Merge branch 'for-4.7/dax' into libnvdimm-for-next

20 files changed, 837 insertions, 594 deletions

diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 53c11621d5b1..7c8a3bf07884 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -88,4 +88,17 @@ config NVDIMM_PFN
 
 	  Select Y if unsure
 
+config NVDIMM_DAX
+	bool "NVDIMM DAX: Raw access to persistent memory"
+	default LIBNVDIMM
+	depends on NVDIMM_PFN
+	help
+	  Support raw device dax access to a persistent memory
+	  namespace.  For environments that want to hard partition
+	  peristent memory, this capability provides a mechanism to
+	  sub-divide a namespace into character devices that can only be
+	  accessed via DAX (mmap(2)).
+
+	  Select Y if unsure
+
 endif
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index ea84d3c4e8e5..909554c3f955 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -23,3 +23,4 @@ libnvdimm-y += label.o
 libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
 libnvdimm-$(CONFIG_BTT) += btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
+libnvdimm-$(CONFIG_NVDIMM_DAX) += dax_devs.o
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index e9ff9229d942..495e06d9f7e7 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -21,19 +21,19 @@
 #include <linux/sizes.h>
 #include "nd.h"
 
-struct nd_blk_device {
-	struct request_queue *queue;
-	struct gendisk *disk;
-	struct nd_namespace_blk *nsblk;
-	struct nd_blk_region *ndbr;
-	size_t disk_size;
-	u32 sector_size;
-	u32 internal_lbasize;
-};
+static u32 nsblk_meta_size(struct nd_namespace_blk *nsblk)
+{
+	return nsblk->lbasize - ((nsblk->lbasize >= 4096) ? 4096 : 512);
+}
+
+static u32 nsblk_internal_lbasize(struct nd_namespace_blk *nsblk)
+{
+	return roundup(nsblk->lbasize, INT_LBASIZE_ALIGNMENT);
+}
 
-static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
+static u32 nsblk_sector_size(struct nd_namespace_blk *nsblk)
 {
-	return blk_dev->nsblk->lbasize - blk_dev->sector_size;
+	return nsblk->lbasize - nsblk_meta_size(nsblk);
 }
 
 static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
@@ -57,20 +57,29 @@ static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
 	return SIZE_MAX;
 }
 
+static struct nd_blk_region *to_ndbr(struct nd_namespace_blk *nsblk)
+{
+	struct nd_region *nd_region;
+	struct device *parent;
+
+	parent = nsblk->common.dev.parent;
+	nd_region = container_of(parent, struct nd_region, dev);
+	return container_of(nd_region, struct nd_blk_region, nd_region);
+}
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
-				struct bio_integrity_payload *bip, u64 lba,
-				int rw)
+static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, u64 lba, int rw)
 {
-	unsigned int len = nd_blk_meta_size(blk_dev);
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
+	unsigned int len = nsblk_meta_size(nsblk);
 	resource_size_t	dev_offset, ns_offset;
-	struct nd_namespace_blk *nsblk;
-	struct nd_blk_region *ndbr;
+	u32 internal_lbasize, sector_size;
 	int err = 0;
 
-	nsblk = blk_dev->nsblk;
-	ndbr = blk_dev->ndbr;
-	ns_offset = lba * blk_dev->internal_lbasize + blk_dev->sector_size;
+	internal_lbasize = nsblk_internal_lbasize(nsblk);
+	sector_size = nsblk_sector_size(nsblk);
+	ns_offset = lba * internal_lbasize + sector_size;
 	dev_offset = to_dev_offset(nsblk, ns_offset, len);
 	if (dev_offset == SIZE_MAX)
 		return -EIO;
@@ -104,25 +113,26 @@ static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
 }
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
-static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
-				struct bio_integrity_payload *bip, u64 lba,
-				int rw)
+static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, u64 lba, int rw)
 {
 	return 0;
 }
 #endif
 
-static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
-			struct bio_integrity_payload *bip, struct page *page,
-			unsigned int len, unsigned int off, int rw,
-			sector_t sector)
+static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, struct page *page,
+		unsigned int len, unsigned int off, int rw, sector_t sector)
 {
-	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
 	resource_size_t	dev_offset, ns_offset;
+	u32 internal_lbasize, sector_size;
 	int err = 0;
 	void *iobuf;
 	u64 lba;
 
