Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:

 - three merges for KVM/s390 with changes for vfio-ccw and cpacf. The
   patches are included in the KVM tree as well, let git sort it out.

 - add the new 'trng' random number generator

 - provide the secure key verification API for the pkey interface

 - introduce the z13 cpu counters to perf

 - add a new system call to set up the guarded storage facility

 - simplify TASK_SIZE and arch_get_unmapped_area

 - export the raw STSI data related to CPU topology to user space

 - ... and the usual churn of bug-fixes and cleanups.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (74 commits)
  s390/crypt: use the correct module alias for paes_s390.
  s390/cpacf: Introduce kma instruction
  s390/cpacf: query instructions use unique parameters for compatibility with KMA
  s390/trng: Introduce s390 TRNG device driver.
  s390/crypto: Provide s390 specific arch random functionality.
  s390/crypto: Add new subfunctions to the cpacf PRNO function.
  s390/crypto: Renaming PPNO to PRNO.
  s390/pageattr: avoid unnecessary page table splitting
  s390/mm: simplify arch_get_unmapped_area[_topdown]
  s390/mm: make TASK_SIZE independent from the number of page table levels
  s390/gs: add regset for the guarded storage broadcast control block
  s390/kvm: Add use_cmma field to mm_context_t
  s390/kvm: Add PGSTE manipulation functions
  vfio: ccw: improve error handling for vfio_ccw_mdev_remove
  vfio: ccw: remove unnecessary NULL checks of a pointer
  s390/spinlock: remove compare and delay instruction
  s390/spinlock: use atomic primitives for spinlocks
  s390/cpumf: simplify detection of guest samples
  s390/pci: remove forward declaration
  s390/pci: increase the PCI_NR_FUNCTIONS default
  ...

18 files changed, 2368 insertions, 53 deletions

diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 0cafe08919c9..b9918fb9587d 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -423,6 +423,20 @@ config HW_RANDOM_CAVIUM
 
          If unsure, say Y.
 
