Merge tag 'kvm-s390-next-4.6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and features for kvm/next (4.6) part 2

- add watchdog diagnose to trace event decoder
- better handle the cpu timer when not inside the guest
- only provide STFLE if the CPU model has STFLE
- reduce DMA page usage

arch/s390/include/asm/kvm_host.h

@@ -20,6 +20,7 @@
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
+#include <linux/seqlock.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
 #include <asm/fpu/api.h>
@@ -552,6 +553,15 @@ struct kvm_vcpu_arch {
 	unsigned long pfault_token;
 	unsigned long pfault_select;
 	unsigned long pfault_compare;
+	bool cputm_enabled;
+	/*
+	 * The seqcount protects updates to cputm_start and sie_block.cputm,
+	 * this way we can have non-blocking reads with consistent values.
+	 * Only the owning VCPU thread (vcpu->cpu) is allowed to change these
+	 * values and to start/stop/enable/disable cpu timer accounting.
+	 */
+	seqcount_t cputm_seqcount;
+	__u64 cputm_start;
 };
 
 struct kvm_vm_stat {
@@ -590,15 +600,11 @@ struct s390_io_adapter {
 #define S390_ARCH_FAC_MASK_SIZE_U64 \
 	(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
 
-struct kvm_s390_fac {
-	/* facility list requested by guest */
-	__u64 list[S390_ARCH_FAC_LIST_SIZE_U64];
-	/* facility mask supported by kvm & hosting machine */
-	__u64 mask[S390_ARCH_FAC_LIST_SIZE_U64];
-};
-
 struct kvm_s390_cpu_model {
-	struct kvm_s390_fac *fac;
+	/* facility mask supported by kvm & hosting machine */
+	__u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+	/* facility list requested by guest (in dma page) */
+	__u64 *fac_list;
 	struct cpuid cpu_id;
 	unsigned short ibc;
 };
@@ -617,6 +623,16 @@ struct kvm_s390_crypto_cb {
 	__u8    reserved80[128];                /* 0x0080 */
 };
 
+/*
+ * sie_page2 has to be allocated as DMA because fac_list and crycb need
+ * 31bit addresses in the sie control block.
+ */
+struct sie_page2 {
+	__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64];	/* 0x0000 */
+	struct kvm_s390_crypto_cb crycb;		/* 0x0800 */
+	u8 reserved900[0x1000 - 0x900];			/* 0x0900 */
+} __packed;
+
 struct kvm_arch{
 	void *sca;
 	int use_esca;
@@ -637,6 +653,7 @@ struct kvm_arch{
 	int ipte_lock_count;
 	struct mutex ipte_mutex;
 	spinlock_t start_stop_lock;
+	struct sie_page2 *sie_page2;
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
 	u64 epoch;

arch/s390/include/uapi/asm/sie.h

@@ -7,6 +7,7 @@
 	{ 0x9c, "DIAG (0x9c) time slice end directed" },	\
 	{ 0x204, "DIAG (0x204) logical-cpu utilization" },	\
 	{ 0x258, "DIAG (0x258) page-reference services" },	\
+	{ 0x288, "DIAG (0x288) watchdog functions" },		\
 	{ 0x308, "DIAG (0x308) ipl functions" },		\
 	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
 	{ 0x501, "DIAG (0x501) KVM breakpoint" }

arch/s390/kvm/interrupt.c

@@ -182,8 +182,9 @@ static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
 
 static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
 {
-	return (vcpu->arch.sie_block->cputm >> 63) &&
-	       cpu_timer_interrupts_enabled(vcpu);
+	if (!cpu_timer_interrupts_enabled(vcpu))
+		return 0;
+	return kvm_s390_get_cpu_timer(vcpu) >> 63;
 }
 
 static inline int is_ioirq(unsigned long irq_type)
@@ -908,9 +909,35 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
 }
 
