Merge tag 'vfio-v6.0-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Cleanup use of extern in function prototypes (Alex Williamson)

 - Simplify bus_type usage and convert to device IOMMU interfaces (Robin
   Murphy)

 - Check missed return value and fix comment typos (Bo Liu)

 - Split migration ops from device ops and fix races in mlx5 migration
   support (Yishai Hadas)

 - Fix missed return value check in noiommu support (Liam Ni)

 - Hardening to clear buffer pointer to avoid use-after-free (Schspa
   Shi)

 - Remove requirement that only the same mm can unmap a previously
   mapped range (Li Zhe)

 - Adjust semaphore release vs device open counter (Yi Liu)

 - Remove unused arg from SPAPR support code (Deming Wang)

 - Rework vfio-ccw driver to better fit new mdev framework (Eric Farman,
   Michael Kawano)

 - Replace DMA unmap notifier with callbacks (Jason Gunthorpe)

 - Clarify SPAPR support comment relative to iommu_ops (Alexey
   Kardashevskiy)

 - Revise page pinning API towards compatibility with future iommufd
   support (Nicolin Chen)

 - Resolve issues in vfio-ccw, including use of DMA unmap callback (Eric
   Farman)

* tag 'vfio-v6.0-rc1' of https://github.com/awilliam/linux-vfio: (40 commits)
  vfio/pci: fix the wrong word
  vfio/ccw: Check return code from subchannel quiesce
  vfio/ccw: Remove FSM Close from remove handlers
  vfio/ccw: Add length to DMA_UNMAP checks
  vfio: Replace phys_pfn with pages for vfio_pin_pages()
  vfio/ccw: Add kmap_local_page() for memcpy
  vfio: Rename user_iova of vfio_dma_rw()
  vfio/ccw: Change pa_pfn list to pa_iova list
  vfio/ap: Change saved_pfn to saved_iova
  vfio: Pass in starting IOVA to vfio_pin/unpin_pages API
  vfio/ccw: Only pass in contiguous pages
  vfio/ap: Pass in physical address of ind to ap_aqic()
  drm/i915/gvt: Replace roundup with DIV_ROUND_UP
  vfio: Make vfio_unpin_pages() return void
  vfio/spapr_tce: Fix the comment
  vfio: Replace the iommu notifier with a device list
  vfio: Replace the DMA unmapping notifier with a callback
  vfio/ccw: Move FSM open/close to MDEV open/close
  vfio/ccw: Refactor vfio_ccw_mdev_reset
  vfio/ccw: Create a CLOSE FSM event
  ...

7 files changed, 261 insertions, 241 deletions

diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
index 7a838e3d7c0f..420d89ba7f83 100644
--- a/drivers/s390/cio/vfio_ccw_async.c
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/vfio.h>
-#include <linux/mdev.h>
 
 #include "vfio_ccw_private.h"
 
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 0c2be9421ab7..7b02e97f4b29 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -11,6 +11,7 @@
 #include <linux/ratelimit.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/highmem.h>
 #include <linux/iommu.h>
 #include <linux/vfio.h>
 #include <asm/idals.h>
@@ -18,13 +19,11 @@
 #include "vfio_ccw_cp.h"
 #include "vfio_ccw_private.h"
 
-struct pfn_array {
-	/* Starting guest physical I/O address. */
-	unsigned long		pa_iova;
-	/* Array that stores PFNs of the pages need to pin. */
-	unsigned long		*pa_iova_pfn;
-	/* Array that receives PFNs of the pages pinned. */
-	unsigned long		*pa_pfn;
+struct page_array {
+	/* Array that stores pages need to pin. */
+	dma_addr_t		*pa_iova;
+	/* Array that receives the pinned pages. */
+	struct page		**pa_page;
 	/* Number of pages pinned from @pa_iova. */
 	int			pa_nr;
 };
@@ -37,116 +36,158 @@ struct ccwchain {
 	/* Count of the valid ccws in chain. */
 	int			ch_len;
 	/* Pinned PAGEs for the original data. */
-	struct pfn_array	*ch_pa;
+	struct page_array	*ch_pa;
 };
 