+config HW_RANDOM_S390
+	tristate "S390 True Random Number Generator support"
+	depends on S390
+	default HW_RANDOM
+	---help---
+	  This driver provides kernel-side support for the True
+	  Random Number Generator available as CPACF extension
+	  on modern s390 hardware platforms.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called s390-trng.
+
+	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 5f52b1e4e7be..dd1765246255 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -36,3 +36,4 @@ obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
 obj-$(CONFIG_HW_RANDOM_PIC32) += pic32-rng.o
 obj-$(CONFIG_HW_RANDOM_MESON) += meson-rng.o
 obj-$(CONFIG_HW_RANDOM_CAVIUM) += cavium-rng.o cavium-rng-vf.o
+obj-$(CONFIG_HW_RANDOM_S390) += s390-trng.o
diff --git a/drivers/char/hw_random/s390-trng.c b/drivers/char/hw_random/s390-trng.c
new file mode 100644
index 000000000000..aca48e893fca
--- /dev/null
+++ b/drivers/char/hw_random/s390-trng.c
@@ -0,0 +1,268 @@
+/*
+ * s390 TRNG device driver
+ *
+ * Driver for the TRNG (true random number generation) command
+ * available via CPACF extension MSA 7 on the s390 arch.
+
+ * Copyright IBM Corp. 2017
+ * Author(s): Harald Freudenberger <freude@de.ibm.com>
+ *
+ * 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.
+ *
+ */
+
+#define KMSG_COMPONENT "trng"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/hw_random.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/miscdevice.h>
+#include <linux/debugfs.h>
+#include <linux/atomic.h>
+#include <linux/random.h>
+#include <linux/sched/signal.h>
+#include <asm/debug.h>
+#include <asm/cpacf.h>
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("s390 CPACF TRNG device driver");
+
+
+/* trng related debug feature things */
+
+static debug_info_t *debug_info;
+
+#define DEBUG_DBG(...)	debug_sprintf_event(debug_info, 6, ##__VA_ARGS__)
+#define DEBUG_INFO(...) debug_sprintf_event(debug_info, 5, ##__VA_ARGS__)
+#define DEBUG_WARN(...) debug_sprintf_event(debug_info, 4, ##__VA_ARGS__)
+#define DEBUG_ERR(...)	debug_sprintf_event(debug_info, 3, ##__VA_ARGS__)
+
+
+/* trng helpers */
+
+static atomic64_t trng_dev_counter = ATOMIC64_INIT(0);
+static atomic64_t trng_hwrng_counter = ATOMIC64_INIT(0);
+
+
+/* file io functions */
+
+static int trng_open(struct inode *inode, struct file *file)
+{
+	return nonseekable_open(inode, file);
+}
+
+static ssize_t trng_read(struct file *file, char __user *ubuf,
+			 size_t nbytes, loff_t *ppos)
+{
+	u8 buf[32];
+	u8 *p = buf;
+	unsigned int n;
+	ssize_t ret = 0;
+
+	/*
+	 * use buf for requests <= sizeof(buf),
+	 * otherwise allocate one page and fetch
+	 * pagewise.
+	 */
+
+	if (nbytes > sizeof(buf)) {
+		p = (u8 *) __get_free_page(GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+	}
+
+	while (nbytes) {
+		if (need_resched()) {
+			if (signal_pending(current)) {
+				if (ret == 0)
+					ret = -ERESTARTSYS;
+				break;
+			}
+			schedule();
+		}
+		n = nbytes > PAGE_SIZE ? PAGE_SIZE : nbytes;
+		cpacf_trng(NULL, 0, p, n);
+		atomic64_add(n, &trng_dev_counter);
+		if (copy_to_user(ubuf, p, n)) {
+			ret = -EFAULT;
+			break;
+		}
+		nbytes -= n;
+		ubuf += n;
+		ret += n;
+	}
+
+	if (p != buf)
+		free_page((unsigned long) p);
+
+	DEBUG_DBG("trng_read()=%zd\n", ret);
+	return ret;
+}
+
+
+/* sysfs */
+
+static ssize_t trng_counter_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	u64 dev_counter = atomic64_read(&trng_dev_counter);
+	u64 hwrng_counter = atomic64_read(&trng_hwrng_counter);
+#if IS_ENABLED(CONFIG_ARCH_RANDOM)
+	u64 arch_counter = atomic64_read(&s390_arch_random_counter);
+
+	return snprintf(buf, PAGE_SIZE,
+			"trng:  %llu\n"
+			"hwrng: %llu\n"
+			"arch:  %llu\n"
+			"total: %llu\n",
+			dev_counter, hwrng_counter, arch_counter,
+			dev_counter + hwrng_counter + arch_counter);
+#else
+	return snprintf(buf, PAGE_SIZE,
+			"trng:  %llu\n"
+			"hwrng: %llu\n"
+			"total: %llu\n",
+			dev_counter, hwrng_counter,
+			dev_counter + hwrng_counter);
+#endif
+}
+static DEVICE_ATTR(byte_counter, 0444, trng_counter_show, NULL);
+
+static struct attribute *trng_dev_attrs[] = {
+	&dev_attr_byte_counter.attr,
+	NULL
+};
+
+static const struct attribute_group trng_dev_attr_group = {
+	.attrs = trng_dev_attrs
+};
+
+static const struct attribute_group *trng_dev_attr_groups[] = {
+	&trng_dev_attr_group,
+	NULL
+};
+
+static const struct file_operations trng_fops = {
+	.owner		= THIS_MODULE,
+	.open		= &trng_open,
+	.release	= NULL,
+	.read		= &trng_read,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice trng_dev = {
+	.name	= "trng",
+	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0444,
+	.fops	= &trng_fops,
+	.groups = trng_dev_attr_groups,
+};
+
+
+/* hwrng_register */
+
+static inline void _trng_hwrng_read(u8 *buf, size_t len)
+{
+	cpacf_trng(NULL, 0, buf, len);
+	atomic64_add(len, &trng_hwrng_counter);
+}
+
+static int trng_hwrng_data_read(struct hwrng *rng, u32 *data)
+{
+	size_t len = sizeof(*data);
+
+	_trng_hwrng_read((u8 *) data, len);
+
+	DEBUG_DBG("trng_hwrng_data_read()=%zu\n", len);
+
+	return len;
+}
+
+static int trng_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	size_t len = max <= PAGE_SIZE ? max : PAGE_SIZE;
+
+	_trng_hwrng_read((u8 *) data, len);
+
+	DEBUG_DBG("trng_hwrng_read()=%zu\n", len);
+
+	return len;
+}
+
+/*
+ * hwrng register struct
+ * The trng is suppost to have 100% entropy, and thus
+ * we register with a very high quality value.
+ */
+static struct hwrng trng_hwrng_dev = {
+	.name		= "s390-trng",
+	.data_read	= trng_hwrng_data_read,
+	.read		= trng_hwrng_read,
+	.quality	= 999,
+};
+
+
+/* init and exit */
+
+static void __init trng_debug_init(void)
+{
+	debug_info = debug_register("trng", 1, 1, 4 * sizeof(long));
+	debug_register_view(debug_info, &debug_sprintf_view);
+	debug_set_level(debug_info, 3);
+}
+
+static void trng_debug_exit(void)
+{
+	debug_unregister(debug_info);
+}
+
+static int __init trng_init(void)
+{
+	int ret;
+
+	trng_debug_init();
+
+	/* check if subfunction CPACF_PRNO_TRNG is available */
+	if (!cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG)) {
+		DEBUG_INFO("trng_init CPACF_PRNO_TRNG not available\n");
+		ret = -ENODEV;
+		goto out_dbg;
+	}
+
+	ret = misc_register(&trng_dev);
+	if (ret) {
+		DEBUG_WARN("trng_init misc_register() failed rc=%d\n", ret);
+		goto out_dbg;
+	}
+
+	ret = hwrng_register(&trng_hwrng_dev);
+	if (ret) {
+		DEBUG_WARN("trng_init hwrng_register() failed rc=%d\n", ret);
+		goto out_misc;
+	}
+
+	DEBUG_DBG("trng_init successful\n");
+
+	return 0;
+
+out_misc:
+	misc_deregister(&trng_dev);
+out_dbg:
+	trng_debug_exit();
+	return ret;
+}
+
+static void __exit trng_exit(void)
+{
+	hwrng_unregister(&trng_hwrng_dev);
+	misc_deregister(&trng_dev);
+	trng_debug_exit();
+}
+
+module_cpu_feature_match(MSA, trng_init);
+module_exit(trng_exit);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 37e204f3d9be..6ee3a25ae731 100644
--- a/drivers/iommu/Kconfig
+++ b/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
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 774da20ceb58..107cd3361e29 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -1052,8 +1052,9 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense)
 	} else {
 		/* fatal error -  set status to FAILED
 		   internal error 09 - Command Reject */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "09");
+		if (!test_bit(DASD_CQR_SUPPRESS_CR, &erp->flags))
+			dev_err(&device->cdev->dev,
+				"An error occurred in the DASD device driver, reason=09\n");
 
