Merge branch 'vfio-ccw-for-martin' of...

Merge branch 'vfio-ccw-for-martin' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/vfio-ccw into features

Pull vfio-ccw branch to add the basic channel I/O passthrough
intrastructure based on vfio.

The focus is on supporting dasd-eckd(cu_type/dev_type = 0x3990/0x3390)
as the target device.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

Documentation/s390/00-INDEX

@@ -22,5 +22,7 @@ qeth.txt
 	- HiperSockets Bridge Port Support.
 s390dbf.txt
 	- information on using the s390 debug feature.
+vfio-ccw.txt
+	  information on the vfio-ccw I/O subchannel driver.
 zfcpdump.txt
 	- information on the s390 SCSI dump tool.

MAINTAINERS

@@ -10860,6 +10860,16 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	drivers/iommu/s390-iommu.c
 
+S390 VFIO-CCW DRIVER
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+M:	Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+L:	linux-s390@vger.kernel.org
+L:	kvm@vger.kernel.org
+S:	Supported
+F:	drivers/s390/cio/vfio_ccw*
+F:	Documentation/s390/vfio-ccw.txt
+F:	include/uapi/linux/vfio_ccw.h
+
 S3C24XX SD/MMC Driver
 M:	Ben Dooks <ben-linux@fluff.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)

arch/s390/Kconfig

@@ -682,6 +682,16 @@ config EADM_SCH
 	  To compile this driver as a module, choose M here: the
 	  module will be called eadm_sch.
 
+config VFIO_CCW
+	def_tristate n
+	prompt "Support for VFIO-CCW subchannels"
+	depends on S390_CCW_IOMMU && VFIO_MDEV
+	help
+	  This driver allows usage of I/O subchannels via VFIO-CCW.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called vfio_ccw.
+
 endmenu
 
 menu "Dump support"

arch/s390/include/asm/cio.h

@@ -33,6 +33,24 @@ struct ccw1 {
 	__u32 cda;
 } __attribute__ ((packed,aligned(8)));
 
+/**
+ * struct ccw0 - channel command word
+ * @cmd_code: command code
+ * @cda: data address
+ * @flags: flags, like IDA addressing, etc.
+ * @reserved: will be ignored
+ * @count: byte count
+ *
+ * The format-0 ccw structure.
+ */
+struct ccw0 {
+	__u8 cmd_code;
+	__u32 cda : 24;
+	__u8  flags;
+	__u8  reserved;
+	__u16 count;
+} __packed __aligned(8);
+
 #define CCW_FLAG_DC		0x80
 #define CCW_FLAG_CC		0x40
 #define CCW_FLAG_SLI		0x20

arch/s390/include/asm/isc.h

@@ -16,6 +16,7 @@
 #define CONSOLE_ISC 1			/* console I/O subchannel */
 #define EADM_SCH_ISC 4			/* EADM subchannels */
 #define CHSC_SCH_ISC 7			/* CHSC subchannels */
+#define VFIO_CCW_ISC IO_SCH_ISC		/* VFIO-CCW I/O subchannels */
 /* Adapter interrupts. */
 #define QDIO_AIRQ_ISC IO_SCH_ISC	/* I/O subchannel in qdio mode */
 #define PCI_ISC 2			/* PCI I/O subchannels */

drivers/iommu/Kconfig

@@ -327,6 +327,14 @@ config S390_IOMMU
 	help
 	  Support for the IOMMU API for s390 PCI devices.
 
+config S390_CCW_IOMMU
+	bool "S390 CCW IOMMU Support"
+	depends on S390 && CCW
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 config MTK_IOMMU
 	bool "MTK IOMMU Support"
 	depends on ARM || ARM64

drivers/s390/cio/Makefile

@@ -17,3 +17,6 @@ obj-$(CONFIG_CCWGROUP) += ccwgroup.o
 
 qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
+
+vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o
+obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o

drivers/s390/cio/cio.c

@@ -170,12 +170,14 @@ cio_start_key (struct subchannel *sch,	/* subchannel structure */
 		return ccode;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_start_key);
 
 int
 cio_start (struct subchannel *sch, struct ccw1 *cpa, __u8 lpm)
 {
 	return cio_start_key(sch, cpa, lpm, PAGE_DEFAULT_KEY);
 }
+EXPORT_SYMBOL_GPL(cio_start);
 
 /*
  * resume suspended I/O operation
@@ -208,6 +210,7 @@ cio_resume (struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_resume);
 
 /*
  * halt I/O operation
@@ -241,6 +244,7 @@ cio_halt(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_halt);
 
 /*
  * Clear I/O operation
@@ -271,6 +275,7 @@ cio_clear(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_clear);
 
 /*
  * Function: cio_cancel
@@ -308,7 +313,68 @@ cio_cancel (struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_cancel);
 
