From 81aa8efe0190cf5bf7eaafb57341cd7d0aea96cd Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 16:13:44 +0200
Subject: KVM: s390: add and extend interrupt information data structs

With the currently available struct kvm_s390_interrupt it is not possible to
inject every kind of interrupt as defined in the z/Architecture. Add
additional interruption parameters to the structures and move it to kvm.h

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 include/uapi/linux/kvm.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 932d7f2637d6..86faf47ae494 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -434,6 +434,69 @@ struct kvm_s390_interrupt {
 	__u64 parm64;
 };
 
+struct kvm_s390_io_info {
+	__u16 subchannel_id;
+	__u16 subchannel_nr;
+	__u32 io_int_parm;
+	__u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+	__u32 ext_params;
+	__u32 pad;
+	__u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+	__u64 trans_exc_code;
+	__u64 mon_code;
+	__u64 per_address;
+	__u32 data_exc_code;
+	__u16 code;
+	__u16 mon_class_nr;
+	__u8 per_code;
+	__u8 per_atmid;
+	__u8 exc_access_id;
+	__u8 per_access_id;
+	__u8 op_access_id;
+	__u8 pad[3];
+};
+
+struct kvm_s390_prefix_info {
+	__u32 address;
+};
+
+struct kvm_s390_extcall_info {
+	__u16 code;
+};
+
+struct kvm_s390_emerg_info {
+	__u16 code;
+};
+
+struct kvm_s390_mchk_info {
+	__u64 cr14;
+	__u64 mcic;
+	__u64 failing_storage_address;
+	__u32 ext_damage_code;
+	__u32 pad;
+	__u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+	__u64 type;
+	union {
+		struct kvm_s390_io_info io;
+		struct kvm_s390_ext_info ext;
+		struct kvm_s390_pgm_info pgm;
+		struct kvm_s390_emerg_info emerg;
+		struct kvm_s390_extcall_info extcall;
+		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_mchk_info mchk;
+		char reserved[64];
+	} u;
+};
+
 /* for KVM_SET_GUEST_DEBUG */
 
 #define KVM_GUESTDBG_ENABLE		0x00000001
-- 
cgit v1.2.3


From c05c4186bbe4e99d64e8a36f7ca7f480da5d109f Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 16:13:45 +0200
Subject: KVM: s390: add floating irq controller

This patch adds a floating irq controller as a kvm_device.
It will be necessary for migration of floating interrupts as well
as for hardening the reset code by allowing user space to explicitly
remove all pending floating interrupts.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 Documentation/virtual/kvm/devices/s390_flic.txt |  36 +++
 arch/s390/include/asm/kvm_host.h                |   1 +
 arch/s390/include/uapi/asm/kvm.h                |  14 ++
 arch/s390/kvm/interrupt.c                       | 304 ++++++++++++++++++++----
 arch/s390/kvm/kvm-s390.c                        |   1 +
 include/linux/kvm_host.h                        |   1 +
 include/uapi/linux/kvm.h                        |   1 +
 virt/kvm/kvm_main.c                             |   5 +
 8 files changed, 312 insertions(+), 51 deletions(-)
 create mode 100644 Documentation/virtual/kvm/devices/s390_flic.txt

(limited to 'include/uapi')

diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
new file mode 100644
index 000000000000..6b557953066a
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -0,0 +1,36 @@
+FLIC (floating interrupt controller)
+====================================
+
+FLIC handles floating (non per-cpu) interrupts, i.e. I/O, service and some
+machine check interruptions. All interrupts are stored in a per-vm list of
+pending interrupts. FLIC performs operations on this list.
+
+Only one FLIC instance may be instantiated.
+
+FLIC provides support to
+- add interrupts (KVM_DEV_FLIC_ENQUEUE)
+- inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
+- purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
+
+Groups:
+  KVM_DEV_FLIC_ENQUEUE
+    Passes a buffer and length into the kernel which are then injected into
+    the list of pending interrupts.
+    attr->addr contains the pointer to the buffer and attr->attr contains
+    the length of the buffer.
+    The format of the data structure kvm_s390_irq as it is copied from userspace
+    is defined in usr/include/linux/kvm.h.
+
+  KVM_DEV_FLIC_GET_ALL_IRQS
+    Copies all floating interrupts into a buffer provided by userspace.
+    When the buffer is too small it returns -ENOMEM, which is the indication
+    for userspace to try again with a bigger buffer.
+    All interrupts remain pending, i.e. are not deleted from the list of
+    currently pending interrupts.
+    attr->addr contains the userspace address of the buffer into which all
+    interrupt data will be copied.
+    attr->attr contains the size of the buffer in bytes.
+
+  KVM_DEV_FLIC_CLEAR_IRQS
+    Simply deletes all elements from the list of currently pending floating
+    interrupts.  No interrupts are injected into the guest.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3ffc9646e742..59635b5c59a6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -243,6 +243,7 @@ struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
+	struct kvm_device *flic;
 	struct gmap *gmap;
 	int css_support;
 };
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index d25da598ec62..38d5f98552bb 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -16,6 +16,20 @@
 
 #define __KVM_S390
 
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS	1
+#define KVM_DEV_FLIC_ENQUEUE		2
+#define KVM_DEV_FLIC_CLEAR_IRQS		3
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+
+#define KVM_S390_FLIC_MAX_BUFFER	0x2000000
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5f79d2d79ca7..a5f18babed4c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -659,53 +659,86 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 	return inti;
 }
 
-int kvm_s390_inject_vm(struct kvm *kvm,
-		       struct kvm_s390_interrupt *s390int)
+static void __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 {
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti, *iter;
+	struct kvm_s390_interrupt_info *iter;
 	int sigcpu;
 