+static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
+{
+	u64 now, cputm, sltime = 0;
+
+	if (ckc_interrupts_enabled(vcpu)) {
+		now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+		sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+		/* already expired or overflow? */
+		if (!sltime || vcpu->arch.sie_block->ckc <= now)
+			return 0;
+		if (cpu_timer_interrupts_enabled(vcpu)) {
+			cputm = kvm_s390_get_cpu_timer(vcpu);
+			/* already expired? */
+			if (cputm >> 63)
+				return 0;
+			return min(sltime, tod_to_ns(cputm));
+		}
+	} else if (cpu_timer_interrupts_enabled(vcpu)) {
+		sltime = kvm_s390_get_cpu_timer(vcpu);
+		/* already expired? */
+		if (sltime >> 63)
+			return 0;
+	}
+	return sltime;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 {
-	u64 now, sltime;
+	u64 sltime;
 
 	vcpu->stat.exit_wait_state++;
 
@@ -923,22 +950,20 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP; /* disabled wait */
 	}
 
-	if (!ckc_interrupts_enabled(vcpu)) {
+	if (!ckc_interrupts_enabled(vcpu) &&
+	    !cpu_timer_interrupts_enabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
 		__set_cpu_idle(vcpu);
 		goto no_timer;
 	}
 
-	now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
-	/* underflow */
-	if (vcpu->arch.sie_block->ckc < now)
+	sltime = __calculate_sltime(vcpu);
+	if (!sltime)
 		return 0;
 
 	__set_cpu_idle(vcpu);
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
-	VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
+	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	kvm_vcpu_block(vcpu);
@@ -965,18 +990,16 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
-	u64 now, sltime;
+	u64 sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+	sltime = __calculate_sltime(vcpu);
 
 	/*
 	 * If the monotonic clock runs faster than the tod clock we might be
 	 * woken up too early and have to go back to sleep to avoid deadlocks.
 	 */
-	if (vcpu->arch.sie_block->ckc > now &&
-	    hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+	if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
 		return HRTIMER_RESTART;
 	kvm_s390_vcpu_wakeup(vcpu);
 	return HRTIMER_NORESTART;

arch/s390/kvm/kvm-s390.c

@@ -158,6 +158,8 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 		kvm->arch.epoch -= *delta;
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			vcpu->arch.sie_block->epoch -= *delta;
+			if (vcpu->arch.cputm_enabled)
+				vcpu->arch.cputm_start += *delta;
 		}
 	}
 	return NOTIFY_OK;
@@ -353,8 +355,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		if (atomic_read(&kvm->online_vcpus)) {
 			r = -EBUSY;
 		} else if (MACHINE_HAS_VX) {
-			set_kvm_facility(kvm->arch.model.fac->mask, 129);
-			set_kvm_facility(kvm->arch.model.fac->list, 129);
+			set_kvm_facility(kvm->arch.model.fac_mask, 129);
+			set_kvm_facility(kvm->arch.model.fac_list, 129);
 			r = 0;
 		} else
 			r = -EINVAL;
@@ -368,8 +370,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		if (atomic_read(&kvm->online_vcpus)) {
 			r = -EBUSY;
 		} else if (test_facility(64)) {
-			set_kvm_facility(kvm->arch.model.fac->mask, 64);
-			set_kvm_facility(kvm->arch.model.fac->list, 64);
+			set_kvm_facility(kvm->arch.model.fac_mask, 64);
+			set_kvm_facility(kvm->arch.model.fac_list, 64);
 			r = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -652,7 +654,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
 		       sizeof(struct cpuid));
 		kvm->arch.model.ibc = proc->ibc;
-		memcpy(kvm->arch.model.fac->list, proc->fac_list,
+		memcpy(kvm->arch.model.fac_list, proc->fac_list,
 		       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	} else
 		ret = -EFAULT;
@@ -686,7 +688,8 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	}
 	memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
 	proc->ibc = kvm->arch.model.ibc;
-	memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
+	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
 		ret = -EFAULT;
 	kfree(proc);
@@ -706,7 +709,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	}
 	get_cpu_id((struct cpuid *) &mach->cpuid);
 	mach->ibc = sclp.ibc;
-	memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+	memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
@@ -1083,16 +1086,12 @@ static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
 	cpu_id->version = 0xff;
 }
 
-static int kvm_s390_crypto_init(struct kvm *kvm)
+static void kvm_s390_crypto_init(struct kvm *kvm)
 {
 	if (!test_kvm_facility(kvm, 76))
-		return 0;
-
-	kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
-					 GFP_KERNEL | GFP_DMA);
-	if (!kvm->arch.crypto.crycb)
-		return -ENOMEM;
+		return;
 