 /*
- * pfn_array_alloc() - alloc memory for PFNs
- * @pa: pfn_array on which to perform the operation
+ * page_array_alloc() - alloc memory for page array
+ * @pa: page_array on which to perform the operation
  * @iova: target guest physical address
  * @len: number of bytes that should be pinned from @iova
  *
- * Attempt to allocate memory for PFNs.
+ * Attempt to allocate memory for page array.
  *
- * Usage of pfn_array:
- * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in
+ * Usage of page_array:
+ * We expect (pa_nr == 0) and (pa_iova == NULL), any field in
  * this structure will be filled in by this function.
  *
  * Returns:
- *         0 if PFNs are allocated
- *   -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova_pfn is not NULL
+ *         0 if page array is allocated
+ *   -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova is not NULL
  *   -ENOMEM if alloc failed
  */
-static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
+static int page_array_alloc(struct page_array *pa, u64 iova, unsigned int len)
 {
 	int i;
 
-	if (pa->pa_nr || pa->pa_iova_pfn)
+	if (pa->pa_nr || pa->pa_iova)
 		return -EINVAL;
 
-	pa->pa_iova = iova;
-
 	pa->pa_nr = ((iova & ~PAGE_MASK) + len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	if (!pa->pa_nr)
 		return -EINVAL;
 
-	pa->pa_iova_pfn = kcalloc(pa->pa_nr,
-				  sizeof(*pa->pa_iova_pfn) +
-				  sizeof(*pa->pa_pfn),
-				  GFP_KERNEL);
-	if (unlikely(!pa->pa_iova_pfn)) {
+	pa->pa_iova = kcalloc(pa->pa_nr,
+			      sizeof(*pa->pa_iova) + sizeof(*pa->pa_page),
+			      GFP_KERNEL);
+	if (unlikely(!pa->pa_iova)) {
 		pa->pa_nr = 0;
 		return -ENOMEM;
 	}
-	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
+	pa->pa_page = (struct page **)&pa->pa_iova[pa->pa_nr];
 
-	pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
-	pa->pa_pfn[0] = -1ULL;
+	pa->pa_iova[0] = iova;
+	pa->pa_page[0] = NULL;
 	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;
+		pa->pa_iova[i] = pa->pa_iova[i - 1] + PAGE_SIZE;
+		pa->pa_page[i] = NULL;
 	}
 
 	return 0;
 }
 
 /*
- * pfn_array_pin() - Pin user pages in memory
- * @pa: pfn_array on which to perform the operation
+ * page_array_unpin() - Unpin user pages in memory
+ * @pa: page_array on which to perform the operation
+ * @vdev: the vfio device to perform the operation
+ * @pa_nr: number of user pages to unpin
+ *
+ * Only unpin if any pages were pinned to begin with, i.e. pa_nr > 0,
+ * otherwise only clear pa->pa_nr
+ */
+static void page_array_unpin(struct page_array *pa,
+			     struct vfio_device *vdev, int pa_nr)
+{
+	int unpinned = 0, npage = 1;
+
+	while (unpinned < pa_nr) {
+		dma_addr_t *first = &pa->pa_iova[unpinned];
+		dma_addr_t *last = &first[npage];
+
+		if (unpinned + npage < pa_nr &&
+		    *first + npage * PAGE_SIZE == *last) {
+			npage++;
+			continue;
+		}
+
+		vfio_unpin_pages(vdev, *first, npage);
+		unpinned += npage;
+		npage = 1;
+	}
+
+	pa->pa_nr = 0;
+}
+
+/*
+ * page_array_pin() - Pin user pages in memory
+ * @pa: page_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 vfio_device *vdev)
+static int page_array_pin(struct page_array *pa, struct vfio_device *vdev)
 {
+	int pinned = 0, npage = 1;
 	int ret = 0;
 
-	ret = vfio_pin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr,
-			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
+	while (pinned < pa->pa_nr) {
+		dma_addr_t *first = &pa->pa_iova[pinned];
+		dma_addr_t *last = &first[npage];
 
-	if (ret < 0) {
-		goto err_out;
-	} else if (ret > 0 && ret != pa->pa_nr) {
-		vfio_unpin_pages(vdev, pa->pa_iova_pfn, ret);
-		ret = -EINVAL;
-		goto err_out;
+		if (pinned + npage < pa->pa_nr &&
+		    *first + npage * PAGE_SIZE == *last) {
+			npage++;
+			continue;
+		}
+
+		ret = vfio_pin_pages(vdev, *first, npage,
+				     IOMMU_READ | IOMMU_WRITE,
+				     &pa->pa_page[pinned]);
+		if (ret < 0) {
+			goto err_out;
+		} else if (ret > 0 && ret != npage) {
+			pinned += ret;
+			ret = -EINVAL;
+			goto err_out;
+		}
+		pinned += npage;
+		npage = 1;
 	}
 
 	return ret;
 
 err_out:
-	pa->pa_nr = 0;
-
+	page_array_unpin(pa, vdev, pinned);
 	return ret;
 }
 
