Merge tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull dax and libnvdimm updates from Dan Williams:
 "The bulk of this is a rework of the dax_operations API after
  discovering the obstacles it posed to the work-in-progress DAX+reflink
  support for XFS and other copy-on-write filesystem mechanics.

  Primarily the need to plumb a block_device through the API to handle
  partition offsets was a sticking point and Christoph untangled that
  dependency in addition to other cleanups to make landing the
  DAX+reflink support easier.

  The DAX_PMEM_COMPAT option has been around for 4 years and not only
  are distributions shipping userspace that understand the current
  configuration API, but some are not even bothering to turn this option
  on anymore, so it seems a good time to remove it per the deprecation
  schedule. Recall that this was added after the device-dax subsystem
  moved from /sys/class/dax to /sys/bus/dax for its sysfs organization.
  All recent functionality depends on /sys/bus/dax.

  Some other miscellaneous cleanups and reflink prep patches are
  included as well.

  Summary:

   - Simplify the dax_operations API:

      - Eliminate bdev_dax_pgoff() in favor of the filesystem
        maintaining and applying a partition offset to all its DAX iomap
        operations.

      - Remove wrappers and device-mapper stacked callbacks for
        ->copy_from_iter() and ->copy_to_iter() in favor of moving
        block_device relative offset responsibility to the
        dax_direct_access() caller.

      - Remove the need for an @bdev in filesystem-DAX infrastructure

      - Remove unused uio helpers copy_from_iter_flushcache() and
        copy_mc_to_iter() as only the non-check_copy_size() versions are
        used for DAX.

   - Prepare XFS for the pending (next merge window) DAX+reflink support

   - Remove deprecated DEV_DAX_PMEM_COMPAT support

   - Cleanup a straggling misuse of the GUID api"

* tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (38 commits)
  iomap: Fix error handling in iomap_zero_iter()
  ACPI: NFIT: Import GUID before use
  dax: remove the copy_from_iter and copy_to_iter methods
  dax: remove the DAXDEV_F_SYNC flag
  dax: simplify dax_synchronous and set_dax_synchronous
  uio: remove copy_from_iter_flushcache() and copy_mc_to_iter()
  iomap: turn the byte variable in iomap_zero_iter into a ssize_t
  memremap: remove support for external pgmap refcounts
  fsdax: don't require CONFIG_BLOCK
  iomap: build the block based code conditionally
  dax: fix up some of the block device related ifdefs
  fsdax: shift partition offset handling into the file systems
  dax: return the partition offset from fs_dax_get_by_bdev
  iomap: add a IOMAP_DAX flag
  xfs: pass the mapping flags to xfs_bmbt_to_iomap
  xfs: use xfs_direct_write_iomap_ops for DAX zeroing
  xfs: move dax device handling into xfs_{alloc,free}_buftarg
  ext4: cleanup the dax handling in ext4_fill_super
  ext2: cleanup the dax handling in ext2_fill_super
  fsdax: decouple zeroing from the iomap buffered I/O code
  ...

3 files changed, 24 insertions, 13 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 715ee206dfe1..71a3cdceaa03 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1699,6 +1699,7 @@ struct ext4_sb_info {
 	 */
 	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
+	u64 s_dax_part_off;
 #ifdef CONFIG_EXT4_DEBUG
 	unsigned long s_simulate_fail;
 #endif
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9dbeb772de60..5f79d265d06a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/iomap.h>
 #include <linux/iversion.h>
+#include <linux/dax.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -3253,7 +3254,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 
 static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 			   struct ext4_map_blocks *map, loff_t offset,
-			   loff_t length)
+			   loff_t length, unsigned int flags)
 {
 	u8 blkbits = inode->i_blkbits;
 
@@ -3270,8 +3271,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_NEW)
 		iomap->flags |= IOMAP_F_NEW;
 
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64) map->m_lblk << blkbits;
 	iomap->length = (u64) map->m_len << blkbits;
 
@@ -3291,9 +3294,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_UNWRITTEN) {
 		iomap->type = IOMAP_UNWRITTEN;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else if (map->m_flags & EXT4_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3330,8 +3337,8 @@ retry:
 	 * DAX and direct I/O are the only two operations that are currently
 	 * supported with IOMAP_WRITE.
 	 */
-	WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
-	if (IS_DAX(inode))
+	WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
+	if (flags & IOMAP_DAX)
 		m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
 	/*
 	 * We use i_size instead of i_disksize here because delalloc writeback
@@ -3402,7 +3409,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret < 0)
 		return ret;
 out:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 
 	return 0;
 }
@@ -3522,7 +3529,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 		delalloc = ext4_iomap_is_delalloc(inode, &map);
 
 set_iomap:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 	if (delalloc && iomap->type == IOMAP_HOLE)
 		iomap->type = IOMAP_DELALLOC;
 
@@ -3762,8 +3769,8 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		length = max;
 
 	if (IS_DAX(inode)) {
-		return iomap_zero_range(inode, from, length, NULL,
-					&ext4_iomap_ops);
+		return dax_zero_range(inode, from, length, NULL,
+				      &ext4_iomap_ops);
 	}
 	return __ext4_block_zero_page_range(handle, mapping, from, length);
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9a936ecbaa3b..0343f682504d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4338,7 +4338,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb)
 	if (!sbi)
 		return NULL;
 
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
@@ -4756,9 +4756,12 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount;
 	}
 
-	if (dax_supported(sbi->s_daxdev, 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_daxdev) {
+		if (blocksize == PAGE_SIZE)
+			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+		else
+			ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+	}
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {