Merge tag 'kvm-4.3-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "A very small release for x86 and s390 KVM.

   - s390: timekeeping changes, cleanups and fixes

   - x86: support for Hyper-V MSRs to report crashes, and a bunch of
     cleanups.

  One interesting feature that was planned for 4.3 (emulating the local
  APIC in kernel while keeping the IOAPIC and 8254 in userspace) had to
  be delayed because Intel complained about my reading of the manual"

* tag 'kvm-4.3-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (42 commits)
  x86/kvm: Rename VMX's segment access rights defines
  KVM: x86/vPMU: Fix unnecessary signed extension for AMD PERFCTRn
  kvm: x86: Fix error handling in the function kvm_lapic_sync_from_vapic
  KVM: s390: Fix assumption that kvm_set_irq_routing is always run successfully
  KVM: VMX: drop ept misconfig check
  KVM: MMU: fully check zero bits for sptes
  KVM: MMU: introduce is_shadow_zero_bits_set()
  KVM: MMU: introduce the framework to check zero bits on sptes
  KVM: MMU: split reset_rsvds_bits_mask_ept
  KVM: MMU: split reset_rsvds_bits_mask
  KVM: MMU: introduce rsvd_bits_validate
  KVM: MMU: move FNAME(is_rsvd_bits_set) to mmu.c
  KVM: MMU: fix validation of mmio page fault
  KVM: MTRR: Use default type for non-MTRR-covered gfn before WARN_ON
  KVM: s390: host STP toleration for VMs
  KVM: x86: clean/fix memory barriers in irqchip_in_kernel
  KVM: document memory barriers for kvm->vcpus/kvm->online_vcpus
  KVM: x86: remove unnecessary memory barriers for shared MSRs
  KVM: move code related to KVM_SET_BOOT_CPU_ID to x86
  KVM: s390: log capability enablement and vm attribute changes
  ...

Documentation/s390/00-INDEX

@@ -16,8 +16,6 @@ Debugging390.txt
 	- hints for debugging on s390 systems.
 driver-model.txt
 	- information on s390 devices and the driver model.
-kvm.txt
-	- ioctl calls to /dev/kvm on s390.
 monreader.txt
 	- information on accessing the z/VM monitor stream from Linux.
 qeth.txt

Documentation/s390/kvm.txt

@@ -1,125 +0,0 @@
-*** BIG FAT WARNING ***
-The kvm module is currently in EXPERIMENTAL state for s390. This means that
-the interface to the module is not yet considered to remain stable. Thus, be
-prepared that we keep breaking your userspace application and guest
-compatibility over and over again until we feel happy with the result. Make sure
-your guest kernel, your host kernel, and your userspace launcher are in a
-consistent state.
-
-This Documentation describes the unique ioctl calls to /dev/kvm, the resulting
-kvm-vm file descriptors, and the kvm-vcpu file descriptors that differ from x86.
-
-1. ioctl calls to /dev/kvm
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_GET_API_VERSION
-KVM_CREATE_VM		(*) see note
-KVM_CHECK_EXTENSION
-KVM_GET_VCPU_MMAP_SIZE
-
-Notes:
-* KVM_CREATE_VM may fail on s390, if the calling process has multiple
-threads and has not called KVM_S390_ENABLE_SIE before.
-
-In addition, on s390 the following architecture specific ioctls are supported:
-ioctl:		KVM_S390_ENABLE_SIE
-args:		none
-see also:	include/linux/kvm.h
-This call causes the kernel to switch on PGSTE in the user page table. This
-operation is needed in order to run a virtual machine, and it requires the
-calling process to be single-threaded. Note that the first call to KVM_CREATE_VM
-will implicitly try to switch on PGSTE if the user process has not called
-KVM_S390_ENABLE_SIE before. User processes that want to launch multiple threads
-before creating a virtual machine have to call KVM_S390_ENABLE_SIE, or will
-observe an error calling KVM_CREATE_VM. Switching on PGSTE is a one-time
-operation, is not reversible, and will persist over the entire lifetime of
-the calling process. It does not have any user-visible effect other than a small
-performance penalty.
-
-2. ioctl calls to the kvm-vm file descriptor
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_CREATE_VCPU
-KVM_SET_USER_MEMORY_REGION      (*) see note
-KVM_GET_DIRTY_LOG		(**) see note
-
-Notes:
-*  kvm does only allow exactly one memory slot on s390, which has to start
-   at guest absolute address zero and at a user address that is aligned on any
-   page boundary. This hardware "limitation" allows us to have a few unique
-   optimizations. The memory slot doesn't have to be filled
-   with memory actually, it may contain sparse holes. That said, with different
-   user memory layout this does still allow a large flexibility when
-   doing the guest memory setup.
-** KVM_GET_DIRTY_LOG doesn't work properly yet. The user will receive an empty
-log. This ioctl call is only needed for guest migration, and we intend to
-implement this one in the future.
-
-In addition, on s390 the following architecture specific ioctls for the kvm-vm
-file descriptor are supported:
-ioctl:		KVM_S390_INTERRUPT
-args:		struct kvm_s390_interrupt *
-see also:	include/linux/kvm.h
-This ioctl is used to submit a floating interrupt for a virtual machine.
-Floating interrupts may be delivered to any virtual cpu in the configuration.
-Only some interrupt types defined in include/linux/kvm.h make sense when
-submitted as floating interrupts. The following interrupts are not considered
-to be useful as floating interrupts, and a call to inject them will result in
--EINVAL error code: program interrupts and interprocessor signals. Valid
-floating interrupts are:
-KVM_S390_INT_VIRTIO
-KVM_S390_INT_SERVICE
-
-3. ioctl calls to the kvm-vcpu file descriptor
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_RUN
-KVM_GET_REGS
-KVM_SET_REGS
-KVM_GET_SREGS
-KVM_SET_SREGS
-KVM_GET_FPU
-KVM_SET_FPU
-
-In addition, on s390 the following architecture specific ioctls for the
-kvm-vcpu file descriptor are supported:
-ioctl:		KVM_S390_INTERRUPT
-args:		struct kvm_s390_interrupt *
-see also:	include/linux/kvm.h
-This ioctl is used to submit an interrupt for a specific virtual cpu.
-Only some interrupt types defined in include/linux/kvm.h make sense when
-submitted for a specific cpu. The following interrupts are not considered
-to be useful, and a call to inject them will result in -EINVAL error code:
-service processor calls and virtio interrupts. Valid interrupt types are:
-KVM_S390_PROGRAM_INT
-KVM_S390_SIGP_STOP
-KVM_S390_RESTART
-KVM_S390_SIGP_SET_PREFIX
-KVM_S390_INT_EMERGENCY
-
-ioctl:		KVM_S390_STORE_STATUS
-args:		unsigned long
-see also:	include/linux/kvm.h
-This ioctl stores the state of the cpu at the guest real address given as
-argument, unless one of the following values defined in include/linux/kvm.h
-is given as argument:
-KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
-absolute lowcore as defined by the principles of operation
-KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
-its prefix page just like the dump tool that comes with zipl. This is useful
-to create a system dump for use with lkcdutils or crash.
-
-ioctl:		KVM_S390_SET_INITIAL_PSW
-args:		struct kvm_s390_psw *
-see also:	include/linux/kvm.h
-This ioctl can be used to set the processor status word (psw) of a stopped cpu
-prior to running it with KVM_RUN. Note that this call is not required to modify
-the psw during sie intercepts that fall back to userspace because struct kvm_run
-does contain the psw, and this value is evaluated during reentry of KVM_RUN
-after the intercept exit was recognized.
-
-ioctl:		KVM_S390_INITIAL_RESET
-args:		none
-see also:	include/linux/kvm.h
-This ioctl can be used to perform an initial cpu reset as defined by the
-principles of operation. The target cpu has to be in stopped state.

Documentation/virtual/kvm/api.txt

@@ -3277,6 +3277,7 @@ should put the acknowledged interrupt vector into the 'epr' field.
 		struct {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
@@ -3296,6 +3297,10 @@ Valid values for 'type' are:
   KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
    As with SHUTDOWN, userspace can choose to ignore the request, or
    to schedule the reset to occur in the future and may call KVM_RUN again.
+  KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+   has requested a crash condition maintenance. Userspace can choose
+   to ignore the request, or to gather VM memory core dump and/or
+   reset/shutdown of the VM.
 
 		/* Fix the size of the union. */
 		char padding[256];

arch/s390/include/asm/etr.h

@@ -214,6 +214,9 @@ static inline int etr_ptff(void *ptff_block, unsigned int func)
 void etr_switch_to_local(void);
 void etr_sync_check(void);
 
+/* notifier for syncs */
+extern struct atomic_notifier_head s390_epoch_delta_notifier;
+
 /* STP interruption parameter */
 struct stp_irq_parm {
 	unsigned int _pad0	: 14;

arch/s390/include/asm/kvm_host.h

@@ -258,6 +258,9 @@ struct kvm_vcpu_stat {
 	u32 diagnose_10;
 	u32 diagnose_44;
 	u32 diagnose_9c;
+	u32 diagnose_258;
+	u32 diagnose_308;
+	u32 diagnose_500;
 };
 
 #define PGM_OPERATION			0x01
@@ -630,7 +633,6 @@ extern char sie_exit;
 
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_check_processor_compat(void *rtn) {}
-static inline void kvm_arch_exit(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}

arch/s390/kernel/time.c

@@ -58,6 +58,9 @@ EXPORT_SYMBOL_GPL(sched_clock_base_cc);
 
 static DEFINE_PER_CPU(struct clock_event_device, comparators);
 
