Merge tag 'libnvdimm-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "Primarily just the virtio_pmem driver:

   - virtio_pmem

     The new virtio_pmem facility introduces a paravirtualized
     persistent memory device that allows a guest VM to use DAX
     mechanisms to access a host-file with host-page-cache. It arranges
     for MAP_SYNC to be disabled and instead triggers a host fsync()
     when a 'write-cache flush' command is sent to the virtual disk
     device.

   - Miscellaneous small fixups"

* tag 'libnvdimm-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  virtio_pmem: fix sparse warning
  xfs: disable map_sync for async flush
  ext4: disable map_sync for async flush
  dax: check synchronous mapping is supported
  dm: enable synchronous dax
  libnvdimm: add dax_dev sync flag
  virtio-pmem: Add virtio pmem driver
  libnvdimm: nd_region flush callback support
  libnvdimm, namespace: Drop uuid_t implementation detail

drivers/acpi/nfit/core.c

@@ -2426,7 +2426,7 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->addr.base + offset);
-	nvdimm_flush(nfit_blk->nd_region);
+	nvdimm_flush(nfit_blk->nd_region, NULL);
 
 	if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH)
 		readq(mmio->addr.base + offset);
@@ -2475,7 +2475,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 	}
 
 	if (rw)
-		nvdimm_flush(nfit_blk->nd_region);
+		nvdimm_flush(nfit_blk->nd_region, NULL);
 
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;

drivers/dax/bus.c

@@ -388,7 +388,7 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
 	 * No 'host' or dax_operations since there is no access to this
 	 * device outside of mmap of the resulting character device.
 	 */
-	dax_dev = alloc_dax(dev_dax, NULL, NULL);
+	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
 	if (!dax_dev)
 		goto err;
 

drivers/dax/super.c

@@ -195,6 +195,8 @@ enum dax_device_flags {
 	DAXDEV_ALIVE,
 	/* gate whether dax_flush() calls the low level flush routine */
 	DAXDEV_WRITE_CACHE,
+	/* flag to check if device supports synchronous flush */
+	DAXDEV_SYNC,
 };
 
 /**
@@ -372,6 +374,18 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
 
+bool __dax_synchronous(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(__dax_synchronous);
+
+void __set_dax_synchronous(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(__set_dax_synchronous);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
@@ -526,7 +540,7 @@ static void dax_add_host(struct dax_device *dax_dev, const char *host)
 }
 
 struct dax_device *alloc_dax(void *private, const char *__host,
-		const struct dax_operations *ops)
+		const struct dax_operations *ops, unsigned long flags)
 {
 	struct dax_device *dax_dev;
 	const char *host;
@@ -549,6 +563,9 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	dax_add_host(dax_dev, host);
 	dax_dev->ops = ops;
 	dax_dev->private = private;
+	if (flags & DAXDEV_F_SYNC)
+		set_dax_synchronous(dax_dev);
+
 	return dax_dev;
 
  err_dev:

drivers/md/dm-table.c

@@ -881,7 +881,7 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
 EXPORT_SYMBOL_GPL(dm_table_set_type);
 
 /* validate the dax capability of the target device span */
-static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 				       sector_t start, sector_t len, void *data)
 {
 	int blocksize = *(int *) data;
@@ -890,7 +890,15 @@ static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 			start, len);
 }
 
-bool dm_table_supports_dax(struct dm_table *t, int blocksize)
+/* Check devices support synchronous DAX */
+static int device_synchronous(struct dm_target *ti, struct dm_dev *dev,
+				       sector_t start, sector_t len, void *data)
+{
+	return dax_synchronous(dev->dax_dev);
+}
+
+bool dm_table_supports_dax(struct dm_table *t,
+			  iterate_devices_callout_fn iterate_fn, int *blocksize)
 {
 	struct dm_target *ti;
 	unsigned i;
@@ -903,8 +911,7 @@ bool dm_table_supports_dax(struct dm_table *t, int blocksize)
 			return false;
 
 		if (!ti->type->iterate_devices ||
-		    !ti->type->iterate_devices(ti, device_supports_dax,
-			    &blocksize))
+			!ti->type->iterate_devices(ti, iterate_fn, blocksize))
 			return false;
 	}
 
