Merge tag 'vfio-ccw-20190425' of...

Merge tag 'vfio-ccw-20190425' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/vfio-ccw into features

Pull vfio-ccw from Cornelia Huck with the following changes:

 - support for sending halt/clear requests to the device

 - various bug fixes

drivers/s390/cio/Makefile

@@ -20,5 +20,6 @@ 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
+vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \
+	vfio_ccw_async.o
 obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o

drivers/s390/cio/ioasm.c

@@ -233,6 +233,7 @@ int hsch(struct subchannel_id schid)
 
 	return ccode;
 }
+EXPORT_SYMBOL(hsch);
 
 static inline int __xsch(struct subchannel_id schid)
 {

drivers/s390/cio/vfio_ccw_async.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Async I/O region for vfio_ccw
+ *
+ * Copyright Red Hat, Inc. 2019
+ *
+ * Author(s): Cornelia Huck <cohuck@redhat.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "vfio_ccw_private.h"
+
+static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
+					  char __user *buf, size_t count,
+					  loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->region[i].data;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
+					   const char __user *buf, size_t count,
+					   loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
+	region = private->region[i].data;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_ASYNC_REQ);
+
+	ret = region->ret_code ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static void vfio_ccw_async_region_release(struct vfio_ccw_private *private,
+					  struct vfio_ccw_region *region)
+{
+
+}
+
+const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
+	.read = vfio_ccw_async_region_read,
+	.write = vfio_ccw_async_region_write,
+	.release = vfio_ccw_async_region_release,
+};
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private)
+{
+	return vfio_ccw_register_dev_region(private,
+					    VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD,
+					    &vfio_ccw_async_region_ops,
+					    sizeof(struct ccw_cmd_region),
+					    VFIO_REGION_INFO_FLAG_READ |
+					    VFIO_REGION_INFO_FLAG_WRITE,
+					    private->cmd_region);
+}

drivers/s390/cio/vfio_ccw_cp.c

@@ -362,6 +362,7 @@ 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,
@@ -732,6 +733,9 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	 */
 	cp->orb.cmd.c64 = 1;
 
+	if (!ret)
+		cp->initialized = true;
+
 	return ret;
 }
 
@@ -746,6 +750,7 @@ 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);
 }
 
@@ -791,6 +796,10 @@ int cp_prefetch(struct channel_program *cp)
 	struct ccwchain *chain;
 	int len, idx, ret;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return -EINVAL;
+
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		len = chain->ch_len;
 		for (idx = 0; idx < len; idx++) {
@@ -826,6 +835,10 @@ union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm)
 	struct ccwchain *chain;
 	struct ccw1 *cpa;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return NULL;
+
 	orb = &cp->orb;
 
 	orb->cmd.intparm = intparm;
@@ -862,6 +875,9 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 	u32 cpa = scsw->cmd.cpa;
 	u32 ccw_head;
 
+	if (!cp->initialized)
+		return;
+
 	/*
 	 * LATER:
 	 * For now, only update the cmd.cpa part. We may need to deal with
@@ -898,6 +914,9 @@ bool cp_iova_pinned(struct channel_program *cp, u64 iova)
 	struct ccwchain *chain;
 	int i;
 
+	if (!cp->initialized)
+		return false;
+
 	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,

drivers/s390/cio/vfio_ccw_cp.h

@@ -21,6 +21,7 @@
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @mdev: the mediated device to perform page pinning/unpinning
+ * @initialized: whether this instance is actually initialized
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -30,6 +31,7 @@ struct channel_program {
 	struct list_head ccwchain_list;
 	union orb orb;
 	struct device *mdev;
+	bool initialized;
 };
 
 extern int cp_init(struct channel_program *cp, struct device *mdev,

drivers/s390/cio/vfio_ccw_drv.c

@@ -3,9 +3,11 @@
  * VFIO based Physical Subchannel device driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 
 struct workqueue_struct *vfio_ccw_work_q;
 static struct kmem_cache *vfio_ccw_io_region;
+static struct kmem_cache *vfio_ccw_cmd_region;
 
 /*
  * Helpers
@@ -40,11 +43,17 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 	if (ret != -EBUSY)
 		goto out_unlock;
 
