Merge tag 's390-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Improve stop_machine wait logic: replace cpu_relax_yield call in
   generic stop_machine function with a weak stop_machine_yield
   function. This is overridden on s390, which yields the current cpu to
   the neighbouring cpu after a couple of retries, instead of blindly
   giving up the cpu to the hipervisor. This significantly improves
   stop_machine performance on s390 in overcommitted scenarios.

   This includes common code changes which have been Acked by Peter
   Zijlstra and Thomas Gleixner.

 - Improve jump label transformation speed: transform jump labels
   without using stop_machine.

 - Refactoring of the vfio-ccw cp handling, simplifying the code and
   avoiding unneeded allocating/copying.

 - Various vfio-ccw fixes (ccw translation, state machine).

 - Add support for vfio-ap queue interrupt control in the guest. This
   includes s390 kvm changes which have been Acked by Christian
   Borntraeger.

 - Add protected virtualization support for virtio-ccw.

 - Enforce both CONFIG_SMP and CONFIG_HOTPLUG_CPU, which allows to
   remove some code which most likely isn't working at all, besides that
   s390 didn't even compile for !CONFIG_SMP.

 - Support for special flagged EP11 CPRBs for zcrypt.

 - Handle PCI devices with no support for new MIO instructions.

 - Avoid KASAN false positives in reworked stack unwinder.

 - Couple of fixes for the QDIO layer.

 - Convert s390 specific documentation to ReST format.

 - Let s390 crypto modules return -ENODEV instead of -EOPNOTSUPP if
   hardware is missing. This way our modules behave like most other
   modules and which is also what systemd's systemd-modules-load.service
   expects.

 - Replace defconfig with performance_defconfig, so there is one config
   file less to maintain.

 - Remove the SCLP call home device driver, which was never useful.

 - Cleanups all over the place.

* tag 's390-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (83 commits)
  docs: s390: s390dbf: typos and formatting, update crash command
  docs: s390: unify and update s390dbf kdocs at debug.c
  docs: s390: restore important non-kdoc parts of s390dbf.rst
  vfio-ccw: Fix the conversion of Format-0 CCWs to Format-1
  s390/pci: correctly handle MIO opt-out
  s390/pci: deal with devices that have no support for MIO instructions
  s390: ap: kvm: Enable PQAP/AQIC facility for the guest
  s390: ap: implement PAPQ AQIC interception in kernel
  vfio: ap: register IOMMU VFIO notifier
  s390: ap: kvm: add PQAP interception for AQIC
  s390/unwind: cleanup unused READ_ONCE_TASK_STACK
  s390/kasan: avoid false positives during stack unwind
  s390/qdio: don't touch the dsci in tiqdio_add_input_queues()
  s390/qdio: (re-)initialize tiqdio list entries
  s390/dasd: Fix a precision vs width bug in dasd_feature_list()
  s390/cio: introduce driver_override on the css bus
  vfio-ccw: make convert_ccw0_to_ccw1 static
  vfio-ccw: Remove copy_ccw_from_iova()
  vfio-ccw: Factor out the ccw0-to-ccw1 transition
  vfio-ccw: Copy CCW data outside length calculation
  ...

18 files changed, 620 insertions, 423 deletions

diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 4534afc63591..427b2e24a8ce 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -16,9 +16,11 @@
 #include <linux/mutex.h>
 #include <linux/rculist.h>
 #include <linux/slab.h>
+#include <linux/dmapool.h>
 
 #include <asm/airq.h>
 #include <asm/isc.h>
+#include <asm/cio.h>
 
 #include "cio.h"
 #include "cio_debug.h"
@@ -27,7 +29,7 @@
 static DEFINE_SPINLOCK(airq_lists_lock);
 static struct hlist_head airq_lists[MAX_ISC+1];
 
-static struct kmem_cache *airq_iv_cache;
+static struct dma_pool *airq_iv_cache;
 
 /**
  * register_adapter_interrupt() - register adapter interrupt handler
@@ -115,6 +117,11 @@ void __init init_airq_interrupts(void)
 	setup_irq(THIN_INTERRUPT, &airq_interrupt);
 }
 
+static inline unsigned long iv_size(unsigned long bits)
+{
+	return BITS_TO_LONGS(bits) * sizeof(unsigned long);
+}
+
 /**
  * airq_iv_create - create an interrupt vector
  * @bits: number of bits in the interrupt vector
@@ -132,17 +139,19 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags)
 		goto out;
 	iv->bits = bits;
 	iv->flags = flags;
-	size = BITS_TO_LONGS(bits) * sizeof(unsigned long);
+	size = iv_size(bits);
 
 	if (flags & AIRQ_IV_CACHELINE) {
-		if ((cache_line_size() * BITS_PER_BYTE) < bits)
+		if ((cache_line_size() * BITS_PER_BYTE) < bits
+				|| !airq_iv_cache)
 			goto out_free;
 
-		iv->vector = kmem_cache_zalloc(airq_iv_cache, GFP_KERNEL);
+		iv->vector = dma_pool_zalloc(airq_iv_cache, GFP_KERNEL,
+					     &iv->vector_dma);
 		if (!iv->vector)
 			goto out_free;
 	} else {
-		iv->vector = kzalloc(size, GFP_KERNEL);
+		iv->vector = cio_dma_zalloc(size);
 		if (!iv->vector)
 			goto out_free;
 	}
@@ -178,10 +187,10 @@ out_free:
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
 	kfree(iv->avail);
-	if (iv->flags & AIRQ_IV_CACHELINE)
-		kmem_cache_free(airq_iv_cache, iv->vector);
+	if (iv->flags & AIRQ_IV_CACHELINE && iv->vector)
+		dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma);
 	else
-		kfree(iv->vector);
+		cio_dma_free(iv->vector, size);
 	kfree(iv);
 out:
 	return NULL;
@@ -198,9 +207,9 @@ void airq_iv_release(struct airq_iv *iv)
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
 	if (iv->flags & AIRQ_IV_CACHELINE)
-		kmem_cache_free(airq_iv_cache, iv->vector);
+		dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma);
 	else
-		kfree(iv->vector);
+		cio_dma_free(iv->vector, iv_size(iv->bits));
 	kfree(iv->avail);
 	kfree(iv);
 }
@@ -295,12 +304,12 @@ unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
 }
 EXPORT_SYMBOL(airq_iv_scan);
 
-static int __init airq_init(void)
+int __init airq_init(void)
 {
-	airq_iv_cache = kmem_cache_create("airq_iv_cache", cache_line_size(),
-					  cache_line_size(), 0, NULL);
+	airq_iv_cache = dma_pool_create("airq_iv_cache", cio_get_dma_css_dev(),
+					cache_line_size(),
+					cache_line_size(), PAGE_SIZE);
 	if (!airq_iv_cache)
 		return -ENOMEM;
 	return 0;
 }
-subsys_initcall(airq_init);
diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c
index 603268a33ea1..73582a0a2622 100644
--- a/drivers/s390/cio/ccwreq.c
+++ b/drivers/s390/cio/ccwreq.c
@@ -63,7 +63,7 @@ static void ccwreq_stop(struct ccw_device *cdev, int rc)
 		return;
 	req->done = 1;
 	ccw_device_set_timeout(cdev, 0);
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 	if (rc && rc != -ENODEV && req->drc)
 		rc = req->drc;
 	req->callback(cdev, req->data, rc);
@@ -86,7 +86,7 @@ static void ccwreq_do(struct ccw_device *cdev)
 			continue;
 		}
 		/* Perform start function. */
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 		rc = cio_start(sch, cp, (u8) req->mask);
 		if (rc == 0) {
 			/* I/O started successfully. */
@@ -169,7 +169,7 @@ int ccw_request_cancel(struct ccw_device *cdev)
  */
 static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb)
 {
-	struct irb *irb = &cdev->private->irb;
+	struct irb *irb = &cdev->private->dma_area->irb;
 	struct cmd_scsw *scsw = &irb->scsw.cmd;
 	enum uc_todo todo;
 
