Message-Id: <20260204082931.13915-7-linkinjeon@kernel.org>
Date: Wed,  4 Feb 2026 17:29:20 +0900
From: Namjae Jeon <linkinjeon@...nel.org>
To: viro@...iv.linux.org.uk,
	brauner@...nel.org,
	hch@....de
Cc: linux-fsdevel@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Namjae Jeon <linkinjeon@...nel.org>,
	Hyunchul Lee <hyc.lee@...il.com>
Subject: [PATCH RESEND v7 06/17] ntfs: update mft operations

Refactors MFT record handling to use folio APIs with consistency
validation, and improving allocation extension and writeback paths
for $MFT and $MFTMirr.

Signed-off-by: Hyunchul Lee <hyc.lee@...il.com>
Signed-off-by: Namjae Jeon <linkinjeon@...nel.org>
---
 fs/ntfs/mft.c | 2497 +++++++++++++++++++++++++------------------------
 fs/ntfs/mst.c |   65 +-
 2 files changed, 1290 insertions(+), 1272 deletions(-)

diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 6fd1dc4b08c8..79fbe90e2bb4 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,57 +1,119 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
+ * NTFS kernel mft record operations.
+ * Part of this file is based on code from the NTFS-3G.
  *
  * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
  * Copyright (c) 2002 Richard Russon
+ * Copyright (c) 2025 LG Electronics Co., Ltd.
  */
 
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
+#include <linux/writeback.h>
 #include <linux/bio.h>
+#include <linux/iomap.h>
 
-#include "attrib.h"
-#include "aops.h"
 #include "bitmap.h"
-#include "debug.h"
-#include "dir.h"
 #include "lcnalloc.h"
-#include "malloc.h"
 #include "mft.h"
 #include "ntfs.h"
 
-#define MAX_BHS	(PAGE_SIZE / NTFS_BLOCK_SIZE)
+/*
+ * ntfs_mft_record_check - Check the consistency of an MFT record
+ *
+ * Make sure its general fields are safe, then examine all its
+ * attributes and apply generic checks to them.
+ *
+ * Returns 0 if the checks are successful. If not, return -EIO.
+ */
+int ntfs_mft_record_check(const struct ntfs_volume *vol, struct mft_record *m,
+		unsigned long mft_no)
+{
+	struct attr_record *a;
+	struct super_block *sb = vol->sb;
+
+	if (!ntfs_is_file_record(m->magic)) {
+		ntfs_error(sb, "Record %llu has no FILE magic (0x%x)\n",
+				(unsigned long long)mft_no, le32_to_cpu(*(__le32 *)m));
+		goto err_out;
+	}
+
+	if (le16_to_cpu(m->usa_ofs) & 0x1 ||
+	    (vol->mft_record_size >> NTFS_BLOCK_SIZE_BITS) + 1 != le16_to_cpu(m->usa_count) ||
+	    le16_to_cpu(m->usa_ofs) + le16_to_cpu(m->usa_count) * 2 > vol->mft_record_size) {
+		ntfs_error(sb, "Record %llu has corrupt fix-up values fields\n",
+				(unsigned long long)mft_no);
+		goto err_out;
+	}
+
+	if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) {
+		ntfs_error(sb, "Record %llu has corrupt allocation size (%u <> %u)\n",
+				(unsigned long long)mft_no,
+				vol->mft_record_size,
+				le32_to_cpu(m->bytes_allocated));
+		goto err_out;
+	}
+
+	if (le32_to_cpu(m->bytes_in_use) > vol->mft_record_size) {
+		ntfs_error(sb, "Record %llu has corrupt in-use size (%u > %u)\n",
+				(unsigned long long)mft_no,
+				le32_to_cpu(m->bytes_in_use),
+				vol->mft_record_size);
+		goto err_out;
+	}
+
+	if (le16_to_cpu(m->attrs_offset) & 7) {
+		ntfs_error(sb, "Attributes badly aligned in record %llu\n",
+				(unsigned long long)mft_no);
+		goto err_out;
+	}
+
+	a = (struct attr_record *)((char *)m + le16_to_cpu(m->attrs_offset));
+	if ((char *)a < (char *)m || (char *)a > (char *)m + vol->mft_record_size) {
+		ntfs_error(sb, "Record %llu is corrupt\n",
+				(unsigned long long)mft_no);
+		goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	return -EIO;
+}
 
-/**
- * map_mft_record_page - map the page in which a specific mft record resides
+/*
+ * map_mft_record_folio - map the folio in which a specific mft record resides
  * @ni:		ntfs inode whose mft record page to map
  *
- * This maps the page in which the mft record of the ntfs inode @ni is situated
- * and returns a pointer to the mft record within the mapped page.
+ * This maps the folio in which the mft record of the ntfs inode @ni is
+ * situated.
+ *
+ * This allocates a new buffer (@ni->mrec), copies the MFT record data from
+ * the mapped folio into this buffer, and applies the MST (Multi Sector
+ * Transfer) fixups on the copy.
  *
- * Return value needs to be checked with IS_ERR() and if that is true PTR_ERR()
- * contains the negative error code returned.
+ * The folio is pinned (referenced) in @ni->folio to ensure the data remains
+ * valid in the page cache, but the returned pointer is the allocated copy.
+ *
+ * Return: A pointer to the allocated and fixed-up mft record (@ni->mrec).
+ * The return value needs to be checked with IS_ERR(). If it is true,
+ * PTR_ERR() contains the negative error code.
  */
-static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
+static inline struct mft_record *map_mft_record_folio(struct ntfs_inode *ni)
 {
 	loff_t i_size;
-	ntfs_volume *vol = ni->vol;
+	struct ntfs_volume *vol = ni->vol;
 	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
+	struct folio *folio;
 	unsigned long index, end_index;
-	unsigned ofs;
+	unsigned int ofs;
 
-	BUG_ON(ni->page);
+	WARN_ON(ni->folio);
 	/*
 	 * The index into the page cache and the offset within the page cache
-	 * page of the wanted mft record. FIXME: We need to check for
-	 * overflowing the unsigned long, but I don't think we would ever get
-	 * here if the volume was that big...
+	 * page of the wanted mft record.
 	 */
-	index = (u64)ni->mft_no << vol->mft_record_size_bits >>
-			PAGE_SHIFT;
-	ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
+	index = NTFS_MFT_NR_TO_PIDX(vol, ni->mft_no);
+	ofs = NTFS_MFT_NR_TO_POFS(vol, ni->mft_no);
 
 	i_size = i_size_read(mft_vi);
 	/* The maximum valid index into the page cache for $MFT's data. */
@@ -61,169 +123,126 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
 	if (unlikely(index >= end_index)) {
 		if (index > end_index || (i_size & ~PAGE_MASK) < ofs +
 				vol->mft_record_size) {
-			page = ERR_PTR(-ENOENT);
-			ntfs_error(vol->sb, "Attempt to read mft record 0x%lx, "
-					"which is beyond the end of the mft.  "
-					"This is probably a bug in the ntfs "
-					"driver.", ni->mft_no);
+			folio = ERR_PTR(-ENOENT);
+			ntfs_error(vol->sb,
+				"Attempt to read mft record 0x%lx, which is beyond the end of the mft. This is probably a bug in the ntfs driver.",
+				ni->mft_no);
 			goto err_out;
 		}
 	}
-	/* Read, map, and pin the page. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (!IS_ERR(page)) {
+
+	/* Read, map, and pin the folio. */
+	folio = read_mapping_folio(mft_vi->i_mapping, index, NULL);
+	if (!IS_ERR(folio)) {
+		u8 *addr;
+
+		ni->mrec = kmalloc(vol->mft_record_size, GFP_NOFS);
+		if (!ni->mrec) {
+			folio_put(folio);
+			folio = ERR_PTR(-ENOMEM);
+			goto err_out;
+		}
+
+		addr = kmap_local_folio(folio, 0);
+		memcpy(ni->mrec, addr + ofs, vol->mft_record_size);
+		post_read_mst_fixup((struct ntfs_record *)ni->mrec, vol->mft_record_size);
+
 		/* Catch multi sector transfer fixup errors. */
-		if (likely(ntfs_is_mft_recordp((le32*)(page_address(page) +
-				ofs)))) {
-			ni->page = page;
-			ni->page_ofs = ofs;
-			return page_address(page) + ofs;
+		if (!ntfs_mft_record_check(vol, (struct mft_record *)ni->mrec, ni->mft_no)) {
+			kunmap_local(addr);
+			ni->folio = folio;
+			ni->folio_ofs = ofs;
+			return ni->mrec;
 		}
-		ntfs_error(vol->sb, "Mft record 0x%lx is corrupt.  "
-				"Run chkdsk.", ni->mft_no);
-		ntfs_unmap_page(page);
-		page = ERR_PTR(-EIO);
+		kunmap_local(addr);
+		folio_put(folio);
+		kfree(ni->mrec);
+		ni->mrec = NULL;
+		folio = ERR_PTR(-EIO);
 		NVolSetErrors(vol);
 	}
 err_out:
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return (void*)page;
+	ni->folio = NULL;
+	ni->folio_ofs = 0;
+	return (struct mft_record *)folio;
 }
 
-/**
- * map_mft_record - map, pin and lock an mft record
+/*
+ * map_mft_record - map and pin an mft record
  * @ni:		ntfs inode whose MFT record to map
  *
- * First, take the mrec_lock mutex.  We might now be sleeping, while waiting
- * for the mutex if it was already locked by someone else.
- *
- * The page of the record is mapped using map_mft_record_page() before being
- * returned to the caller.
- *
- * This in turn uses ntfs_map_page() to get the page containing the wanted mft
- * record (it in turn calls read_cache_page() which reads it in from disk if
- * necessary, increments the use count on the page so that it cannot disappear
- * under us and returns a reference to the page cache page).
- *
- * If read_cache_page() invokes ntfs_readpage() to load the page from disk, it
- * sets PG_locked and clears PG_uptodate on the page. Once I/O has completed
- * and the post-read mst fixups on each mft record in the page have been
- * performed, the page gets PG_uptodate set and PG_locked cleared (this is done
- * in our asynchronous I/O completion handler end_buffer_read_mft_async()).
- * ntfs_map_page() waits for PG_locked to become clear and checks if
- * PG_uptodate is set and returns an error code if not. This provides
- * sufficient protection against races when reading/using the page.
- *
- * However there is the write mapping to think about. Doing the above described
- * checking here will be fine, because when initiating the write we will set
- * PG_locked and clear PG_uptodate making sure nobody is touching the page
- * contents. Doing the locking this way means that the commit to disk code in
- * the page cache code paths is automatically sufficiently locked with us as
- * we will not touch a page that has been locked or is not uptodate. The only
- * locking problem then is them locking the page while we are accessing it.
- *
- * So that code will end up having to own the mrec_lock of all mft
- * records/inodes present in the page before I/O can proceed. In that case we
- * wouldn't need to bother with PG_locked and PG_uptodate as nobody will be
- * accessing anything without owning the mrec_lock mutex.  But we do need to
- * use them because of the read_cache_page() invocation and the code becomes so
- * much simpler this way that it is well worth it.
- *
- * The mft record is now ours and we return a pointer to it. You need to check
- * the returned pointer with IS_ERR() and if that is true, PTR_ERR() will return
- * the error code.
- *
- * NOTE: Caller is responsible for setting the mft record dirty before calling
- * unmap_mft_record(). This is obviously only necessary if the caller really
- * modified the mft record...
- * Q: Do we want to recycle one of the VFS inode state bits instead?
- * A: No, the inode ones mean we want to change the mft record, not we want to
- * write it out.
+ * This function ensures the MFT record for the given inode is mapped and
+ * accessible.
+ *
+ * It increments the reference count of the ntfs inode. If the record is
+ * already mapped (@ni->folio is set), it returns the cached record
+ * immediately.
+ *
+ * Otherwise, it calls map_mft_record_folio() to read the folio from disk
+ * (if necessary via read_mapping_folio), allocate a buffer, and copy the
+ * record data.
+ *
+ * Return: A pointer to the mft record. You need to check the returned
+ * pointer with IS_ERR().
  */
-MFT_RECORD *map_mft_record(ntfs_inode *ni)
+struct mft_record *map_mft_record(struct ntfs_inode *ni)
 {
-	MFT_RECORD *m;
+	struct mft_record *m;
+
+	if (!ni)
+		return ERR_PTR(-EINVAL);
 
 	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
 
 	/* Make sure the ntfs inode doesn't go away. */
 	atomic_inc(&ni->count);
 
-	/* Serialize access to this mft record. */
-	mutex_lock(&ni->mrec_lock);
+	if (ni->folio)
+		return (struct mft_record *)ni->mrec;
 
-	m = map_mft_record_page(ni);
+	m = map_mft_record_folio(ni);
 	if (!IS_ERR(m))
 		return m;
 
-	mutex_unlock(&ni->mrec_lock);
 	atomic_dec(&ni->count);
 	ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m));
 	return m;
 }
 
-/**
- * unmap_mft_record_page - unmap the page in which a specific mft record resides
- * @ni:		ntfs inode whose mft record page to unmap
- *
- * This unmaps the page in which the mft record of the ntfs inode @ni is
- * situated and returns. This is a NOOP if highmem is not configured.
- *
- * The unmap happens via ntfs_unmap_page() which in turn decrements the use
- * count on the page thus releasing it from the pinned state.
- *
- * We do not actually unmap the page from memory of course, as that will be
- * done by the page cache code itself when memory pressure increases or
- * whatever.
- */
-static inline void unmap_mft_record_page(ntfs_inode *ni)
-{
-	BUG_ON(!ni->page);
-
-	// TODO: If dirty, blah...
-	ntfs_unmap_page(ni->page);
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return;
-}
-
-/**
- * unmap_mft_record - release a mapped mft record
+/*
+ * unmap_mft_record - release a reference to a mapped mft record
  * @ni:		ntfs inode whose MFT record to unmap
  *
- * We release the page mapping and the mrec_lock mutex which unmaps the mft
- * record and releases it for others to get hold of. We also release the ntfs
- * inode by decrementing the ntfs inode reference count.
+ * This decrements the reference count of the ntfs inode.
+ *
+ * It releases the caller's hold on the inode. If the reference count indicates
+ * that there are still other users (count > 1), the function returns
+ * immediately, keeping the resources (folio and mrec buffer) pinned for
+ * those users.
  *
  * NOTE: If caller has modified the mft record, it is imperative to set the mft
  * record dirty BEFORE calling unmap_mft_record().
  */
-void unmap_mft_record(ntfs_inode *ni)
+void unmap_mft_record(struct ntfs_inode *ni)
 {
-	struct page *page = ni->page;
+	struct folio *folio;
 
-	BUG_ON(!page);
+	if (!ni)
+		return;
 
 	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
 
-	unmap_mft_record_page(ni);
-	mutex_unlock(&ni->mrec_lock);
-	atomic_dec(&ni->count);
-	/*
-	 * If pure ntfs_inode, i.e. no vfs inode attached, we leave it to
-	 * ntfs_clear_extent_inode() in the extent inode case, and to the
-	 * caller in the non-extent, yet pure ntfs inode case, to do the actual
-	 * tear down of all structures and freeing of all allocated memory.
-	 */
-	return;
+	folio = ni->folio;
+	if (atomic_dec_return(&ni->count) > 1)
+		return;
+	WARN_ON(!folio);
 }
 
-/**
+/*
  * map_extent_mft_record - load an extent inode and attach it to its base
  * @base_ni:	base ntfs inode
  * @mref:	mft reference of the extent inode to load
- * @ntfs_ino:	on successful return, pointer to the ntfs_inode structure
+ * @ntfs_ino:	on successful return, pointer to the struct ntfs_inode structure
  *
  * Load the extent mft record @mref and attach it to its base inode @base_ni.
  * Return the mapped extent mft record if IS_ERR(result) is false.  Otherwise
@@ -232,12 +251,12 @@ void unmap_mft_record(ntfs_inode *ni)
  * On successful return, @ntfs_ino contains a pointer to the ntfs_inode
  * structure of the mapped extent inode.
  */
-MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
-		ntfs_inode **ntfs_ino)
+struct mft_record *map_extent_mft_record(struct ntfs_inode *base_ni, u64 mref,
+		struct ntfs_inode **ntfs_ino)
 {
-	MFT_RECORD *m;
-	ntfs_inode *ni = NULL;
-	ntfs_inode **extent_nis = NULL;
+	struct mft_record *m;
+	struct ntfs_inode *ni = NULL;
+	struct ntfs_inode **extent_nis = NULL;
 	int i;
 	unsigned long mft_no = MREF(mref);
 	u16 seq_no = MSEQNO(mref);
@@ -252,6 +271,7 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 	 * in which case just return it. If not found, add it to the base
 	 * inode before returning it.
 	 */
+retry:
 	mutex_lock(&base_ni->extent_lock);
 	if (base_ni->nr_extents > 0) {
 		extent_nis = base_ni->ext.extent_ntfs_inos;
@@ -279,20 +299,21 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 				return m;
 			}
 			unmap_mft_record(ni);
-			ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-					"reference! Corrupt filesystem. "
-					"Run chkdsk.");
+			ntfs_error(base_ni->vol->sb,
+					"Found stale extent mft reference! Corrupt filesystem. Run chkdsk.");
 			return ERR_PTR(-EIO);
 		}
 map_err_out:
-		ntfs_error(base_ni->vol->sb, "Failed to map extent "
-				"mft record, error code %ld.", -PTR_ERR(m));
+		ntfs_error(base_ni->vol->sb,
+				"Failed to map extent mft record, error code %ld.",
+				-PTR_ERR(m));
 		return m;
 	}
+	mutex_unlock(&base_ni->extent_lock);
+
 	/* Record wasn't there. Get a new ntfs inode and initialize it. */
 	ni = ntfs_new_extent_inode(base_ni->vol->sb, mft_no);
 	if (unlikely(!ni)) {
-		mutex_unlock(&base_ni->extent_lock);
 		atomic_dec(&base_ni->count);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -303,37 +324,44 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 	/* Now map the record. */
 	m = map_mft_record(ni);
 	if (IS_ERR(m)) {
-		mutex_unlock(&base_ni->extent_lock);
 		atomic_dec(&base_ni->count);
 		ntfs_clear_extent_inode(ni);
 		goto map_err_out;
 	}
 	/* Verify the sequence number if it is present. */
 	if (seq_no && (le16_to_cpu(m->sequence_number) != seq_no)) {
-		ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-				"reference! Corrupt filesystem. Run chkdsk.");
+		ntfs_error(base_ni->vol->sb,
+				"Found stale extent mft reference! Corrupt filesystem. Run chkdsk.");
 		destroy_ni = true;
 		m = ERR_PTR(-EIO);
-		goto unm_err_out;
+		goto unm_nolock_err_out;
+	}
+
+	mutex_lock(&base_ni->extent_lock);
+	for (i = 0; i < base_ni->nr_extents; i++) {
+		if (mft_no == extent_nis[i]->mft_no) {
+			mutex_unlock(&base_ni->extent_lock);
+			ntfs_clear_extent_inode(ni);
+			goto retry;
+		}
 	}
 	/* Attach extent inode to base inode, reallocating memory if needed. */
 	if (!(base_ni->nr_extents & 3)) {
-		ntfs_inode **tmp;
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode *);
+		struct ntfs_inode **tmp;
+		int new_size = (base_ni->nr_extents + 4) * sizeof(struct ntfs_inode *);
 