-	do {
 	iretry = 255;
+	do {
 
 		ret = cio_cancel_halt_clear(sch, &iretry);
-		while (ret == -EBUSY) {
+
+		if (ret == -EIO) {
+			pr_err("vfio_ccw: could not quiesce subchannel 0.%x.%04x!\n",
+			       sch->schid.ssid, sch->schid.sch_no);
+			break;
+		}
+
 		/*
 		 * Flush all I/O and wait for
 		 * cancel/halt/clear completion.
@@ -52,14 +61,12 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 		private->completion = &completion;
 		spin_unlock_irq(sch->lock);
 
+		if (ret == -EBUSY)
 			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);
-		};
-
+		spin_lock_irq(sch->lock);
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
 out_unlock:
@@ -84,7 +91,9 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 		if (is_final)
 			cp_free(&private->cp);
 	}
+	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger, 1);
@@ -108,7 +117,7 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 {
 	struct pmcw *pmcw = &sch->schib.pmcw;
 	struct vfio_ccw_private *private;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (pmcw->qf) {
 		dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
@@ -122,13 +131,17 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 
 	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
 					       GFP_KERNEL | GFP_DMA);
-	if (!private->io_region) {
-		kfree(private);
-		return -ENOMEM;
-	}
+	if (!private->io_region)
+		goto out_free;
+
+	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
+						GFP_KERNEL | GFP_DMA);
+	if (!private->cmd_region)
+		goto out_free;
 
 	private->sch = sch;
 	dev_set_drvdata(&sch->dev, private);
+	mutex_init(&private->io_mutex);
 
 	spin_lock_irq(sch->lock);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
@@ -152,6 +165,9 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 	cio_disable_subchannel(sch);
 out_free:
 	dev_set_drvdata(&sch->dev, NULL);
+	if (private->cmd_region)
+		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);
 	return ret;
@@ -167,6 +183,7 @@ static int vfio_ccw_sch_remove(struct subchannel *sch)
 
 	dev_set_drvdata(&sch->dev, NULL);
 
+	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private);
 
@@ -241,7 +258,7 @@ static struct css_driver vfio_ccw_sch_driver = {
 
 static int __init vfio_ccw_sch_init(void)
 {
-	int ret;
+	int ret = -ENOMEM;
 
 	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
 	if (!vfio_ccw_work_q)
@@ -251,20 +268,30 @@ static int __init vfio_ccw_sch_init(void)
 					sizeof(struct ccw_io_region), 0,
 					SLAB_ACCOUNT, 0,
 					sizeof(struct ccw_io_region), NULL);
-	if (!vfio_ccw_io_region) {
-		destroy_workqueue(vfio_ccw_work_q);
-		return -ENOMEM;
-	}
+	if (!vfio_ccw_io_region)
+		goto out_err;
+
+	vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region",
+					sizeof(struct ccw_cmd_region), 0,
+					SLAB_ACCOUNT, 0,
+					sizeof(struct ccw_cmd_region), NULL);
+	if (!vfio_ccw_cmd_region)
+		goto out_err;
 
 	isc_register(VFIO_CCW_ISC);
 	ret = css_driver_register(&vfio_ccw_sch_driver);
 	if (ret) {
 		isc_unregister(VFIO_CCW_ISC);
-		kmem_cache_destroy(vfio_ccw_io_region);
-		destroy_workqueue(vfio_ccw_work_q);
+		goto out_err;
 	}
 
 	return ret;
+
+out_err:
+	kmem_cache_destroy(vfio_ccw_cmd_region);
+	kmem_cache_destroy(vfio_ccw_io_region);
+	destroy_workqueue(vfio_ccw_work_q);
+	return ret;
 }
 
 static void __exit vfio_ccw_sch_exit(void)

drivers/s390/cio/vfio_ccw_fsm.c

@@ -3,8 +3,10 @@
  * Finite state machine for vfio-ccw device handling
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
@@ -28,9 +30,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	sch = private->sch;
 
 	spin_lock_irqsave(sch->lock, flags);
-	private->state = VFIO_CCW_STATE_BUSY;
 
 	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+	if (!orb) {
+		ret = -EIO;
+		goto out;
+	}
 