+ATOMIC_NOTIFIER_HEAD(s390_epoch_delta_notifier);
+EXPORT_SYMBOL(s390_epoch_delta_notifier);
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -752,7 +755,7 @@ static void clock_sync_cpu(struct clock_sync_data *sync)
 static int etr_sync_clock(void *data)
 {
 	static int first;
-	unsigned long long clock, old_clock, delay, delta;
+	unsigned long long clock, old_clock, clock_delta, delay, delta;
 	struct clock_sync_data *etr_sync;
 	struct etr_aib *sync_port, *aib;
 	int port;
@@ -789,6 +792,9 @@ static int etr_sync_clock(void *data)
 		delay = (unsigned long long)
 			(aib->edf2.etv - sync_port->edf2.etv) << 32;
 		delta = adjust_time(old_clock, clock, delay);
+		clock_delta = clock - old_clock;
+		atomic_notifier_call_chain(&s390_epoch_delta_notifier, 0,
+					   &clock_delta);
 		etr_sync->fixup_cc = delta;
 		fixup_clock_comparator(delta);
 		/* Verify that the clock is properly set. */
@@ -1526,7 +1532,7 @@ void stp_island_check(void)
 static int stp_sync_clock(void *data)
 {
 	static int first;
-	unsigned long long old_clock, delta;
+	unsigned long long old_clock, delta, new_clock, clock_delta;
 	struct clock_sync_data *stp_sync;
 	int rc;
 
@@ -1551,7 +1557,11 @@ static int stp_sync_clock(void *data)
 		old_clock = get_tod_clock();
 		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0);
 		if (rc == 0) {
-			delta = adjust_time(old_clock, get_tod_clock(), 0);
+			new_clock = get_tod_clock();
+			delta = adjust_time(old_clock, new_clock, 0);
+			clock_delta = new_clock - old_clock;
+			atomic_notifier_call_chain(&s390_epoch_delta_notifier,
+						   0, &clock_delta);
 			fixup_clock_comparator(delta);
 			rc = chsc_sstpi(stp_page, &stp_info,
 					sizeof(struct stp_sstpi));

arch/s390/kvm/diag.c

@@ -27,13 +27,13 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 
 	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+	vcpu->stat.diagnose_10++;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
 	    || start < 2 * PAGE_SIZE)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
-	vcpu->stat.diagnose_10++;
 
 	/*
 	 * We checked for start >= end above, so lets check for the
@@ -75,6 +75,9 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 	u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
 	u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
 
+	VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
+		   vcpu->run->s.regs.gprs[rx]);
+	vcpu->stat.diagnose_258++;
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
@@ -85,6 +88,9 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 
 	switch (parm.subcode) {
 	case 0: /* TOKEN */
+		VCPU_EVENT(vcpu, 3, "pageref token addr 0x%llx "
+			   "select mask 0x%llx compare mask 0x%llx",
+			   parm.token_addr, parm.select_mask, parm.compare_mask);
 		if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) {
 			/*
 			 * If the pagefault handshake is already activated,
@@ -114,6 +120,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 		 * the cancel, therefore to reduce code complexity, we assume
 		 * all outstanding tokens are already pending.
 		 */
+		VCPU_EVENT(vcpu, 3, "pageref cancel addr 0x%llx", parm.token_addr);
 		if (parm.token_addr || parm.select_mask ||
 		    parm.compare_mask || parm.zarch)
 			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -174,7 +181,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
 	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
-	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+	VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
+	vcpu->stat.diagnose_308++;
 	switch (subcode) {
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
@@ -202,6 +210,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 {
 	int ret;
 
+	vcpu->stat.diagnose_500++;
 	/* No virtio-ccw notification? Get out quickly. */
 	if (!vcpu->kvm->arch.css_support ||
 	    (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))

arch/s390/kvm/guestdbg.c

@@ -473,10 +473,45 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->iprcc &= ~PGM_PER;
 }
 
+#define pssec(vcpu) (vcpu->arch.sie_block->gcr[1] & _ASCE_SPACE_SWITCH)
+#define hssec(vcpu) (vcpu->arch.sie_block->gcr[13] & _ASCE_SPACE_SWITCH)
+#define old_ssec(vcpu) ((vcpu->arch.sie_block->tecmc >> 31) & 0x1)
+#define old_as_is_home(vcpu) !(vcpu->arch.sie_block->tecmc & 0xffff)
+
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 {
+	int new_as;
+
 	if (debug_exit_required(vcpu))
 		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
 
 	filter_guest_per_event(vcpu);
+
+	/*
+	 * Only RP, SAC, SACF, PT, PTI, PR, PC instructions can trigger
+	 * a space-switch event. PER events enforce space-switch events
+	 * for these instructions. So if no PER event for the guest is left,
+	 * we might have to filter the space-switch element out, too.
+	 */
+	if (vcpu->arch.sie_block->iprcc == PGM_SPACE_SWITCH) {
+		vcpu->arch.sie_block->iprcc = 0;
+		new_as = psw_bits(vcpu->arch.sie_block->gpsw).as;
+
+		/*
+		 * If the AS changed from / to home, we had RP, SAC or SACF
+		 * instruction. Check primary and home space-switch-event
+		 * controls. (theoretically home -> home produced no event)
+		 */
+		if (((new_as == PSW_AS_HOME) ^ old_as_is_home(vcpu)) &&
+		     (pssec(vcpu) || hssec(vcpu)))
+			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
+
+		/*
+		 * PT, PTI, PR, PC instruction operate on primary AS only. Check
+		 * if the primary-space-switch-event control was or got set.
+		 */
+		if (new_as == PSW_AS_PRIMARY && !old_as_is_home(vcpu) &&
+		    (pssec(vcpu) || old_ssec(vcpu)))
+			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
+	}
 }

arch/s390/kvm/interrupt.c

@@ -30,7 +30,6 @@
 #define IOINT_SCHID_MASK 0x0000ffff
 #define IOINT_SSID_MASK 0x00030000
 #define IOINT_CSSID_MASK 0x03fc0000
-#define IOINT_AI_MASK 0x04000000
 #define PFAULT_INIT 0x0600
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
@@ -72,9 +71,13 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
 
 static int ckc_irq_pending(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
 	if (!(vcpu->arch.sie_block->ckc <
-	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
+	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
+		preempt_enable();
 		return 0;
+	}
+	preempt_enable();
 	return ckc_interrupts_enabled(vcpu);
 }
 
@@ -311,8 +314,8 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
 	li->irq.ext.ext_params2 = 0;
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
-		   0, ext.ext_params2);
+	VCPU_EVENT(vcpu, 4, "deliver: pfault init token 0x%llx",
+		   ext.ext_params2);
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_INT_PFAULT_INIT,
 					 0, ext.ext_params2);
@@ -368,7 +371,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
 	spin_unlock(&fi->lock);
 
 	if (deliver) {
-		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+		VCPU_EVENT(vcpu, 3, "deliver: machine check mcic 0x%llx",
 			   mchk.mcic);
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 						 KVM_S390_MCHK,
@@ -403,7 +406,7 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc;
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+	VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
 	vcpu->stat.deliver_restart_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
@@ -427,7 +430,6 @@ static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
 	vcpu->stat.deliver_prefix_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_SIGP_SET_PREFIX,
@@ -450,7 +452,7 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
 		clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp emerg");
 	vcpu->stat.deliver_emergency_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
 					 cpu_addr, 0);
@@ -477,7 +479,7 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
+	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp ext call");
 	vcpu->stat.deliver_external_call++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_INT_EXTERNAL_CALL,
@@ -506,7 +508,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	memset(&li->irq.pgm, 0, sizeof(pgm_info));
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
 		   pgm_info.code, ilc);
 	vcpu->stat.deliver_program_int++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
@@ -622,7 +624,7 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
 	spin_unlock(&fi->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+	VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
 		   ext.ext_params);
 	vcpu->stat.deliver_service_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
@@ -651,9 +653,6 @@ static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
 					struct kvm_s390_interrupt_info,
 					list);
 	if (inti) {
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
-				KVM_S390_INT_PFAULT_DONE, 0,
-				inti->ext.ext_params2);
 		list_del(&inti->list);
 		fi->counters[FIRQ_CNTR_PFAULT] -= 1;
 	}
@@ -662,6 +661,12 @@ static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
 	spin_unlock(&fi->lock);
 
 	if (inti) {
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+						 KVM_S390_INT_PFAULT_DONE, 0,
+						 inti->ext.ext_params2);
+		VCPU_EVENT(vcpu, 4, "deliver: pfault done token 0x%llx",
+			   inti->ext.ext_params2);
+
 		rc  = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
 				(u16 *)__LC_EXT_INT_CODE);
 		rc |= put_guest_lc(vcpu, PFAULT_DONE,
@@ -691,7 +696,7 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
 					list);
 	if (inti) {
 		VCPU_EVENT(vcpu, 4,
-			   "interrupt: virtio parm:%x,parm64:%llx",
+			   "deliver: virtio parm: 0x%x,parm64: 0x%llx",
 			   inti->ext.ext_params, inti->ext.ext_params2);
 		vcpu->stat.deliver_virtio_interrupt++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
@@ -741,7 +746,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 					struct kvm_s390_interrupt_info,
 					list);
 	if (inti) {
-		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
+		VCPU_EVENT(vcpu, 4, "deliver: I/O 0x%llx", inti->type);
 		vcpu->stat.deliver_io_int++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 				inti->type,
@@ -855,7 +860,9 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		goto no_timer;
 	}
 
+	preempt_disable();
 	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	preempt_enable();
 	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
 	/* underflow */
@@ -864,7 +871,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 
 	__set_cpu_idle(vcpu);
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
-	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
+	VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	kvm_vcpu_block(vcpu);
@@ -894,7 +901,9 @@ enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 	u64 now, sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
+	preempt_disable();
 	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	preempt_enable();
 	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
 	/*
@@ -968,6 +977,10 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	VCPU_EVENT(vcpu, 3, "inject: program irq code 0x%x", irq->u.pgm.code);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
+				   irq->u.pgm.code, 0);
+
 	li->irq.pgm = irq->u.pgm;
 	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
 	return 0;
@@ -978,9 +991,6 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_irq irq;
 
-	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
-				   0, 1);
 	spin_lock(&li->lock);
 	irq.u.pgm.code = code;
 	__inject_prog(vcpu, &irq);
@@ -996,10 +1006,6 @@ int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
 	struct kvm_s390_irq irq;
 	int rc;
 