+	kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
 	kvm_s390_set_crycb_format(kvm);
 
 	/* Enable AES/DEA protected key functions by default */
@@ -1102,8 +1101,6 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
 			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
 	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
 			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
-
-	return 0;
 }
 
 static void sca_dispose(struct kvm *kvm)
@@ -1157,37 +1154,30 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (!kvm->arch.dbf)
 		goto out_err;
 
-	/*
-	 * The architectural maximum amount of facilities is 16 kbit. To store
-	 * this amount, 2 kbyte of memory is required. Thus we need a full
-	 * page to hold the guest facility list (arch.model.fac->list) and the
-	 * facility mask (arch.model.fac->mask). Its address size has to be
-	 * 31 bits and word aligned.
-	 */
-	kvm->arch.model.fac =
-		(struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
-	if (!kvm->arch.model.fac)
+	kvm->arch.sie_page2 =
+	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!kvm->arch.sie_page2)
 		goto out_err;
 
 	/* Populate the facility mask initially. */
-	memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
 		if (i < kvm_s390_fac_list_mask_size())
-			kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
+			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
 		else
-			kvm->arch.model.fac->mask[i] = 0UL;
+			kvm->arch.model.fac_mask[i] = 0UL;
 	}
 
 	/* Populate the facility list initially. */
-	memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+	kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
+	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 
 	kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
 	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
 
-	if (kvm_s390_crypto_init(kvm) < 0)
-		goto out_err;
+	kvm_s390_crypto_init(kvm);
 
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -1223,8 +1213,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	return 0;
 out_err:
-	kfree(kvm->arch.crypto.crycb);
-	free_page((unsigned long)kvm->arch.model.fac);
+	free_page((unsigned long)kvm->arch.sie_page2);
 	debug_unregister(kvm->arch.dbf);
 	sca_dispose(kvm);
 	KVM_EVENT(3, "creation of vm failed: %d", rc);
@@ -1270,10 +1259,9 @@ static void kvm_free_vcpus(struct kvm *kvm)
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
-	free_page((unsigned long)kvm->arch.model.fac);
 	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
-	kfree(kvm->arch.crypto.crycb);
+	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
@@ -1429,6 +1417,93 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	vcpu->arch.cputm_start = get_tod_clock_fast();
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+	vcpu->arch.cputm_start = 0;
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_enabled);
+	vcpu->arch.cputm_enabled = true;
+	__start_cpu_timer_accounting(vcpu);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
+	__stop_cpu_timer_accounting(vcpu);
+	vcpu->arch.cputm_enabled = false;
+}
+
+static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	__enable_cpu_timer_accounting(vcpu);
+	preempt_enable();
+}
+
+static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	__disable_cpu_timer_accounting(vcpu);
+	preempt_enable();
+}
+
+/* set the cpu timer - may only be called from the VCPU thread itself */
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	if (vcpu->arch.cputm_enabled)
+		vcpu->arch.cputm_start = get_tod_clock_fast();
+	vcpu->arch.sie_block->cputm = cputm;
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+	preempt_enable();
+}
+
+/* update and get the cpu timer - can also be called from other VCPU threads */
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
+{
+	unsigned int seq;
+	__u64 value;
+
+	if (unlikely(!vcpu->arch.cputm_enabled))
+		return vcpu->arch.sie_block->cputm;
+
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	do {
+		seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
+		/*
+		 * If the writer would ever execute a read in the critical
+		 * section, e.g. in irq context, we have a deadlock.
+		 */
+		WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
+		value = vcpu->arch.sie_block->cputm;
+		/* if cputm_start is 0, accounting is being started/stopped */
+		if (likely(vcpu->arch.cputm_start))
+			value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+	} while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
+	preempt_enable();
+	return value;
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
@@ -1449,10 +1524,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+		__start_cpu_timer_accounting(vcpu);
+	vcpu->cpu = cpu;
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	vcpu->cpu = -1;
+	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+		__stop_cpu_timer_accounting(vcpu);
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
@@ -1474,7 +1555,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gpsw.mask = 0UL;
 	vcpu->arch.sie_block->gpsw.addr = 0UL;
 	kvm_s390_set_prefix(vcpu, 0);
-	vcpu->arch.sie_block->cputm     = 0UL;
+	kvm_s390_set_cpu_timer(vcpu, 0);
 	vcpu->arch.sie_block->ckc       = 0UL;
 	vcpu->arch.sie_block->todpr     = 0;
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
@@ -1544,7 +1625,8 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.cpu_id = model->cpu_id;
 	vcpu->arch.sie_block->ibc = model->ibc;
-	vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+	if (test_kvm_facility(vcpu->kvm, 7))
+		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
 }
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -1622,6 +1704,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+	seqcount_init(&vcpu->arch.cputm_seqcount);
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
@@ -1721,7 +1804,7 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CPU_TIMER:
-		r = put_user(vcpu->arch.sie_block->cputm,
+		r = put_user(kvm_s390_get_cpu_timer(vcpu),
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CLOCK_COMP:
@@ -1759,6 +1842,7 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 					   struct kvm_one_reg *reg)
 {
 	int r = -EINVAL;
+	__u64 val;
 