+/**
+ * cio_cancel_halt_clear - Cancel running I/O by performing cancel, halt
+ * and clear ordinally if subchannel is valid.
+ * @sch: subchannel on which to perform the cancel_halt_clear operation
+ * @iretry: the number of the times remained to retry the next operation
+ *
+ * This should be called repeatedly since halt/clear are asynchronous
+ * operations. We do one try with cio_cancel, three tries with cio_halt,
+ * 255 tries with cio_clear. The caller should initialize @iretry with
+ * the value 255 for its first call to this, and keep using the same
+ * @iretry in the subsequent calls until it gets a non -EBUSY return.
+ *
+ * Returns 0 if device now idle, -ENODEV for device not operational,
+ * -EBUSY if an interrupt is expected (either from halt/clear or from a
+ * status pending), and -EIO if out of retries.
+ */
+int cio_cancel_halt_clear(struct subchannel *sch, int *iretry)
+{
+	int ret;
+
+	if (cio_update_schib(sch))
+		return -ENODEV;
+	if (!sch->schib.pmcw.ena)
+		/* Not operational -> done. */
+		return 0;
+	/* Stage 1: cancel io. */
+	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_HALT_PEND) &&
+	    !(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
+		if (!scsw_is_tm(&sch->schib.scsw)) {
+			ret = cio_cancel(sch);
+			if (ret != -EINVAL)
+				return ret;
+		}
+		/*
+		 * Cancel io unsuccessful or not applicable (transport mode).
+		 * Continue with asynchronous instructions.
+		 */
+		*iretry = 3;	/* 3 halt retries. */
+	}
+	/* Stage 2: halt io. */
+	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
+		if (*iretry) {
+			*iretry -= 1;
+			ret = cio_halt(sch);
+			if (ret != -EBUSY)
+				return (ret == 0) ? -EBUSY : ret;
+		}
+		/* Halt io unsuccessful. */
+		*iretry = 255;	/* 255 clear retries. */
+	}
+	/* Stage 3: clear io. */
+	if (*iretry) {
+		*iretry -= 1;
+		ret = cio_clear(sch);
+		return (ret == 0) ? -EBUSY : ret;
+	}
+	/* Function was unsuccessful */
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(cio_cancel_halt_clear);
 
 static void cio_apply_config(struct subchannel *sch, struct schib *schib)
 {
@@ -382,6 +448,7 @@ int cio_commit_config(struct subchannel *sch)
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cio_commit_config);
 
 /**
  * cio_update_schib - Perform stsch and update schib if subchannel is valid.
@@ -987,6 +1054,7 @@ int cio_tm_start_key(struct subchannel *sch, struct tcw *tcw, u8 lpm, u8 key)
 		return cio_start_handle_notoper(sch, lpm);
 	}
 }
+EXPORT_SYMBOL_GPL(cio_tm_start_key);
 
 /**
  * cio_tm_intrg - perform interrogate function
@@ -1012,3 +1080,4 @@ int cio_tm_intrg(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_tm_intrg);

drivers/s390/cio/cio.h

@@ -123,6 +123,7 @@ extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
 extern int cio_clear (struct subchannel *);
+extern int cio_cancel_halt_clear(struct subchannel *, int *);
 extern int cio_resume (struct subchannel *);
 extern int cio_halt (struct subchannel *);
 extern int cio_start (struct subchannel *, struct ccw1 *, __u8);

drivers/s390/cio/device_fsm.c

@@ -124,14 +124,6 @@ ccw_device_set_timeout(struct ccw_device *cdev, int expires)
 	add_timer(&cdev->private->timer);
 }
 
-/*
- * Cancel running i/o. This is called repeatedly since halt/clear are
- * asynchronous operations. We do one try with cio_cancel, two tries
- * with cio_halt, 255 tries with cio_clear. If everythings fails panic.
- * Returns 0 if device now idle, -ENODEV for device not operational and
- * -EBUSY if an interrupt is expected (either from halt/clear or from a
- * status pending).
- */
 int
 ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 {
@@ -139,44 +131,14 @@ ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 	int ret;
 