-	VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
-		   pgm_info->code);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
-				   pgm_info->code, 0, 1);
 	spin_lock(&li->lock);
 	irq.u.pgm = *pgm_info;
 	rc = __inject_prog(vcpu, &irq);
@@ -1012,11 +1018,11 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx",
-		   irq->u.ext.ext_params, irq->u.ext.ext_params2);
+	VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
+		   irq->u.ext.ext_params2);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
 				   irq->u.ext.ext_params,
-				   irq->u.ext.ext_params2, 2);
+				   irq->u.ext.ext_params2);
 
 	li->irq.ext = irq->u.ext;
 	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
@@ -1045,10 +1051,10 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
 	uint16_t src_id = irq->u.extcall.code;
 
-	VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
+	VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
 		   src_id);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
-				   src_id, 0, 2);
+				   src_id, 0);
 
 	/* sending vcpu invalid */
 	if (src_id >= KVM_MAX_VCPUS ||
@@ -1070,10 +1076,10 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
 
-	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
+	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
 		   irq->u.prefix.address);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
-				   irq->u.prefix.address, 0, 2);
+				   irq->u.prefix.address, 0);
 
 	if (!is_vcpu_stopped(vcpu))
 		return -EBUSY;
@@ -1090,7 +1096,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_stop_info *stop = &li->irq.stop;
 	int rc = 0;
 
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
 
 	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
 		return -EINVAL;
@@ -1114,8 +1120,8 @@ static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
 	set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
 	return 0;
@@ -1126,10 +1132,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: emergency %u\n",
+	VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
 		   irq->u.emerg.code);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
-				   irq->u.emerg.code, 0, 2);
+				   irq->u.emerg.code, 0);
 
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
@@ -1142,10 +1148,10 @@ static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
 
-	VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+	VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
 		   irq->u.mchk.mcic);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
-				   irq->u.mchk.mcic, 2);
+				   irq->u.mchk.mcic);
 
 	/*
 	 * Because repressible machine checks can be indicated along with
@@ -1172,9 +1178,9 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
-				   0, 0, 2);
+				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
@@ -1185,9 +1191,9 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
-				   0, 0, 2);
+				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
@@ -1435,20 +1441,20 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_INT_SERVICE:
-		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
+		VM_EVENT(kvm, 4, "inject: sclp parm:%x", s390int->parm);
 		inti->ext.ext_params = s390int->parm;
 		break;
 	case KVM_S390_INT_PFAULT_DONE:
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_MCHK:
-		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+		VM_EVENT(kvm, 3, "inject: machine check mcic 0x%llx",
 			 s390int->parm64);
 		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
 		inti->mchk.mcic = s390int->parm64;
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (inti->type & IOINT_AI_MASK)
+		if (inti->type & KVM_S390_INT_IO_AI_MASK)
 			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
 		else
 			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
@@ -1535,8 +1541,6 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 
 	switch (irq->type) {
 	case KVM_S390_PROGRAM_INT:
-		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
-			   irq->u.pgm.code);
 		rc = __inject_prog(vcpu, irq);
 		break;
 	case KVM_S390_SIGP_SET_PREFIX:

arch/s390/kvm/kvm-s390.c

@@ -28,6 +28,7 @@
 #include <linux/vmalloc.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
+#include <asm/etr.h>
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
@@ -108,6 +109,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "diagnose_10", VCPU_STAT(diagnose_10) },
 	{ "diagnose_44", VCPU_STAT(diagnose_44) },
 	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
+	{ "diagnose_258", VCPU_STAT(diagnose_258) },
+	{ "diagnose_308", VCPU_STAT(diagnose_308) },
+	{ "diagnose_500", VCPU_STAT(diagnose_500) },
 	{ NULL }
 };
 
@@ -124,6 +128,7 @@ unsigned long kvm_s390_fac_list_mask_size(void)
 }
 
 static struct gmap_notifier gmap_notifier;
+debug_info_t *kvm_s390_dbf;
 
 /* Section: not file related */
 int kvm_arch_hardware_enable(void)
@@ -134,24 +139,69 @@ int kvm_arch_hardware_enable(void)
 
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
 
+/*
+ * This callback is executed during stop_machine(). All CPUs are therefore
+ * temporarily stopped. In order not to change guest behavior, we have to
+ * disable preemption whenever we touch the epoch of kvm and the VCPUs,
+ * so a CPU won't be stopped while calculating with the epoch.
+ */
+static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
+			  void *v)
+{
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+	unsigned long long *delta = v;
+
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		kvm->arch.epoch -= *delta;
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			vcpu->arch.sie_block->epoch -= *delta;
+		}
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_clock_notifier = {
+	.notifier_call = kvm_clock_sync,
+};
+
 int kvm_arch_hardware_setup(void)
 {
 	gmap_notifier.notifier_call = kvm_gmap_notifier;
 	gmap_register_ipte_notifier(&gmap_notifier);
+	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
+				       &kvm_clock_notifier);
 	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)
 {
 	gmap_unregister_ipte_notifier(&gmap_notifier);
+	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
+					 &kvm_clock_notifier);
 }
 
 int kvm_arch_init(void *opaque)
 {
+	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
+	if (!kvm_s390_dbf)
+		return -ENOMEM;
+
+	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
+		debug_unregister(kvm_s390_dbf);
+		return -ENOMEM;
+	}
+
 	/* Register floating interrupt controller interface. */
 	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 }
 
+void kvm_arch_exit(void)
+{
+	debug_unregister(kvm_s390_dbf);
+}
+
 /* Section: device related */
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg)
@@ -281,10 +331,12 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 
 	switch (cap->cap) {
 	case KVM_CAP_S390_IRQCHIP:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_IRQCHIP");
 		kvm->arch.use_irqchip = 1;
 		r = 0;
 		break;
 	case KVM_CAP_S390_USER_SIGP:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_SIGP");
 		kvm->arch.user_sigp = 1;
 		r = 0;
 		break;
@@ -295,8 +347,11 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 			r = 0;
 		} else
 			r = -EINVAL;
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
+			 r ? "(not available)" : "(success)");
 		break;
 	case KVM_CAP_S390_USER_STSI:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
 		r = 0;
 		break;
@@ -314,6 +369,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	switch (attr->attr) {
 	case KVM_S390_VM_MEM_LIMIT_SIZE:
 		ret = 0;
+		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
+			 kvm->arch.gmap->asce_end);
 		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
 			ret = -EFAULT;
 		break;
@@ -330,7 +387,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	unsigned int idx;
 	switch (attr->attr) {
 	case KVM_S390_VM_MEM_ENABLE_CMMA:
+		/* enable CMMA only for z10 and later (EDAT_1) */
+		ret = -EINVAL;
+		if (!MACHINE_IS_LPAR || !MACHINE_HAS_EDAT1)
+			break;
+
 		ret = -EBUSY;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) == 0) {
 			kvm->arch.use_cmma = 1;
@@ -339,6 +402,11 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		mutex_unlock(&kvm->lock);
 		break;
 	case KVM_S390_VM_MEM_CLR_CMMA:
+		ret = -EINVAL;
+		if (!kvm->arch.use_cmma)
+			break;
+
+		VM_EVENT(kvm, 3, "%s", "RESET: CMMA states");
 		mutex_lock(&kvm->lock);
 		idx = srcu_read_lock(&kvm->srcu);
 		s390_reset_cmma(kvm->arch.gmap->mm);
@@ -374,6 +442,7 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 			}
 		}
 		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
 		break;
 	}
 	default:
@@ -400,22 +469,26 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
 		kvm->arch.crypto.aes_kw = 1;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
 		get_random_bytes(
 			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
 		kvm->arch.crypto.dea_kw = 1;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
 		kvm->arch.crypto.aes_kw = 0;
 		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
+		VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
 		kvm->arch.crypto.dea_kw = 0;
 		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
+		VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
 		break;
 	default:
 		mutex_unlock(&kvm->lock);
@@ -440,6 +513,7 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 
 	if (gtod_high != 0)
 		return -EINVAL;
+	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x\n", gtod_high);
 
 	return 0;
 }
@@ -459,12 +533,15 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 		return r;
 
 	mutex_lock(&kvm->lock);
+	preempt_disable();
 	kvm->arch.epoch = gtod - host_tod;
 	kvm_s390_vcpu_block_all(kvm);
 	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm)
 		cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
 	kvm_s390_vcpu_unblock_all(kvm);
+	preempt_enable();
 	mutex_unlock(&kvm->lock);
+	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx\n", gtod);
 	return 0;
 }
 
@@ -496,6 +573,7 @@ static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (copy_to_user((void __user *)attr->addr, &gtod_high,
 					 sizeof(gtod_high)))
 		return -EFAULT;
+	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x\n", gtod_high);
 
 	return 0;
 }
@@ -509,9 +587,12 @@ static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (r)
 		return r;
 
+	preempt_disable();
 	gtod = host_tod + kvm->arch.epoch;
+	preempt_enable();
 	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
 		return -EFAULT;
+	VM_EVENT(kvm, 3, "QUERY: TOD base: 0x%llx\n", gtod);
 
 	return 0;
 }
@@ -821,7 +902,9 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	}
 
 	/* Enable storage key handling for the guest */
-	s390_enable_skey();
+	r = s390_enable_skey();
+	if (r)
+		goto out;
 
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
@@ -879,8 +962,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.use_irqchip) {
 			/* Set up dummy routing. */
 			memset(&routing, 0, sizeof(routing));
-			kvm_set_irq_routing(kvm, &routing, 0, 0);
-			r = 0;
+			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
 		}
 		break;
 	}
@@ -1043,7 +1125,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	sprintf(debug_name, "kvm-%u", current->pid);
 
-	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
+	kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
 	if (!kvm->arch.dbf)
 		goto out_err;
 
@@ -1086,7 +1168,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.ipte_mutex);
 
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
-	VM_EVENT(kvm, 3, "%s", "vm created");
+	VM_EVENT(kvm, 3, "vm created with type %lu", type);
 
 	if (type & KVM_VM_S390_UCONTROL) {
 		kvm->arch.gmap = NULL;
@@ -1103,6 +1185,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
+	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -1110,6 +1193,7 @@ out_err:
 	free_page((unsigned long)kvm->arch.model.fac);
 	debug_unregister(kvm->arch.dbf);
 	free_page((unsigned long)(kvm->arch.sca));
+	KVM_EVENT(3, "creation of vm failed: %d", rc);
 	return rc;
 }
 