 /* Unpin the pages before releasing the memory. */
-static void pfn_array_unpin_free(struct pfn_array *pa, struct vfio_device *vdev)
+static void page_array_unpin_free(struct page_array *pa, struct vfio_device *vdev)
 {
-	/* Only unpin if any pages were pinned to begin with */
-	if (pa->pa_nr)
-		vfio_unpin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr);
-	pa->pa_nr = 0;
-	kfree(pa->pa_iova_pfn);
+	page_array_unpin(pa, vdev, pa->pa_nr);
+	kfree(pa->pa_iova);
 }
 
-static bool pfn_array_iova_pinned(struct pfn_array *pa, unsigned long iova)
+static bool page_array_iova_pinned(struct page_array *pa, u64 iova, u64 length)
 {
-	unsigned long iova_pfn = iova >> PAGE_SHIFT;
+	u64 iova_pfn_start = iova >> PAGE_SHIFT;
+	u64 iova_pfn_end = (iova + length - 1) >> PAGE_SHIFT;
+	u64 pfn;
 	int i;
 
-	for (i = 0; i < pa->pa_nr; i++)
-		if (pa->pa_iova_pfn[i] == iova_pfn)
+	for (i = 0; i < pa->pa_nr; i++) {
+		pfn = pa->pa_iova[i] >> PAGE_SHIFT;
+		if (pfn >= iova_pfn_start && pfn <= iova_pfn_end)
 			return true;
+	}
 
 	return false;
 }
-/* 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)
+/* Create the list of IDAL words for a page_array. */
+static inline void page_array_idal_create_words(struct page_array *pa,
+						unsigned long *idaws)
 {
 	int i;
 
@@ -159,10 +200,10 @@ static inline void pfn_array_idal_create_words(
 	 */
 
 	for (i = 0; i < pa->pa_nr; i++)
-		idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT;
+		idaws[i] = page_to_phys(pa->pa_page[i]);
 
 	/* Adjust the first IDAW, since it may not start on a page boundary */
-	idaws[0] += pa->pa_iova & (PAGE_SIZE - 1);
+	idaws[0] += pa->pa_iova[0] & (PAGE_SIZE - 1);
 }
 
 static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
@@ -194,24 +235,24 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
 static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova,
 			   unsigned long n)
 {
-	struct pfn_array pa = {0};
-	u64 from;
+	struct page_array pa = {0};
 	int i, ret;
 	unsigned long l, m;
 
-	ret = pfn_array_alloc(&pa, iova, n);
+	ret = page_array_alloc(&pa, iova, n);
 	if (ret < 0)
 		return ret;
 
-	ret = pfn_array_pin(&pa, vdev);
+	ret = page_array_pin(&pa, vdev);
 	if (ret < 0) {
-		pfn_array_unpin_free(&pa, vdev);
+		page_array_unpin_free(&pa, vdev);
 		return ret;
 	}
 
 	l = n;
 	for (i = 0; i < pa.pa_nr; i++) {
-		from = pa.pa_pfn[i] << PAGE_SHIFT;
+		void *from = kmap_local_page(pa.pa_page[i]);
+
 		m = PAGE_SIZE;
 		if (i == 0) {
 			from += iova & (PAGE_SIZE - 1);
@@ -219,14 +260,15 @@ static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova,
 		}
 
 		m = min(l, m);
-		memcpy(to + (n - l), (void *)from, m);
+		memcpy(to + (n - l), from, m);
+		kunmap_local(from);
 
 		l -= m;
 		if (l == 0)
 			break;
 	}
 
-	pfn_array_unpin_free(&pa, vdev);
+	page_array_unpin_free(&pa, vdev);
 
 	return l;
 }
@@ -329,7 +371,7 @@ 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_pa = (struct pfn_array *)data;
+	chain->ch_pa = (struct page_array *)data;
 
 	chain->ch_len = len;
 