@@ -940,6 +947,7 @@ static int dm_table_determine_type(struct dm_table *t)
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
+	int page_size = PAGE_SIZE;
 
 	if (t->type != DM_TYPE_NONE) {
 		/* target already set the table's type */
@@ -984,7 +992,7 @@ static int dm_table_determine_type(struct dm_table *t)
 verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
-		if (dm_table_supports_dax(t, PAGE_SIZE) ||
+		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
 		} else {
@@ -1883,6 +1891,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
 	bool wc = false, fua = false;
+	int page_size = PAGE_SIZE;
 
 	/*
 	 * Copy table's limits to the DM device's request_queue
@@ -1910,8 +1919,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (dm_table_supports_dax(t, PAGE_SIZE))
+	if (dm_table_supports_dax(t, device_supports_dax, &page_size)) {
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+		if (dm_table_supports_dax(t, device_synchronous, NULL))
+			set_dax_synchronous(t->md->dax_dev);
+	}
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
 

drivers/md/dm.c

@@ -1117,7 +1117,7 @@ static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bd
 	if (!map)
 		return false;
 
-	ret = dm_table_supports_dax(map, blocksize);
+	ret = dm_table_supports_dax(map, device_supports_dax, &blocksize);
 
 	dm_put_live_table(md, srcu_idx);
 
@@ -1989,7 +1989,8 @@ static struct mapped_device *alloc_dev(int minor)
 	sprintf(md->disk->disk_name, "dm-%d", minor);
 
 	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
-		md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops);
+		md->dax_dev = alloc_dax(md, md->disk->disk_name,
+					&dm_dax_ops, 0);
 		if (!md->dax_dev)
 			goto bad;
 	}

drivers/md/dm.h

@@ -72,7 +72,10 @@ bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
-bool dm_table_supports_dax(struct dm_table *t, int blocksize);
+bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn,
+			   int *blocksize);
+int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+			   sector_t start, sector_t len, void *data);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);

drivers/nvdimm/Makefile

@@ -5,6 +5,7 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
 obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_OF_PMEM) += of_pmem.o
+obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o
 
 nd_pmem-y := pmem.o
 

drivers/nvdimm/claim.c

@@ -255,7 +255,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
 	sector_t sector = offset >> 9;
-	int rc = 0;
+	int rc = 0, ret = 0;
 
 	if (unlikely(!size))
 		return 0;
@@ -293,7 +293,9 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	}
 
 	memcpy_flushcache(nsio->addr + offset, buf, size);
-	nvdimm_flush(to_nd_region(ndns->dev.parent));
+	ret = nvdimm_flush(to_nd_region(ndns->dev.parent), NULL);
+	if (ret)
+		rc = ret;
 
 	return rc;
 }

drivers/nvdimm/namespace_devs.c

@@ -1822,8 +1822,8 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid,
 					&& !guid_equal(&nd_set->type_guid,
 						&nd_label->type_guid)) {
 				dev_dbg(ndd->dev, "expect type_guid %pUb got %pUb\n",
-						nd_set->type_guid.b,
-						nd_label->type_guid.b);
+						&nd_set->type_guid,
+						&nd_label->type_guid);
 				continue;
 			}
 
@@ -2227,8 +2227,8 @@ static struct device *create_namespace_blk(struct nd_region *nd_region,
 	if (namespace_label_has(ndd, type_guid)) {
 		if (!guid_equal(&nd_set->type_guid, &nd_label->type_guid)) {
 			dev_dbg(ndd->dev, "expect type_guid %pUb got %pUb\n",
-					nd_set->type_guid.b,
-					nd_label->type_guid.b);
+					&nd_set->type_guid,
+					&nd_label->type_guid);
 			return ERR_PTR(-EAGAIN);
 		}
 

drivers/nvdimm/nd.h

@@ -155,6 +155,7 @@ struct nd_region {
 	struct badblocks bb;
 	struct nd_interleave_set *nd_set;
 	struct nd_percpu_lane __percpu *lane;
+	int (*flush)(struct nd_region *nd_region, struct bio *bio);
 	struct nd_mapping mapping[0];
 };
 