-		tmp = kmalloc(new_size, GFP_NOFS);
+		tmp = kvzalloc(new_size, GFP_NOFS);
 		if (unlikely(!tmp)) {
-			ntfs_error(base_ni->vol->sb, "Failed to allocate "
-					"internal buffer.");
+			ntfs_error(base_ni->vol->sb, "Failed to allocate internal buffer.");
 			destroy_ni = true;
 			m = ERR_PTR(-ENOMEM);
 			goto unm_err_out;
 		}
 		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
+			WARN_ON(!base_ni->ext.extent_ntfs_inos);
 			memcpy(tmp, base_ni->ext.extent_ntfs_inos, new_size -
-					4 * sizeof(ntfs_inode *));
-			kfree(base_ni->ext.extent_ntfs_inos);
+					4 * sizeof(struct ntfs_inode *));
+			kvfree(base_ni->ext.extent_ntfs_inos);
 		}
 		base_ni->ext.extent_ntfs_inos = tmp;
 	}
@@ -344,8 +372,9 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 	*ntfs_ino = ni;
 	return m;
 unm_err_out:
-	unmap_mft_record(ni);
 	mutex_unlock(&base_ni->extent_lock);
+unm_nolock_err_out:
+	unmap_mft_record(ni);
 	atomic_dec(&base_ni->count);
 	/*
 	 * If the extent inode was not attached to the base inode we need to
@@ -356,18 +385,14 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 	return m;
 }
 
-#ifdef NTFS_RW
-
-/**
- * __mark_mft_record_dirty - set the mft record and the page containing it dirty
+/*
+ * __mark_mft_record_dirty - mark the base vfs inode dirty
  * @ni:		ntfs inode describing the mapped mft record
  *
  * Internal function.  Users should call mark_mft_record_dirty() instead.
  *
- * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
- * as well as the page containing the mft record, dirty.  Also, mark the base
- * vfs inode dirty.  This ensures that any changes to the mft record are
- * written out to disk.
+ * This function determines the base ntfs inode (in case @ni is an extent
+ * inode) and marks the corresponding VFS inode dirty.
  *
  * NOTE:  We only set I_DIRTY_DATASYNC (and not I_DIRTY_PAGES)
  * on the base vfs inode, because even though file data may have been modified,
@@ -381,64 +406,40 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
  * I_DIRTY_SYNC, since the file data has not actually hit the block device yet,
  * which is not what I_DIRTY_SYNC on its own would suggest.
  */
-void __mark_mft_record_dirty(ntfs_inode *ni)
+void __mark_mft_record_dirty(struct ntfs_inode *ni)
 {
-	ntfs_inode *base_ni;
+	struct ntfs_inode *base_ni;
 
 	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	mark_ntfs_record_dirty(ni->page, ni->page_ofs);
+	WARN_ON(NInoAttr(ni));
 	/* Determine the base vfs inode and mark it dirty, too. */
-	mutex_lock(&ni->extent_lock);
 	if (likely(ni->nr_extents >= 0))
 		base_ni = ni;
 	else
 		base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
 	__mark_inode_dirty(VFS_I(base_ni), I_DIRTY_DATASYNC);
 }
 
-static const char *ntfs_please_email = "Please email "
-		"linux-ntfs-dev@...ts.sourceforge.net and say that you saw "
-		"this message.  Thank you.";
-
-/**
- * ntfs_sync_mft_mirror_umount - synchronise an mft record to the mft mirror
- * @vol:	ntfs volume on which the mft record to synchronize resides
- * @mft_no:	mft record number of mft record to synchronize
- * @m:		mapped, mst protected (extent) mft record to synchronize
- *
- * Write the mapped, mst protected (extent) mft record @m with mft record
- * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol,
- * bypassing the page cache and the $MFTMirr inode itself.
- *
- * This function is only for use at umount time when the mft mirror inode has
- * already been disposed off.  We BUG() if we are called while the mft mirror
- * inode is still attached to the volume.
- *
- * On success return 0.  On error return -errno.
+/*
+ * ntfs_bio_end_io - bio completion callback for MFT record writes
  *
- * NOTE:  This function is not implemented yet as I am not convinced it can
- * actually be triggered considering the sequence of commits we do in super.c::
- * ntfs_put_super().  But just in case we provide this place holder as the
- * alternative would be either to BUG() or to get a NULL pointer dereference
- * and Oops.
+ * Decrements the folio reference count that was incremented before
+ * submit_bio(). This prevents a race condition where umount could
+ * evict the inode and release the folio while I/O is still in flight,
+ * potentially causing data corruption or use-after-free.
  */
-static int ntfs_sync_mft_mirror_umount(ntfs_volume *vol,
-		const unsigned long mft_no, MFT_RECORD *m)
+static void ntfs_bio_end_io(struct bio *bio)
 {
-	BUG_ON(vol->mftmirr_ino);
-	ntfs_error(vol->sb, "Umount time mft mirror syncing is not "
-			"implemented yet.  %s", ntfs_please_email);
-	return -EOPNOTSUPP;
+	if (bio->bi_private)
+		folio_put((struct folio *)bio->bi_private);
+	bio_put(bio);
 }
 
-/**
+/*
  * ntfs_sync_mft_mirror - synchronize an mft record to the mft mirror
  * @vol:	ntfs volume on which the mft record to synchronize resides
  * @mft_no:	mft record number of mft record to synchronize
  * @m:		mapped, mst protected (extent) mft record to synchronize
- * @sync:	if true, wait for i/o completion
  *
  * Write the mapped, mst protected (extent) mft record @m with mft record
  * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol.
@@ -446,187 +447,81 @@ static int ntfs_sync_mft_mirror_umount(ntfs_volume *vol,
  * On success return 0.  On error return -errno and set the volume errors flag
  * in the ntfs volume @vol.
  *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
+ * NOTE:  We always perform synchronous i/o.
  */
-int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
-		MFT_RECORD *m, int sync)
+int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const unsigned long mft_no,
+		struct mft_record *m)
 {
-	struct page *page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	u8 *kmirr;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end, page_ofs;
-	int i_bhs, nr_bhs, err = 0;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
+	u8 *kmirr = NULL;
+	struct folio *folio;
+	unsigned int folio_ofs, lcn_folio_off = 0;
+	int err = 0;
+	struct bio *bio;
 
 	ntfs_debug("Entering for inode 0x%lx.", mft_no);
-	BUG_ON(!max_bhs);
-	if (WARN_ON(max_bhs > MAX_BHS))
-		return -EINVAL;
+
 	if (unlikely(!vol->mftmirr_ino)) {
 		/* This could happen during umount... */
-		err = ntfs_sync_mft_mirror_umount(vol, mft_no, m);
-		if (likely(!err))
-			return err;
+		err = -EIO;
 		goto err_out;
 	}
 	/* Get the page containing the mirror copy of the mft record @m. */
-	page = ntfs_map_page(vol->mftmirr_ino->i_mapping, mft_no >>
-			(PAGE_SHIFT - vol->mft_record_size_bits));
-	if (IS_ERR(page)) {
+	folio = read_mapping_folio(vol->mftmirr_ino->i_mapping,
+			NTFS_MFT_NR_TO_PIDX(vol, mft_no), NULL);
+	if (IS_ERR(folio)) {
 		ntfs_error(vol->sb, "Failed to map mft mirror page.");
-		err = PTR_ERR(page);
+		err = PTR_ERR(folio);
 		goto err_out;
 	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
+
+	folio_lock(folio);
+	folio_clear_uptodate(folio);
 	/* Offset of the mft mirror record inside the page. */
-	page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
+	folio_ofs = NTFS_MFT_NR_TO_POFS(vol, mft_no);
 	/* The address in the page of the mirror copy of the mft record @m. */
-	kmirr = page_address(page) + page_ofs;
+	kmirr = kmap_local_folio(folio, 0) + folio_ofs;
 	/* Copy the mst protected mft record to the mirror. */
 	memcpy(kmirr, m, vol->mft_record_size);
-	/* Create uptodate buffers if not present. */
-	if (unlikely(!page_has_buffers(page))) {
-		struct buffer_head *tail;
-
-		bh = head = alloc_page_buffers(page, blocksize, true);
-		do {
-			set_buffer_uptodate(bh);
-			tail = bh;
-			bh = bh->b_this_page;
-		} while (bh);
-		tail->b_this_page = head;
-		attach_page_private(page, head);
-	}
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = kmirr - (u8*)page_address(page);
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mftmirr_ino)->
-						runlist.lock);
-				rl = NTFS_I(vol->mftmirr_ino)->runlist.rl;
-				/*
-				 * $MFTMirr always has the whole of its runlist
-				 * in memory.
-				 */
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFTMirr, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft mirror "
-						"record 0x%lx because its "
-						"location on disk could not "
-						"be determined (error code "
-						"%lli).", mft_no,
-						(long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mftmirr_ino)->runlist.lock);
-	if (likely(!err)) {
-		/* Lock buffers and start synchronous write i/o on them. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
-
-			if (!trylock_buffer(tbh))
-				BUG();
-			BUG_ON(!buffer_uptodate(tbh));
-			clear_buffer_dirty(tbh);
-			get_bh(tbh);
-			tbh->b_end_io = end_buffer_write_sync;
-			submit_bh(REQ_OP_WRITE, tbh);
-		}
-		/* Wait on i/o completion of buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
 
-			wait_on_buffer(tbh);
-			if (unlikely(!buffer_uptodate(tbh))) {
-				err = -EIO;
-				/*
-				 * Set the buffer uptodate so the page and
-				 * buffer states do not become out of sync.
-				 */
-				set_buffer_uptodate(tbh);
-			}
-		}
-	} else /* if (unlikely(err)) */ {
-		/* Clean the buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-			clear_buffer_dirty(bhs[i_bhs]);
+	if (vol->cluster_size_bits > PAGE_SHIFT) {
+		lcn_folio_off = folio->index << PAGE_SHIFT;
+		lcn_folio_off &= vol->cluster_size_mask;
 	}
+
+	bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO);
+	bio->bi_iter.bi_sector =
+		NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) +
+				 lcn_folio_off + folio_ofs);
+
+	if (!bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) {
+		err = -EIO;
+		bio_put(bio);
+		goto unlock_folio;
+	}
+
+	bio->bi_end_io = ntfs_bio_end_io;
+	submit_bio(bio);
 	/* Current state: all buffers are clean, unlocked, and uptodate. */
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)kmirr);
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	ntfs_unmap_page(page);
+	folio_mark_uptodate(folio);
+
+unlock_folio:
+	folio_unlock(folio);
+	kunmap_local(kmirr);
+	folio_put(folio);
 	if (likely(!err)) {
 		ntfs_debug("Done.");
 	} else {
-		ntfs_error(vol->sb, "I/O error while writing mft mirror "
-				"record 0x%lx!", mft_no);
+		ntfs_error(vol->sb, "I/O error while writing mft mirror record 0x%lx!", mft_no);
 err_out:
-		ntfs_error(vol->sb, "Failed to synchronize $MFTMirr (error "
-				"code %i).  Volume will be left marked dirty "
-				"on umount.  Run ntfsfix on the partition "
-				"after umounting to correct this.", -err);
+		ntfs_error(vol->sb,
+			"Failed to synchronize $MFTMirr (error code %i).  Volume will be left marked dirty on umount.  Run chkdsk on the partition after umounting to correct this.",
+			err);
 		NVolSetErrors(vol);
 	}
 	return err;
 }
 
-/**
+/*
  * write_mft_record_nolock - write out a mapped (extent) mft record
  * @ni:		ntfs inode describing the mapped (extent) mft record
  * @m:		mapped (extent) mft record to write
@@ -636,201 +531,103 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
  * ntfs inode @ni to backing store.  If the mft record @m has a counterpart in
  * the mft mirror, that is also updated.
  *
- * We only write the mft record if the ntfs inode @ni is dirty and the first
- * buffer belonging to its mft record is dirty, too.  We ignore the dirty state
- * of subsequent buffers because we could have raced with
- * fs/ntfs/aops.c::mark_ntfs_record_dirty().
- *
- * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.
- *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- * However, if the mft record has a counterpart in the mft mirror and @sync is
- * true, we write the mft record, wait for i/o completion, and only then write
- * the mft mirror copy.  This ensures that if the system crashes either the mft
- * or the mft mirror will contain a self-consistent mft record @m.  If @sync is
- * false on the other hand, we start i/o on both and then wait for completion
- * on them.  This provides a speedup but no longer guarantees that you will end
- * up with a self-consistent mft record in the case of a crash but if you asked
- * for asynchronous writing you probably do not care about that anyway.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
+ * We only write the mft record if the ntfs inode @ni is dirty.
+ *
+ * On success, clean the mft record and return 0.
+ * On error (specifically ENOMEM), we redirty the record so it can be retried.
+ * For other errors, we mark the volume with errors.
  */
-int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
+int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int sync)
 {
-	ntfs_volume *vol = ni->vol;
-	struct page *page = ni->page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end;
-	int i_bhs, nr_bhs, err = 0;
+	struct ntfs_volume *vol = ni->vol;
+	struct folio *folio = ni->folio;
+	int err = 0, i = 0;
+	u8 *kaddr;
+	struct mft_record *fixup_m;
+	struct bio *bio;
+	unsigned int offset = 0, folio_size;
 
 	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(!max_bhs);
-	BUG_ON(!PageLocked(page));
-	if (WARN_ON(max_bhs > MAX_BHS)) {
-		err = -EINVAL;
-		goto err_out;
-	}
+
+	WARN_ON(NInoAttr(ni));
+	WARN_ON(!folio_test_locked(folio));
+
 	/*
-	 * If the ntfs_inode is clean no need to do anything.  If it is dirty,
+	 * If the struct ntfs_inode is clean no need to do anything.  If it is dirty,
 	 * mark it as clean now so that it can be redirtied later on if needed.
 	 * There is no danger of races since the caller is holding the locks
 	 * for the mft record @m and the page it is in.
 	 */
 	if (!NInoTestClearDirty(ni))
 		goto done;
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = ni->page_ofs;
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/*
-		 * If this block is not the first one in the record, we ignore
-		 * the buffer's dirty state because we could have raced with a
-		 * parallel mark_ntfs_record_dirty().
-		 */
-		if (block_start == m_start) {
-			/* This block is the first one in the record. */
-			if (!buffer_dirty(bh)) {
-				BUG_ON(nr_bhs);
-				/* Clean records are not written out. */
-				break;
-			}
-		}
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)ni->mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-				rl = NTFS_I(vol->mft_ino)->runlist.rl;
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFT, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft record "
-						"0x%lx because its location "
-						"on disk could not be "
-						"determined (error code %lli).",
-						ni->mft_no, (long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-	if (!nr_bhs)
-		goto done;
-	if (unlikely(err))
-		goto cleanup_out;
+
+	kaddr = kmap_local_folio(folio, 0);
+	fixup_m = (struct mft_record *)(kaddr + ni->folio_ofs);
+	memcpy(fixup_m, m, vol->mft_record_size);
+
 	/* Apply the mst protection fixups. */
-	err = pre_write_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size);
+	err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size);
 	if (err) {
 		ntfs_error(vol->sb, "Failed to apply mst fixups!");
-		goto cleanup_out;
-	}
-	flush_dcache_mft_record_page(ni);
-	/* Lock buffers and start synchronous write i/o on them. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		if (!trylock_buffer(tbh))
-			BUG();
-		BUG_ON(!buffer_uptodate(tbh));
-		clear_buffer_dirty(tbh);
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, tbh);
-	}
-	/* Synchronize the mft mirror now if not @sync. */
-	if (!sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Wait on i/o completion of buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		wait_on_buffer(tbh);
-		if (unlikely(!buffer_uptodate(tbh))) {
+		goto err_out;
+	}
+
+	folio_size = vol->mft_record_size / ni->mft_lcn_count;
+	while (i < ni->mft_lcn_count) {
+		unsigned int clu_off;
+
+		clu_off = (unsigned int)((s64)ni->mft_no * vol->mft_record_size + offset) &
+			vol->cluster_size_mask;
+
+		bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO);
+		bio->bi_iter.bi_sector =
+			NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) +
+					 clu_off);
+
+		if (!bio_add_folio(bio, folio, folio_size,
+				   ni->folio_ofs + offset)) {
 			err = -EIO;
-			/*
-			 * Set the buffer uptodate so the page and buffer
-			 * states do not become out of sync.
-			 */
-			if (PageUptodate(page))
-				set_buffer_uptodate(tbh);
+			goto put_bio_out;
 		}
+
+		/* Synchronize the mft mirror now if not @sync. */
+		if (!sync && ni->mft_no < vol->mftmirr_size)
+			ntfs_sync_mft_mirror(vol, ni->mft_no, fixup_m);
+
+		folio_get(folio);
+		bio->bi_private = folio;
+		bio->bi_end_io = ntfs_bio_end_io;
+		submit_bio(bio);
+		offset += vol->cluster_size;
+		i++;
 	}
+
 	/* If @sync, now synchronize the mft mirror. */
 	if (sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)m);
-	flush_dcache_mft_record_page(ni);
+		ntfs_sync_mft_mirror(vol, ni->mft_no, fixup_m);
+	kunmap_local(kaddr);
 	if (unlikely(err)) {
 		/* I/O error during writing.  This is really bad! */
-		ntfs_error(vol->sb, "I/O error while writing mft record "
-				"0x%lx!  Marking base inode as bad.  You "
-				"should unmount the volume and run chkdsk.",
-				ni->mft_no);
+		ntfs_error(vol->sb,
+			"I/O error while writing mft record 0x%lx!  Marking base inode as bad.  You should unmount the volume and run chkdsk.",
+			ni->mft_no);
 		goto err_out;
 	}
 done:
 	ntfs_debug("Done.");
 	return 0;
-cleanup_out:
-	/* Clean the buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-		clear_buffer_dirty(bhs[i_bhs]);
+put_bio_out:
+	bio_put(bio);
 err_out:
 	/*
 	 * Current state: all buffers are clean, unlocked, and uptodate.
 	 * The caller should mark the base inode as bad so that no more i/o
-	 * happens.  ->clear_inode() will still be invoked so all extent inodes
+	 * happens.  ->drop_inode() will still be invoked so all extent inodes
 	 * and other allocated memory will be freed.
 	 */
 	if (err == -ENOMEM) {
-		ntfs_error(vol->sb, "Not enough memory to write mft record.  "
-				"Redirtying so the write is retried later.");
+		ntfs_error(vol->sb,
+			"Not enough memory to write mft record. Redirtying so the write is retried later.");
 		mark_mft_record_dirty(ni);
 		err = 0;
 	} else
@@ -838,12 +635,46 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 	return err;
 }
 
