Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost fixes from Michael Tsirkin:
 "Bugfixes and documentation fixes.

  Igor's patch that allows users to tweak memory table size is
  borderline, but it does fix known crashes, so I merged it"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost: add max_mem_regions module parameter
  vhost: extend memory regions allocation to vmalloc
  9p/trans_virtio: reset virtio device on remove
  virtio/s390: rename drivers/s390/kvm -> drivers/s390/virtio
  MAINTAINERS: separate section for s390 virtio drivers
  virtio: define virtio_pci_cfg_cap in header.
  virtio: Fix typecast of pointer in vring_init()
  virtio scsi: fix unused variable warning
  vhost: use binary search instead of linear in find_region()
  virtio_net: document VIRTIO_NET_CTRL_GUEST_OFFLOADS

3 files changed, 1906 insertions, 0 deletions

diff --git a/drivers/s390/virtio/Makefile b/drivers/s390/virtio/Makefile
new file mode 100644
index 000000000000..241891a57caf
--- /dev/null
+++ b/drivers/s390/virtio/Makefile
@@ -0,0 +1,9 @@
+# Makefile for kvm guest drivers on s390
+#
+# Copyright IBM Corp. 2008
+#
+# 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.
+
+obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o
diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c
new file mode 100644
index 000000000000..53fb975c404b
--- /dev/null
+++ b/drivers/s390/virtio/kvm_virtio.c
@@ -0,0 +1,510 @@
+/*
+ * virtio for kvm on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * 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): Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/slab.h>
+#include <linux/virtio_console.h>
+#include <linux/interrupt.h>
+#include <linux/virtio_ring.h>
+#include <linux/export.h>
+#include <linux/pfn.h>
+#include <asm/io.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm_virtio.h>
+#include <asm/sclp.h>
+#include <asm/setup.h>
+#include <asm/irq.h>
+
+#define VIRTIO_SUBCODE_64 0x0D00
+
+/*
+ * The pointer to our (page) of device descriptions.
+ */
+static void *kvm_devices;
+static struct work_struct hotplug_work;
+
+struct kvm_device {
+	struct virtio_device vdev;
+	struct kvm_device_desc *desc;
+};
+
+#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev)
+
+/*
+ * memory layout:
+ * - kvm_device_descriptor
+ *        struct kvm_device_desc
+ * - configuration
+ *        struct kvm_vqconfig
+ * - feature bits
+ * - config space
+ */
+static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc)
+{
+	return (struct kvm_vqconfig *)(desc + 1);
+}
+
+static u8 *kvm_vq_features(const struct kvm_device_desc *desc)
+{
+	return (u8 *)(kvm_vq_config(desc) + desc->num_vq);
+}
+
+static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc)
+{
+	return kvm_vq_features(desc) + desc->feature_len * 2;
+}
+
+/*
+ * The total size of the config page used by this device (incl. desc)
+ */
+static unsigned desc_size(const struct kvm_device_desc *desc)
+{
+	return sizeof(*desc)
+		+ desc->num_vq * sizeof(struct kvm_vqconfig)
+		+ desc->feature_len * 2
+		+ desc->config_len;
+}
+
+/* This gets the device's feature bits. */
+static u64 kvm_get_features(struct virtio_device *vdev)
+{
+	unsigned int i;
+	u32 features = 0;
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+	u8 *in_features = kvm_vq_features(desc);
+
+	for (i = 0; i < min(desc->feature_len * 8, 32); i++)
+		if (in_features[i / 8] & (1 << (i % 8)))
+			features |= (1 << i);
+	return features;
+}
+
+static int kvm_finalize_features(struct virtio_device *vdev)
+{
+	unsigned int i, bits;
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+	/* Second half of bitmap is features we accept. */
+	u8 *out_features = kvm_vq_features(desc) + desc->feature_len;
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	/* Make sure we don't have any features > 32 bits! */
+	BUG_ON((u32)vdev->features != vdev->features);
+
+	memset(out_features, 0, desc->feature_len);
+	bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
+	for (i = 0; i < bits; i++) {
+		if (__virtio_test_bit(vdev, i))
+			out_features[i / 8] |= (1 << (i % 8));
+	}
+
+	return 0;
+}
+
+/*
+ * Reading and writing elements in config space
+ */
+static void kvm_get(struct virtio_device *vdev, unsigned int offset,
+		   void *buf, unsigned len)
+{
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(buf, kvm_vq_configspace(desc) + offset, len);
+}
+
+static void kvm_set(struct virtio_device *vdev, unsigned int offset,
+		   const void *buf, unsigned len)
+{
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(kvm_vq_configspace(desc) + offset, buf, len);
+}
+
+/*
+ * The operations to get and set the status word just access
+ * the status field of the device descriptor. set_status will also
+ * make a hypercall to the host, to tell about status changes
+ */
+static u8 kvm_get_status(struct virtio_device *vdev)
+{
+	return to_kvmdev(vdev)->desc->status;
+}
+
+static void kvm_set_status(struct virtio_device *vdev, u8 status)
+{
+	BUG_ON(!status);
+	to_kvmdev(vdev)->desc->status = status;
+	kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS,
+		       (unsigned long) to_kvmdev(vdev)->desc);
+}
+
+/*
+ * To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the
+ * descriptor address. The Host will zero the status and all the
+ * features.