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 0b38217f8147..122456e4db89 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -4927,10 +4927,14 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
 		dasd_eckd_dump_sense_tcw(device, req, irb);
 	} else {
 		/*
-		 * In some cases the 'No Record Found' error might be expected
-		 * and log messages shouldn't be written then. Check if the
-		 * according suppress bit is set.
+		 * In some cases the 'Command Reject' or 'No Record Found'
+		 * error might be expected and log messages shouldn't be
+		 * written then. Check if the according suppress bit is set.
 		 */
+		if (sense && sense[0] & SNS0_CMD_REJECT &&
+		    test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
+			return;
+
 		if (sense && sense[1] & SNS1_NO_REC_FOUND &&
 		    test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
 			return;
@@ -5172,6 +5176,10 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
 	if (!device->block && private->lcu->pav == HYPER_PAV)
 		return -EOPNOTSUPP;
 
+	/* may not be supported by the storage server */
+	if (!(private->features.feature[14] & 0x80))
+		return -EOPNOTSUPP;
+
 	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */	+ 1 /* RSSD */,
 				   sizeof(struct dasd_psf_prssd_data) + 1,
 				   device);
@@ -5219,6 +5227,8 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
 
 	cqr->buildclk = get_tod_clock();
 	cqr->status = DASD_CQR_FILLED;
+	/* the command might not be supported, suppress error message */
+	__set_bit(DASD_CQR_SUPPRESS_CR, &cqr->flags);
 	rc = dasd_sleep_on_interruptible(cqr);
 	if (rc == 0) {
 		*data = *host_access;
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 518dba2732d5..dca7cb1e6f65 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -239,11 +239,11 @@ struct dasd_ccw_req {
 					 */
 /*
  * The following flags are used to suppress output of certain errors.
- * These flags should only be used for format checks!
  */
 #define DASD_CQR_SUPPRESS_NRF	4	/* Suppress 'No Record Found' error */
 #define DASD_CQR_SUPPRESS_FP	5	/* Suppress 'File Protected' error*/
 #define DASD_CQR_SUPPRESS_IL	6	/* Suppress 'Incorrect Length' error */
+#define DASD_CQR_SUPPRESS_CR	7	/* Suppress 'Command Reject' error */
 
 /* Signature for error recovery functions. */
 typedef struct dasd_ccw_req *(*dasd_erp_fn_t) (struct dasd_ccw_req *);
diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index 3ab9aedeb84a..bdf47526038a 100644
--- a/drivers/s390/cio/Makefile
+++ b/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
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 1b350665c823..89216174fcbb 100644
--- a/drivers/s390/cio/cio.c
+++ b/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);
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index f0e57aefb5f2..939596d81b73 100644
--- a/drivers/s390/cio/cio.h
+++ b/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);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 9afb5ce13007..12016e32e519 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/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 */
-	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;
+	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 ret;
 }
 