@@ -1131,7 +1215,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
 
-	if (kvm_s390_cmma_enabled(vcpu->kvm))
+	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
 	free_page((unsigned long)(vcpu->arch.sie_block));
 
@@ -1166,6 +1250,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
+	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -1264,7 +1349,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 	mutex_lock(&vcpu->kvm->lock);
+	preempt_disable();
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 	if (!kvm_is_ucontrol(vcpu->kvm))
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
@@ -1342,7 +1429,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	}
 	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
-	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
+	if (vcpu->kvm->arch.use_cmma) {
 		rc = kvm_s390_vcpu_setup_cmma(vcpu);
 		if (rc)
 			return rc;
@@ -1723,18 +1810,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return rc;
 }
 
-bool kvm_s390_cmma_enabled(struct kvm *kvm)
-{
-	if (!MACHINE_IS_LPAR)
-		return false;
-	/* only enable for z10 and later */
-	if (!MACHINE_HAS_EDAT1)
-		return false;
-	if (!kvm->arch.use_cmma)
-		return false;
-	return true;
-}
-
 static bool ibs_enabled(struct kvm_vcpu *vcpu)
 {
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
@@ -2340,6 +2415,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	case KVM_CAP_S390_CSS_SUPPORT:
 		if (!vcpu->kvm->arch.css_support) {
 			vcpu->kvm->arch.css_support = 1;
+			VM_EVENT(vcpu->kvm, 3, "%s", "ENABLE: CSS support");
 			trace_kvm_s390_enable_css(vcpu->kvm);
 		}
 		r = 0;

arch/s390/kvm/kvm-s390.h

@@ -27,6 +27,13 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 #define TDB_FORMAT1		1
 #define IS_ITDB_VALID(vcpu)	((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
 
+extern debug_info_t *kvm_s390_dbf;
+#define KVM_EVENT(d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \
+	  d_args); \
+} while (0)
+
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
 do { \
 	debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
@@ -65,6 +72,8 @@ static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu)
 
 static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 {
+	VCPU_EVENT(vcpu, 3, "set prefix of cpu %03u to 0x%x", vcpu->vcpu_id,
+		   prefix);
 	vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT;
 	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
@@ -217,8 +226,6 @@ void exit_sie(struct kvm_vcpu *vcpu);
 void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
-/* is cmma enabled */
-bool kvm_s390_cmma_enabled(struct kvm *kvm);
 unsigned long kvm_s390_fac_list_mask_size(void);
 extern unsigned long kvm_s390_fac_list_mask[];
 

arch/s390/kvm/priv.c

@@ -53,11 +53,14 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 		kvm_s390_set_psw_cc(vcpu, 3);
 		return 0;
 	}
+	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val);
 	val = (val - hostclk) & ~0x3fUL;
 
 	mutex_lock(&vcpu->kvm->lock);
+	preempt_disable();
 	kvm_for_each_vcpu(i, cpup, vcpu->kvm)
 		cpup->arch.sie_block->epoch = val;
+	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 
 	kvm_s390_set_psw_cc(vcpu, 0);
@@ -98,8 +101,6 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 	kvm_s390_set_prefix(vcpu, address);
-
-	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
 	trace_kvm_s390_handle_prefix(vcpu, 1, address);
 	return 0;
 }
@@ -129,7 +130,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+	VCPU_EVENT(vcpu, 3, "STPX: storing prefix 0x%x into 0x%llx", address, operand2);
 	trace_kvm_s390_handle_prefix(vcpu, 0, address);
 	return 0;
 }
@@ -155,7 +156,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", ga);
+	VCPU_EVENT(vcpu, 3, "STAP: storing cpu address (%u) to 0x%llx", vcpu_id, ga);
 	trace_kvm_s390_handle_stap(vcpu, ga);
 	return 0;
 }
@@ -167,6 +168,7 @@ static int __skey_check_enable(struct kvm_vcpu *vcpu)
 		return rc;
 
 	rc = s390_enable_skey();
+	VCPU_EVENT(vcpu, 3, "%s", "enabling storage keys for guest");
 	trace_kvm_s390_skey_related_inst(vcpu);
 	vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
 	return rc;
@@ -370,7 +372,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 			    &fac, sizeof(fac));
 	if (rc)
 		return rc;
-	VCPU_EVENT(vcpu, 5, "store facility list value %x", fac);
+	VCPU_EVENT(vcpu, 3, "STFL: store facility list 0x%x", fac);
 	trace_kvm_s390_handle_stfl(vcpu, fac);
 	return 0;
 }
@@ -468,7 +470,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+	VCPU_EVENT(vcpu, 3, "STIDP: store cpu id 0x%llx", stidp_data);
 	return 0;
 }
 
@@ -521,7 +523,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	ar_t ar;
 
 	vcpu->stat.instruction_stsi++;
-	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+	VCPU_EVENT(vcpu, 3, "STSI: fc: %u sel1: %u sel2: %u", fc, sel1, sel2);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -758,10 +760,10 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 	struct gmap *gmap;
 	int i;
 
-	VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
+	VCPU_EVENT(vcpu, 4, "ESSA: release %d pages", entries);
 	gmap = vcpu->arch.gmap;
 	vcpu->stat.instruction_essa++;
-	if (!kvm_s390_cmma_enabled(vcpu->kvm))
+	if (!vcpu->kvm->arch.use_cmma)
 		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
@@ -829,7 +831,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
 	if (ga & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "LCTL: r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
 
 	nr_regs = ((reg3 - reg1) & 0xf) + 1;
@@ -868,7 +870,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
 	if (ga & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "stctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "STCTL r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga);
 
 	reg = reg1;
@@ -902,7 +904,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	if (ga & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "LCTLG: r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
 
 	nr_regs = ((reg3 - reg1) & 0xf) + 1;
@@ -940,7 +942,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
 	if (ga & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "STCTG r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga);
 
 	reg = reg1;

arch/s390/kvm/sigp.c

@@ -205,9 +205,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
 		return SIGP_CC_STATUS_STORED;
-	} else if (rc == 0) {
-		VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x",
-			   dst_vcpu->vcpu_id, irq.u.prefix.address);
 	}
 
 	return rc;
@@ -371,7 +368,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	return rc;
 }
 
-static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
+static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code,
+					   u16 cpu_addr)
 {
 	if (!vcpu->kvm->arch.user_sigp)
 		return 0;
@@ -414,9 +412,8 @@ static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
 	default:
 		vcpu->stat.instruction_sigp_unknown++;
 	}
-
-	VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space",
-		   order_code);
+	VCPU_EVENT(vcpu, 3, "SIGP: order %u for CPU %d handled in userspace",
+		   order_code, cpu_addr);
 
 	return 1;
 }
@@ -435,7 +432,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
 	order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
-	if (handle_sigp_order_in_user_space(vcpu, order_code))
+	if (handle_sigp_order_in_user_space(vcpu, order_code, cpu_addr))
 		return -EOPNOTSUPP;
 
 	if (r1 % 2)

arch/s390/kvm/trace-s390.h

@@ -105,11 +105,22 @@ TRACE_EVENT(kvm_s390_vcpu_start_stop,
 	{KVM_S390_PROGRAM_INT, "program interrupt"},			\
 	{KVM_S390_SIGP_SET_PREFIX, "sigp set prefix"},			\
 	{KVM_S390_RESTART, "sigp restart"},				\
+	{KVM_S390_INT_PFAULT_INIT, "pfault init"},			\
+	{KVM_S390_INT_PFAULT_DONE, "pfault done"},			\
+	{KVM_S390_MCHK, "machine check"},				\
+	{KVM_S390_INT_CLOCK_COMP, "clock comparator"},			\
+	{KVM_S390_INT_CPU_TIMER, "cpu timer"},				\
 	{KVM_S390_INT_VIRTIO, "virtio interrupt"},			\
 	{KVM_S390_INT_SERVICE, "sclp interrupt"},			\
 	{KVM_S390_INT_EMERGENCY, "sigp emergency"},			\
 	{KVM_S390_INT_EXTERNAL_CALL, "sigp ext call"}
 
+#define get_irq_name(__type) \
+	(__type > KVM_S390_INT_IO_MAX ? \
+	__print_symbolic(__type, kvm_s390_int_type) : \
+		(__type & KVM_S390_INT_IO_AI_MASK ? \
+		 "adapter I/O interrupt" : "subchannel I/O interrupt"))
+
 TRACE_EVENT(kvm_s390_inject_vm,
 	    TP_PROTO(__u64 type, __u32 parm, __u64 parm64, int who),
 	    TP_ARGS(type, parm, parm64, who),
@@ -131,22 +142,19 @@ TRACE_EVENT(kvm_s390_inject_vm,
 	    TP_printk("inject%s: type:%x (%s) parm:%x parm64:%llx",
 		      (__entry->who == 1) ? " (from kernel)" :
 		      (__entry->who == 2) ? " (from user)" : "",
-		      __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->inttype, get_irq_name(__entry->inttype),
 		      __entry->parm, __entry->parm64)
 	);
 
 TRACE_EVENT(kvm_s390_inject_vcpu,
-	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64, \
-		     int who),
-	    TP_ARGS(id, type, parm, parm64, who),
+	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64),
+	    TP_ARGS(id, type, parm, parm64),
 
 	    TP_STRUCT__entry(
 		    __field(int, id)
 		    __field(__u32, inttype)
 		    __field(__u32, parm)
 		    __field(__u64, parm64)
-		    __field(int, who)
 		    ),
 
 	    TP_fast_assign(
@@ -154,15 +162,12 @@ TRACE_EVENT(kvm_s390_inject_vcpu,
 		    __entry->inttype = type & 0x00000000ffffffff;
 		    __entry->parm = parm;
 		    __entry->parm64 = parm64;
-		    __entry->who = who;
 		    ),
 