+ */
+static void kvm_reset(struct virtio_device *vdev)
+{
+	kvm_hypercall1(KVM_S390_VIRTIO_RESET,
+		       (unsigned long) to_kvmdev(vdev)->desc);
+}
+
+/*
+ * When the virtio_ring code wants to notify the Host, it calls us here and we
+ * make a hypercall.  We hand the address  of the virtqueue so the Host
+ * knows which virtqueue we're talking about.
+ */
+static bool kvm_notify(struct virtqueue *vq)
+{
+	long rc;
+	struct kvm_vqconfig *config = vq->priv;
+
+	rc = kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
+	if (rc < 0)
+		return false;
+	return true;
+}
+
+/*
+ * This routine finds the first virtqueue described in the configuration of
+ * this device and sets it up.
+ */
+static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
+				     unsigned index,
+				     void (*callback)(struct virtqueue *vq),
+				     const char *name)
+{
+	struct kvm_device *kdev = to_kvmdev(vdev);
+	struct kvm_vqconfig *config;
+	struct virtqueue *vq;
+	int err;
+
+	if (index >= kdev->desc->num_vq)
+		return ERR_PTR(-ENOENT);
+
+	if (!name)
+		return NULL;
+
+	config = kvm_vq_config(kdev->desc)+index;
+
+	err = vmem_add_mapping(config->address,
+			       vring_size(config->num,
+					  KVM_S390_VIRTIO_RING_ALIGN));
+	if (err)
+		goto out;
+
+	vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN,
+				 vdev, true, (void *) config->address,
+				 kvm_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto unmap;
+	}
+
+	/*
+	 * register a callback token
+	 * The host will sent this via the external interrupt parameter
+	 */
+	config->token = (u64) vq;
+
+	vq->priv = config;
+	return vq;
+unmap:
+	vmem_remove_mapping(config->address,
+			    vring_size(config->num,
+				       KVM_S390_VIRTIO_RING_ALIGN));
+out:
+	return ERR_PTR(err);
+}
+
+static void kvm_del_vq(struct virtqueue *vq)
+{
+	struct kvm_vqconfig *config = vq->priv;
+
+	vring_del_virtqueue(vq);
+	vmem_remove_mapping(config->address,
+			    vring_size(config->num,
+				       KVM_S390_VIRTIO_RING_ALIGN));
+}
+
+static void kvm_del_vqs(struct virtio_device *vdev)
+{
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		kvm_del_vq(vq);
+}
+
+static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			struct virtqueue *vqs[],
+			vq_callback_t *callbacks[],
+			const char *names[])
+{
+	struct kvm_device *kdev = to_kvmdev(vdev);
+	int i;
+
+	/* We must have this many virtqueues. */
+	if (nvqs > kdev->desc->num_vq)
+		return -ENOENT;
+
+	for (i = 0; i < nvqs; ++i) {
+		vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i]);
+		if (IS_ERR(vqs[i]))
+			goto error;
+	}
+	return 0;
+
+error:
+	kvm_del_vqs(vdev);
+	return PTR_ERR(vqs[i]);
+}
+
+static const char *kvm_bus_name(struct virtio_device *vdev)
+{
+	return "";
+}
+
+/*
+ * The config ops structure as defined by virtio config
+ */
+static const struct virtio_config_ops kvm_vq_configspace_ops = {
+	.get_features = kvm_get_features,
+	.finalize_features = kvm_finalize_features,
+	.get = kvm_get,
+	.set = kvm_set,
+	.get_status = kvm_get_status,
+	.set_status = kvm_set_status,
+	.reset = kvm_reset,
+	.find_vqs = kvm_find_vqs,
+	.del_vqs = kvm_del_vqs,
+	.bus_name = kvm_bus_name,
+};
+
+/*
+ * The root device for the kvm virtio devices.