@@ -187,7 +187,8 @@ static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb)
 		CIO_TRACE_EVENT(2, "sensedata");
 		CIO_HEX_EVENT(2, &cdev->private->dev_id,
 			      sizeof(struct ccw_dev_id));
-		CIO_HEX_EVENT(2, &cdev->private->irb.ecw, SENSE_MAX_COUNT);
+		CIO_HEX_EVENT(2, &cdev->private->dma_area->irb.ecw,
+			      SENSE_MAX_COUNT);
 		/* Check for command reject. */
 		if (irb->ecw[0] & SNS0_CMD_REJECT)
 			return IO_REJECTED;
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index a835b31aad99..6392a1b95b02 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -323,36 +323,6 @@ struct chsc_sei {
 } __packed __aligned(PAGE_SIZE);
 
 /*
- * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
- */
-
-#define ND_VALIDITY_VALID	0
-#define ND_VALIDITY_OUTDATED	1
-#define ND_VALIDITY_INVALID	2
-
-struct node_descriptor {
-	/* Flags. */
-	union {
-		struct {
-			u32 validity:3;
-			u32 reserved:5;
-		} __packed;
-		u8 byte0;
-	} __packed;
-
-	/* Node parameters. */
-	u32 params:24;
-
-	/* Node ID. */
-	char type[6];
-	char model[3];
-	char manufacturer[3];
-	char plant[2];
-	char seq[12];
-	u16 tag;
-} __packed;
-
-/*
  * Link Incident Record as defined in SA22-7202, "ESCON I/O Interface"
  */
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 06a91743335a..ba7d2480613b 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -113,6 +113,7 @@ struct subchannel {
 	enum sch_todo todo;
 	struct work_struct todo_work;
 	struct schib_config config;
+	char *driver_override; /* Driver name to force a match */
 } __attribute__ ((aligned(8)));
 
 DECLARE_PER_CPU_ALIGNED(struct irb, cio_irb);
@@ -135,6 +136,8 @@ extern int cio_commit_config(struct subchannel *sch);
 int cio_tm_start_key(struct subchannel *sch, struct tcw *tcw, u8 lpm, u8 key);
 int cio_tm_intrg(struct subchannel *sch);
 
+extern int __init airq_init(void);
+
 /* Use with care. */
 #ifdef CONFIG_CCW_CONSOLE
 extern struct subchannel *cio_probe_console(void);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index aea502922646..e1f2d0eed544 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -20,6 +20,8 @@
 #include <linux/reboot.h>
 #include <linux/suspend.h>
 #include <linux/proc_fs.h>
+#include <linux/genalloc.h>
+#include <linux/dma-mapping.h>
 #include <asm/isc.h>
 #include <asm/crw.h>
 
@@ -165,6 +167,7 @@ static void css_subchannel_release(struct device *dev)
 
 	sch->config.intparm = 0;
 	cio_commit_config(sch);
+	kfree(sch->driver_override);
 	kfree(sch->lock);
 	kfree(sch);
 }
@@ -224,6 +227,12 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
 	INIT_WORK(&sch->todo_work, css_sch_todo);
 	sch->dev.release = &css_subchannel_release;
 	device_initialize(&sch->dev);
+	/*
+	 * The physical addresses of some the dma structures that can
+	 * belong to a subchannel need to fit 31 bit width (e.g. ccw).
+	 */
+	sch->dev.coherent_dma_mask = DMA_BIT_MASK(31);
+	sch->dev.dma_mask = &sch->dev.coherent_dma_mask;
 	return sch;
 
 err:
@@ -315,9 +324,57 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	char *driver_override, *old, *cp;
+
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	device_lock(dev);
+	old = sch->driver_override;
+	if (strlen(driver_override)) {
+		sch->driver_override = driver_override;
+	} else {
+		kfree(driver_override);
+		sch->driver_override = NULL;
+	}
+	device_unlock(dev);
+
+	kfree(old);
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	ssize_t len;
+
+	device_lock(dev);
+	len = snprintf(buf, PAGE_SIZE, "%s\n", sch->driver_override);
+	device_unlock(dev);
+	return len;
+}
+static DEVICE_ATTR_RW(driver_override);
+
 static struct attribute *subch_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_modalias.attr,
+	&dev_attr_driver_override.attr,
 	NULL,
 };
 
@@ -899,6 +956,13 @@ static int __init setup_css(int nr)
 	dev_set_name(&css->device, "css%x", nr);
 	css->device.groups = cssdev_attr_groups;
 	css->device.release = channel_subsystem_release;
+	/*
+	 * We currently allocate notifier bits with this (using
+	 * css->device as the device argument with the DMA API)
+	 * and are fine with 64 bit addresses.
+	 */
+	css->device.coherent_dma_mask = DMA_BIT_MASK(64);
+	css->device.dma_mask = &css->device.coherent_dma_mask;
 
 	mutex_init(&css->mutex);
 	css->cssid = chsc_get_cssid(nr);
@@ -1018,6 +1082,111 @@ static struct notifier_block css_power_notifier = {
 	.notifier_call = css_power_event,
 };
 
+#define  CIO_DMA_GFP (GFP_KERNEL | __GFP_ZERO)
+static struct gen_pool *cio_dma_pool;
+
+/* Currently cio supports only a single css */
+struct device *cio_get_dma_css_dev(void)
+{
+	return &channel_subsystems[0]->device;
+}
+
+struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages)
+{
+	struct gen_pool *gp_dma;
+	void *cpu_addr;
+	dma_addr_t dma_addr;
+	int i;
+
+	gp_dma = gen_pool_create(3, -1);
+	if (!gp_dma)
+		return NULL;
+	for (i = 0; i < nr_pages; ++i) {
+		cpu_addr = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr,
+					      CIO_DMA_GFP);
+		if (!cpu_addr)
+			return gp_dma;
+		gen_pool_add_virt(gp_dma, (unsigned long) cpu_addr,
+				  dma_addr, PAGE_SIZE, -1);
+	}
+	return gp_dma;
+}
+
+static void __gp_dma_free_dma(struct gen_pool *pool,
+			      struct gen_pool_chunk *chunk, void *data)
+{
+	size_t chunk_size = chunk->end_addr - chunk->start_addr + 1;
+
+	dma_free_coherent((struct device *) data, chunk_size,
+			 (void *) chunk->start_addr,
+			 (dma_addr_t) chunk->phys_addr);
+}
+
+void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev)
+{
+	if (!gp_dma)
+		return;
+	/* this is quite ugly but no better idea */
+	gen_pool_for_each_chunk(gp_dma, __gp_dma_free_dma, dma_dev);
+	gen_pool_destroy(gp_dma);
+}
+
+static int cio_dma_pool_init(void)
+{
+	/* No need to free up the resources: compiled in */
+	cio_dma_pool = cio_gp_dma_create(cio_get_dma_css_dev(), 1);
+	if (!cio_dma_pool)
+		return -ENOMEM;
+	return 0;
+}
+
+void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
+			size_t size)
+{
+	dma_addr_t dma_addr;
+	unsigned long addr;
+	size_t chunk_size;
+
+	if (!gp_dma)
+		return NULL;
+	addr = gen_pool_alloc(gp_dma, size);
+	while (!addr) {
+		chunk_size = round_up(size, PAGE_SIZE);
+		addr = (unsigned long) dma_alloc_coherent(dma_dev,
+					 chunk_size, &dma_addr, CIO_DMA_GFP);
+		if (!addr)
+			return NULL;
+		gen_pool_add_virt(gp_dma, addr, dma_addr, chunk_size, -1);
+		addr = gen_pool_alloc(gp_dma, size);
+	}
+	return (void *) addr;
+}
+
+void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size)
+{
+	if (!cpu_addr)
+		return;
+	memset(cpu_addr, 0, size);
+	gen_pool_free(gp_dma, (unsigned long) cpu_addr, size);
+}
+
+/*
+ * Allocate dma memory from the css global pool. Intended for memory not
+ * specific to any single device within the css. The allocated memory
+ * is not guaranteed to be 31-bit addressable.
+ *
+ * Caution: Not suitable for early stuff like console.
+ */
+void *cio_dma_zalloc(size_t size)
+{
+	return cio_gp_dma_zalloc(cio_dma_pool, cio_get_dma_css_dev(), size);
+}
+
+void cio_dma_free(void *cpu_addr, size_t size)
+{
+	cio_gp_dma_free(cio_dma_pool, cpu_addr, size);
+}
+
 /*
  * Now that the driver core is running, we can setup our channel subsystem.
  * The struct subchannel's are created during probing.
@@ -1059,16 +1228,22 @@ static int __init css_bus_init(void)
 	if (ret)
 		goto out_unregister;
 	ret = register_pm_notifier(&css_power_notifier);
-	if (ret) {
-		unregister_reboot_notifier(&css_reboot_notifier);
-		goto out_unregister;
-	}
+	if (ret)
+		goto out_unregister_rn;
+	ret = cio_dma_pool_init();
+	if (ret)
+		goto out_unregister_pmn;
+	airq_init();
 	css_init_done = 1;
 