 void ccw_device_update_sense_data(struct ccw_device *cdev)
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
new file mode 100644
index 000000000000..ba6ac83a6c25
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -0,0 +1,842 @@
+/*
+ * 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>
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/iommu.h>
+#include <linux/vfio.h>
+#include <asm/idals.h>
+
+#include "vfio_ccw_cp.h"
+
+/*
+ * Max length for ccw chain.
+ * XXX: Limit to 256, need to check more?
+ */
+#define CCWCHAIN_LEN_MAX	256
+
+struct pfn_array {
+	unsigned long		pa_iova;
+	unsigned long		*pa_iova_pfn;
+	unsigned long		*pa_pfn;
+	int			pa_nr;
+};
+
+struct pfn_array_table {
+	struct pfn_array	*pat_pa;
+	int			pat_nr;
+};
+
+struct ccwchain {
+	struct list_head	next;
+	struct ccw1		*ch_ccw;
+	/* Guest physical address of the current chain. */
+	u64			ch_iova;
+	/* Count of the valid ccws in chain. */
+	int			ch_len;
+	/* Pinned PAGEs for the original data. */
+	struct pfn_array_table	*ch_pat;
+};
+
+/*
+ * pfn_array_pin() - pin user pages in memory
+ * @pa: pfn_array on which to perform the operation
+ * @mdev: the mediated device to perform pin/unpin operations
+ *
+ * Attempt to pin user pages in memory.
+ *
+ * Usage of pfn_array:
+ * @pa->pa_iova     starting guest physical I/O address. Assigned by caller.
+ * @pa->pa_iova_pfn array that stores PFNs of the pages need to pin. Allocated
+ *                  by caller.
+ * @pa->pa_pfn      array that receives PFNs of the pages pinned. Allocated by
+ *                  caller.
+ * @pa->pa_nr       number of pages from @pa->pa_iova to pin. Assigned by
+ *                  caller.
+ *                  number of pages pinned. Assigned by callee.
+ *
+ * Returns:
+ *   Number of pages pinned on success.
+ *   If @pa->pa_nr is 0 or negative, returns 0.
+ *   If no pages were pinned, returns -errno.
+ */
+static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+{
+	int i, ret;
+
+	if (pa->pa_nr <= 0) {
+		pa->pa_nr = 0;
+		return 0;
+	}
+
+	pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
+	for (i = 1; i < pa->pa_nr; i++)
+		pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
+
+	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
+
+	if (ret > 0 && ret != pa->pa_nr) {
+		vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
+		pa->pa_nr = 0;
+		return 0;
+	}
+
+	return ret;
+}
+
+/* Unpin the pages before releasing the memory. */
+static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+{
+	vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+	pa->pa_nr = 0;
+	kfree(pa->pa_iova_pfn);
+}
+
+/* Alloc memory for PFNs, then pin pages with them. */
+static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
+			       u64 iova, unsigned int len)
+{
+	int ret = 0;
+
+	if (!len || pa->pa_nr)
+		return -EINVAL;
+
+	pa->pa_iova = iova;
+
+	pa->pa_nr = ((iova & ~PAGE_MASK) + len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+	if (!pa->pa_nr)
+		return -EINVAL;
+
+	pa->pa_iova_pfn = kcalloc(pa->pa_nr,
+				  sizeof(*pa->pa_iova_pfn) +
+				  sizeof(*pa->pa_pfn),
+				  GFP_KERNEL);
+	if (unlikely(!pa->pa_iova_pfn))
+		return -ENOMEM;
+	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
+
+	ret = pfn_array_pin(pa, mdev);
+
+	if (ret > 0)
+		return ret;
+	else if (!ret)
+		ret = -EINVAL;
+
+	kfree(pa->pa_iova_pfn);
+
+	return ret;
+}
+
+static int pfn_array_table_init(struct pfn_array_table *pat, int nr)
+{
+	pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL);
+	if (unlikely(ZERO_OR_NULL_PTR(pat->pat_pa))) {
+		pat->pat_nr = 0;
+		return -ENOMEM;
+	}
+
+	pat->pat_nr = nr;
+
+	return 0;
+}
+
+static void pfn_array_table_unpin_free(struct pfn_array_table *pat,
+				       struct device *mdev)
+{
+	int i;
+
+	for (i = 0; i < pat->pat_nr; i++)
+		pfn_array_unpin_free(pat->pat_pa + i, mdev);
+
+	if (pat->pat_nr) {
+		kfree(pat->pat_pa);
+		pat->pat_pa = NULL;
+		pat->pat_nr = 0;
+	}
+}
+
+static bool pfn_array_table_iova_pinned(struct pfn_array_table *pat,
+					unsigned long iova)
+{
+	struct pfn_array *pa = pat->pat_pa;
+	unsigned long iova_pfn = iova >> PAGE_SHIFT;
+	int i, j;
+
+	for (i = 0; i < pat->pat_nr; i++, pa++)
+		for (j = 0; j < pa->pa_nr; j++)
+			if (pa->pa_iova_pfn[i] == iova_pfn)
+				return true;
+
+	return false;
+}
+/* Create the list idal words for a pfn_array_table. */
+static inline void pfn_array_table_idal_create_words(
+	struct pfn_array_table *pat,
+	unsigned long *idaws)
+{
+	struct pfn_array *pa;
+	int i, j, k;
+
+	/*
+	 * Idal words (execept the first one) rely on the memory being 4k
+	 * aligned. If a user virtual address is 4K aligned, then it's
+	 * corresponding kernel physical address will also be 4K aligned. Thus
+	 * there will be no problem here to simply use the phys to create an
+	 * idaw.
+	 */
+	k = 0;
+	for (i = 0; i < pat->pat_nr; i++) {
+		pa = pat->pat_pa + i;
+		for (j = 0; j < pa->pa_nr; j++) {
+			idaws[k] = pa->pa_pfn[j] << PAGE_SHIFT;
+			if (k == 0)
+				idaws[k] += pa->pa_iova & (PAGE_SIZE - 1);
+			k++;
+		}
+	}
+}
+
+
+/*
+ * Within the domain (@mdev), copy @n bytes from a guest physical
+ * address (@iova) to a host physical address (@to).
+ */
+static long copy_from_iova(struct device *mdev,
+			   void *to, u64 iova,
+			   unsigned long n)
+{
+	struct pfn_array pa = {0};
+	u64 from;
+	int i, ret;
+	unsigned long l, m;
+
+	ret = pfn_array_alloc_pin(&pa, mdev, iova, n);
+	if (ret <= 0)
+		return ret;
+
+	l = n;
+	for (i = 0; i < pa.pa_nr; i++) {
+		from = pa.pa_pfn[i] << PAGE_SHIFT;
+		m = PAGE_SIZE;
+		if (i == 0) {
+			from += iova & (PAGE_SIZE - 1);
+			m -= iova & (PAGE_SIZE - 1);
+		}
+
+		m = min(l, m);
+		memcpy(to + (n - l), (void *)from, m);
+
+		l -= m;
+		if (l == 0)
+			break;
+	}
+
+	pfn_array_unpin_free(&pa, mdev);
+
+	return l;
+}
+