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	if (!is_ioint(inti->type)) {
+		list_add_tail(&inti->list, &fi->list);
+	} else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+		/* Keep I/O interrupts sorted in isc order. */
+		list_for_each_entry(iter, &fi->list, list) {
+			if (!is_ioint(iter->type))
+				continue;
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
+				continue;
+			break;
+		}
+		list_add_tail(&inti->list, &iter->list);
+	}
+	atomic_set(&fi->active, 1);
+	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+	if (sigcpu == KVM_MAX_VCPUS) {
+		do {
+			sigcpu = fi->next_rr_cpu++;
+			if (sigcpu == KVM_MAX_VCPUS)
+				sigcpu = fi->next_rr_cpu = 0;
+		} while (fi->local_int[sigcpu] == NULL);
+	}
+	li = fi->local_int[sigcpu];
+	spin_lock_bh(&li->lock);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(li->wq))
+		wake_up_interruptible(li->wq);
+	spin_unlock_bh(&li->lock);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+		       struct kvm_s390_interrupt *s390int)
+{
+	struct kvm_s390_interrupt_info *inti;
+
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
 		return -ENOMEM;
 
-	switch (s390int->type) {
+	inti->type = s390int->type;
+	switch (inti->type) {
 	case KVM_S390_INT_VIRTIO:
 		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
 			 s390int->parm, s390int->parm64);
-		inti->type = s390int->type;
 		inti->ext.ext_params = s390int->parm;
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_INT_SERVICE:
 		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
-		inti->type = s390int->type;
 		inti->ext.ext_params = s390int->parm;
 		break;
-	case KVM_S390_PROGRAM_INT:
-	case KVM_S390_SIGP_STOP:
-	case KVM_S390_INT_EXTERNAL_CALL:
-	case KVM_S390_INT_EMERGENCY:
-		kfree(inti);
-		return -EINVAL;
 	case KVM_S390_MCHK:
 		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
 			 s390int->parm64);
-		inti->type = s390int->type;
 		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 (s390int->type & IOINT_AI_MASK)
+		if (inti->type & IOINT_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",
 				 s390int->type & IOINT_CSSID_MASK,
 				 s390int->type & IOINT_SSID_MASK,
 				 s390int->type & IOINT_SCHID_MASK);
-		inti->type = s390int->type;
 		inti->io.subchannel_id = s390int->parm >> 16;
 		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
 		inti->io.io_int_parm = s390int->parm64 >> 32;
@@ -718,42 +751,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
 				 2);
 
-	mutex_lock(&kvm->lock);
-	fi = &kvm->arch.float_int;
-	spin_lock(&fi->lock);
-	if (!is_ioint(inti->type))
-		list_add_tail(&inti->list, &fi->list);
-	else {
-		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
-
-		/* Keep I/O interrupts sorted in isc order. */
-		list_for_each_entry(iter, &fi->list, list) {
-			if (!is_ioint(iter->type))
-				continue;
-			if (int_word_to_isc_bits(iter->io.io_int_word)
-			    <= isc_bits)
-				continue;
-			break;
-		}
-		list_add_tail(&inti->list, &iter->list);
-	}
-	atomic_set(&fi->active, 1);
-	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
-	if (sigcpu == KVM_MAX_VCPUS) {
-		do {
-			sigcpu = fi->next_rr_cpu++;
-			if (sigcpu == KVM_MAX_VCPUS)
-				sigcpu = fi->next_rr_cpu = 0;
-		} while (fi->local_int[sigcpu] == NULL);
-	}
-	li = fi->local_int[sigcpu];
-	spin_lock_bh(&li->lock);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
-	spin_unlock_bh(&li->lock);
-	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
+	__inject_vm(kvm, inti);
 	return 0;
 }
 