-/**
+static int ntfs_test_inode_wb(struct inode *vi, unsigned long ino, void *data)
+{
+	struct ntfs_attr *na = data;
+
+	if (!ntfs_test_inode(vi, na))
+		return 0;
+
+	/*
+	 * Without this, ntfs_write_mst_block() could call iput_final()
+	 * , and ntfs_evict_big_inode() could try to unlink this inode
+	 * and the contex could be blocked infinitly in map_mft_record().
+	 */
+	if (NInoBeingDeleted(NTFS_I(vi))) {
+		na->state = NI_BeingDeleted;
+		return -1;
+	}
+
+	/*
+	 * This condition can prevent ntfs_write_mst_block()
+	 * from applying/undo fixups while ntfs_create() being
+	 * called
+	 */
+	spin_lock(&vi->i_lock);
+	if (inode_state_read_once(vi) & I_CREATING) {
+		spin_unlock(&vi->i_lock);
+		na->state = NI_BeingCreated;
+		return -1;
+	}
+	spin_unlock(&vi->i_lock);
+
+	return igrab(vi) ? 1 : -1;
+}
+
+/*
  * ntfs_may_write_mft_record - check if an mft record may be written out
  * @vol:	[IN]  ntfs volume on which the mft record to check resides
  * @mft_no:	[IN]  mft record number of the mft record to check
  * @m:		[IN]  mapped mft record to check
  * @locked_ni:	[OUT] caller has to unlock this ntfs inode if one is returned
+ * @ref_vi:	[OUT] caller has to drop this vfs inode if one is returned
  *
  * Check if the mapped (base or extent) mft record @m with mft record number
  * @mft_no belonging to the ntfs volume @vol may be written out.  If necessary
@@ -852,23 +683,23 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
  * caller is responsible for unlocking the ntfs inode and unpinning the base
  * vfs inode.
  *
+ * To avoid deadlock when the caller holds a folio lock, if the function
+ * returns @ref_vi it defers dropping the vfs inode reference by returning
+ * it in @ref_vi instead of calling iput() directly.  The caller must call
+ * iput() on @ref_vi after releasing the folio lock.
+ *
  * Return 'true' if the mft record may be written out and 'false' if not.
  *
  * The caller has locked the page and cleared the uptodate flag on it which
  * means that we can safely write out any dirty mft records that do not have
- * their inodes in icache as determined by ilookup5() as anyone
- * opening/creating such an inode would block when attempting to map the mft
- * record in read_cache_page() until we are finished with the write out.
+ * their inodes in icache as determined by find_inode_nowait().
  *
  * Here is a description of the tests we perform:
  *
  * If the inode is found in icache we know the mft record must be a base mft
  * record.  If it is dirty, we do not write it and return 'false' as the vfs
  * inode write paths will result in the access times being updated which would
- * cause the base mft record to be redirtied and written out again.  (We know
- * the access time update will modify the base mft record because Windows
- * chkdsk complains if the standard information attribute is not in the base
- * mft record.)
+ * cause the base mft record to be redirtied and written out again.
  *
  * If the inode is in icache and not dirty, we attempt to lock the mft record
  * and if we find the lock was already taken, it is not safe to write the mft
@@ -879,9 +710,7 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
  * @locked_ni to the locked ntfs inode and return 'true'.
  *
  * Note we cannot just lock the mft record and sleep while waiting for the lock
- * because this would deadlock due to lock reversal (normally the mft record is
- * locked before the page is locked but we already have the page locked here
- * when we try to lock the mft record).
+ * because this would deadlock due to lock reversal.
  *
  * If the inode is not in icache we need to perform further checks.
  *
@@ -889,58 +718,46 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
  * safely write it and return 'true'.
  *
  * We now know the mft record is an extent mft record.  We check if the inode
- * corresponding to its base mft record is in icache and obtain a reference to
- * it if it is.  If it is not, we can safely write it and return 'true'.
+ * corresponding to its base mft record is in icache. If it is not, we cannot
+ * safely determine the state of the extent inode, so we return 'false'.
  *
  * We now have the base inode for the extent mft record.  We check if it has an
- * ntfs inode for the extent mft record attached and if not it is safe to write
+ * ntfs inode for the extent mft record attached. If not, it is safe to write
  * the extent mft record and we return 'true'.
  *
- * The ntfs inode for the extent mft record is attached to the base inode so we
- * attempt to lock the extent mft record and if we find the lock was already
- * taken, it is not safe to write the extent mft record and we return 'false'.
+ * If the extent inode is attached, we check if it is dirty. If so, we return
+ * 'false' (letting the standard write_inode path handle it).
+ *
+ * If it is not dirty, we attempt to lock the extent mft record. If the lock
+ * was already taken, it is not safe to write and we return 'false'.
  *
  * If we manage to obtain the lock we have exclusive access to the extent mft
- * record, which also allows us safe writeout of the extent mft record.  We
- * set the ntfs inode of the extent mft record clean and then set @locked_ni to
- * the now locked ntfs inode and return 'true'.
- *
- * Note, the reason for actually writing dirty mft records here and not just
- * relying on the vfs inode dirty code paths is that we can have mft records
- * modified without them ever having actual inodes in memory.  Also we can have
- * dirty mft records with clean ntfs inodes in memory.  None of the described
- * cases would result in the dirty mft records being written out if we only
- * relied on the vfs inode dirty code paths.  And these cases can really occur
- * during allocation of new mft records and in particular when the
- * initialized_size of the $MFT/$DATA attribute is extended and the new space
- * is initialized using ntfs_mft_record_format().  The clean inode can then
- * appear if the mft record is reused for a new inode before it got written
- * out.
+ * record. We set @locked_ni to the now locked ntfs inode and return 'true'.
  */
-bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
-		const MFT_RECORD *m, ntfs_inode **locked_ni)
+bool ntfs_may_write_mft_record(struct ntfs_volume *vol, const unsigned long mft_no,
+		const struct mft_record *m, struct ntfs_inode **locked_ni,
+		struct inode **ref_vi)
 {
 	struct super_block *sb = vol->sb;
 	struct inode *mft_vi = vol->mft_ino;
 	struct inode *vi;
-	ntfs_inode *ni, *eni, **extent_nis;
+	struct ntfs_inode *ni, *eni, **extent_nis;
 	int i;
-	ntfs_attr na;
+	struct ntfs_attr na = {0};
 
 	ntfs_debug("Entering for inode 0x%lx.", mft_no);
 	/*
 	 * Normally we do not return a locked inode so set @locked_ni to NULL.
 	 */
-	BUG_ON(!locked_ni);
 	*locked_ni = NULL;
+	*ref_vi = NULL;
+
 	/*
 	 * Check if the inode corresponding to this mft record is in the VFS
 	 * inode cache and obtain a reference to it if it is.
 	 */
 	ntfs_debug("Looking for inode 0x%lx in icache.", mft_no);
 	na.mft_no = mft_no;
-	na.name = NULL;
-	na.name_len = 0;
 	na.type = AT_UNUSED;
 	/*
 	 * Optimize inode 0, i.e. $MFT itself, since we have it in memory and
@@ -949,16 +766,16 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	if (!mft_no) {
 		/* Balance the below iput(). */
 		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
+		WARN_ON(vi != mft_vi);
 	} else {
 		/*
-		 * Have to use ilookup5_nowait() since ilookup5() waits for the
-		 * inode lock which causes ntfs to deadlock when a concurrent
-		 * inode write via the inode dirty code paths and the page
-		 * dirty code path of the inode dirty code path when writing
-		 * $MFT occurs.
+		 * Have to use find_inode_nowait() since ilookup5_nowait()
+		 * waits for inode with I_FREEING, which causes ntfs to deadlock
+		 * when inodes are unlinked concurrently
 		 */
-		vi = ilookup5_nowait(sb, mft_no, ntfs_test_inode, &na);
+		vi = find_inode_nowait(sb, mft_no, ntfs_test_inode_wb, &na);
+		if (na.state == NI_BeingDeleted || na.state == NI_BeingCreated)
+			return false;
 	}
 	if (vi) {
 		ntfs_debug("Base inode 0x%lx is in icache.", mft_no);
@@ -971,16 +788,15 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 			ntfs_debug("Inode 0x%lx is dirty, do not write it.",
 					mft_no);
 			atomic_dec(&ni->count);
-			iput(vi);
+			*ref_vi = vi;
 			return false;
 		}
 		ntfs_debug("Inode 0x%lx is not dirty.", mft_no);
 		/* The inode is not dirty, try to take the mft record lock. */
 		if (unlikely(!mutex_trylock(&ni->mrec_lock))) {
-			ntfs_debug("Mft record 0x%lx is already locked, do "
-					"not write it.", mft_no);
+			ntfs_debug("Mft record 0x%lx is already locked, do not write it.", mft_no);
 			atomic_dec(&ni->count);
-			iput(vi);
+			*ref_vi = vi;
 			return false;
 		}
 		ntfs_debug("Managed to lock mft record 0x%lx, write it.",
@@ -1012,24 +828,21 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	 * is.
 	 */
 	na.mft_no = MREF_LE(m->base_mft_record);
-	ntfs_debug("Mft record 0x%lx is an extent record.  Looking for base "
-			"inode 0x%lx in icache.", mft_no, na.mft_no);
+	na.state = 0;
+	ntfs_debug("Mft record 0x%lx is an extent record.  Looking for base inode 0x%lx in icache.",
+			mft_no, na.mft_no);
 	if (!na.mft_no) {
 		/* Balance the below iput(). */
 		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
-	} else
-		vi = ilookup5_nowait(sb, na.mft_no, ntfs_test_inode,
-				&na);
-	if (!vi) {
-		/*
-		 * The base inode is not in icache, write this extent mft
-		 * record.
-		 */
-		ntfs_debug("Base inode 0x%lx is not in icache, write the "
-				"extent record.", na.mft_no);
-		return true;
+		WARN_ON(vi != mft_vi);
+	} else {
+		vi = find_inode_nowait(sb, mft_no, ntfs_test_inode_wb, &na);
+		if (na.state == NI_BeingDeleted || na.state == NI_BeingCreated)
+			return false;
 	}
+
+	if (!vi)
+		return false;
 	ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no);
 	/*
 	 * The base inode is in icache.  Check if it has the extent inode
@@ -1043,9 +856,9 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 		 * extent mft record.
 		 */
 		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Base inode 0x%lx has no attached extent inodes, "
-				"write the extent record.", na.mft_no);
+		*ref_vi = vi;
+		ntfs_debug("Base inode 0x%lx has no attached extent inodes, write the extent record.",
+				na.mft_no);
 		return true;
 	}
 	/* Iterate over the attached extent inodes. */
@@ -1066,9 +879,8 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	 */
 	if (!eni) {
 		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Extent inode 0x%lx is not attached to its base "
-				"inode 0x%lx, write the extent record.",
+		*ref_vi = vi;
+		ntfs_debug("Extent inode 0x%lx is not attached to its base inode 0x%lx, write the extent record.",
 				mft_no, na.mft_no);
 		return true;
 	}
@@ -1077,22 +889,27 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	/* Take a reference to the extent ntfs inode. */
 	atomic_inc(&eni->count);
 	mutex_unlock(&ni->extent_lock);
+
+	/* if extent inode is dirty, write_inode will write it */
+	if (NInoDirty(eni)) {
+		atomic_dec(&eni->count);
+		*ref_vi = vi;
+		return false;
+	}
+
 	/*
 	 * Found the extent inode coresponding to this extent mft record.
 	 * Try to take the mft record lock.
 	 */
 	if (unlikely(!mutex_trylock(&eni->mrec_lock))) {
 		atomic_dec(&eni->count);
-		iput(vi);
-		ntfs_debug("Extent mft record 0x%lx is already locked, do "
-				"not write it.", mft_no);
+		*ref_vi = vi;
+		ntfs_debug("Extent mft record 0x%lx is already locked, do not write it.",
+				mft_no);
 		return false;
 	}
 	ntfs_debug("Managed to lock extent mft record 0x%lx, write it.",
 			mft_no);
-	if (NInoTestClearDirty(eni))
-		ntfs_debug("Extent inode 0x%lx is dirty, marking it clean.",
-				mft_no);
 	/*
 	 * The write has to occur while we hold the mft record lock so return
 	 * the locked extent ntfs inode.
@@ -1101,10 +918,11 @@ bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	return true;
 }
 
-static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
-		"chkdsk.";
+static const char *es = "  Leaving inconsistent metadata.  Unmount and run chkdsk.";
+
+#define RESERVED_MFT_RECORDS	64
 
-/**
+/*
  * ntfs_mft_bitmap_find_and_alloc_free_rec_nolock - see name
  * @vol:	volume on which to search for a free mft record
  * @base_ni:	open base inode if allocating an extent mft record or NULL
@@ -1123,19 +941,18 @@ static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
  *
  * Locking: Caller must hold vol->mftbmp_lock for writing.
  */
-static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
-		ntfs_inode *base_ni)
+static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vol,
+		struct ntfs_inode *base_ni)
 {
 	s64 pass_end, ll, data_pos, pass_start, ofs, bit;
 	unsigned long flags;
 	struct address_space *mftbmp_mapping;
-	u8 *buf, *byte;
-	struct page *page;
-	unsigned int page_ofs, size;
+	u8 *buf = NULL, *byte;
+	struct folio *folio;
+	unsigned int folio_ofs, size;
 	u8 pass, b;
 