+ * This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2.
+ */
+static struct device *kvm_root;
+
+/*
+ * adds a new device and register it with virtio
+ * appropriate drivers are loaded by the device model
+ */
+static void add_kvm_device(struct kvm_device_desc *d, unsigned int offset)
+{
+	struct kvm_device *kdev;
+
+	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
+	if (!kdev) {
+		printk(KERN_EMERG "Cannot allocate kvm dev %u type %u\n",
+		       offset, d->type);
+		return;
+	}
+
+	kdev->vdev.dev.parent = kvm_root;
+	kdev->vdev.id.device = d->type;
+	kdev->vdev.config = &kvm_vq_configspace_ops;
+	kdev->desc = d;
+
+	if (register_virtio_device(&kdev->vdev) != 0) {
+		printk(KERN_ERR "Failed to register kvm device %u type %u\n",
+		       offset, d->type);
+		kfree(kdev);
+	}
+}
+
+/*
+ * scan_devices() simply iterates through the device page.
+ * The type 0 is reserved to mean "end of devices".
+ */
+static void scan_devices(void)
+{
+	unsigned int i;
+	struct kvm_device_desc *d;
+
+	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
+		d = kvm_devices + i;
+
+		if (d->type == 0)
+			break;
+
+		add_kvm_device(d, i);
+	}
+}
+
+/*
+ * match for a kvm device with a specific desc pointer
+ */
+static int match_desc(struct device *dev, void *data)
+{
+	struct virtio_device *vdev = dev_to_virtio(dev);
+	struct kvm_device *kdev = to_kvmdev(vdev);
+
+	return kdev->desc == data;
+}
+
+/*
+ * hotplug_device tries to find changes in the device page.
+ */
+static void hotplug_devices(struct work_struct *dummy)
+{
+	unsigned int i;
+	struct kvm_device_desc *d;
+	struct device *dev;
+
+	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
+		d = kvm_devices + i;
+
+		/* end of list */
+		if (d->type == 0)
+			break;
+
+		/* device already exists */
+		dev = device_find_child(kvm_root, d, match_desc);
+		if (dev) {
+			/* XXX check for hotplug remove */
+			put_device(dev);
+			continue;
+		}
+
+		/* new device */
+		printk(KERN_INFO "Adding new virtio device %p\n", d);
+		add_kvm_device(d, i);
+	}
+}
+
+/*
+ * we emulate the request_irq behaviour on top of s390 extints
+ */
+static void kvm_extint_handler(struct ext_code ext_code,
+			       unsigned int param32, unsigned long param64)
+{
+	struct virtqueue *vq;
+	u32 param;
+
+	if ((ext_code.subcode & 0xff00) != VIRTIO_SUBCODE_64)
+		return;
+	inc_irq_stat(IRQEXT_VRT);
+
+	/* The LSB might be overloaded, we have to mask it */
+	vq = (struct virtqueue *)(param64 & ~1UL);
+
+	/* We use ext_params to decide what this interrupt means */
+	param = param32 & VIRTIO_PARAM_MASK;
+
+	switch (param) {
+	case VIRTIO_PARAM_CONFIG_CHANGED:
+		virtio_config_changed(vq->vdev);
+		break;
+	case VIRTIO_PARAM_DEV_ADD:
+		schedule_work(&hotplug_work);
+		break;
+	case VIRTIO_PARAM_VRING_INTERRUPT:
+	default:
+		vring_interrupt(0, vq);
+		break;
+	}
+}
+
+/*
+ * For s390-virtio, we expect a page above main storage containing
+ * the virtio configuration. Try to actually load from this area
+ * in order to figure out if the host provides this page.