+	internal_lbasize = nsblk_internal_lbasize(nsblk);
+	sector_size = nsblk_sector_size(nsblk);
 	while (len) {
 		unsigned int cur_len;
 
@@ -132,11 +142,11 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 		 * Block Window setup/move steps. the do_io routine is capable
 		 * of handling len <= PAGE_SIZE.
 		 */
-		cur_len = bip ? min(len, blk_dev->sector_size) : len;
+		cur_len = bip ? min(len, sector_size) : len;
 
-		lba = div_u64(sector << SECTOR_SHIFT, blk_dev->sector_size);
-		ns_offset = lba * blk_dev->internal_lbasize;
-		dev_offset = to_dev_offset(blk_dev->nsblk, ns_offset, cur_len);
+		lba = div_u64(sector << SECTOR_SHIFT, sector_size);
+		ns_offset = lba * internal_lbasize;
+		dev_offset = to_dev_offset(nsblk, ns_offset, cur_len);
 		if (dev_offset == SIZE_MAX)
 			return -EIO;
 
@@ -147,13 +157,13 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 			return err;
 
 		if (bip) {
-			err = nd_blk_rw_integrity(blk_dev, bip, lba, rw);
+			err = nd_blk_rw_integrity(nsblk, bip, lba, rw);
 			if (err)
 				return err;
 		}
 		len -= cur_len;
 		off += cur_len;
-		sector += blk_dev->sector_size >> SECTOR_SHIFT;
+		sector += sector_size >> SECTOR_SHIFT;
 	}
 
 	return err;
@@ -161,10 +171,8 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 
 static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 {
-	struct block_device *bdev = bio->bi_bdev;
-	struct gendisk *disk = bdev->bd_disk;
 	struct bio_integrity_payload *bip;
-	struct nd_blk_device *blk_dev;
+	struct nd_namespace_blk *nsblk;
 	struct bvec_iter iter;
 	unsigned long start;
 	struct bio_vec bvec;
@@ -183,17 +191,17 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	bip = bio_integrity(bio);
-	blk_dev = disk->private_data;
+	nsblk = q->queuedata;
 	rw = bio_data_dir(bio);
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 
 		BUG_ON(len > PAGE_SIZE);
-		err = nd_blk_do_bvec(blk_dev, bip, bvec.bv_page, len,
-					bvec.bv_offset, rw, iter.bi_sector);
+		err = nsblk_do_bvec(nsblk, bip, bvec.bv_page, len,
+				bvec.bv_offset, rw, iter.bi_sector);
 		if (err) {
-			dev_info(&blk_dev->nsblk->common.dev,
+			dev_dbg(&nsblk->common.dev,
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
@@ -209,17 +217,16 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
-static int nd_blk_rw_bytes(struct nd_namespace_common *ndns,
+static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
 		resource_size_t offset, void *iobuf, size_t n, int rw)
 {
-	struct nd_blk_device *blk_dev = dev_get_drvdata(ndns->claim);
-	struct nd_namespace_blk *nsblk = blk_dev->nsblk;
-	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev);
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
 	resource_size_t	dev_offset;
 
 	dev_offset = to_dev_offset(nsblk, offset, n);
 
-	if (unlikely(offset + n > blk_dev->disk_size)) {
+	if (unlikely(offset + n > nsblk->size)) {
 		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
 		return -EFAULT;
 	}
@@ -235,51 +242,65 @@ static const struct block_device_operations nd_blk_fops = {
 	.revalidate_disk = nvdimm_revalidate_disk,
 };
 
-static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
-		struct nd_blk_device *blk_dev)
+static void nd_blk_release_queue(void *q)
+{
+	blk_cleanup_queue(q);
+}
+
+static void nd_blk_release_disk(void *disk)
+{
+	del_gendisk(disk);
+	put_disk(disk);
+}
+
+static int nsblk_attach_disk(struct nd_namespace_blk *nsblk)
 {
+	struct device *dev = &nsblk->common.dev;
 	resource_size_t available_disk_size;
+	struct request_queue *q;
 	struct gendisk *disk;
 	u64 internal_nlba;
 
-	internal_nlba = div_u64(blk_dev->disk_size, blk_dev->internal_lbasize);
-	available_disk_size = internal_nlba * blk_dev->sector_size;
+	internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk));
+	available_disk_size = internal_nlba * nsblk_sector_size(nsblk);
 