-	ntfs_debug("Searching for free mft record in the currently "
-			"initialized mft bitmap.");
+	ntfs_debug("Searching for free mft record in the currently initialized mft bitmap.");
 	mftbmp_mapping = vol->mftbmp_ino->i_mapping;
 	/*
 	 * Set the end of the pass making sure we do not overflow the mft
@@ -1155,26 +972,30 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 		data_pos = vol->mft_data_pos;
 	else
 		data_pos = base_ni->mft_no + 1;
-	if (data_pos < 24)
-		data_pos = 24;
+	if (data_pos < RESERVED_MFT_RECORDS)
+		data_pos = RESERVED_MFT_RECORDS;
 	if (data_pos >= pass_end) {
-		data_pos = 24;
+		data_pos = RESERVED_MFT_RECORDS;
 		pass = 2;
 		/* This happens on a freshly formatted volume. */
 		if (data_pos >= pass_end)
 			return -ENOSPC;
 	}
+
+	if (base_ni && base_ni->mft_no == FILE_MFT) {
+		data_pos = 0;
+		pass = 2;
+	}
+
 	pass_start = data_pos;
-	ntfs_debug("Starting bitmap search: pass %u, pass_start 0x%llx, "
-			"pass_end 0x%llx, data_pos 0x%llx.", pass,
-			(long long)pass_start, (long long)pass_end,
-			(long long)data_pos);
+	ntfs_debug("Starting bitmap search: pass %u, pass_start 0x%llx, pass_end 0x%llx, data_pos 0x%llx.",
+			pass, pass_start, pass_end, data_pos);
 	/* Loop until a free mft record is found. */
 	for (; pass <= 2;) {
 		/* Cap size to pass_end. */
 		ofs = data_pos >> 3;
-		page_ofs = ofs & ~PAGE_MASK;
-		size = PAGE_SIZE - page_ofs;
+		folio_ofs = ofs & ~PAGE_MASK;
+		size = PAGE_SIZE - folio_ofs;
 		ll = ((pass_end + 7) >> 3) - ofs;
 		if (size > ll)
 			size = ll;
@@ -1184,21 +1005,32 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 		 * for a zero bit.
 		 */
 		if (size) {
-			page = ntfs_map_page(mftbmp_mapping,
-					ofs >> PAGE_SHIFT);
-			if (IS_ERR(page)) {
-				ntfs_error(vol->sb, "Failed to read mft "
-						"bitmap, aborting.");
-				return PTR_ERR(page);
+			folio = read_mapping_folio(mftbmp_mapping,
+					ofs >> PAGE_SHIFT, NULL);
+			if (IS_ERR(folio)) {
+				ntfs_error(vol->sb, "Failed to read mft bitmap, aborting.");
+				return PTR_ERR(folio);
 			}
-			buf = (u8*)page_address(page) + page_ofs;
+			folio_lock(folio);
+			buf = (u8 *)kmap_local_folio(folio, 0) + folio_ofs;
 			bit = data_pos & 7;
 			data_pos &= ~7ull;
-			ntfs_debug("Before inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
+			ntfs_debug("Before inner for loop: size 0x%x, data_pos 0x%llx, bit 0x%llx",
+					size, data_pos, bit);
 			for (; bit < size && data_pos + bit < pass_end;
 					bit &= ~7ull, bit += 8) {
+				/*
+				 * If we're extending $MFT and running out of the first
+				 * mft record (base record) then give up searching since
+				 * no guarantee that the found record will be accessible.
+				 */
+				if (base_ni && base_ni->mft_no == FILE_MFT && bit > 400) {
+					folio_unlock(folio);
+					kunmap_local(buf);
+					folio_put(folio);
+					return -ENOSPC;
+				}
+
 				byte = buf + (bit >> 3);
 				if (*byte == 0xff)
 					continue;
@@ -1206,25 +1038,27 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 				if (b < 8 && b >= (bit & 7)) {
 					ll = data_pos + (bit & ~7ull) + b;
 					if (unlikely(ll > (1ll << 32))) {
-						ntfs_unmap_page(page);
+						folio_unlock(folio);
+						kunmap_local(buf);
+						folio_put(folio);
 						return -ENOSPC;
 					}
 					*byte |= 1 << b;
-					flush_dcache_page(page);
-					set_page_dirty(page);
-					ntfs_unmap_page(page);
-					ntfs_debug("Done.  (Found and "
-							"allocated mft record "
-							"0x%llx.)",
-							(long long)ll);
+					folio_mark_dirty(folio);
+					folio_unlock(folio);
+					kunmap_local(buf);
+					folio_put(folio);
+					ntfs_debug("Done.  (Found and allocated mft record 0x%llx.)",
+							ll);
 					return ll;
 				}
 			}
-			ntfs_debug("After inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
+			ntfs_debug("After inner for loop: size 0x%x, data_pos 0x%llx, bit 0x%llx",
+					size, data_pos, bit);
 			data_pos += size;
-			ntfs_unmap_page(page);
+			folio_unlock(folio);
+			kunmap_local(buf);
+			folio_put(folio);
 			/*
 			 * If the end of the pass has not been reached yet,
 			 * continue searching the mft bitmap for a zero bit.
@@ -1239,21 +1073,48 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 			 * part of the zone which we omitted earlier.
 			 */
 			pass_end = pass_start;
-			data_pos = pass_start = 24;
-			ntfs_debug("pass %i, pass_start 0x%llx, pass_end "
-					"0x%llx.", pass, (long long)pass_start,
-					(long long)pass_end);
+			data_pos = pass_start = RESERVED_MFT_RECORDS;
+			ntfs_debug("pass %i, pass_start 0x%llx, pass_end 0x%llx.",
+					pass, pass_start, pass_end);
 			if (data_pos >= pass_end)
 				break;
 		}
 	}
 	/* No free mft records in currently initialized mft bitmap. */
-	ntfs_debug("Done.  (No free mft records left in currently initialized "
-			"mft bitmap.)");
+	ntfs_debug("Done.  (No free mft records left in currently initialized mft bitmap.)");
 	return -ENOSPC;
 }
 
-/**
+static int ntfs_mft_attr_extend(struct ntfs_inode *ni)
+{
+	int ret = 0;
+	struct ntfs_inode *base_ni;
+
+	if (NInoAttr(ni))
+		base_ni = ni->ext.base_ntfs_ino;
+	else
+		base_ni = ni;
+
+	if (!NInoAttrList(base_ni)) {
+		ret = ntfs_inode_add_attrlist(base_ni);
+		if (ret) {
+			pr_err("Can not add attrlist\n");
+			goto out;
+		} else {
+			ret = -EAGAIN;
+			goto out;
+		}
+	}
+
+	ret = ntfs_attr_update_mapping_pairs(ni, 0);
+	if (ret)
+		pr_err("MP update failed\n");
+
+out:
+	return ret;
+}
+
+/*
  * ntfs_mft_bitmap_extend_allocation_nolock - extend mft bitmap by a cluster
  * @vol:	volume on which to extend the mft bitmap attribute
  *
@@ -1270,17 +1131,17 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
  *	    - This function takes vol->lcnbmp_lock for writing and releases it
  *	      before returning.
  */
-static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
+static int ntfs_mft_bitmap_extend_allocation_nolock(struct ntfs_volume *vol)
 {
-	LCN lcn;
+	s64 lcn;
 	s64 ll;
 	unsigned long flags;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	runlist_element *rl, *rl2 = NULL;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
+	struct folio *folio;
+	struct ntfs_inode *mft_ni, *mftbmp_ni;
+	struct runlist_element *rl, *rl2 = NULL;
+	struct ntfs_attr_search_ctx *ctx = NULL;
+	struct mft_record *mrec;
+	struct attr_record *a = NULL;
 	int ret, mp_size;
 	u32 old_alen = 0;
 	u8 *b, tb;
@@ -1288,7 +1149,9 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 		u8 added_cluster:1;
 		u8 added_run:1;
 		u8 mp_rebuilt:1;
-	} status = { 0, 0, 0 };
+		u8 mp_extended:1;
+	} status = { 0, 0, 0, 0 };
+	size_t new_rl_count;
 
 	ntfs_debug("Extending mft bitmap allocation.");
 	mft_ni = NTFS_I(vol->mft_ino);
@@ -1302,11 +1165,11 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 	ll = mftbmp_ni->allocated_size;
 	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 	rl = ntfs_attr_find_vcn_nolock(mftbmp_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
+			NTFS_B_TO_CLU(vol, ll - 1), NULL);
 	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
 		up_write(&mftbmp_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft bitmap attribute.");
+		ntfs_error(vol->sb,
+			"Failed to determine last allocated cluster of mft bitmap attribute.");
 		if (!IS_ERR(rl))
 			ret = -EIO;
 		else
@@ -1322,54 +1185,59 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 	 * to us.
 	 */
 	ll = lcn >> 3;
-	page = ntfs_map_page(vol->lcnbmp_ino->i_mapping,
-			ll >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
+	folio = read_mapping_folio(vol->lcnbmp_ino->i_mapping,
+			ll >> PAGE_SHIFT, NULL);
+	if (IS_ERR(folio)) {
 		up_write(&mftbmp_ni->runlist.lock);
 		ntfs_error(vol->sb, "Failed to read from lcn bitmap.");
-		return PTR_ERR(page);
+		return PTR_ERR(folio);
 	}
-	b = (u8*)page_address(page) + (ll & ~PAGE_MASK);
-	tb = 1 << (lcn & 7ull);
+
 	down_write(&vol->lcnbmp_lock);
+	folio_lock(folio);
+	b = (u8 *)kmap_local_folio(folio, 0) + (ll & ~PAGE_MASK);
+	tb = 1 << (lcn & 7ull);
 	if (*b != 0xff && !(*b & tb)) {
 		/* Next cluster is free, allocate it. */
 		*b |= tb;
-		flush_dcache_page(page);
-		set_page_dirty(page);
+		folio_mark_dirty(folio);
+		folio_unlock(folio);
+		kunmap_local(b);
+		folio_put(folio);
 		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
 		/* Update the mft bitmap runlist. */
 		rl->length++;
 		rl[1].vcn++;
 		status.added_cluster = 1;
 		ntfs_debug("Appending one cluster to mft bitmap.");
 	} else {
+		folio_unlock(folio);
+		kunmap_local(b);
+		folio_put(folio);
 		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
 		/* Allocate a cluster from the DATA_ZONE. */
 		rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE,
-				true);
+				true, false, false);
 		if (IS_ERR(rl2)) {
 			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to allocate a cluster for "
-					"the mft bitmap.");
+			ntfs_error(vol->sb,
+					"Failed to allocate a cluster for the mft bitmap.");
 			return PTR_ERR(rl2);
 		}
-		rl = ntfs_runlists_merge(mftbmp_ni->runlist.rl, rl2);
+		rl = ntfs_runlists_merge(&mftbmp_ni->runlist, rl2, 0, &new_rl_count);
 		if (IS_ERR(rl)) {
 			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to merge runlists for mft "
-					"bitmap.");
+			ntfs_error(vol->sb, "Failed to merge runlists for mft bitmap.");
 			if (ntfs_cluster_free_from_rl(vol, rl2)) {
-				ntfs_error(vol->sb, "Failed to deallocate "
-						"allocated cluster.%s", es);
+				ntfs_error(vol->sb, "Failed to deallocate allocated cluster.%s",
+						es);
 				NVolSetErrors(vol);
 			}
-			ntfs_free(rl2);
+			kvfree(rl2);
 			return PTR_ERR(rl);
 		}
 		mftbmp_ni->runlist.rl = rl;
+		mftbmp_ni->runlist.count = new_rl_count;
 		status.added_run = 1;
 		ntfs_debug("Adding one run to mft bitmap.");
 		/* Find the last run in the new runlist. */
@@ -1396,26 +1264,26 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
 			0, ctx);
 	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.");
+		ntfs_error(vol->sb,
+			"Failed to find last attribute extent of mft bitmap attribute.");
 		if (ret == -ENOENT)
 			ret = -EIO;
 		goto undo_alloc;
 	}
 	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
+	ll = le64_to_cpu(a->data.non_resident.lowest_vcn);
 	/* Search back for the previous last allocated cluster of mft bitmap. */
 	for (rl2 = rl; rl2 > mftbmp_ni->runlist.rl; rl2--) {
 		if (ll >= rl2->vcn)
 			break;
 	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
+	WARN_ON(ll < rl2->vcn);
+	WARN_ON(ll >= rl2->vcn + rl2->length);
 	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
+	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1, -1);
 	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft bitmap attribute extent.");
+		ntfs_error(vol->sb,
+			"Get size for mapping pairs failed for mft bitmap attribute extent.");
 		ret = mp_size;
 		if (!ret)
 			ret = -EIO;
@@ -1426,76 +1294,67 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
 			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
 	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft bitmap attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: It will need to be a special mft record and if none of
-		// those are available it gets rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft bitmap attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
+		ret = ntfs_mft_attr_extend(mftbmp_ni);
+		if (!ret)
+			goto extended_ok;
+		status.mp_extended = 1;
 		goto undo_alloc;
 	}
 	status.mp_rebuilt = 1;
 	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
+	ret = ntfs_mapping_pairs_build(vol, (u8 *)a +
 			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
+			mp_size, rl2, ll, -1, NULL, NULL, NULL);
 	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array for "
-				"mft bitmap attribute.");
+		ntfs_error(vol->sb,
+			"Failed to build mapping pairs array for mft bitmap attribute.");
 		goto undo_alloc;
 	}
 	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
+	a->data.non_resident.highest_vcn = cpu_to_le64(rl[1].vcn - 1);
 	/*
 	 * We now have extended the mft bitmap allocated_size by one cluster.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
+	 * Reflect this in the struct ntfs_inode structure and the attribute record.
 	 */
 	if (a->data.non_resident.lowest_vcn) {
 		/*
 		 * We are not in the first attribute extent, switch to it, but
 		 * first ensure the changes will make it to disk later.
 		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
 		mark_mft_record_dirty(ctx->ntfs_ino);
 		ntfs_attr_reinit_search_ctx(ctx);
 		ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
 				mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL,
 				0, ctx);
 		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft bitmap attribute.");
+			ntfs_error(vol->sb,
+				"Failed to find first attribute extent of mft bitmap attribute.");
 			goto restore_undo_alloc;
 		}
 		a = ctx->attr;
 	}
+
+extended_ok:
 	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
 	mftbmp_ni->allocated_size += vol->cluster_size;
 	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mftbmp_ni->allocated_size);
+			cpu_to_le64(mftbmp_ni->allocated_size);
 	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	mark_mft_record_dirty(ctx->ntfs_ino);
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(mft_ni);
 	up_write(&mftbmp_ni->runlist.lock);
 	ntfs_debug("Done.");
 	return 0;
+
 restore_undo_alloc:
 	ntfs_attr_reinit_search_ctx(ctx);
 	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
 			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
 			0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.%s", es);
+		ntfs_error(vol->sb,
+			"Failed to find last attribute extent of mft bitmap attribute.%s", es);
 		write_lock_irqsave(&mftbmp_ni->size_lock, flags);
 		mftbmp_ni->allocated_size += vol->cluster_size;
 		write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
@@ -1510,7 +1369,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 		return ret;
 	}
 	a = ctx->attr;
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 2);
+	a->data.non_resident.highest_vcn = cpu_to_le64(rl[1].vcn - 2);
 undo_alloc:
 	if (status.added_cluster) {
 		/* Truncate the last run in the runlist by one cluster. */
@@ -1521,31 +1380,33 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 		/* Remove the last run from the runlist. */
 		rl->lcn = rl[1].lcn;
 		rl->length = 0;
+		mftbmp_ni->runlist.count--;
 	}
 	/* Deallocate the cluster. */
 	down_write(&vol->lcnbmp_lock);
 	if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
 		ntfs_error(vol->sb, "Failed to free allocated cluster.%s", es);
 		NVolSetErrors(vol);
-	}
+	} else
+		ntfs_inc_free_clusters(vol, 1);
 	up_write(&vol->lcnbmp_lock);
 	if (status.mp_rebuilt) {
-		if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
+		if (ntfs_mapping_pairs_build(vol, (u8 *)a + le16_to_cpu(
 				a->data.non_resident.mapping_pairs_offset),
 				old_alen - le16_to_cpu(
 				a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-			ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
+				rl2, ll, -1, NULL, NULL, NULL)) {
+			ntfs_error(vol->sb, "Failed to restore mapping pairs array.%s", es);
 			NVolSetErrors(vol);
 		}
 		if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
+			ntfs_error(vol->sb, "Failed to restore attribute record.%s", es);
 			NVolSetErrors(vol);
 		}
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
 		mark_mft_record_dirty(ctx->ntfs_ino);
+	} else if (status.mp_extended && ntfs_attr_update_mapping_pairs(mftbmp_ni, 0)) {
+		ntfs_error(vol->sb, "Failed to restore mapping pairs.%s", es);
+		NVolSetErrors(vol);
 	}
 	if (ctx)
 		ntfs_attr_put_search_ctx(ctx);
@@ -1555,7 +1416,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 	return ret;
 }
 
-/**
+/*
  * ntfs_mft_bitmap_extend_initialized_nolock - extend mftbmp initialized data
  * @vol:	volume on which to extend the mft bitmap attribute
  *
@@ -1569,15 +1430,15 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
  *
  * Locking: Caller must hold vol->mftbmp_lock for writing.
  */
-static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
+static int ntfs_mft_bitmap_extend_initialized_nolock(struct ntfs_volume *vol)
 {
 	s64 old_data_size, old_initialized_size;
 	unsigned long flags;
 	struct inode *mftbmp_vi;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a;
+	struct ntfs_inode *mft_ni, *mftbmp_ni;
+	struct ntfs_attr_search_ctx *ctx;
+	struct mft_record *mrec;
+	struct attr_record *a;
 	int ret;
 
 	ntfs_debug("Extending mft bitmap initiailized (and data) size.");
@@ -1599,8 +1460,8 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
 	ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
 			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx);
 	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.");
+		ntfs_error(vol->sb,
+			"Failed to find first attribute extent of mft bitmap attribute.");
 		if (ret == -ENOENT)
 			ret = -EIO;
 		goto put_err_out;
@@ -1616,23 +1477,22 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
 	 */
 	mftbmp_ni->initialized_size += 8;
 	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mftbmp_ni->initialized_size);
+			cpu_to_le64(mftbmp_ni->initialized_size);
 	if (mftbmp_ni->initialized_size > old_data_size) {
 		i_size_write(mftbmp_vi, mftbmp_ni->initialized_size);
 		a->data.non_resident.data_size =
-				cpu_to_sle64(mftbmp_ni->initialized_size);
+				cpu_to_le64(mftbmp_ni->initialized_size);
 	}
 	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	mark_mft_record_dirty(ctx->ntfs_ino);
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(mft_ni);
 	/* Initialize the mft bitmap attribute value with zeroes. */
 	ret = ntfs_attr_set(mftbmp_ni, old_initialized_size, 8, 0);
 	if (likely(!ret)) {
-		ntfs_debug("Done.  (Wrote eight initialized bytes to mft "
-				"bitmap.");
+		ntfs_debug("Done.  (Wrote eight initialized bytes to mft bitmap.");
+		ntfs_inc_free_mft_records(vol, 8 * 8);
 		return 0;
 	}
 	ntfs_error(vol->sb, "Failed to write to mft bitmap.");
@@ -1651,8 +1511,8 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
 	}
 	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
 			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.%s", es);
+		ntfs_error(vol->sb,
+			"Failed to find first attribute extent of mft bitmap attribute.%s", es);
 		NVolSetErrors(vol);
 put_err_out:
 		ntfs_attr_put_search_ctx(ctx);
@@ -1664,30 +1524,27 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
 	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
 	mftbmp_ni->initialized_size = old_initialized_size;
 	a->data.non_resident.initialized_size =
-			cpu_to_sle64(old_initialized_size);
+			cpu_to_le64(old_initialized_size);
 	if (i_size_read(mftbmp_vi) != old_data_size) {
 		i_size_write(mftbmp_vi, old_data_size);
-		a->data.non_resident.data_size = cpu_to_sle64(old_data_size);
+		a->data.non_resident.data_size = cpu_to_le64(old_data_size);
 	}
 	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	mark_mft_record_dirty(ctx->ntfs_ino);
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(mft_ni);
 #ifdef DEBUG
 	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Restored status of mftbmp: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(mftbmp_vi),
-			(long long)mftbmp_ni->initialized_size);
+	ntfs_debug("Restored status of mftbmp: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+			mftbmp_ni->allocated_size, i_size_read(mftbmp_vi),
+			mftbmp_ni->initialized_size);
 	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 #endif /* DEBUG */
 err_out:
 	return ret;
 }
 