 	/* Enable default isc for I/O subchannels. */
 	isc_register(IO_SCH_ISC);
 
 	return 0;
+out_unregister_pmn:
+	unregister_pm_notifier(&css_power_notifier);
+out_unregister_rn:
+	unregister_reboot_notifier(&css_reboot_notifier);
 out_unregister:
 	while (i-- > 0) {
 		struct channel_subsystem *css = channel_subsystems[i];
@@ -1222,6 +1397,10 @@ static int css_bus_match(struct device *dev, struct device_driver *drv)
 	struct css_driver *driver = to_cssdriver(drv);
 	struct css_device_id *id;
 
+	/* When driver_override is set, only bind to the matching driver */
+	if (sch->driver_override && strcmp(sch->driver_override, drv->name))
+		return 0;
+
 	for (id = driver->subchannel_type; id->match_flags; id++) {
 		if (sch->st == id->type)
 			return 1;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 1540229a37bb..9985b7484a6b 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -24,6 +24,7 @@
 #include <linux/timer.h>
 #include <linux/kernel_stat.h>
 #include <linux/sched/signal.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/ccwdev.h>
 #include <asm/cio.h>
@@ -687,6 +688,9 @@ ccw_device_release(struct device *dev)
 	struct ccw_device *cdev;
 
 	cdev = to_ccwdev(dev);
+	cio_gp_dma_free(cdev->private->dma_pool, cdev->private->dma_area,
+			sizeof(*cdev->private->dma_area));
+	cio_gp_dma_destroy(cdev->private->dma_pool, &cdev->dev);
 	/* Release reference of parent subchannel. */
 	put_device(cdev->dev.parent);
 	kfree(cdev->private);
@@ -696,15 +700,33 @@ ccw_device_release(struct device *dev)
 static struct ccw_device * io_subchannel_allocate_dev(struct subchannel *sch)
 {
 	struct ccw_device *cdev;
+	struct gen_pool *dma_pool;
 
 	cdev  = kzalloc(sizeof(*cdev), GFP_KERNEL);
-	if (cdev) {
-		cdev->private = kzalloc(sizeof(struct ccw_device_private),
-					GFP_KERNEL | GFP_DMA);
-		if (cdev->private)
-			return cdev;
-	}
+	if (!cdev)
+		goto err_cdev;
+	cdev->private = kzalloc(sizeof(struct ccw_device_private),
+				GFP_KERNEL | GFP_DMA);
+	if (!cdev->private)
+		goto err_priv;
+	cdev->dev.coherent_dma_mask = sch->dev.coherent_dma_mask;
+	cdev->dev.dma_mask = &cdev->dev.coherent_dma_mask;
+	dma_pool = cio_gp_dma_create(&cdev->dev, 1);
+	if (!dma_pool)
+		goto err_dma_pool;
+	cdev->private->dma_pool = dma_pool;
+	cdev->private->dma_area = cio_gp_dma_zalloc(dma_pool, &cdev->dev,
+					sizeof(*cdev->private->dma_area));
+	if (!cdev->private->dma_area)
+		goto err_dma_area;
+	return cdev;
+err_dma_area:
+	cio_gp_dma_destroy(dma_pool, &cdev->dev);
+err_dma_pool:
+	kfree(cdev->private);
+err_priv:
 	kfree(cdev);
+err_cdev:
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -884,7 +906,7 @@ io_subchannel_recog_done(struct ccw_device *cdev)
 			wake_up(&ccw_device_init_wq);
 		break;
 	case DEV_STATE_OFFLINE:
-		/* 
+		/*
 		 * We can't register the device in interrupt context so
 		 * we schedule a work item.
 		 */
@@ -1062,6 +1084,14 @@ static int io_subchannel_probe(struct subchannel *sch)
 	if (!io_priv)
 		goto out_schedule;
 
+	io_priv->dma_area = dma_alloc_coherent(&sch->dev,
+				sizeof(*io_priv->dma_area),
+				&io_priv->dma_area_dma, GFP_KERNEL);
+	if (!io_priv->dma_area) {
+		kfree(io_priv);
+		goto out_schedule;
+	}
+
 	set_io_private(sch, io_priv);
 	css_schedule_eval(sch->schid);
 	return 0;
@@ -1088,6 +1118,8 @@ static int io_subchannel_remove(struct subchannel *sch)
 	set_io_private(sch, NULL);
 	spin_unlock_irq(sch->lock);
 out_free:
+	dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area),
+			  io_priv->dma_area, io_priv->dma_area_dma);
 	kfree(io_priv);
 	sysfs_remove_group(&sch->dev.kobj, &io_subchannel_attr_group);
 	return 0;
@@ -1593,13 +1625,19 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 		return ERR_CAST(sch);
 
 	io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA);
-	if (!io_priv) {
-		put_device(&sch->dev);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!io_priv)
+		goto err_priv;
+	io_priv->dma_area = dma_alloc_coherent(&sch->dev,
+				sizeof(*io_priv->dma_area),
+				&io_priv->dma_area_dma, GFP_KERNEL);
+	if (!io_priv->dma_area)
+		goto err_dma_area;
 	set_io_private(sch, io_priv);
 	cdev = io_subchannel_create_ccwdev(sch);
 	if (IS_ERR(cdev)) {
+		dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area),
+				  io_priv->dma_area, io_priv->dma_area_dma);
+		set_io_private(sch, NULL);
 		put_device(&sch->dev);
 		kfree(io_priv);
 		return cdev;
@@ -1607,6 +1645,12 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 	cdev->drv = drv;
 	ccw_device_set_int_class(cdev);
 	return cdev;
+
+err_dma_area:
+	kfree(io_priv);
+err_priv:
+	put_device(&sch->dev);
+	return ERR_PTR(-ENOMEM);
 }
 
 void __init ccw_device_destroy_console(struct ccw_device *cdev)
@@ -1617,6 +1661,8 @@ void __init ccw_device_destroy_console(struct ccw_device *cdev)
 	set_io_private(sch, NULL);
 	put_device(&sch->dev);
 	put_device(&cdev->dev);
+	dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area),
+			  io_priv->dma_area, io_priv->dma_area_dma);
 	kfree(io_priv);
 }
 
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 9169af7dbb43..8fc267324ebb 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -67,8 +67,10 @@ static void ccw_timeout_log(struct ccw_device *cdev)
 			       sizeof(struct tcw), 0);
 	} else {
 		printk(KERN_WARNING "cio: orb indicates command mode\n");
-		if ((void *)(addr_t)orb->cmd.cpa == &private->sense_ccw ||
-		    (void *)(addr_t)orb->cmd.cpa == cdev->private->iccws)
+		if ((void *)(addr_t)orb->cmd.cpa ==
+		    &private->dma_area->sense_ccw ||
+		    (void *)(addr_t)orb->cmd.cpa ==
+		    cdev->private->dma_area->iccws)
 			printk(KERN_WARNING "cio: last channel program "
 			       "(intern):\n");
 		else
@@ -143,18 +145,22 @@ ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 void ccw_device_update_sense_data(struct ccw_device *cdev)
 {
 	memset(&cdev->id, 0, sizeof(cdev->id));
-	cdev->id.cu_type   = cdev->private->senseid.cu_type;
-	cdev->id.cu_model  = cdev->private->senseid.cu_model;
-	cdev->id.dev_type  = cdev->private->senseid.dev_type;
-	cdev->id.dev_model = cdev->private->senseid.dev_model;
+	cdev->id.cu_type = cdev->private->dma_area->senseid.cu_type;
+	cdev->id.cu_model = cdev->private->dma_area->senseid.cu_model;
+	cdev->id.dev_type = cdev->private->dma_area->senseid.dev_type;
+	cdev->id.dev_model = cdev->private->dma_area->senseid.dev_model;
 }
 
 int ccw_device_test_sense_data(struct ccw_device *cdev)
 {
-	return cdev->id.cu_type == cdev->private->senseid.cu_type &&
-		cdev->id.cu_model == cdev->private->senseid.cu_model &&
-		cdev->id.dev_type == cdev->private->senseid.dev_type &&
-		cdev->id.dev_model == cdev->private->senseid.dev_model;
+	return cdev->id.cu_type ==
+		cdev->private->dma_area->senseid.cu_type &&
+		cdev->id.cu_model ==
+		cdev->private->dma_area->senseid.cu_model &&
+		cdev->id.dev_type ==
+		cdev->private->dma_area->senseid.dev_type &&
+		cdev->id.dev_model ==
+		cdev->private->dma_area->senseid.dev_model;
 }
 