@@ -841,3 +839,207 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 	mutex_unlock(&vcpu->kvm->lock);
 	return 0;
 }
+
+static void clear_floating_interrupts(struct kvm *kvm)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info	*n, *inti = NULL;
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	list_for_each_entry_safe(inti, n, &fi->list, list) {
+		list_del(&inti->list);
+		kfree(inti);
+	}
+	atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+}
+
+static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
+				   u8 *addr)
+{
+	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+	struct kvm_s390_irq irq = {0};
+
+	irq.type = inti->type;
+	switch (inti->type) {
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+		irq.u.ext = inti->ext;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		irq.u.io = inti->io;
+		break;
+	case KVM_S390_MCHK:
+		irq.u.mchk = inti->mchk;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(uptr, &irq, sizeof(irq)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
+{
+	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_float_interrupt *fi;
+	int ret = 0;
+	int n = 0;
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+
+	list_for_each_entry(inti, &fi->list, list) {
+		if (len < sizeof(struct kvm_s390_irq)) {
+			/* signal userspace to try again */
+			ret = -ENOMEM;
+			break;
+		}
+		ret = copy_irq_to_user(inti, buf);
+		if (ret)
+			break;
+		buf += sizeof(struct kvm_s390_irq);
+		len -= sizeof(struct kvm_s390_irq);
+		n++;
+	}
+
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+
+	return ret < 0 ? ret : n;
+}
+
+static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r;
+
+	switch (attr->group) {
+	case KVM_DEV_FLIC_GET_ALL_IRQS:
+		r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
+					  attr->attr);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti,
+				     u64 addr)
+{
+	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+	void *target = NULL;
+	void __user *source;
+	u64 size;
+
+	if (get_user(inti->type, (u64 __user *)addr))
+		return -EFAULT;
+
+	switch (inti->type) {
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+		target = (void *) &inti->ext;
+		source = &uptr->u.ext;
+		size = sizeof(inti->ext);
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		target = (void *) &inti->io;
+		source = &uptr->u.io;
+		size = sizeof(inti->io);
+		break;
+	case KVM_S390_MCHK:
+		target = (void *) &inti->mchk;
+		source = &uptr->u.mchk;
+		size = sizeof(inti->mchk);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_from_user(target, source, size))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int enqueue_floating_irq(struct kvm_device *dev,
+				struct kvm_device_attr *attr)
+{
+	struct kvm_s390_interrupt_info *inti = NULL;
+	int r = 0;
+	int len = attr->attr;
+
+	if (len % sizeof(struct kvm_s390_irq) != 0)
+		return -EINVAL;
+	else if (len > KVM_S390_FLIC_MAX_BUFFER)
+		return -EINVAL;
+
+	while (len >= sizeof(struct kvm_s390_irq)) {
+		inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+		if (!inti)
+			return -ENOMEM;
+
+		r = copy_irq_from_user(inti, attr->addr);
+		if (r) {
+			kfree(inti);
+			return r;
+		}
+		__inject_vm(dev->kvm, inti);
+		len -= sizeof(struct kvm_s390_irq);
+		attr->addr += sizeof(struct kvm_s390_irq);
+	}
+
+	return r;
+}
+
+static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r = 0;
+
+	switch (attr->group) {
+	case KVM_DEV_FLIC_ENQUEUE:
+		r = enqueue_floating_irq(dev, attr);
+		break;
+	case KVM_DEV_FLIC_CLEAR_IRQS:
+		r = 0;
+		clear_floating_interrupts(dev->kvm);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+static int flic_create(struct kvm_device *dev, u32 type)
+{
+	if (!dev)
+		return -EINVAL;
+	if (dev->kvm->arch.flic)
+		return -EINVAL;
+	dev->kvm->arch.flic = dev;
+	return 0;
+}
+
+static void flic_destroy(struct kvm_device *dev)
+{
+	dev->kvm->arch.flic = NULL;
+	kfree(dev);
+}
+
+/* s390 floating irq controller (flic) */
+struct kvm_device_ops kvm_flic_ops = {
+	.name = "kvm-flic",
+	.get_attr = flic_get_attr,
+	.set_attr = flic_set_attr,
+	.create = flic_create,
+	.destroy = flic_destroy,
+};
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f390d57..782420f3c4d5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -157,6 +157,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
 	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_DEVICE_CTRL:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b8e9a43e501a..c0102ef2de48 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1064,6 +1064,7 @@ extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
 extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
+extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 86faf47ae494..19f717b15297 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -918,6 +918,7 @@ struct kvm_device_attr {
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
 #define KVM_DEV_TYPE_ARM_VGIC_V2	5
+#define KVM_DEV_TYPE_FLIC		6
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381b1cb7..a9e999a48e43 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2283,6 +2283,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	case KVM_DEV_TYPE_ARM_VGIC_V2:
 		ops = &kvm_arm_vgic_v2_ops;
 		break;
+#endif
+#ifdef CONFIG_S390
+	case KVM_DEV_TYPE_FLIC:
+		ops = &kvm_flic_ops;
+		break;
 #endif
 	default:
 		return -ENODEV;
-- 
cgit v1.2.3


From 3c038e6be0e299d4d3762d0a9a29f02de6e04991 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 17:11:48 +0200
Subject: KVM: async_pf: Async page fault support on s390

This patch enables async page faults for s390 kvm guests.
It provides the userspace API to enable and disable_wait this feature.
The disable_wait will enforce that the feature is off by waiting on it.
Also it includes the diagnose code, called by the guest to enable async page faults.

The async page faults will use an already existing guest interface for this
purpose, as described in "CP Programming Services (SC24-6084)".

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 Documentation/virtual/kvm/devices/s390_flic.txt | 10 +++
 arch/s390/include/asm/kvm_host.h                | 22 ++++++
 arch/s390/include/uapi/asm/kvm.h                |  2 +
 arch/s390/kvm/Kconfig                           |  2 +
 arch/s390/kvm/Makefile                          |  2 +-
 arch/s390/kvm/diag.c                            | 84 +++++++++++++++++++++++
 arch/s390/kvm/interrupt.c                       | 65 ++++++++++++++++--
 arch/s390/kvm/kvm-s390.c                        | 89 ++++++++++++++++++++++++-
 arch/s390/kvm/kvm-s390.h                        |  4 ++
 arch/s390/kvm/sigp.c                            |  7 ++
 arch/s390/kvm/trace.h                           | 46 +++++++++++++
 include/uapi/linux/kvm.h                        |  2 +
 12 files changed, 326 insertions(+), 9 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index 6b557953066a..410fa673e5b6 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -11,6 +11,7 @@ FLIC provides support to
 - add interrupts (KVM_DEV_FLIC_ENQUEUE)
 - inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
 - purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
+- enable/disable for the guest transparent async page faults
 
 Groups:
   KVM_DEV_FLIC_ENQUEUE
@@ -34,3 +35,12 @@ Groups:
   KVM_DEV_FLIC_CLEAR_IRQS
     Simply deletes all elements from the list of currently pending floating
     interrupts.  No interrupts are injected into the guest.
+
+  KVM_DEV_FLIC_APF_ENABLE
+    Enables async page faults for the guest. So in case of a major page fault
+    the host is allowed to handle this async and continues the guest.
+
+  KVM_DEV_FLIC_APF_DISABLE_WAIT
+    Disables async page faults for the guest and waits until already pending
+    async page faults are done. This is necessary to trigger a completion interrupt
+    for every init interrupt before migrating the interrupt list.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index c3c5e1028136..2c69ba285e81 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -231,6 +231,10 @@ struct kvm_vcpu_arch {
 		u64		stidp_data;
 	};
 	struct gmap *gmap;
+#define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
+	unsigned long pfault_token;
+	unsigned long pfault_select;
+	unsigned long pfault_compare;
 };
 
 struct kvm_vm_stat {
@@ -257,6 +261,24 @@ static inline bool kvm_is_error_hva(unsigned long addr)
 	return IS_ERR_VALUE(addr);
 }
 
