Merge tag 'kvm-s390-next-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390 features, kvm_get_vcpu_by_id and stat

Several features for s390
1. ESCA support (up to 248 vCPUs)
2. KVM detection: we  can now detect if we support KVM (e.g. does KVM
   under KVM work?)

kvm_stat:
1. cleanup the exit path

kvm_get_vcpu_by_id:
1. Use kvm_get_vcpu_by_id where appropriate
2. Apply a heuristic to optimize for ID VCPU == No. VCPU

arch/powerpc/kvm/book3s_hv.c

@@ -308,16 +308,10 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 
 static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
-	int r;
-	struct kvm_vcpu *v, *ret = NULL;
+	struct kvm_vcpu *ret;
 
 	mutex_lock(&kvm->lock);
-	kvm_for_each_vcpu(r, v, kvm) {
-		if (v->vcpu_id == id) {
-			ret = v;
-			break;
-		}
-	}
+	ret = kvm_get_vcpu_by_id(kvm, id);
 	mutex_unlock(&kvm->lock);
 	return ret;
 }

arch/s390/include/asm/elf.h

@@ -104,6 +104,9 @@
 #define HWCAP_S390_TE		1024
 #define HWCAP_S390_VXRS		2048
 
+/* Internal bits, not exposed via elf */
+#define HWCAP_INT_SIE		1UL
+
 /*
  * These are used to set parameters in the core dumps.
  */
@@ -169,6 +172,10 @@ extern unsigned int vdso_enabled;
 extern unsigned long elf_hwcap;
 #define ELF_HWCAP (elf_hwcap)
 
+/* Internal hardware capabilities, not exposed via elf */
+
+extern unsigned long int_hwcap;
+
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
    intent than poking at uname or /proc/cpuinfo.

arch/s390/include/asm/kvm_host.h

@@ -25,7 +25,9 @@
 #include <asm/fpu/api.h>
 #include <asm/isc.h>
 
-#define KVM_MAX_VCPUS 64
+#define KVM_S390_BSCA_CPU_SLOTS 64
+#define KVM_S390_ESCA_CPU_SLOTS 248
+#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS
 #define KVM_USER_MEM_SLOTS 32
 
 /*
@@ -40,9 +42,34 @@
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
 
-struct sca_entry {
+union bsca_sigp_ctrl {
+	__u8 value;
+	struct {
+		__u8 c : 1;
+		__u8 r : 1;
+		__u8 scn : 6;
+	};
+} __packed;
+
+union esca_sigp_ctrl {
+	__u16 value;
+	struct {
+		__u8 c : 1;
+		__u8 reserved: 7;
+		__u8 scn;
+	};
+} __packed;
+
+struct esca_entry {
+	union esca_sigp_ctrl sigp_ctrl;
+	__u16   reserved1[3];
+	__u64   sda;
+	__u64   reserved2[6];
+} __packed;
+
+struct bsca_entry {
 	__u8	reserved0;
-	__u8	sigp_ctrl;
+	union bsca_sigp_ctrl	sigp_ctrl;
 	__u16	reserved[3];
 	__u64	sda;
 	__u64	reserved2[2];
@@ -57,14 +84,22 @@ union ipte_control {
 	};
 };
 
-struct sca_block {
+struct bsca_block {
 	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
-	struct sca_entry cpu[64];
+	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
 } __attribute__((packed));
 
+struct esca_block {
+	union ipte_control ipte_control;
+	__u64   reserved1[7];
+	__u64   mcn[4];
+	__u64   reserved2[20];
+	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
+} __packed;
+
 #define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
@@ -585,7 +620,9 @@ struct kvm_s390_crypto_cb {
 };
 
 struct kvm_arch{
-	struct sca_block *sca;
+	void *sca;
+	int use_esca;
+	rwlock_t sca_lock;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;

arch/s390/include/asm/sclp.h

@@ -29,7 +29,10 @@ struct sclp_ipl_info {
 
 struct sclp_core_entry {
 	u8 core_id;
-	u8 reserved0[2];
+	u8 reserved0;
+	u8 : 4;
+	u8 sief2 : 1;
+	u8 : 3;
 	u8 : 3;
 	u8 siif : 1;
 	u8 sigpif : 1;
@@ -53,6 +56,9 @@ struct sclp_info {
 	unsigned char has_sigpif : 1;
 	unsigned char has_core_type : 1;
 	unsigned char has_sprp : 1;
+	unsigned char has_hvs : 1;
+	unsigned char has_esca : 1;
+	unsigned char has_sief2 : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;

arch/s390/kernel/processor.c

@@ -61,6 +61,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
 		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
+	static const char * const int_hwcap_str[] = {
+		"sie"
+	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
 
