be saved/restored.
+
+KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
+  This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+  support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
+  per-vCPU local APIC upcall vector, configured by a Xen guest with
+  the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
+  used by Windows guests, and is distinct from the HVM-wide upcall
+  vector configured with HVM_PARAM_CALLBACK_IRQ.
+
+
 4.129 KVM_XEN_VCPU_GET_ATTR
 ---------------------------
 
@@ -5645,6 +5729,25 @@ enabled with ``arch_prctl()``, but this may change in the future.
 The offsets of the state save areas in struct kvm_xsave follow the contents
 of CPUID leaf 0xD on the host.
 
+4.135 KVM_XEN_HVM_EVTCHN_SEND
+-----------------------------
+
+:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_irq_routing_xen_evtchn
+:Returns: 0 on success, < 0 on error
+
+
+::
+
+   struct kvm_irq_routing_xen_evtchn {
+	__u32 port;
+	__u32 vcpu;
+	__u32 priority;
+   };
+
+This ioctl injects an event channel interrupt directly to the guest vCPU.
 
 5. The kvm_run structure
 ========================
@@ -7135,6 +7238,15 @@ The valid bits in cap.args[0] are:
                                     Additionally, when this quirk is disabled,
                                     KVM clears CPUID.01H:ECX[bit 3] if
                                     IA32_MISC_ENABLE[bit 18] is cleared.
+
+ KVM_X86_QUIRK_FIX_HYPERCALL_INSN   By default, KVM rewrites guest
+                                    VMMCALL/VMCALL instructions to match the
+                                    vendor's hypercall instruction for the
+                                    system. When this quirk is disabled, KVM
+                                    will no longer rewrite invalid guest
+                                    hypercall instructions. Executing the
+                                    incorrect hypercall instruction will
+                                    generate a #UD within the guest.
 =================================== ============================================
 
 8. Other capabilities.
@@ -7612,8 +7724,9 @@ PVHVM guests. Valid flags are::
   #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
   #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
   #define KVM_XEN_HVM_CONFIG_SHARED_INFO	(1 << 2)
-  #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 2)
-  #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 3)
+  #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
+  #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
+  #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND	(1 << 5)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -7637,6 +7750,14 @@ The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries
 of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority
 field set to indicate 2 level event channel delivery.
 
+The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates that KVM supports
+injecting event channel events directly into the guest with the
+KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indicates support for the
+KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attributes and the
+KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes.
+related to event channel delivery, timers, and the XENVER_version
+interception.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 

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

@@ -126,6 +126,7 @@ KVM_X86_OP_OPTIONAL(migrate_timers)
 KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
+KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL

arch/x86/include/asm/kvm_host.h

@@ -607,16 +607,21 @@ struct kvm_vcpu_hv {
 struct kvm_vcpu_xen {
 	u64 hypercall_rip;
 	u32 current_runstate;
-	bool vcpu_info_set;
-	bool vcpu_time_info_set;
-	bool runstate_set;
-	struct gfn_to_hva_cache vcpu_info_cache;
-	struct gfn_to_hva_cache vcpu_time_info_cache;
-	struct gfn_to_hva_cache runstate_cache;
+	u8 upcall_vector;
+	struct gfn_to_pfn_cache vcpu_info_cache;
+	struct gfn_to_pfn_cache vcpu_time_info_cache;
+	struct gfn_to_pfn_cache runstate_cache;
 	u64 last_steal;
 	u64 runstate_entry_time;
 	u64 runstate_times[4];
 	unsigned long evtchn_pending_sel;
+	u32 vcpu_id; /* The Xen / ACPI vCPU ID */
+	u32 timer_virq;
+	u64 timer_expires; /* In guest epoch */
+	atomic_t timer_pending;
+	struct hrtimer timer;
+	int poll_evtchn;
+	struct timer_list poll_timer;
 };
 
 struct kvm_vcpu_arch {
@@ -753,8 +758,7 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	struct gfn_to_hva_cache pv_time;
-	bool pv_time_enabled;
+	struct gfn_to_pfn_cache pv_time;
 	/* set guest stopped flag in pvclock flags field */
 	bool pvclock_set_guest_stopped_request;
 