-	    TP_printk("inject%s (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
-		      (__entry->who == 1) ? " (from kernel)" :
-		      (__entry->who == 2) ? " (from user)" : "",
+	    TP_printk("inject (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
 		      __entry->id, __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
-		      __entry->parm, __entry->parm64)
+		      get_irq_name(__entry->inttype), __entry->parm,
+		      __entry->parm64)
 	);
 
 /*
@@ -189,8 +194,8 @@ TRACE_EVENT(kvm_s390_deliver_interrupt,
 	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
 		      "data:%08llx %016llx",
 		      __entry->id, __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
-		      __entry->data0, __entry->data1)
+		      get_irq_name(__entry->inttype), __entry->data0,
+		      __entry->data1)
 	);
 
 /*

arch/x86/include/asm/kvm_host.h

@@ -252,6 +252,11 @@ struct kvm_pio_request {
 	int size;
 };
 
+struct rsvd_bits_validate {
+	u64 rsvd_bits_mask[2][4];
+	u64 bad_mt_xwr;
+};
+
 /*
  * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
  * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
@@ -289,8 +294,15 @@ struct kvm_mmu {
 
 	u64 *pae_root;
 	u64 *lm_root;
-	u64 rsvd_bits_mask[2][4];
-	u64 bad_mt_xwr;
+
+	/*
+	 * check zero bits on shadow page table entries, these
+	 * bits include not only hardware reserved bits but also
+	 * the bits spte never used.
+	 */
+	struct rsvd_bits_validate shadow_zero_check;
+
+	struct rsvd_bits_validate guest_rsvd_check;
 
 	/*
 	 * Bitmap: bit set = last pte in walk
@@ -358,6 +370,11 @@ struct kvm_mtrr {
 	struct list_head head;
 };
 
+/* Hyper-V per vcpu emulation context */
+struct kvm_vcpu_hv {
+	u64 hv_vapic;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -514,8 +531,7 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_vapic;
+	struct kvm_vcpu_hv hyperv;
 
 	cpumask_var_t wbinvd_dirty_mask;
 
@@ -586,6 +602,17 @@ struct kvm_apic_map {
 	struct kvm_lapic *logical_map[16][16];
 };
 
+/* Hyper-V emulation context */
+struct kvm_hv {
+	u64 hv_guest_os_id;
+	u64 hv_hypercall;
+	u64 hv_tsc_page;
+
+	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
+	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
+	u64 hv_crash_ctl;
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -645,16 +672,14 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_guest_os_id;
-	u64 hv_hypercall;
-	u64 hv_tsc_page;
+	struct kvm_hv hyperv;
 
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
 
 	bool boot_vcpu_runs_old_kvmclock;
+	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
 };
@@ -1203,5 +1228,7 @@ int __x86_set_memory_region(struct kvm *kvm,
 			    const struct kvm_userspace_memory_region *mem);
 int x86_set_memory_region(struct kvm *kvm,
 			  const struct kvm_userspace_memory_region *mem);
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/vmx.h

@@ -47,6 +47,7 @@
 #define CPU_BASED_MOV_DR_EXITING                0x00800000
 #define CPU_BASED_UNCOND_IO_EXITING             0x01000000
 #define CPU_BASED_USE_IO_BITMAPS                0x02000000
+#define CPU_BASED_MONITOR_TRAP_FLAG             0x08000000
 #define CPU_BASED_USE_MSR_BITMAPS               0x10000000
 #define CPU_BASED_MONITOR_EXITING               0x20000000
 #define CPU_BASED_PAUSE_EXITING                 0x40000000
@@ -367,29 +368,29 @@ enum vmcs_field {
 #define TYPE_PHYSICAL_APIC_EVENT        (10 << 12)
 #define TYPE_PHYSICAL_APIC_INST         (15 << 12)
 
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
+/* segment AR in VMCS -- these are different from what LAR reports */
+#define VMX_SEGMENT_AR_L_MASK (1 << 13)
+
+#define VMX_AR_TYPE_ACCESSES_MASK 1
+#define VMX_AR_TYPE_READABLE_MASK (1 << 1)
+#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2)
+#define VMX_AR_TYPE_CODE_MASK (1 << 3)
+#define VMX_AR_TYPE_MASK 0x0f
+#define VMX_AR_TYPE_BUSY_64_TSS 11
+#define VMX_AR_TYPE_BUSY_32_TSS 11
+#define VMX_AR_TYPE_BUSY_16_TSS 3
+#define VMX_AR_TYPE_LDT 2
+
+#define VMX_AR_UNUSABLE_MASK (1 << 16)
+#define VMX_AR_S_MASK (1 << 4)
+#define VMX_AR_P_MASK (1 << 7)
+#define VMX_AR_L_MASK (1 << 13)
+#define VMX_AR_DB_MASK (1 << 14)
+#define VMX_AR_G_MASK (1 << 15)
+#define VMX_AR_DPL_SHIFT 5
+#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3)
+
+#define VMX_AR_RESERVD_MASK 0xfffe0f00
 
 #define TSS_PRIVATE_MEMSLOT			(KVM_USER_MEM_SLOTS + 0)
 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 1)

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

@@ -58,6 +58,7 @@
 #define EXIT_REASON_INVALID_STATE       33
 #define EXIT_REASON_MSR_LOAD_FAIL       34
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_TRAP_FLAG   37
 #define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY  41
@@ -106,6 +107,7 @@
 	{ EXIT_REASON_MSR_READ,              "MSR_READ" }, \
 	{ EXIT_REASON_MSR_WRITE,             "MSR_WRITE" }, \
 	{ EXIT_REASON_MWAIT_INSTRUCTION,     "MWAIT_INSTRUCTION" }, \
+	{ EXIT_REASON_MONITOR_TRAP_FLAG,     "MONITOR_TRAP_FLAG" }, \
 	{ EXIT_REASON_MONITOR_INSTRUCTION,   "MONITOR_INSTRUCTION" }, \
 	{ EXIT_REASON_PAUSE_INSTRUCTION,     "PAUSE_INSTRUCTION" }, \
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \

arch/x86/kvm/Makefile

@@ -12,7 +12,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+			   hyperv.o
+
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
 kvm-intel-y		+= vmx.o pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o

arch/x86/kvm/hyperv.c

@@ -0,0 +1,377 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "x86.h"
+#include "lapic.h"
+#include "hyperv.h"
+
+#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+	case HV_X64_MSR_REFERENCE_TSC:
+	case HV_X64_MSR_TIME_REF_COUNT:
+	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	*pdata = hv->hv_crash_param[index];
+	return 0;
+}
+
+static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	*pdata = hv->hv_crash_ctl;
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (host)
+		hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;
+
+	if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {
+
+		vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
+			  hv->hv_crash_param[0],
+			  hv->hv_crash_param[1],
+			  hv->hv_crash_param[2],
+			  hv->hv_crash_param[3],
+			  hv->hv_crash_param[4]);
+
+		/* Send notification about crash to user space */
+		kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
+	}
+
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 data)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	hv->hv_crash_param[index] = data;
+	return 0;
+}
+
+static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
+			     bool host)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		hv->hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!hv->hv_guest_os_id)
+			hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!hv->hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			hv->hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (__copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		hv->hv_hypercall = data;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC: {
+		u64 gfn;
+		HV_REFERENCE_TSC_PAGE tsc_ref;
+
+		memset(&tsc_ref, 0, sizeof(tsc_ref));
+		hv->hv_tsc_page = data;
+		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+			break;
+		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+		if (kvm_write_guest(
+				kvm,
+				gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
+				&tsc_ref, sizeof(tsc_ref)))
+			return 1;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_set_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 data);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		u64 gfn;
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			hv->hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+				return 1;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (__clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		hv->hv_vapic = data;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+		if (kvm_lapic_enable_pv_eoi(vcpu,
+					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+			return 1;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = hv->hv_guest_os_id;
+		break;
+	case HV_X64_MSR_HYPERCALL:
+		data = hv->hv_hypercall;
+		break;
+	case HV_X64_MSR_TIME_REF_COUNT: {
+		data =
+		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC:
+		data = hv->hv_tsc_page;
+		break;
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_get_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 pdata);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+
+		kvm_for_each_vcpu(r, v, vcpu->kvm) {
+			if (v == vcpu) {
+				data = r;
+				break;
+			}
+		}
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	case HV_X64_MSR_APIC_ASSIST_PAGE:
+		data = hv->hv_vapic;
+		break;
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_set_msr(vcpu, msr, data);
+}
+
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_get_msr(vcpu, msr, pdata);
+}
+
+bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	longmode = is_64_bit_mode(vcpu);
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}

arch/x86/kvm/hyperv.h

@@ -0,0 +1,32 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef __ARCH_X86_KVM_HYPERV_H__
+#define __ARCH_X86_KVM_HYPERV_H__
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_hv_hypercall_enabled(struct kvm *kvm);
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
+
+#endif

arch/x86/kvm/i8259.c

@@ -651,15 +651,10 @@ fail_unlock:
 	return NULL;
 }
 
-void kvm_destroy_pic(struct kvm *kvm)
+void kvm_destroy_pic(struct kvm_pic *vpic)
 {
-	struct kvm_pic *vpic = kvm->arch.vpic;
-
-	if (vpic) {
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master);
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave);
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr);
-		kvm->arch.vpic = NULL;
-		kfree(vpic);
-	}
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
+	kfree(vpic);
 }

arch/x86/kvm/irq.h

@@ -74,7 +74,7 @@ struct kvm_pic {
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
-void kvm_destroy_pic(struct kvm *kvm);
+void kvm_destroy_pic(struct kvm_pic *vpic);
 int kvm_pic_read_irq(struct kvm *kvm);
 void kvm_pic_update_irq(struct kvm_pic *s);
 
@@ -85,11 +85,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
-	int ret;
+	struct kvm_pic *vpic = pic_irqchip(kvm);
 