 	sch = to_subchannel(cdev->dev.parent);
-	if (cio_update_schib(sch))
-		return -ENODEV; 
-	if (!sch->schib.pmcw.ena)
-		/* Not operational -> done. */
-		return 0;
-	/* Stage 1: cancel io. */
-	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_HALT_PEND) &&
-	    !(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
-		if (!scsw_is_tm(&sch->schib.scsw)) {
-			ret = cio_cancel(sch);
-			if (ret != -EINVAL)
-				return ret;
-		}
-		/* cancel io unsuccessful or not applicable (transport mode).
-		 * Continue with asynchronous instructions. */
-		cdev->private->iretry = 3;	/* 3 halt retries. */
-	}
-	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
-		/* Stage 2: halt io. */
-		if (cdev->private->iretry) {
-			cdev->private->iretry--;
-			ret = cio_halt(sch);
-			if (ret != -EBUSY)
-				return (ret == 0) ? -EBUSY : ret;
-		}
-		/* halt io unsuccessful. */
-		cdev->private->iretry = 255;	/* 255 clear retries. */
-	}
-	/* Stage 3: clear io. */
-	if (cdev->private->iretry) {
-		cdev->private->iretry--;
-		ret = cio_clear (sch);
-		return (ret == 0) ? -EBUSY : ret;
-	}
-	/* Function was unsuccessful */
+	ret = cio_cancel_halt_clear(sch, &cdev->private->iretry);
+
+	if (ret == -EIO)
 		CIO_MSG_EVENT(0, "0.%x.%04x: could not stop I/O\n",
-		      cdev->private->dev_id.ssid, cdev->private->dev_id.devno);
-	return -EIO;
+			      cdev->private->dev_id.ssid,
+			      cdev->private->dev_id.devno);
+
+	return ret;
 }
 
 void ccw_device_update_sense_data(struct ccw_device *cdev)

drivers/s390/cio/vfio_ccw_cp.h

+/*
+ * channel program interfaces
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_CP_H_
+#define _VFIO_CCW_CP_H_
+
+#include <asm/cio.h>
+#include <asm/scsw.h>
+
+#include "orb.h"
+
+/**
+ * struct channel_program - manage information for channel program
+ * @ccwchain_list: list head of ccwchains
+ * @orb: orb for the currently processed ssch request
+ * @mdev: the mediated device to perform page pinning/unpinning
+ *
+ * @ccwchain_list is the head of a ccwchain list, that contents the
+ * translated result of the guest channel program that pointed out by
+ * the iova parameter when calling cp_init.
+ */
+struct channel_program {
+	struct list_head ccwchain_list;
+	union orb orb;
+	struct device *mdev;
+};
+
+extern int cp_init(struct channel_program *cp, struct device *mdev,
+		   union orb *orb);
+extern void cp_free(struct channel_program *cp);
+extern int cp_prefetch(struct channel_program *cp);
+extern union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);
+extern void cp_update_scsw(struct channel_program *cp, union scsw *scsw);
+extern bool cp_iova_pinned(struct channel_program *cp, u64 iova);
+
+#endif