 /*
@@ -342,7 +348,7 @@ ccw_device_done(struct ccw_device *cdev, int state)
 		cio_disable_subchannel(sch);
 
 	/* Reset device status. */
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 
 	cdev->private->state = state;
 
@@ -509,13 +515,14 @@ callback:
 		ccw_device_done(cdev, DEV_STATE_ONLINE);
 		/* Deliver fake irb to device driver, if needed. */
 		if (cdev->private->flags.fake_irb) {
-			create_fake_irb(&cdev->private->irb,
+			create_fake_irb(&cdev->private->dma_area->irb,
 					cdev->private->flags.fake_irb);
 			cdev->private->flags.fake_irb = 0;
 			if (cdev->handler)
 				cdev->handler(cdev, cdev->private->intparm,
-					      &cdev->private->irb);
-			memset(&cdev->private->irb, 0, sizeof(struct irb));
+					      &cdev->private->dma_area->irb);
+			memset(&cdev->private->dma_area->irb, 0,
+			       sizeof(struct irb));
 		}
 		ccw_device_report_path_events(cdev);
 		ccw_device_handle_broken_paths(cdev);
@@ -672,7 +679,8 @@ ccw_device_online_verify(struct ccw_device *cdev, enum dev_event dev_event)
 
 	if (scsw_actl(&sch->schib.scsw) != 0 ||
 	    (scsw_stctl(&sch->schib.scsw) & SCSW_STCTL_STATUS_PEND) ||
-	    (scsw_stctl(&cdev->private->irb.scsw) & SCSW_STCTL_STATUS_PEND)) {
+	    (scsw_stctl(&cdev->private->dma_area->irb.scsw) &
+	     SCSW_STCTL_STATUS_PEND)) {
 		/*
 		 * No final status yet or final status not yet delivered
 		 * to the device driver. Can't do path verification now,
@@ -719,7 +727,7 @@ static int ccw_device_call_handler(struct ccw_device *cdev)
 	 *  - fast notification was requested (primary status)
 	 *  - unsolicited interrupts
 	 */
-	stctl = scsw_stctl(&cdev->private->irb.scsw);
+	stctl = scsw_stctl(&cdev->private->dma_area->irb.scsw);
 	ending_status = (stctl & SCSW_STCTL_SEC_STATUS) ||
 		(stctl == (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND)) ||
 		(stctl == SCSW_STCTL_STATUS_PEND);
@@ -735,9 +743,9 @@ static int ccw_device_call_handler(struct ccw_device *cdev)
 
 	if (cdev->handler)
 		cdev->handler(cdev, cdev->private->intparm,
-			      &cdev->private->irb);
+			      &cdev->private->dma_area->irb);
 
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 	return 1;
 }
 
@@ -759,7 +767,8 @@ ccw_device_irq(struct ccw_device *cdev, enum dev_event dev_event)
 			/* Unit check but no sense data. Need basic sense. */
 			if (ccw_device_do_sense(cdev, irb) != 0)
 				goto call_handler_unsol;
-			memcpy(&cdev->private->irb, irb, sizeof(struct irb));
+			memcpy(&cdev->private->dma_area->irb, irb,
+			       sizeof(struct irb));
 			cdev->private->state = DEV_STATE_W4SENSE;
 			cdev->private->intparm = 0;
 			return;
@@ -842,7 +851,7 @@ ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event)
 	if (scsw_fctl(&irb->scsw) &
 	    (SCSW_FCTL_CLEAR_FUNC | SCSW_FCTL_HALT_FUNC)) {
 		cdev->private->flags.dosense = 0;
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 		ccw_device_accumulate_irb(cdev, irb);
 		goto call_handler;
 	}
diff --git a/drivers/s390/cio/device_id.c b/drivers/s390/cio/device_id.c
index f6df83a9dfbb..740996d0dc8c 100644
--- a/drivers/s390/cio/device_id.c
+++ b/drivers/s390/cio/device_id.c
@@ -99,7 +99,7 @@ static int diag210_to_senseid(struct senseid *senseid, struct diag210 *diag)
 static int diag210_get_dev_info(struct ccw_device *cdev)
 {
 	struct ccw_dev_id *dev_id = &cdev->private->dev_id;
-	struct senseid *senseid = &cdev->private->senseid;
+	struct senseid *senseid = &cdev->private->dma_area->senseid;
 	struct diag210 diag_data;
 	int rc;
 
@@ -134,8 +134,10 @@ err_failed:
 static void snsid_init(struct ccw_device *cdev)
 {
 	cdev->private->flags.esid = 0;
-	memset(&cdev->private->senseid, 0, sizeof(cdev->private->senseid));
-	cdev->private->senseid.cu_type = 0xffff;
+
+	memset(&cdev->private->dma_area->senseid, 0,
+	       sizeof(cdev->private->dma_area->senseid));
+	cdev->private->dma_area->senseid.cu_type = 0xffff;
 }
 
 /*
@@ -143,16 +145,16 @@ static void snsid_init(struct ccw_device *cdev)
  */
 static int snsid_check(struct ccw_device *cdev, void *data)
 {
-	struct cmd_scsw *scsw = &cdev->private->irb.scsw.cmd;
+	struct cmd_scsw *scsw = &cdev->private->dma_area->irb.scsw.cmd;
 	int len = sizeof(struct senseid) - scsw->count;
 
 	/* Check for incomplete SENSE ID data. */
 	if (len < SENSE_ID_MIN_LEN)
 		goto out_restart;
-	if (cdev->private->senseid.cu_type == 0xffff)
+	if (cdev->private->dma_area->senseid.cu_type == 0xffff)
 		goto out_restart;
 	/* Check for incompatible SENSE ID data. */
-	if (cdev->private->senseid.reserved != 0xff)
+	if (cdev->private->dma_area->senseid.reserved != 0xff)
 		return -EOPNOTSUPP;
 	/* Check for extended-identification information. */
 	if (len > SENSE_ID_BASIC_LEN)
@@ -170,7 +172,7 @@ out_restart:
 static void snsid_callback(struct ccw_device *cdev, void *data, int rc)
 {
 	struct ccw_dev_id *id = &cdev->private->dev_id;
-	struct senseid *senseid = &cdev->private->senseid;
+	struct senseid *senseid = &cdev->private->dma_area->senseid;
 	int vm = 0;
 
 	if (rc && MACHINE_IS_VM) {
@@ -200,7 +202,7 @@ void ccw_device_sense_id_start(struct ccw_device *cdev)
 {
 	struct subchannel *sch = to_subchannel(cdev->dev.parent);
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	CIO_TRACE_EVENT(4, "snsid");
 	CIO_HEX_EVENT(4, &cdev->private->dev_id, sizeof(cdev->private->dev_id));
@@ -208,7 +210,7 @@ void ccw_device_sense_id_start(struct ccw_device *cdev)
 	snsid_init(cdev);
 	/* Channel program setup. */
 	cp->cmd_code	= CCW_CMD_SENSE_ID;
-	cp->cda		= (u32) (addr_t) &cdev->private->senseid;
+	cp->cda		= (u32) (addr_t) &cdev->private->dma_area->senseid;
 	cp->count	= sizeof(struct senseid);
 	cp->flags	= CCW_FLAG_SLI;
 	/* Request setup. */
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index 4435ae0b3027..d722458c5928 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -429,8 +429,8 @@ struct ciw *ccw_device_get_ciw(struct ccw_device *cdev, __u32 ct)
 	if (cdev->private->flags.esid == 0)
 		return NULL;
 	for (ciw_cnt = 0; ciw_cnt < MAX_CIWS; ciw_cnt++)
-		if (cdev->private->senseid.ciw[ciw_cnt].ct == ct)
-			return cdev->private->senseid.ciw + ciw_cnt;
+		if (cdev->private->dma_area->senseid.ciw[ciw_cnt].ct == ct)
+			return cdev->private->dma_area->senseid.ciw + ciw_cnt;
 	return NULL;
 }
 
