Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

15 files changed, 386 insertions, 22 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 1131dd01e4fe..03135a1c31b6 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -130,6 +130,11 @@ xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
 xfs-$(CONFIG_EXPORTFS_BLOCK_OPS)	+= xfs_pnfs.o
 
+# notify failure
+ifeq ($(CONFIG_MEMORY_FAILURE),y)
+xfs-$(CONFIG_FS_DAX)		+= xfs_notify_failure.o
+endif
+
 # online scrub/repair
 ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 584afe076923..dde346450952 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -5,6 +5,7 @@
  */
 #include "xfs.h"
 #include <linux/backing-dev.h>
+#include <linux/dax.h>
 
 #include "xfs_shared.h"
 #include "xfs_format.h"
@@ -1944,7 +1945,7 @@ xfs_free_buftarg(
 	list_lru_destroy(&btp->bt_lru);
 
 	blkdev_issue_flush(btp->bt_bdev);
-	fs_put_dax(btp->bt_daxdev);
+	fs_put_dax(btp->bt_daxdev, btp->bt_mount);
 
 	kmem_free(btp);
 }
@@ -1991,13 +1992,18 @@ xfs_alloc_buftarg(
 	struct block_device	*bdev)
 {
 	xfs_buftarg_t		*btp;
+	const struct dax_holder_operations *ops = NULL;
 
+#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE)
+	ops = &xfs_dax_holder_operations;
+#endif
 	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
 
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
+	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off,
+					    mp, ops);
 
 	/*
 	 * Buffer IO error rate limiting. Limit it to no more than 10 messages
@@ -2019,7 +2025,8 @@ xfs_alloc_buftarg(
 	btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
 	btp->bt_shrinker.seeks = DEFAULT_SEEKS;
 	btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE;
-	if (register_shrinker(&btp->bt_shrinker))
+	if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s",
+			      mp->m_super->s_id))
 		goto error_pcpu;
 	return btp;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8d9b14d2b912..aa7e458ab169 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -25,6 +25,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 
+#include <linux/dax.h>
 #include <linux/falloc.h>
 #include <linux/backing-dev.h>
 #include <linux/mman.h>
@@ -669,7 +670,7 @@ xfs_file_dax_write(
 	pos = iocb->ki_pos;
 
 	trace_xfs_file_dax_write(iocb, from);
-	ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
@@ -806,7 +807,7 @@ xfs_wait_dax_page(
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 }
 
-static int
+int
 xfs_break_dax_layouts(
 	struct inode		*inode,
 	bool			*retry)
@@ -1253,6 +1254,31 @@ xfs_file_llseek(
 	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
+#ifdef CONFIG_FS_DAX
+static int
+xfs_dax_fault(
+	struct vm_fault		*vmf,
+	enum page_entry_size	pe_size,
+	bool			write_fault,
+	pfn_t			*pfn)
+{
+	return dax_iomap_fault(vmf, pe_size, pfn, NULL,
+			(write_fault && !vmf->cow_page) ?
+				&xfs_dax_write_iomap_ops :
+				&xfs_read_iomap_ops);
+}
+#else
+static int
+xfs_dax_fault(
+	struct vm_fault		*vmf,
+	enum page_entry_size	pe_size,
+	bool			write_fault,
+	pfn_t			*pfn)
+{
+	return 0;
+}
+#endif
+
 /*
  * Locking for serialisation of IO during page faults. This results in a lock
  * ordering of:
@@ -1284,10 +1310,7 @@ __xfs_filemap_fault(
 		pfn_t pfn;
 
 		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
-				(write_fault && !vmf->cow_page) ?
-				 &xfs_direct_write_iomap_ops :
-				 &xfs_read_iomap_ops);
+		ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
 		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 5fe9af24dfcd..13851c0d640b 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -531,6 +531,9 @@ xfs_do_force_shutdown(
 	} else if (flags & SHUTDOWN_CORRUPT_INCORE) {
 		tag = XFS_PTAG_SHUTDOWN_CORRUPT;
 		why = "Corruption of in-memory data";
+	} else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
+		tag = XFS_PTAG_SHUTDOWN_CORRUPT;
+		why = "Corruption of on-disk metadata";
 	} else {
 		tag = XFS_PTAG_SHUTDOWN_IOERROR;
 		why = "Metadata I/O Error";
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index e3b2304bb4d2..2bbe7916a998 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -2221,5 +2221,5 @@ xfs_inodegc_register_shrinker(
 	shrink->flags = SHRINKER_NONSLAB;
 	shrink->batch = XFS_INODEGC_SHRINKER_BATCH;
 
