Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm fixes from Dan Williams:
 "Incremental fixes and a small feature addition on top of the main
  libnvdimm 4.12 pull request:

   - Geert noticed that tinyconfig was bloated by BLOCK selecting DAX.
     The size regression is fixed by moving all dax helpers into the
     dax-core and only specifying "select DAX" for FS_DAX and
     dax-capable drivers. He also asked for clarification of the
     NR_DEV_DAX config option which, on closer look, does not need to be
     a config option at all. Mike also throws in a DEV_DAX_PMEM fixup
     for good measure.

   - Ben's attention to detail on -stable patch submissions caught a
     case where the recent fixes to arch_copy_from_iter_pmem() missed a
     condition where we strand dirty data in the cache. This is tagged
     for -stable and will also be included in the rework of the pmem api
     to a proposed {memcpy,copy_user}_flushcache() interface for 4.13.

   - Vishal adds a feature that missed the initial pull due to pending
     review feedback. It allows the kernel to clear media errors when
     initializing a BTT (atomic sector update driver) instance on a pmem
     namespace.

   - Ross noticed that the dax_device + dax_operations conversion broke
     __dax_zero_page_range(). The nvdimm unit tests fail to check this
     path, but xfstests immediately trips over it. No excuse for missing
     this before submitting the 4.12 pull request.

  These all pass the nvdimm unit tests and an xfstests spot check. The
  set has received a build success notification from the kbuild robot"

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  filesystem-dax: fix broken __dax_zero_page_range() conversion
  libnvdimm, btt: ensure that initializing metadata clears poison
  libnvdimm: add an atomic vs process context flag to rw_bytes
  x86, pmem: Fix cache flushing for iovec write < 8 bytes
  device-dax: kill NR_DEV_DAX
  block, dax: move "select DAX" from BLOCK to FS_DAX
  device-dax: Tell kbuild DEV_DAX_PMEM depends on DEV_DAX

19 files changed, 208 insertions, 136 deletions

diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d5a22ba..0ff8fe7 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -98,7 +98,7 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 
 		if (bytes < 8) {
 			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
-				arch_wb_cache_pmem(addr, 1);
+				arch_wb_cache_pmem(addr, bytes);
 		} else {
 			if (!IS_ALIGNED(dest, 8)) {
 				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
diff --git a/block/Kconfig b/block/Kconfig
index a8ad7e7..89cd28f 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -6,7 +6,6 @@ menuconfig BLOCK
        default y
        select SBITMAP
        select SRCU
-       select DAX
        help
 	 Provide block layer support for the kernel.
 
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index b7053ea..b79aa8f 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -19,7 +19,7 @@ config DEV_DAX
 
 config DEV_DAX_PMEM
 	tristate "PMEM DAX: direct access to persistent memory"
-	depends on LIBNVDIMM && NVDIMM_DAX
+	depends on LIBNVDIMM && NVDIMM_DAX && DEV_DAX
 	default DEV_DAX
 	help
 	  Support raw access to persistent memory.  Note that this
@@ -28,9 +28,4 @@ config DEV_DAX_PMEM
 
 	  Say Y if unsure
 
-config NR_DEV_DAX
-	int "Maximum number of Device-DAX instances"
-	default 32768
-	range 256 2147483647
-
 endif
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 465dcd7..ebf43f5 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -14,16 +14,13 @@
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/magic.h>
+#include <linux/genhd.h>
 #include <linux/cdev.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
 