drivers/s390/cio/vfio_ccw_drv.c

+/*
+ * VFIO based Physical Subchannel device driver
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/mdev.h>
+
+#include <asm/isc.h>
+
+#include "ioasm.h"
+#include "css.h"
+#include "vfio_ccw_private.h"
+
+struct workqueue_struct *vfio_ccw_work_q;
+
+/*
+ * Helpers
+ */
+int vfio_ccw_sch_quiesce(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	DECLARE_COMPLETION_ONSTACK(completion);
+	int iretry, ret = 0;
+
+	spin_lock_irq(sch->lock);
+	if (!sch->schib.pmcw.ena)
+		goto out_unlock;
+	ret = cio_disable_subchannel(sch);
+	if (ret != -EBUSY)
+		goto out_unlock;
+
+	do {
+		iretry = 255;
+
+		ret = cio_cancel_halt_clear(sch, &iretry);
+		while (ret == -EBUSY) {
+			/*
+			 * Flush all I/O and wait for
+			 * cancel/halt/clear completion.
+			 */
+			private->completion = &completion;
+			spin_unlock_irq(sch->lock);
+
+			wait_for_completion_timeout(&completion, 3*HZ);
+
+			spin_lock_irq(sch->lock);
+			private->completion = NULL;
+			flush_workqueue(vfio_ccw_work_q);
+			ret = cio_cancel_halt_clear(sch, &iretry);
+		};
+
+		ret = cio_disable_subchannel(sch);
+	} while (ret == -EBUSY);
+out_unlock:
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+	spin_unlock_irq(sch->lock);
+	return ret;
+}
+
+static void vfio_ccw_sch_io_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+	struct subchannel *sch;
+	struct irb *irb;
+
+	private = container_of(work, struct vfio_ccw_private, io_work);
+	irb = &private->irb;
+	sch = private->sch;
+
+	if (scsw_is_solicited(&irb->scsw)) {
+		cp_update_scsw(&private->cp, &irb->scsw);
+		cp_free(&private->cp);
+	}
+	memcpy(private->io_region.irb_area, irb, sizeof(*irb));
+
+	if (private->io_trigger)
+		eventfd_signal(private->io_trigger, 1);
+
+	if (private->mdev)
+		private->state = VFIO_CCW_STATE_IDLE;
+}
+
+/*
+ * Sysfs interfaces
+ */
+static ssize_t chpids_show(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	struct chsc_ssd_info *ssd = &sch->ssd_info;
+	ssize_t ret = 0;
+	int chp;
+	int mask;
+
+	for (chp = 0; chp < 8; chp++) {
+		mask = 0x80 >> chp;
+		if (ssd->path_mask & mask)
+			ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id);
+		else
+			ret += sprintf(buf + ret, "00 ");
+	}
+	ret += sprintf(buf+ret, "\n");
+	return ret;
+}
+
+static ssize_t pimpampom_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	struct pmcw *pmcw = &sch->schib.pmcw;
+
+	return sprintf(buf, "%02x %02x %02x\n",
+		       pmcw->pim, pmcw->pam, pmcw->pom);
+}
+
+static DEVICE_ATTR(chpids, 0444, chpids_show, NULL);
+static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL);
+
+static struct attribute *vfio_subchannel_attrs[] = {
+	&dev_attr_chpids.attr,
+	&dev_attr_pimpampom.attr,
+	NULL,
+};
+
+static struct attribute_group vfio_subchannel_attr_group = {
+	.attrs = vfio_subchannel_attrs,
+};
+
+/*
+ * Css driver callbacks
+ */
+static void vfio_ccw_sch_irq(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+
+	inc_irq_stat(IRQIO_CIO);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_INTERRUPT);
+}
+
+static int vfio_ccw_sch_probe(struct subchannel *sch)
+{
+	struct pmcw *pmcw = &sch->schib.pmcw;
+	struct vfio_ccw_private *private;
+	int ret;
+
+	if (pmcw->qf) {
+		dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
+			 dev_name(&sch->dev));
+		return -ENODEV;
+	}
+
+	private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
+	if (!private)
+		return -ENOMEM;
+	private->sch = sch;
+	dev_set_drvdata(&sch->dev, private);
+
+	spin_lock_irq(sch->lock);
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+	sch->isc = VFIO_CCW_ISC;
+	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
+	spin_unlock_irq(sch->lock);
+	if (ret)
+		goto out_free;
+
+	ret = sysfs_create_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+	if (ret)
+		goto out_disable;
+
+	ret = vfio_ccw_mdev_reg(sch);
+	if (ret)
+		goto out_rm_group;
+
+	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
+	atomic_set(&private->avail, 1);
+	private->state = VFIO_CCW_STATE_STANDBY;
+
+	return 0;
+
+out_rm_group:
+	sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+out_disable:
+	cio_disable_subchannel(sch);
+out_free:
+	dev_set_drvdata(&sch->dev, NULL);
+	kfree(private);
+	return ret;
+}
+
+static int vfio_ccw_sch_remove(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+
+	vfio_ccw_sch_quiesce(sch);
+
+	vfio_ccw_mdev_unreg(sch);
+
+	sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+
+	dev_set_drvdata(&sch->dev, NULL);
+
+	kfree(private);
+
+	return 0;
+}
+
+static void vfio_ccw_sch_shutdown(struct subchannel *sch)
+{
+	vfio_ccw_sch_quiesce(sch);
+}
+
+/**
+ * vfio_ccw_sch_event - process subchannel event
+ * @sch: subchannel
+ * @process: non-zero if function is called in process context
+ *
+ * An unspecified event occurred for this subchannel. Adjust data according
+ * to the current operational state of the subchannel. Return zero when the
+ * event has been handled sufficiently or -EAGAIN when this function should
+ * be called again in process context.
+ */
+static int vfio_ccw_sch_event(struct subchannel *sch, int process)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(sch->lock, flags);
+	if (!device_is_registered(&sch->dev))
+		goto out_unlock;
+
+	if (work_pending(&sch->todo_work))
+		goto out_unlock;
+
+	if (cio_update_schib(sch)) {
+		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+		goto out_unlock;
+	}
+
+	private = dev_get_drvdata(&sch->dev);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
+		private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
+				 VFIO_CCW_STATE_STANDBY;
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(sch->lock, flags);
+
+	return 0;
+}
+
+static struct css_device_id vfio_ccw_sch_ids[] = {
+	{ .match_flags = 0x1, .type = SUBCHANNEL_TYPE_IO, },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(css, vfio_ccw_sch_ids);
+
+static struct css_driver vfio_ccw_sch_driver = {
+	.drv = {
+		.name = "vfio_ccw",
+		.owner = THIS_MODULE,
+	},
+	.subchannel_type = vfio_ccw_sch_ids,
+	.irq = vfio_ccw_sch_irq,
+	.probe = vfio_ccw_sch_probe,
+	.remove = vfio_ccw_sch_remove,
+	.shutdown = vfio_ccw_sch_shutdown,
+	.sch_event = vfio_ccw_sch_event,
+};
+
+static int __init vfio_ccw_sch_init(void)
+{
+	int ret;
+
+	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
+	if (!vfio_ccw_work_q)
+		return -ENOMEM;
+
+	isc_register(VFIO_CCW_ISC);
+	ret = css_driver_register(&vfio_ccw_sch_driver);
+	if (ret) {
+		isc_unregister(VFIO_CCW_ISC);
+		destroy_workqueue(vfio_ccw_work_q);
+	}
+
+	return ret;
+}
+
+static void __exit vfio_ccw_sch_exit(void)
+{
+	css_driver_unregister(&vfio_ccw_sch_driver);
+	isc_unregister(VFIO_CCW_ISC);
+	destroy_workqueue(vfio_ccw_work_q);
+}
+module_init(vfio_ccw_sch_init);
+module_exit(vfio_ccw_sch_exit);
+
+MODULE_LICENSE("GPL v2");