@@ -513,7 +555,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	struct vfio_device *vdev =
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccw1 *ccw;
-	struct pfn_array *pa;
+	struct page_array *pa;
 	u64 iova;
 	unsigned long *idaws;
 	int ret;
@@ -547,13 +589,13 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	}
 
 	/*
-	 * Allocate an array of pfn's for pages to pin/translate.
+	 * Allocate an array of 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);
+	ret = page_array_alloc(pa, iova, bytes);
 	if (ret < 0)
 		goto out_free_idaws;
 
@@ -564,21 +606,21 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 			goto out_unpin;
 
 		/*
-		 * Copy guest IDAWs into pfn_array, in case the memory they
+		 * Copy guest IDAWs into page_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;
+			pa->pa_iova[i] = idaws[i];
 	} else {
 		/*
-		 * No action is required here; the iova addresses in pfn_array
-		 * were initialized sequentially in pfn_array_alloc() beginning
+		 * No action is required here; the iova addresses in page_array
+		 * were initialized sequentially in page_array_alloc() beginning
 		 * with the contents of ccw->cda.
 		 */
 	}
 
 	if (ccw_does_data_transfer(ccw)) {
-		ret = pfn_array_pin(pa, vdev);
+		ret = page_array_pin(pa, vdev);
 		if (ret < 0)
 			goto out_unpin;
 	} else {
@@ -588,13 +630,13 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	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);
+	/* Populate the IDAL with pinned/translated addresses from page */
+	page_array_idal_create_words(pa, idaws);
 
 	return 0;
 
 out_unpin:
-	pfn_array_unpin_free(pa, vdev);
+	page_array_unpin_free(pa, vdev);
 out_free_idaws:
 	kfree(idaws);
 out_init:
@@ -700,7 +742,7 @@ void cp_free(struct channel_program *cp)
 	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, vdev);
+			page_array_unpin_free(chain->ch_pa + i, vdev);
 			ccwchain_cda_free(chain, i);
 		}
 		ccwchain_free(chain);
@@ -862,11 +904,12 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
  * cp_iova_pinned() - check if an iova is pinned for a ccw chain.
  * @cp: channel_program on which to perform the operation
  * @iova: the iova to check
+ * @length: the length to check from @iova
  *
  * If the @iova is currently pinned for the ccw chain, return true;
  * else return false.
  */
-bool cp_iova_pinned(struct channel_program *cp, u64 iova)
+bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
 {
 	struct ccwchain *chain;
 	int i;
@@ -876,7 +919,7 @@ 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_iova_pinned(chain->ch_pa + i, iova))
+			if (page_array_iova_pinned(chain->ch_pa + i, iova, length))
 				return true;
 	}
 
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index e4c436199b4c..54d26e242533 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -41,11 +41,11 @@ struct channel_program {
 	struct ccw1 *guest_cp;
 };
 
-extern int cp_init(struct channel_program *cp, union orb *orb);
-extern void cp_free(struct channel_program *cp);
-extern int cp_prefetch(struct channel_program *cp);
-extern union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);
-extern void cp_update_scsw(struct channel_program *cp, union scsw *scsw);
-extern bool cp_iova_pinned(struct channel_program *cp, u64 iova);
+int cp_init(struct channel_program *cp, union orb *orb);
+void cp_free(struct channel_program *cp);
+int cp_prefetch(struct channel_program *cp);
+union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);
+void cp_update_scsw(struct channel_program *cp, union scsw *scsw);
+bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length);
 
 #endif
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index ee182cfb467d..86d9e428357b 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/slab.h>
-#include <linux/uuid.h>
 #include <linux/mdev.h>
 
 #include <asm/isc.h>
@@ -42,13 +41,6 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 	DECLARE_COMPLETION_ONSTACK(completion);
 	int iretry, ret = 0;
 
-	spin_lock_irq(sch->lock);
-	if (!sch->schib.pmcw.ena)
-		goto out_unlock;
-	ret = cio_disable_subchannel(sch);
-	if (ret != -EBUSY)
-		goto out_unlock;
-
 	iretry = 255;
 	do {
 
@@ -75,9 +67,7 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 		spin_lock_irq(sch->lock);
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
-out_unlock:
-	private->state = VFIO_CCW_STATE_NOT_OPER;
-	spin_unlock_irq(sch->lock);
+
 	return ret;
 }
 