-	ret = (pic_irqchip(kvm) != NULL);
+	/* Read vpic before kvm->irq_routing.  */
 	smp_rmb();
-	return ret;
+	return vpic != NULL;
 }
 
 void kvm_pic_reset(struct kvm_kpic_state *s);

arch/x86/kvm/lapic.c

@@ -1900,8 +1900,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
-				sizeof(u32));
+	if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				  sizeof(u32)))
+		return;
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }

arch/x86/kvm/lapic.h

@@ -91,7 +91,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
 static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
 }
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);

arch/x86/kvm/mmu.c

@@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep)
 {
 	return ACCESS_ONCE(*sptep);
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	/* It is valid if the spte is zapped. */
-	return spte == 0ull;
-}
 #else
 union split_spte {
 	struct {
@@ -478,23 +472,6 @@ retry:
 
 	return spte.spte;
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	union split_spte sspte = (union split_spte)spte;
-	u32 high_mmio_mask = shadow_mmio_mask >> 32;
-
-	/* It is valid if the spte is zapped. */
-	if (spte == 0ull)
-		return true;
-
-	/* It is valid if the spte is being zapped. */
-	if (sspte.spte_low == 0ull &&
-	    (sspte.spte_high & high_mmio_mask) == high_mmio_mask)
-		return true;
-
-	return false;
-}
 #endif
 
 static bool spte_is_locklessly_modifiable(u64 spte)
@@ -3291,54 +3268,89 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
 	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
 }
 
-static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+static bool
+__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level)
 {
-	if (direct)
-		return vcpu_match_mmio_gpa(vcpu, addr);
+	int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f;
 
-	return vcpu_match_mmio_gva(vcpu, addr);
+	return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) |
+		((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0);
 }
 
+static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level);
+}
 
-/*
- * On direct hosts, the last spte is only allows two states
- * for mmio page fault:
- *   - It is the mmio spte
- *   - It is zapped or it is being zapped.
- *
- * This function completely checks the spte when the last spte
- * is not the mmio spte.
- */
-static bool check_direct_spte_mmio_pf(u64 spte)
+static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
 {
-	return __check_direct_spte_mmio_pf(spte);
+	return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
 }
 
-static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
+static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+{
+	if (direct)
+		return vcpu_match_mmio_gpa(vcpu, addr);
+
+	return vcpu_match_mmio_gva(vcpu, addr);
+}
+
+/* return true if reserved bit is detected on spte. */
+static bool
+walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	u64 spte = 0ull;
+	u64 sptes[PT64_ROOT_LEVEL], spte = 0ull;
+	int root, leaf;
+	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		return spte;
+		goto exit;
 
 	walk_shadow_page_lockless_begin(vcpu);
-	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
+
+	for (shadow_walk_init(&iterator, vcpu, addr), root = iterator.level;
+	     shadow_walk_okay(&iterator);
+	     __shadow_walk_next(&iterator, spte)) {
+		leaf = iterator.level;
+		spte = mmu_spte_get_lockless(iterator.sptep);
+
+		sptes[leaf - 1] = spte;
+
 		if (!is_shadow_present_pte(spte))
 			break;
+
+		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+						    leaf);
+	}
+
 	walk_shadow_page_lockless_end(vcpu);
 
-	return spte;
+	if (reserved) {
+		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
+		       __func__, addr);
+		while (root >= leaf) {
+			pr_err("------ spte 0x%llx level %d.\n",
+			       sptes[root - 1], root);
+			root--;
+		}
+	}
+exit:
+	*sptep = spte;
+	return reserved;
 }
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 {
 	u64 spte;
+	bool reserved;
 
 	if (quickly_check_mmio_pf(vcpu, addr, direct))
 		return RET_MMIO_PF_EMULATE;
 
-	spte = walk_shadow_page_get_mmio_spte(vcpu, addr);
+	reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
+	if (unlikely(reserved))
+		return RET_MMIO_PF_BUG;
 
 	if (is_mmio_spte(spte)) {
 		gfn_t gfn = get_mmio_spte_gfn(spte);
@@ -3355,13 +3367,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 		return RET_MMIO_PF_EMULATE;
 	}
 
-	/*
-	 * It's ok if the gva is remapped by other cpus on shadow guest,
-	 * it's a BUG if the gfn is not a mmio page.
-	 */
-	if (direct && !check_direct_spte_mmio_pf(spte))
-		return RET_MMIO_PF_BUG;
-
 	/*
 	 * If the page table is zapped by other cpus, let CPU fault again on
 	 * the address.
@@ -3604,19 +3609,21 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
 #include "paging_tmpl.h"
 #undef PTTYPE
 
-static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu *context)
+static void
+__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+			struct rsvd_bits_validate *rsvd_check,
+			int maxphyaddr, int level, bool nx, bool gbpages,
+			bool pse)
 {
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
 	u64 nonleaf_bit8_rsvd = 0;
 
-	context->bad_mt_xwr = 0;
+	rsvd_check->bad_mt_xwr = 0;
 
-	if (!context->nx)
+	if (!nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
-	if (!guest_cpuid_has_gbpages(vcpu))
+	if (!gbpages)
 		gbpages_bit_rsvd = rsvd_bits(7, 7);
 
 	/*
@@ -3626,80 +3633,95 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	if (guest_cpuid_is_amd(vcpu))
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
-	switch (context->root_level) {
+	switch (level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
-		context->rsvd_bits_mask[0][1] = 0;
-		context->rsvd_bits_mask[0][0] = 0;
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[0][1] = 0;
+		rsvd_check->rsvd_bits_mask[0][0] = 0;
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 
-		if (!is_pse(vcpu)) {
-			context->rsvd_bits_mask[1][1] = 0;
+		if (!pse) {
+			rsvd_check->rsvd_bits_mask[1][1] = 0;
 			break;
 		}
 
 		if (is_cpuid_PSE36())
 			/* 36bits PSE 4MB page */
-			context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
 		else
 			/* 32 bits PSE 4MB page */
-			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
 		break;
 	case PT32E_ROOT_LEVEL:
-		context->rsvd_bits_mask[0][2] =
+		rsvd_check->rsvd_bits_mask[0][2] =
 			rsvd_bits(maxphyaddr, 63) |
 			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
-		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62);	/* PDE */
-		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62); 	/* PTE */
-		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 		break;
 	case PT64_ROOT_LEVEL:
-		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
+			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
-		context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[1][3] =
+			rsvd_check->rsvd_bits_mask[0][3];
+		rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd |
 			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 29);
-		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 		break;
 	}
 }
 
-static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *context, bool execonly)
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu *context)
+{
+	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
+				cpuid_maxphyaddr(vcpu), context->root_level,
+				context->nx, guest_cpuid_has_gbpages(vcpu),
+				is_pse(vcpu));
+}
+
+static void
+__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
+			    int maxphyaddr, bool execonly)
 {
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	int pte;
 
-	context->rsvd_bits_mask[0][3] =
+	rsvd_check->rsvd_bits_mask[0][3] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
-	context->rsvd_bits_mask[0][2] =
+	rsvd_check->rsvd_bits_mask[0][2] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	context->rsvd_bits_mask[0][1] =
+	rsvd_check->rsvd_bits_mask[0][1] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+	rsvd_check->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_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
+	rsvd_check->rsvd_bits_mask[1][2] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
-	context->rsvd_bits_mask[1][1] =
+	rsvd_check->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];
+	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
 
 	for (pte = 0; pte < 64; pte++) {
 		int rwx_bits = pte & 7;
@@ -3707,10 +3729,64 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
 				rwx_bits == 0x2 || rwx_bits == 0x6 ||
 				(rwx_bits == 0x4 && !execonly))
-			context->bad_mt_xwr |= (1ull << pte);
+			rsvd_check->bad_mt_xwr |= (1ull << pte);
 	}
 }
 
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *context, bool execonly)
+{
+	__reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
+				    cpuid_maxphyaddr(vcpu), execonly);
+}
+
+/*
+ * the page table on host is the shadow page table for the page
+ * table in guest or amd nested guest, its mmu features completely
+ * follow the features in guest.
+ */
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
+{
+	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+				boot_cpu_data.x86_phys_bits,
+				context->shadow_root_level, context->nx,
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+}
+EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+
+/*
+ * the direct page table on host, use as much mmu features as
+ * possible, however, kvm currently does not do execution-protection.
+ */
+static void
+reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+				struct kvm_mmu *context)
+{
+	if (guest_cpuid_is_amd(vcpu))
+		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+					boot_cpu_data.x86_phys_bits,
+					context->shadow_root_level, false,
+					cpu_has_gbpages, true);
+	else
+		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+					    boot_cpu_data.x86_phys_bits,
+					    false);
+
+}
+
+/*
+ * as the comments in reset_shadow_zero_bits_mask() except it
+ * is the shadow page table for intel nested guest.
+ */
+static void
+reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+				struct kvm_mmu *context, bool execonly)
+{
+	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+				    boot_cpu_data.x86_phys_bits, execonly);
+}
+
 static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				      struct kvm_mmu *mmu, bool ept)
 {
@@ -3889,6 +3965,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 
 	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
+	reset_tdp_shadow_zero_bits_mask(vcpu, context);
 }
 
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
@@ -3916,6 +3993,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 	context->base_role.smap_andnot_wp
 		= smap && !is_write_protection(vcpu);
 	context->base_role.smm = is_smm(vcpu);
+	reset_shadow_zero_bits_mask(vcpu, context);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -3939,6 +4017,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly)
 
 	update_permission_bitmask(vcpu, context, true);
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
 
@@ -4860,28 +4939,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	return nr_mmu_pages;
 }
 
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
-{
-	struct kvm_shadow_walk_iterator iterator;
-	u64 spte;
-	int nr_sptes = 0;
-
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		return nr_sptes;
-
-	walk_shadow_page_lockless_begin(vcpu);
-	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
-		sptes[iterator.level-1] = spte;
-		nr_sptes++;
-		if (!is_shadow_present_pte(spte))
-			break;
-	}
-	walk_shadow_page_lockless_end(vcpu);
-
-	return nr_sptes;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
-
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);

arch/x86/kvm/mmu.h

@@ -50,9 +50,11 @@ static inline u64 rsvd_bits(int s, int e)
 	return ((1ULL << (e - s + 1)) - 1) << s;
 }
 