@@ -1024,9 +1028,12 @@ struct msr_bitmap_range {
 
 /* Xen emulation context */
 struct kvm_xen {
+	u32 xen_version;
 	bool long_mode;
 	u8 upcall_vector;
 	struct gfn_to_pfn_cache shinfo_cache;
+	struct idr evtchn_ports;
+	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 };
 
 enum kvm_irqchip_mode {
@@ -1119,6 +1126,8 @@ struct kvm_arch {
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
 
+	u32 default_tsc_khz;
+
 	seqcount_raw_spinlock_t pvclock_sc;
 	bool use_master_clock;
 	u64 master_kernel_ns;
@@ -1498,6 +1507,11 @@ struct kvm_x86_ops {
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+
+	/*
+	 * Returns vCPU specific APICv inhibit reasons
+	 */
+	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {
@@ -1799,6 +1813,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 				struct x86_exception *exception);
 
 bool kvm_apicv_activated(struct kvm *kvm);
+bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu);
 void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
 void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 				      enum kvm_apicv_inhibit reason, bool set);
@@ -1988,6 +2003,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_CD_NW_CLEARED |		\
 	 KVM_X86_QUIRK_LAPIC_MMIO_HOLE |	\
 	 KVM_X86_QUIRK_OUT_7E_INC_RIP |		\
-	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)
+	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT |	\
+	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
 
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/uapi/asm/kvm.h

@@ -428,11 +428,12 @@ struct kvm_sync_regs {
 	struct kvm_vcpu_events events;
 };
 
-#define KVM_X86_QUIRK_LINT0_REENABLED	   (1 << 0)
-#define KVM_X86_QUIRK_CD_NW_CLEARED	   (1 << 1)
-#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	   (1 << 2)
-#define KVM_X86_QUIRK_OUT_7E_INC_RIP	   (1 << 3)
-#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
+#define KVM_X86_QUIRK_LINT0_REENABLED		(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED		(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE		(1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP		(1 << 3)
+#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
+#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1

arch/x86/kernel/asm-offsets_64.c

@@ -5,7 +5,7 @@
 
 #include <asm/ia32.h>
 
-#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#if defined(CONFIG_KVM_GUEST)
 #include <asm/kvm_para.h>
 #endif
 
@@ -20,7 +20,7 @@ int main(void)
 	BLANK();
 #endif
 
-#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#if defined(CONFIG_KVM_GUEST)
 	OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted);
 	BLANK();
 #endif

arch/x86/kernel/kvm.c

@@ -752,6 +752,42 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
+#if defined(CONFIG_X86_32) || !defined(CONFIG_SMP)
+bool __kvm_vcpu_is_preempted(long cpu);
+
+__visible bool __kvm_vcpu_is_preempted(long cpu)
+{
+	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+	return !!(src->preempted & KVM_VCPU_PREEMPTED);
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+ASM_ENDBR
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+ASM_RET
+".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
+".popsection");
+
+#endif
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -764,6 +800,9 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
 		static_call_update(pv_steal_clock, kvm_steal_clock);
+
+		pv_ops.lock.vcpu_is_preempted =
+			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1005,40 +1044,6 @@ static void kvm_wait(u8 *ptr, u8 val)
 	}
 }
 
-#ifdef CONFIG_X86_32
-__visible bool __kvm_vcpu_is_preempted(long cpu)
-{
-	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
-
-	return !!(src->preempted & KVM_VCPU_PREEMPTED);
-}
-PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
-
-#else
-
-#include <asm/asm-offsets.h>
-
-extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
-
-/*
- * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
- * restoring to/from the stack.
- */
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-ASM_ENDBR
-"movq	__per_cpu_offset(,%rdi,8), %rax;"
-"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne	%al;"
-ASM_RET
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
-
-#endif
-
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -1082,10 +1087,6 @@ void __init kvm_spinlock_init(void)
 	pv_ops.lock.wait = kvm_wait;
 	pv_ops.lock.kick = kvm_kick_cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		pv_ops.lock.vcpu_is_preempted =
-			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
-	}
 	/*
 	 * When PV spinlock is enabled which is preferred over
 	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.