 	switch (reg->id) {
 	case KVM_REG_S390_TODPR:
@@ -1770,8 +1854,9 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CPU_TIMER:
-		r = get_user(vcpu->arch.sie_block->cputm,
-			     (u64 __user *)reg->addr);
+		r = get_user(val, (u64 __user *)reg->addr);
+		if (!r)
+			kvm_s390_set_cpu_timer(vcpu, val);
 		break;
 	case KVM_REG_S390_CLOCK_COMP:
 		r = get_user(vcpu->arch.sie_block->ckc,
@@ -2261,10 +2346,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		 */
 		local_irq_disable();
 		__kvm_guest_enter();
+		__disable_cpu_timer_accounting(vcpu);
 		local_irq_enable();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
 		local_irq_disable();
+		__enable_cpu_timer_accounting(vcpu);
 		__kvm_guest_exit();
 		local_irq_enable();
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -2288,7 +2375,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
 	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
-		vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
+		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
 		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
 		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
 		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
@@ -2310,7 +2397,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
 	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
 	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
-	kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
+	kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
 	kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
 	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
 	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
@@ -2342,6 +2429,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	sync_regs(vcpu, kvm_run);
+	enable_cpu_timer_accounting(vcpu);
 
 	might_fault();
 	rc = __vcpu_run(vcpu);
@@ -2361,6 +2449,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = 0;
 	}
 
+	disable_cpu_timer_accounting(vcpu);
 	store_regs(vcpu, kvm_run);
 
 	if (vcpu->sigset_active)
@@ -2381,7 +2470,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 	unsigned char archmode = 1;
 	freg_t fprs[NUM_FPRS];
 	unsigned int px;
-	u64 clkcomp;
+	u64 clkcomp, cputm;
 	int rc;
 
 	px = kvm_s390_get_prefix(vcpu);
@@ -2415,8 +2504,9 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
+	cputm = kvm_s390_get_cpu_timer(vcpu);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
-			      &vcpu->arch.sie_block->cputm, 8);
+			      &cputm, 8);
 	clkcomp = vcpu->arch.sie_block->ckc >> 8;
 	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
 			      &clkcomp, 8);

arch/s390/kvm/kvm-s390.h

@@ -54,6 +54,11 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
 }
 
+static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_WAIT;
+}
+
 static inline int kvm_is_ucontrol(struct kvm *kvm)
 {
 #ifdef CONFIG_KVM_S390_UCONTROL
@@ -155,8 +160,8 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 /* test availability of facility in a kvm instance */
 static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
 {
-	return __test_facility(nr, kvm->arch.model.fac->mask) &&
-		__test_facility(nr, kvm->arch.model.fac->list);
+	return __test_facility(nr, kvm->arch.model.fac_mask) &&
+		__test_facility(nr, kvm->arch.model.fac_list);
 }
 
 static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
@@ -263,6 +268,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 unsigned long kvm_s390_fac_list_mask_size(void);
 extern unsigned long kvm_s390_fac_list_mask[];
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
 
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -354,7 +354,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	 * We need to shift the lower 32 facility bits (bit 0-31) from a u64
 	 * into a u32 memory representation. They will remain bits 0-31.
 	 */
-	fac = *vcpu->kvm->arch.model.fac->list >> 32;
+	fac = *vcpu->kvm->arch.model.fac_list >> 32;
 	rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
 			    &fac, sizeof(fac));
 	if (rc)