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
 
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+
 /*
  * Return values of handle_mmio_page_fault_common:
  * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction

arch/x86/kvm/paging_tmpl.h

@@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
 	*access &= mask;
 }
 
-static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
-{
-	int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
-
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
-		((mmu->bad_mt_xwr & (1ull << low6)) != 0);
-}
-
 static inline int FNAME(is_present_gpte)(unsigned long pte)
 {
 #if PTTYPE != PTTYPE_EPT
@@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
 {
-	if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
 		goto no_present;
 
 	if (!FNAME(is_present_gpte)(gpte))
@@ -353,8 +345,7 @@ retry_walk:
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
-					             walker->level))) {
+		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
 			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}

arch/x86/kvm/pmu_amd.c

@@ -133,8 +133,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_K7_PERFCTRn */
 	pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
 	if (pmc) {
-		if (!msr_info->host_initiated)
-			data = (s64)data;
 		pmc->counter += data - pmc_read_counter(pmc);
 		return 0;
 	}

arch/x86/kvm/svm.c

@@ -1173,6 +1173,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
 		return 0;
 
+	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
+	    kvm_read_cr0(vcpu) & X86_CR0_CD)
+		return _PAGE_NOCACHE;
+
 	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
 	return mtrr2protval[mtrr];
 }
@@ -1667,13 +1671,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-	/*
-	 * re-enable caching here because the QEMU bios
-	 * does not do it - this results in some delay at
-	 * reboot
-	 */
-	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
-		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
+	/* These are emulated via page tables.  */
+	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -2106,6 +2107,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;
 	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
 	vcpu->arch.mmu.shadow_root_level = get_npt_level();
+	reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
 }
 

arch/x86/kvm/vmx.c

@@ -2443,10 +2443,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
 #endif
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
-		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
-		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
-		CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
-		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
+		CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
+		CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
+		CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
 	 * hardware. For example, L1 can specify an MSR bitmap - and we
@@ -3423,12 +3423,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 	vmx_segment_cache_clear(to_vmx(vcpu));
 
 	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
-	if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
+	if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
 		pr_debug_ratelimited("%s: tss fixup for long mode. \n",
 				     __func__);
 		vmcs_write32(GUEST_TR_AR_BYTES,
-			     (guest_tr_ar & ~AR_TYPE_MASK)
-			     | AR_TYPE_BUSY_64_TSS);
+			     (guest_tr_ar & ~VMX_AR_TYPE_MASK)
+			     | VMX_AR_TYPE_BUSY_64_TSS);
 	}
 	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
 }
@@ -3719,7 +3719,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu)
 		return 0;
 	else {
 		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
-		return AR_DPL(ar);
+		return VMX_AR_DPL(ar);
 	}
 }
 
@@ -3847,11 +3847,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
 
 	if (cs.unusable)
 		return false;
-	if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
+	if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
 		return false;
 	if (!cs.s)
 		return false;
-	if (cs.type & AR_TYPE_WRITEABLE_MASK) {
+	if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
 		if (cs.dpl > cs_rpl)
 			return false;
 	} else {
@@ -3901,7 +3901,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
 		return false;
 	if (!var.present)
 		return false;
-	if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) {
+	if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
 		if (var.dpl < rpl) /* DPL < RPL */
 			return false;
 	}
@@ -5759,73 +5759,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
-static u64 ept_rsvd_mask(u64 spte, int level)
-{
-	int i;
-	u64 mask = 0;
-
-	for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
-		mask |= (1ULL << i);
-
-	if (level == 4)
-		/* bits 7:3 reserved */
-		mask |= 0xf8;
-	else if (spte & (1ULL << 7))
-		/*
-		 * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively,
-		 * level == 1 if the hypervisor is using the ignored bit 7.
-		 */
-		mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE;
-	else if (level > 1)
-		/* bits 6:3 reserved */
-		mask |= 0x78;
-
-	return mask;
-}
-
-static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
-				       int level)
-{
-	printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
-
-	/* 010b (write-only) */
-	WARN_ON((spte & 0x7) == 0x2);
-
-	/* 110b (write/execute) */
-	WARN_ON((spte & 0x7) == 0x6);
-
-	/* 100b (execute-only) and value not supported by logical processor */
-	if (!cpu_has_vmx_ept_execute_only())
-		WARN_ON((spte & 0x7) == 0x4);
-
-	/* not 000b */
-	if ((spte & 0x7)) {
-		u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
-
-		if (rsvd_bits != 0) {
-			printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
-					 __func__, rsvd_bits);
-			WARN_ON(1);
-		}
-
-		/* bits 5:3 are _not_ reserved for large page or leaf page */
-		if ((rsvd_bits & 0x38) == 0) {
-			u64 ept_mem_type = (spte & 0x38) >> 3;
-
-			if (ept_mem_type == 2 || ept_mem_type == 3 ||
-			    ept_mem_type == 7) {
-				printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
-						__func__, ept_mem_type);
-				WARN_ON(1);
-			}
-		}
-	}
-}
-
 static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 {
-	u64 sptes[4];
-	int nr_sptes, i, ret;
+	int ret;
 	gpa_t gpa;
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
@@ -5846,13 +5782,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 		return 1;
 
 	/* It is the real ept misconfig */
-	printk(KERN_ERR "EPT: Misconfiguration.\n");
-	printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
-
-	nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
-
-	for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
-		ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+	WARN_ON(1);
 
 	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
 	vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
@@ -6246,6 +6176,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu)
 	return handle_nop(vcpu);
 }
 
+static int handle_monitor_trap(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 static int handle_monitor(struct kvm_vcpu *vcpu)
 {
 	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
@@ -6408,8 +6343,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
  */
 static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, gva_t *ret)
+				 u32 vmx_instruction_info, bool wr, gva_t *ret)
 {
+	gva_t off;
+	bool exn;
+	struct kvm_segment s;
+
 	/*
 	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
 	 * Execution", on an exit, vmx_instruction_info holds most of the
@@ -6434,22 +6373,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
 	/* Addr = segment_base + offset */
 	/* offset = base + [index * scale] + displacement */
-	*ret = vmx_get_segment_base(vcpu, seg_reg);
+	off = exit_qualification; /* holds the displacement */
 	if (base_is_valid)
-		*ret += kvm_register_read(vcpu, base_reg);
+		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
-		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
-	*ret += exit_qualification; /* holds the displacement */
+		off += kvm_register_read(vcpu, index_reg)<<scaling;
+	vmx_get_segment(vcpu, &s, seg_reg);
+	*ret = s.base + off;
 
 	if (addr_size == 1) /* 32 bit */
 		*ret &= 0xffffffff;
 
-	/*
-	 * TODO: throw #GP (and return 1) in various cases that the VM*
-	 * instructions require it - e.g., offset beyond segment limit,
-	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
-	 * address, and so on. Currently these are not checked.
-	 */
+	/* Checks for #GP/#SS exceptions. */
+	exn = false;
+	if (is_protmode(vcpu)) {
+		/* Protected mode: apply checks for segment validity in the
+		 * following order:
+		 * - segment type check (#GP(0) may be thrown)
+		 * - usability check (#GP(0)/#SS(0))
+		 * - limit check (#GP(0)/#SS(0))
+		 */
+		if (wr)
+			/* #GP(0) if the destination operand is located in a
+			 * read-only data segment or any code segment.
+			 */
+			exn = ((s.type & 0xa) == 0 || (s.type & 8));
+		else
+			/* #GP(0) if the source operand is located in an
+			 * execute-only code segment
+			 */
+			exn = ((s.type & 0xa) == 8);
+	}
+	if (exn) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is an only check for long mode.
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
+		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
+		 */
+		exn = (s.unusable != 0);
+		/* Protected mode: #GP(0)/#SS(0) if the memory
+		 * operand is outside the segment limit.
+		 */
+		exn = exn || (off + sizeof(u64) > s.limit);
+	}
+	if (exn) {
+		kvm_queue_exception_e(vcpu,
+				      seg_reg == VCPU_SREG_SS ?
+						SS_VECTOR : GP_VECTOR,
+				      0);
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -6471,7 +6451,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
 	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
@@ -6999,7 +6979,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 			field_value);
 	} else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, &gva))
+				vmx_instruction_info, true, &gva))
 			return 1;
 		/* _system ok, as nested_vmx_check_permission verified cpl=0 */
 		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
@@ -7036,7 +7016,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 			(((vmx_instruction_info) >> 3) & 0xf));
 	else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, &gva))
+				vmx_instruction_info, false, &gva))
 			return 1;
 		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
 			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
@@ -7128,7 +7108,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, &vmcs_gva))
+			vmx_instruction_info, true, &vmcs_gva))
 		return 1;
 	/* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */
 	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
@@ -7184,7 +7164,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	 * operand is read even if it isn't needed (e.g., for type==global)
 	 */
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmx_instruction_info, &gva))
+			vmx_instruction_info, false, &gva))
 		return 1;
 	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
 				sizeof(operand), &e)) {
@@ -7282,6 +7262,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_TRAP_FLAG]       = handle_monitor_trap,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 	[EXIT_REASON_INVVPID]                 = handle_invvpid,
@@ -7542,6 +7523,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return true;
 	case EXIT_REASON_MWAIT_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
+	case EXIT_REASON_MONITOR_TRAP_FLAG:
+		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
 	case EXIT_REASON_MONITOR_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
 	case EXIT_REASON_PAUSE_INSTRUCTION:

arch/x86/kvm/x86.c

@@ -29,6 +29,7 @@
 #include "cpuid.h"
 #include "assigned-dev.h"
 #include "pmu.h"
+#include "hyperv.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -221,11 +222,9 @@ static void shared_msr_update(unsigned slot, u32 msr)
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
+	shared_msrs_global.msrs[slot] = msr;
 	if (slot >= shared_msrs_global.nr)
 		shared_msrs_global.nr = slot + 1;
-	shared_msrs_global.msrs[slot] = msr;
-	/* we need ensured the shared_msr_global have been updated */
-	smp_wmb();
 }
 EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
@@ -526,7 +525,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
 		if (is_present_gpte(pdpte[i]) &&
-		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
+		    (pdpte[i] &
+		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
 			ret = 0;
 			goto out;
 		}
@@ -949,6 +949,8 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
+	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 
@@ -1217,11 +1219,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 		 __func__, base_khz, scaled_khz, shift, *pmultiplier);
 }
 