arch/x86/kvm/i8259.c

@@ -252,7 +252,6 @@ int kvm_pic_read_irq(struct kvm *kvm)
 				 */
 				irq2 = 7;
 			intno = s->pics[1].irq_base + irq2;
-			irq = irq2 + 8;
 		} else
 			intno = s->pics[0].irq_base + irq;
 	} else {

arch/x86/kvm/irq.c

@@ -22,10 +22,14 @@
  */
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
+	int r = 0;
+
 	if (lapic_in_kernel(vcpu))
-		return apic_has_pending_timer(vcpu);
+		r = apic_has_pending_timer(vcpu);
+	if (kvm_xen_timer_enabled(vcpu))
+		r += kvm_xen_has_pending_timer(vcpu);
 
-	return 0;
+	return r;
 }
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
@@ -143,6 +147,8 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	if (lapic_in_kernel(vcpu))
 		kvm_inject_apic_timer_irqs(vcpu);
+	if (kvm_xen_timer_enabled(vcpu))
+		kvm_xen_inject_timer_irqs(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
 

arch/x86/kvm/irq_comm.c

@@ -181,7 +181,7 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 		if (!level)
 			return -1;
 
-		return kvm_xen_set_evtchn_fast(e, kvm);
+		return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm);
 #endif
 	default:
 		break;

arch/x86/kvm/mmu/mmu.c

@@ -1866,17 +1866,14 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])	\
 		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
-static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			 struct list_head *invalid_list)
 {
 	int ret = vcpu->arch.mmu->sync_page(vcpu, sp);
 
-	if (ret < 0) {
+	if (ret < 0)
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
-		return false;
-	}
-
-	return !!ret;
+	return ret;
 }
 
 static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
@@ -1998,7 +1995,7 @@ static int mmu_sync_children(struct kvm_vcpu *vcpu,
 
 		for_each_sp(pages, sp, parents, i) {
 			kvm_unlink_unsync_page(vcpu->kvm, sp);
-			flush |= kvm_sync_page(vcpu, sp, &invalid_list);
+			flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0;
 			mmu_pages_clear_parents(&parents);
 		}
 		if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
@@ -2039,6 +2036,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	struct hlist_head *sp_list;
 	unsigned quadrant;
 	struct kvm_mmu_page *sp;
+	int ret;
 	int collisions = 0;
 	LIST_HEAD(invalid_list);
 
@@ -2091,11 +2089,13 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			 * If the sync fails, the page is zapped.  If so, break
 			 * in order to rebuild it.
 			 */
-			if (!kvm_sync_page(vcpu, sp, &invalid_list))
+			ret = kvm_sync_page(vcpu, sp, &invalid_list);
+			if (ret < 0)
 				break;
 
 			WARN_ON(!list_empty(&invalid_list));
-			kvm_flush_remote_tlbs(vcpu->kvm);
+			if (ret > 0)
+				kvm_flush_remote_tlbs(vcpu->kvm);
 		}
 
 		__clear_sp_write_flooding_count(sp);

arch/x86/kvm/svm/avic.c

@@ -165,9 +165,8 @@ int avic_vm_init(struct kvm *kvm)
 	return err;
 }
 
-void avic_init_vmcb(struct vcpu_svm *svm)
+void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 {
-	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
 	phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
 	phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
@@ -357,6 +356,13 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return APICV_INHIBIT_REASON_NESTED;
+	return 0;
+}
+
 static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
 {
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);

arch/x86/kvm/svm/svm.h

@@ -33,6 +33,7 @@
 #define MSRPM_OFFSETS	16
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
+extern int vgif;
 extern bool intercept_smi;
 
 /*
@@ -231,9 +232,14 @@ struct vcpu_svm {
 	unsigned int3_injected;
 	unsigned long int3_rip;
 
-	/* cached guest cpuid flags for faster access */
+	/* optional nested SVM features that are enabled for this guest  */
 	bool nrips_enabled                : 1;
 	bool tsc_scaling_enabled          : 1;
+	bool v_vmload_vmsave_enabled      : 1;
+	bool lbrv_enabled                 : 1;
+	bool pause_filter_enabled         : 1;
+	bool pause_threshold_enabled      : 1;
+	bool vgif_enabled                 : 1;
 
 	u32 ldr_reg;
 	u32 dfr_reg;
@@ -452,44 +458,70 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit)
 	return vmcb_is_intercept(&svm->vmcb->control, bit);
 }
 