@@ -699,6 +699,23 @@ void ccw_device_get_schid(struct ccw_device *cdev, struct subchannel_id *schid)
 }
 EXPORT_SYMBOL_GPL(ccw_device_get_schid);
 
+/*
+ * Allocate zeroed dma coherent 31 bit addressable memory using
+ * the subchannels dma pool. Maximal size of allocation supported
+ * is PAGE_SIZE.
+ */
+void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size)
+{
+	return cio_gp_dma_zalloc(cdev->private->dma_pool, &cdev->dev, size);
+}
+EXPORT_SYMBOL(ccw_device_dma_zalloc);
+
+void ccw_device_dma_free(struct ccw_device *cdev, void *cpu_addr, size_t size)
+{
+	cio_gp_dma_free(cdev->private->dma_pool, cpu_addr, size);
+}
+EXPORT_SYMBOL(ccw_device_dma_free);
+
 EXPORT_SYMBOL(ccw_device_set_options_mask);
 EXPORT_SYMBOL(ccw_device_set_options);
 EXPORT_SYMBOL(ccw_device_clear_options);
diff --git a/drivers/s390/cio/device_pgid.c b/drivers/s390/cio/device_pgid.c
index d30a3babf176..767a85635a0f 100644
--- a/drivers/s390/cio/device_pgid.c
+++ b/drivers/s390/cio/device_pgid.c
@@ -57,7 +57,7 @@ out:
 static void nop_build_cp(struct ccw_device *cdev)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	cp->cmd_code	= CCW_CMD_NOOP;
 	cp->cda		= 0;
@@ -134,9 +134,9 @@ err:
 static void spid_build_cp(struct ccw_device *cdev, u8 fn)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 	int i = pathmask_to_pos(req->lpm);
-	struct pgid *pgid = &cdev->private->pgid[i];
+	struct pgid *pgid = &cdev->private->dma_area->pgid[i];
 
 	pgid->inf.fc	= fn;
 	cp->cmd_code	= CCW_CMD_SET_PGID;
@@ -300,7 +300,7 @@ static int pgid_cmp(struct pgid *p1, struct pgid *p2)
 static void pgid_analyze(struct ccw_device *cdev, struct pgid **p,
 			 int *mismatch, u8 *reserved, u8 *reset)
 {
-	struct pgid *pgid = &cdev->private->pgid[0];
+	struct pgid *pgid = &cdev->private->dma_area->pgid[0];
 	struct pgid *first = NULL;
 	int lpm;
 	int i;
@@ -342,7 +342,7 @@ static u8 pgid_to_donepm(struct ccw_device *cdev)
 		lpm = 0x80 >> i;
 		if ((cdev->private->pgid_valid_mask & lpm) == 0)
 			continue;
-		pgid = &cdev->private->pgid[i];
+		pgid = &cdev->private->dma_area->pgid[i];
 		if (sch->opm & lpm) {
 			if (pgid->inf.ps.state1 != SNID_STATE1_GROUPED)
 				continue;
@@ -368,7 +368,8 @@ static void pgid_fill(struct ccw_device *cdev, struct pgid *pgid)
 	int i;
 
 	for (i = 0; i < 8; i++)
-		memcpy(&cdev->private->pgid[i], pgid, sizeof(struct pgid));
+		memcpy(&cdev->private->dma_area->pgid[i], pgid,
+		       sizeof(struct pgid));
 }
 
 /*
@@ -435,12 +436,12 @@ out:
 static void snid_build_cp(struct ccw_device *cdev)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 	int i = pathmask_to_pos(req->lpm);
 
 	/* Channel program setup. */
 	cp->cmd_code	= CCW_CMD_SENSE_PGID;
-	cp->cda		= (u32) (addr_t) &cdev->private->pgid[i];
+	cp->cda		= (u32) (addr_t) &cdev->private->dma_area->pgid[i];
 	cp->count	= sizeof(struct pgid);
 	cp->flags	= CCW_FLAG_SLI;
 	req->cp		= cp;
@@ -516,7 +517,8 @@ static void verify_start(struct ccw_device *cdev)
 	sch->lpm = sch->schib.pmcw.pam;
 
 	/* Initialize PGID data. */
-	memset(cdev->private->pgid, 0, sizeof(cdev->private->pgid));
+	memset(cdev->private->dma_area->pgid, 0,
+	       sizeof(cdev->private->dma_area->pgid));
 	cdev->private->pgid_valid_mask = 0;
 	cdev->private->pgid_todo_mask = sch->schib.pmcw.pam;
 	cdev->private->path_notoper_mask = 0;
@@ -626,7 +628,7 @@ struct stlck_data {
 static void stlck_build_cp(struct ccw_device *cdev, void *buf1, void *buf2)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	cp[0].cmd_code = CCW_CMD_STLCK;
 	cp[0].cda = (u32) (addr_t) buf1;
diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c
index 7d5c7892b2c4..0bd8f2642732 100644
--- a/drivers/s390/cio/device_status.c
+++ b/drivers/s390/cio/device_status.c
@@ -79,15 +79,15 @@ ccw_device_accumulate_ecw(struct ccw_device *cdev, struct irb *irb)
 	 * are condition that have to be met for the extended control
 	 * bit to have meaning. Sick.
 	 */
-	cdev->private->irb.scsw.cmd.ectl = 0;
+	cdev->private->dma_area->irb.scsw.cmd.ectl = 0;
 	if ((irb->scsw.cmd.stctl & SCSW_STCTL_ALERT_STATUS) &&
 	    !(irb->scsw.cmd.stctl & SCSW_STCTL_INTER_STATUS))
-		cdev->private->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl;
+		cdev->private->dma_area->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl;
 	/* Check if extended control word is valid. */
-	if (!cdev->private->irb.scsw.cmd.ectl)
+	if (!cdev->private->dma_area->irb.scsw.cmd.ectl)
 		return;
 	/* Copy concurrent sense / model dependent information. */
-	memcpy (&cdev->private->irb.ecw, irb->ecw, sizeof (irb->ecw));
+	memcpy(&cdev->private->dma_area->irb.ecw, irb->ecw, sizeof(irb->ecw));
 }
 
 /*
@@ -118,7 +118,7 @@ ccw_device_accumulate_esw(struct ccw_device *cdev, struct irb *irb)
 	if (!ccw_device_accumulate_esw_valid(irb))
 		return;
 
-	cdev_irb = &cdev->private->irb;
+	cdev_irb = &cdev->private->dma_area->irb;
 
 	/* Copy last path used mask. */
 	cdev_irb->esw.esw1.lpum = irb->esw.esw1.lpum;
@@ -210,7 +210,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 		ccw_device_path_notoper(cdev);
 	/* No irb accumulation for transport mode irbs. */
 	if (scsw_is_tm(&irb->scsw)) {
-		memcpy(&cdev->private->irb, irb, sizeof(struct irb));
+		memcpy(&cdev->private->dma_area->irb, irb, sizeof(struct irb));
 		return;
 	}
 	/*
@@ -219,7 +219,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 	if (!scsw_is_solicited(&irb->scsw))
 		return;
 
-	cdev_irb = &cdev->private->irb;
+	cdev_irb = &cdev->private->dma_area->irb;
 
