Merge tag 'ntfs3_for_6.0' of https://github.com/Paragon-Software-Group/linux-ntfs3

Pull ntfs3 updates from Konstantin Komarov:

 - implement FALLOC_FL_INSERT_RANGE

 - fix some logic errors

 - fixed xfstests (tested on x86_64): generic/064 generic/213
   generic/300 generic/361 generic/449 generic/485

 - some dead code removed or refactored

* tag 'ntfs3_for_6.0' of https://github.com/Paragon-Software-Group/linux-ntfs3: (39 commits)
  fs/ntfs3: uninitialized variable in ntfs_set_acl_ex()
  fs/ntfs3: Remove unused function wnd_bits
  fs/ntfs3: Make ni_ins_new_attr return error
  fs/ntfs3: Create MFT zone only if length is large enough
  fs/ntfs3: Refactoring attr_insert_range to restore after errors
  fs/ntfs3: Refactoring attr_punch_hole to restore after errors
  fs/ntfs3: Refactoring attr_set_size to restore after errors
  fs/ntfs3: New function ntfs_bad_inode
  fs/ntfs3: Make MFT zone less fragmented
  fs/ntfs3: Check possible errors in run_pack in advance
  fs/ntfs3: Added comments to frecord functions
  fs/ntfs3: Fill duplicate info in ni_add_name
  fs/ntfs3: Make static function attr_load_runs
  fs/ntfs3: Add new argument is_mft to ntfs_mark_rec_free
  fs/ntfs3: Remove unused mi_mark_free
  fs/ntfs3: Fix very fragmented case in attr_punch_hole
  fs/ntfs3: Fix work with fragmented xattr
  fs/ntfs3: Make ntfs_fallocate return -ENOSPC instead of -EFBIG
  fs/ntfs3: extend ni_insert_nonresident to return inserted ATTR_LIST_ENTRY
  fs/ntfs3: Check reserved size for maximum allowed
  ...

fs/ntfs3/bitmap.c

@@ -51,11 +51,6 @@ void ntfs3_exit_bitmap(void)
 	kmem_cache_destroy(ntfs_enode_cachep);
 }
 
-static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i)
-{
-	return i + 1 == wnd->nwnd ? wnd->bits_last : wnd->sb->s_blocksize * 8;
-}
-
 /*
  * wnd_scan
  *
@@ -1333,9 +1328,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		if (!new_free)
 			return -ENOMEM;
 
-		if (new_free != wnd->free_bits)
-			memcpy(new_free, wnd->free_bits,
-			       wnd->nwnd * sizeof(short));
+		memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
 		memset(new_free + wnd->nwnd, 0,
 		       (new_wnd - wnd->nwnd) * sizeof(short));
 		kfree(wnd->free_bits);
@@ -1395,9 +1388,8 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 
 void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len)
 {
-	size_t zlen;
+	size_t zlen = wnd->zone_end - wnd->zone_bit;
 
-	zlen = wnd->zone_end - wnd->zone_bit;
 	if (zlen)
 		wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false);
 

fs/ntfs3/file.c

@@ -530,21 +530,35 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size)
 static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 {
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct super_block *sb = inode->i_sb;
 	struct ntfs_sb_info *sbi = sb->s_fs_info;
 	struct ntfs_inode *ni = ntfs_i(inode);
 	loff_t end = vbo + len;
 	loff_t vbo_down = round_down(vbo, PAGE_SIZE);
-	loff_t i_size;
+	bool is_supported_holes = is_sparsed(ni) || is_compressed(ni);
+	loff_t i_size, new_size;
+	bool map_locked;
 	int err;
 
 	/* No support for dir. */
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	/* Return error if mode is not supported. */
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
-		     FALLOC_FL_COLLAPSE_RANGE)) {
+	/*
+	 * vfs_fallocate checks all possible combinations of mode.
+	 * Do additional checks here before ntfs_set_state(dirty).
+	 */
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		if (!is_supported_holes)
+			return -EOPNOTSUPP;
+	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+	} else if (mode & FALLOC_FL_INSERT_RANGE) {
+		if (!is_supported_holes)
+			return -EOPNOTSUPP;
+	} else if (mode &
+		   ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)) {
 		ntfs_inode_warn(inode, "fallocate(0x%x) is not supported",
 				mode);
 		return -EOPNOTSUPP;
@@ -554,6 +568,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 
 	inode_lock(inode);
 	i_size = inode->i_size;
+	new_size = max(end, i_size);
+	map_locked = false;
 