-static inline bool vgif_enabled(struct vcpu_svm *svm)
+static inline bool nested_vgif_enabled(struct vcpu_svm *svm)
 {
-	return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK);
+	return svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK);
+}
+
+static inline struct vmcb *get_vgif_vmcb(struct vcpu_svm *svm)
+{
+	if (!vgif)
+		return NULL;
+
+	if (is_guest_mode(&svm->vcpu) && !nested_vgif_enabled(svm))
+		return svm->nested.vmcb02.ptr;
+	else
+		return svm->vmcb01.ptr;
 }
 
 static inline void enable_gif(struct vcpu_svm *svm)
 {
-	if (vgif_enabled(svm))
-		svm->vmcb->control.int_ctl |= V_GIF_MASK;
+	struct vmcb *vmcb = get_vgif_vmcb(svm);
+
+	if (vmcb)
+		vmcb->control.int_ctl |= V_GIF_MASK;
 	else
 		svm->vcpu.arch.hflags |= HF_GIF_MASK;
 }
 
 static inline void disable_gif(struct vcpu_svm *svm)
 {
-	if (vgif_enabled(svm))
-		svm->vmcb->control.int_ctl &= ~V_GIF_MASK;
+	struct vmcb *vmcb = get_vgif_vmcb(svm);
+
+	if (vmcb)
+		vmcb->control.int_ctl &= ~V_GIF_MASK;
 	else
 		svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
 }
 
 static inline bool gif_set(struct vcpu_svm *svm)
 {
-	if (vgif_enabled(svm))
-		return !!(svm->vmcb->control.int_ctl & V_GIF_MASK);
+	struct vmcb *vmcb = get_vgif_vmcb(svm);
+
+	if (vmcb)
+		return !!(vmcb->control.int_ctl & V_GIF_MASK);
 	else
 		return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
 }
 
+static inline bool nested_npt_enabled(struct vcpu_svm *svm)
+{
+	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
+}
+
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
+#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+
 extern bool dump_invalid_vmcb;
 
 u32 svm_msrpm_offset(u32 msr);
 u32 *svm_vcpu_alloc_msrpm(void);
 void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
 void svm_vcpu_free_msrpm(u32 *msrpm);
+void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
+void svm_update_lbrv(struct kvm_vcpu *vcpu);
 
 int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
 void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -574,7 +606,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 int avic_ga_log_notifier(u32 ga_tag);
 void avic_vm_destroy(struct kvm *kvm);
 int avic_vm_init(struct kvm *kvm);
-void avic_init_vmcb(struct vcpu_svm *svm);
+void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
 int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu);
 int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu);
 int avic_init_vcpu(struct vcpu_svm *svm);
@@ -592,6 +624,7 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
 void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void avic_ring_doorbell(struct kvm_vcpu *vcpu);
+unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu);
 
 /* sev.c */
 

arch/x86/kvm/vmx/vmx.c

@@ -4380,7 +4380,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	if (cpu_has_secondary_exec_ctrls())
 		secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx));
 
-	if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
+	if (enable_apicv && lapic_in_kernel(&vmx->vcpu)) {
 		vmcs_write64(EOI_EXIT_BITMAP0, 0);
 		vmcs_write64(EOI_EXIT_BITMAP1, 0);
 		vmcs_write64(EOI_EXIT_BITMAP2, 0);

arch/x86/kvm/xen.h

@@ -15,16 +15,19 @@
 extern struct static_key_false_deferred kvm_xen_enabled;
 
 int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu);
 int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data);
 int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data);
+int kvm_xen_hvm_evtchn_send(struct kvm *kvm, struct kvm_irq_routing_xen_evtchn *evt);
 int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data);
 int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc);
 void kvm_xen_init_vm(struct kvm *kvm);
 void kvm_xen_destroy_vm(struct kvm *kvm);
-
-int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
+void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu);
+void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu);
+int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe,
 			    struct kvm *kvm);
 int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 struct kvm_kernel_irq_routing_entry *e,
@@ -46,11 +49,33 @@ static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_xen_enabled.key) &&
-	    vcpu->arch.xen.vcpu_info_set && vcpu->kvm->arch.xen.upcall_vector)
+	    vcpu->arch.xen.vcpu_info_cache.active &&
+	    vcpu->kvm->arch.xen.upcall_vector)
 		return __kvm_xen_has_interrupt(vcpu);
 