+#define ASYNC_PF_PER_VCPU	64
+struct kvm_vcpu;
+struct kvm_async_pf;
+struct kvm_arch_async_pf {
+	unsigned long pfault_token;
+};
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+			       struct kvm_async_pf *work);
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+				     struct kvm_async_pf *work);
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+				 struct kvm_async_pf *work);
+
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
 #endif
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 058b178391d4..ccfd0b1d056d 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -20,6 +20,8 @@
 #define KVM_DEV_FLIC_GET_ALL_IRQS	1
 #define KVM_DEV_FLIC_ENQUEUE		2
 #define KVM_DEV_FLIC_CLEAR_IRQS		3
+#define KVM_DEV_FLIC_APF_ENABLE		4
+#define KVM_DEV_FLIC_APF_DISABLE_WAIT	5
 /*
  * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
  * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 70b46eacf8e1..c8bacbcd2e5b 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -23,6 +23,8 @@ config KVM
 	select ANON_INODES
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_EVENTFD
+	select KVM_ASYNC_PF
+	select KVM_ASYNC_PF_SYNC
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 40b4c6470f88..a47d2c355f68 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8216c0e0b2e2..bf9ed34c2bcd 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -17,6 +17,7 @@
 #include "kvm-s390.h"
 #include "trace.h"
 #include "trace-s390.h"
+#include "gaccess.h"
 
 static int diag_release_pages(struct kvm_vcpu *vcpu)
 {
@@ -46,6 +47,87 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
+{
+	struct prs_parm {
+		u16 code;
+		u16 subcode;
+		u16 parm_len;
+		u16 parm_version;
+		u64 token_addr;
+		u64 select_mask;
+		u64 compare_mask;
+		u64 zarch;
+	};
+	struct prs_parm parm;
+	int rc;
+	u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
+	u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
+	unsigned long hva_token = KVM_HVA_ERR_BAD;
+
+	if (vcpu->run->s.regs.gprs[rx] & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	if (copy_from_guest(vcpu, &parm, vcpu->run->s.regs.gprs[rx], sizeof(parm)))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	switch (parm.subcode) {
+	case 0: /* TOKEN */
+		if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) {
+			/*
+			 * If the pagefault handshake is already activated,
+			 * the token must not be changed.  We have to return
+			 * decimal 8 instead, as mandated in SC24-6084.
+			 */
+			vcpu->run->s.regs.gprs[ry] = 8;
+			return 0;
+		}
+
+		if ((parm.compare_mask & parm.select_mask) != parm.compare_mask ||
+		    parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL)
+			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+		hva_token = gfn_to_hva(vcpu->kvm, gpa_to_gfn(parm.token_addr));
+		if (kvm_is_error_hva(hva_token))
+			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+		vcpu->arch.pfault_token = parm.token_addr;
+		vcpu->arch.pfault_select = parm.select_mask;
+		vcpu->arch.pfault_compare = parm.compare_mask;
+		vcpu->run->s.regs.gprs[ry] = 0;
+		rc = 0;
+		break;
+	case 1: /*
+		 * CANCEL
+		 * Specification allows to let already pending tokens survive
+		 * the cancel, therefore to reduce code complexity, we assume
+		 * all outstanding tokens are already pending.
+		 */
+		if (parm.token_addr || parm.select_mask ||
+		    parm.compare_mask || parm.zarch)
+			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+		vcpu->run->s.regs.gprs[ry] = 0;
+		/*
+		 * If the pfault handling was not established or is already
+		 * canceled SC24-6084 requests to return decimal 4.
+		 */
+		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+			vcpu->run->s.regs.gprs[ry] = 4;
+		else
+			vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+
+		rc = 0;
+		break;
+	default:
+		rc = -EOPNOTSUPP;
+		break;
+	}
+
+	return rc;
+}
+
 static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
@@ -150,6 +232,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 		return __diag_time_slice_end(vcpu);
 	case 0x9c:
 		return __diag_time_slice_end_directed(vcpu);
+	case 0x258:
+		return __diag_page_ref_service(vcpu);
 	case 0x308:
 		return __diag_ipl_functions(vcpu);
 	case 0x500:
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9c9192b5e339..1848080c3f34 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -31,7 +31,7 @@ static int is_ioint(u64 type)
 	return ((type & 0xfffe0000u) != 0xfffe0000u);
 }
 
-static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
 }
@@ -78,11 +78,8 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 			return 1;
 		return 0;
 	case KVM_S390_INT_SERVICE:
-		if (psw_extint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
-			return 1;
-		return 0;
+	case KVM_S390_INT_PFAULT_INIT:
+	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
 		if (psw_extint_disabled(vcpu))
 			return 0;
@@ -150,6 +147,8 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 	case KVM_S390_INT_EXTERNAL_CALL:
 	case KVM_S390_INT_EMERGENCY:
 	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_PFAULT_INIT:
+	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
 		if (psw_extint_disabled(vcpu))
 			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
@@ -223,6 +222,30 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		rc |= put_guest(vcpu, inti->ext.ext_params,
 				(u32 __user *)__LC_EXT_PARAMS);
 		break;
+	case KVM_S390_INT_PFAULT_INIT:
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
+						 inti->ext.ext_params2);
+		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
+		rc |= put_guest(vcpu, 0x0600, (u16 __user *) __LC_EXT_CPU_ADDR);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		rc |= put_guest(vcpu, inti->ext.ext_params2,
+				(u64 __user *) __LC_EXT_PARAMS2);
+		break;
+	case KVM_S390_INT_PFAULT_DONE:
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
+						 inti->ext.ext_params2);
+		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
+		rc |= put_guest(vcpu, 0x0680, (u16 __user *) __LC_EXT_CPU_ADDR);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		rc |= put_guest(vcpu, inti->ext.ext_params2,
+				(u64 __user *) __LC_EXT_PARAMS2);
+		break;
 	case KVM_S390_INT_VIRTIO:
 		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
 			   inti->ext.ext_params, inti->ext.ext_params2);
@@ -357,7 +380,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
@@ -737,6 +760,10 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
 		inti->ext.ext_params = s390int->parm;
 		break;
+	case KVM_S390_INT_PFAULT_DONE:
+		inti->type = s390int->type;
+		inti->ext.ext_params2 = s390int->parm64;
+		break;
 	case KVM_S390_MCHK:
 		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
 			 s390int->parm64);
@@ -823,6 +850,10 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		inti->type = s390int->type;
 		inti->mchk.mcic = s390int->parm64;
 		break;
+	case KVM_S390_INT_PFAULT_INIT:
+		inti->type = s390int->type;
+		inti->ext.ext_params2 = s390int->parm64;
+		break;
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
@@ -877,6 +908,8 @@ static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
 