-/**
+/*
  * ntfs_mft_data_extend_allocation_nolock - extend mft data attribute
  * @vol:	volume on which to extend the mft data attribute
  *
@@ -1706,20 +1563,21 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
  *	    - This function calls functions which take vol->lcnbmp_lock for
  *	      writing and release it before returning.
  */
-static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
+static int ntfs_mft_data_extend_allocation_nolock(struct ntfs_volume *vol)
 {
-	LCN lcn;
-	VCN old_last_vcn;
+	s64 lcn;
+	s64 old_last_vcn;
 	s64 min_nr, nr, ll;
 	unsigned long flags;
-	ntfs_inode *mft_ni;
-	runlist_element *rl, *rl2;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
+	struct ntfs_inode *mft_ni;
+	struct runlist_element *rl, *rl2;
+	struct ntfs_attr_search_ctx *ctx = NULL;
+	struct mft_record *mrec;
+	struct attr_record *a = NULL;
 	int ret, mp_size;
 	u32 old_alen = 0;
-	bool mp_rebuilt = false;
+	bool mp_rebuilt = false, mp_extended = false;
+	size_t new_rl_count;
 
 	ntfs_debug("Extending mft data allocation.");
 	mft_ni = NTFS_I(vol->mft_ino);
@@ -1733,11 +1591,11 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 	ll = mft_ni->allocated_size;
 	read_unlock_irqrestore(&mft_ni->size_lock, flags);
 	rl = ntfs_attr_find_vcn_nolock(mft_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
+			NTFS_B_TO_CLU(vol, ll - 1), NULL);
 	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
 		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft data attribute.");
+		ntfs_error(vol->sb,
+			"Failed to determine last allocated cluster of mft data attribute.");
 		if (!IS_ERR(rl))
 			ret = -EIO;
 		else
@@ -1745,9 +1603,9 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 		return ret;
 	}
 	lcn = rl->lcn + rl->length;
-	ntfs_debug("Last lcn of mft data attribute is 0x%llx.", (long long)lcn);
+	ntfs_debug("Last lcn of mft data attribute is 0x%llx.", lcn);
 	/* Minimum allocation is one mft record worth of clusters. */
-	min_nr = vol->mft_record_size >> vol->cluster_size_bits;
+	min_nr = NTFS_B_TO_CLU(vol, vol->mft_record_size);
 	if (!min_nr)
 		min_nr = 1;
 	/* Want to allocate 16 mft records worth of clusters. */
@@ -1758,14 +1616,13 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 	read_lock_irqsave(&mft_ni->size_lock, flags);
 	ll = mft_ni->allocated_size;
 	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
+	if (unlikely((ll + NTFS_CLU_TO_B(vol, nr)) >>
 			vol->mft_record_size_bits >= (1ll << 32))) {
 		nr = min_nr;
-		if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
+		if (unlikely((ll + NTFS_CLU_TO_B(vol, nr)) >>
 				vol->mft_record_size_bits >= (1ll << 32))) {
-			ntfs_warning(vol->sb, "Cannot allocate mft record "
-					"because the maximum number of inodes "
-					"(2^32) has already been reached.");
+			ntfs_warning(vol->sb,
+				"Cannot allocate mft record because the maximum number of inodes (2^32) has already been reached.");
 			up_write(&mft_ni->runlist.lock);
 			return -ENOSPC;
 		}
@@ -1773,16 +1630,24 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 	ntfs_debug("Trying mft data allocation with %s cluster count %lli.",
 			nr > min_nr ? "default" : "minimal", (long long)nr);
 	old_last_vcn = rl[1].vcn;
+	/*
+	 * We can release the mft_ni runlist lock, Because this function is
+	 * the only one that expends $MFT data attribute and is called with
+	 * mft_ni->mrec_lock.
+	 * This is required for the lock order, vol->lcnbmp_lock =>
+	 * mft_ni->runlist.lock.
+	 */
+	up_write(&mft_ni->runlist.lock);
+
 	do {
 		rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE,
-				true);
+				true, false, false);
 		if (!IS_ERR(rl2))
 			break;
 		if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) {
-			ntfs_error(vol->sb, "Failed to allocate the minimal "
-					"number of clusters (%lli) for the "
-					"mft data attribute.", (long long)nr);
-			up_write(&mft_ni->runlist.lock);
+			ntfs_error(vol->sb,
+				"Failed to allocate the minimal number of clusters (%lli) for the mft data attribute.",
+				nr);
 			return PTR_ERR(rl2);
 		}
 		/*
@@ -1791,32 +1656,36 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 		 * before failing.
 		 */
 		nr = min_nr;
-		ntfs_debug("Retrying mft data allocation with minimal cluster "
-				"count %lli.", (long long)nr);
+		ntfs_debug("Retrying mft data allocation with minimal cluster count %lli.", nr);
 	} while (1);
-	rl = ntfs_runlists_merge(mft_ni->runlist.rl, rl2);
+
+	down_write(&mft_ni->runlist.lock);
+	rl = ntfs_runlists_merge(&mft_ni->runlist, rl2, 0, &new_rl_count);
 	if (IS_ERR(rl)) {
 		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to merge runlists for mft data "
-				"attribute.");
+		ntfs_error(vol->sb, "Failed to merge runlists for mft data attribute.");
 		if (ntfs_cluster_free_from_rl(vol, rl2)) {
-			ntfs_error(vol->sb, "Failed to deallocate clusters "
-					"from the mft data attribute.%s", es);
+			ntfs_error(vol->sb,
+				"Failed to deallocate clusters from the mft data attribute.%s", es);
 			NVolSetErrors(vol);
 		}
-		ntfs_free(rl2);
+		kvfree(rl2);
 		return PTR_ERR(rl);
 	}
 	mft_ni->runlist.rl = rl;
+	mft_ni->runlist.count = new_rl_count;
 	ntfs_debug("Allocated %lli clusters.", (long long)nr);
 	/* Find the last run in the new runlist. */
 	for (; rl[1].length; rl++)
 		;
+	up_write(&mft_ni->runlist.lock);
+
 	/* Update the attribute record as well. */
 	mrec = map_mft_record(mft_ni);
 	if (IS_ERR(mrec)) {
 		ntfs_error(vol->sb, "Failed to map mft record.");
 		ret = PTR_ERR(mrec);
+		down_write(&mft_ni->runlist.lock);
 		goto undo_alloc;
 	}
 	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
@@ -1828,72 +1697,60 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 	ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
 			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx);
 	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.");
+		ntfs_error(vol->sb, "Failed to find last attribute extent of mft data attribute.");
 		if (ret == -ENOENT)
 			ret = -EIO;
 		goto undo_alloc;
 	}
 	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
+	ll = le64_to_cpu(a->data.non_resident.lowest_vcn);
+
+	down_write(&mft_ni->runlist.lock);
 	/* Search back for the previous last allocated cluster of mft bitmap. */
 	for (rl2 = rl; rl2 > mft_ni->runlist.rl; rl2--) {
 		if (ll >= rl2->vcn)
 			break;
 	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
+	WARN_ON(ll < rl2->vcn);
+	WARN_ON(ll >= rl2->vcn + rl2->length);
 	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
+	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1, -1);
 	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft data attribute extent.");
+		ntfs_error(vol->sb,
+			"Get size for mapping pairs failed for mft data attribute extent.");
 		ret = mp_size;
 		if (!ret)
 			ret = -EIO;
+		up_write(&mft_ni->runlist.lock);
 		goto undo_alloc;
 	}
+	up_write(&mft_ni->runlist.lock);
+
 	/* Expand the attribute record if necessary. */
 	old_alen = le32_to_cpu(a->length);
 	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
 			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
 	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft data attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: Use the special reserved mft records and ensure that
-		// this extent is not required to find the mft record in
-		// question.  If no free special records left we would need to
-		// move an existing record away, insert ours in its place, and
-		// then place the moved record into the newly allocated space
-		// and we would then need to update all references to this mft
-		// record appropriately.  This is rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft data attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
+		ret = ntfs_mft_attr_extend(mft_ni);
+		if (!ret)
+			goto extended_ok;
+		mp_extended = true;
 		goto undo_alloc;
 	}
 	mp_rebuilt = true;
 	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
+	ret = ntfs_mapping_pairs_build(vol, (u8 *)a +
 			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
+			mp_size, rl2, ll, -1, NULL, NULL, NULL);
 	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array of "
-				"mft data attribute.");
+		ntfs_error(vol->sb, "Failed to build mapping pairs array of mft data attribute.");
 		goto undo_alloc;
 	}
 	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
+	a->data.non_resident.highest_vcn = cpu_to_le64(rl[1].vcn - 1);
 	/*
 	 * We now have extended the mft data allocated_size by nr clusters.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
+	 * Reflect this in the struct ntfs_inode structure and the attribute record.
 	 * @rl is the last (non-terminator) runlist element of mft data
 	 * attribute.
 	 */
@@ -1902,40 +1759,39 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 		 * We are not in the first attribute extent, switch to it, but
 		 * first ensure the changes will make it to disk later.
 		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
 		mark_mft_record_dirty(ctx->ntfs_ino);
 		ntfs_attr_reinit_search_ctx(ctx);
 		ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name,
 				mft_ni->name_len, CASE_SENSITIVE, 0, NULL, 0,
 				ctx);
 		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft data attribute.");
+			ntfs_error(vol->sb,
+				"Failed to find first attribute extent of mft data attribute.");
 			goto restore_undo_alloc;
 		}
 		a = ctx->attr;
 	}
+
+extended_ok:
 	write_lock_irqsave(&mft_ni->size_lock, flags);
-	mft_ni->allocated_size += nr << vol->cluster_size_bits;
+	mft_ni->allocated_size += NTFS_CLU_TO_B(vol, nr);
 	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mft_ni->allocated_size);
+			cpu_to_le64(mft_ni->allocated_size);
 	write_unlock_irqrestore(&mft_ni->size_lock, flags);
 	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	mark_mft_record_dirty(ctx->ntfs_ino);
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
 	ntfs_debug("Done.");
 	return 0;
 restore_undo_alloc:
 	ntfs_attr_reinit_search_ctx(ctx);
 	if (ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
 			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.%s", es);
+		ntfs_error(vol->sb,
+			"Failed to find last attribute extent of mft data attribute.%s", es);
 		write_lock_irqsave(&mft_ni->size_lock, flags);
-		mft_ni->allocated_size += nr << vol->cluster_size_bits;
+		mft_ni->allocated_size += NTFS_CLU_TO_B(vol, nr);
 		write_unlock_irqrestore(&mft_ni->size_lock, flags);
 		ntfs_attr_put_search_ctx(ctx);
 		unmap_mft_record(mft_ni);
@@ -1948,17 +1804,20 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 		return ret;
 	}
 	ctx->attr->data.non_resident.highest_vcn =
-			cpu_to_sle64(old_last_vcn - 1);
+			cpu_to_le64(old_last_vcn - 1);
 undo_alloc:
 	if (ntfs_cluster_free(mft_ni, old_last_vcn, -1, ctx) < 0) {
-		ntfs_error(vol->sb, "Failed to free clusters from mft data "
-				"attribute.%s", es);
+		ntfs_error(vol->sb, "Failed to free clusters from mft data attribute.%s", es);
 		NVolSetErrors(vol);
 	}
 
 	if (ntfs_rl_truncate_nolock(vol, &mft_ni->runlist, old_last_vcn)) {
-		ntfs_error(vol->sb, "Failed to truncate mft data attribute "
-				"runlist.%s", es);
+		ntfs_error(vol->sb, "Failed to truncate mft data attribute runlist.%s", es);
+		NVolSetErrors(vol);
+	}
+	if (mp_extended && ntfs_attr_update_mapping_pairs(mft_ni, 0)) {
+		ntfs_error(vol->sb, "Failed to restore mapping pairs.%s",
+			   es);
 		NVolSetErrors(vol);
 	}
 	if (ctx) {
@@ -1968,32 +1827,27 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
 				a->data.non_resident.mapping_pairs_offset),
 				old_alen - le16_to_cpu(
 					a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-				ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
+				rl2, ll, -1, NULL, NULL, NULL)) {
+				ntfs_error(vol->sb, "Failed to restore mapping pairs array.%s", es);
 				NVolSetErrors(vol);
 			}
 			if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-				ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
+				ntfs_error(vol->sb, "Failed to restore attribute record.%s", es);
 				NVolSetErrors(vol);
 			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
 			mark_mft_record_dirty(ctx->ntfs_ino);
 		} else if (IS_ERR(ctx->mrec)) {
-			ntfs_error(vol->sb, "Failed to restore attribute search "
-				"context.%s", es);
+			ntfs_error(vol->sb, "Failed to restore attribute search context.%s", es);
 			NVolSetErrors(vol);
 		}
 		ntfs_attr_put_search_ctx(ctx);
 	}
 	if (!IS_ERR(mrec))
 		unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
 	return ret;
 }
 
-/**
+/*
  * ntfs_mft_record_layout - layout an mft record into a memory buffer
  * @vol:	volume to which the mft record will belong
  * @mft_no:	mft reference specifying the mft record number
@@ -2006,24 +1860,24 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
  *
  * Return 0 on success and -errno on error.
  */
-static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
-		MFT_RECORD *m)
+static int ntfs_mft_record_layout(const struct ntfs_volume *vol, const s64 mft_no,
+		struct mft_record *m)
 {
-	ATTR_RECORD *a;
+	struct attr_record *a;
 
 	ntfs_debug("Entering for mft record 0x%llx.", (long long)mft_no);
 	if (mft_no >= (1ll << 32)) {
-		ntfs_error(vol->sb, "Mft record number 0x%llx exceeds "
-				"maximum of 2^32.", (long long)mft_no);
+		ntfs_error(vol->sb, "Mft record number 0x%llx exceeds maximum of 2^32.",
+				(long long)mft_no);
 		return -ERANGE;
 	}
 	/* Start by clearing the whole mft record to gives us a clean slate. */
 	memset(m, 0, vol->mft_record_size);
 	/* Aligned to 2-byte boundary. */
 	if (vol->major_ver < 3 || (vol->major_ver == 3 && !vol->minor_ver))
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD_OLD) + 1) & ~1);
+		m->usa_ofs = cpu_to_le16((sizeof(struct mft_record_old) + 1) & ~1);
 	else {
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD) + 1) & ~1);
+		m->usa_ofs = cpu_to_le16((sizeof(struct mft_record) + 1) & ~1);
 		/*
 		 * Set the NTFS 3.1+ specific fields while we know that the
 		 * volume version is 3.1+.
@@ -2037,16 +1891,11 @@ static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
 				NTFS_BLOCK_SIZE + 1);
 	else {
 		m->usa_count = cpu_to_le16(1);
-		ntfs_warning(vol->sb, "Sector size is bigger than mft record "
-				"size.  Setting usa_count to 1.  If chkdsk "
-				"reports this as corruption, please email "
-				"linux-ntfs-dev@...ts.sourceforge.net stating "
-				"that you saw this message and that the "
-				"modified filesystem created was corrupt.  "
-				"Thank you.");
+		ntfs_warning(vol->sb,
+			"Sector size is bigger than mft record size.  Setting usa_count to 1.  If chkdsk reports this as corruption");
 	}
 	/* Set the update sequence number to 1. */
-	*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = cpu_to_le16(1);
+	*(__le16 *)((u8 *)m + le16_to_cpu(m->usa_ofs)) = cpu_to_le16(1);
 	m->lsn = 0;
 	m->sequence_number = cpu_to_le16(1);
 	m->link_count = 0;
@@ -2067,14 +1916,14 @@ static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
 	m->base_mft_record = 0;
 	m->next_attr_instance = 0;
 	/* Add the termination attribute. */
-	a = (ATTR_RECORD*)((u8*)m + le16_to_cpu(m->attrs_offset));
+	a = (struct attr_record *)((u8 *)m + le16_to_cpu(m->attrs_offset));
 	a->type = AT_END;
 	a->length = 0;
 	ntfs_debug("Done.");
 	return 0;
 }
 