drivers/nvdimm/nd_virtio.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * virtio_pmem.c: Virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and provides a virtio based flushing
+ * interface.
+ */
+#include "virtio_pmem.h"
+#include "nd.h"
+
+ /* The interrupt handler */
+void virtio_pmem_host_ack(struct virtqueue *vq)
+{
+	struct virtio_pmem *vpmem = vq->vdev->priv;
+	struct virtio_pmem_request *req_data, *req_buf;
+	unsigned long flags;
+	unsigned int len;
+
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	while ((req_data = virtqueue_get_buf(vq, &len)) != NULL) {
+		req_data->done = true;
+		wake_up(&req_data->host_acked);
+
+		if (!list_empty(&vpmem->req_list)) {
+			req_buf = list_first_entry(&vpmem->req_list,
+					struct virtio_pmem_request, list);
+			req_buf->wq_buf_avail = true;
+			wake_up(&req_buf->wq_buf);
+			list_del(&req_buf->list);
+		}
+	}
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_pmem_host_ack);
+
+ /* The request submission function */
+static int virtio_pmem_flush(struct nd_region *nd_region)
+{
+	struct virtio_device *vdev = nd_region->provider_data;
+	struct virtio_pmem *vpmem  = vdev->priv;
+	struct virtio_pmem_request *req_data;
+	struct scatterlist *sgs[2], sg, ret;
+	unsigned long flags;
+	int err, err1;
+
+	might_sleep();
+	req_data = kmalloc(sizeof(*req_data), GFP_KERNEL);
+	if (!req_data)
+		return -ENOMEM;
+
+	req_data->done = false;
+	init_waitqueue_head(&req_data->host_acked);
+	init_waitqueue_head(&req_data->wq_buf);
+	INIT_LIST_HEAD(&req_data->list);
+	req_data->req.type = cpu_to_le32(VIRTIO_PMEM_REQ_TYPE_FLUSH);
+	sg_init_one(&sg, &req_data->req, sizeof(req_data->req));
+	sgs[0] = &sg;
+	sg_init_one(&ret, &req_data->resp.ret, sizeof(req_data->resp));
+	sgs[1] = &ret;
+
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	 /*
+	  * If virtqueue_add_sgs returns -ENOSPC then req_vq virtual
+	  * queue does not have free descriptor. We add the request
+	  * to req_list and wait for host_ack to wake us up when free
+	  * slots are available.
+	  */
+	while ((err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req_data,
+					GFP_ATOMIC)) == -ENOSPC) {
+
+		dev_info(&vdev->dev, "failed to send command to virtio pmem device, no free slots in the virtqueue\n");
+		req_data->wq_buf_avail = false;
+		list_add_tail(&req_data->list, &vpmem->req_list);
+		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+
+		/* A host response results in "host_ack" getting called */
+		wait_event(req_data->wq_buf, req_data->wq_buf_avail);
+		spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	}
+	err1 = virtqueue_kick(vpmem->req_vq);
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+	/*
+	 * virtqueue_add_sgs failed with error different than -ENOSPC, we can't
+	 * do anything about that.
+	 */
+	if (err || !err1) {
+		dev_info(&vdev->dev, "failed to send command to virtio pmem device\n");
+		err = -EIO;
+	} else {
+		/* A host repsonse results in "host_ack" getting called */
+		wait_event(req_data->host_acked, req_data->done);
+		err = le32_to_cpu(req_data->resp.ret);
+	}
+
+	kfree(req_data);
+	return err;
+};
+
+/* The asynchronous flush callback function */
+int async_pmem_flush(struct nd_region *nd_region, struct bio *bio)
+{
+	/*
+	 * Create child bio for asynchronous flush and chain with
+	 * parent bio. Otherwise directly call nd_region flush.
+	 */
+	if (bio && bio->bi_iter.bi_sector != -1) {
+		struct bio *child = bio_alloc(GFP_ATOMIC, 0);
+
+		if (!child)
+			return -ENOMEM;
+		bio_copy_dev(child, bio);
+		child->bi_opf = REQ_PREFLUSH;
+		child->bi_iter.bi_sector = -1;
+		bio_chain(child, bio);
+		submit_bio(child);
+		return 0;
+	}
+	if (virtio_pmem_flush(nd_region))
+		return -EIO;
+
+	return 0;
+};
+EXPORT_SYMBOL_GPL(async_pmem_flush);
+MODULE_LICENSE("GPL");