-	return register_shrinker(shrink);
+	return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id);
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 3022918bf96a..28493c8e9bb2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3447,6 +3447,50 @@ retry:
 	return 0;
 }
 
+static int
+xfs_mmaplock_two_inodes_and_break_dax_layout(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	int			error;
+	bool			retry;
+	struct page		*page;
+
+	if (ip1->i_ino > ip2->i_ino)
+		swap(ip1, ip2);
+
+again:
+	retry = false;
+	/* Lock the first inode */
+	xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
+	error = xfs_break_dax_layouts(VFS_I(ip1), &retry);
+	if (error || retry) {
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+		if (error == 0 && retry)
+			goto again;
+		return error;
+	}
+
+	if (ip1 == ip2)
+		return 0;
+
+	/* Nested lock the second inode */
+	xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1));
+	/*
+	 * We cannot use xfs_break_dax_layouts() directly here because it may
+	 * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable
+	 * for this nested lock case.
+	 */
+	page = dax_layout_busy_page(VFS_I(ip2)->i_mapping);
+	if (page && page_ref_count(page) != 1) {
+		xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+		goto again;
+	}
+
+	return 0;
+}
+
 /*
  * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
  * mmap activity.
@@ -3461,8 +3505,19 @@ xfs_ilock2_io_mmap(
 	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
 	if (ret)
 		return ret;
-	filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
-				    VFS_I(ip2)->i_mapping);
+
+	if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) {
+		ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2);
+		if (ret) {
+			inode_unlock(VFS_I(ip2));
+			if (ip1 != ip2)
+				inode_unlock(VFS_I(ip1));
+			return ret;
+		}
+	} else
+		filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
+					    VFS_I(ip2)->i_mapping);
+
 	return 0;
 }
 
@@ -3472,8 +3527,14 @@ xfs_iunlock2_io_mmap(
 	struct xfs_inode	*ip1,
 	struct xfs_inode	*ip2)
 {
-	filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
-				      VFS_I(ip2)->i_mapping);
+	if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) {
+		xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+		if (ip1 != ip2)
+			xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+	} else
+		filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
+					      VFS_I(ip2)->i_mapping);
+
 	inode_unlock(VFS_I(ip2));
 	if (ip1 != ip2)
 		inode_unlock(VFS_I(ip1));
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 4d626f4321bc..fa780f08dc89 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -531,6 +531,7 @@ xfs_itruncate_extents(
 }
 
 /* from xfs_file.c */
+int	xfs_break_dax_layouts(struct inode *inode, bool *retry);
 int	xfs_break_layouts(struct inode *inode, uint *iolock,
 		enum layout_break_reason reason);
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 2817d3dd25eb..07da03976ec1 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin(
 
 		/* may drop and re-acquire the ilock */
 		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-				&lockmode, flags & IOMAP_DIRECT);
+				&lockmode,
+				(flags & IOMAP_DIRECT) || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
 		if (shared)
@@ -868,6 +869,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
 };
 
 static int
+xfs_dax_write_iomap_end(
+	struct inode		*inode,
+	loff_t			pos,
+	loff_t			length,
+	ssize_t			written,
+	unsigned		flags,
+	struct iomap		*iomap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	if (!xfs_is_cow_inode(ip))
+		return 0;
+
+	if (!written) {
+		xfs_reflink_cancel_cow_range(ip, pos, length, true);
+		return 0;
+	}
+
+	return xfs_reflink_end_cow(ip, pos, written);
+}
+
+const struct iomap_ops xfs_dax_write_iomap_ops = {
+	.iomap_begin	= xfs_direct_write_iomap_begin,
+	.iomap_end	= xfs_dax_write_iomap_end,
+};
+
+static int
 xfs_buffered_write_iomap_begin(
 	struct inode		*inode,
 	loff_t			offset,
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index e88dc162c785..c782e8c0479c 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops;
 extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index d2eaebd85abf..8aca2cc173ac 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -454,6 +454,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname,
 #define SHUTDOWN_LOG_IO_ERROR	(1u << 1) /* write attempt to the log failed */
 #define SHUTDOWN_FORCE_UMOUNT	(1u << 2) /* shutdown from a forced unmount */
 #define SHUTDOWN_CORRUPT_INCORE	(1u << 3) /* corrupt in-memory structures */
+#define SHUTDOWN_CORRUPT_ONDISK	(1u << 4)  /* corrupt metadata on device */
 