-/**
+/*
  * ntfs_mft_record_format - format an mft record on an ntfs volume
  * @vol:	volume on which to format the mft record
  * @mft_no:	mft record number to format
@@ -2085,12 +1934,12 @@ static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
  *
  * Return 0 on success and -errno on error.
  */
-static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
+static int ntfs_mft_record_format(const struct ntfs_volume *vol, const s64 mft_no)
 {
 	loff_t i_size;
 	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
-	MFT_RECORD *m;
+	struct folio *folio;
+	struct mft_record *m;
 	pgoff_t index, end_index;
 	unsigned int ofs;
 	int err;
@@ -2100,59 +1949,62 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
 	 * The index into the page cache and the offset within the page cache
 	 * page of the wanted mft record.
 	 */
-	index = mft_no << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
+	index = NTFS_MFT_NR_TO_PIDX(vol, mft_no);
+	ofs = NTFS_MFT_NR_TO_POFS(vol, mft_no);
 	/* The maximum valid index into the page cache for $MFT's data. */
 	i_size = i_size_read(mft_vi);
 	end_index = i_size >> PAGE_SHIFT;
 	if (unlikely(index >= end_index)) {
-		if (unlikely(index > end_index || ofs + vol->mft_record_size >=
-				(i_size & ~PAGE_MASK))) {
-			ntfs_error(vol->sb, "Tried to format non-existing mft "
-					"record 0x%llx.", (long long)mft_no);
+		if (unlikely(index > end_index ||
+			     ofs + vol->mft_record_size > (i_size & ~PAGE_MASK))) {
+			ntfs_error(vol->sb, "Tried to format non-existing mft record 0x%llx.",
+					(long long)mft_no);
 			return -ENOENT;
 		}
 	}
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing mft record "
-				"to format 0x%llx.", (long long)mft_no);
-		return PTR_ERR(page);
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
+
+	/* Read, map, and pin the folio containing the mft record. */
+	folio = read_mapping_folio(mft_vi->i_mapping, index, NULL);
+	if (IS_ERR(folio)) {
+		ntfs_error(vol->sb, "Failed to map page containing mft record to format 0x%llx.",
+				(long long)mft_no);
+		return PTR_ERR(folio);
+	}
+	folio_lock(folio);
+	folio_clear_uptodate(folio);
+	m = (struct mft_record *)((u8 *)kmap_local_folio(folio, 0) + ofs);
 	err = ntfs_mft_record_layout(vol, mft_no, m);
 	if (unlikely(err)) {
 		ntfs_error(vol->sb, "Failed to layout mft record 0x%llx.",
 				(long long)mft_no);
-		SetPageUptodate(page);
-		unlock_page(page);
-		ntfs_unmap_page(page);
+		folio_mark_uptodate(folio);
+		folio_unlock(folio);
+		kunmap_local(m);
+		folio_put(folio);
 		return err;
 	}
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
+	pre_write_mst_fixup((struct ntfs_record *)m, vol->mft_record_size);
+	folio_mark_uptodate(folio);
 	/*
 	 * Make sure the mft record is written out to disk.  We could use
 	 * ilookup5() to check if an inode is in icache and so on but this is
 	 * unnecessary as ntfs_writepage() will write the dirty record anyway.
 	 */
-	mark_ntfs_record_dirty(page, ofs);
-	ntfs_unmap_page(page);
+	ntfs_mft_mark_dirty(folio);
+	folio_unlock(folio);
+	kunmap_local(m);
+	folio_put(folio);
 	ntfs_debug("Done.");
 	return 0;
 }
 
-/**
+/*
  * ntfs_mft_record_alloc - allocate an mft record on an ntfs volume
  * @vol:	[IN]  volume on which to allocate the mft record
  * @mode:	[IN]  mode if want a file or directory, i.e. base inode or 0
+ * @ni:		[OUT] on success, set to the allocated ntfs inode
  * @base_ni:	[IN]  open base inode if allocating an extent mft record or NULL
- * @mrec:	[OUT] on successful return this is the mapped mft record
+ * @ni_mrec:	[OUT] on successful return this is the mapped mft record
  *
  * Allocate an mft record in $MFT/$DATA of an open ntfs volume @vol.
  *
@@ -2180,8 +2032,8 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
  * optimize this we start scanning at the place specified by @base_ni or if
  * @base_ni is NULL we start where we last stopped and we perform wrap around
  * when we reach the end.  Note, we do not try to allocate mft records below
- * number 24 because numbers 0 to 15 are the defined system files anyway and 16
- * to 24 are special in that they are used for storing extension mft records
+ * number 64 because numbers 0 to 15 are the defined system files anyway and 16
+ * to 64 are special in that they are used for storing extension mft records
  * for the $DATA attribute of $MFT.  This is required to avoid the possibility
  * of creating a runlist with a circular dependency which once written to disk
  * can never be read in again.  Windows will only use records 16 to 24 for
@@ -2191,7 +2043,7 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
  * doing this at some later time, it does not matter much for now.
  *
  * When scanning the mft bitmap, we only search up to the last allocated mft
- * record.  If there are no free records left in the range 24 to number of
+ * record.  If there are no free records left in the range 64 to number of
  * allocated mft records, then we extend the $MFT/$DATA attribute in order to
  * create free mft records.  We extend the allocated size of $MFT/$DATA by 16
  * records at a time or one cluster, if cluster size is above 16kiB.  If there
@@ -2200,24 +2052,24 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
  *
  * No matter how many mft records we allocate, we initialize only the first
  * allocated mft record, incrementing mft data size and initialized size
- * accordingly, open an ntfs_inode for it and return it to the caller, unless
- * there are less than 24 mft records, in which case we allocate and initialize
- * mft records until we reach record 24 which we consider as the first free mft
+ * accordingly, open an struct ntfs_inode for it and return it to the caller, unless
+ * there are less than 64 mft records, in which case we allocate and initialize
+ * mft records until we reach record 64 which we consider as the first free mft
  * record for use by normal files.
  *
  * If during any stage we overflow the initialized data in the mft bitmap, we
  * extend the initialized size (and data size) by 8 bytes, allocating another
  * cluster if required.  The bitmap data size has to be at least equal to the
  * number of mft records in the mft, but it can be bigger, in which case the
- * superflous bits are padded with zeroes.
+ * superfluous bits are padded with zeroes.
  *
  * Thus, when we return successfully (IS_ERR() is false), we will have:
  *	- initialized / extended the mft bitmap if necessary,
  *	- initialized / extended the mft data if necessary,
  *	- set the bit corresponding to the mft record being allocated in the
  *	  mft bitmap,
- *	- opened an ntfs_inode for the allocated mft record, and we will have
- *	- returned the ntfs_inode as well as the allocated mapped, pinned, and
+ *	- opened an struct ntfs_inode for the allocated mft record, and we will have
+ *	- returned the struct ntfs_inode as well as the allocated mapped, pinned, and
  *	  locked mft record.
  *
  * On error, the volume will be left in a consistent state and no record will
@@ -2237,42 +2089,46 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
  * easier because otherwise there might be circular invocations of functions
  * when reading the bitmap.
  */
-ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
-		ntfs_inode *base_ni, MFT_RECORD **mrec)
+int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode,
+			  struct ntfs_inode **ni, struct ntfs_inode *base_ni,
+			  struct mft_record **ni_mrec)
 {
 	s64 ll, bit, old_data_initialized, old_data_size;
 	unsigned long flags;
-	struct inode *vi;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni, *ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
+	struct folio *folio;
+	struct ntfs_inode *mft_ni, *mftbmp_ni;
+	struct ntfs_attr_search_ctx *ctx;
+	struct mft_record *m = NULL;
+	struct attr_record *a;
 	pgoff_t index;
 	unsigned int ofs;
 	int err;
-	le16 seq_no, usn;
+	__le16 seq_no, usn;
 	bool record_formatted = false;
+	unsigned int memalloc_flags;
 
-	if (base_ni) {
-		ntfs_debug("Entering (allocating an extent mft record for "
-				"base mft record 0x%llx).",
+	if (base_ni && *ni)
+		return -EINVAL;
+
+	/* @mode and @base_ni are mutually exclusive. */
+	if (mode && base_ni)
+		return -EINVAL;
+
+	if (base_ni)
+		ntfs_debug("Entering (allocating an extent mft record for base mft record 0x%llx).",
 				(long long)base_ni->mft_no);
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(mode);
-	} else
+	else
 		ntfs_debug("Entering (allocating a base mft record).");
-	if (mode) {
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(base_ni);
-		/* We only support creation of normal files and directories. */
-		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			return ERR_PTR(-EOPNOTSUPP);
-	}
-	BUG_ON(!mrec);
+
+	memalloc_flags = memalloc_nofs_save();
+
 	mft_ni = NTFS_I(vol->mft_ino);
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		mutex_lock(&mft_ni->mrec_lock);
 	mftbmp_ni = NTFS_I(vol->mftbmp_ino);
-	down_write(&vol->mftbmp_lock);
+search_free_rec:
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		down_write(&vol->mftbmp_lock);
 	bit = ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(vol, base_ni);
 	if (bit >= 0) {
 		ntfs_debug("Found and allocated free record (#1), bit 0x%llx.",
@@ -2280,9 +2136,19 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		goto have_alloc_rec;
 	}
 	if (bit != -ENOSPC) {
-		up_write(&vol->mftbmp_lock);
-		return ERR_PTR(bit);
+		if (!base_ni || base_ni->mft_no != FILE_MFT) {
+			up_write(&vol->mftbmp_lock);
+			mutex_unlock(&mft_ni->mrec_lock);
+		}
+		memalloc_nofs_restore(memalloc_flags);
+		return bit;
+	}
+
+	if (base_ni && base_ni->mft_no == FILE_MFT) {
+		memalloc_nofs_restore(memalloc_flags);
+		return bit;
 	}
+
 	/*
 	 * No free mft records left.  If the mft bitmap already covers more
 	 * than the currently used mft records, the next records are all free,
@@ -2297,10 +2163,11 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
 	old_data_initialized = mftbmp_ni->initialized_size;
 	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	if (old_data_initialized << 3 > ll && old_data_initialized > 3) {
+	if (old_data_initialized << 3 > ll &&
+	    old_data_initialized > RESERVED_MFT_RECORDS / 8) {
 		bit = ll;
-		if (bit < 24)
-			bit = 24;
+		if (bit < RESERVED_MFT_RECORDS)
+			bit = RESERVED_MFT_RECORDS;
 		if (unlikely(bit >= (1ll << 32)))
 			goto max_err_out;
 		ntfs_debug("Found free record (#2), bit 0x%llx.",
@@ -2317,28 +2184,28 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		goto max_err_out;
 	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
 	old_data_size = mftbmp_ni->allocated_size;
-	ntfs_debug("Status of mftbmp before extension: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)old_data_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)old_data_initialized);
+	ntfs_debug("Status of mftbmp before extension: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+			old_data_size, i_size_read(vol->mftbmp_ino),
+			old_data_initialized);
 	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 	if (old_data_initialized + 8 > old_data_size) {
 		/* Need to extend bitmap by one more cluster. */
 		ntfs_debug("mftbmp: initialized_size + 8 > allocated_size.");
 		err = ntfs_mft_bitmap_extend_allocation_nolock(vol);
+		if (err == -EAGAIN)
+			err = ntfs_mft_bitmap_extend_allocation_nolock(vol);
+
 		if (unlikely(err)) {
-			up_write(&vol->mftbmp_lock);
+			if (!base_ni || base_ni->mft_no != FILE_MFT)
+				up_write(&vol->mftbmp_lock);
 			goto err_out;
 		}
 #ifdef DEBUG
 		read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-		ntfs_debug("Status of mftbmp after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mftbmp_ni->allocated_size,
-				(long long)i_size_read(vol->mftbmp_ino),
-				(long long)mftbmp_ni->initialized_size);
+		ntfs_debug("Status of mftbmp after allocation extension: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+				mftbmp_ni->allocated_size,
+				i_size_read(vol->mftbmp_ino),
+				mftbmp_ni->initialized_size);
 		read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 #endif /* DEBUG */
 	}
@@ -2349,17 +2216,16 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	 */
 	err = ntfs_mft_bitmap_extend_initialized_nolock(vol);
 	if (unlikely(err)) {
-		up_write(&vol->mftbmp_lock);
+		if (!base_ni || base_ni->mft_no != FILE_MFT)
+			up_write(&vol->mftbmp_lock);
 		goto err_out;
 	}
 #ifdef DEBUG
 	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Status of mftbmp after initialized extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)mftbmp_ni->initialized_size);
+	ntfs_debug("Status of mftbmp after initialized extension: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+			mftbmp_ni->allocated_size,
+			i_size_read(vol->mftbmp_ino),
+			mftbmp_ni->initialized_size);
 	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
 #endif /* DEBUG */
 	ntfs_debug("Found free record (#3), bit 0x%llx.", (long long)bit);
@@ -2369,7 +2235,8 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	err = ntfs_bitmap_set_bit(vol->mftbmp_ino, bit);
 	if (unlikely(err)) {
 		ntfs_error(vol->sb, "Failed to allocate bit in mft bitmap.");
-		up_write(&vol->mftbmp_lock);
+		if (!base_ni || base_ni->mft_no != FILE_MFT)
+			up_write(&vol->mftbmp_lock);
 		goto err_out;
 	}
 	ntfs_debug("Set bit 0x%llx in mft bitmap.", (long long)bit);
@@ -2397,34 +2264,35 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	 * actually traversed more than once when a freshly formatted volume is
 	 * first written to so it optimizes away nicely in the common case.
 	 */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data before extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	while (ll > mft_ni->allocated_size) {
-		read_unlock_irqrestore(&mft_ni->size_lock, flags);
-		err = ntfs_mft_data_extend_allocation_nolock(vol);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to extend mft data "
-					"allocation.");
-			goto undo_mftbmp_alloc_nolock;
-		}
+	if (!base_ni || base_ni->mft_no != FILE_MFT) {
 		read_lock_irqsave(&mft_ni->size_lock, flags);
-		ntfs_debug("Status of mft data after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mft_ni->allocated_size,
-				(long long)i_size_read(vol->mft_ino),
-				(long long)mft_ni->initialized_size);
+		ntfs_debug("Status of mft data before extension: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+				mft_ni->allocated_size, i_size_read(vol->mft_ino),
+				mft_ni->initialized_size);
+		while (ll > mft_ni->allocated_size) {
+			read_unlock_irqrestore(&mft_ni->size_lock, flags);
+			err = ntfs_mft_data_extend_allocation_nolock(vol);
+			if (err == -EAGAIN)
+				err = ntfs_mft_data_extend_allocation_nolock(vol);
+
+			if (unlikely(err)) {
+				ntfs_error(vol->sb, "Failed to extend mft data allocation.");
+				goto undo_mftbmp_alloc_nolock;
+			}
+			read_lock_irqsave(&mft_ni->size_lock, flags);
+			ntfs_debug("Status of mft data after allocation extension: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+					mft_ni->allocated_size, i_size_read(vol->mft_ino),
+					mft_ni->initialized_size);
+		}
+		read_unlock_irqrestore(&mft_ni->size_lock, flags);
+	} else if (ll > mft_ni->allocated_size) {
+		err = -ENOSPC;
+		goto undo_mftbmp_alloc_nolock;
 	}
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
 	/*
 	 * Extend mft data initialized size (and data size of course) to reach
 	 * the allocated mft record, formatting the mft records allong the way.
-	 * Note: We only modify the ntfs_inode structure as that is all that is
+	 * Note: We only modify the struct ntfs_inode structure as that is all that is
 	 * needed by ntfs_mft_record_format().  We will update the attribute
 	 * record itself in one fell swoop later on.
 	 */
@@ -2433,7 +2301,7 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	old_data_size = vol->mft_ino->i_size;
 	while (ll > mft_ni->initialized_size) {
 		s64 new_initialized_size, mft_no;
-		
+
 		new_initialized_size = mft_ni->initialized_size +
 				vol->mft_record_size;
 		mft_no = mft_ni->initialized_size >> vol->mft_record_size_bits;
@@ -2469,8 +2337,7 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	err = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
 			CASE_SENSITIVE, 0, NULL, 0, ctx);
 	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft data attribute.");
+		ntfs_error(vol->sb, "Failed to find first attribute extent of mft data attribute.");
 		ntfs_attr_put_search_ctx(ctx);
 		unmap_mft_record(mft_ni);
 		goto undo_data_init;
@@ -2478,24 +2345,20 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	a = ctx->attr;
 	read_lock_irqsave(&mft_ni->size_lock, flags);
 	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mft_ni->initialized_size);
+			cpu_to_le64(mft_ni->initialized_size);
 	a->data.non_resident.data_size =
-			cpu_to_sle64(i_size_read(vol->mft_ino));
+			cpu_to_le64(i_size_read(vol->mft_ino));
 	read_unlock_irqrestore(&mft_ni->size_lock, flags);
 	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	mark_mft_record_dirty(ctx->ntfs_ino);
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(mft_ni);
 	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data after mft record initialization: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	BUG_ON(i_size_read(vol->mft_ino) > mft_ni->allocated_size);
-	BUG_ON(mft_ni->initialized_size > i_size_read(vol->mft_ino));
+	ntfs_debug("Status of mft data after mft record initialization: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.",
+			mft_ni->allocated_size,	i_size_read(vol->mft_ino),
+			mft_ni->initialized_size);
+	WARN_ON(i_size_read(vol->mft_ino) > mft_ni->allocated_size);
+	WARN_ON(mft_ni->initialized_size > i_size_read(vol->mft_ino));
 	read_unlock_irqrestore(&mft_ni->size_lock, flags);
 mft_rec_already_initialized:
 	/*
@@ -2507,41 +2370,39 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	 * that it is allocated in the mft bitmap means that no-one will try to
 	 * allocate it either.
 	 */
-	up_write(&vol->mftbmp_lock);
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		up_write(&vol->mftbmp_lock);
 	/*
 	 * We now have allocated and initialized the mft record.  Calculate the
 	 * index of and the offset within the page cache page the record is in.
 	 */
-	index = bit << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(vol->mft_ino->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing allocated "
-				"mft record 0x%llx.", (long long)bit);
-		err = PTR_ERR(page);
+	index = NTFS_MFT_NR_TO_PIDX(vol, bit);
+	ofs = NTFS_MFT_NR_TO_POFS(vol, bit);
+	/* Read, map, and pin the folio containing the mft record. */
+	folio = read_mapping_folio(vol->mft_ino->i_mapping, index, NULL);
+	if (IS_ERR(folio)) {
+		ntfs_error(vol->sb, "Failed to map page containing allocated mft record 0x%llx.",
+				bit);
+		err = PTR_ERR(folio);
 		goto undo_mftbmp_alloc;
 	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
+	folio_lock(folio);
+	folio_clear_uptodate(folio);
+	m = (struct mft_record *)((u8 *)kmap_local_folio(folio, 0) + ofs);
 	/* If we just formatted the mft record no need to do it again. */
 	if (!record_formatted) {
 		/* Sanity check that the mft record is really not in use. */
 		if (ntfs_is_file_record(m->magic) &&
 				(m->flags & MFT_RECORD_IN_USE)) {
-			ntfs_error(vol->sb, "Mft record 0x%llx was marked "
-					"free in mft bitmap but is marked "
-					"used itself.  Corrupt filesystem.  "
-					"Unmount and run chkdsk.",
-					(long long)bit);
-			err = -EIO;
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
+			ntfs_warning(vol->sb,
+				"Mft record 0x%llx was marked free in mft bitmap but is marked used itself. Unmount and run chkdsk.",
+				bit);
+			folio_mark_uptodate(folio);
+			folio_unlock(folio);
+			kunmap_local(m);
+			folio_put(folio);
 			NVolSetErrors(vol);
-			goto undo_mftbmp_alloc;
+			goto search_free_rec;
 		}
 		/*
 		 * We need to (re-)format the mft record, preserving the
@@ -2551,29 +2412,30 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		 * wrong with the previous mft record.
 		 */
 		seq_no = m->sequence_number;
-		usn = *(le16*)((u8*)m + le16_to_cpu(m->usa_ofs));
+		usn = *(__le16 *)((u8 *)m + le16_to_cpu(m->usa_ofs));
 		err = ntfs_mft_record_layout(vol, bit, m);
 		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to layout allocated mft "
-					"record 0x%llx.", (long long)bit);
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
+			ntfs_error(vol->sb, "Failed to layout allocated mft record 0x%llx.",
+					bit);
+			folio_mark_uptodate(folio);
+			folio_unlock(folio);
+			kunmap_local(m);
+			folio_put(folio);
 			goto undo_mftbmp_alloc;
 		}
 		if (seq_no)
 			m->sequence_number = seq_no;
 		if (usn && le16_to_cpu(usn) != 0xffff)
-			*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = usn;
+			*(__le16 *)((u8 *)m + le16_to_cpu(m->usa_ofs)) = usn;
+		pre_write_mst_fixup((struct ntfs_record *)m, vol->mft_record_size);
 	}
 	/* Set the mft record itself in use. */
 	m->flags |= MFT_RECORD_IN_USE;
 	if (S_ISDIR(mode))
 		m->flags |= MFT_RECORD_IS_DIRECTORY;
-	flush_dcache_page(page);
-	SetPageUptodate(page);
+	folio_mark_uptodate(folio);
 	if (base_ni) {
-		MFT_RECORD *m_tmp;
+		struct mft_record *m_tmp;
 