-	blk_dev->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!blk_dev->queue)
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
 		return -ENOMEM;
+	if (devm_add_action(dev, nd_blk_release_queue, q)) {
+		blk_cleanup_queue(q);
+		return -ENOMEM;
+	}
 
-	blk_queue_make_request(blk_dev->queue, nd_blk_make_request);
-	blk_queue_max_hw_sectors(blk_dev->queue, UINT_MAX);
-	blk_queue_bounce_limit(blk_dev->queue, BLK_BOUNCE_ANY);
-	blk_queue_logical_block_size(blk_dev->queue, blk_dev->sector_size);
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, blk_dev->queue);
+	blk_queue_make_request(q, nd_blk_make_request);
+	blk_queue_max_hw_sectors(q, UINT_MAX);
+	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
+	blk_queue_logical_block_size(q, nsblk_sector_size(nsblk));
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	q->queuedata = nsblk;
 
-	disk = blk_dev->disk = alloc_disk(0);
-	if (!disk) {
-		blk_cleanup_queue(blk_dev->queue);
+	disk = alloc_disk(0);
+	if (!disk)
+		return -ENOMEM;
+	if (devm_add_action(dev, nd_blk_release_disk, disk)) {
+		put_disk(disk);
 		return -ENOMEM;
 	}
 
-	disk->driverfs_dev	= &ndns->dev;
+	disk->driverfs_dev	= dev;
 	disk->first_minor	= 0;
 	disk->fops		= &nd_blk_fops;
-	disk->private_data	= blk_dev;
-	disk->queue		= blk_dev->queue;
+	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
-	nvdimm_namespace_disk_name(ndns, disk->disk_name);
+	nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name);
 	set_capacity(disk, 0);
 	add_disk(disk);
 
-	if (nd_blk_meta_size(blk_dev)) {
-		int rc = nd_integrity_init(disk, nd_blk_meta_size(blk_dev));
+	if (nsblk_meta_size(nsblk)) {
+		int rc = nd_integrity_init(disk, nsblk_meta_size(nsblk));
 
-		if (rc) {
-			del_gendisk(disk);
-			put_disk(disk);
-			blk_cleanup_queue(blk_dev->queue);
+		if (rc)
 			return rc;
-		}
 	}
 
 	set_capacity(disk, available_disk_size >> SECTOR_SHIFT);
@@ -291,56 +312,29 @@ static int nd_blk_probe(struct device *dev)
 {
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_blk *nsblk;
-	struct nd_blk_device *blk_dev;
-	int rc;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
 		return PTR_ERR(ndns);
 
-	blk_dev = kzalloc(sizeof(*blk_dev), GFP_KERNEL);
-	if (!blk_dev)
-		return -ENOMEM;
-
 	nsblk = to_nd_namespace_blk(&ndns->dev);
-	blk_dev->disk_size = nvdimm_namespace_capacity(ndns);
-	blk_dev->ndbr = to_nd_blk_region(dev->parent);
-	blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev);
-	blk_dev->internal_lbasize = roundup(nsblk->lbasize,
-						INT_LBASIZE_ALIGNMENT);
-	blk_dev->sector_size = ((nsblk->lbasize >= 4096) ? 4096 : 512);
-	dev_set_drvdata(dev, blk_dev);
-
-	ndns->rw_bytes = nd_blk_rw_bytes;
+	nsblk->size = nvdimm_namespace_capacity(ndns);
+	dev_set_drvdata(dev, nsblk);
+
+	ndns->rw_bytes = nsblk_rw_bytes;
 	if (is_nd_btt(dev))
-		rc = nvdimm_namespace_attach_btt(ndns);
-	else if (nd_btt_probe(ndns, blk_dev) == 0) {
+		return nvdimm_namespace_attach_btt(ndns);
+	else if (nd_btt_probe(dev, ndns) == 0) {
 		/* we'll come back as btt-blk */
-		rc = -ENXIO;
+		return -ENXIO;
 	} else
-		rc = nd_blk_attach_disk(ndns, blk_dev);
-	if (rc)
-		kfree(blk_dev);
-	return rc;
-}
-
-static void nd_blk_detach_disk(struct nd_blk_device *blk_dev)
-{
-	del_gendisk(blk_dev->disk);
-	put_disk(blk_dev->disk);
-	blk_cleanup_queue(blk_dev->queue);
+		return nsblk_attach_disk(nsblk);
 }
 