+ */
+static int __init test_devices_support(unsigned long addr)
+{
+	int ret = -EIO;
+
+	asm volatile(
+		"0:	lura	0,%1\n"
+		"1:	xgr	%0,%0\n"
+		"2:\n"
+		EX_TABLE(0b,2b)
+		EX_TABLE(1b,2b)
+		: "+d" (ret)
+		: "a" (addr)
+		: "0", "cc");
+	return ret;
+}
+/*
+ * Init function for virtio
+ * devices are in a single page above top of "normal" + standby mem
+ */
+static int __init kvm_devices_init(void)
+{
+	int rc;
+	unsigned long total_memory_size = sclp.rzm * sclp.rnmax;
+
+	if (!MACHINE_IS_KVM)
+		return -ENODEV;
+
+	if (test_devices_support(total_memory_size) < 0)
+		return -ENODEV;
+
+	rc = vmem_add_mapping(total_memory_size, PAGE_SIZE);
+	if (rc)
+		return rc;
+
+	kvm_devices = (void *) total_memory_size;
+
+	kvm_root = root_device_register("kvm_s390");
+	if (IS_ERR(kvm_root)) {
+		rc = PTR_ERR(kvm_root);
+		printk(KERN_ERR "Could not register kvm_s390 root device");
+		vmem_remove_mapping(total_memory_size, PAGE_SIZE);
+		return rc;
+	}
+
+	INIT_WORK(&hotplug_work, hotplug_devices);
+
+	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
+	register_external_irq(EXT_IRQ_CP_SERVICE, kvm_extint_handler);
+
+	scan_devices();
+	return 0;
+}
+
+/* code for early console output with virtio_console */
+static __init int early_put_chars(u32 vtermno, const char *buf, int count)
+{
+	char scratch[17];
+	unsigned int len = count;
+
+	if (len > sizeof(scratch) - 1)
+		len = sizeof(scratch) - 1;
+	scratch[len] = '\0';
+	memcpy(scratch, buf, len);
+	kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, __pa(scratch));
+	return len;
+}
+
+static int __init s390_virtio_console_init(void)
+{
+	if (sclp.has_vt220 || sclp.has_linemode)
+		return -ENODEV;
+	return virtio_cons_early_init(early_put_chars);
+}
+console_initcall(s390_virtio_console_init);
+
+
+/*
+ * We do this after core stuff, but before the drivers.
+ */
+postcore_initcall(kvm_devices_init);
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
new file mode 100644
index 000000000000..f8d8fdb26b72
--- /dev/null
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -0,0 +1,1387 @@
+/*
+ * ccw based virtio transport
+ *
+ * Copyright IBM Corp. 2012, 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>
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio_ring.h>
+#include <linux/pfn.h>
+#include <linux/async.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/kvm_para.h>
+#include <linux/notifier.h>
+#include <asm/setup.h>
+#include <asm/irq.h>
+#include <asm/cio.h>
+#include <asm/ccwdev.h>
+#include <asm/virtio-ccw.h>
+#include <asm/isc.h>
+#include <asm/airq.h>
+
+/*
+ * virtio related functions
+ */
+
+struct vq_config_block {
+	__u16 index;
+	__u16 num;
+} __packed;
+
+#define VIRTIO_CCW_CONFIG_SIZE 0x100
+/* same as PCI config space size, should be enough for all drivers */
+
+struct virtio_ccw_device {
+	struct virtio_device vdev;
+	__u8 *status;
+	__u8 config[VIRTIO_CCW_CONFIG_SIZE];
+	struct ccw_device *cdev;
+	__u32 curr_io;
+	int err;
+	unsigned int revision; /* Transport revision */
+	wait_queue_head_t wait_q;
+	spinlock_t lock;
+	struct list_head virtqueues;
+	unsigned long indicators;
+	unsigned long indicators2;
+	struct vq_config_block *config_block;
+	bool is_thinint;
+	bool going_away;
+	bool device_lost;
+	unsigned int config_ready;
+	void *airq_info;
+};
+
+struct vq_info_block_legacy {
+	__u64 queue;
+	__u32 align;