 #define XFS_SHUTDOWN_STRINGS \
 	{ SHUTDOWN_META_IO_ERROR,	"metadata_io" }, \
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
new file mode 100644
index 000000000000..69d9c83ea4b2
--- /dev/null
+++ b/fs/xfs/xfs_notify_failure.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Fujitsu.  All Rights Reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_alloc.h"
+#include "xfs_bit.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtalloc.h"
+#include "xfs_trans.h"
+#include "xfs_ag.h"
+
+#include <linux/mm.h>
+#include <linux/dax.h>
+
+struct failure_info {
+	xfs_agblock_t		startblock;
+	xfs_extlen_t		blockcount;
+	int			mf_flags;
+};
+
+static pgoff_t
+xfs_failure_pgoff(
+	struct xfs_mount		*mp,
+	const struct xfs_rmap_irec	*rec,
+	const struct failure_info	*notify)
+{
+	loff_t				pos = XFS_FSB_TO_B(mp, rec->rm_offset);
+
+	if (notify->startblock > rec->rm_startblock)
+		pos += XFS_FSB_TO_B(mp,
+				notify->startblock - rec->rm_startblock);
+	return pos >> PAGE_SHIFT;
+}
+
+static unsigned long
+xfs_failure_pgcnt(
+	struct xfs_mount		*mp,
+	const struct xfs_rmap_irec	*rec,
+	const struct failure_info	*notify)
+{
+	xfs_agblock_t			end_rec;
+	xfs_agblock_t			end_notify;
+	xfs_agblock_t			start_cross;
+	xfs_agblock_t			end_cross;
+
+	start_cross = max(rec->rm_startblock, notify->startblock);
+
+	end_rec = rec->rm_startblock + rec->rm_blockcount;
+	end_notify = notify->startblock + notify->blockcount;
+	end_cross = min(end_rec, end_notify);
+
+	return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT;
+}
+
+static int
+xfs_dax_failure_fn(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*data)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_inode		*ip;
+	struct failure_info		*notify = data;
+	int				error = 0;
+
+	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
+	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
+		return -EFSCORRUPTED;
+	}
+
+	/* Get files that incore, filter out others that are not in use. */
+	error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE,
+			 0, &ip);
+	/* Continue the rmap query if the inode isn't incore */
+	if (error == -ENODATA)
+		return 0;
+	if (error)
+		return error;
+
+	error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
+				  xfs_failure_pgoff(mp, rec, notify),
+				  xfs_failure_pgcnt(mp, rec, notify),
+				  notify->mf_flags);
+	xfs_irele(ip);
+	return error;
+}
+
+static int
+xfs_dax_notify_ddev_failure(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		daddr,
+	xfs_daddr_t		bblen,
+	int			mf_flags)
+{
+	struct xfs_trans	*tp = NULL;
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_buf		*agf_bp = NULL;
+	int			error = 0;
+	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
+	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen);
+	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	for (; agno <= end_agno; agno++) {
+		struct xfs_rmap_irec	ri_low = { };
+		struct xfs_rmap_irec	ri_high;
+		struct failure_info	notify;
+		struct xfs_agf		*agf;
+		xfs_agblock_t		agend;
+		struct xfs_perag	*pag;
+
+		pag = xfs_perag_get(mp, agno);
+		error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
+		if (error) {
+			xfs_perag_put(pag);
+			break;
+		}
+
+		cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag);
+
+		/*
+		 * Set the rmap range from ri_low to ri_high, which represents
+		 * a [start, end] where we looking for the files or metadata.
+		 */
+		memset(&ri_high, 0xFF, sizeof(ri_high));
+		ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno);
+		if (agno == end_agno)
+			ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);
+
+		agf = agf_bp->b_addr;
+		agend = min(be32_to_cpu(agf->agf_length),
+				ri_high.rm_startblock);
+		notify.startblock = ri_low.rm_startblock;
+		notify.blockcount = agend - ri_low.rm_startblock;
+
+		error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
+				xfs_dax_failure_fn, &notify);
+		xfs_btree_del_cursor(cur, error);
+		xfs_trans_brelse(tp, agf_bp);
+		xfs_perag_put(pag);
+		if (error)
+			break;
+
+		fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0);
+	}
+
+	xfs_trans_cancel(tp);
+	return error;
+}
+
+static int
+xfs_dax_notify_failure(
+	struct dax_device	*dax_dev,
+	u64			offset,
+	u64			len,
+	int			mf_flags)
+{
+	struct xfs_mount	*mp = dax_holder(dax_dev);
+	u64			ddev_start;
+	u64			ddev_end;
+
+	if (!(mp->m_sb.sb_flags & SB_BORN)) {
+		xfs_warn(mp, "filesystem is not ready for notify_failure()!");
+		return -EIO;
+	}
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
+		xfs_warn(mp,
+			 "notify_failure() not supported on realtime device!");
+		return -EOPNOTSUPP;
+	}
+
+	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
+	    mp->m_logdev_targp != mp->m_ddev_targp) {
+		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
+		return -EFSCORRUPTED;
+	}
+
+	if (!xfs_has_rmapbt(mp)) {
+		xfs_warn(mp, "notify_failure() needs rmapbt enabled!");
+		return -EOPNOTSUPP;
+	}
+
+	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
+	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
+
+	/* Ignore the range out of filesystem area */
+	if (offset + len < ddev_start)
+		return -ENXIO;
+	if (offset > ddev_end)
+		return -ENXIO;
+
+	/* Calculate the real range when it touches the boundary */
+	if (offset > ddev_start)
+		offset -= ddev_start;
+	else {
+		len -= ddev_start - offset;
+		offset = 0;
+	}
+	if (offset + len > ddev_end)
+		len -= ddev_end - offset;
+
+	return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
+			mf_flags);
+}
+
+const struct dax_holder_operations xfs_dax_holder_operations = {
+	.notify_failure		= xfs_dax_notify_failure,
+};
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 57dd3b722265..fbff7924ff3f 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -677,7 +677,8 @@ xfs_qm_init_quotainfo(
 	qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
 	qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE;
 