 	irq.type = inti->type;
 	switch (inti->type) {
+	case KVM_S390_INT_PFAULT_INIT:
+	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
 		irq.u.ext = inti->ext;
@@ -956,6 +989,8 @@ static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti,
 		return -EFAULT;
 
 	switch (inti->type) {
+	case KVM_S390_INT_PFAULT_INIT:
+	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
 		target = (void *) &inti->ext;
@@ -1019,6 +1054,8 @@ static int enqueue_floating_irq(struct kvm_device *dev,
 static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	int r = 0;
+	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
 	switch (attr->group) {
 	case KVM_DEV_FLIC_ENQUEUE:
@@ -1028,6 +1065,20 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		r = 0;
 		clear_floating_interrupts(dev->kvm);
 		break;
+	case KVM_DEV_FLIC_APF_ENABLE:
+		dev->kvm->arch.gmap->pfault_enabled = 1;
+		break;
+	case KVM_DEV_FLIC_APF_DISABLE_WAIT:
+		dev->kvm->arch.gmap->pfault_enabled = 0;
+		/*
+		 * Make sure no async faults are in transition when
+		 * clearing the queues. So we don't need to worry
+		 * about late coming workers.
+		 */
+		synchronize_srcu(&dev->kvm->srcu);
+		kvm_for_each_vcpu(i, vcpu, dev->kvm)
+			kvm_clear_async_pf_completion_queue(vcpu);
+		break;
 	default:
 		r = -EINVAL;
 	}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9eec794caa7f..d8e9f04977db 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -152,6 +152,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_S390_UCONTROL
 	case KVM_CAP_S390_UCONTROL:
 #endif
+	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_SYNC_REGS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
@@ -273,6 +274,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
+	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);
@@ -322,6 +324,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+	kvm_clear_async_pf_completion_queue(vcpu);
 	if (kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->arch.gmap = gmap_alloc(current->mm);
 		if (!vcpu->arch.gmap)
@@ -382,6 +386,8 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.guest_fpregs.fpc = 0;
 	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
 	vcpu->arch.sie_block->gbea = 1;
+	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+	kvm_clear_async_pf_completion_queue(vcpu);
 	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 }
 
@@ -713,10 +719,89 @@ static long kvm_arch_fault_in_sync(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
+static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
+				      unsigned long token)
+{
+	struct kvm_s390_interrupt inti;
+	inti.parm64 = token;
+
+	if (start_token) {
+		inti.type = KVM_S390_INT_PFAULT_INIT;
+		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
+	} else {
+		inti.type = KVM_S390_INT_PFAULT_DONE;
+		WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
+	}
+}
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+				     struct kvm_async_pf *work)
+{
+	trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token);
+	__kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token);
+}
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+				 struct kvm_async_pf *work)
+{
+	trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token);
+	__kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token);
+}
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+			       struct kvm_async_pf *work)
+{
+	/* s390 will always inject the page directly */
+}
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * s390 will always inject the page directly,
+	 * but we still want check_async_completion to cleanup
+	 */
+	return true;
+}
+
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
+{
+	hva_t hva;
+	struct kvm_arch_async_pf arch;
+	int rc;
+
+	if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+		return 0;
+	if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
+	    vcpu->arch.pfault_compare)
+		return 0;
+	if (psw_extint_disabled(vcpu))
+		return 0;
+	if (kvm_cpu_has_interrupt(vcpu))
+		return 0;
+	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
+		return 0;
+	if (!vcpu->arch.gmap->pfault_enabled)
+		return 0;
+
+	hva = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
+	if (copy_from_guest(vcpu, &arch.pfault_token, vcpu->arch.pfault_token, 8))
+		return 0;
+
+	rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
+	return rc;
+}
+
 static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 {
 	int rc, cpuflags;
 
+	/*
+	 * On s390 notifications for arriving pages will be delivered directly
+	 * to the guest but the house keeping for completed pfaults is
+	 * handled outside the worker.
+	 */
+	kvm_check_async_pf_completion(vcpu);
+
 	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
 
 	if (need_resched())
@@ -758,8 +843,10 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 		rc = -EREMOTE;
 
 	} else if (current->thread.gmap_pfault) {
+		trace_kvm_s390_major_guest_pfault(vcpu);
 		current->thread.gmap_pfault = 0;
-		if (kvm_arch_fault_in_sync(vcpu) >= 0)
+		if (kvm_arch_setup_async_pf(vcpu) ||
+		    (kvm_arch_fault_in_sync(vcpu) >= 0))
 			rc = 0;
 	}
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index f9559b0bd620..ed4750a5bc3c 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -159,4 +159,8 @@ void exit_sie_sync(struct kvm_vcpu *vcpu);
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 
+/* implemented in interrupt.c */
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int psw_extint_disabled(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 87c2b3a3bd3e..fe9442d39f0e 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -224,6 +224,8 @@ unlock:
 static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 {
 	int rc;
+	unsigned int i;
+	struct kvm_vcpu *v;
 
 	switch (parameter & 0xff) {
 	case 0:
@@ -231,6 +233,11 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 		break;
 	case 1:
 	case 2:
+		kvm_for_each_vcpu(i, v, vcpu->kvm) {
+			v->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+			kvm_clear_async_pf_completion_queue(v);
+		}
+
 		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 		break;
 	default:
diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h
index 3db76b2daed7..e8e7213d4cc5 100644
--- a/arch/s390/kvm/trace.h
+++ b/arch/s390/kvm/trace.h
@@ -30,6 +30,52 @@
 	TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id,		\
 		  __entry->pswmask, __entry->pswaddr, p_args)
 