+	__u16 index;
+	__u16 num;
+} __packed;
+
+struct vq_info_block {
+	__u64 desc;
+	__u32 res0;
+	__u16 index;
+	__u16 num;
+	__u64 avail;
+	__u64 used;
+} __packed;
+
+struct virtio_feature_desc {
+	__u32 features;
+	__u8 index;
+} __packed;
+
+struct virtio_thinint_area {
+	unsigned long summary_indicator;
+	unsigned long indicator;
+	u64 bit_nr;
+	u8 isc;
+} __packed;
+
+struct virtio_rev_info {
+	__u16 revision;
+	__u16 length;
+	__u8 data[];
+};
+
+/* the highest virtio-ccw revision we support */
+#define VIRTIO_CCW_REV_MAX 1
+
+struct virtio_ccw_vq_info {
+	struct virtqueue *vq;
+	int num;
+	void *queue;
+	union {
+		struct vq_info_block s;
+		struct vq_info_block_legacy l;
+	} *info_block;
+	int bit_nr;
+	struct list_head node;
+	long cookie;
+};
+
+#define VIRTIO_AIRQ_ISC IO_SCH_ISC /* inherit from subchannel */
+
+#define VIRTIO_IV_BITS (L1_CACHE_BYTES * 8)
+#define MAX_AIRQ_AREAS 20
+
+static int virtio_ccw_use_airq = 1;
+
+struct airq_info {
+	rwlock_t lock;
+	u8 summary_indicator;
+	struct airq_struct airq;
+	struct airq_iv *aiv;
+};
+static struct airq_info *airq_areas[MAX_AIRQ_AREAS];
+
+#define CCW_CMD_SET_VQ 0x13
+#define CCW_CMD_VDEV_RESET 0x33
+#define CCW_CMD_SET_IND 0x43
+#define CCW_CMD_SET_CONF_IND 0x53
+#define CCW_CMD_READ_FEAT 0x12
+#define CCW_CMD_WRITE_FEAT 0x11
+#define CCW_CMD_READ_CONF 0x22
+#define CCW_CMD_WRITE_CONF 0x21
+#define CCW_CMD_WRITE_STATUS 0x31
+#define CCW_CMD_READ_VQ_CONF 0x32
+#define CCW_CMD_SET_IND_ADAPTER 0x73
+#define CCW_CMD_SET_VIRTIO_REV 0x83
+
+#define VIRTIO_CCW_DOING_SET_VQ 0x00010000
+#define VIRTIO_CCW_DOING_RESET 0x00040000
+#define VIRTIO_CCW_DOING_READ_FEAT 0x00080000
+#define VIRTIO_CCW_DOING_WRITE_FEAT 0x00100000
+#define VIRTIO_CCW_DOING_READ_CONFIG 0x00200000
+#define VIRTIO_CCW_DOING_WRITE_CONFIG 0x00400000
+#define VIRTIO_CCW_DOING_WRITE_STATUS 0x00800000
+#define VIRTIO_CCW_DOING_SET_IND 0x01000000
+#define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000
+#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000
+#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000
+#define VIRTIO_CCW_DOING_SET_VIRTIO_REV 0x10000000
+#define VIRTIO_CCW_INTPARM_MASK 0xffff0000
+
+static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
+{
+	return container_of(vdev, struct virtio_ccw_device, vdev);
+}
+
+static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info)
+{
+	unsigned long i, flags;
+
+	write_lock_irqsave(&info->lock, flags);
+	for (i = 0; i < airq_iv_end(info->aiv); i++) {
+		if (vq == (void *)airq_iv_get_ptr(info->aiv, i)) {
+			airq_iv_free_bit(info->aiv, i);
+			airq_iv_set_ptr(info->aiv, i, 0);
+			break;
+		}
+	}
+	write_unlock_irqrestore(&info->lock, flags);
+}
+
+static void virtio_airq_handler(struct airq_struct *airq)
+{
+	struct airq_info *info = container_of(airq, struct airq_info, airq);
+	unsigned long ai;
+
+	inc_irq_stat(IRQIO_VAI);
+	read_lock(&info->lock);
+	/* Walk through indicators field, summary indicator active. */
+	for (ai = 0;;) {
+		ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv));
+		if (ai == -1UL)
+			break;
+		vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai));
+	}
+	info->summary_indicator = 0;
+	smp_wmb();
+	/* Walk through indicators field, summary indicator not active. */
+	for (ai = 0;;) {
+		ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv));
+		if (ai == -1UL)