drivers/s390/cio/vfio_ccw_fsm.c

+/*
+ * Finite state machine for vfio-ccw device handling
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "ioasm.h"
+#include "vfio_ccw_private.h"
+
+static int fsm_io_helper(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	union orb *orb;
+	int ccode;
+	__u8 lpm;
+	unsigned long flags;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+	private->state = VFIO_CCW_STATE_BUSY;
+	spin_unlock_irqrestore(sch->lock, flags);
+
+	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+
+	/* Issue "Start Subchannel" */
+	ccode = ssch(sch->schid, orb);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
+		return 0;
+	case 1:		/* Status pending */
+	case 2:		/* Busy */
+		return -EBUSY;
+	case 3:		/* Device/path not operational */
+	{
+		lpm = orb->cmd.lpm;
+		if (lpm != 0)
+			sch->lpm &= ~lpm;
+		else
+			sch->lpm = 0;
+
+		if (cio_update_schib(sch))
+			return -ENODEV;
+
+		return sch->lpm ? -EACCES : -ENODEV;
+	}
+	default:
+		return ccode;
+	}
+}
+
+static void fsm_notoper(struct vfio_ccw_private *private,
+			enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+
+	/*
+	 * TODO:
+	 * Probably we should send the machine check to the guest.
+	 */
+	css_sched_sch_todo(sch, SCH_TODO_UNREG);
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+}
+
+/*
+ * No operation action.
+ */
+static void fsm_nop(struct vfio_ccw_private *private,
+		    enum vfio_ccw_event event)
+{
+}
+
+static void fsm_io_error(struct vfio_ccw_private *private,
+			 enum vfio_ccw_event event)
+{
+	pr_err("vfio-ccw: FSM: I/O request from state:%d\n", private->state);
+	private->io_region.ret_code = -EIO;
+}
+
+static void fsm_io_busy(struct vfio_ccw_private *private,
+			enum vfio_ccw_event event)
+{
+	private->io_region.ret_code = -EBUSY;
+}
+
+static void fsm_disabled_irq(struct vfio_ccw_private *private,
+			     enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+
+	/*
+	 * An interrupt in a disabled state means a previous disable was not
+	 * successful - should not happen, but we try to disable again.
+	 */
+	cio_disable_subchannel(sch);
+}
+
+/*
+ * Deal with the ccw command request from the userspace.
+ */
+static void fsm_io_request(struct vfio_ccw_private *private,
+			   enum vfio_ccw_event event)
+{
+	union orb *orb;
+	union scsw *scsw = &private->scsw;
+	struct ccw_io_region *io_region = &private->io_region;
+	struct mdev_device *mdev = private->mdev;
+
+	private->state = VFIO_CCW_STATE_BOXED;
+
+	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
+
+	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
+		orb = (union orb *)io_region->orb_area;
+
+		io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
+					      orb);
+		if (io_region->ret_code)
+			goto err_out;
+
+		io_region->ret_code = cp_prefetch(&private->cp);
+		if (io_region->ret_code) {
+			cp_free(&private->cp);
+			goto err_out;
+		}
+
+		/* Start channel program and wait for I/O interrupt. */
+		io_region->ret_code = fsm_io_helper(private);
+		if (io_region->ret_code) {
+			cp_free(&private->cp);
+			goto err_out;
+		}
+		return;
+	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
+		/* XXX: Handle halt. */
+		io_region->ret_code = -EOPNOTSUPP;
+		goto err_out;
+	} else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) {
+		/* XXX: Handle clear. */
+		io_region->ret_code = -EOPNOTSUPP;
+		goto err_out;
+	}
+
+err_out:
+	private->state = VFIO_CCW_STATE_IDLE;
+}
+
+/*
+ * Got an interrupt for a normal io (state busy).
+ */
+static void fsm_irq(struct vfio_ccw_private *private,
+		    enum vfio_ccw_event event)
+{
+	struct irb *irb;
+
+	if (!private)
+		return;
+
+	irb = this_cpu_ptr(&cio_irb);
+	memcpy(&private->irb, irb, sizeof(*irb));
+
+	queue_work(vfio_ccw_work_q, &private->io_work);
+
+	if (private->completion)
+		complete(private->completion);
+}
+
+/*
+ * Device statemachine
+ */
+fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = {
+	[VFIO_CCW_STATE_NOT_OPER] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_nop,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_disabled_irq,
+	},
+	[VFIO_CCW_STATE_STANDBY] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_IDLE] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_request,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_BOXED] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_BUSY] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+};