+static long copy_ccw_from_iova(struct channel_program *cp,
+			       struct ccw1 *to, u64 iova,
+			       unsigned long len)
+{
+	struct ccw0 ccw0;
+	struct ccw1 *pccw1;
+	int ret;
+	int i;
+
+	ret = copy_from_iova(cp->mdev, to, iova, len * sizeof(struct ccw1));
+	if (ret)
+		return ret;
+
+	if (!cp->orb.cmd.fmt) {
+		pccw1 = to;
+		for (i = 0; i < len; i++) {
+			ccw0 = *(struct ccw0 *)pccw1;
+			if ((pccw1->cmd_code & 0x0f) == CCW_CMD_TIC) {
+				pccw1->cmd_code = CCW_CMD_TIC;
+				pccw1->flags = 0;
+				pccw1->count = 0;
+			} else {
+				pccw1->cmd_code = ccw0.cmd_code;
+				pccw1->flags = ccw0.flags;
+				pccw1->count = ccw0.count;
+			}
+			pccw1->cda = ccw0.cda;
+			pccw1++;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Helpers to operate ccwchain.
+ */
+#define ccw_is_test(_ccw) (((_ccw)->cmd_code & 0x0F) == 0)
+
+#define ccw_is_noop(_ccw) ((_ccw)->cmd_code == CCW_CMD_NOOP)
+
+#define ccw_is_tic(_ccw) ((_ccw)->cmd_code == CCW_CMD_TIC)
+
+#define ccw_is_idal(_ccw) ((_ccw)->flags & CCW_FLAG_IDA)
+
+
+#define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC))
+
+static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
+{
+	struct ccwchain *chain;
+	void *data;
+	size_t size;
+
+	/* Make ccw address aligned to 8. */
+	size = ((sizeof(*chain) + 7L) & -8L) +
+		sizeof(*chain->ch_ccw) * len +
+		sizeof(*chain->ch_pat) * len;
+	chain = kzalloc(size, GFP_DMA | GFP_KERNEL);
+	if (!chain)
+		return NULL;
+
+	data = (u8 *)chain + ((sizeof(*chain) + 7L) & -8L);
+	chain->ch_ccw = (struct ccw1 *)data;
+
+	data = (u8 *)(chain->ch_ccw) + sizeof(*chain->ch_ccw) * len;
+	chain->ch_pat = (struct pfn_array_table *)data;
+
+	chain->ch_len = len;
+
+	list_add_tail(&chain->next, &cp->ccwchain_list);
+
+	return chain;
+}
+
+static void ccwchain_free(struct ccwchain *chain)
+{
+	list_del(&chain->next);
+	kfree(chain);
+}
+
+/* Free resource for a ccw that allocated memory for its cda. */
+static void ccwchain_cda_free(struct ccwchain *chain, int idx)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+
+	if (!ccw->count)
+		return;
+
+	kfree((void *)(u64)ccw->cda);
+}
+
+/* Unpin the pages then free the memory resources. */
+static void cp_unpin_free(struct channel_program *cp)
+{
+	struct ccwchain *chain, *temp;
+	int i;
+
+	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+		for (i = 0; i < chain->ch_len; i++) {
+			pfn_array_table_unpin_free(chain->ch_pat + i,
+						   cp->mdev);
+			ccwchain_cda_free(chain, i);
+		}
+		ccwchain_free(chain);
+	}
+}
+
+/**
+ * ccwchain_calc_length - calculate the length of the ccw chain.
+ * @iova: guest physical address of the target ccw chain
+ * @cp: channel_program on which to perform the operation
+ *
+ * This is the chain length not considering any TICs.
+ * You need to do a new round for each TIC target.
+ *
+ * Returns: the length of the ccw chain or -errno.
+ */
+static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
+{
+	struct ccw1 *ccw, *p;
+	int cnt;
+
+	/*
+	 * Copy current chain from guest to host kernel.
+	 * Currently the chain length is limited to CCWCHAIN_LEN_MAX (256).
+	 * So copying 2K is enough (safe).
+	 */
+	p = ccw = kcalloc(CCWCHAIN_LEN_MAX, sizeof(*ccw), GFP_KERNEL);
+	if (!ccw)
+		return -ENOMEM;
+
+	cnt = copy_ccw_from_iova(cp, ccw, iova, CCWCHAIN_LEN_MAX);
+	if (cnt) {
+		kfree(ccw);
+		return cnt;
+	}
+
+	cnt = 0;
+	do {
+		cnt++;
+
+		if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw)))
+			break;
+
+		ccw++;
+	} while (cnt < CCWCHAIN_LEN_MAX + 1);
+
+	if (cnt == CCWCHAIN_LEN_MAX + 1)
+		cnt = -EINVAL;
+
+	kfree(p);
+	return cnt;
+}
+
+static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	u32 ccw_head, ccw_tail;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		ccw_head = chain->ch_iova;
+		ccw_tail = ccw_head + (chain->ch_len - 1) * sizeof(struct ccw1);
+
+		if ((ccw_head <= tic->cda) && (tic->cda <= ccw_tail))
+			return 1;
+	}
+
+	return 0;
+}
+
+static int ccwchain_loop_tic(struct ccwchain *chain,
+			     struct channel_program *cp);
+
+static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	int len, ret;
+
+	/* May transfer to an existing chain. */
+	if (tic_target_chain_exists(tic, cp))
+		return 0;
+
+	/* Get chain length. */
+	len = ccwchain_calc_length(tic->cda, cp);
+	if (len < 0)
+		return len;
+
+	/* Need alloc a new chain for this one. */
+	chain = ccwchain_alloc(cp, len);
+	if (!chain)
+		return -ENOMEM;
+	chain->ch_iova = tic->cda;
+
+	/* Copy the new chain from user. */
+	ret = copy_ccw_from_iova(cp, chain->ch_ccw, tic->cda, len);
+	if (ret) {
+		ccwchain_free(chain);
+		return ret;
+	}
+
+	/* Loop for tics on this new chain. */
+	return ccwchain_loop_tic(chain, cp);
+}
+
+/* Loop for TICs. */
+static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
+{
+	struct ccw1 *tic;
+	int i, ret;
+
+	for (i = 0; i < chain->ch_len; i++) {
+		tic = chain->ch_ccw + i;
+
+		if (!ccw_is_tic(tic))
+			continue;
+
+		ret = ccwchain_handle_tic(tic, cp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ccwchain_fetch_tic(struct ccwchain *chain,
+			      int idx,
+			      struct channel_program *cp)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+	struct ccwchain *iter;
+	u32 ccw_head, ccw_tail;
+
+	list_for_each_entry(iter, &cp->ccwchain_list, next) {
+		ccw_head = iter->ch_iova;
+		ccw_tail = ccw_head + (iter->ch_len - 1) * sizeof(struct ccw1);
+
+		if ((ccw_head <= ccw->cda) && (ccw->cda <= ccw_tail)) {
+			ccw->cda = (__u32) (addr_t) (iter->ch_ccw +
+						     (ccw->cda - ccw_head));
+			return 0;
+		}
+	}
+
+	return -EFAULT;
+}
+
+static int ccwchain_fetch_direct(struct ccwchain *chain,
+				 int idx,
+				 struct channel_program *cp)
+{
+	struct ccw1 *ccw;
+	struct pfn_array_table *pat;
+	unsigned long *idaws;
+	int idaw_nr;
+
+	ccw = chain->ch_ccw + idx;
+
+	/*