+			break;
+		vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai));
+	}
+	read_unlock(&info->lock);
+}
+
+static struct airq_info *new_airq_info(void)
+{
+	struct airq_info *info;
+	int rc;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return NULL;
+	rwlock_init(&info->lock);
+	info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR);
+	if (!info->aiv) {
+		kfree(info);
+		return NULL;
+	}
+	info->airq.handler = virtio_airq_handler;
+	info->airq.lsi_ptr = &info->summary_indicator;
+	info->airq.lsi_mask = 0xff;
+	info->airq.isc = VIRTIO_AIRQ_ISC;
+	rc = register_adapter_interrupt(&info->airq);
+	if (rc) {
+		airq_iv_release(info->aiv);
+		kfree(info);
+		return NULL;
+	}
+	return info;
+}
+
+static void destroy_airq_info(struct airq_info *info)
+{
+	if (!info)
+		return;
+
+	unregister_adapter_interrupt(&info->airq);
+	airq_iv_release(info->aiv);
+	kfree(info);
+}
+
+static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs,
+					u64 *first, void **airq_info)
+{
+	int i, j;
+	struct airq_info *info;
+	unsigned long indicator_addr = 0;
+	unsigned long bit, flags;
+
+	for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
+		if (!airq_areas[i])
+			airq_areas[i] = new_airq_info();
+		info = airq_areas[i];
+		if (!info)
+			return 0;
+		write_lock_irqsave(&info->lock, flags);
+		bit = airq_iv_alloc(info->aiv, nvqs);
+		if (bit == -1UL) {
+			/* Not enough vacancies. */
+			write_unlock_irqrestore(&info->lock, flags);
+			continue;
+		}
+		*first = bit;
+		*airq_info = info;
+		indicator_addr = (unsigned long)info->aiv->vector;
+		for (j = 0; j < nvqs; j++) {
+			airq_iv_set_ptr(info->aiv, bit + j,
+					(unsigned long)vqs[j]);
+		}
+		write_unlock_irqrestore(&info->lock, flags);
+	}
+	return indicator_addr;
+}
+
+static void virtio_ccw_drop_indicators(struct virtio_ccw_device *vcdev)
+{
+	struct virtio_ccw_vq_info *info;
+
+	list_for_each_entry(info, &vcdev->virtqueues, node)
+		drop_airq_indicator(info->vq, vcdev->airq_info);
+}
+
+static int doing_io(struct virtio_ccw_device *vcdev, __u32 flag)
+{
+	unsigned long flags;
+	__u32 ret;
+
+	spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags);
+	if (vcdev->err)
+		ret = 0;
+	else
+		ret = vcdev->curr_io & flag;
+	spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags);
+	return ret;
+}
+
+static int ccw_io_helper(struct virtio_ccw_device *vcdev,
+			 struct ccw1 *ccw, __u32 intparm)
+{
+	int ret;
+	unsigned long flags;
+	int flag = intparm & VIRTIO_CCW_INTPARM_MASK;
+
+	do {
+		spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags);
+		ret = ccw_device_start(vcdev->cdev, ccw, intparm, 0, 0);
+		if (!ret) {
+			if (!vcdev->curr_io)
+				vcdev->err = 0;
+			vcdev->curr_io |= flag;
+		}
+		spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags);
+		cpu_relax();
+	} while (ret == -EBUSY);
+	wait_event(vcdev->wait_q, doing_io(vcdev, flag) == 0);
+	return ret ? ret : vcdev->err;
+}
+
+static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev,
+				      struct ccw1 *ccw)
+{
+	int ret;
+	unsigned long *indicatorp = NULL;
+	struct virtio_thinint_area *thinint_area = NULL;
+	struct airq_info *airq_info = vcdev->airq_info;
+
+	if (vcdev->is_thinint) {
+		thinint_area = kzalloc(sizeof(*thinint_area),
+				       GFP_DMA | GFP_KERNEL);
+		if (!thinint_area)
+			return;
+		thinint_area->summary_indicator =