-static inline u64 get_kernel_ns(void)
-{
-	return ktime_get_boot_ns();
-}
-
 #ifdef CONFIG_X86_64
 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
 #endif
@@ -1869,123 +1866,6 @@ out:
 	return r;
 }
 
-static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
-{
-	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
-}
-
-static bool kvm_hv_msr_partition_wide(u32 msr)
-{
-	bool r = false;
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-	case HV_X64_MSR_HYPERCALL:
-	case HV_X64_MSR_REFERENCE_TSC:
-	case HV_X64_MSR_TIME_REF_COUNT:
-		r = true;
-		break;
-	}
-
-	return r;
-}
-
-static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		kvm->arch.hv_guest_os_id = data;
-		/* setting guest os id to zero disables hypercall page */
-		if (!kvm->arch.hv_guest_os_id)
-			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
-		break;
-	case HV_X64_MSR_HYPERCALL: {
-		u64 gfn;
-		unsigned long addr;
-		u8 instructions[4];
-
-		/* if guest os id is not set hypercall should remain disabled */
-		if (!kvm->arch.hv_guest_os_id)
-			break;
-		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
-			kvm->arch.hv_hypercall = data;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
-		addr = gfn_to_hva(kvm, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		kvm_x86_ops->patch_hypercall(vcpu, instructions);
-		((unsigned char *)instructions)[3] = 0xc3; /* ret */
-		if (__copy_to_user((void __user *)addr, instructions, 4))
-			return 1;
-		kvm->arch.hv_hypercall = data;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC: {
-		u64 gfn;
-		HV_REFERENCE_TSC_PAGE tsc_ref;
-		memset(&tsc_ref, 0, sizeof(tsc_ref));
-		kvm->arch.hv_tsc_page = data;
-		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
-			break;
-		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
-			&tsc_ref, sizeof(tsc_ref)))
-			return 1;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-	return 0;
-}
-
-static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	switch (msr) {
-	case HV_X64_MSR_APIC_ASSIST_PAGE: {
-		u64 gfn;
-		unsigned long addr;
-
-		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
-			vcpu->arch.hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
-				return 1;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
-		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		if (__clear_user((void __user *)addr, PAGE_SIZE))
-			return 1;
-		vcpu->arch.hv_vapic = data;
-		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
-			return 1;
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
-	case HV_X64_MSR_ICR:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
-	case HV_X64_MSR_TPR:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-
-	return 0;
-}
-
 static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
@@ -2224,15 +2104,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = set_msr_hyperv_pw(vcpu, msr, data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return set_msr_hyperv(vcpu, msr, data);
-		break;
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_set_msr_common(vcpu, msr, data,
+					     msr_info->host_initiated);
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -2315,68 +2190,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
-static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		data = kvm->arch.hv_guest_os_id;
-		break;
-	case HV_X64_MSR_HYPERCALL:
-		data = kvm->arch.hv_hypercall;
-		break;
-	case HV_X64_MSR_TIME_REF_COUNT: {
-		data =
-		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC:
-		data = kvm->arch.hv_tsc_page;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-
-	*pdata = data;
-	return 0;
-}
-
-static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-
-	switch (msr) {
-	case HV_X64_MSR_VP_INDEX: {
-		int r;
-		struct kvm_vcpu *v;
-		kvm_for_each_vcpu(r, v, vcpu->kvm) {
-			if (v == vcpu) {
-				data = r;
-				break;
-			}
-		}
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
-	case HV_X64_MSR_ICR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
-	case HV_X64_MSR_TPR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
-	case HV_X64_MSR_APIC_ASSIST_PAGE:
-		data = vcpu->arch.hv_vapic;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-	*pdata = data;
-	return 0;
-}
-
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	switch (msr_info->index) {
@@ -2493,14 +2306,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0x20000000;
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr_info->index)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_get_msr_common(vcpu,
+					     msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
@@ -2651,6 +2460,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_DISABLE_QUIRKS:
+	case KVM_CAP_SET_BOOT_CPU_ID:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -3817,30 +3627,25 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = kvm_ioapic_init(kvm);
 			if (r) {
 				mutex_lock(&kvm->slots_lock);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_master);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_slave);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_eclr);
+				kvm_destroy_pic(vpic);
 				mutex_unlock(&kvm->slots_lock);
-				kfree(vpic);
 				goto create_irqchip_unlock;
 			}
 		} else
 			goto create_irqchip_unlock;
-		smp_wmb();
-		kvm->arch.vpic = vpic;
-		smp_wmb();
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
 			mutex_lock(&kvm->slots_lock);
 			mutex_lock(&kvm->irq_lock);
 			kvm_ioapic_destroy(kvm);
-			kvm_destroy_pic(kvm);
+			kvm_destroy_pic(vpic);
 			mutex_unlock(&kvm->irq_lock);
 			mutex_unlock(&kvm->slots_lock);
+			goto create_irqchip_unlock;
 		}
+		/* Write kvm->irq_routing before kvm->arch.vpic.  */
+		smp_wmb();
+		kvm->arch.vpic = vpic;
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -3967,6 +3772,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_reinject(kvm, &control);
 		break;
 	}
+	case KVM_SET_BOOT_CPU_ID:
+		r = 0;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus) != 0)
+			r = -EBUSY;
+		else
+			kvm->arch.bsp_vcpu_id = arg;
+		mutex_unlock(&kvm->lock);
+		break;
 	case KVM_XEN_HVM_CONFIG: {
 		r = -EFAULT;
 		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
@@ -5882,66 +5696,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
-int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
-{
-	u64 param, ingpa, outgpa, ret;
-	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
-	bool fast, longmode;
-
-	/*
-	 * hypercall generates UD from non zero cpl and real mode
-	 * per HYPER-V spec
-	 */
-	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 0;
-	}
-
-	longmode = is_64_bit_mode(vcpu);
-
-	if (!longmode) {
-		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
-		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
-		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
-	}
-#ifdef CONFIG_X86_64
-	else {
-		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
-		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
-	}
-#endif
-
-	code = param & 0xffff;
-	fast = (param >> 16) & 0x1;
-	rep_cnt = (param >> 32) & 0xfff;
-	rep_idx = (param >> 48) & 0xfff;
-
-	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
-
-	switch (code) {
-	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
-		kvm_vcpu_on_spin(vcpu);
-		break;
-	default:
-		res = HV_STATUS_INVALID_HYPERCALL_CODE;
-		break;
-	}
-
-	ret = res | (((u64)rep_done & 0xfff) << 32);
-	if (longmode) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
-	} else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
-	}
-
-	return 1;
-}
-
 /*
  * kvm_pv_kick_cpu_op:  Kick a vcpu.
  *
@@ -6518,6 +6272,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu_scan_ioapic(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
 			kvm_vcpu_reload_apic_access_page(vcpu);
+		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
+			r = 0;
+			goto out;
+		}
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -7540,6 +7300,17 @@ void kvm_arch_check_processor_compat(void *rtn)
 	kvm_x86_ops->check_processor_compatibility(rtn);
 }
 
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
+
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
+}
+
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 {
 	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);

arch/x86/kvm/x86.h

@@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
 	return kvm_register_write(vcpu, reg, val);
 }
 
+static inline u64 get_kernel_ns(void)
+{
+	return ktime_get_boot_ns();
+}
+
 static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
 {
 	return !(kvm->arch.disabled_quirks & quirk);

include/linux/kvm_host.h

@@ -139,6 +139,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_DISABLE_IBS       24
 #define KVM_REQ_APIC_PAGE_RELOAD  25
 #define KVM_REQ_SMI               26
+#define KVM_REQ_HV_CRASH          27
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -363,9 +364,6 @@ struct kvm {
 	struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-	u32 bsp_vcpu_id;
-#endif
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	atomic_t online_vcpus;
 	int last_boosted_vcpu;
@@ -424,8 +422,15 @@ struct kvm {
 #define vcpu_unimpl(vcpu, fmt, ...)					\
 	kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+#define vcpu_debug(vcpu, fmt, ...)					\
+	kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
+	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
+	 * the caller has read kvm->online_vcpus before (as is the case
+	 * for kvm_for_each_vcpu, for example).
+	 */
 	smp_rmb();
 	return kvm->vcpus[i];
 }
@@ -1055,22 +1060,9 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 #endif /* CONFIG_HAVE_KVM_EVENTFD */
 
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
-static inline bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
-{
-	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
-}
-
-static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
-{
-	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
-}
-
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
-
 #else
-
 static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
-
 #endif
 
 static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)

include/uapi/linux/kvm.h

@@ -317,6 +317,7 @@ struct kvm_run {
 		struct {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
@@ -481,6 +482,7 @@ struct kvm_s390_psw {
 	 ((ai) << 26))
 #define KVM_S390_INT_IO_MIN		0x00000000u
 #define KVM_S390_INT_IO_MAX		0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK		0x04000000u
 
 
 struct kvm_s390_interrupt {

virt/kvm/kvm_main.c

@@ -2206,6 +2206,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	}
 
 	kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu;
+
+	/*
+	 * Pairs with smp_rmb() in kvm_get_vcpu.  Write kvm->vcpus
+	 * before kvm->online_vcpu's incremented value.
+	 */
 	smp_wmb();
 	atomic_inc(&kvm->online_vcpus);
 
@@ -2618,9 +2623,6 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-	case KVM_CAP_SET_BOOT_CPU_ID:
-#endif
 	case KVM_CAP_INTERNAL_ERROR_DATA:
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
@@ -2716,17 +2718,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_ioeventfd(kvm, &data);
 		break;
 	}
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-	case KVM_SET_BOOT_CPU_ID:
-		r = 0;
-		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus) != 0)
-			r = -EBUSY;
-		else
-			kvm->bsp_vcpu_id = arg;
-		mutex_unlock(&kvm->lock);
-		break;
-#endif
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_SIGNAL_MSI: {
 		struct kvm_msi msi;