+TRACE_EVENT(kvm_s390_major_guest_pfault,
+	    TP_PROTO(VCPU_PROTO_COMMON),
+	    TP_ARGS(VCPU_ARGS_COMMON),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    ),
+	    VCPU_TP_PRINTK("%s", "major fault, maybe applicable for pfault")
+	);
+
+TRACE_EVENT(kvm_s390_pfault_init,
+	    TP_PROTO(VCPU_PROTO_COMMON, long pfault_token),
+	    TP_ARGS(VCPU_ARGS_COMMON, pfault_token),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(long, pfault_token)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->pfault_token = pfault_token;
+		    ),
+	    VCPU_TP_PRINTK("init pfault token %ld", __entry->pfault_token)
+	);
+
+TRACE_EVENT(kvm_s390_pfault_done,
+	    TP_PROTO(VCPU_PROTO_COMMON, long pfault_token),
+	    TP_ARGS(VCPU_ARGS_COMMON, pfault_token),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(long, pfault_token)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->pfault_token = pfault_token;
+		    ),
+	    VCPU_TP_PRINTK("done pfault token %ld", __entry->pfault_token)
+	);
+
 /*
  * Tracepoints for SIE entry and exit.
  */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 19f717b15297..7d76401d2bb5 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -413,6 +413,8 @@ struct kvm_s390_psw {
 #define KVM_S390_PROGRAM_INT		0xfffe0001u
 #define KVM_S390_SIGP_SET_PREFIX	0xfffe0002u
 #define KVM_S390_RESTART		0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT	0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE	0xfffe0005u
 #define KVM_S390_MCHK			0xfffe1000u
 #define KVM_S390_INT_VIRTIO		0xffff2603u
 #define KVM_S390_INT_SERVICE		0xffff2401u
-- 
cgit v1.2.3


From 100943c54e0947a07d2c0185368fc2fd848f7f28 Mon Sep 17 00:00:00 2001
From: "Gabriel L. Somlo" <gsomlo@gmail.com>
Date: Thu, 27 Feb 2014 23:06:17 -0500
Subject: kvm: x86: ignore ioapic polarity

Both QEMU and KVM have already accumulated a significant number of
optimizations based on the hard-coded assumption that ioapic polarity
will always use the ActiveHigh convention, where the logical and
physical states of level-triggered irq lines always match (i.e.,
active(asserted) == high == 1, inactive == low == 0). QEMU guests
are expected to follow directions given via ACPI and configure the
ioapic with polarity 0 (ActiveHigh). However, even when misbehaving
guests (e.g. OS X <= 10.9) set the ioapic polarity to 1 (ActiveLow),
QEMU will still use the ActiveHigh signaling convention when
interfacing with KVM.

This patch modifies KVM to completely ignore ioapic polarity as set by
the guest OS, enabling misbehaving guests to work alongside those which
comply with the ActiveHigh polarity specified by QEMU's ACPI tables.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gabriel L. Somlo <somlo@cmu.edu>
[Move documentation to KVM_IRQ_LINE, add ia64. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 16 +++++++++++++++-
 arch/ia64/kvm/kvm-ia64.c          |  1 +
 arch/x86/kvm/x86.c                |  1 +
 include/uapi/linux/kvm.h          |  1 +
 virt/kvm/ioapic.c                 |  1 -
 5 files changed, 18 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6cd63a9010fb..4714f282a43e 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -612,6 +612,20 @@ On some architectures it is required that an interrupt controller model has
 been previously created with KVM_CREATE_IRQCHIP.  Note that edge-triggered
 interrupts require the level to be set to 1 and then back to 0.
 
+On real hardware, interrupt pins can be active-low or active-high.  This
+does not matter for the level field of struct kvm_irq_level: 1 always
+means active (asserted), 0 means inactive (deasserted).
+
+x86 allows the operating system to program the interrupt polarity
+(active-low/active-high) for level-triggered interrupts, and KVM used
+to consider the polarity.  However, due to bitrot in the handling of
+active-low interrupts, the above convention is now valid on x86 too.
+This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED.  Userspace
+should not present interrupts to the guest as active-low unless this
+capability is present (or unless it is not using the in-kernel irqchip,
+of course).
+
+
 ARM/arm64 can signal an interrupt either at the CPU level, or at the
 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
 use PPIs designated for specific cpus.  The irq field is interpreted
@@ -628,7 +642,7 @@ The irq_type field has the following values:
 
 (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
 
-In both cases, level is used to raise/lower the line.
+In both cases, level is used to assert/deassert the line.
 
 struct kvm_irq_level {
 	union {
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 53f44bee9ebb..6a4309bb821a 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -199,6 +199,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IRQCHIP:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_IRQ_INJECT_STATUS:
+	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d906391a0a3f..a37da6b0165a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2657,6 +2657,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
 	case KVM_CAP_HYPERV_TIME:
+	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7d76401d2bb5..a7518be31d53 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -740,6 +740,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_SPAPR_MULTITCE 94
 #define KVM_CAP_EXT_EMUL_CPUID 95
 #define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index ce9ed99ad7dc..1539d3757a04 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -328,7 +328,6 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 	irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
 					 irq_source_id, level);
 	entry = ioapic->redirtbl[irq];
-	irq_level ^= entry.fields.polarity;
 	if (!irq_level) {
 		ioapic->irr &= ~mask;
 		ret = 1;
-- 
cgit v1.2.3


From d938dc55225a7212e7f31c5a8571da304cc3de16 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Wed, 23 Oct 2013 18:26:34 +0200
Subject: KVM: Add per-vm capability enablement.

Allow KVM_ENABLE_CAP to act on a vm as well as on a vcpu. This makes more
sense when the caller wants to enable a vm-related capability.

s390 will be the first user; wire it up.

Reviewed-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 Documentation/virtual/kvm/api.txt |  6 ++++--
 arch/s390/kvm/kvm-s390.c          | 24 ++++++++++++++++++++++++
 include/uapi/linux/kvm.h          |  5 +++++
 3 files changed, 33 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4714f282a43e..faf6fe9772c7 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -932,9 +932,9 @@ documentation when it pops into existence).
 