@@ -107,9 +97,10 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 	/*
 	 * Reset to IDLE only if processing of a channel program
 	 * has finished. Do not overwrite a possible processing
-	 * state if the final interrupt was for HSCH or CSCH.
+	 * state if the interrupt was unsolicited, or if the final
+	 * interrupt was for HSCH or CSCH.
 	 */
-	if (private->mdev && cp_is_finished)
+	if (cp_is_finished)
 		private->state = VFIO_CCW_STATE_IDLE;
 
 	if (private->io_trigger)
@@ -147,7 +138,7 @@ static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 
 	private->sch = sch;
 	mutex_init(&private->io_mutex);
-	private->state = VFIO_CCW_STATE_NOT_OPER;
+	private->state = VFIO_CCW_STATE_STANDBY;
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
@@ -231,26 +222,15 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 
 	dev_set_drvdata(&sch->dev, private);
 
-	spin_lock_irq(sch->lock);
-	sch->isc = VFIO_CCW_ISC;
-	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
-	spin_unlock_irq(sch->lock);
+	ret = mdev_register_device(&sch->dev, &vfio_ccw_mdev_driver);
 	if (ret)
 		goto out_free;
 
-	private->state = VFIO_CCW_STATE_STANDBY;
-
-	ret = vfio_ccw_mdev_reg(sch);
-	if (ret)
-		goto out_disable;
-
 	VFIO_CCW_MSG_EVENT(4, "bound to subchannel %x.%x.%04x\n",
 			   sch->schid.cssid, sch->schid.ssid,
 			   sch->schid.sch_no);
 	return 0;
 
-out_disable:
-	cio_disable_subchannel(sch);
 out_free:
 	dev_set_drvdata(&sch->dev, NULL);
 	vfio_ccw_free_private(private);
@@ -261,8 +241,7 @@ static void vfio_ccw_sch_remove(struct subchannel *sch)
 {
 	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
 
-	vfio_ccw_sch_quiesce(sch);
-	vfio_ccw_mdev_unreg(sch);
+	mdev_unregister_device(&sch->dev);
 
 	dev_set_drvdata(&sch->dev, NULL);
 
@@ -275,7 +254,10 @@ static void vfio_ccw_sch_remove(struct subchannel *sch)
 
 static void vfio_ccw_sch_shutdown(struct subchannel *sch)
 {
-	vfio_ccw_sch_quiesce(sch);
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
 }
 
 /**
@@ -301,19 +283,11 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 	if (work_pending(&sch->todo_work))
 		goto out_unlock;
 
-	if (cio_update_schib(sch)) {
-		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
-		rc = 0;
-		goto out_unlock;
-	}
-
-	private = dev_get_drvdata(&sch->dev);
-	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
-		private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
-				 VFIO_CCW_STATE_STANDBY;
-	}
 	rc = 0;
 
+	if (cio_update_schib(sch))
+		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+
 out_unlock:
 	spin_unlock_irqrestore(sch->lock, flags);
 
@@ -358,8 +332,8 @@ static int vfio_ccw_chp_event(struct subchannel *sch,
 		return 0;
 
 	trace_vfio_ccw_chp_event(private->sch->schid, mask, event);
-	VFIO_CCW_MSG_EVENT(2, "%pUl (%x.%x.%04x): mask=0x%x event=%d\n",
-			   mdev_uuid(private->mdev), sch->schid.cssid,
+	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: mask=0x%x event=%d\n",
+			   sch->schid.cssid,
 			   sch->schid.ssid, sch->schid.sch_no,
 			   mask, event);
 
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 8483a266051c..a59c758869f8 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -10,7 +10,8 @@
  */
 
 #include <linux/vfio.h>
-#include <linux/mdev.h>
+
+#include <asm/isc.h>
 
 #include "ioasm.h"
 #include "vfio_ccw_private.h"
@@ -161,8 +162,12 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 {
 	struct subchannel *sch = private->sch;
 
-	VFIO_CCW_TRACE_EVENT(2, "notoper");
-	VFIO_CCW_TRACE_EVENT(2, dev_name(&sch->dev));
+	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: notoper event %x state %x\n",
+			   sch->schid.cssid,
+			   sch->schid.ssid,
+			   sch->schid.sch_no,
+			   event,
+			   private->state);
 
 	/*
 	 * TODO:
@@ -170,6 +175,9 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 	 */
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
+
+	/* This is usually handled during CLOSE event */
+	cp_free(&private->cp);
 }
 