 	/*
 	 * If the clear function had been performed, all formerly pending
@@ -227,7 +227,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 	 * intermediate accumulated status to the device driver.
 	 */
 	if (irb->scsw.cmd.fctl & SCSW_FCTL_CLEAR_FUNC)
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 
 	/* Copy bits which are valid only for the start function. */
 	if (irb->scsw.cmd.fctl & SCSW_FCTL_START_FUNC) {
@@ -329,9 +329,9 @@ ccw_device_do_sense(struct ccw_device *cdev, struct irb *irb)
 	/*
 	 * We have ending status but no sense information. Do a basic sense.
 	 */
-	sense_ccw = &to_io_private(sch)->sense_ccw;
+	sense_ccw = &to_io_private(sch)->dma_area->sense_ccw;
 	sense_ccw->cmd_code = CCW_CMD_BASIC_SENSE;
-	sense_ccw->cda = (__u32) __pa(cdev->private->irb.ecw);
+	sense_ccw->cda = (__u32) __pa(cdev->private->dma_area->irb.ecw);
 	sense_ccw->count = SENSE_MAX_COUNT;
 	sense_ccw->flags = CCW_FLAG_SLI;
 
@@ -364,7 +364,7 @@ ccw_device_accumulate_basic_sense(struct ccw_device *cdev, struct irb *irb)
 
 	if (!(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK) &&
 	    (irb->scsw.cmd.dstat & DEV_STAT_CHN_END)) {
-		cdev->private->irb.esw.esw0.erw.cons = 1;
+		cdev->private->dma_area->irb.esw.esw0.erw.cons = 1;
 		cdev->private->flags.dosense = 0;
 	}
 	/* Check if path verification is required. */
@@ -386,7 +386,7 @@ ccw_device_accumulate_and_sense(struct ccw_device *cdev, struct irb *irb)
 	/* Check for basic sense. */
 	if (cdev->private->flags.dosense &&
 	    !(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK)) {
-		cdev->private->irb.esw.esw0.erw.cons = 1;
+		cdev->private->dma_area->irb.esw.esw0.erw.cons = 1;
 		cdev->private->flags.dosense = 0;
 		return 0;
 	}
diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
index 90e4e3a7841b..c03b4a19974e 100644
--- a/drivers/s390/cio/io_sch.h
+++ b/drivers/s390/cio/io_sch.h
@@ -9,15 +9,20 @@
 #include "css.h"
 #include "orb.h"
 
+struct io_subchannel_dma_area {
+	struct ccw1 sense_ccw;	/* static ccw for sense command */
+};
+
 struct io_subchannel_private {
 	union orb orb;		/* operation request block */
-	struct ccw1 sense_ccw;	/* static ccw for sense command */
 	struct ccw_device *cdev;/* pointer to the child ccw device */
 	struct {
 		unsigned int suspend:1;	/* allow suspend */
 		unsigned int prefetch:1;/* deny prefetch */
 		unsigned int inter:1;	/* suppress intermediate interrupts */
 	} __packed options;
+	struct io_subchannel_dma_area *dma_area;
+	dma_addr_t dma_area_dma;
 } __aligned(8);
 
 #define to_io_private(n) ((struct io_subchannel_private *) \
@@ -115,6 +120,13 @@ enum cdev_todo {
 #define FAKE_CMD_IRB	1
 #define FAKE_TM_IRB	2
 
+struct ccw_device_dma_area {
+	struct senseid senseid;	/* SenseID info */
+	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
+	struct irb irb;		/* device status */
+	struct pgid pgid[8];	/* path group IDs per chpid*/
+};
+
 struct ccw_device_private {
 	struct ccw_device *cdev;
 	struct subchannel *sch;
@@ -156,11 +168,7 @@ struct ccw_device_private {
 	} __attribute__((packed)) flags;
 	unsigned long intparm;	/* user interruption parameter */
 	struct qdio_irq *qdio_data;
-	struct irb irb;		/* device status */
 	int async_kill_io_rc;
-	struct senseid senseid;	/* SenseID info */
-	struct pgid pgid[8];	/* path group IDs per chpid*/
-	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
 	struct work_struct todo_work;
 	enum cdev_todo todo;
 	wait_queue_head_t wait_q;
@@ -169,6 +177,8 @@ struct ccw_device_private {
 	struct list_head cmb_list;	/* list of measured devices */
 	u64 cmb_start_time;		/* clock value of cmb reset */
 	void *cmb_wait;			/* deferred cmb enable/disable */
+	struct gen_pool *dma_pool;
+	struct ccw_device_dma_area *dma_area;
 	enum interruption_class int_class;
 };
 
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 7b7620de2acd..730c4e68094b 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -736,6 +736,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 
 	switch (state) {
 	case SLSB_P_OUTPUT_EMPTY:
+	case SLSB_P_OUTPUT_PENDING:
 		/* the adapter got it */
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr,
 			"out empty:%1d %02x", q->nr, count);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 99d7d2566a3a..d4101cecdc8d 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -150,6 +150,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
 			return -ENOMEM;
 		}
 		irq_ptr_qs[i] = q;
+		INIT_LIST_HEAD(&q->entry);
 	}
 	return 0;
 }
@@ -178,6 +179,7 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	q->mask = 1 << (31 - i);
 	q->nr = i;
 	q->handler = handler;
+	INIT_LIST_HEAD(&q->entry);
 }
 
 static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 28d59ac2204c..93ee067c10ca 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -79,7 +79,6 @@ void tiqdio_add_input_queues(struct qdio_irq *irq_ptr)
 	mutex_lock(&tiq_list_lock);
 	list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list);
 	mutex_unlock(&tiq_list_lock);
-	xchg(irq_ptr->dsci, 1 << 7);
 }
 
 void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
@@ -87,14 +86,14 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 	struct qdio_q *q;
 
 	q = irq_ptr->input_qs[0];
-	/* if establish triggered an error */
-	if (!q || !q->entry.prev || !q->entry.next)
+	if (!q)
 		return;
 
 	mutex_lock(&tiq_list_lock);
 	list_del_rcu(&q->entry);
 	mutex_unlock(&tiq_list_lock);
 	synchronize_rcu();
+	INIT_LIST_HEAD(&q->entry);
 }
 
 static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr)
@@ -178,6 +177,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 /**
  * tiqdio_thinint_handler - thin interrupt handler for qdio
  * @airq: pointer to adapter interrupt descriptor
+ * @floating: flag to recognize floating vs. directed interrupts (unused)
  */
 static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 {
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 0e79799e9a71..1d4c893ead23 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -16,12 +16,6 @@
 
 #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 {
 	/* Starting guest physical I/O address. */
 	unsigned long		pa_iova;
@@ -33,11 +27,6 @@ struct pfn_array {
 	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;
@@ -46,35 +35,29 @@ struct ccwchain {
 	/* Count of the valid ccws in chain. */
 	int			ch_len;
 	/* Pinned PAGEs for the original data. */
-	struct pfn_array_table	*ch_pat;
+	struct pfn_array	*ch_pa;
 };
 
 /*
- * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory
+ * pfn_array_alloc() - alloc memory for PFNs
  * @pa: pfn_array on which to perform the operation
- * @mdev: the mediated device to perform pin/unpin operations
  * @iova: target guest physical address
  * @len: number of bytes that should be pinned from @iova
  *
- * Attempt to allocate memory for PFNs, and pin user pages in memory.
+ * Attempt to allocate memory for PFNs.
  *
  * Usage of pfn_array:
  * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in
  * this structure will be filled in by this function.
  *
  * Returns:
- *   Number of pages pinned on success.
- *   If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially,
- *   returns -EINVAL.
- *   If no pages were pinned, returns -errno.
+ *         0 if PFNs are allocated
+ *   -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova_pfn is not NULL
+ *   -ENOMEM if alloc failed
  */
-static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
-			       u64 iova, unsigned int len)
+static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
 {
-	int i, ret = 0;
-
-	if (!len)
-		return 0;
+	int i;
 
 	if (pa->pa_nr || pa->pa_iova_pfn)
 		return -EINVAL;
@@ -94,8 +77,27 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
 
 	pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
-	for (i = 1; i < pa->pa_nr; i++)
+	pa->pa_pfn[0] = -1ULL;
+	for (i = 1; i < pa->pa_nr; i++) {
 		pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
+		pa->pa_pfn[i] = -1ULL;
+	}
+
+	return 0;
+}
+
+/*
+ * pfn_array_pin() - Pin user pages in memory
+ * @pa: pfn_array on which to perform the operation
+ * @mdev: the mediated device to perform pin operations
+ *
+ * Returns number of pages pinned upon success.
+ * If the pin request partially succeeds, or fails completely,
+ * all pages are left unpinned and a negative error value is returned.
+ */
+static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+{
+	int ret = 0;
 