 4.37 KVM_ENABLE_CAP
 
-Capability: KVM_CAP_ENABLE_CAP
+Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
 Architectures: ppc, s390
-Type: vcpu ioctl
+Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
 Parameters: struct kvm_enable_cap (in)
 Returns: 0 on success; -1 on error
 
@@ -965,6 +965,8 @@ function properly, this is the place to put them.
        __u8  pad[64];
 };
 
+The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
+for vm-wide capabilities.
 
 4.38 KVM_GET_MP_STATE
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7337c577e949..9f1e99f12d4f 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -159,6 +159,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_S390_CSS_SUPPORT:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
+	case KVM_CAP_ENABLE_CAP_VM:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -187,6 +188,21 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	return 0;
 }
 
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -204,6 +220,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_s390_inject_vm(kvm, &s390int);
 		break;
 	}
+	case KVM_ENABLE_CAP: {
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			break;
+		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a7518be31d53..46ea1b470c76 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -741,6 +741,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_EXT_EMUL_CPUID 95
 #define KVM_CAP_HYPERV_TIME 96
 #define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
+#define KVM_CAP_ENABLE_CAP_VM 98
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1076,6 +1077,10 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_DEBUGREGS */
 #define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
 #define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
+/*
+ * vcpu version available with KVM_ENABLE_CAP
+ * vm version available with KVM_CAP_ENABLE_CAP_VM
+ */
 #define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)
 /* Available with KVM_CAP_XSAVE */
 #define KVM_GET_XSAVE		  _IOR(KVMIO,  0xa4, struct kvm_xsave)
-- 
cgit v1.2.3


From 84223598778ba08041f4297fda485df83414d57e Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Mon, 15 Jul 2013 13:36:01 +0200
Subject: KVM: s390: irq routing for adapter interrupts.

Introduce a new interrupt class for s390 adapter interrupts and enable
irqfds for s390.

This is depending on a new s390 specific vm capability, KVM_CAP_S390_IRQCHIP,
that needs to be enabled by userspace.

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 Documentation/virtual/kvm/api.txt |  21 +++++--
 arch/s390/include/asm/kvm_host.h  |   9 +++
 arch/s390/kvm/Kconfig             |   2 +
 arch/s390/kvm/Makefile            |   2 +-
 arch/s390/kvm/interrupt.c         | 121 ++++++++++++++++++++++++++++++++++++++
 arch/s390/kvm/irq.h               |  22 +++++++
 arch/s390/kvm/kvm-s390.c          |  17 ++++++
 include/linux/kvm_host.h          |   9 +++
 include/uapi/linux/kvm.h          |  11 ++++
 9 files changed, 209 insertions(+), 5 deletions(-)
 create mode 100644 arch/s390/kvm/irq.h

(limited to 'include/uapi')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index faf6fe9772c7..2cb1640a90ad 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -586,8 +586,8 @@ struct kvm_fpu {
 
 4.24 KVM_CREATE_IRQCHIP
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86, ia64, ARM, arm64
+Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
+Architectures: x86, ia64, ARM, arm64, s390
 Type: vm ioctl
 Parameters: none
 Returns: 0 on success, -1 on error
@@ -596,7 +596,10 @@ Creates an interrupt controller model in the kernel.  On x86, creates a virtual
 ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
 local APIC.  IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
 only go to the IOAPIC.  On ia64, a IOSAPIC is created. On ARM/arm64, a GIC is
-created.
+created. On s390, a dummy irq routing table is created.
+
+Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
+before KVM_CREATE_IRQCHIP can be used.
 
 
 4.25 KVM_IRQ_LINE
@@ -1336,7 +1339,7 @@ KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 ia64
+Architectures: x86 ia64 s390
 Type: vm ioctl
 Parameters: struct kvm_irq_routing (in)
 Returns: 0 on success, -1 on error
@@ -1359,6 +1362,7 @@ struct kvm_irq_routing_entry {
 	union {
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
+		struct kvm_irq_routing_s390_adapter adapter;
 		__u32 pad[8];
 	} u;
 };
@@ -1366,6 +1370,7 @@ struct kvm_irq_routing_entry {
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
 
 No flags are specified so far, the corresponding field must be set to zero.
 
@@ -1381,6 +1386,14 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+struct kvm_irq_routing_s390_adapter {
+	__u64 ind_addr;
+	__u64 summary_addr;
+	__u64 ind_offset;
+	__u32 summary_offset;
+	__u32 adapter_id;
+};
+
 
 4.53 KVM_ASSIGN_SET_MSIX_NR
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 0d5235262707..dd3933754d23 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -24,6 +24,14 @@
 #define KVM_MAX_VCPUS 64
 #define KVM_USER_MEM_SLOTS 32
 
+/*
+ * These seem to be used for allocating ->chip in the routing table,
+ * which we don't use. 4096 is an out-of-thin-air value. If we need
+ * to look at ->chip later on, we'll need to revisit this.
+ */
+#define KVM_NR_IRQCHIPS 1
+#define KVM_IRQCHIP_NUM_PINS 4096
+
 struct sca_entry {
 	atomic_t scn;
 	__u32	reserved;
@@ -274,6 +282,7 @@ struct kvm_arch{
 	struct kvm_device *flic;
 	struct gmap *gmap;
 	int css_support;
+	int use_irqchip;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 };
 