-static int nr_dax = CONFIG_NR_DEV_DAX;
-module_param(nr_dax, int, S_IRUGO);
-MODULE_PARM_DESC(nr_dax, "max number of dax device instances");
-
 static dev_t dax_devt;
 DEFINE_STATIC_SRCU(dax_srcu);
 static struct vfsmount *dax_mnt;
@@ -47,6 +44,75 @@ void dax_read_unlock(int id)
 }
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
+int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
+		pgoff_t *pgoff)
+{
+	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
+
+	if (pgoff)
+		*pgoff = PHYS_PFN(phys_off);
+	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(bdev_dax_pgoff);
+
+/**
+ * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @sb: The superblock of the device
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: negative errno if unsupported, 0 if supported.
+ */
+int __bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+	struct block_device *bdev = sb->s_bdev;
+	struct dax_device *dax_dev;
+	pgoff_t pgoff;
+	int err, id;
+	void *kaddr;
+	pfn_t pfn;
+	long len;
+
+	if (blocksize != PAGE_SIZE) {
+		pr_err("VFS (%s): error: unsupported blocksize for dax\n",
+				sb->s_id);
+		return -EINVAL;
+	}
+
+	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+	if (err) {
+		pr_err("VFS (%s): error: unaligned partition for dax\n",
+				sb->s_id);
+		return err;
+	}
+
+	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev) {
+		pr_err("VFS (%s): error: device does not support dax\n",
+				sb->s_id);
+		return -EOPNOTSUPP;
+	}
+
+	id = dax_read_lock();
+	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
+	dax_read_unlock(id);
+
+	put_dax(dax_dev);
+
+	if (len < 1) {
+		pr_err("VFS (%s): error: dax access failed (%ld)",
+				sb->s_id, len);
+		return len < 0 ? len : -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__bdev_dax_supported);
+
 /**
  * struct dax_device - anchor object for dax services
  * @inode: core vfs
@@ -261,7 +327,7 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	if (__host && !host)
 		return NULL;
 
-	minor = ida_simple_get(&dax_minor_ida, 0, nr_dax, GFP_KERNEL);
+	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
 	if (minor < 0)
 		goto err_minor;
 
@@ -405,8 +471,7 @@ static int __init dax_fs_init(void)
 	if (rc)
 		return rc;
 
-	nr_dax = max(nr_dax, 256);
-	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
+	rc = alloc_chrdev_region(&dax_devt, 0, MINORMASK+1, "dax");
 	if (rc)
 		__dax_fs_exit();
 	return rc;
@@ -414,7 +479,7 @@ static int __init dax_fs_init(void)
 
 static void __exit dax_fs_exit(void)
 {
-	unregister_chrdev_region(dax_devt, nr_dax);
+	unregister_chrdev_region(dax_devt, MINORMASK+1);
 	ida_destroy(&dax_minor_ida);
 	__dax_fs_exit();
 }
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 9faaa96..822198a 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -218,7 +218,8 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
-		resource_size_t offset, void *iobuf, size_t n, int rw)
+		resource_size_t offset, void *iobuf, size_t n, int rw,
+		unsigned long flags)
 {
 	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev);
 	struct nd_blk_region *ndbr = to_ndbr(nsblk);
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 368795a..983718b 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -32,45 +32,53 @@ enum log_ent_request {
 };
 
 static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
-		void *buf, size_t n)
+		void *buf, size_t n, unsigned long flags)
 {
 	struct nd_btt *nd_btt = arena->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
 	/* arena offsets are 4K from the base of the device */
 	offset += SZ_4K;
-	return nvdimm_read_bytes(ndns, offset, buf, n);
+	return nvdimm_read_bytes(ndns, offset, buf, n, flags);
 }
 
 static int arena_write_bytes(struct arena_info *arena, resource_size_t offset,
-		void *buf, size_t n)
+		void *buf, size_t n, unsigned long flags)
 {
 	struct nd_btt *nd_btt = arena->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
 	/* arena offsets are 4K from the base of the device */
 	offset += SZ_4K;
-	return nvdimm_write_bytes(ndns, offset, buf, n);
+	return nvdimm_write_bytes(ndns, offset, buf, n, flags);
 }
 
 static int btt_info_write(struct arena_info *arena, struct btt_sb *super)
 {
 	int ret;
 
+	/*
+	 * infooff and info2off should always be at least 512B aligned.
+	 * We rely on that to make sure rw_bytes does error clearing
+	 * correctly, so make sure that is the case.
+	 */
+	WARN_ON_ONCE(!IS_ALIGNED(arena->infooff, 512));
+	WARN_ON_ONCE(!IS_ALIGNED(arena->info2off, 512));
+
 	ret = arena_write_bytes(arena, arena->info2off, super,
-			sizeof(struct btt_sb));
+			sizeof(struct btt_sb), 0);
 	if (ret)
 		return ret;
 
 	return arena_write_bytes(arena, arena->infooff, super,
-			sizeof(struct btt_sb));
+			sizeof(struct btt_sb), 0);
 }
 
 static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
 {
 	WARN_ON(!super);
 	return arena_read_bytes(arena, arena->infooff, super,
-			sizeof(struct btt_sb));
+			sizeof(struct btt_sb), 0);
 }
 