 /*
@@ -242,7 +250,6 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	union orb *orb;
 	union scsw *scsw = &private->scsw;
 	struct ccw_io_region *io_region = private->io_region;
-	struct mdev_device *mdev = private->mdev;
 	char *errstr = "request";
 	struct subchannel_id schid = get_schid(private);
 
@@ -256,8 +263,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		if (orb->tm.b) {
 			io_region->ret_code = -EOPNOTSUPP;
 			VFIO_CCW_MSG_EVENT(2,
-					   "%pUl (%x.%x.%04x): transport mode\n",
-					   mdev_uuid(mdev), schid.cssid,
+					   "sch %x.%x.%04x: transport mode\n",
+					   schid.cssid,
 					   schid.ssid, schid.sch_no);
 			errstr = "transport mode";
 			goto err_out;
@@ -265,8 +272,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		io_region->ret_code = cp_init(&private->cp, orb);
 		if (io_region->ret_code) {
 			VFIO_CCW_MSG_EVENT(2,
-					   "%pUl (%x.%x.%04x): cp_init=%d\n",
-					   mdev_uuid(mdev), schid.cssid,
+					   "sch %x.%x.%04x: cp_init=%d\n",
+					   schid.cssid,
 					   schid.ssid, schid.sch_no,
 					   io_region->ret_code);
 			errstr = "cp init";
@@ -276,8 +283,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		io_region->ret_code = cp_prefetch(&private->cp);
 		if (io_region->ret_code) {
 			VFIO_CCW_MSG_EVENT(2,
-					   "%pUl (%x.%x.%04x): cp_prefetch=%d\n",
-					   mdev_uuid(mdev), schid.cssid,
+					   "sch %x.%x.%04x: cp_prefetch=%d\n",
+					   schid.cssid,
 					   schid.ssid, schid.sch_no,
 					   io_region->ret_code);
 			errstr = "cp prefetch";
@@ -289,8 +296,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		io_region->ret_code = fsm_io_helper(private);
 		if (io_region->ret_code) {
 			VFIO_CCW_MSG_EVENT(2,
-					   "%pUl (%x.%x.%04x): fsm_io_helper=%d\n",
-					   mdev_uuid(mdev), schid.cssid,
+					   "sch %x.%x.%04x: fsm_io_helper=%d\n",
+					   schid.cssid,
 					   schid.ssid, schid.sch_no,
 					   io_region->ret_code);
 			errstr = "cp fsm_io_helper";
@@ -300,16 +307,16 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		return;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
 		VFIO_CCW_MSG_EVENT(2,
-				   "%pUl (%x.%x.%04x): halt on io_region\n",
-				   mdev_uuid(mdev), schid.cssid,
+				   "sch %x.%x.%04x: halt on io_region\n",
+				   schid.cssid,
 				   schid.ssid, schid.sch_no);
 		/* 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) {
 		VFIO_CCW_MSG_EVENT(2,
-				   "%pUl (%x.%x.%04x): clear on io_region\n",
-				   mdev_uuid(mdev), schid.cssid,
+				   "sch %x.%x.%04x: clear on io_region\n",
+				   schid.cssid,
 				   schid.ssid, schid.sch_no);
 		/* clear is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
@@ -366,6 +373,54 @@ static void fsm_irq(struct vfio_ccw_private *private,
 		complete(private->completion);
 }
 