 	/* Issue "Start Subchannel" */
 	ccode = ssch(sch->schid, orb);
@@ -42,6 +47,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 		 */
 		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
 		ret = 0;
+		private->state = VFIO_CCW_STATE_CP_PENDING;
 		break;
 	case 1:		/* Status pending */
 	case 2:		/* Busy */
@@ -64,6 +70,76 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
+out:
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_halt(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Halt Subchannel" */
+	ccode = hsch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl |= SCSW_ACTL_HALT_PEND;
+		ret = 0;
+		break;
+	case 1:		/* Status pending */
+	case 2:		/* Busy */
+		ret = -EBUSY;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_clear(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Clear Subchannel" */
+	ccode = csch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl = SCSW_ACTL_CLEAR_PEND;
+		/* TODO: check what else we might need to clear */
+		ret = 0;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
 	spin_unlock_irqrestore(sch->lock, flags);
 	return ret;
 }
@@ -102,6 +178,30 @@ static void fsm_io_busy(struct vfio_ccw_private *private,
 	private->io_region->ret_code = -EBUSY;
 }
 
+static void fsm_io_retry(struct vfio_ccw_private *private,
+			 enum vfio_ccw_event event)
+{
+	private->io_region->ret_code = -EAGAIN;
+}
+
+static void fsm_async_error(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	pr_err("vfio-ccw: FSM: %s request from state:%d\n",
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_HSCH ? "halt" :
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_CSCH ? "clear" :
+	       "<unknown>", private->state);
+	cmd_region->ret_code = -EIO;
+}
+
+static void fsm_async_retry(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	private->cmd_region->ret_code = -EAGAIN;
+}
+
 static void fsm_disabled_irq(struct vfio_ccw_private *private,
 			     enum vfio_ccw_event event)
 {
@@ -130,8 +230,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	struct mdev_device *mdev = private->mdev;
 	char *errstr = "request";
 
-	private->state = VFIO_CCW_STATE_BUSY;
-
+	private->state = VFIO_CCW_STATE_CP_PROCESSING;
 	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
 
 	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
@@ -166,21 +265,41 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		}
 		return;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
-		/* XXX: Handle halt. */
+		/* halt is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) {
-		/* XXX: Handle clear. */
+		/* clear is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	}
 
 err_out:
-	private->state = VFIO_CCW_STATE_IDLE;
 	trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private),
 			       io_region->ret_code, errstr);
 }
 
+/*
+ * Deal with an async request from userspace.
+ */
+static void fsm_async_request(struct vfio_ccw_private *private,
+			      enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	switch (cmd_region->command) {
+	case VFIO_CCW_ASYNC_CMD_HSCH:
+		cmd_region->ret_code = fsm_do_halt(private);
+		break;
+	case VFIO_CCW_ASYNC_CMD_CSCH:
+		cmd_region->ret_code = fsm_do_clear(private);
+		break;
+	default:
+		/* should not happen? */
+		cmd_region->ret_code = -EINVAL;
+	}
+}
+
 /*
  * Got an interrupt for a normal io (state busy).
  */
@@ -204,21 +323,31 @@ 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_ASYNC_REQ]	= fsm_async_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_ASYNC_REQ]	= fsm_async_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_ASYNC_REQ]	= fsm_async_request,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_CP_PROCESSING] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_retry,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_retry,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
-	[VFIO_CCW_STATE_BUSY] = {
+	[VFIO_CCW_STATE_CP_PENDING] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_request,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
 };

drivers/s390/cio/vfio_ccw_ops.c

@@ -3,13 +3,17 @@
  * Physical device callbacks for vfio_ccw
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
 #include <linux/mdev.h>
+#include <linux/nospec.h>
+#include <linux/slab.h>
 
 #include "vfio_ccw_private.h"
 
@@ -130,11 +134,12 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
 
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(mdev))
+		if (!vfio_ccw_sch_quiesce(private->sch))
 			private->state = VFIO_CCW_STATE_STANDBY;
 		/* The state will be NOT_OPER on error. */
 	}
 
+	cp_free(&private->cp);
 	private->mdev = NULL;
 	atomic_inc(&private->avail);
 
@@ -146,20 +151,66 @@ 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;
+	int ret;
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 				     &events, &private->nb);
+	if (ret)
+		return ret;
+
+	ret = vfio_ccw_register_async_dev_regions(private);
+	if (ret)
+		vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+					 &private->nb);
+	return ret;
 }
 
 static void vfio_ccw_mdev_release(struct mdev_device *mdev)
 {
 	struct vfio_ccw_private *private =
 		dev_get_drvdata(mdev_parent_dev(mdev));
+	int i;
 