 		/*
 		 * Setup the base mft record in the extent mft record.  This
@@ -2587,22 +2449,24 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		 * attach it to the base inode @base_ni and map, pin, and lock
 		 * its, i.e. the allocated, mft record.
 		 */
-		m_tmp = map_extent_mft_record(base_ni, bit, &ni);
+		m_tmp = map_extent_mft_record(base_ni,
+					      MK_MREF(bit, le16_to_cpu(m->sequence_number)),
+					      ni);
 		if (IS_ERR(m_tmp)) {
-			ntfs_error(vol->sb, "Failed to map allocated extent "
-					"mft record 0x%llx.", (long long)bit);
+			ntfs_error(vol->sb, "Failed to map allocated extent mft record 0x%llx.",
+					bit);
 			err = PTR_ERR(m_tmp);
 			/* Set the mft record itself not in use. */
 			m->flags &= cpu_to_le16(
 					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
 			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
+			   ntfs_mft_mark_dirty(folio);
+			folio_unlock(folio);
+			kunmap_local(m);
+			folio_put(folio);
 			goto undo_mftbmp_alloc;
 		}
-		BUG_ON(m != m_tmp);
+
 		/*
 		 * Make sure the allocated mft record is written out to disk.
 		 * No need to set the inode dirty because the caller is going
@@ -2610,96 +2474,20 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		 * record (e.g. at a minimum a new attribute will be added to
 		 * the mft record.
 		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
+		ntfs_mft_mark_dirty(folio);
+		folio_unlock(folio);
 		/*
 		 * Need to unmap the page since map_extent_mft_record() mapped
 		 * it as well so we have it mapped twice at the moment.
 		 */
-		ntfs_unmap_page(page);
+		kunmap_local(m);
+		folio_put(folio);
 	} else {
-		/*
-		 * Allocate a new VFS inode and set it up.  NOTE: @vi->i_nlink
-		 * is set to 1 but the mft record->link_count is 0.  The caller
-		 * needs to bear this in mind.
-		 */
-		vi = new_inode(vol->sb);
-		if (unlikely(!vi)) {
-			err = -ENOMEM;
-			/* Set the mft record itself not in use. */
-			m->flags &= cpu_to_le16(
-					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
-			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		vi->i_ino = bit;
-
-		/* The owner and group come from the ntfs volume. */
-		vi->i_uid = vol->uid;
-		vi->i_gid = vol->gid;
-
-		/* Initialize the ntfs specific part of @vi. */
-		ntfs_init_big_inode(vi);
-		ni = NTFS_I(vi);
-		/*
-		 * Set the appropriate mode, attribute type, and name.  For
-		 * directories, also setup the index values to the defaults.
-		 */
-		if (S_ISDIR(mode)) {
-			vi->i_mode = S_IFDIR | S_IRWXUGO;
-			vi->i_mode &= ~vol->dmask;
-
-			NInoSetMstProtected(ni);
-			ni->type = AT_INDEX_ALLOCATION;
-			ni->name = I30;
-			ni->name_len = 4;
-
-			ni->itype.index.block_size = 4096;
-			ni->itype.index.block_size_bits = ntfs_ffs(4096) - 1;
-			ni->itype.index.collation_rule = COLLATION_FILE_NAME;
-			if (vol->cluster_size <= ni->itype.index.block_size) {
-				ni->itype.index.vcn_size = vol->cluster_size;
-				ni->itype.index.vcn_size_bits =
-						vol->cluster_size_bits;
-			} else {
-				ni->itype.index.vcn_size = vol->sector_size;
-				ni->itype.index.vcn_size_bits =
-						vol->sector_size_bits;
-			}
-		} else {
-			vi->i_mode = S_IFREG | S_IRWXUGO;
-			vi->i_mode &= ~vol->fmask;
-
-			ni->type = AT_DATA;
-			ni->name = NULL;
-			ni->name_len = 0;
-		}
-		if (IS_RDONLY(vi))
-			vi->i_mode &= ~S_IWUGO;
-
-		/* Set the inode times to the current time. */
-		simple_inode_init_ts(vi);
-		/*
-		 * Set the file size to 0, the ntfs inode sizes are set to 0 by
-		 * the call to ntfs_init_big_inode() below.
-		 */
-		vi->i_size = 0;
-		vi->i_blocks = 0;
-
-		/* Set the sequence number. */
-		vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
 		/*
 		 * Manually map, pin, and lock the mft record as we already
 		 * have its page mapped and it is very easy to do.
 		 */
-		atomic_inc(&ni->count);
-		mutex_lock(&ni->mrec_lock);
-		ni->page = page;
-		ni->page_ofs = ofs;
+		(*ni)->seq_no = le16_to_cpu(m->sequence_number);
 		/*
 		 * Make sure the allocated mft record is written out to disk.
 		 * NOTE: We do not set the ntfs inode dirty because this would
@@ -2710,23 +2498,40 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 		 * a minimum some new attributes will be added to the mft
 		 * record.
 		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
 
-		/* Add the inode to the inode hash for the superblock. */
-		insert_inode_hash(vi);
+		(*ni)->mrec = kmalloc(vol->mft_record_size, GFP_NOFS);
+		if (!(*ni)->mrec) {
+			folio_unlock(folio);
+			kunmap_local(m);
+			folio_put(folio);
+			goto undo_mftbmp_alloc;
+		}
 
+		memcpy((*ni)->mrec, m, vol->mft_record_size);
+		post_read_mst_fixup((struct ntfs_record *)(*ni)->mrec, vol->mft_record_size);
+		ntfs_mft_mark_dirty(folio);
+		folio_unlock(folio);
+		(*ni)->folio = folio;
+		(*ni)->folio_ofs = ofs;
+		atomic_inc(&(*ni)->count);
 		/* Update the default mft allocation position. */
 		vol->mft_data_pos = bit + 1;
 	}
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		mutex_unlock(&mft_ni->mrec_lock);
+	memalloc_nofs_restore(memalloc_flags);
+
 	/*
 	 * Return the opened, allocated inode of the allocated mft record as
 	 * well as the mapped, pinned, and locked mft record.
 	 */
 	ntfs_debug("Returning opened, allocated %sinode 0x%llx.",
-			base_ni ? "extent " : "", (long long)bit);
-	*mrec = m;
-	return ni;
+			base_ni ? "extent " : "", bit);
+	(*ni)->mft_no = bit;
+	if (ni_mrec)
+		*ni_mrec = (*ni)->mrec;
+	ntfs_dec_free_mft_records(vol, 1);
+	return 0;
 undo_data_init:
 	write_lock_irqsave(&mft_ni->size_lock, flags);
 	mft_ni->initialized_size = old_data_initialized;
@@ -2734,114 +2539,83 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	write_unlock_irqrestore(&mft_ni->size_lock, flags);
 	goto undo_mftbmp_alloc_nolock;
 undo_mftbmp_alloc:
-	down_write(&vol->mftbmp_lock);
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		down_write(&vol->mftbmp_lock);
 undo_mftbmp_alloc_nolock:
 	if (ntfs_bitmap_clear_bit(vol->mftbmp_ino, bit)) {
 		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
 		NVolSetErrors(vol);
 	}
-	up_write(&vol->mftbmp_lock);
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		up_write(&vol->mftbmp_lock);
 err_out:
-	return ERR_PTR(err);
+	if (!base_ni || base_ni->mft_no != FILE_MFT)
+		mutex_unlock(&mft_ni->mrec_lock);
+	memalloc_nofs_restore(memalloc_flags);
+	return err;
 max_err_out:
-	ntfs_warning(vol->sb, "Cannot allocate mft record because the maximum "
-			"number of inodes (2^32) has already been reached.");
-	up_write(&vol->mftbmp_lock);
-	return ERR_PTR(-ENOSPC);
+	ntfs_warning(vol->sb,
+		"Cannot allocate mft record because the maximum number of inodes (2^32) has already been reached.");
+	if (!base_ni || base_ni->mft_no != FILE_MFT) {
+		up_write(&vol->mftbmp_lock);
+		mutex_unlock(&mft_ni->mrec_lock);
+	}
+	memalloc_nofs_restore(memalloc_flags);
+	return -ENOSPC;
 }
 
-/**
- * ntfs_extent_mft_record_free - free an extent mft record on an ntfs volume
- * @ni:		ntfs inode of the mapped extent mft record to free
- * @m:		mapped extent mft record of the ntfs inode @ni
- *
- * Free the mapped extent mft record @m of the extent ntfs inode @ni.
- *
- * Note that this function unmaps the mft record and closes and destroys @ni
- * internally and hence you cannot use either @ni nor @m any more after this
- * function returns success.
+/*
+ * ntfs_mft_record_free - free an mft record on an ntfs volume
+ * @vol:	volume on which to free the mft record
+ * @ni:		open ntfs inode of the mft record to free
  *
- * On success return 0 and on error return -errno.  @ni and @m are still valid
- * in this case and have not been freed.
+ * Free the mft record of the open inode @ni on the mounted ntfs volume @vol.
+ * Note that this function calls ntfs_inode_close() internally and hence you
+ * cannot use the pointer @ni any more after this function returns success.
  *
- * For some errors an error message is displayed and the success code 0 is
- * returned and the volume is then left dirty on umount.  This makes sense in
- * case we could not rollback the changes that were already done since the
- * caller no longer wants to reference this mft record so it does not matter to
- * the caller if something is wrong with it as long as it is properly detached
- * from the base inode.
+ * On success return 0 and on error return -1 with errno set to the error code.
  */
-int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m)
+int ntfs_mft_record_free(struct ntfs_volume *vol, struct ntfs_inode *ni)
 {
-	unsigned long mft_no = ni->mft_no;
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	ntfs_inode **extent_nis;
-	int i, err;
-	le16 old_seq_no;
+	u64 mft_no;
+	int err;
 	u16 seq_no;
-	
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(ni->nr_extents != -1);
-
-	mutex_lock(&ni->extent_lock);
-	base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
-
-	BUG_ON(base_ni->nr_extents <= 0);
-
-	ntfs_debug("Entering for extent inode 0x%lx, base inode 0x%lx.\n",
-			mft_no, base_ni->mft_no);
-
-	mutex_lock(&base_ni->extent_lock);
+	__le16 old_seq_no;
+	struct mft_record *ni_mrec;
+	unsigned int memalloc_flags;
+	struct ntfs_inode *base_ni;
 
-	/* Make sure we are holding the only reference to the extent inode. */
-	if (atomic_read(&ni->count) > 2) {
-		ntfs_error(vol->sb, "Tried to free busy extent inode 0x%lx, "
-				"not freeing.", base_ni->mft_no);
-		mutex_unlock(&base_ni->extent_lock);
-		return -EBUSY;
-	}
-
-	/* Dissociate the ntfs inode from the base inode. */
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	err = -ENOENT;
-	for (i = 0; i < base_ni->nr_extents; i++) {
-		if (ni != extent_nis[i])
-			continue;
-		extent_nis += i;
-		base_ni->nr_extents--;
-		memmove(extent_nis, extent_nis + 1, (base_ni->nr_extents - i) *
-				sizeof(ntfs_inode*));
-		err = 0;
-		break;
-	}
+	if (!vol || !ni)
+		return -EINVAL;
 
-	mutex_unlock(&base_ni->extent_lock);
+	ntfs_debug("Entering for inode 0x%llx.\n", (long long)ni->mft_no);
 
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Extent inode 0x%lx is not attached to "
-				"its base inode 0x%lx.", mft_no,
-				base_ni->mft_no);
-		BUG();
-	}
+	ni_mrec = map_mft_record(ni);
+	if (IS_ERR(ni_mrec))
+		return -EIO;
 
-	/*
-	 * The extent inode is no longer attached to the base inode so no one
-	 * can get a reference to it any more.
-	 */
+	/* Cache the mft reference for later. */
+	mft_no = ni->mft_no;
 
 	/* Mark the mft record as not in use. */
-	m->flags &= ~MFT_RECORD_IN_USE;
+	ni_mrec->flags &= ~MFT_RECORD_IN_USE;
 
 	/* Increment the sequence number, skipping zero, if it is not zero. */
-	old_seq_no = m->sequence_number;
+	old_seq_no = ni_mrec->sequence_number;
 	seq_no = le16_to_cpu(old_seq_no);
 	if (seq_no == 0xffff)
 		seq_no = 1;
 	else if (seq_no)
 		seq_no++;
-	m->sequence_number = cpu_to_le16(seq_no);
+	ni_mrec->sequence_number = cpu_to_le16(seq_no);
+
+	down_read(&NTFS_I(vol->mft_ino)->runlist.lock);
+	err = ntfs_get_block_mft_record(NTFS_I(vol->mft_ino), ni);
+	up_read(&NTFS_I(vol->mft_ino)->runlist.lock);
+	if (err) {
+		unmap_mft_record(ni);
+		return err;
+	}
 
 	/*
 	 * Set the ntfs inode dirty and write it out.  We do not need to worry
@@ -2849,59 +2623,298 @@ int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m)
 	 * record to be freed is guaranteed to do it already.
 	 */
 	NInoSetDirty(ni);
-	err = write_mft_record(ni, m, 0);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to write mft record 0x%lx, not "
-				"freeing.", mft_no);
-		goto rollback;
-	}
-rollback_error:
-	/* Unmap and throw away the now freed extent inode. */
-	unmap_extent_mft_record(ni);
-	ntfs_clear_extent_inode(ni);
+	err = write_mft_record(ni, ni_mrec, 0);
+	if (err)
+		goto sync_rollback;
+
+	if (likely(ni->nr_extents >= 0))
+		base_ni = ni;
+	else
+		base_ni = ni->ext.base_ntfs_ino;
 
 	/* Clear the bit in the $MFT/$BITMAP corresponding to this record. */
-	down_write(&vol->mftbmp_lock);
+	memalloc_flags = memalloc_nofs_save();
+	if (base_ni->mft_no != FILE_MFT)
+		down_write(&vol->mftbmp_lock);
 	err = ntfs_bitmap_clear_bit(vol->mftbmp_ino, mft_no);
-	up_write(&vol->mftbmp_lock);
-	if (unlikely(err)) {
-		/*
-		 * The extent inode is gone but we failed to deallocate it in
-		 * the mft bitmap.  Just emit a warning and leave the volume
-		 * dirty on umount.
-		 */
-		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
-		NVolSetErrors(vol);
-	}
+	if (base_ni->mft_no != FILE_MFT)
+		up_write(&vol->mftbmp_lock);
+	memalloc_nofs_restore(memalloc_flags);
+	if (err)
+		goto bitmap_rollback;
+
+	unmap_mft_record(ni);
+	ntfs_inc_free_mft_records(vol, 1);
 	return 0;
-rollback:
+
 	/* Rollback what we did... */
-	mutex_lock(&base_ni->extent_lock);
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	if (!(base_ni->nr_extents & 3)) {
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode*);
+bitmap_rollback:
+	memalloc_flags = memalloc_nofs_save();
+	if (base_ni->mft_no != FILE_MFT)
+		down_write(&vol->mftbmp_lock);
+	if (ntfs_bitmap_set_bit(vol->mftbmp_ino, mft_no))
+		ntfs_error(vol->sb, "ntfs_bitmap_set_bit failed in bitmap_rollback\n");
+	if (base_ni->mft_no != FILE_MFT)
+		up_write(&vol->mftbmp_lock);
+	memalloc_nofs_restore(memalloc_flags);
+sync_rollback:
+	ntfs_error(vol->sb,
+		"Eeek! Rollback failed in %s. Leaving inconsistent metadata!\n", __func__);
+	ni_mrec->flags |= MFT_RECORD_IN_USE;
+	ni_mrec->sequence_number = old_seq_no;
+	NInoSetDirty(ni);
+	write_mft_record(ni, ni_mrec, 0);
+	unmap_mft_record(ni);
+	return err;
+}
 