+	 * Pin data page(s) in memory.
+	 * The number of pages actually is the count of the idaws which will be
+	 * needed when translating a direct ccw to a idal ccw.
+	 */
+	pat = chain->ch_pat + idx;
+	if (pfn_array_table_init(pat, 1))
+		return -ENOMEM;
+	idaw_nr = pfn_array_alloc_pin(pat->pat_pa, cp->mdev,
+				      ccw->cda, ccw->count);
+	if (idaw_nr < 0)
+		return idaw_nr;
+
+	/* Translate this direct ccw to a idal ccw. */
+	idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
+	if (!idaws) {
+		pfn_array_table_unpin_free(pat, cp->mdev);
+		return -ENOMEM;
+	}
+	ccw->cda = (__u32) virt_to_phys(idaws);
+	ccw->flags |= CCW_FLAG_IDA;
+
+	pfn_array_table_idal_create_words(pat, idaws);
+
+	return 0;
+}
+
+static int ccwchain_fetch_idal(struct ccwchain *chain,
+			       int idx,
+			       struct channel_program *cp)
+{
+	struct ccw1 *ccw;
+	struct pfn_array_table *pat;
+	unsigned long *idaws;
+	u64 idaw_iova;
+	unsigned int idaw_nr, idaw_len;
+	int i, ret;
+
+	ccw = chain->ch_ccw + idx;
+
+	/* Calculate size of idaws. */
+	ret = copy_from_iova(cp->mdev, &idaw_iova, ccw->cda, sizeof(idaw_iova));
+	if (ret)
+		return ret;
+	idaw_nr = idal_nr_words((void *)(idaw_iova), ccw->count);
+	idaw_len = idaw_nr * sizeof(*idaws);
+
+	/* Pin data page(s) in memory. */
+	pat = chain->ch_pat + idx;
+	ret = pfn_array_table_init(pat, idaw_nr);
+	if (ret)
+		return ret;
+
+	/* Translate idal ccw to use new allocated idaws. */
+	idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL);
+	if (!idaws) {
+		ret = -ENOMEM;
+		goto out_unpin;
+	}
+
+	ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idaw_len);
+	if (ret)
+		goto out_free_idaws;
+
+	ccw->cda = virt_to_phys(idaws);
+
+	for (i = 0; i < idaw_nr; i++) {
+		idaw_iova = *(idaws + i);
+		if (IS_ERR_VALUE(idaw_iova)) {
+			ret = -EFAULT;
+			goto out_free_idaws;
+		}
+
+		ret = pfn_array_alloc_pin(pat->pat_pa + i, cp->mdev,
+					  idaw_iova, 1);
+		if (ret < 0)
+			goto out_free_idaws;
+	}
+
+	pfn_array_table_idal_create_words(pat, idaws);
+
+	return 0;
+
+out_free_idaws:
+	kfree(idaws);
+out_unpin:
+	pfn_array_table_unpin_free(pat, cp->mdev);
+	return ret;
+}
+
+/*
+ * Fetch one ccw.
+ * To reduce memory copy, we'll pin the cda page in memory,
+ * and to get rid of the cda 2G limitiaion of ccw1, we'll translate
+ * direct ccws to idal ccws.
+ */
+static int ccwchain_fetch_one(struct ccwchain *chain,
+			      int idx,
+			      struct channel_program *cp)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+
+	if (ccw_is_test(ccw) || ccw_is_noop(ccw))
+		return 0;
+
+	if (ccw_is_tic(ccw))
+		return ccwchain_fetch_tic(chain, idx, cp);
+
+	if (ccw_is_idal(ccw))
+		return ccwchain_fetch_idal(chain, idx, cp);
+
+	return ccwchain_fetch_direct(chain, idx, cp);
+}
+
+/**
+ * cp_init() - allocate ccwchains for a channel program.
+ * @cp: channel_program on which to perform the operation
+ * @mdev: the mediated device to perform pin/unpin operations
+ * @orb: control block for the channel program from the guest
+ *
+ * This creates one or more ccwchain(s), and copies the raw data of
+ * the target channel program from @orb->cmd.iova to the new ccwchain(s).
+ *
+ * Limitations:
+ * 1. Supports only prefetch enabled mode.
+ * 2. Supports idal(c64) ccw chaining.
+ * 3. Supports 4k idaw.
+ *
+ * Returns:
+ *   %0 on success and a negative error value on failure.
+ */
+int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
+{
+	u64 iova = orb->cmd.cpa;
+	struct ccwchain *chain;
+	int len, ret;
+
+	/*
+	 * XXX:
+	 * Only support prefetch enable mode now.
+	 * Only support 64bit addressing idal.
+	 * Only support 4k IDAW.
+	 */
+	if (!orb->cmd.pfch || !orb->cmd.c64 || orb->cmd.i2k)
+		return -EOPNOTSUPP;
+
+	INIT_LIST_HEAD(&cp->ccwchain_list);
+	memcpy(&cp->orb, orb, sizeof(*orb));
+	cp->mdev = mdev;
+
+	/* Get chain length. */
+	len = ccwchain_calc_length(iova, cp);
+	if (len < 0)
+		return len;
+
+	/* Alloc mem for the head chain. */
+	chain = ccwchain_alloc(cp, len);
+	if (!chain)
+		return -ENOMEM;
+	chain->ch_iova = iova;
+
+	/* Copy the head chain from guest. */
+	ret = copy_ccw_from_iova(cp, chain->ch_ccw, iova, len);
+	if (ret) {
+		ccwchain_free(chain);
+		return ret;
+	}
+
+	/* Now loop for its TICs. */
+	ret = ccwchain_loop_tic(chain, cp);
+	if (ret)
+		cp_unpin_free(cp);
+
+	return ret;
+}
+
+
+/**
+ * cp_free() - free resources for channel program.
+ * @cp: channel_program on which to perform the operation
+ *
+ * This unpins the memory pages and frees the memory space occupied by
+ * @cp, which must have been returned by a previous call to cp_init().
+ * Otherwise, undefined behavior occurs.
+ */
+void cp_free(struct channel_program *cp)
+{
+	cp_unpin_free(cp);
+}
+
+/**
+ * cp_prefetch() - translate a guest physical address channel program to
+ *                 a real-device runnable channel program.
+ * @cp: channel_program on which to perform the operation
+ *
+ * This function translates the guest-physical-address channel program
+ * and stores the result to ccwchain list. @cp must have been
+ * initialized by a previous call with cp_init(). Otherwise, undefined
+ * behavior occurs.
+ *
+ * The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
+ * as helpers to do ccw chain translation inside the kernel. Basically
+ * they accept a channel program issued by a virtual machine, and
+ * translate the channel program to a real-device runnable channel
+ * program.
+ *
+ * These APIs will copy the ccws into kernel-space buffers, and update
+ * the guest phsical addresses with their corresponding host physical
+ * addresses.  Then channel I/O device drivers could issue the
+ * translated channel program to real devices to perform an I/O
+ * operation.
+ *
+ * These interfaces are designed to support translation only for
+ * channel programs, which are generated and formatted by a