@@ -75,6 +78,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
 			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
 				seq_printf(m, "%s ", hwcap_str[i]);
+		for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
+			if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
+				seq_printf(m, "%s ", int_hwcap_str[i]);
 		seq_puts(m, "\n");
 		show_cacheinfo(m);
 	}

arch/s390/kernel/setup.c

@@ -80,6 +80,8 @@ EXPORT_SYMBOL(console_irq);
 unsigned long elf_hwcap __read_mostly = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
+unsigned long int_hwcap = 0;
+
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
 unsigned long __initdata max_physmem_end;
@@ -793,6 +795,13 @@ static int __init setup_hwcaps(void)
 		strcpy(elf_platform, "z13");
 		break;
 	}
+
+	/*
+	 * Virtualization support HWCAP_INT_SIE is bit 0.
+	 */
+	if (sclp.has_sief2)
+		int_hwcap |= HWCAP_INT_SIE;
+
 	return 0;
 }
 arch_initcall(setup_hwcaps);

arch/s390/kvm/diag.c

@@ -155,10 +155,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 
 static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tcpu;
 	int tid;
-	int i;
 
 	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	vcpu->stat.diagnose_9c++;
@@ -167,12 +165,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 	if (tid == vcpu->vcpu_id)
 		return 0;
 
-	kvm_for_each_vcpu(i, tcpu, kvm)
-		if (tcpu->vcpu_id == tid) {
-			kvm_vcpu_yield_to(tcpu);
-			break;
-		}
-
+	tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+	if (tcpu)
+		kvm_vcpu_yield_to(tcpu);
 	return 0;
 }
 

arch/s390/kvm/gaccess.c

@@ -259,10 +259,14 @@ struct aste {
 
 int ipte_lock_held(struct kvm_vcpu *vcpu)
 {
-	union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+	if (vcpu->arch.sie_block->eca & 1) {
+		int rc;
 
-	if (vcpu->arch.sie_block->eca & 1)
-		return ic->kh != 0;
+		read_lock(&vcpu->kvm->arch.sca_lock);
+		rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+		read_unlock(&vcpu->kvm->arch.sca_lock);
+		return rc;
+	}
 	return vcpu->kvm->arch.ipte_lock_count != 0;
 }
 
@@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count++;
 	if (vcpu->kvm->arch.ipte_lock_count > 1)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.k) {
+		if (old.k) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
 }
@@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count--;
 	if (vcpu->kvm->arch.ipte_lock_count)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
 		new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	wake_up(&vcpu->kvm->arch.ipte_wq);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,24 +321,29 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.kg) {
+		if (old.kg) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 		new.kh++;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
 static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
@@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 		if (!new.kh)
 			new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	if (!new.kh)
 		wake_up(&vcpu->kvm->arch.ipte_wq);
 }

arch/s390/kvm/intercept.c

@@ -54,9 +54,6 @@ void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
 static int handle_noop(struct kvm_vcpu *vcpu)
 {
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x0:
-		vcpu->stat.exit_null++;
-		break;
 	case 0x10:
 		vcpu->stat.exit_external_request++;
 		break;
@@ -338,8 +335,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
 
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm))
+		return -EOPNOTSUPP;
+
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x00:
 	case 0x10:
 	case 0x18:
 		return handle_noop(vcpu);

arch/s390/kvm/interrupt.c

@@ -34,6 +34,106 @@
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
 
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+	int c, scn;
+
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+		return 0;
+
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+
+	if (src_id)
+		*src_id = scn;
+
+	return c;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+	int expect, rc;
+
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
+
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
+
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+
+	if (rc != expect) {
+		/* another external call is pending */
+		return -EBUSY;
+	}
+	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	return 0;
+}
+
+static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	int rc, expect;
+
+	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+	WARN_ON(rc != expect); /* cannot clear? */
+}
+
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -792,13 +892,11 @@ static const deliver_irq_t deliver_irq_funcs[] = {
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
 	if (!sclp.has_sigpif)
 		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 
-	return (sigp_ctrl & SIGP_CTRL_C) &&
-	       (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+	return sca_ext_call_pending(vcpu, NULL);
 }
 
 int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -909,9 +1007,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 	memset(&li->irq, 0, sizeof(li->irq));
 	spin_unlock(&li->lock);
 