drivers/nvdimm/pmem.c

@@ -184,6 +184,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 
 static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 {
+	int ret = 0;
 	blk_status_t rc = 0;
 	bool do_acct;
 	unsigned long start;
@@ -193,7 +194,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	struct nd_region *nd_region = to_region(pmem);
 
 	if (bio->bi_opf & REQ_PREFLUSH)
-		nvdimm_flush(nd_region);
+		ret = nvdimm_flush(nd_region, bio);
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
@@ -208,7 +209,10 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 		nd_iostat_end(bio, start);
 
 	if (bio->bi_opf & REQ_FUA)
-		nvdimm_flush(nd_region);
+		ret = nvdimm_flush(nd_region, bio);
+
+	if (ret)
+		bio->bi_status = errno_to_blk_status(ret);
 
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
@@ -362,6 +366,7 @@ static int pmem_attach_disk(struct device *dev,
 	struct gendisk *disk;
 	void *addr;
 	int rc;
+	unsigned long flags = 0UL;
 
 	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
 	if (!pmem)
@@ -457,14 +462,15 @@ static int pmem_attach_disk(struct device *dev,
 	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
 	disk->bb = &pmem->bb;
 
-	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
+	if (is_nvdimm_sync(nd_region))
+		flags = DAXDEV_F_SYNC;
+	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
 	if (!dax_dev) {
 		put_disk(disk);
 		return -ENOMEM;
 	}
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
-
 	gendev = disk_to_dev(disk);
 	gendev->groups = pmem_attribute_groups;
 
@@ -522,14 +528,14 @@ static int nd_pmem_remove(struct device *dev)
 		sysfs_put(pmem->bb_state);
 		pmem->bb_state = NULL;
 	}
-	nvdimm_flush(to_nd_region(dev->parent));
+	nvdimm_flush(to_nd_region(dev->parent), NULL);
 
 	return 0;
 }
 
 static void nd_pmem_shutdown(struct device *dev)
 {
-	nvdimm_flush(to_nd_region(dev->parent));
+	nvdimm_flush(to_nd_region(dev->parent), NULL);
 }
 
 static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)

drivers/nvdimm/region_devs.c

@@ -287,7 +287,9 @@ static ssize_t deep_flush_store(struct device *dev, struct device_attribute *att
 		return rc;
 	if (!flush)
 		return -EINVAL;
-	nvdimm_flush(nd_region);
+	rc = nvdimm_flush(nd_region, NULL);
+	if (rc)
+		return rc;
 
 	return len;
 }
@@ -1077,6 +1079,11 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	dev->of_node = ndr_desc->of_node;
 	nd_region->ndr_size = resource_size(ndr_desc->res);
 	nd_region->ndr_start = ndr_desc->res->start;
+	if (ndr_desc->flush)
+		nd_region->flush = ndr_desc->flush;
+	else
+		nd_region->flush = NULL;
+
 	nd_device_register(dev);
 
 	return nd_region;
@@ -1117,11 +1124,24 @@ struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
 }
 EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
 
+int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
+{
+	int rc = 0;
+
+	if (!nd_region->flush)
+		rc = generic_nvdimm_flush(nd_region);
+	else {
+		if (nd_region->flush(nd_region, bio))
+			rc = -EIO;
+	}
+
+	return rc;
+}
 /**
  * nvdimm_flush - flush any posted write queues between the cpu and pmem media
  * @nd_region: blk or interleaved pmem region
  */
-void nvdimm_flush(struct nd_region *nd_region)
+int generic_nvdimm_flush(struct nd_region *nd_region)
 {
 	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
 	int i, idx;
@@ -1145,6 +1165,8 @@ void nvdimm_flush(struct nd_region *nd_region)
 		if (ndrd_get_flush_wpq(ndrd, i, 0))
 			writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
 	wmb();
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nvdimm_flush);
 
@@ -1189,6 +1211,13 @@ int nvdimm_has_cache(struct nd_region *nd_region)
 }
 EXPORT_SYMBOL_GPL(nvdimm_has_cache);
 
+bool is_nvdimm_sync(struct nd_region *nd_region)
+{
+	return is_nd_pmem(&nd_region->dev) &&
+		!test_bit(ND_REGION_ASYNC, &nd_region->flags);
+}
+EXPORT_SYMBOL_GPL(is_nvdimm_sync);
+
 struct conflict_context {
 	struct nd_region *nd_region;
 	resource_size_t start, size;

drivers/nvdimm/virtio_pmem.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * virtio_pmem.c: Virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and registers the virtual pmem device
+ * with libnvdimm core.
+ */
+#include "virtio_pmem.h"
+#include "nd.h"
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+ /* Initialize virt queue */
+static int init_vq(struct virtio_pmem *vpmem)
+{
+	/* single vq */
+	vpmem->req_vq = virtio_find_single_vq(vpmem->vdev,
+					virtio_pmem_host_ack, "flush_queue");
+	if (IS_ERR(vpmem->req_vq))
+		return PTR_ERR(vpmem->req_vq);
+
+	spin_lock_init(&vpmem->pmem_lock);
+	INIT_LIST_HEAD(&vpmem->req_list);
+
+	return 0;
+};
+
+static int virtio_pmem_probe(struct virtio_device *vdev)
+{
+	struct nd_region_desc ndr_desc = {};
+	int nid = dev_to_node(&vdev->dev);
+	struct nd_region *nd_region;
+	struct virtio_pmem *vpmem;
+	struct resource res;
+	int err = 0;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem), GFP_KERNEL);
+	if (!vpmem) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	vpmem->vdev = vdev;
+	vdev->priv = vpmem;
+	err = init_vq(vpmem);
+	if (err) {
+		dev_err(&vdev->dev, "failed to initialize virtio pmem vq's\n");
+		goto out_err;
+	}
+
+	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+			start, &vpmem->start);
+	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+			size, &vpmem->size);
+
+	res.start = vpmem->start;
+	res.end   = vpmem->start + vpmem->size - 1;
+	vpmem->nd_desc.provider_name = "virtio-pmem";
+	vpmem->nd_desc.module = THIS_MODULE;
+
+	vpmem->nvdimm_bus = nvdimm_bus_register(&vdev->dev,
+						&vpmem->nd_desc);
+	if (!vpmem->nvdimm_bus) {
+		dev_err(&vdev->dev, "failed to register device with nvdimm_bus\n");
+		err = -ENXIO;
+		goto out_vq;
+	}
+
+	dev_set_drvdata(&vdev->dev, vpmem->nvdimm_bus);
+
+	ndr_desc.res = &res;
+	ndr_desc.numa_node = nid;
+	ndr_desc.flush = async_pmem_flush;
+	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
+	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
+	nd_region = nvdimm_pmem_region_create(vpmem->nvdimm_bus, &ndr_desc);
+	if (!nd_region) {
+		dev_err(&vdev->dev, "failed to create nvdimm region\n");
+		err = -ENXIO;
+		goto out_nd;
+	}
+	nd_region->provider_data = dev_to_virtio(nd_region->dev.parent->parent);
+	return 0;
+out_nd:
+	nvdimm_bus_unregister(vpmem->nvdimm_bus);
+out_vq:
+	vdev->config->del_vqs(vdev);
+out_err:
+	return err;
+}
+
+static void virtio_pmem_remove(struct virtio_device *vdev)
+{
+	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
+
+	nvdimm_bus_unregister(nvdimm_bus);
+	vdev->config->del_vqs(vdev);
+	vdev->config->reset(vdev);
+}
+
+static struct virtio_driver virtio_pmem_driver = {
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtio_pmem_probe,
+	.remove			= virtio_pmem_remove,
+};
+
+module_virtio_driver(virtio_pmem_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio pmem driver");
+MODULE_LICENSE("GPL");

drivers/nvdimm/virtio_pmem.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * virtio_pmem.h: virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and provides a virtio based flushing
+ * interface.
+ **/
+
+#ifndef _LINUX_VIRTIO_PMEM_H
+#define _LINUX_VIRTIO_PMEM_H
+
+#include <linux/module.h>
+#include <uapi/linux/virtio_pmem.h>
+#include <linux/libnvdimm.h>
+#include <linux/spinlock.h>
+
+struct virtio_pmem_request {
+	struct virtio_pmem_req req;
+	struct virtio_pmem_resp resp;
+
+	/* Wait queue to process deferred work after ack from host */
+	wait_queue_head_t host_acked;
+	bool done;
+
+	/* Wait queue to process deferred work after virt queue buffer avail */
+	wait_queue_head_t wq_buf;
+	bool wq_buf_avail;
+	struct list_head list;
+};
+
+struct virtio_pmem {
+	struct virtio_device *vdev;
+
+	/* Virtio pmem request queue */
+	struct virtqueue *req_vq;
+
+	/* nvdimm bus registers virtio pmem device */
+	struct nvdimm_bus *nvdimm_bus;
+	struct nvdimm_bus_descriptor nd_desc;
+
+	/* List to store deferred work if virtqueue is full */
+	struct list_head req_list;
+
+	/* Synchronize virtqueue data */
+	spinlock_t pmem_lock;
+
+	/* Memory region information */
+	__u64 start;
+	__u64 size;
+};
+
+void virtio_pmem_host_ack(struct virtqueue *vq);
+int async_pmem_flush(struct nd_region *nd_region, struct bio *bio);
+#endif

drivers/s390/block/dcssblk.c

@@ -679,7 +679,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 		goto put_dev;
 
 	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
-			&dcssblk_dax_ops);
+			&dcssblk_dax_ops, DAXDEV_F_SYNC);
 	if (!dev_info->dax_dev) {
 		rc = -ENOMEM;
 		goto put_dev;

drivers/virtio/Kconfig

@@ -43,6 +43,17 @@ config VIRTIO_PCI_LEGACY
 
 	  If unsure, say Y.
 
+config VIRTIO_PMEM
+	tristate "Support for virtio pmem driver"
+	depends on VIRTIO
+	depends on LIBNVDIMM
+	help
+	  This driver provides access to virtio-pmem devices, storage devices
+	  that are mapped into the physical address space - similar to NVDIMMs
+	   - with a virtio-based flushing interface.
+
+	  If unsure, say Y.
+
 config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO

fs/ext4/file.c

@@ -371,15 +371,17 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct dax_device *dax_dev = sbi->s_daxdev;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(sbi)))
 		return -EIO;
 
 	/*
-	 * We don't support synchronous mappings for non-DAX files. At least
-	 * until someone comes with a sensible use case.
+	 * We don't support synchronous mappings for non-DAX files and
+	 * for DAX files if underneath dax_device is not synchronous.
 	 */
-	if (!IS_DAX(file_inode(file)) && (vma->vm_flags & VM_SYNC))
+	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;
 
 	file_accessed(file);

fs/xfs/xfs_file.c

@@ -1197,11 +1197,14 @@ xfs_file_mmap(
 	struct file	*filp,
 	struct vm_area_struct *vma)
 {
+	struct dax_device 	*dax_dev;
+
+	dax_dev = xfs_find_daxdev_for_inode(file_inode(filp));
 	/*
-	 * We don't support synchronous mappings for non-DAX files. At least
-	 * until someone comes with a sensible use case.
+	 * We don't support synchronous mappings for non-DAX files and
+	 * for DAX files if underneath dax_device is not synchronous.
 	 */
-	if (!IS_DAX(file_inode(filp)) && (vma->vm_flags & VM_SYNC))
+	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;
 
 	file_accessed(filp);

include/linux/dax.h

@@ -7,6 +7,9 @@
 #include <linux/radix-tree.h>
 #include <asm/pgtable.h>
 
+/* Flag for synchronous flush */
+#define DAXDEV_F_SYNC (1UL << 0)
+
 typedef unsigned long dax_entry_t;
 