drivers/s390/cio/vfio_ccw_ops.c

+/*
+ * Physical device callbacks for vfio_ccw
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "vfio_ccw_private.h"
+
+static int vfio_ccw_mdev_reset(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private;
+	struct subchannel *sch;
+	int ret;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!private)
+		return -ENODEV;
+
+	sch = private->sch;
+	/*
+	 * TODO:
+	 * In the cureent stage, some things like "no I/O running" and "no
+	 * interrupt pending" are clear, but we are not sure what other state
+	 * we need to care about.
+	 * There are still a lot more instructions need to be handled. We
+	 * should come back here later.
+	 */
+	ret = vfio_ccw_sch_quiesce(sch);
+	if (ret)
+		return ret;
+
+	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
+	if (!ret)
+		private->state = VFIO_CCW_STATE_IDLE;
+
+	return ret;
+}
+
+static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
+				  unsigned long action,
+				  void *data)
+{
+	struct vfio_ccw_private *private =
+		container_of(nb, struct vfio_ccw_private, nb);
+
+	if (!private)
+		return NOTIFY_STOP;
+
+	/*
+	 * Vendor drivers MUST unpin pages in response to an
+	 * invalidation.
+	 */
+	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
+		struct vfio_iommu_type1_dma_unmap *unmap = data;
+
+		if (!cp_iova_pinned(&private->cp, unmap->iova))
+			return NOTIFY_OK;
+
+		if (vfio_ccw_mdev_reset(private->mdev))
+			return NOTIFY_BAD;
+
+		cp_free(&private->cp);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static ssize_t name_show(struct kobject *kobj, struct device *dev, char *buf)
+{
+	return sprintf(buf, "I/O subchannel (Non-QDIO)\n");
+}
+MDEV_TYPE_ATTR_RO(name);
+
+static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
+			       char *buf)
+{
+	return sprintf(buf, "%s\n", VFIO_DEVICE_API_CCW_STRING);
+}
+MDEV_TYPE_ATTR_RO(device_api);
+
+static ssize_t available_instances_show(struct kobject *kobj,
+					struct device *dev, char *buf)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", atomic_read(&private->avail));
+}
+MDEV_TYPE_ATTR_RO(available_instances);
+
+static struct attribute *mdev_types_attrs[] = {
+	&mdev_type_attr_name.attr,
+	&mdev_type_attr_device_api.attr,
+	&mdev_type_attr_available_instances.attr,
+	NULL,
+};
+
+static struct attribute_group mdev_type_group = {
+	.name  = "io",
+	.attrs = mdev_types_attrs,
+};
+
+struct attribute_group *mdev_type_groups[] = {
+	&mdev_type_group,
+	NULL,
+};
+
+static int vfio_ccw_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -ENODEV;
+
+	if (atomic_dec_if_positive(&private->avail) < 0)
+		return -EPERM;
+
+	private->mdev = mdev;
+	private->state = VFIO_CCW_STATE_IDLE;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+	int ret;
+
+	if (!private)
+		goto out;
+
+	if ((private->state == VFIO_CCW_STATE_NOT_OPER) ||
+	    (private->state == VFIO_CCW_STATE_STANDBY))
+		goto out;
+
+	ret = vfio_ccw_mdev_reset(mdev);
+	if (ret)
+		return ret;
+
+	private->state = VFIO_CCW_STATE_STANDBY;
+
+out:
+	private->mdev = NULL;
+	atomic_inc(&private->avail);
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_open(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+
+	private->nb.notifier_call = vfio_ccw_mdev_notifier;
+
+	return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				      &events, &private->nb);
+}
+
+void vfio_ccw_mdev_release(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				 &private->nb);
+}
+
+static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
+				  char __user *buf,
+				  size_t count,
+				  loff_t *ppos)
+{
+	struct vfio_ccw_private *private;
+	struct ccw_io_region *region;
+
+	if (*ppos + count > sizeof(*region))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!private)
+		return -ENODEV;
+
+	region = &private->io_region;
+	if (copy_to_user(buf, (void *)region + *ppos, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
+				   const char __user *buf,
+				   size_t count,
+				   loff_t *ppos)
+{
+	struct vfio_ccw_private *private;
+	struct ccw_io_region *region;
+
+	if (*ppos + count > sizeof(*region))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!private)
+		return -ENODEV;
+	if (private->state != VFIO_CCW_STATE_IDLE)
+		return -EACCES;
+
+	region = &private->io_region;