-	/* clear pending external calls set by sigp interpretation facility */
-	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
-	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+	sca_clear_ext_call(vcpu);
 }
 
 int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -1003,21 +1099,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	return 0;
 }
 
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
-	unsigned char new_val, old_val;
-	uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
-	new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
-	old_val = *sigp_ctrl & ~SIGP_CTRL_C;
-	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
-		/* another external call is pending */
-		return -EBUSY;
-	}
-	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
-	return 0;
-}
-
 static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1034,7 +1115,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 		return -EINVAL;
 
 	if (sclp.has_sigpif)
-		return __inject_extcall_sigpif(vcpu, src_id);
+		return sca_inject_ext_call(vcpu, src_id);
 
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
@@ -2203,7 +2284,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li,
 
 int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 {
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	int scn;
 	unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	unsigned long pending_irqs;
@@ -2243,14 +2324,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 		}
 	}
 
-	if ((sigp_ctrl & SIGP_CTRL_C) &&
-	    (atomic_read(&vcpu->arch.sie_block->cpuflags) &
-	     CPUSTAT_ECALL_PEND)) {
+	if (sca_ext_call_pending(vcpu, &scn)) {
 		if (n + sizeof(irq) > len)
 			return -ENOBUFS;
 		memset(&irq, 0, sizeof(irq));
 		irq.type = KVM_S390_INT_EXTERNAL_CALL;
-		irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+		irq.u.extcall.code = scn;
 		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
 			return -EFAULT;
 		n += sizeof(irq);

arch/s390/kvm/kvm-s390.c

@@ -246,7 +246,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
-		r = KVM_MAX_VCPUS;
+		r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+				  : KVM_S390_BSCA_CPU_SLOTS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_USER_MEM_SLOTS;
@@ -283,6 +284,8 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 }
 
 /* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -1024,7 +1027,7 @@ static int kvm_s390_apxa_installed(void)
 	u8 config[128];
 	int cc;
 
-	if (test_facility(2) && test_facility(12)) {
+	if (test_facility(12)) {
 		cc = kvm_s390_query_ap_config(config);
 
 		if (cc)
@@ -1075,6 +1078,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
 	return 0;
 }
 
+static void sca_dispose(struct kvm *kvm)
+{
+	if (kvm->arch.use_esca)
+		free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
+	else
+		free_page((unsigned long)(kvm->arch.sca));
+	kvm->arch.sca = NULL;
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int i, rc;
@@ -1098,14 +1110,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	rc = -ENOMEM;
 
-	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+	kvm->arch.use_esca = 0; /* start with basic SCA */
+	rwlock_init(&kvm->arch.sca_lock);
+	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
 		goto out_err;
 	spin_lock(&kvm_lock);
 	sca_offset += 16;
-	if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
 		sca_offset = 0;
-	kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+	kvm->arch.sca = (struct bsca_block *)
+			((char *) kvm->arch.sca + sca_offset);
 	spin_unlock(&kvm_lock);
 
 	sprintf(debug_name, "kvm-%u", current->pid);
@@ -1177,7 +1192,7 @@ out_err:
 	kfree(kvm->arch.crypto.crycb);
 	free_page((unsigned long)kvm->arch.model.fac);
 	debug_unregister(kvm->arch.dbf);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	KVM_EVENT(3, "creation of vm failed: %d", rc);
 	return rc;
 }
@@ -1188,13 +1203,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
 	kvm_s390_clear_local_irqs(vcpu);
 	kvm_clear_async_pf_completion_queue(vcpu);
-	if (!kvm_is_ucontrol(vcpu->kvm)) {
-		clear_bit(63 - vcpu->vcpu_id,
-			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		    (__u64) vcpu->arch.sie_block)
-			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
-	}
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		sca_del_vcpu(vcpu);
 	smp_mb();
 