 	return 0;
 }
+
+static inline bool kvm_xen_has_pending_events(struct kvm_vcpu *vcpu)
+{
+	return static_branch_unlikely(&kvm_xen_enabled.key) &&
+		vcpu->arch.xen.evtchn_pending_sel;
+}
+
+static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu)
+{
+	return !!vcpu->arch.xen.timer_virq;
+}
+
+static inline int kvm_xen_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	if (kvm_xen_hypercall_enabled(vcpu->kvm) && kvm_xen_timer_enabled(vcpu))
+		return atomic_read(&vcpu->arch.xen.timer_pending);
+
+	return 0;
+}
+
+void kvm_xen_inject_timer_irqs(struct kvm_vcpu *vcpu);
 #else
 static inline int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data)
 {
@@ -65,6 +90,14 @@ static inline void kvm_xen_destroy_vm(struct kvm *kvm)
 {
 }
 
+static inline void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
+{
+}
+
 static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 {
 	return false;
@@ -79,6 +112,29 @@ static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
+
+static inline void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline bool kvm_xen_has_pending_events(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
+static inline int kvm_xen_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static inline void kvm_xen_inject_timer_irqs(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
 #endif
 
 int kvm_xen_hypercall(struct kvm_vcpu *vcpu);

include/linux/kvm_host.h

@@ -611,7 +611,8 @@ struct kvm_hv_sint {
 
 struct kvm_xen_evtchn {
 	u32 port;
-	u32 vcpu;
+	u32 vcpu_id;
+	int vcpu_idx;
 	u32 priority;
 };
 

include/uapi/linux/kvm.h

@@ -1144,6 +1144,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_MEM_OP_EXTENSION 211
 #define KVM_CAP_PMU_CAPABILITY 212
 #define KVM_CAP_DISABLE_QUIRKS2 213
+#define KVM_CAP_VM_TSC_CONTROL 214
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1232,6 +1233,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1470,7 +1472,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
 /* Available with KVM_CAP_PPC_GET_PVINFO */
 #define KVM_PPC_GET_PVINFO	  _IOW(KVMIO,  0xa1, struct kvm_ppc_pvinfo)
-/* Available with KVM_CAP_TSC_CONTROL */
+/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with
+*  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
 /* Available with KVM_CAP_PCI_2_3 */
@@ -1686,6 +1689,32 @@ struct kvm_xen_hvm_attr {
 		struct {
 			__u64 gfn;
 		} shared_info;
+		struct {
+			__u32 send_port;
+			__u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+			__u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN		(1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE		(1 << 1)
+#define KVM_XEN_EVTCHN_RESET		(1 << 2)
+			/*
+			 * Events sent by the guest are either looped back to
+			 * the guest itself (potentially on a different port#)
+			 * or signalled via an eventfd.
+			 */
+			union {
+				struct {
+					__u32 port;
+					__u32 vcpu;
+					__u32 priority;
+				} port;
+				struct {
+					__u32 port; /* Zero for eventfd */
+					__s32 fd;
+				} eventfd;
+				__u32 padding[4];
+			} deliver;
+		} evtchn;
+		__u32 xen_version;
 		__u64 pad[8];
 	} u;
 };
@@ -1694,11 +1723,17 @@ struct kvm_xen_hvm_attr {
 #define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
 #define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN		0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION		0x4
 
 /* Per-vCPU Xen attributes */
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
 #define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
 
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_HVM_EVTCHN_SEND	_IOW(KVMIO,  0xd0, struct kvm_irq_routing_xen_evtchn)
+
 #define KVM_GET_SREGS2             _IOR(KVMIO,  0xcc, struct kvm_sregs2)
 #define KVM_SET_SREGS2             _IOW(KVMIO,  0xcd, struct kvm_sregs2)
 
@@ -1716,6 +1751,13 @@ struct kvm_xen_vcpu_attr {
 			__u64 time_blocked;
 			__u64 time_offline;
 		} runstate;
+		__u32 vcpu_id;
+		struct {
+			__u32 port;
+			__u32 priority;
+			__u64 expires_ns;
+		} timer;
+		__u8 vector;
 	} u;
 };
 