+			(unsigned long) &airq_info->summary_indicator;
+		thinint_area->isc = VIRTIO_AIRQ_ISC;
+		ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER;
+		ccw->count = sizeof(*thinint_area);
+		ccw->cda = (__u32)(unsigned long) thinint_area;
+	} else {
+		indicatorp = kmalloc(sizeof(&vcdev->indicators),
+				     GFP_DMA | GFP_KERNEL);
+		if (!indicatorp)
+			return;
+		*indicatorp = 0;
+		ccw->cmd_code = CCW_CMD_SET_IND;
+		ccw->count = sizeof(vcdev->indicators);
+		ccw->cda = (__u32)(unsigned long) indicatorp;
+	}
+	/* Deregister indicators from host. */
+	vcdev->indicators = 0;
+	ccw->flags = 0;
+	ret = ccw_io_helper(vcdev, ccw,
+			    vcdev->is_thinint ?
+			    VIRTIO_CCW_DOING_SET_IND_ADAPTER :
+			    VIRTIO_CCW_DOING_SET_IND);
+	if (ret && (ret != -ENODEV))
+		dev_info(&vcdev->cdev->dev,
+			 "Failed to deregister indicators (%d)\n", ret);
+	else if (vcdev->is_thinint)
+		virtio_ccw_drop_indicators(vcdev);
+	kfree(indicatorp);
+	kfree(thinint_area);
+}
+
+static inline long do_kvm_notify(struct subchannel_id schid,
+				 unsigned long queue_index,
+				 long cookie)
+{
+	register unsigned long __nr asm("1") = KVM_S390_VIRTIO_CCW_NOTIFY;
+	register struct subchannel_id __schid asm("2") = schid;
+	register unsigned long __index asm("3") = queue_index;
+	register long __rc asm("2");
+	register long __cookie asm("4") = cookie;
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "d" (__schid), "d" (__index),
+		      "d"(__cookie)
+		      : "memory", "cc");
+	return __rc;
+}
+
+static bool virtio_ccw_kvm_notify(struct virtqueue *vq)
+{
+	struct virtio_ccw_vq_info *info = vq->priv;
+	struct virtio_ccw_device *vcdev;
+	struct subchannel_id schid;
+
+	vcdev = to_vc_device(info->vq->vdev);
+	ccw_device_get_schid(vcdev->cdev, &schid);
+	info->cookie = do_kvm_notify(schid, vq->index, info->cookie);
+	if (info->cookie < 0)
+		return false;
+	return true;
+}
+
+static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev,
+				   struct ccw1 *ccw, int index)
+{
+	vcdev->config_block->index = index;
+	ccw->cmd_code = CCW_CMD_READ_VQ_CONF;
+	ccw->flags = 0;
+	ccw->count = sizeof(struct vq_config_block);
+	ccw->cda = (__u32)(unsigned long)(vcdev->config_block);
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF);
+	return vcdev->config_block->num;
+}
+
+static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vq->vdev);
+	struct virtio_ccw_vq_info *info = vq->priv;
+	unsigned long flags;
+	unsigned long size;
+	int ret;
+	unsigned int index = vq->index;
+
+	/* Remove from our list. */
+	spin_lock_irqsave(&vcdev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vcdev->lock, flags);
+
+	/* Release from host. */
+	if (vcdev->revision == 0) {
+		info->info_block->l.queue = 0;
+		info->info_block->l.align = 0;
+		info->info_block->l.index = index;
+		info->info_block->l.num = 0;
+		ccw->count = sizeof(info->info_block->l);
+	} else {
+		info->info_block->s.desc = 0;
+		info->info_block->s.index = index;
+		info->info_block->s.num = 0;
+		info->info_block->s.avail = 0;
+		info->info_block->s.used = 0;
+		ccw->count = sizeof(info->info_block->s);
+	}
+	ccw->cmd_code = CCW_CMD_SET_VQ;
+	ccw->flags = 0;
+	ccw->cda = (__u32)(unsigned long)(info->info_block);
+	ret = ccw_io_helper(vcdev, ccw,
+			    VIRTIO_CCW_DOING_SET_VQ | index);
+	/*
+	 * -ENODEV isn't considered an error: The device is gone anyway.
