Merge tag 'libnvdimm-for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:

 - Fix a race condition in the teardown path of raw mode pmem
   namespaces.

 - Cleanup the code that filesystems use to detect filesystem-dax
   capabilities of their underlying block device.

* tag 'libnvdimm-for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  dax: remove bdev_dax_supported
  xfs: factor out a xfs_buftarg_is_dax helper
  dax: stub out dax_supported for !CONFIG_FS_DAX
  dax: remove __generic_fsdax_supported
  dax: move the dax_read_lock() locking into dax_supported
  dax: mark dax_get_by_host static
  dm: use fs_dax_get_by_bdev instead of dax_get_by_host
  dax: stop using bdevname
  fsdax: improve the FS_DAX Kconfig description and help text
  libnvdimm/pmem: Fix crash triggered when I/O in-flight during unbind

10 files changed, 120 insertions, 172 deletions

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 44736cbd446e..fc89e91beea7 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -17,6 +17,24 @@
 #include <linux/fs.h>
 #include "dax-private.h"
 
+/**
+ * struct dax_device - anchor object for dax services
+ * @inode: core vfs
+ * @cdev: optional character interface for "device dax"
+ * @host: optional name for lookups where the device path is not available
+ * @private: dax driver private data
+ * @flags: state and boolean properties
+ */
+struct dax_device {
+	struct hlist_node list;
+	struct inode inode;
+	struct cdev cdev;
+	const char *host;
+	void *private;
+	unsigned long flags;
+	const struct dax_operations *ops;
+};
+
 static dev_t dax_devt;
 DEFINE_STATIC_SRCU(dax_srcu);
 static struct vfsmount *dax_mnt;
@@ -40,6 +58,42 @@ void dax_read_unlock(int id)
 }
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
+static int dax_host_hash(const char *host)
+{
+	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
+}
+
+/**
+ * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
+ * @host: alternate name for the device registered by a dax driver
+ */
+static struct dax_device *dax_get_by_host(const char *host)
+{
+	struct dax_device *dax_dev, *found = NULL;
+	int hash, id;
+
+	if (!host)
+		return NULL;
+
+	hash = dax_host_hash(host);
+
+	id = dax_read_lock();
+	spin_lock(&dax_host_lock);
+	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
+		if (!dax_alive(dax_dev)
+				|| strcmp(host, dax_dev->host) != 0)
+			continue;
+
+		if (igrab(&dax_dev->inode))
+			found = dax_dev;
+		break;
+	}
+	spin_unlock(&dax_host_lock);
+	dax_read_unlock(id);
+
+	return found;
+}
+
 #ifdef CONFIG_BLOCK
 #include <linux/blkdev.h>
 
@@ -65,15 +119,13 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 	return dax_get_by_host(bdev->bd_disk->disk_name);
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-#endif
 
-bool __generic_fsdax_supported(struct dax_device *dax_dev,
+bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors)
 {
 	bool dax_enabled = false;
 	pgoff_t pgoff, pgoff_end;
-	char buf[BDEVNAME_SIZE];
 	void *kaddr, *end_kaddr;
 	pfn_t pfn, end_pfn;
 	sector_t last_page;
@@ -81,29 +133,25 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 	int err, id;
 
 	if (blocksize != PAGE_SIZE) {
-		pr_info("%s: error: unsupported blocksize for dax\n",
-				bdevname(bdev, buf));
+		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
 		return false;
 	}
 
 	if (!dax_dev) {
-		pr_debug("%s: error: dax unsupported by block device\n",
-				bdevname(bdev, buf));
+		pr_debug("%pg: error: dax unsupported by block device\n", bdev);
 		return false;
 	}
 
 	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
 	if (err) {
-		pr_info("%s: error: unaligned partition for dax\n",
-				bdevname(bdev, buf));
+		pr_info("%pg: error: unaligned partition for dax\n", bdev);
 		return false;
 	}
 
 	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
 	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
 	if (err) {
-		pr_info("%s: error: unaligned partition for dax\n",
-				bdevname(bdev, buf));
+		pr_info("%pg: error: unaligned partition for dax\n", bdev);
 		return false;
 	}
 
@@ -112,8 +160,8 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
 
 	if (len < 1 || len2 < 1) {
-		pr_info("%s: error: dax access failed (%ld)\n",
-				bdevname(bdev, buf), len < 1 ? len : len2);
+		pr_info("%pg: error: dax access failed (%ld)\n",
+				bdev, len < 1 ? len : len2);
 		dax_read_unlock(id);
 		return false;
 	}
@@ -147,57 +195,32 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 	dax_read_unlock(id);
 
 	if (!dax_enabled) {
-		pr_info("%s: error: dax support not enabled\n",
-				bdevname(bdev, buf));
+		pr_info("%pg: error: dax support not enabled\n", bdev);
 		return false;
 	}
 	return true;
 }
-EXPORT_SYMBOL_GPL(__generic_fsdax_supported);
+EXPORT_SYMBOL_GPL(generic_fsdax_supported);
 
-/**
- * __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @bdev: block device to check
- * @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: true if supported, false if unsupported
- */
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len)
 {
-	struct dax_device *dax_dev;
-	struct request_queue *q;
-	char buf[BDEVNAME_SIZE];
-	bool ret;
+	bool ret = false;
 	int id;
 
-	q = bdev_get_queue(bdev);
-	if (!q || !blk_queue_dax(q)) {
-		pr_debug("%s: error: request queue doesn't support dax\n",
-				bdevname(bdev, buf));
-		return false;
-	}
-
-	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
-	if (!dax_dev) {
-		pr_debug("%s: error: device does not support dax\n",
-				bdevname(bdev, buf));
+	if (!dax_dev)
 		return false;
-	}
 
 	id = dax_read_lock();
-	ret = dax_supported(dax_dev, bdev, blocksize, 0,
-			i_size_read(bdev->bd_inode) / 512);
+	if (dax_alive(dax_dev) && dax_dev->ops->dax_supported)
+		ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize,
+						  start, len);
 	dax_read_unlock(id);
-
-	put_dax(dax_dev);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__bdev_dax_supported);
-#endif
+EXPORT_SYMBOL_GPL(dax_supported);
+#endif /* CONFIG_FS_DAX */
+#endif /* CONFIG_BLOCK */
 
 enum dax_device_flags {
 	/* !alive + rcu grace period == no new operations / mappings */
@@ -208,24 +231,6 @@ enum dax_device_flags {
 	DAXDEV_SYNC,
 };
 
-/**
- * struct dax_device - anchor object for dax services
- * @inode: core vfs
- * @cdev: optional character interface for "device dax"
- * @host: optional name for lookups where the device path is not available
- * @private: dax driver private data
- * @flags: state and boolean properties
- */
-struct dax_device {
-	struct hlist_node list;
-	struct inode inode;
-	struct cdev cdev;
-	const char *host;
-	void *private;
-	unsigned long flags;
-	const struct dax_operations *ops;
-};
-
 static ssize_t write_cache_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -323,19 +328,6 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 }
 EXPORT_SYMBOL_GPL(dax_direct_access);
 
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len)
-{
-	if (!dax_dev)
-		return false;
-
-	if (!dax_alive(dax_dev))
-		return false;
-
-	return dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len);
-}
-EXPORT_SYMBOL_GPL(dax_supported);
-
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i)
 {
@@ -423,11 +415,6 @@ bool dax_alive(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(dax_alive);
 
-static int dax_host_hash(const char *host)
-{
-	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
-}
-
 /*
  * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring
  * that any fault handlers or operations that might have seen
@@ -625,38 +612,6 @@ void put_dax(struct dax_device *dax_dev)
 EXPORT_SYMBOL_GPL(put_dax);
 
 /**
- * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
- * @host: alternate name for the device registered by a dax driver
- */
-struct dax_device *dax_get_by_host(const char *host)
-{
-	struct dax_device *dax_dev, *found = NULL;
-	int hash, id;
-
-	if (!host)
-		return NULL;
-
-	hash = dax_host_hash(host);
-
-	id = dax_read_lock();
-	spin_lock(&dax_host_lock);
-	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
-		if (!dax_alive(dax_dev)
-				|| strcmp(host, dax_dev->host) != 0)
-			continue;
-
-		if (igrab(&dax_dev->inode))
-			found = dax_dev;
-		break;
-	}
-	spin_unlock(&dax_host_lock);
-	dax_read_unlock(id);
-
-	return found;
-}
-EXPORT_SYMBOL_GPL(dax_get_by_host);
-
-/**
  * inode_dax: convert a public inode into its dax_dev
  * @inode: An inode with i_cdev pointing to a dax_dev
  *
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index b03eabc1ed7c..2111daaacaba 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -809,14 +809,9 @@ EXPORT_SYMBOL_GPL(dm_table_set_type);
 int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
 			sector_t start, sector_t len, void *data)
 {
-	int blocksize = *(int *) data, id;
-	bool rc;
+	int blocksize = *(int *) data;
 
-	id = dax_read_lock();
-	rc = !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
-	dax_read_unlock(id);
-
-	return rc;
+	return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
 }
 
 /* Check devices support synchronous DAX */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 84e9145b1714..a011d09cb0fa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -654,7 +654,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 	}
 
 	td->dm_dev.bdev = bdev;
-	td->dm_dev.dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev);
 	return 0;
 }
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1e0615b8565e..72de88ff0d30 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -450,11 +450,11 @@ static int pmem_attach_disk(struct device *dev,
 		pmem->pfn_flags |= PFN_MAP;
 		bb_range = pmem->pgmap.range;
 	} else {
+		addr = devm_memremap(dev, pmem->phys_addr,
+				pmem->size, ARCH_MEMREMAP_PMEM);
 		if (devm_add_action_or_reset(dev, pmem_release_queue,
 					&pmem->pgmap))
 			return -ENOMEM;
-		addr = devm_memremap(dev, pmem->phys_addr,
-				pmem->size, ARCH_MEMREMAP_PMEM);
 		bb_range.start =  res->start;
 		bb_range.end = res->end;
 	}
diff --git a/fs/Kconfig b/fs/Kconfig
index d8207a1b8c44..c854725db417 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -43,7 +43,7 @@ source "fs/f2fs/Kconfig"
 source "fs/zonefs/Kconfig"
 
 config FS_DAX
-	bool "Direct Access (DAX) support"
+	bool "File system based Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
 	select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)
@@ -53,8 +53,23 @@ config FS_DAX
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,
 	  then you can avoid using the pagecache to buffer I/Os.  Turning
-	  on this option will compile in support for DAX; you will need to
-	  mount the filesystem using the -o dax option.
+	  on this option will compile in support for DAX.
+
+	  For a DAX device to support file system access it needs to have
+	  struct pages.  For the nfit based NVDIMMs this can be enabled
+	  using the ndctl utility:
+
+		# ndctl create-namespace --force --reconfig=namespace0.0 \
+			--mode=fsdax --map=mem
+
+	  See the 'create-namespace' man page for details on the overhead of
+	  --map=mem:
+	  https://docs.pmem.io/ndctl-user-guide/ndctl-man-pages/ndctl-create-namespace
+
+          For ndctl to work CONFIG_DEV_DAX needs to be enabled as well. For most
+	  file systems DAX support needs to be manually enabled globally or
+	  per-inode using a mount option as well.  See the file documentation in
+	  Documentation/filesystems/dax.rst for details.
 
 	  If you do not have a block device that is capable of using this,
 	  or if unsure, say N.  Saying Y will increase the size of the kernel
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index a8d49e8fc83a..11b88559f8bf 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -546,7 +546,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		return err;
 
 	if (test_opt(ctx, DAX_ALWAYS) &&
-	    !bdev_dax_supported(sb->s_bdev, EROFS_BLKSIZ)) {
+	    !dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) {
 		errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
 		clear_opt(ctx, DAX_ALWAYS);
 	}
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 987bcf32ed46..d8d580b609ba 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -946,7 +946,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (test_opt(sb, DAX)) {
-		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
+		if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
+				bdev_nr_sectors(sb->s_bdev))) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			clear_opt(sbi->s_mount_opt, DAX);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 136940af00b8..0775950ee84e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4287,7 +4287,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (bdev_dax_supported(sb->s_bdev, blocksize))
+	if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
+			bdev_nr_sectors(sb->s_bdev)))
 		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9a86d3ec2cb6..c4e0cd1c1c8c 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -330,6 +330,15 @@ xfs_set_inode_alloc(
 	return xfs_is_inode32(mp) ? maxagi : agcount;
 }
 
+static bool
+xfs_buftarg_is_dax(
+	struct super_block	*sb,
+	struct xfs_buftarg	*bt)
+{
+	return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0,
+			bdev_nr_sectors(bt->bt_bdev));
+}
+
 STATIC int
 xfs_blkdev_get(
 	xfs_mount_t		*mp,
@@ -1588,11 +1597,10 @@ xfs_fs_fill_super(
 		xfs_warn(mp,
 		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 
-		datadev_is_dax = bdev_dax_supported(mp->m_ddev_targp->bt_bdev,
-			sb->s_blocksize);
+		datadev_is_dax = xfs_buftarg_is_dax(sb, mp->m_ddev_targp);
 		if (mp->m_rtdev_targp)
-			rtdev_is_dax = bdev_dax_supported(
-				mp->m_rtdev_targp->bt_bdev, sb->s_blocksize);
+			rtdev_is_dax = xfs_buftarg_is_dax(sb,
+						mp->m_rtdev_targp);
 		if (!rtdev_is_dax && !datadev_is_dax) {
 			xfs_alert(mp,
 			"DAX unsupported by block device. Turning off DAX.");
diff --git a/include/linux/dax.h b/include/linux/dax.h
index b52f084aa643..2619d94c308d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -41,7 +41,6 @@ struct dax_operations {
 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, unsigned long flags);
 void put_dax(struct dax_device *dax_dev);
@@ -58,8 +57,6 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 	__set_dax_synchronous(dax_dev);
 }
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -73,10 +70,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	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, unsigned long flags)
 {
@@ -106,12 +99,6 @@ static inline bool dax_synchronous(struct dax_device *dax_dev)
 static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 }
-static inline bool dax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t len)
-{
-	return false;
-}
 static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 				struct dax_device *dax_dev)
 {
@@ -122,22 +109,12 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 struct writeback_control;
 int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
-static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
-{
-	return __bdev_dax_supported(bdev, blocksize);
-}
-
-bool __generic_fsdax_supported(struct dax_device *dax_dev,
+bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors);
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
-{
-	return __generic_fsdax_supported(dax_dev, bdev, blocksize, start,
-			sectors);
-}
+
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len);
 
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
@@ -153,15 +130,11 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
-static inline bool bdev_dax_supported(struct block_device *bdev,
-		int blocksize)
-{
-	return false;
-}
+#define generic_fsdax_supported		NULL
 
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
+static inline bool dax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
+		sector_t len)
 {
 	return false;
 }