 	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
 			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
@@ -112,8 +114,6 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 
 err_out:
 	pa->pa_nr = 0;
-	kfree(pa->pa_iova_pfn);
-	pa->pa_iova_pfn = NULL;
 
 	return ret;
 }
@@ -121,60 +121,30 @@ err_out:
 /* 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);
+	/* Only unpin if any pages were pinned to begin with */
+	if (pa->pa_nr)
+		vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
 	pa->pa_nr = 0;
 	kfree(pa->pa_iova_pfn);
 }
 
-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)
+static bool pfn_array_iova_pinned(struct pfn_array *pa, unsigned long iova)
 {
-	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;
+	int i;
 
-	for (i = 0; i < pat->pat_nr; i++, pa++)
-		for (j = 0; j < pa->pa_nr; j++)
-			if (pa->pa_iova_pfn[j] == iova_pfn)
-				return true;
+	for (i = 0; i < pa->pa_nr; i++)
+		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,
+/* Create the list of IDAL words for a pfn_array. */
+static inline void pfn_array_idal_create_words(
+	struct pfn_array *pa,
 	unsigned long *idaws)
 {
-	struct pfn_array *pa;
-	int i, j, k;
+	int i;
 
 	/*
 	 * Idal words (execept the first one) rely on the memory being 4k
@@ -183,19 +153,36 @@ static inline void pfn_array_table_idal_create_words(
 	 * 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++;
+
+	for (i = 0; i < pa->pa_nr; i++)
+		idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT;
+
+	/* Adjust the first IDAW, since it may not start on a page boundary */
+	idaws[0] += pa->pa_iova & (PAGE_SIZE - 1);
+}
+
+static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
+{
+	struct ccw0 ccw0;
+	struct ccw1 *pccw1 = source;
+	int i;
+
+	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++;
 	}
 }
 
-
 /*
  * Within the domain (@mdev), copy @n bytes from a guest physical
  * address (@iova) to a host physical address (@to).
@@ -209,9 +196,15 @@ static long copy_from_iova(struct device *mdev,
 	int i, ret;
 	unsigned long l, m;
 
-	ret = pfn_array_alloc_pin(&pa, mdev, iova, n);
-	if (ret <= 0)
+	ret = pfn_array_alloc(&pa, iova, n);
+	if (ret < 0)
+		return ret;
+
+	ret = pfn_array_pin(&pa, mdev);
+	if (ret < 0) {
+		pfn_array_unpin_free(&pa, mdev);
 		return ret;
+	}
 
 	l = n;
 	for (i = 0; i < pa.pa_nr; i++) {
@@ -235,55 +228,60 @@ static long copy_from_iova(struct device *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_read(_ccw) (((_ccw)->cmd_code & 0x03) == 0x02)
+#define ccw_is_read_backward(_ccw) (((_ccw)->cmd_code & 0x0F) == 0x0C)
+#define ccw_is_sense(_ccw) (((_ccw)->cmd_code & 0x0F) == CCW_CMD_BASIC_SENSE)
 
 #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_skip(_ccw) ((_ccw)->flags & CCW_FLAG_SKIP)
 
 #define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC))
 
 /*
+ * ccw_does_data_transfer()
+ *
+ * Determine whether a CCW will move any data, such that the guest pages
+ * would need to be pinned before performing the I/O.
+ *
+ * Returns 1 if yes, 0 if no.
+ */
+static inline int ccw_does_data_transfer(struct ccw1 *ccw)
+{
+	/* If the count field is zero, then no data will be transferred */
+	if (ccw->count == 0)
+		return 0;
+
+	/* If the command is a NOP, then no data will be transferred */
+	if (ccw_is_noop(ccw))
+		return 0;
+
+	/* If the skip flag is off, then data will be transferred */
+	if (!ccw_is_skip(ccw))
+		return 1;
+
+	/*
+	 * If the skip flag is on, it is only meaningful if the command
+	 * code is a read, read backward, sense, or sense ID.  In those
+	 * cases, no data will be transferred.
+	 */
+	if (ccw_is_read(ccw) || ccw_is_read_backward(ccw))
+		return 0;
+
+	if (ccw_is_sense(ccw))
+		return 0;
+
+	/* The skip flag is on, but it is ignored for this command code. */
+	return 1;
+}
+
+/*
  * is_cpa_within_range()
  *
  * @cpa: channel program address being questioned
@@ -319,7 +317,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 	/* Make ccw address aligned to 8. */
 	size = ((sizeof(*chain) + 7L) & -8L) +
 		sizeof(*chain->ch_ccw) * len +
-		sizeof(*chain->ch_pat) * len;
+		sizeof(*chain->ch_pa) * len;
 	chain = kzalloc(size, GFP_DMA | GFP_KERNEL);
 	if (!chain)
 		return NULL;
@@ -328,7 +326,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 	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_pa = (struct pfn_array *)data;
 
 	chain->ch_len = len;
 
@@ -348,31 +346,12 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
 {
 	struct ccw1 *ccw = chain->ch_ccw + idx;
 
-	if (ccw_is_test(ccw) || ccw_is_noop(ccw) || ccw_is_tic(ccw))
-		return;
-	if (!ccw->count)
+	if (ccw_is_tic(ccw))
 		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;
-
-	cp->initialized = false;
-	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
@@ -388,25 +367,9 @@ static void cp_unpin_free(struct channel_program *cp)
  */
 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;
-	}
+	struct ccw1 *ccw = cp->guest_cp;
+	int cnt = 0;
 
-	cnt = 0;
 	do {
 		cnt++;
 
@@ -415,10 +378,8 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 		 * orb specified one of the unsupported formats, we defer
 		 * checking for IDAWs in unsupported formats to here.
 		 */
-		if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) {
-			kfree(p);
+		if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw))
 			return -EOPNOTSUPP;
-		}
 
 		/*
 		 * We want to keep counting if the current CCW has the
@@ -437,7 +398,6 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 	if (cnt == CCWCHAIN_LEN_MAX + 1)
 		cnt = -EINVAL;
 
-	kfree(p);
 	return cnt;
 }
 
@@ -458,17 +418,23 @@ static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
 static int ccwchain_loop_tic(struct ccwchain *chain,
 			     struct channel_program *cp);
 
-static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp)
+static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
 {
 	struct ccwchain *chain;
-	int len, ret;
+	int len;
 
-	/* May transfer to an existing chain. */
-	if (tic_target_chain_exists(tic, cp))
-		return 0;
+	/* Copy 2K (the most we support today) of possible CCWs */
+	len = copy_from_iova(cp->mdev, cp->guest_cp, cda,
+			     CCWCHAIN_LEN_MAX * sizeof(struct ccw1));
+	if (len)
+		return len;
 
-	/* Get chain length. */
-	len = ccwchain_calc_length(tic->cda, cp);
+	/* Convert any Format-0 CCWs to Format-1 */
+	if (!cp->orb.cmd.fmt)
+		convert_ccw0_to_ccw1(cp->guest_cp, CCWCHAIN_LEN_MAX);
+
+	/* Count the CCWs in the current chain */
+	len = ccwchain_calc_length(cda, cp);
 	if (len < 0)
 		return len;
 
@@ -476,14 +442,10 @@ static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp)
 	chain = ccwchain_alloc(cp, len);
 	if (!chain)
 		return -ENOMEM;
-	chain->ch_iova = tic->cda;
+	chain->ch_iova = 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;
-	}
+	/* Copy the actual CCWs into the new chain */
+	memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1));
 
 	/* Loop for tics on this new chain. */
 	return ccwchain_loop_tic(chain, cp);
@@ -501,7 +463,12 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
 		if (!ccw_is_tic(tic))
 			continue;
 
-		ret = ccwchain_handle_tic(tic, cp);
+		/* May transfer to an existing chain. */
+		if (tic_target_chain_exists(tic, cp))
+			continue;
+
+		/* Build a ccwchain for the next segment */
+		ret = ccwchain_handle_ccw(tic->cda, cp);
 		if (ret)
 			return ret;
 	}
@@ -534,115 +501,90 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 				 struct channel_program *cp)
 {
 	struct ccw1 *ccw;
-	struct pfn_array_table *pat;
+	struct pfn_array *pa;
+	u64 iova;
 	unsigned long *idaws;
 	int ret;
+	int bytes = 1;
+	int idaw_nr, idal_len;
+	int i;
 
 	ccw = chain->ch_ccw + idx;
 