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index c8bacbcd2e5b..10d529ac9821 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -25,6 +25,8 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index a47d2c355f68..d3adb37e93a4 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 7ecef5a18e25..2e2814eceb85 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <linux/kvm_host.h>
 #include <linux/hrtimer.h>
+#include <linux/mmu_context.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
 #include <asm/asm-offsets.h>
@@ -1284,3 +1285,123 @@ struct kvm_device_ops kvm_flic_ops = {
 	.create = flic_create,
 	.destroy = flic_destroy,
 };
+
+static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
+{
+	unsigned long bit;
+
+	bit = bit_nr + (addr % PAGE_SIZE) * 8;
+
+	return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
+}
+
+static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
+					  u64 addr)
+{
+	struct s390_map_info *map;
+
+	if (!adapter)
+		return NULL;
+
+	list_for_each_entry(map, &adapter->maps, list) {
+		if (map->guest_addr == addr)
+			return map;
+	}
+	return NULL;
+}
+
+static int adapter_indicators_set(struct kvm *kvm,
+				  struct s390_io_adapter *adapter,
+				  struct kvm_s390_adapter_int *adapter_int)
+{
+	unsigned long bit;
+	int summary_set, idx;
+	struct s390_map_info *info;
+	void *map;
+
+	info = get_map_info(adapter, adapter_int->ind_addr);
+	if (!info)
+		return -1;
+	map = page_address(info->page);
+	bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap);
+	set_bit(bit, map);
+	idx = srcu_read_lock(&kvm->srcu);
+	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+	set_page_dirty_lock(info->page);
+	info = get_map_info(adapter, adapter_int->summary_addr);
+	if (!info) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -1;
+	}
+	map = page_address(info->page);
+	bit = get_ind_bit(info->addr, adapter_int->summary_offset,
+			  adapter->swap);
+	summary_set = test_and_set_bit(bit, map);
+	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+	set_page_dirty_lock(info->page);
+	srcu_read_unlock(&kvm->srcu, idx);
+	return summary_set ? 0 : 1;
+}
+
+/*
+ * < 0 - not injected due to error
+ * = 0 - coalesced, summary indicator already active
+ * > 0 - injected interrupt
+ */
+static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
+			   struct kvm *kvm, int irq_source_id, int level,
+			   bool line_status)
+{
+	int ret;
+	struct s390_io_adapter *adapter;
+
+	/* We're only interested in the 0->1 transition. */
+	if (!level)
+		return 0;
+	adapter = get_io_adapter(kvm, e->adapter.adapter_id);
+	if (!adapter)
+		return -1;
+	down_read(&adapter->maps_lock);
+	ret = adapter_indicators_set(kvm, adapter, &e->adapter);
+	up_read(&adapter->maps_lock);
+	if ((ret > 0) && !adapter->masked) {
+		struct kvm_s390_interrupt s390int = {
+			.type = KVM_S390_INT_IO(1, 0, 0, 0),
+			.parm = 0,
+			.parm64 = (adapter->isc << 27) | 0x80000000,
+		};
+		ret = kvm_s390_inject_vm(kvm, &s390int);
+		if (ret == 0)
+			ret = 1;
+	}
+	return ret;
+}
+
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+			  struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue)
+{
+	int ret;
+
+	switch (ue->type) {
+	case KVM_IRQ_ROUTING_S390_ADAPTER:
+		e->set = set_adapter_int;
+		e->adapter.summary_addr = ue->u.adapter.summary_addr;
+		e->adapter.ind_addr = ue->u.adapter.ind_addr;
+		e->adapter.summary_offset = ue->u.adapter.summary_offset;
+		e->adapter.ind_offset = ue->u.adapter.ind_offset;
+		e->adapter.adapter_id = ue->u.adapter.adapter_id;
+		ret = 0;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+		int irq_source_id, int level, bool line_status)
+{
+	return -EINVAL;
+}
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
new file mode 100644
index 000000000000..d98e4159643d
--- /dev/null
+++ b/arch/s390/kvm/irq.h
@@ -0,0 +1,22 @@
+/*
+ * s390 irqchip routines
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+#ifndef __KVM_IRQ_H
+#define __KVM_IRQ_H
+
+#include <linux/kvm_host.h>
+
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+	return 1;
+}
+
+#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2e6fbb0b4f68..ce5b659ec531 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -196,6 +196,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_S390_IRQCHIP:
+		kvm->arch.use_irqchip = 1;
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -228,6 +232,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
 		break;
 	}
+	case KVM_CREATE_IRQCHIP: {
+		struct kvm_irq_routing_entry routing;
+
+		r = -EINVAL;
+		if (kvm->arch.use_irqchip) {
+			/* Set up dummy routing. */
+			memset(&routing, 0, sizeof(routing));
+			kvm_set_irq_routing(kvm, &routing, 0, 0);
+			r = 0;
+		}
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -284,6 +300,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	}
 
 	kvm->arch.css_support = 0;
+	kvm->arch.use_irqchip = 0;
 
 	return 0;
 out_nogmap:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9816b68b085f..da7510b4c6ad 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -297,6 +297,14 @@ static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memsl
 	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 }
 
+struct kvm_s390_adapter_int {
+	u64 ind_addr;
+	u64 summary_addr;
+	u64 ind_offset;
+	u32 summary_offset;
+	u32 adapter_id;
+};
+
 struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
 	u32 type;
@@ -309,6 +317,7 @@ struct kvm_kernel_irq_routing_entry {
 			unsigned pin;
 		} irqchip;
 		struct msi_msg msi;
+		struct kvm_s390_adapter_int adapter;
 	};
 	struct hlist_node link;
 };
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 46ea1b470c76..a8f4ee5d2e82 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -742,6 +742,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_HYPERV_TIME 96
 #define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
 #define KVM_CAP_ENABLE_CAP_VM 98
+#define KVM_CAP_S390_IRQCHIP 99
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -757,9 +758,18 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+struct kvm_irq_routing_s390_adapter {
+	__u64 ind_addr;
+	__u64 summary_addr;
+	__u64 ind_offset;
+	__u32 summary_offset;
+	__u32 adapter_id;
+};
+
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
 
 struct kvm_irq_routing_entry {
 	__u32 gsi;
@@ -769,6 +779,7 @@ struct kvm_irq_routing_entry {
 	union {
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
+		struct kvm_irq_routing_s390_adapter adapter;
 		__u32 pad[8];
 	} u;
 };
-- 
cgit v1.2.3