 /*
@@ -79,16 +87,17 @@ static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
  *   mapping is in little-endian
  *   mapping contains 'E' and 'Z' flags as desired
  */
-static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping)
+static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping,
+		unsigned long flags)
 {
 	u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
 
 	WARN_ON(lba >= arena->external_nlba);
-	return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE);
+	return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE, flags);
 }
 
 static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
-			u32 z_flag, u32 e_flag)
+			u32 z_flag, u32 e_flag, unsigned long rwb_flags)
 {
 	u32 ze;
 	__le32 mapping_le;
@@ -127,11 +136,11 @@ static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
 	}
 
 	mapping_le = cpu_to_le32(mapping);
-	return __btt_map_write(arena, lba, mapping_le);
+	return __btt_map_write(arena, lba, mapping_le, rwb_flags);
 }
 
 static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
-			int *trim, int *error)
+			int *trim, int *error, unsigned long rwb_flags)
 {
 	int ret;
 	__le32 in;
@@ -140,7 +149,7 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
 
 	WARN_ON(lba >= arena->external_nlba);
 
-	ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE);
+	ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE, rwb_flags);
 	if (ret)
 		return ret;
 
@@ -189,7 +198,7 @@ static int btt_log_read_pair(struct arena_info *arena, u32 lane,
 	WARN_ON(!ent);
 	return arena_read_bytes(arena,
 			arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
-			2 * LOG_ENT_SIZE);
+			2 * LOG_ENT_SIZE, 0);
 }
 
 static struct dentry *debugfs_root;
@@ -335,7 +344,7 @@ static int btt_log_read(struct arena_info *arena, u32 lane,
  * btt_flog_write is the wrapper for updating the freelist elements
  */
 static int __btt_log_write(struct arena_info *arena, u32 lane,
-			u32 sub, struct log_entry *ent)
+			u32 sub, struct log_entry *ent, unsigned long flags)
 {
 	int ret;
 	/*
@@ -350,13 +359,13 @@ static int __btt_log_write(struct arena_info *arena, u32 lane,
 	void *src = ent;
 
 	/* split the 16B write into atomic, durable halves */
-	ret = arena_write_bytes(arena, ns_off, src, log_half);
+	ret = arena_write_bytes(arena, ns_off, src, log_half, flags);
 	if (ret)
 		return ret;
 
 	ns_off += log_half;
 	src += log_half;
-	return arena_write_bytes(arena, ns_off, src, log_half);
+	return arena_write_bytes(arena, ns_off, src, log_half, flags);
 }
 
 static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
@@ -364,7 +373,7 @@ static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
 {
 	int ret;
 
-	ret = __btt_log_write(arena, lane, sub, ent);
+	ret = __btt_log_write(arena, lane, sub, ent, NVDIMM_IO_ATOMIC);
 	if (ret)
 		return ret;
 
@@ -393,11 +402,19 @@ static int btt_map_init(struct arena_info *arena)
 	if (!zerobuf)
 		return -ENOMEM;
 
+	/*
+	 * mapoff should always be at least 512B  aligned. We rely on that to
+	 * make sure rw_bytes does error clearing correctly, so make sure that
+	 * is the case.
+	 */
+	WARN_ON_ONCE(!IS_ALIGNED(arena->mapoff, 512));
+
 	while (mapsize) {
 		size_t size = min(mapsize, chunk_size);
 
+		WARN_ON_ONCE(size < 512);
 		ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf,
-				size);
+				size, 0);
 		if (ret)
 			goto free;
 
@@ -417,26 +434,50 @@ static int btt_map_init(struct arena_info *arena)
  */
 static int btt_log_init(struct arena_info *arena)
 {
+	size_t logsize = arena->info2off - arena->logoff;
+	size_t chunk_size = SZ_4K, offset = 0;
+	struct log_entry log;
+	void *zerobuf;
 	int ret;
 	u32 i;
-	struct log_entry log, zerolog;
 