-		extent_nis = kmalloc(new_size, GFP_NOFS);
-		if (unlikely(!extent_nis)) {
-			ntfs_error(vol->sb, "Failed to allocate internal "
-					"buffer during rollback.%s", es);
-			mutex_unlock(&base_ni->extent_lock);
-			NVolSetErrors(vol);
-			goto rollback_error;
-		}
-		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
-			memcpy(extent_nis, base_ni->ext.extent_ntfs_inos,
-					new_size - 4 * sizeof(ntfs_inode*));
-			kfree(base_ni->ext.extent_ntfs_inos);
-		}
-		base_ni->ext.extent_ntfs_inos = extent_nis;
+static s64 lcn_from_index(struct ntfs_volume *vol, struct ntfs_inode *ni,
+		unsigned long index)
+{
+	s64 vcn;
+	s64 lcn;
+
+	vcn = ntfs_pidx_to_cluster(vol, index);
+
+	down_read(&ni->runlist.lock);
+	lcn = ntfs_attr_vcn_to_lcn_nolock(ni, vcn, false);
+	up_read(&ni->runlist.lock);
+
+	return lcn;
+}
+
+/*
+ * ntfs_write_mft_block - Write back a folio containing MFT records
+ * @folio:	The folio to write back (contains one or more MFT records)
+ * @wbc:	Writeback control structure
+ *
+ * This function is called as part of the address_space_operations
+ * .writepages implementation for the $MFT inode (or $MFTMirr).
+ * It handles writing one folio (normally 4KiB page) worth of MFT records
+ * to the underlying block device.
+ *
+ * Return: 0 on success, or -errno on error.
+ */
+static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *wbc)
+{
+	struct address_space *mapping = folio->mapping;
+	struct inode *vi = mapping->host;
+	struct ntfs_inode *ni = NTFS_I(vi);
+	struct ntfs_volume *vol = ni->vol;
+	u8 *kaddr;
+	struct ntfs_inode *locked_nis[PAGE_SIZE / NTFS_BLOCK_SIZE];
+	int nr_locked_nis = 0, err = 0, mft_ofs, prev_mft_ofs;
+	struct inode *ref_inos[PAGE_SIZE / NTFS_BLOCK_SIZE];
+	int nr_ref_inos = 0;
+	struct bio *bio = NULL;
+	unsigned long mft_no;
+	struct ntfs_inode *tni;
+	s64 lcn;
+	s64 vcn = ntfs_pidx_to_cluster(vol, folio->index);
+	s64 end_vcn = ntfs_bytes_to_cluster(vol, ni->allocated_size);
+	unsigned int folio_sz;
+	struct runlist_element *rl;
+	loff_t i_size = i_size_read(vi);
+
+	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, folio index 0x%lx.",
+			vi->i_ino, ni->type, folio->index);
+
+	/* We have to zero every time due to mmap-at-end-of-file. */
+	if (folio->index >= (i_size >> folio_shift(folio)))
+		/* The page straddles i_size. */
+		folio_zero_segment(folio,
+				   offset_in_folio(folio, i_size),
+				   folio_size(folio));
+
+	lcn = lcn_from_index(vol, ni, folio->index);
+	if (lcn <= LCN_HOLE) {
+		folio_start_writeback(folio);
+		folio_unlock(folio);
+		folio_end_writeback(folio);
+		return -EIO;
+	}
+
+	/* Map folio so we can access its contents. */
+	kaddr = kmap_local_folio(folio, 0);
+	/* Clear the page uptodate flag whilst the mst fixups are applied. */
+	folio_clear_uptodate(folio);
+
+	for (mft_ofs = 0; mft_ofs < PAGE_SIZE && vcn < end_vcn;
+	     mft_ofs += vol->mft_record_size) {
+		/* Get the mft record number. */
+		mft_no = (((s64)folio->index << PAGE_SHIFT) + mft_ofs) >>
+			vol->mft_record_size_bits;
+		vcn = ntfs_mft_no_to_cluster(vol, mft_no);
+		/* Check whether to write this mft record. */
+		tni = NULL;
+		if (ntfs_may_write_mft_record(vol, mft_no,
+					(struct mft_record *)(kaddr + mft_ofs),
+					&tni, &ref_inos[nr_ref_inos])) {
+			unsigned int mft_record_off = 0;
+			s64 vcn_off = vcn;
+
+			/*
+			 * Skip $MFT extent mft records and let them being written
+			 * by writeback to avioid deadlocks. the $MFT runlist
+			 * lock must be taken before $MFT extent mrec_lock is taken.
+			 */
+			if (tni && tni->nr_extents < 0 &&
+				tni->ext.base_ntfs_ino == NTFS_I(vol->mft_ino)) {
+				mutex_unlock(&tni->mrec_lock);
+				atomic_dec(&tni->count);
+				iput(vol->mft_ino);
+				continue;
+			}
+
+			/*
+			 * The record should be written.  If a locked ntfs
+			 * inode was returned, add it to the array of locked
+			 * ntfs inodes.
+			 */
+			if (tni)
+				locked_nis[nr_locked_nis++] = tni;
+			else if (ref_inos[nr_ref_inos])
+				nr_ref_inos++;
+
+			if (bio && (mft_ofs != prev_mft_ofs + vol->mft_record_size)) {
+flush_bio:
+				bio->bi_end_io = ntfs_bio_end_io;
+				submit_bio(bio);
+				bio = NULL;
+			}
+
+			if (vol->cluster_size < folio_size(folio)) {
+				down_write(&ni->runlist.lock);
+				rl = ntfs_attr_vcn_to_rl(ni, vcn_off, &lcn);
+				up_write(&ni->runlist.lock);
+				if (IS_ERR(rl) || lcn < 0) {
+					err = -EIO;
+					goto unm_done;
+				}
+
+				if (bio &&
+				   (bio_end_sector(bio) >> (vol->cluster_size_bits - 9)) !=
+				    lcn) {
+					bio->bi_end_io = ntfs_bio_end_io;
+					submit_bio(bio);
+					bio = NULL;
+				}
+			}
+
+			if (!bio) {
+				unsigned int off;
+
+				off = ((mft_no << vol->mft_record_size_bits) +
+				       mft_record_off) & vol->cluster_size_mask;
+
+				bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE,
+						GFP_NOIO);
+				bio->bi_iter.bi_sector =
+					ntfs_bytes_to_sector(vol,
+							ntfs_cluster_to_bytes(vol, lcn) + off);
+			}
+
+			if (vol->cluster_size == NTFS_BLOCK_SIZE &&
+			    (mft_record_off ||
+			     rl->length - (vcn_off - rl->vcn) == 1 ||
+			     mft_ofs + NTFS_BLOCK_SIZE >= PAGE_SIZE))
+				folio_sz = NTFS_BLOCK_SIZE;
+			else
+				folio_sz = vol->mft_record_size;
+			if (!bio_add_folio(bio, folio, folio_sz,
+					   mft_ofs + mft_record_off)) {
+				err = -EIO;
+				bio_put(bio);
+				goto unm_done;
+			}
+			mft_record_off += folio_sz;
+
+			if (mft_record_off != vol->mft_record_size) {
+				vcn_off++;
+				goto flush_bio;
+			}
+			prev_mft_ofs = mft_ofs;
+
+			if (mft_no < vol->mftmirr_size)
+				ntfs_sync_mft_mirror(vol, mft_no,
+						(struct mft_record *)(kaddr + mft_ofs));
+		} else if (ref_inos[nr_ref_inos])
+			nr_ref_inos++;
 	}
-	m->flags |= MFT_RECORD_IN_USE;
-	m->sequence_number = old_seq_no;
-	extent_nis[base_ni->nr_extents++] = ni;
-	mutex_unlock(&base_ni->extent_lock);
-	mark_mft_record_dirty(ni);
+
+	if (bio) {
+		bio->bi_end_io = ntfs_bio_end_io;
+		submit_bio(bio);
+	}
+unm_done:
+	folio_mark_uptodate(folio);
+	kunmap_local(kaddr);
+
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+	folio_end_writeback(folio);
+
+	/* Unlock any locked inodes. */
+	while (nr_locked_nis-- > 0) {
+		struct ntfs_inode *base_tni;
+
+		tni = locked_nis[nr_locked_nis];
+		mutex_unlock(&tni->mrec_lock);
+
+		/* Get the base inode. */
+		mutex_lock(&tni->extent_lock);
+		if (tni->nr_extents >= 0)
+			base_tni = tni;
+		else
+			base_tni = tni->ext.base_ntfs_ino;
+		mutex_unlock(&tni->extent_lock);
+		ntfs_debug("Unlocking %s inode 0x%lx.",
+				tni == base_tni ? "base" : "extent",
+				tni->mft_no);
+		atomic_dec(&tni->count);
+		iput(VFS_I(base_tni));
+	}
+
+	/* Dropping deferred references */
+	while (nr_ref_inos-- > 0) {
+		if (ref_inos[nr_ref_inos])
+			iput(ref_inos[nr_ref_inos]);
+	}
+
+	if (unlikely(err && err != -ENOMEM))
+		NVolSetErrors(vol);
+	if (likely(!err))
+		ntfs_debug("Done.");
 	return err;
 }
-#endif /* NTFS_RW */
+
+/*
+ * ntfs_mft_writepages - Write back dirty folios for the $MFT inode
+ * @mapping:	address space of the $MFT inode
+ * @wbc:	writeback control
+ *
+ * Writeback iterator for MFT records. Iterates over dirty folios and
+ * delegates actual writing to ntfs_write_mft_block() for each folio.
+ * Called from the address_space_operations .writepages vector of the
+ * $MFT inode.
+ *
+ * Returns 0 on success, or the first error encountered.
+ */
+int ntfs_mft_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct folio *folio = NULL;
+	int error;
+
+	if (NVolShutdown(NTFS_I(mapping->host)->vol))
+		return -EIO;
+
+	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+		error = ntfs_write_mft_block(folio, wbc);
+	return error;
+}
+
+void ntfs_mft_mark_dirty(struct folio *folio)
+{
+	iomap_dirty_folio(folio->mapping, folio);
+}
diff --git a/fs/ntfs/mst.c b/fs/ntfs/mst.c
index 16b3c884abfc..7f9faad924ad 100644
--- a/fs/ntfs/mst.c
+++ b/fs/ntfs/mst.c
@@ -1,14 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * mst.c - NTFS multi sector transfer protection handling code. Part of the
- *	   Linux-NTFS project.
+ * NTFS multi sector transfer protection handling code.
  *
  * Copyright (c) 2001-2004 Anton Altaparmakov
  */
 
+#include <linux/ratelimit.h>
+
 #include "ntfs.h"
 
-/**
+/*
  * post_read_mst_fixup - deprotect multi sector transfer protected data
  * @b:		pointer to the data to deprotect
  * @size:	size in bytes of @b
@@ -25,7 +26,7 @@
  * be fixed up. Thus, we return success and not failure in this case. This is
  * in contrast to pre_write_mst_fixup(), see below.
  */
-int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
+int post_read_mst_fixup(struct ntfs_record *b, const u32 size)
 {
 	u16 usa_ofs, usa_count, usn;
 	u16 *usa_pos, *data_pos;
@@ -35,13 +36,12 @@ int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
 	/* Decrement usa_count to get number of fixups. */
 	usa_count = le16_to_cpu(b->usa_count) - 1;
 	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
+	if (size & (NTFS_BLOCK_SIZE - 1) || usa_ofs & 1	||
+	    usa_ofs + (usa_count * 2) > size ||
+	    (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
 		return 0;
 	/* Position of usn in update sequence array. */
-	usa_pos = (u16*)b + usa_ofs/sizeof(u16);
+	usa_pos = (u16 *)b + usa_ofs/sizeof(u16);
 	/*
 	 * The update sequence number which has to be equal to each of the
 	 * u16 values before they are fixed up. Note no need to care for
@@ -53,12 +53,18 @@ int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
 	/*
 	 * Position in protected data of first u16 that needs fixing up.
 	 */
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
+	data_pos = (u16 *)b + NTFS_BLOCK_SIZE / sizeof(u16) - 1;
 	/*
 	 * Check for incomplete multi sector transfer(s).
 	 */
 	while (usa_count--) {
 		if (*data_pos != usn) {
+			struct mft_record *m = (struct mft_record *)b;
+
+			pr_err_ratelimited("ntfs: Incomplete multi sector transfer detected! (Record magic : 0x%x, mft number : 0x%x, base mft number : 0x%lx, mft in use : %d, data : 0x%x, usn 0x%x)\n",
+					le32_to_cpu(m->magic), le32_to_cpu(m->mft_record_number),
+					MREF_LE(m->base_mft_record), m->flags & MFT_RECORD_IN_USE,
+					*data_pos, usn);
 			/*
 			 * Incomplete multi sector transfer detected! )-:
 			 * Set the magic to "BAAD" and return failure.
@@ -67,11 +73,11 @@ int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
 			b->magic = magic_BAAD;
 			return -EINVAL;
 		}
-		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
+		data_pos += NTFS_BLOCK_SIZE / sizeof(u16);
 	}
 	/* Re-setup the variables. */
 	usa_count = le16_to_cpu(b->usa_count) - 1;
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
+	data_pos = (u16 *)b + NTFS_BLOCK_SIZE / sizeof(u16) - 1;
 	/* Fixup all sectors. */
 	while (usa_count--) {
 		/*
@@ -85,7 +91,7 @@ int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
 	return 0;
 }
 
-/**
+/*
  * pre_write_mst_fixup - apply multi sector transfer protection
  * @b:		pointer to the data to protect
  * @size:	size in bytes of @b
@@ -106,28 +112,27 @@ int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
  * otherwise a random word will be used (whatever was in the record at that
  * position at that time).
  */
-int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
+int pre_write_mst_fixup(struct ntfs_record *b, const u32 size)
 {
-	le16 *usa_pos, *data_pos;
+	__le16 *usa_pos, *data_pos;
 	u16 usa_ofs, usa_count, usn;
-	le16 le_usn;
+	__le16 le_usn;
 
 	/* Sanity check + only fixup if it makes sense. */
 	if (!b || ntfs_is_baad_record(b->magic) ||
-			ntfs_is_hole_record(b->magic))
+	    ntfs_is_hole_record(b->magic))
 		return -EINVAL;
 	/* Setup the variables. */
 	usa_ofs = le16_to_cpu(b->usa_ofs);
 	/* Decrement usa_count to get number of fixups. */
 	usa_count = le16_to_cpu(b->usa_count) - 1;
 	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
+	if (size & (NTFS_BLOCK_SIZE - 1) || usa_ofs & 1	||
+	    usa_ofs + (usa_count * 2) > size ||
+	    (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
 		return -EINVAL;
 	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)((u8*)b + usa_ofs);
+	usa_pos = (__le16 *)((u8 *)b + usa_ofs);
 	/*
 	 * Cyclically increment the update sequence number
 	 * (skipping 0 and -1, i.e. 0xffff).
@@ -138,7 +143,7 @@ int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
 	le_usn = cpu_to_le16(usn);
 	*usa_pos = le_usn;
 	/* Position in data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
+	data_pos = (__le16 *)b + NTFS_BLOCK_SIZE/sizeof(__le16) - 1;
 	/* Fixup all sectors. */
 	while (usa_count--) {
 		/*
@@ -149,12 +154,12 @@ int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
 		/* Apply fixup to data. */
 		*data_pos = le_usn;
 		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
+		data_pos += NTFS_BLOCK_SIZE / sizeof(__le16);
 	}
 	return 0;
 }
 
-/**
+/*
  * post_write_mst_fixup - fast deprotect multi sector transfer protected data
  * @b:		pointer to the data to deprotect
  *
@@ -162,18 +167,18 @@ int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
  * for any errors, because we assume we have just used pre_write_mst_fixup(),
  * thus the data will be fine or we would never have gotten here.
  */
-void post_write_mst_fixup(NTFS_RECORD *b)
+void post_write_mst_fixup(struct ntfs_record *b)
 {
-	le16 *usa_pos, *data_pos;
+	__le16 *usa_pos, *data_pos;
 
 	u16 usa_ofs = le16_to_cpu(b->usa_ofs);
 	u16 usa_count = le16_to_cpu(b->usa_count) - 1;
 
 	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)b + usa_ofs/sizeof(le16);
+	usa_pos = (__le16 *)b + usa_ofs/sizeof(__le16);
 
 	/* Position in protected data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
+	data_pos = (__le16 *)b + NTFS_BLOCK_SIZE/sizeof(__le16) - 1;
 
 	/* Fixup all sectors. */
 	while (usa_count--) {
@@ -184,6 +189,6 @@ void post_write_mst_fixup(NTFS_RECORD *b)
 		*data_pos = *(++usa_pos);
 
 		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
+		data_pos += NTFS_BLOCK_SIZE/sizeof(__le16);
 	}
 }
-- 
2.25.1

Powered by blists - more mailing lists