-	if (!ccw->count) {
-		/*
-		 * We just want the translation result of any direct ccw
-		 * to be an IDA ccw, so let's add the IDA flag for it.
-		 * Although the flag will be ignored by firmware.
-		 */
-		ccw->flags |= CCW_FLAG_IDA;
-		return 0;
-	}
-
-	/*
-	 * 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;
-	ret = pfn_array_table_init(pat, 1);
-	if (ret)
-		goto out_init;
-
-	ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count);
-	if (ret < 0)
-		goto out_unpin;
+	if (ccw->count)
+		bytes = ccw->count;
 
-	/* Translate this direct ccw to a idal ccw. */
-	idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
-	if (!idaws) {
-		ret = -ENOMEM;
-		goto out_unpin;
+	/* Calculate size of IDAL */
+	if (ccw_is_idal(ccw)) {
+		/* Read first IDAW to see if it's 4K-aligned or not. */
+		/* All subsequent IDAws will be 4K-aligned. */
+		ret = copy_from_iova(cp->mdev, &iova, ccw->cda, sizeof(iova));
+		if (ret)
+			return ret;
+	} else {
+		iova = ccw->cda;
 	}
-	ccw->cda = (__u32) virt_to_phys(idaws);
-	ccw->flags |= CCW_FLAG_IDA;
-
-	pfn_array_table_idal_create_words(pat, idaws);
-
-	return 0;
-
-out_unpin:
-	pfn_array_table_unpin_free(pat, cp->mdev);
-out_init:
-	ccw->cda = 0;
-	return ret;
-}
-
-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;
-
-	if (!ccw->count)
-		return 0;
-
-	/* 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)
-		goto out_init;
+	idaw_nr = idal_nr_words((void *)iova, bytes);
+	idal_len = idaw_nr * sizeof(*idaws);
 
-	/* Translate idal ccw to use new allocated idaws. */
-	idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL);
+	/* Allocate an IDAL from host storage */
+	idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
 	if (!idaws) {
 		ret = -ENOMEM;
-		goto out_unpin;
+		goto out_init;
 	}
 
-	ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idaw_len);
-	if (ret)
+	/*
+	 * Allocate an array of pfn's for pages to pin/translate.
+	 * The number of pages is actually the count of the idaws
+	 * required for the data transfer, since we only only support
+	 * 4K IDAWs today.
+	 */
+	pa = chain->ch_pa + idx;
+	ret = pfn_array_alloc(pa, iova, bytes);
+	if (ret < 0)
 		goto out_free_idaws;
 
-	ccw->cda = virt_to_phys(idaws);
+	if (ccw_is_idal(ccw)) {
+		/* Copy guest IDAL into host IDAL */
+		ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idal_len);
+		if (ret)
+			goto out_unpin;
 
-	for (i = 0; i < idaw_nr; i++) {
-		idaw_iova = *(idaws + i);
+		/*
+		 * Copy guest IDAWs into pfn_array, in case the memory they
+		 * occupy is not contiguous.
+		 */
+		for (i = 0; i < idaw_nr; i++)
+			pa->pa_iova_pfn[i] = idaws[i] >> PAGE_SHIFT;
+	} else {
+		/*
+		 * No action is required here; the iova addresses in pfn_array
+		 * were initialized sequentially in pfn_array_alloc() beginning
+		 * with the contents of ccw->cda.
+		 */
+	}
 
-		ret = pfn_array_alloc_pin(pat->pat_pa + i, cp->mdev,
-					  idaw_iova, 1);
+	if (ccw_does_data_transfer(ccw)) {
+		ret = pfn_array_pin(pa, cp->mdev);
 		if (ret < 0)
-			goto out_free_idaws;
+			goto out_unpin;
+	} else {
+		pa->pa_nr = 0;
 	}
 
-	pfn_array_table_idal_create_words(pat, idaws);
+	ccw->cda = (__u32) virt_to_phys(idaws);
+	ccw->flags |= CCW_FLAG_IDA;
+
+	/* Populate the IDAL with pinned/translated addresses from pfn */
+	pfn_array_idal_create_words(pa, idaws);
 
 	return 0;
 
+out_unpin:
+	pfn_array_unpin_free(pa, cp->mdev);
 out_free_idaws:
 	kfree(idaws);
-out_unpin:
-	pfn_array_table_unpin_free(pat, cp->mdev);
 out_init:
 	ccw->cda = 0;
 	return ret;
@@ -660,15 +602,9 @@ static int ccwchain_fetch_one(struct ccwchain *chain,
 {
 	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);
 }
 
@@ -691,9 +627,7 @@ static int ccwchain_fetch_one(struct ccwchain *chain,
  */
 int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 {
-	u64 iova = orb->cmd.cpa;
-	struct ccwchain *chain;
-	int len, ret;
+	int ret;
 
 	/*
 	 * XXX:
@@ -706,28 +640,11 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	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);
+	/* Build a ccwchain for the first CCW segment */
+	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
 	if (ret)
-		cp_unpin_free(cp);
+		cp_free(cp);
+
 	/* It is safe to force: if not set but idals used
 	 * ccwchain_calc_length returns an error.
 	 */
@@ -750,8 +667,20 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
-	if (cp->initialized)
-		cp_unpin_free(cp);
+	struct ccwchain *chain, *temp;
+	int i;
+
+	if (!cp->initialized)
+		return;
+
+	cp->initialized = false;
+	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+		for (i = 0; i < chain->ch_len; i++) {
+			pfn_array_unpin_free(chain->ch_pa + i, cp->mdev);
+			ccwchain_cda_free(chain, i);
+		}
+		ccwchain_free(chain);
+	}
 }
 
 /**
@@ -886,7 +815,11 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 	 */
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		ccw_head = (u32)(u64)chain->ch_ccw;
-		if (is_cpa_within_range(cpa, ccw_head, chain->ch_len)) {
+		/*
+		 * On successful execution, cpa points just beyond the end
+		 * of the chain.
+		 */
+		if (is_cpa_within_range(cpa, ccw_head, chain->ch_len + 1)) {
 			/*
 			 * (cpa - ccw_head) is the offset value of the host
 			 * physical ccw to its chain head.
@@ -919,8 +852,7 @@ bool cp_iova_pinned(struct channel_program *cp, u64 iova)
 
 	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))
+			if (pfn_array_iova_pinned(chain->ch_pa + i, iova))
 				return true;
 	}
 
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index 3c20cd208da5..7cdc38049033 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -16,6 +16,12 @@
 
 #include "orb.h"
 
+/*
+ * Max length for ccw chain.
+ * XXX: Limit to 256, need to check more?
+ */
+#define CCWCHAIN_LEN_MAX	256
+
 /**
  * struct channel_program - manage information for channel program
  * @ccwchain_list: list head of ccwchains
@@ -32,6 +38,7 @@ struct channel_program {
 	union orb orb;
 	struct device *mdev;
 	bool initialized;
+	struct ccw1 *guest_cp;
 };
 
 extern int cp_init(struct channel_program *cp, struct device *mdev,
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 9125f7f4e64c..2b90a5ecaeb9 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -95,11 +95,11 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
 	mutex_unlock(&private->io_mutex);
 
-	if (private->io_trigger)
-		eventfd_signal(private->io_trigger, 1);
-
 	if (private->mdev && is_final)
 		private->state = VFIO_CCW_STATE_IDLE;
+
+	if (private->io_trigger)
+		eventfd_signal(private->io_trigger, 1);
 }
 
 /*
@@ -129,6 +129,11 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 	if (!private)
 		return -ENOMEM;
 
+	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
+				       GFP_KERNEL);
+	if (!private->cp.guest_cp)
+		goto out_free;
+
 	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
 					       GFP_KERNEL | GFP_DMA);
 	if (!private->io_region)
@@ -169,6 +174,7 @@ out_free:
 		kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	if (private->io_region)
 		kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	kfree(private->cp.guest_cp);
 	kfree(private);
 	return ret;
 }
@@ -185,6 +191,7 @@ static int vfio_ccw_sch_remove(struct subchannel *sch)
 
 	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	kfree(private->cp.guest_cp);
 	kfree(private);
 
 	return 0;