+	if (copy_from_user((void *)region + *ppos, buf, count))
+		return -EFAULT;
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
+	if (region->ret_code != 0) {
+		private->state = VFIO_CCW_STATE_IDLE;
+		return region->ret_code;
+	}
+
+	return count;
+}
+
+static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info)
+{
+	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
+	info->num_regions = VFIO_CCW_NUM_REGIONS;
+	info->num_irqs = VFIO_CCW_NUM_IRQS;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
+					 u16 *cap_type_id,
+					 void **cap_type)
+{
+	switch (info->index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		info->offset = 0;
+		info->size = sizeof(struct ccw_io_region);
+		info->flags = VFIO_REGION_INFO_FLAG_READ
+			      | VFIO_REGION_INFO_FLAG_WRITE;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
+{
+	if (info->index != VFIO_CCW_IO_IRQ_INDEX)
+		return -EINVAL;
+
+	info->count = 1;
+	info->flags = VFIO_IRQ_INFO_EVENTFD;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
+				  uint32_t flags,
+				  void __user *data)
+{
+	struct vfio_ccw_private *private;
+	struct eventfd_ctx **ctx;
+
+	if (!(flags & VFIO_IRQ_SET_ACTION_TRIGGER))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!private)
+		return -ENODEV;
+
+	ctx = &private->io_trigger;
+
+	switch (flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
+	case VFIO_IRQ_SET_DATA_NONE:
+	{
+		if (*ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	}
+	case VFIO_IRQ_SET_DATA_BOOL:
+	{
+		uint8_t trigger;
+
+		if (get_user(trigger, (uint8_t __user *)data))
+			return -EFAULT;
+
+		if (trigger && *ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	}
+	case VFIO_IRQ_SET_DATA_EVENTFD:
+	{
+		int32_t fd;
+
+		if (get_user(fd, (int32_t __user *)data))
+			return -EFAULT;
+
+		if (fd == -1) {
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+			*ctx = NULL;
+		} else if (fd >= 0) {
+			struct eventfd_ctx *efdctx;
+
+			efdctx = eventfd_ctx_fdget(fd);
+			if (IS_ERR(efdctx))
+				return PTR_ERR(efdctx);
+
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+
+			*ctx = efdctx;
+		} else
+			return -EINVAL;
+
+		return 0;
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
+				   unsigned int cmd,
+				   unsigned long arg)
+{
+	int ret = 0;
+	unsigned long minsz;
+
+	switch (cmd) {
+	case VFIO_DEVICE_GET_INFO:
+	{
+		struct vfio_device_info info;
+
+		minsz = offsetofend(struct vfio_device_info, num_irqs);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_device_info(&info);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_GET_REGION_INFO:
+	{
+		struct vfio_region_info info;
+		u16 cap_type_id = 0;
+		void *cap_type = NULL;
+
+		minsz = offsetofend(struct vfio_region_info, offset);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id,
+						    &cap_type);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_GET_IRQ_INFO:
+	{
+		struct vfio_irq_info info;
+
+		minsz = offsetofend(struct vfio_irq_info, count);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz || info.index >= VFIO_CCW_NUM_IRQS)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_irq_info(&info);
+		if (ret)
+			return ret;
+
+		if (info.count == -1)
+			return -EINVAL;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_SET_IRQS:
+	{
+		struct vfio_irq_set hdr;
+		size_t data_size;
+		void __user *data;
+
+		minsz = offsetofend(struct vfio_irq_set, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		ret = vfio_set_irqs_validate_and_prepare(&hdr, 1,
+							 VFIO_CCW_NUM_IRQS,
+							 &data_size);
+		if (ret)
+			return ret;
+
+		data = (void __user *)(arg + minsz);
+		return vfio_ccw_mdev_set_irqs(mdev, hdr.flags, data);
+	}
+	case VFIO_DEVICE_RESET:
+		return vfio_ccw_mdev_reset(mdev);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
+	.owner			= THIS_MODULE,
+	.supported_type_groups  = mdev_type_groups,
+	.create			= vfio_ccw_mdev_create,
+	.remove			= vfio_ccw_mdev_remove,
+	.open			= vfio_ccw_mdev_open,
+	.release		= vfio_ccw_mdev_release,
+	.read			= vfio_ccw_mdev_read,
+	.write			= vfio_ccw_mdev_write,
+	.ioctl			= vfio_ccw_mdev_ioctl,
+};
+
+int vfio_ccw_mdev_reg(struct subchannel *sch)
+{
+	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_ops);
+}
+
+void vfio_ccw_mdev_unreg(struct subchannel *sch)
+{
+	mdev_unregister_device(&sch->dev);
+}