+ * guest. Thus this will make it possible for things like VFIO to
+ * leverage the interfaces to passthrough a channel I/O mediated
+ * device in QEMU.
+ *
+ * We support direct ccw chaining by translating them to idal ccws.
+ *
+ * Returns:
+ *   %0 on success and a negative error value on failure.
+ */
+int cp_prefetch(struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	int len, idx, ret;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		len = chain->ch_len;
+		for (idx = 0; idx < len; idx++) {
+			ret = ccwchain_fetch_one(chain, idx, cp);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * cp_get_orb() - get the orb of the channel program
+ * @cp: channel_program on which to perform the operation
+ * @intparm: new intparm for the returned orb
+ * @lpm: candidate value of the logical-path mask for the returned orb
+ *
+ * This function returns the address of the updated orb of the channel
+ * program. Channel I/O device drivers could use this orb to issue a
+ * ssch.
+ */
+union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm)
+{
+	union orb *orb;
+	struct ccwchain *chain;
+	struct ccw1 *cpa;
+
+	orb = &cp->orb;
+
+	orb->cmd.intparm = intparm;
+	orb->cmd.fmt = 1;
+	orb->cmd.key = PAGE_DEFAULT_KEY >> 4;
+
+	if (orb->cmd.lpm == 0)
+		orb->cmd.lpm = lpm;
+
+	chain = list_first_entry(&cp->ccwchain_list, struct ccwchain, next);
+	cpa = chain->ch_ccw;
+	orb->cmd.cpa = (__u32) __pa(cpa);
+
+	return orb;
+}
+
+/**
+ * cp_update_scsw() - update scsw for a channel program.
+ * @cp: channel_program on which to perform the operation
+ * @scsw: I/O results of the channel program and also the target to be
+ *        updated
+ *
+ * @scsw contains the I/O results of the channel program that pointed
+ * to by @cp. However what @scsw->cpa stores is a host physical
+ * address, which is meaningless for the guest, which is waiting for
+ * the I/O results.
+ *
+ * This function updates @scsw->cpa to its coressponding guest physical
+ * address.
+ */
+void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
+{
+	struct ccwchain *chain;
+	u32 cpa = scsw->cmd.cpa;
+	u32 ccw_head, ccw_tail;
+
+	/*
+	 * LATER:
+	 * For now, only update the cmd.cpa part. We may need to deal with
+	 * other portions of the schib as well, even if we don't return them
+	 * in the ioctl directly. Path status changes etc.
+	 */
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		ccw_head = (u32)(u64)chain->ch_ccw;
+		ccw_tail = (u32)(u64)(chain->ch_ccw + chain->ch_len - 1);
+
+		if ((ccw_head <= cpa) && (cpa <= ccw_tail)) {
+			/*
+			 * (cpa - ccw_head) is the offset value of the host
+			 * physical ccw to its chain head.
+			 * Adding this value to the guest physical ccw chain
+			 * head gets us the guest cpa.
+			 */
+			cpa = chain->ch_iova + (cpa - ccw_head);
+			break;
+		}
+	}
+
+	scsw->cmd.cpa = cpa;
+}
+
+/**
+ * cp_iova_pinned() - check if an iova is pinned for a ccw chain.
+ * @cmd: ccwchain command on which to perform the operation
+ * @iova: the iova to check
+ *
+ * If the @iova is currently pinned for the ccw chain, return true;
+ * else return false.
+ */
+bool cp_iova_pinned(struct channel_program *cp, u64 iova)
+{
+	struct ccwchain *chain;
+	int i;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		for (i = 0; i < chain->ch_len; i++)
+			if (pfn_array_table_iova_pinned(chain->ch_pat + i,
+							iova))
+				return true;
+	}
+
+	return false;
+}
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
new file mode 100644
index 000000000000..7a1996b3b36d
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -0,0 +1,42 @@
+/*
+ * 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
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
new file mode 100644
index 000000000000..e90dd43d2a55
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -0,0 +1,308 @@
+/*
+ * 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");
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
new file mode 100644
index 000000000000..80a0559cd7ce
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -0,0 +1,203 @@
+/*
+ * 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 = 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,
+	},
+};
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
new file mode 100644
index 000000000000..e72abbc18ee3
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -0,0 +1,425 @@
+/*
+ * 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));
+	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);
+
+	/*
+	 * 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));
+
+	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
+	    (private->state != VFIO_CCW_STATE_STANDBY)) {
+		if (!vfio_ccw_mdev_reset(mdev))
+			private->state = VFIO_CCW_STATE_STANDBY;
+		/* The state will be NOT_OPER on error. */
+	}
+
+	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));
+	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->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));
+	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);
+}
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
new file mode 100644
index 000000000000..fc0f01c16ef9
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -0,0 +1,96 @@
+/*
+ * 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
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 058db724b5a2..ea86da8c75f9 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -80,7 +80,7 @@ struct secaeskeytoken {
  * token. If keybitsize is given, the bitsize of the key is
  * also checked. Returns 0 on success or errno value on failure.
  */
-static int check_secaeskeytoken(u8 *token, int keybitsize)
+static int check_secaeskeytoken(const u8 *token, int keybitsize)
 {
 	struct secaeskeytoken *t = (struct secaeskeytoken *) token;
 