-	error = register_shrinker(&qinf->qi_shrinker);
+	error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s",
+				  mp->m_super->s_id);
 	if (error)
 		goto out_free_inos;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 724806c7ce3e..e17a84e8b527 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1364,12 +1364,16 @@ xfs_reflink_remap_prep(
 	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
 		goto out_unlock;
 
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
+	/* Don't share DAX file data with non-DAX file. */
+	if (IS_DAX(inode_in) != IS_DAX(inode_out))
 		goto out_unlock;
 
-	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-			len, remap_flags);
+	if (!IS_DAX(inode_in))
+		ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
+				pos_out, len, remap_flags);
+	else
+		ret = dax_remap_file_range_prep(file_in, pos_in, file_out,
+				pos_out, len, remap_flags, &xfs_read_iomap_ops);
 	if (ret || *len == 0)
 		goto out_unlock;
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3d27ba1295c9..9ac59814bbb6 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -351,8 +351,10 @@ xfs_setup_dax_always(
 		goto disable_dax;
 	}
 
-	if (xfs_has_reflink(mp)) {
-		xfs_alert(mp, "DAX and reflink cannot be used together!");
+	if (xfs_has_reflink(mp) &&
+	    bdev_is_partition(mp->m_ddev_targp->bt_bdev)) {
+		xfs_alert(mp,
+			"DAX and reflink cannot work with multi-partitions!");
 		return -EINVAL;
 	}
 
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 3cd5a51bace1..364e2c2648a8 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -92,6 +92,7 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
 
 extern const struct export_operations xfs_export_operations;
 extern const struct quotactl_ops xfs_quotactl_operations;
+extern const struct dax_holder_operations xfs_dax_holder_operations;
 
 extern void xfs_reinit_percpu_counters(struct xfs_mount *mp);