 static int nd_blk_remove(struct device *dev)
 {
-	struct nd_blk_device *blk_dev = dev_get_drvdata(dev);
-
 	if (is_nd_btt(dev))
-		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
-	else
-		nd_blk_detach_disk(blk_dev);
-	kfree(blk_dev);
-
+		nvdimm_namespace_detach_btt(to_nd_btt(dev));
 	return 0;
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index f068b6513cd2..cc9fafed9362 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1306,7 +1306,7 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	struct btt *btt;
 	struct device *dev = &nd_btt->dev;
 
-	btt = kzalloc(sizeof(struct btt), GFP_KERNEL);
+	btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL);
 	if (!btt)
 		return NULL;
 
@@ -1321,13 +1321,13 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	ret = discover_arenas(btt);
 	if (ret) {
 		dev_err(dev, "init: error in arena_discover: %d\n", ret);
-		goto out_free;
+		return NULL;
 	}
 
 	if (btt->init_state != INIT_READY && nd_region->ro) {
 		dev_info(dev, "%s is read-only, unable to init btt metadata\n",
 				dev_name(&nd_region->dev));
-		goto out_free;
+		return NULL;
 	} else if (btt->init_state != INIT_READY) {
 		btt->num_arenas = (rawsize / ARENA_MAX_SIZE) +
 			((rawsize % ARENA_MAX_SIZE) ? 1 : 0);
@@ -1337,29 +1337,25 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 		ret = create_arenas(btt);
 		if (ret) {
 			dev_info(dev, "init: create_arenas: %d\n", ret);
-			goto out_free;
+			return NULL;
 		}
 
 		ret = btt_meta_init(btt);
 		if (ret) {
 			dev_err(dev, "init: error in meta_init: %d\n", ret);
-			goto out_free;
+			return NULL;
 		}
 	}
 
 	ret = btt_blk_init(btt);
 	if (ret) {
 		dev_err(dev, "init: error in blk_init: %d\n", ret);
-		goto out_free;
+		return NULL;
 	}
 
 	btt_debugfs_init(btt);
 
 	return btt;
-
- out_free:
-	kfree(btt);
-	return NULL;
 }
 
 /**
@@ -1377,7 +1373,6 @@ static void btt_fini(struct btt *btt)
 		btt_blk_cleanup(btt);
 		free_arenas(btt);
 		debugfs_remove_recursive(btt->debugfs_dir);
-		kfree(btt);
 	}
 }
 
@@ -1406,9 +1401,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 }
 EXPORT_SYMBOL(nvdimm_namespace_attach_btt);
 
-int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns)
+int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt)
 {
-	struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
 	struct btt *btt = nd_btt->btt;
 
 	btt_fini(btt);
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index cb477518dd0e..816d0dae6398 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -273,10 +273,10 @@ static int __nd_btt_probe(struct nd_btt *nd_btt,
 	return 0;
 }
 
-int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
+int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns)
 {
 	int rc;
-	struct device *dev;
+	struct device *btt_dev;
 	struct btt_sb *btt_sb;
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
 
@@ -284,21 +284,19 @@ int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
 		return -ENODEV;
 
 	nvdimm_bus_lock(&ndns->dev);
-	dev = __nd_btt_create(nd_region, 0, NULL, ndns);
+	btt_dev = __nd_btt_create(nd_region, 0, NULL, ndns);
 	nvdimm_bus_unlock(&ndns->dev);
-	if (!dev)
+	if (!btt_dev)
 		return -ENOMEM;
-	dev_set_drvdata(dev, drvdata);
-	btt_sb = kzalloc(sizeof(*btt_sb), GFP_KERNEL);
-	rc = __nd_btt_probe(to_nd_btt(dev), ndns, btt_sb);
-	kfree(btt_sb);
-	dev_dbg(&ndns->dev, "%s: btt: %s\n", __func__,
-			rc == 0 ? dev_name(dev) : "<none>");
+	btt_sb = devm_kzalloc(dev, sizeof(*btt_sb), GFP_KERNEL);
+	rc = __nd_btt_probe(to_nd_btt(btt_dev), ndns, btt_sb);
+	dev_dbg(dev, "%s: btt: %s\n", __func__,
+			rc == 0 ? dev_name(btt_dev) : "<none>");
 	if (rc < 0) {
-		struct nd_btt *nd_btt = to_nd_btt(dev);
+		struct nd_btt *nd_btt = to_nd_btt(btt_dev);
 
-		__nd_detach_ndns(dev, &nd_btt->ndns);
-		put_device(dev);
+		__nd_detach_ndns(btt_dev, &nd_btt->ndns);
+		put_device(btt_dev);
 	}
 
 	return rc;
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 19f822d7f652..97589e3cb852 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -40,6 +40,8 @@ static int to_nd_device_type(struct device *dev)
 		return ND_DEVICE_REGION_PMEM;
 	else if (is_nd_blk(dev))
 		return ND_DEVICE_REGION_BLK;
+	else if (is_nd_dax(dev))
+		return ND_DEVICE_DAX_PMEM;
 	else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent))
 		return nd_region_to_nstype(to_nd_region(dev->parent));
 
@@ -246,6 +248,8 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie)
 
 void __nd_device_register(struct device *dev)
 {
+	if (!dev)
+		return;
 	dev->bus = &nvdimm_bus_type;
 	get_device(dev);
 	async_schedule_domain(nd_async_device_register, dev,
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index e8f03b0e95e4..5f53db59a058 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -12,6 +12,7 @@
  */
 #include <linux/device.h>
 #include <linux/sizes.h>
+#include <linux/pmem.h>
 #include "nd-core.h"
 #include "pfn.h"
 #include "btt.h"
@@ -84,6 +85,8 @@ static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
 		seed = nd_region->btt_seed;
 	else if (is_nd_pfn(dev))
 		seed = nd_region->pfn_seed;
+	else if (is_nd_dax(dev))
+		seed = nd_region->dax_seed;
 
 	if (seed == dev || ndns || dev->driver)
 		return false;
@@ -199,3 +202,63 @@ u64 nd_sb_checksum(struct nd_gen_sb *nd_gen_sb)
 	return sum;
 }
 EXPORT_SYMBOL(nd_sb_checksum);
+
+static int nsio_rw_bytes(struct nd_namespace_common *ndns,
+		resource_size_t offset, void *buf, size_t size, int rw)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+	if (unlikely(offset + size > nsio->size)) {
+		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
+		return -EFAULT;
+	}
+
+	if (rw == READ) {
+		unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
+
+		if (unlikely(is_bad_pmem(&nsio->bb, offset / 512, sz_align)))
+			return -EIO;
+		return memcpy_from_pmem(buf, nsio->addr + offset, size);
+	} else {
+		memcpy_to_pmem(nsio->addr + offset, buf, size);
+		wmb_pmem();
+	}
+
+	return 0;
+}
+
+int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio)
+{
+	struct resource *res = &nsio->res;
+	struct nd_namespace_common *ndns = &nsio->common;
+
+	nsio->size = resource_size(res);
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				dev_name(dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", res);
+		return -EBUSY;
+	}
+
+	ndns->rw_bytes = nsio_rw_bytes;
+	if (devm_init_badblocks(dev, &nsio->bb))
+		return -ENOMEM;
+	nvdimm_badblocks_populate(to_nd_region(ndns->dev.parent), &nsio->bb,
+			&nsio->res);
+
+	nsio->addr = devm_memremap(dev, res->start, resource_size(res),
+			ARCH_MEMREMAP_PMEM);
+	if (IS_ERR(nsio->addr))
+		return PTR_ERR(nsio->addr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_nsio_enable);
+
+void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio)
+{
+	struct resource *res = &nsio->res;
+
+	devm_memunmap(dev, nsio->addr);
+	devm_exit_badblocks(dev, &nsio->bb);
+	devm_release_mem_region(dev, res->start, resource_size(res));
+}
+EXPORT_SYMBOL_GPL(devm_nsio_disable);
diff --git a/drivers/nvdimm/dax_devs.c b/drivers/nvdimm/dax_devs.c
new file mode 100644
index 000000000000..f90f7549e7f4
--- /dev/null
+++ b/drivers/nvdimm/dax_devs.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include "nd-core.h"
+#include "nd.h"
+
+static void nd_dax_release(struct device *dev)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_dax *nd_dax = to_nd_dax(dev);
+	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+
+	dev_dbg(dev, "%s\n", __func__);
+	nd_detach_ndns(dev, &nd_pfn->ndns);
+	ida_simple_remove(&nd_region->dax_ida, nd_pfn->id);
+	kfree(nd_pfn->uuid);
+	kfree(nd_dax);
+}
+
+static struct device_type nd_dax_device_type = {
+	.name = "nd_dax",
+	.release = nd_dax_release,
+};
+
+bool is_nd_dax(struct device *dev)
+{
+	return dev ? dev->type == &nd_dax_device_type : false;
+}
+EXPORT_SYMBOL(is_nd_dax);
+
+struct nd_dax *to_nd_dax(struct device *dev)
+{
+	struct nd_dax *nd_dax = container_of(dev, struct nd_dax, nd_pfn.dev);
+
+	WARN_ON(!is_nd_dax(dev));
+	return nd_dax;
+}
+EXPORT_SYMBOL(to_nd_dax);
+
+static const struct attribute_group *nd_dax_attribute_groups[] = {
+	&nd_pfn_attribute_group,
+	&nd_device_attribute_group,
+	&nd_numa_attribute_group,
+	NULL,
+};
+
+static struct nd_dax *nd_dax_alloc(struct nd_region *nd_region)
+{
+	struct nd_pfn *nd_pfn;
+	struct nd_dax *nd_dax;
+	struct device *dev;
+
+	nd_dax = kzalloc(sizeof(*nd_dax), GFP_KERNEL);
+	if (!nd_dax)
+		return NULL;
+
+	nd_pfn = &nd_dax->nd_pfn;
+	nd_pfn->id = ida_simple_get(&nd_region->dax_ida, 0, 0, GFP_KERNEL);
+	if (nd_pfn->id < 0) {
+		kfree(nd_dax);
+		return NULL;
+	}
+
+	dev = &nd_pfn->dev;
+	dev_set_name(dev, "dax%d.%d", nd_region->id, nd_pfn->id);
+	dev->groups = nd_dax_attribute_groups;
+	dev->type = &nd_dax_device_type;
+	dev->parent = &nd_region->dev;
+
+	return nd_dax;
+}
+
+struct device *nd_dax_create(struct nd_region *nd_region)
+{
+	struct device *dev = NULL;
+	struct nd_dax *nd_dax;
+
+	if (!is_nd_pmem(&nd_region->dev))
+		return NULL;
+
+	nd_dax = nd_dax_alloc(nd_region);
+	if (nd_dax)
+		dev = nd_pfn_devinit(&nd_dax->nd_pfn, NULL);
+	__nd_device_register(dev);
+	return dev;
+}
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index f5cb88601359..c5e3196c45b0 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1288,6 +1288,8 @@ static ssize_t mode_show(struct device *dev,
 		mode = "safe";
 	else if (claim && is_nd_pfn(claim))
 		mode = "memory";
+	else if (claim && is_nd_dax(claim))
+		mode = "dax";
 	else if (!claim && pmem_should_map_pages(dev))
 		mode = "memory";
 	else
@@ -1379,21 +1381,19 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 {
 	struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL;
 	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
-	struct nd_namespace_common *ndns;
+	struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL;
+	struct nd_namespace_common *ndns = NULL;
 	resource_size_t size;
 
-	if (nd_btt || nd_pfn) {
-		struct device *host = NULL;
-
-		if (nd_btt) {
-			host = &nd_btt->dev;
+	if (nd_btt || nd_pfn || nd_dax) {
+		if (nd_btt)
 			ndns = nd_btt->ndns;
-		} else if (nd_pfn) {
-			host = &nd_pfn->dev;
+		else if (nd_pfn)
 			ndns = nd_pfn->ndns;
-		}
+		else if (nd_dax)
+			ndns = nd_dax->nd_pfn.ndns;
 
-		if (!ndns || !host)
+		if (!ndns)
 			return ERR_PTR(-ENODEV);
 
 		/*
@@ -1404,12 +1404,12 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 		device_unlock(&ndns->dev);
 		if (ndns->dev.driver) {
 			dev_dbg(&ndns->dev, "is active, can't bind %s\n",
-					dev_name(host));
+					dev_name(dev));
 			return ERR_PTR(-EBUSY);
 		}
-		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != host,
+		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != dev,
 					"host (%s) vs claim (%s) mismatch\n",
-					dev_name(host),
+					dev_name(dev),
 					dev_name(ndns->claim)))
 			return ERR_PTR(-ENXIO);
 	} else {
@@ -1784,6 +1784,18 @@ void nd_region_create_blk_seed(struct nd_region *nd_region)
 		nd_device_register(nd_region->ns_seed);
 }
 
+void nd_region_create_dax_seed(struct nd_region *nd_region)
+{
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	nd_region->dax_seed = nd_dax_create(nd_region);
+	/*
+	 * Seed creation failures are not fatal, provisioning is simply
+	 * disabled until memory becomes available
+	 */
+	if (!nd_region->dax_seed)
+		dev_err(&nd_region->dev, "failed to create dax namespace\n");
+}
+
 void nd_region_create_pfn_seed(struct nd_region *nd_region)
 {
 	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 1d1500f3d8b5..cb65308c0329 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -54,6 +54,7 @@ struct nd_region;
 void nd_region_create_blk_seed(struct nd_region *nd_region);
 void nd_region_create_btt_seed(struct nd_region *nd_region);
 void nd_region_create_pfn_seed(struct nd_region *nd_region);
+void nd_region_create_dax_seed(struct nd_region *nd_region);
 void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 875c524fafb0..46910b8f32b1 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -13,6 +13,7 @@
 #ifndef __ND_H__
 #define __ND_H__
 #include <linux/libnvdimm.h>
+#include <linux/badblocks.h>
 #include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
@@ -100,10 +101,12 @@ struct nd_region {
 	struct ida ns_ida;
 	struct ida btt_ida;
 	struct ida pfn_ida;
+	struct ida dax_ida;
 	unsigned long flags;
 	struct device *ns_seed;
 	struct device *btt_seed;
 	struct device *pfn_seed;
+	struct device *dax_seed;
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
@@ -160,6 +163,10 @@ struct nd_pfn {
 	struct nd_namespace_common *ndns;
 };
 
+struct nd_dax {
+	struct nd_pfn nd_pfn;
+};
+
 enum nd_async_mode {
 	ND_SYNC,
 	ND_ASYNC,
@@ -197,11 +204,12 @@ struct nd_gen_sb {
 
 u64 nd_sb_checksum(struct nd_gen_sb *sb);
 #if IS_ENABLED(CONFIG_BTT)
-int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata);
+int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_btt(struct device *dev);
 struct device *nd_btt_create(struct nd_region *nd_region);
 #else
-static inline int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
+static inline int nd_btt_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
 {
 	return -ENODEV;
 }
@@ -219,12 +227,16 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 
 struct nd_pfn *to_nd_pfn(struct device *dev);
 #if IS_ENABLED(CONFIG_NVDIMM_PFN)
-int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata);
+int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_pfn(struct device *dev);
 struct device *nd_pfn_create(struct nd_region *nd_region);
+struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
+		struct nd_namespace_common *ndns);
 int nd_pfn_validate(struct nd_pfn *nd_pfn);
+extern struct attribute_group nd_pfn_attribute_group;
 #else
-static inline int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
+static inline int nd_pfn_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
 {
 	return -ENODEV;
 }
@@ -245,6 +257,22 @@ static inline int nd_pfn_validate(struct nd_pfn *nd_pfn)
 }
 #endif
 
+struct nd_dax *to_nd_dax(struct device *dev);
+#if IS_ENABLED(CONFIG_NVDIMM_DAX)
+bool is_nd_dax(struct device *dev);
+struct device *nd_dax_create(struct nd_region *nd_region);
+#else
+static inline bool is_nd_dax(struct device *dev)
+{
+	return false;
+}
+
+static inline struct device *nd_dax_create(struct nd_region *nd_region)
+{
+	return NULL;
+}
+#endif
+
 struct nd_region *to_nd_region(struct device *dev);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
@@ -263,11 +291,32 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
 resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
 struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev);
 int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns);
-int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns);
+int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
 		struct badblocks *bb, const struct resource *res);
+#if IS_ENABLED(CONFIG_ND_CLAIM)
+struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap);
+int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio);
+void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio);
+#else
+static inline struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	return ERR_PTR(-ENXIO);
+}
+static inline int devm_nsio_enable(struct device *dev,
+