-	memset(&zerolog, 0, sizeof(zerolog));
+	zerobuf = kzalloc(chunk_size, GFP_KERNEL);
+	if (!zerobuf)
+		return -ENOMEM;
+	/*
+	 * logoff should always be at least 512B  aligned. We rely on that to
+	 * make sure rw_bytes does error clearing correctly, so make sure that
+	 * is the case.
+	 */
+	WARN_ON_ONCE(!IS_ALIGNED(arena->logoff, 512));
+
+	while (logsize) {
+		size_t size = min(logsize, chunk_size);
+
+		WARN_ON_ONCE(size < 512);
+		ret = arena_write_bytes(arena, arena->logoff + offset, zerobuf,
+				size, 0);
+		if (ret)
+			goto free;
+
+		offset += size;
+		logsize -= size;
+		cond_resched();
+	}
 
 	for (i = 0; i < arena->nfree; i++) {
 		log.lba = cpu_to_le32(i);
 		log.old_map = cpu_to_le32(arena->external_nlba + i);
 		log.new_map = cpu_to_le32(arena->external_nlba + i);
 		log.seq = cpu_to_le32(LOG_SEQ_INIT);
-		ret = __btt_log_write(arena, i, 0, &log);
-		if (ret)
-			return ret;
-		ret = __btt_log_write(arena, i, 1, &zerolog);
+		ret = __btt_log_write(arena, i, 0, &log, 0);
 		if (ret)
-			return ret;
+			goto free;
 	}
 
-	return 0;
+ free:
+	kfree(zerobuf);
+	return ret;
 }
 
 static int btt_freelist_init(struct arena_info *arena)
@@ -470,7 +511,7 @@ static int btt_freelist_init(struct arena_info *arena)
 
 		/* Check if map recovery is needed */
 		ret = btt_map_read(arena, le32_to_cpu(log_new.lba), &map_entry,
-				NULL, NULL);
+				NULL, NULL, 0);
 		if (ret)
 			return ret;
 		if ((le32_to_cpu(log_new.new_map) != map_entry) &&
@@ -480,7 +521,7 @@ static int btt_freelist_init(struct arena_info *arena)
 			 * to complete the map write. So fix up the map.
 			 */
 			ret = btt_map_write(arena, le32_to_cpu(log_new.lba),
-					le32_to_cpu(log_new.new_map), 0, 0);
+					le32_to_cpu(log_new.new_map), 0, 0, 0);
 			if (ret)
 				return ret;
 		}
@@ -875,7 +916,7 @@ static int btt_data_read(struct arena_info *arena, struct page *page,
 	u64 nsoff = to_namespace_offset(arena, lba);
 	void *mem = kmap_atomic(page);
 
-	ret = arena_read_bytes(arena, nsoff, mem + off, len);
+	ret = arena_read_bytes(arena, nsoff, mem + off, len, NVDIMM_IO_ATOMIC);
 	kunmap_atomic(mem);
 
 	return ret;
@@ -888,7 +929,7 @@ static int btt_data_write(struct arena_info *arena, u32 lba,
 	u64 nsoff = to_namespace_offset(arena, lba);
 	void *mem = kmap_atomic(page);
 
-	ret = arena_write_bytes(arena, nsoff, mem + off, len);
+	ret = arena_write_bytes(arena, nsoff, mem + off, len, NVDIMM_IO_ATOMIC);
 	kunmap_atomic(mem);
 
 	return ret;
@@ -931,10 +972,12 @@ static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
 		mem = kmap_atomic(bv.bv_page);
 		if (rw)
 			ret = arena_write_bytes(arena, meta_nsoff,
-					mem + bv.bv_offset, cur_len);
+					mem + bv.bv_offset, cur_len,
+					NVDIMM_IO_ATOMIC);
 		else
 			ret = arena_read_bytes(arena, meta_nsoff,
-					mem + bv.bv_offset, cur_len);
+					mem + bv.bv_offset, cur_len,
+					NVDIMM_IO_ATOMIC);
 
 		kunmap_atomic(mem);
 		if (ret)
@@ -976,7 +1019,8 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 		cur_len = min(btt->sector_size, len);
 
-		ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag);
+		ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag,
+				NVDIMM_IO_ATOMIC);
 		if (ret)
 			goto out_lane;
 
@@ -1006,7 +1050,7 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
 			barrier();
 
 			ret = btt_map_read(arena, premap, &new_map, &t_flag,
-						&e_flag);
+						&e_flag, NVDIMM_IO_ATOMIC);
 			if (ret)
 				goto out_rtt;
 
@@ -1093,7 +1137,8 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 		}
 
 		lock_map(arena, premap);
-		ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL);
+		ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL,
+				NVDIMM_IO_ATOMIC);
 		if (ret)
 			goto out_map;
 		if (old_postmap >= arena->internal_nlba) {
@@ -1110,7 +1155,7 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 		if (ret)
 			goto out_map;
 
-		ret = btt_map_write(arena, premap, new_postmap, 0, 0);
+		ret = btt_map_write(arena, premap, new_postmap, 0, 0, 0);
 		if (ret)
 			goto out_map;
 
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index 4b76af2..ae00dc0 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -273,7 +273,7 @@ static int __nd_btt_probe(struct nd_btt *nd_btt,
 	if (!btt_sb || !ndns || !nd_btt)
 		return -ENODEV;
 
-	if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb)))
+	if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb), 0))
 		return -ENXIO;
 
 	if (nvdimm_namespace_capacity(ndns) < SZ_16M)
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 93d128d..7ceb5fa 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -228,7 +228,8 @@ u64 nd_sb_checksum(struct nd_gen_sb *nd_gen_sb)
 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)
+		resource_size_t offset, void *buf, size_t size, int rw,
+		unsigned long flags)
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
@@ -259,7 +260,8 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 		 * work around this collision.
 		 */
 		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
-				&& (!ndns->claim || !is_nd_btt(ndns->claim))) {
+				&& !(flags & NVDIMM_IO_ATOMIC)
+				&& !ndns->claim) {
 			long cleared;
 
 			cleared = nvdimm_clear_poison(&ndns->dev,
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 77d0321..03852d7 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -31,6 +31,7 @@ enum {
 	ND_MAX_LANES = 256,
 	SECTOR_SHIFT = 9,
 	INT_LBASIZE_ALIGNMENT = 64,
+	NVDIMM_IO_ATOMIC = 1,
 };
 
 struct nd_poison {
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 335c817..a6c4036 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -357,7 +357,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 	if (!is_nd_pmem(nd_pfn->dev.parent))
 		return -ENODEV;
 
-	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
+	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0))
 		return -ENXIO;
 
 	if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
@@ -662,7 +662,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);
 
-	return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
+	return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0);
 }
 
 /*
diff --git a/fs/Kconfig b/fs/Kconfig
index 83eab52..b0e42b6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -39,6 +39,7 @@ config FS_DAX
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
 	select FS_IOMAP
+	select DAX
 	help
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2a305c1..519599d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -717,72 +717,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
-int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
-		pgoff_t *pgoff)
-{
-	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
-
-	if (pgoff)
-		*pgoff = PHYS_PFN(phys_off);
-	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
-		return -EINVAL;
-	return 0;
-}
-EXPORT_SYMBOL(bdev_dax_pgoff);
-
-/**
- * bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
- * @blocksize: The block size of the device
- *
- * This is a library function for filesystems to check if the block device
- * can be mounted with dax option.
- *
- * Return: negative errno if unsupported, 0 if supported.
- */
-int bdev_dax_supported(struct super_block *sb, int blocksize)
-{
-	struct block_device *bdev = sb->s_bdev;
-	struct dax_device *dax_dev;
-	pgoff_t pgoff;
-	int err, id;
-	void *kaddr;
-	pfn_t pfn;
-	long len;
-
-	if (blocksize != PAGE_SIZE) {
-		vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
-		return -EINVAL;
-	}
-
-	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
-	if (err) {
-		vfs_msg(sb, KERN_ERR, "error: unaligned partition for dax");
-		return err;
-	}
-
-	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
-	if (!dax_dev) {
-		vfs_msg(sb, KERN_ERR, "error: device does not support dax");
-		return -EOPNOTSUPP;
-	}
-
-	id = dax_read_lock();
-	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
-	dax_read_unlock(id);
-
-	put_dax(dax_dev);
-
-	if (len < 1) {
-		vfs_msg(sb, KERN_ERR,
-				"error: dax access failed (%ld)", len);
-		return len < 0 ? len : -EIO;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bdev_dax_supported);
-
 /*
  * pseudo-fs
  */
diff --git a/fs/dax.c b/fs/dax.c
index 66d7906..18fe9bb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -993,12 +993,12 @@ int __dax_zero_page_range(struct block_device *bdev,
 		void *kaddr;
 		pfn_t pfn;
 
