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

5 files changed, 35 insertions, 10 deletions

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.");