 	if (kvm_is_ucontrol(vcpu->kvm))
@@ -1228,7 +1238,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)kvm->arch.model.fac);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
 	kfree(kvm->arch.crypto.crycb);
 	if (!kvm_is_ucontrol(kvm))
@@ -1249,6 +1259,116 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+		sca->cpu[vcpu->vcpu_id].sda = 0;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+		sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
+{
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+	d->sda = s->sda;
+	d->sigp_ctrl.c = s->sigp_ctrl.c;
+	d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+	int i;
+
+	d->ipte_control = s->ipte_control;
+	d->mcn[0] = s->mcn;
+	for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+		sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+static int sca_switch_to_extended(struct kvm *kvm)
+{
+	struct bsca_block *old_sca = kvm->arch.sca;
+	struct esca_block *new_sca;
+	struct kvm_vcpu *vcpu;
+	unsigned int vcpu_idx;
+	u32 scaol, scaoh;
+
+	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+	if (!new_sca)
+		return -ENOMEM;
+
+	scaoh = (u32)((u64)(new_sca) >> 32);
+	scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+	kvm_s390_vcpu_block_all(kvm);
+	write_lock(&kvm->arch.sca_lock);
+
+	sca_copy_b_to_e(new_sca, old_sca);
+
+	kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+		vcpu->arch.sie_block->scaoh = scaoh;
+		vcpu->arch.sie_block->scaol = scaol;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
+	}
+	kvm->arch.sca = new_sca;
+	kvm->arch.use_esca = 1;
+
+	write_unlock(&kvm->arch.sca_lock);
+	kvm_s390_vcpu_unblock_all(kvm);
+
+	free_page((unsigned long)old_sca);
+
+	VM_EVENT(kvm, 2, "Switched to ESCA (%p -> %p)", old_sca, kvm->arch.sca);
+	return 0;
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+	int rc;
+
+	if (id < KVM_S390_BSCA_CPU_SLOTS)
+		return true;
+	if (!sclp.has_esca)
+		return false;
+
+	mutex_lock(&kvm->lock);
+	rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
+	mutex_unlock(&kvm->lock);
+
+	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1369,8 +1489,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
 	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
-	if (!kvm_is_ucontrol(vcpu->kvm))
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+		sca_add_vcpu(vcpu);
+	}
+
 }
 
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1465,7 +1588,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	struct sie_page *sie_page;
 	int rc = -EINVAL;
 
-	if (id >= KVM_MAX_VCPUS)
+	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
 		goto out;
 
 	rc = -ENOMEM;
@@ -1482,20 +1605,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
 
 	vcpu->arch.sie_block->icpua = id;
-	if (!kvm_is_ucontrol(kvm)) {
-		if (!kvm->arch.sca) {
-			WARN_ON_ONCE(1);
-			goto out_free_cpu;
-		}
-		if (!kvm->arch.sca->cpu[id].sda)
-			kvm->arch.sca->cpu[id].sda =
-				(__u64) vcpu->arch.sie_block;
-		vcpu->arch.sie_block->scaoh =
-			(__u32)(((__u64)kvm->arch.sca) >> 32);
-		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
-	}
-
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
@@ -1509,10 +1618,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	 */
 	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
 					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs) {
-		rc = -ENOMEM;
+	if (!vcpu->arch.guest_fpregs.fprs)
 		goto out_free_sie_block;
-	}
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
@@ -2071,8 +2178,6 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 {
-	int rc = -1;
-
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2080,40 +2185,35 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	if (guestdbg_enabled(vcpu))
 		kvm_s390_restore_guest_per_regs(vcpu);
 
-	if (exit_reason >= 0) {
-		rc = 0;
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+
+	if (vcpu->arch.sie_block->icptcode > 0) {
+		int rc = kvm_handle_sie_intercept(vcpu);
+
+		if (rc != -EOPNOTSUPP)
+			return rc;
+		vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+		vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+		vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+		vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+		return -EREMOTE;
+	} else if (exit_reason != -EFAULT) {
+		vcpu->stat.exit_null++;
+		return 0;
 	} else if (kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
 		vcpu->run->s390_ucontrol.trans_exc_code =
 						current->thread.gmap_addr;
 		vcpu->run->s390_ucontrol.pgm_code = 0x10;
-		rc = -EREMOTE;
-
+		return -EREMOTE;
 	} else if (current->thread.gmap_pfault) {
 		trace_kvm_s390_major_guest_pfault(vcpu);
 		current->thread.gmap_pfault = 0;
-		if (kvm_arch_setup_async_pf(vcpu)) {
-			rc = 0;
-		} else {
-			gpa_t gpa = current->thread.gmap_addr;
-			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
-		}
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
 	}
-
-	if (rc == -1)
-		rc = vcpu_post_run_fault_in_sie(vcpu);
-
-	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
-	if (rc == 0) {
-		if (kvm_is_ucontrol(vcpu->kvm))
-			/* Don't exit for host interrupts. */
-			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
-		else
-			rc = kvm_handle_sie_intercept(vcpu);
-	}
-
-	return rc;
+	return vcpu_post_run_fault_in_sie(vcpu);
 }
 
 static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2233,18 +2333,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = 0;
 	}
 