+	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. */
+	}
+
+	cp_free(&private->cp);
 	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 				 &private->nb);
+
+	for (i = 0; i < private->num_regions; i++)
+		private->region[i].ops->release(private, &private->region[i]);
+
+	private->num_regions = 0;
+	kfree(private->region);
+	private->region = NULL;
+}
+
+static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
+					    char __user *buf, size_t count,
+					    loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_io_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->io_region;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
@@ -167,18 +218,54 @@ static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
 				  size_t count,
 				  loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
 	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
+
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->read(private, buf, count,
+							ppos);
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private,
+					     const char __user *buf,
+					     size_t count, loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_io_region *region;
+	int ret;
 
-	if (*ppos + count > sizeof(*region))
+	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
 	region = private->io_region;
-	if (copy_to_user(buf, (void *)region + *ppos, count))
-		return -EFAULT;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
 
-	return count;
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
+	if (region->ret_code != 0)
+		private->state = VFIO_CCW_STATE_IDLE;
+	ret = (region->ret_code != 0) ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
@@ -186,42 +273,47 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
 				   size_t count,
 				   loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*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;
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
 
-	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;
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->write(private, buf, count,
+							 ppos);
 	}
 
-	return count;
+	return -EINVAL;
 }
 
-static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info)
+static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info,
+					 struct mdev_device *mdev)
 {
+	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
-	info->num_regions = VFIO_CCW_NUM_REGIONS;
+	info->num_regions = VFIO_CCW_NUM_REGIONS + private->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)
+					 struct mdev_device *mdev,
+					 unsigned long arg)
 {
+	struct vfio_ccw_private *private;
+	int i;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	switch (info->index) {
 	case VFIO_CCW_CONFIG_REGION_INDEX:
 		info->offset = 0;
@@ -229,9 +321,55 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
 		info->flags = VFIO_REGION_INFO_FLAG_READ
 			      | VFIO_REGION_INFO_FLAG_WRITE;
 		return 0;
-	default:
+	default: /* all other regions are handled via capability chain */
+	{
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		struct vfio_region_info_cap_type cap_type = {
+			.header.id = VFIO_REGION_INFO_CAP_TYPE,
+			.header.version = 1 };
+		int ret;
+
+		if (info->index >=
+		    VFIO_CCW_NUM_REGIONS + private->num_regions)
 			return -EINVAL;
+
+		info->index = array_index_nospec(info->index,
+						 VFIO_CCW_NUM_REGIONS +
+						 private->num_regions);
+
+		i = info->index - VFIO_CCW_NUM_REGIONS;
+
+		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
+		info->size = private->region[i].size;
+		info->flags = private->region[i].flags;
+
+		cap_type.type = private->region[i].type;
+		cap_type.subtype = private->region[i].subtype;
+
+		ret = vfio_info_add_capability(&caps, &cap_type.header,
+					       sizeof(cap_type));
+		if (ret)
+			return ret;
+
+		info->flags |= VFIO_REGION_INFO_FLAG_CAPS;
+		if (info->argsz < sizeof(*info) + caps.size) {
+			info->argsz = sizeof(*info) + caps.size;
+			info->cap_offset = 0;
+		} else {
+			vfio_info_cap_shift(&caps, sizeof(*info));
+			if (copy_to_user((void __user *)arg + sizeof(*info),
+					 caps.buf, caps.size)) {
+				kfree(caps.buf);
+				return -EFAULT;
+			}
+			info->cap_offset = sizeof(*info);
+		}
+
+		kfree(caps.buf);
+
+	}
 	}
+	return 0;
 }
 
 static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
@@ -308,6 +446,32 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
 	}
 }
 
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data)
+{
+	struct vfio_ccw_region *region;
+
+	region = krealloc(private->region,
+			  (private->num_regions + 1) * sizeof(*region),
+			  GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
+
+	private->region = region;
+	private->region[private->num_regions].type = VFIO_REGION_TYPE_CCW;
+	private->region[private->num_regions].subtype = subtype;
+	private->region[private->num_regions].ops = ops;
+	private->region[private->num_regions].size = size;
+	private->region[private->num_regions].flags = flags;
+	private->region[private->num_regions].data = data;
+
+	private->num_regions++;
+
+	return 0;
+}
+
 static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 				   unsigned int cmd,
 				   unsigned long arg)
@@ -328,7 +492,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_device_info(&info);
+		ret = vfio_ccw_mdev_get_device_info(&info, mdev);
 		if (ret)
 			return ret;
 
@@ -337,8 +501,6 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 	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);
 