+static void fsm_open(struct vfio_ccw_private *private,
+		     enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+	int ret;
+
+	spin_lock_irq(sch->lock);
+	sch->isc = VFIO_CCW_ISC;
+	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
+	if (ret)
+		goto err_unlock;
+
+	private->state = VFIO_CCW_STATE_IDLE;
+	spin_unlock_irq(sch->lock);
+	return;
+
+err_unlock:
+	spin_unlock_irq(sch->lock);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+}
+
+static void fsm_close(struct vfio_ccw_private *private,
+		      enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+	int ret;
+
+	spin_lock_irq(sch->lock);
+
+	if (!sch->schib.pmcw.ena)
+		goto err_unlock;
+
+	ret = cio_disable_subchannel(sch);
+	if (ret == -EBUSY)
+		ret = vfio_ccw_sch_quiesce(sch);
+	if (ret)
+		goto err_unlock;
+
+	private->state = VFIO_CCW_STATE_STANDBY;
+	spin_unlock_irq(sch->lock);
+	cp_free(&private->cp);
+	return;
+
+err_unlock:
+	spin_unlock_irq(sch->lock);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+}
+
 /*
  * Device statemachine
  */
@@ -375,29 +430,39 @@ fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = {
 		[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_EVENT_OPEN]		= fsm_nop,
+		[VFIO_CCW_EVENT_CLOSE]		= fsm_nop,
 	},
 	[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_EVENT_INTERRUPT]	= fsm_disabled_irq,
+		[VFIO_CCW_EVENT_OPEN]		= fsm_open,
+		[VFIO_CCW_EVENT_CLOSE]		= fsm_notoper,
 	},
 	[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_EVENT_OPEN]		= fsm_notoper,
+		[VFIO_CCW_EVENT_CLOSE]		= fsm_close,
 	},
 	[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_EVENT_OPEN]		= fsm_notoper,
+		[VFIO_CCW_EVENT_CLOSE]		= fsm_close,
 	},
 	[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,
+		[VFIO_CCW_EVENT_OPEN]		= fsm_notoper,
+		[VFIO_CCW_EVENT_CLOSE]		= fsm_close,
 	},
 };
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index b49e2e9db2dc..4a806a2273b5 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -21,54 +21,28 @@ static const struct vfio_device_ops vfio_ccw_dev_ops;
 
 static int vfio_ccw_mdev_reset(struct vfio_ccw_private *private)
 {
-	struct subchannel *sch;
-	int ret;
-
-	sch = private->sch;
 	/*
-	 * TODO:
-	 * In the cureent stage, some things like "no I/O running" and "no
-	 * interrupt pending" are clear, but we are not sure what other state
-	 * we need to care about.
-	 * There are still a lot more instructions need to be handled. We
-	 * should come back here later.
+	 * If the FSM state is seen as Not Operational after closing
+	 * and re-opening the mdev, return an error.
 	 */
-	ret = vfio_ccw_sch_quiesce(sch);
-	if (ret)
-		return ret;
-
-	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
-	if (!ret)
-		private->state = VFIO_CCW_STATE_IDLE;
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_OPEN);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
-static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
-				  unsigned long action,
-				  void *data)
+static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
 {
 	struct vfio_ccw_private *private =
-		container_of(nb, struct vfio_ccw_private, nb);
-
-	/*
-	 * Vendor drivers MUST unpin pages in response to an
-	 * invalidation.
-	 */
-	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
-		struct vfio_iommu_type1_dma_unmap *unmap = data;
-
-		if (!cp_iova_pinned(&private->cp, unmap->iova))
-			return NOTIFY_OK;
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
-		if (vfio_ccw_mdev_reset(private))
-			return NOTIFY_BAD;
+	/* Drivers MUST unpin pages in response to an invalidation. */
+	if (!cp_iova_pinned(&private->cp, iova, length))
+		return;
 
-		cp_free(&private->cp);
-		return NOTIFY_OK;
-	}
-
-	return NOTIFY_DONE;
+	vfio_ccw_mdev_reset(private);
 }
 
 static ssize_t name_show(struct mdev_type *mtype,
@@ -128,11 +102,8 @@ static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 	vfio_init_group_dev(&private->vdev, &mdev->dev,
 			    &vfio_ccw_dev_ops);
 
-	private->mdev = mdev;
-	private->state = VFIO_CCW_STATE_IDLE;
-
-	VFIO_CCW_MSG_EVENT(2, "mdev %pUl, sch %x.%x.%04x: create\n",
-			   mdev_uuid(mdev), private->sch->schid.cssid,
+	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: create\n",
+			   private->sch->schid.cssid,
 			   private->sch->schid.ssid,
 			   private->sch->schid.sch_no);
 
@@ -145,8 +116,6 @@ static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 err_atomic:
 	vfio_uninit_group_dev(&private->vdev);
 	atomic_inc(&private->avail);
-	private->mdev = NULL;
-	private->state = VFIO_CCW_STATE_IDLE;
 	return ret;
 }
 
@@ -154,23 +123,14 @@ static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
 {
 	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
 
-	VFIO_CCW_MSG_EVENT(2, "mdev %pUl, sch %x.%x.%04x: remove\n",
-			   mdev_uuid(mdev), private->sch->schid.cssid,
+	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: remove\n",
+			   private->sch->schid.cssid,
 			   private->sch->schid.ssid,
 			   private->sch->schid.sch_no);
 
 	vfio_unregister_group_dev(&private->vdev);
 