-	if (rc == -EOPNOTSUPP) {
-		/* intercept cannot be handled in-kernel, prepare kvm-run */
-		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
-		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
-		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
-		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
-		rc = 0;
-	}
-
 	if (rc == -EREMOTE) {
-		/* intercept was handled, but userspace support is needed
-		 * kvm_run has been prepared by the handler */
+		/* userspace support is needed, kvm_run has been prepared */
 		rc = 0;
 	}
 
@@ -2767,6 +2857,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 static int __init kvm_s390_init(void)
 {
+	if (!sclp.has_sief2) {
+		pr_info("SIE not available\n");
+		return -ENODEV;
+	}
+
 	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 }
 

arch/s390/kvm/kvm-s390.h

@@ -340,4 +340,11 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+	struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+	return &sca->ipte_control;
+}
 #endif

drivers/s390/char/sclp_early.c

@@ -43,7 +43,10 @@ struct read_info_sccb {
 	u8	_pad_92[100 - 92];	/* 92-99 */
 	u32	rnsize2;		/* 100-103 */
 	u64	rnmax2;			/* 104-111 */
-	u8	_pad_112[120 - 112];	/* 112-119 */
+	u8	_pad_112[116 - 112];	/* 112-115 */
+	u8	fac116;			/* 116 */
+	u8	_pad_117[119 - 117];	/* 117-118 */
+	u8	fac119;			/* 119 */
 	u16	hcpua;			/* 120-121 */
 	u8	_pad_122[4096 - 122];	/* 122-4095 */
 } __packed __aligned(PAGE_SIZE);
@@ -108,6 +111,8 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 	sclp.facilities = sccb->facilities;
 	sclp.has_sprp = !!(sccb->fac84 & 0x02);
 	sclp.has_core_type = !!(sccb->fac84 & 0x01);
+	sclp.has_esca = !!(sccb->fac116 & 0x08);
+	sclp.has_hvs = !!(sccb->fac119 & 0x80);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
 	sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
@@ -131,6 +136,7 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 			continue;
 		sclp.has_siif = cpue->siif;
 		sclp.has_sigpif = cpue->sigpif;
+		sclp.has_sief2 = cpue->sief2;
 		break;
 	}
 

include/linux/kvm_host.h

@@ -472,6 +472,11 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 	struct kvm_vcpu *vcpu;
 	int i;
 
+	if (id < 0 || id >= KVM_MAX_VCPUS)
+		return NULL;
+	vcpu = kvm_get_vcpu(kvm, id);
+	if (vcpu && vcpu->vcpu_id == id)
+		return vcpu;
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		if (vcpu->vcpu_id == id)
 			return vcpu;
@@ -1011,7 +1016,6 @@ struct kvm_stats_debugfs_item {
 	const char *name;
 	int offset;
 	enum kvm_stat_kind kind;
-	struct dentry *dentry;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;

virt/kvm/kvm_main.c

@@ -2257,7 +2257,7 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 {
 	int r;
-	struct kvm_vcpu *vcpu, *v;
+	struct kvm_vcpu *vcpu;
 
 	if (id >= KVM_MAX_VCPUS)
 		return -EINVAL;
@@ -2281,12 +2281,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		r = -EINVAL;
 		goto unlock_vcpu_destroy;
 	}
-
-	kvm_for_each_vcpu(r, v, kvm)
-		if (v->vcpu_id == id) {
-			r = -EEXIST;
-			goto unlock_vcpu_destroy;
-		}
+	if (kvm_get_vcpu_by_id(kvm, id)) {
+		r = -EEXIST;
+		goto unlock_vcpu_destroy;
+	}
 
 	BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]);
 
@@ -3449,10 +3447,9 @@ static int kvm_init_debug(void)
 		goto out;
 
 	for (p = debugfs_entries; p->name; ++p) {
-		p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
-						(void *)(long)p->offset,
-						stat_fops[p->kind]);
-		if (p->dentry == NULL)
+		if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
+					 (void *)(long)p->offset,
+					 stat_fops[p->kind]))
 			goto out_dir;
 	}
 
@@ -3464,15 +3461,6 @@ out:
 	return r;
 }
 
-static void kvm_exit_debug(void)
-{
-	struct kvm_stats_debugfs_item *p;
-
-	for (p = debugfs_entries; p->name; ++p)
-		debugfs_remove(p->dentry);
-	debugfs_remove(kvm_debugfs_dir);
-}
-
 static int kvm_suspend(void)
 {
 	if (kvm_usage_count)
@@ -3630,7 +3618,7 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	kvm_exit_debug();
+	debugfs_remove_recursive(kvm_debugfs_dir);
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	kvm_async_pf_deinit();