@@ -1004,6 +1004,53 @@ int pkey_skey2pkey(const struct pkey_seckey *seckey,
 EXPORT_SYMBOL(pkey_skey2pkey);
 
 /*
+ * Verify key and give back some info about the key.
+ */
+int pkey_verifykey(const struct pkey_seckey *seckey,
+		   u16 *pcardnr, u16 *pdomain,
+		   u16 *pkeysize, u32 *pattributes)
+{
+	struct secaeskeytoken *t = (struct secaeskeytoken *) seckey;
+	u16 cardnr, domain;
+	u64 mkvp[2];
+	int rc;
+
+	/* check the secure key for valid AES secure key */
+	rc = check_secaeskeytoken((u8 *) seckey, 0);
+	if (rc)
+		goto out;
+	if (pattributes)
+		*pattributes = PKEY_VERIFY_ATTR_AES;
+	if (pkeysize)
+		*pkeysize = t->bitsize;
+
+	/* try to find a card which can handle this key */
+	rc = pkey_findcard(seckey, &cardnr, &domain, 1);
+	if (rc)
+		goto out;
+
+	/* check mkvp for old mkvp match */
+	rc = mkvp_cache_fetch(cardnr, domain, mkvp);
+	if (rc)
+		goto out;
+	if (t->mkvp == mkvp[1]) {
+		DEBUG_DBG("pkey_verifykey secure key has old mkvp\n");
+		if (pattributes)
+			*pattributes |= PKEY_VERIFY_ATTR_OLD_MKVP;
+	}
+
+	if (pcardnr)
+		*pcardnr = cardnr;
+	if (pdomain)
+		*pdomain = domain;
+
+out:
+	DEBUG_DBG("pkey_verifykey rc=%d\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(pkey_verifykey);
+
+/*
  * File io functions
  */
 
@@ -1104,6 +1151,21 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		break;
 	}
+	case PKEY_VERIFYKEY: {
+		struct pkey_verifykey __user *uvk = (void __user *) arg;
+		struct pkey_verifykey kvk;
+
+		if (copy_from_user(&kvk, uvk, sizeof(kvk)))
+			return -EFAULT;
+		rc = pkey_verifykey(&kvk.seckey, &kvk.cardnr, &kvk.domain,
+				    &kvk.keysize, &kvk.attributes);
+		DEBUG_DBG("pkey_ioctl pkey_verifykey()=%d\n", rc);
+		if (rc)
+			break;
+		if (copy_to_user(uvk, &kvk, sizeof(kvk)))
+			return -EFAULT;
+		break;
+	}
 	default:
 		/* unknown/unsupported ioctl cmd */
 		return -ENOTTY;