drivers/s390/cio/vfio_ccw_private.h

+/*
+ * Private stuff for vfio_ccw driver
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_PRIVATE_H_
+#define _VFIO_CCW_PRIVATE_H_
+
+#include <linux/completion.h>
+#include <linux/eventfd.h>
+#include <linux/workqueue.h>
+#include <linux/vfio_ccw.h>
+
+#include "css.h"
+#include "vfio_ccw_cp.h"
+
+/**
+ * struct vfio_ccw_private
+ * @sch: pointer to the subchannel
+ * @state: internal state of the device
+ * @completion: synchronization helper of the I/O completion
+ * @avail: available for creating a mediated device
+ * @mdev: pointer to the mediated device
+ * @nb: notifier for vfio events
+ * @io_region: MMIO region to input/output I/O arguments/results
+ * @cp: channel program for the current I/O operation
+ * @irb: irb info received from interrupt
+ * @scsw: scsw info
+ * @io_trigger: eventfd ctx for signaling userspace I/O results
+ * @io_work: work for deferral process of I/O handling
+ */
+struct vfio_ccw_private {
+	struct subchannel	*sch;
+	int			state;
+	struct completion	*completion;
+	atomic_t		avail;
+	struct mdev_device	*mdev;
+	struct notifier_block	nb;
+	struct ccw_io_region	io_region;
+
+	struct channel_program	cp;
+	struct irb		irb;
+	union scsw		scsw;
+
+	struct eventfd_ctx	*io_trigger;
+	struct work_struct	io_work;
+} __aligned(8);
+
+extern int vfio_ccw_mdev_reg(struct subchannel *sch);
+extern void vfio_ccw_mdev_unreg(struct subchannel *sch);
+
+extern int vfio_ccw_sch_quiesce(struct subchannel *sch);
+
+/*
+ * States of the device statemachine.
+ */
+enum vfio_ccw_state {
+	VFIO_CCW_STATE_NOT_OPER,
+	VFIO_CCW_STATE_STANDBY,
+	VFIO_CCW_STATE_IDLE,
+	VFIO_CCW_STATE_BOXED,
+	VFIO_CCW_STATE_BUSY,
+	/* last element! */
+	NR_VFIO_CCW_STATES
+};
+
+/*
+ * Asynchronous events of the device statemachine.
+ */
+enum vfio_ccw_event {
+	VFIO_CCW_EVENT_NOT_OPER,
+	VFIO_CCW_EVENT_IO_REQ,
+	VFIO_CCW_EVENT_INTERRUPT,
+	/* last element! */
+	NR_VFIO_CCW_EVENTS
+};
+
+/*
+ * Action called through jumptable.
+ */
+typedef void (fsm_func_t)(struct vfio_ccw_private *, enum vfio_ccw_event);
+extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
+
+static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
+				     int event)
+{
+	vfio_ccw_jumptable[private->state][event](private, event);
+}
+
+extern struct workqueue_struct *vfio_ccw_work_q;
+
+#endif

include/uapi/linux/vfio.h

@@ -198,6 +198,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_PCI	(1 << 1)	/* vfio-pci device */
 #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2)	/* vfio-platform device */
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)	/* vfio-amba device */
+#define VFIO_DEVICE_FLAGS_CCW	(1 << 4)	/* vfio-ccw device */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 };
@@ -212,6 +213,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_API_PCI_STRING		"vfio-pci"
 #define VFIO_DEVICE_API_PLATFORM_STRING		"vfio-platform"
 #define VFIO_DEVICE_API_AMBA_STRING		"vfio-amba"
+#define VFIO_DEVICE_API_CCW_STRING		"vfio-ccw"
 
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
@@ -446,6 +448,22 @@ enum {
 	VFIO_PCI_NUM_IRQS
 };
 
+/*
+ * The vfio-ccw bus driver makes use of the following fixed region and
+ * IRQ index mapping. Unimplemented regions return a size of zero.
+ * Unimplemented IRQ types return a count of zero.
+ */
+
+enum {
+	VFIO_CCW_CONFIG_REGION_INDEX,
+	VFIO_CCW_NUM_REGIONS
+};
+
+enum {
+	VFIO_CCW_IO_IRQ_INDEX,
+	VFIO_CCW_NUM_IRQS
+};
+
 /**
  * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12,
  *					      struct vfio_pci_hot_reset_info)

include/uapi/linux/vfio_ccw.h

+/*
+ * Interfaces for vfio-ccw
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_H_
+#define _VFIO_CCW_H_
+
+#include <linux/types.h>
+
+struct ccw_io_region {
+#define ORB_AREA_SIZE 12
+	__u8	orb_area[ORB_AREA_SIZE];
+#define SCSW_AREA_SIZE 12
+	__u8	scsw_area[SCSW_AREA_SIZE];
+#define IRB_AREA_SIZE 96
+	__u8	irb_area[IRB_AREA_SIZE];
+	__u32	ret_code;
+} __packed;
+
+#endif