 struct iomap_ops;
@@ -38,18 +41,40 @@ extern struct attribute_group dax_attribute_group;
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *dax_get_by_host(const char *host);
 struct dax_device *alloc_dax(void *private, const char *host,
-		const struct dax_operations *ops);
+		const struct dax_operations *ops, unsigned long flags);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
+bool __dax_synchronous(struct dax_device *dax_dev);
+static inline bool dax_synchronous(struct dax_device *dax_dev)
+{
+	return  __dax_synchronous(dax_dev);
+}
+void __set_dax_synchronous(struct dax_device *dax_dev);
+static inline void set_dax_synchronous(struct dax_device *dax_dev)
+{
+	__set_dax_synchronous(dax_dev);
+}
+/*
+ * Check if given mapping is supported by the file / underlying device.
+ */
+static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
+					     struct dax_device *dax_dev)
+{
+	if (!(vma->vm_flags & VM_SYNC))
+		return true;
+	if (!IS_DAX(file_inode(vma->vm_file)))
+		return false;
+	return dax_synchronous(dax_dev);
+}
 #else
 static inline struct dax_device *dax_get_by_host(const char *host)
 {
 	return NULL;
 }
 static inline struct dax_device *alloc_dax(void *private, const char *host,
-		const struct dax_operations *ops)
+		const struct dax_operations *ops, unsigned long flags)
 {
 	/*
 	 * Callers should check IS_ENABLED(CONFIG_DAX) to know if this
@@ -70,6 +95,18 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
 {
 	return false;
 }
+static inline bool dax_synchronous(struct dax_device *dax_dev)
+{
+	return true;
+}
+static inline void set_dax_synchronous(struct dax_device *dax_dev)
+{
+}
+static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
+				struct dax_device *dax_dev)
+{
+	return !(vma->vm_flags & VM_SYNC);
+}
 #endif
 
 struct writeback_control;

include/linux/libnvdimm.h

@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/uuid.h>
 #include <linux/spinlock.h>
+#include <linux/bio.h>
 
 struct badrange_entry {
 	u64 start;
@@ -57,6 +58,9 @@ enum {
 	 */
 	ND_REGION_PERSIST_MEMCTRL = 2,
 
+	/* Platform provides asynchronous flush mechanism */
+	ND_REGION_ASYNC = 3,
+
 	/* mark newly adjusted resources as requiring a label update */
 	DPA_RESOURCE_ADJUSTED = 1 << 0,
 };
@@ -113,6 +117,7 @@ struct nd_mapping_desc {
 	int position;
 };
 
+struct nd_region;
 struct nd_region_desc {
 	struct resource *res;
 	struct nd_mapping_desc *mapping;
@@ -125,6 +130,7 @@ struct nd_region_desc {
 	int target_node;
 	unsigned long flags;
 	struct device_node *of_node;
+	int (*flush)(struct nd_region *nd_region, struct bio *bio);
 };
 
 struct device;
@@ -252,10 +258,12 @@ unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr);
 unsigned int nd_region_acquire_lane(struct nd_region *nd_region);
 void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane);
 u64 nd_fletcher64(void *addr, size_t len, bool le);
-void nvdimm_flush(struct nd_region *nd_region);
+int nvdimm_flush(struct nd_region *nd_region, struct bio *bio);
+int generic_nvdimm_flush(struct nd_region *nd_region);
 int nvdimm_has_flush(struct nd_region *nd_region);
 int nvdimm_has_cache(struct nd_region *nd_region);
 int nvdimm_in_overwrite(struct nvdimm *nvdimm);
+bool is_nvdimm_sync(struct nd_region *nd_region);
 
 static inline int nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc)

include/uapi/linux/virtio_ids.h

@@ -44,5 +44,6 @@
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
 #define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
+#define VIRTIO_ID_PMEM         27 /* virtio pmem */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

include/uapi/linux/virtio_pmem.h

+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Definitions for virtio-pmem devices.
+ *
+ * Copyright (C) 2019 Red Hat, Inc.
+ *
+ * Author(s): Pankaj Gupta <pagupta@redhat.com>
+ */
+
+#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
+#define _UAPI_LINUX_VIRTIO_PMEM_H
+
+#include <linux/types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+
+struct virtio_pmem_config {
+	__u64 start;
+	__u64 size;
+};
+
+#define VIRTIO_PMEM_REQ_TYPE_FLUSH      0
+
+struct virtio_pmem_resp {
+	/* Host return status corresponding to flush request */
+	__le32 ret;
+};
+
+struct virtio_pmem_req {
+	/* command type */
+	__le32 type;
+};
+
+#endif