@@ -1726,6 +1768,10 @@ struct kvm_xen_vcpu_attr {
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID		0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER		0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR	0x8
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {

tools/testing/selftests/kvm/.gitignore

@@ -16,6 +16,7 @@
 /x86_64/debug_regs
 /x86_64/evmcs_test
 /x86_64/emulator_error_test
+/x86_64/fix_hypercall_test
 /x86_64/get_msr_index_features
 /x86_64/kvm_clock_test
 /x86_64/kvm_pv_test

tools/testing/selftests/kvm/Makefile

@@ -48,6 +48,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
+TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
@@ -65,6 +66,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
+TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test

tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <linux/stringify.h>
+#include <stdint.h>
+
+#include "apic.h"
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+static bool ud_expected;
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+	GUEST_ASSERT(ud_expected);
+	GUEST_DONE();
+}
+
+extern unsigned char svm_hypercall_insn;
+static uint64_t svm_do_sched_yield(uint8_t apic_id)
+{
+	uint64_t ret;
+
+	asm volatile("mov %1, %%rax\n\t"
+		     "mov %2, %%rbx\n\t"
+		     "svm_hypercall_insn:\n\t"
+		     "vmmcall\n\t"
+		     "mov %%rax, %0\n\t"
+		     : "=r"(ret)
+		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
+		     : "rax", "rbx", "memory");
+
+	return ret;
+}
+
+extern unsigned char vmx_hypercall_insn;
+static uint64_t vmx_do_sched_yield(uint8_t apic_id)
+{
+	uint64_t ret;
+
+	asm volatile("mov %1, %%rax\n\t"
+		     "mov %2, %%rbx\n\t"
+		     "vmx_hypercall_insn:\n\t"
+		     "vmcall\n\t"
+		     "mov %%rax, %0\n\t"
+		     : "=r"(ret)
+		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
+		     : "rax", "rbx", "memory");
+
+	return ret;
+}
+
+static void assert_hypercall_insn(unsigned char *exp_insn, unsigned char *obs_insn)
+{
+	uint32_t exp = 0, obs = 0;
+
+	memcpy(&exp, exp_insn, sizeof(exp));
+	memcpy(&obs, obs_insn, sizeof(obs));
+
+	GUEST_ASSERT_EQ(exp, obs);
+}
+
+static void guest_main(void)
+{
+	unsigned char *native_hypercall_insn, *hypercall_insn;
+	uint8_t apic_id;
+
+	apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID));
+
+	if (is_intel_cpu()) {
+		native_hypercall_insn = &vmx_hypercall_insn;
+		hypercall_insn = &svm_hypercall_insn;
+		svm_do_sched_yield(apic_id);
+	} else if (is_amd_cpu()) {
+		native_hypercall_insn = &svm_hypercall_insn;
+		hypercall_insn = &vmx_hypercall_insn;
+		vmx_do_sched_yield(apic_id);
+	} else {
+		GUEST_ASSERT(0);
+		/* unreachable */
+		return;
+	}
+
+	GUEST_ASSERT(!ud_expected);
+	assert_hypercall_insn(native_hypercall_insn, hypercall_insn);
+	GUEST_DONE();
+}
+
+static void setup_ud_vector(struct kvm_vm *vm)
+{
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+}
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_run(vm, VCPU_ID);
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_SYNC:
+		pr_info("%s: %016lx\n", (const char *)uc.args[2], uc.args[3]);
+		break;
+	case UCALL_DONE:
+		return;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, uc.args[1]);
+	default:
+		TEST_FAIL("Unhandled ucall: %ld\nexit_reason: %u (%s)",
+			  uc.cmd, run->exit_reason, exit_reason_str(run->exit_reason));
+	}
+}
+
+static void test_fix_hypercall(void)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	setup_ud_vector(vm);
+
+	ud_expected = false;
+	sync_global_to_guest(vm, ud_expected);
+
+	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
+
+	enter_guest(vm);
+}
+
+static void test_fix_hypercall_disabled(void)
+{
+	struct kvm_enable_cap cap = {0};
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	setup_ud_vector(vm);
+
+	cap.cap = KVM_CAP_DISABLE_QUIRKS2;
+	cap.args[0] = KVM_X86_QUIRK_FIX_HYPERCALL_INSN;
+	vm_enable_cap(vm, &cap);
+
+	ud_expected = true;
+	sync_global_to_guest(vm, ud_expected);
+
+	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
+
+	enter_guest(vm);
+}
+
+int main(void)
+{
+	if (!(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) {
+		print_skip("KVM_X86_QUIRK_HYPERCALL_INSN not supported");
+		exit(KSFT_SKIP);
+	}
+
+	test_fix_hypercall();
+	test_fix_hypercall_disabled();
+}

tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_vmcall_test
+ *
+ * Copyright © 2021 Amazon.com, Inc. or its affiliates.
+ *
+ * Xen shared_info / pvclock testing
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#include <stdint.h>
+#include <time.h>
+#include <sched.h>
+#include <signal.h>
+#include <pthread.h>
+
+#define NR_TEST_VCPUS 20
+
+static struct kvm_vm *vm;
+pthread_spinlock_t create_lock;
+
+#define TEST_TSC_KHZ    2345678UL
+#define TEST_TSC_OFFSET 200000000
+
+uint64_t tsc_sync;
+static void guest_code(void)
+{
+	uint64_t start_tsc, local_tsc, tmp;
+
+	start_tsc = rdtsc();
+	do {
+		tmp = READ_ONCE(tsc_sync);
+		local_tsc = rdtsc();
+		WRITE_ONCE(tsc_sync, local_tsc);
+		if (unlikely(local_tsc < tmp))
+			GUEST_SYNC_ARGS(0, local_tsc, tmp, 0, 0);
+
+	} while (local_tsc - start_tsc < 5000 * TEST_TSC_KHZ);
+
+	GUEST_DONE();
+}
+
+
+static void *run_vcpu(void *_cpu_nr)
+{
+	unsigned long cpu = (unsigned long)_cpu_nr;
+	unsigned long failures = 0;
+	static bool first_cpu_done;
+
+	/* The kernel is fine, but vm_vcpu_add_default() needs locking */
+	pthread_spin_lock(&create_lock);
+
+	vm_vcpu_add_default(vm, cpu, guest_code);
+
+	if (!first_cpu_done) {
+		first_cpu_done = true;
+		vcpu_set_msr(vm, cpu, MSR_IA32_TSC, TEST_TSC_OFFSET);
+	}
+
+	pthread_spin_unlock(&create_lock);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, cpu);
+                struct ucall uc;
+
+                vcpu_run(vm, cpu);
+                TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+                            "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+                            run->exit_reason,
+                            exit_reason_str(run->exit_reason));
+
+                switch (get_ucall(vm, cpu, &uc)) {
+                case UCALL_DONE:
+			goto out;
+
+                case UCALL_SYNC:
+			printf("Guest %ld sync %lx %lx %ld\n", cpu, uc.args[2], uc.args[3], uc.args[2] - uc.args[3]);
+			failures++;
+			break;
+
+                default:
+                        TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+ out:
+	return (void *)failures;
+}
+
+int main(int argc, char *argv[])
+{
+        if (!kvm_check_cap(KVM_CAP_VM_TSC_CONTROL)) {
+		print_skip("KVM_CAP_VM_TSC_CONTROL not available");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default_with_vcpus(0, DEFAULT_STACK_PGS * NR_TEST_VCPUS, 0, guest_code, NULL);
+	vm_ioctl(vm, KVM_SET_TSC_KHZ, (void *) TEST_TSC_KHZ);
+
+	pthread_spin_init(&create_lock, PTHREAD_PROCESS_PRIVATE);
+	pthread_t cpu_threads[NR_TEST_VCPUS];
+	unsigned long cpu;
+	for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++)
+		pthread_create(&cpu_threads[cpu], NULL, run_vcpu, (void *)cpu);
+
+	unsigned long failures = 0;
+	for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++) {
+		void *this_cpu_failures;
+		pthread_join(cpu_threads[cpu], &this_cpu_failures);
+		failures += (unsigned long)this_cpu_failures;
+	}
+
+	TEST_ASSERT(!failures, "TSC sync failed");
+	pthread_spin_destroy(&create_lock);
+	kvm_vm_free(vm);
+	return 0;
+}