@@ -348,8 +510,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id,
-						    &cap_type);
+		ret = vfio_ccw_mdev_get_region_info(&info, mdev, arg);
 		if (ret)
 			return ret;
 

drivers/s390/cio/vfio_ccw_private.h

@@ -3,9 +3,11 @@
  * Private stuff for vfio_ccw driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #ifndef _VFIO_CCW_PRIVATE_H_
@@ -19,6 +21,40 @@
 #include "css.h"
 #include "vfio_ccw_cp.h"
 
+#define VFIO_CCW_OFFSET_SHIFT   10
+#define VFIO_CCW_OFFSET_TO_INDEX(off)	(off >> VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_OFFSET_MASK	(((u64)(1) << VFIO_CCW_OFFSET_SHIFT) - 1)
+
+/* capability chain handling similar to vfio-pci */
+struct vfio_ccw_private;
+struct vfio_ccw_region;
+
+struct vfio_ccw_regops {
+	ssize_t	(*read)(struct vfio_ccw_private *private, char __user *buf,
+			size_t count, loff_t *ppos);
+	ssize_t	(*write)(struct vfio_ccw_private *private,
+			 const char __user *buf, size_t count, loff_t *ppos);
+	void	(*release)(struct vfio_ccw_private *private,
+			   struct vfio_ccw_region *region);
+};
+
+struct vfio_ccw_region {
+	u32				type;
+	u32				subtype;
+	const struct vfio_ccw_regops	*ops;
+	void				*data;
+	size_t				size;
+	u32				flags;
+};
+
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data);
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private);
+
 /**
  * struct vfio_ccw_private
  * @sch: pointer to the subchannel
@@ -28,6 +64,10 @@
  * @mdev: pointer to the mediated device
  * @nb: notifier for vfio events
  * @io_region: MMIO region to input/output I/O arguments/results
+ * @io_mutex: protect against concurrent update of I/O regions
+ * @region: additional regions for other subchannel operations
+ * @cmd_region: MMIO region for asynchronous I/O commands other than START
+ * @num_regions: number of additional regions
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
@@ -42,6 +82,10 @@ struct vfio_ccw_private {
 	struct mdev_device	*mdev;
 	struct notifier_block	nb;
 	struct ccw_io_region	*io_region;
+	struct mutex		io_mutex;
+	struct vfio_ccw_region *region;
+	struct ccw_cmd_region	*cmd_region;
+	int num_regions;
 
 	struct channel_program	cp;
 	struct irb		irb;
@@ -63,7 +107,8 @@ enum vfio_ccw_state {
 	VFIO_CCW_STATE_NOT_OPER,
 	VFIO_CCW_STATE_STANDBY,
 	VFIO_CCW_STATE_IDLE,
-	VFIO_CCW_STATE_BUSY,
+	VFIO_CCW_STATE_CP_PROCESSING,
+	VFIO_CCW_STATE_CP_PENDING,
 	/* last element! */
 	NR_VFIO_CCW_STATES
 };
@@ -75,6 +120,7 @@ enum vfio_ccw_event {
 	VFIO_CCW_EVENT_NOT_OPER,
 	VFIO_CCW_EVENT_IO_REQ,
 	VFIO_CCW_EVENT_INTERRUPT,
+	VFIO_CCW_EVENT_ASYNC_REQ,
 	/* last element! */
 	NR_VFIO_CCW_EVENTS
 };

include/uapi/linux/vfio.h

@@ -353,6 +353,10 @@ struct vfio_region_gfx_edid {
 #define VFIO_DEVICE_GFX_LINK_STATE_DOWN  2
 };
 
+#define VFIO_REGION_TYPE_CCW			(2)
+/* ccw sub-types */
+#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
+
 /*
  * 10de vendor sub-type
  *

include/uapi/linux/vfio_ccw.h

@@ -12,6 +12,7 @@
 
 #include <linux/types.h>
 
+/* used for START SUBCHANNEL, always present */
 struct ccw_io_region {
 #define ORB_AREA_SIZE 12
 	__u8	orb_area[ORB_AREA_SIZE];
@@ -22,4 +23,15 @@ struct ccw_io_region {
 	__u32	ret_code;
 } __packed;
 
+/*
+ * used for processing commands that trigger asynchronous actions
+ * Note: this is controlled by a capability
+ */
+#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0)
+#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1)
+struct ccw_cmd_region {
+	__u32 command;
+	__u32 ret_code;
+} __packed;
+
 #endif