-		rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+		rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
 		if (rc)
 			return rc;
 
 		id = dax_read_lock();
-		rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr,
+		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr,
 				&pfn);
 		if (rc < 0) {
 			dax_read_unlock(id);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 8ac673c..9c2028b 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -32,6 +32,7 @@
 #include <linux/log2.h>
 #include <linux/quotaops.h>
 #include <linux/uaccess.h>
+#include <linux/dax.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c90edf0..0b177da 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -37,6 +37,7 @@
 #include <linux/ctype.h>
 #include <linux/log2.h>
 #include <linux/crc16.h>
+#include <linux/dax.h>
 #include <linux/cleancache.h>
 #include <linux/uaccess.h>
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 47d239d..455a575 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -52,6 +52,7 @@
 #include "xfs_reflink.h"
 
 #include <linux/namei.h>
+#include <linux/dax.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b5d1e27..ab92c4e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1947,8 +1947,6 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
-extern int bdev_dax_supported(struct super_block *, int);
-int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index d3158e7..7fdf1d7 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -18,12 +18,38 @@ struct dax_operations {
 			void **, pfn_t *);
 };
 
+int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
+#if IS_ENABLED(CONFIG_FS_DAX)
+int __bdev_dax_supported(struct super_block *sb, int blocksize);
+static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+	return __bdev_dax_supported(sb, blocksize);
+}
+#else
+static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_DAX)
+struct dax_device *dax_get_by_host(const char *host);
+void put_dax(struct dax_device *dax_dev);
+#else
+static inline struct dax_device *dax_get_by_host(const char *host)
+{
+	return NULL;
+}
+
+static inline void put_dax(struct dax_device *dax_dev)
+{
+}
+#endif
+
 int dax_read_lock(void);
 void dax_read_unlock(int id);
-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);
-void put_dax(struct dax_device *dax_dev);
 bool dax_alive(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
diff --git a/include/linux/nd.h b/include/linux/nd.h
index fa66aee..194b8e0 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -48,7 +48,7 @@ struct nd_namespace_common {
 	struct device dev;
 	struct device *claim;
 	int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset,
-			void *buf, size_t size, int rw);
+			void *buf, size_t size, int rw, unsigned long flags);
 };
 
 static inline struct nd_namespace_common *to_ndns(struct device *dev)
@@ -134,9 +134,10 @@ static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *
  * @buf is up-to-date upon return from this routine.
  */
 static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns,
-		resource_size_t offset, void *buf, size_t size)
+		resource_size_t offset, void *buf, size_t size,
+		unsigned long flags)
 {
-	return ndns->rw_bytes(ndns, offset, buf, size, READ);
+	return ndns->rw_bytes(ndns, offset, buf, size, READ, flags);
 }
 
 /**
@@ -152,9 +153,10 @@ static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns,
  * to media is handled internal to the @ndns driver, if at all.
  */
 static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns,
-		resource_size_t offset, void *buf, size_t size)
+		resource_size_t offset, void *buf, size_t size,
+		unsigned long flags)
 {
-	return ndns->rw_bytes(ndns, offset, buf, size, WRITE);
+	return ndns->rw_bytes(ndns, offset, buf, size, WRITE, flags);
 }
 
 #define MODULE_ALIAS_ND_DEVICE(type) \