-	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
-	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_sch_quiesce(private->sch))
-			private->state = VFIO_CCW_STATE_STANDBY;
-		/* The state will be NOT_OPER on error. */
-	}
-
 	vfio_uninit_group_dev(&private->vdev);
-	cp_free(&private->cp);
-	private->mdev = NULL;
 	atomic_inc(&private->avail);
 }
 
@@ -178,19 +138,15 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
-	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
 	int ret;
 
-	private->nb.notifier_call = vfio_ccw_mdev_notifier;
-
-	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY,
-				     &events, &private->nb);
-	if (ret)
-		return ret;
+	/* Device cannot simply be opened again from this state */
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -EINVAL;
 
 	ret = vfio_ccw_register_async_dev_regions(private);
 	if (ret)
-		goto out_unregister;
+		return ret;
 
 	ret = vfio_ccw_register_schib_dev_regions(private);
 	if (ret)
@@ -200,11 +156,16 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 	if (ret)
 		goto out_unregister;
 
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_OPEN);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
+		ret = -EINVAL;
+		goto out_unregister;
+	}
+
 	return ret;
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 	return ret;
 }
 
@@ -213,16 +174,8 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
-	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
-	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(private))
-			private->state = VFIO_CCW_STATE_STANDBY;
-		/* The state will be NOT_OPER on error. */
-	}
-
-	cp_free(&private->cp);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
@@ -645,6 +598,7 @@ static const struct vfio_device_ops vfio_ccw_dev_ops = {
 	.write = vfio_ccw_mdev_write,
 	.ioctl = vfio_ccw_mdev_ioctl,
 	.request = vfio_ccw_mdev_request,
+	.dma_unmap = vfio_ccw_dma_unmap,
 };
 
 struct mdev_driver vfio_ccw_mdev_driver = {
@@ -657,13 +611,3 @@ struct mdev_driver vfio_ccw_mdev_driver = {
 	.remove = vfio_ccw_mdev_remove,
 	.supported_type_groups  = mdev_type_groups,
 };
-
-int vfio_ccw_mdev_reg(struct subchannel *sch)
-{
-	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_driver);
-}
-
-void vfio_ccw_mdev_unreg(struct subchannel *sch)
-{
-	mdev_unregister_device(&sch->dev);
-}
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 7272eb788612..cd24b7fada91 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -73,8 +73,6 @@ struct vfio_ccw_crw {
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
  * @avail: available for creating a mediated device
- * @mdev: pointer to the mediated device
- * @nb: notifier for vfio events
  * @io_region: MMIO region to input/output I/O arguments/results
  * @io_mutex: protect against concurrent update of I/O regions
  * @region: additional regions for other subchannel operations
@@ -97,8 +95,6 @@ struct vfio_ccw_private {
 	int			state;
 	struct completion	*completion;
 	atomic_t		avail;
-	struct mdev_device	*mdev;
-	struct notifier_block	nb;
 	struct ccw_io_region	*io_region;
 	struct mutex		io_mutex;
 	struct vfio_ccw_region *region;
@@ -119,10 +115,7 @@ struct vfio_ccw_private {
 	struct work_struct	crw_work;
 } __aligned(8);
 
-extern int vfio_ccw_mdev_reg(struct subchannel *sch);
-extern void vfio_ccw_mdev_unreg(struct subchannel *sch);
-
-extern int vfio_ccw_sch_quiesce(struct subchannel *sch);
+int vfio_ccw_sch_quiesce(struct subchannel *sch);
 
 extern struct mdev_driver vfio_ccw_mdev_driver;
 
@@ -147,6 +140,8 @@ enum vfio_ccw_event {
 	VFIO_CCW_EVENT_IO_REQ,
 	VFIO_CCW_EVENT_INTERRUPT,
 	VFIO_CCW_EVENT_ASYNC_REQ,
+	VFIO_CCW_EVENT_OPEN,
+	VFIO_CCW_EVENT_CLOSE,
 	/* last element! */
 	NR_VFIO_CCW_EVENTS
 };
@@ -158,7 +153,7 @@ typedef void (fsm_func_t)(struct vfio_ccw_private *, enum vfio_ccw_event);
 extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
 
 static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
-				     int event)
+				      enum vfio_ccw_event event)
 {
 	trace_vfio_ccw_fsm_event(private->sch->schid, private->state, event);
 	vfio_ccw_jumptable[private->state][event](private, event);