+	 * This may happen on device detach.
+	 */
+	if (ret && (ret != -ENODEV))
+		dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d",
+			 ret, index);
+
+	vring_del_virtqueue(vq);
+	size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info->info_block);
+	kfree(info);
+}
+
+static void virtio_ccw_del_vqs(struct virtio_device *vdev)
+{
+	struct virtqueue *vq, *n;
+	struct ccw1 *ccw;
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	virtio_ccw_drop_indicator(vcdev, ccw);
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		virtio_ccw_del_vq(vq, ccw);
+
+	kfree(ccw);
+}
+
+static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
+					     int i, vq_callback_t *callback,
+					     const char *name,
+					     struct ccw1 *ccw)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	int err;
+	struct virtqueue *vq = NULL;
+	struct virtio_ccw_vq_info *info;
+	unsigned long size = 0; /* silence the compiler */
+	unsigned long flags;
+
+	/* Allocate queue. */
+	info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL);
+	if (!info) {
+		dev_warn(&vcdev->cdev->dev, "no info\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+	info->info_block = kzalloc(sizeof(*info->info_block),
+				   GFP_DMA | GFP_KERNEL);
+	if (!info->info_block) {
+		dev_warn(&vcdev->cdev->dev, "no info block\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+	info->num = virtio_ccw_read_vq_conf(vcdev, ccw, i);
+	size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN));
+	info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+	if (info->queue == NULL) {
+		dev_warn(&vcdev->cdev->dev, "no queue\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev,
+				 true, info->queue, virtio_ccw_kvm_notify,
+				 callback, name);
+	if (!vq) {
+		/* For now, we fail if we can't get the requested size. */
+		dev_warn(&vcdev->cdev->dev, "no vq\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	/* Register it with the host. */
+	if (vcdev->revision == 0) {
+		info->info_block->l.queue = (__u64)info->queue;
+		info->info_block->l.align = KVM_VIRTIO_CCW_RING_ALIGN;
+		info->info_block->l.index = i;
+		info->info_block->l.num = info->num;
+		ccw->count = sizeof(info->info_block->l);
+	} else {
+		info->info_block->s.desc = (__u64)info->queue;
+		info->info_block->s.index = i;
+		info->info_block->s.num = info->num;
+		info->info_block->s.avail = (__u64)virtqueue_get_avail(vq);
+		info->info_block->s.used = (__u64)virtqueue_get_used(vq);
+		ccw->count = sizeof(info->info_block->s);
+	}
+	ccw->cmd_code = CCW_CMD_SET_VQ;
+	ccw->flags = 0;
+	ccw->cda = (__u32)(unsigned long)(info->info_block);
+	err = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_VQ | i);
+	if (err) {
+		dev_warn(&vcdev->cdev->dev, "SET_VQ failed\n");
+		goto out_err;
+	}
+
+	info->vq = vq;
+	vq->priv = info;
+
+	/* Save it to our list. */
+	spin_lock_irqsave(&vcdev->lock, flags);
+	list_add(&info->node, &vcdev->virtqueues);
+	spin_unlock_irqrestore(&vcdev->lock, flags);
+
+	return vq;
+
+out_err:
+	if (vq)
+		vring_del_virtqueue(vq);
+	if (info) {
+		if (info->queue)
+			free_pages_exact(info->queue, size);
+		kfree(info->info_block);
+	}
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev,
+					   struct virtqueue *vqs[], int nvqs,
+					   struct ccw1 *ccw)
+{