 	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
 		/* Should never be here, see ntfs_file_open. */
@@ -561,38 +577,27 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		goto out;
 	}
 
+	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
+		    FALLOC_FL_INSERT_RANGE)) {
+		inode_dio_wait(inode);
+		filemap_invalidate_lock(mapping);
+		map_locked = true;
+	}
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		u32 frame_size;
 		loff_t mask, vbo_a, end_a, tmp;
 
-		if (!(mode & FALLOC_FL_KEEP_SIZE)) {
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = filemap_write_and_wait_range(inode->i_mapping, vbo,
-						   end - 1);
+		err = filemap_write_and_wait_range(mapping, vbo, end - 1);
 		if (err)
 			goto out;
 
-		err = filemap_write_and_wait_range(inode->i_mapping, end,
-						   LLONG_MAX);
+		err = filemap_write_and_wait_range(mapping, end, LLONG_MAX);
 		if (err)
 			goto out;
 
-		inode_dio_wait(inode);
-
 		truncate_pagecache(inode, vbo_down);
 
-		if (!is_sparsed(ni) && !is_compressed(ni)) {
-			/*
-			 * Normal file, can't make hole.
-			 * TODO: Try to find way to save info about hole.
-			 */
-			err = -EOPNOTSUPP;
-			goto out;
-		}
-
 		ni_lock(ni);
 		err = attr_punch_hole(ni, vbo, len, &frame_size);
 		ni_unlock(ni);
@@ -624,17 +629,11 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			ni_unlock(ni);
 		}
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		if (mode & ~FALLOC_FL_COLLAPSE_RANGE) {
-			err = -EINVAL;
-			goto out;
-		}
-
 		/*
 		 * Write tail of the last page before removed range since
 		 * it will get removed from the page cache below.
 		 */
-		err = filemap_write_and_wait_range(inode->i_mapping, vbo_down,
-						   vbo);
+		err = filemap_write_and_wait_range(mapping, vbo_down, vbo);
 		if (err)
 			goto out;
 
@@ -642,34 +641,58 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		 * Write data that will be shifted to preserve them
 		 * when discarding page cache below.
 		 */
-		err = filemap_write_and_wait_range(inode->i_mapping, end,
-						   LLONG_MAX);
+		err = filemap_write_and_wait_range(mapping, end, LLONG_MAX);
 		if (err)
 			goto out;
 
-		/* Wait for existing dio to complete. */
-		inode_dio_wait(inode);
-
 		truncate_pagecache(inode, vbo_down);
 
 		ni_lock(ni);
 		err = attr_collapse_range(ni, vbo, len);
 		ni_unlock(ni);
+	} else if (mode & FALLOC_FL_INSERT_RANGE) {
+		/* Check new size. */
+		err = inode_newsize_ok(inode, new_size);
+		if (err)
+			goto out;
+
+		/* Write out all dirty pages. */
+		err = filemap_write_and_wait_range(mapping, vbo_down,
+						   LLONG_MAX);
+		if (err)
+			goto out;
+		truncate_pagecache(inode, vbo_down);
+
+		ni_lock(ni);
+		err = attr_insert_range(ni, vbo, len);
+		ni_unlock(ni);
 	} else {
-		/*
-		 * Normal file: Allocate clusters, do not change 'valid' size.
-		 */
-		loff_t new_size = max(end, i_size);
+		/* Check new size. */
+
+		/* generic/213: expected -ENOSPC instead of -EFBIG. */
+		if (!is_supported_holes) {
+			loff_t to_alloc = new_size - inode_get_bytes(inode);
+
+			if (to_alloc > 0 &&
+			    (to_alloc >> sbi->cluster_bits) >
+				    wnd_zeroes(&sbi->used.bitmap)) {
+				err = -ENOSPC;
+				goto out;
+			}
+		}
 
 		err = inode_newsize_ok(inode, new_size);
 		if (err)
 			goto out;
 
+		/*
+		 * Allocate clusters, do not change 'valid' size.
+		 */
 		err = ntfs_set_size(inode, new_size);
 		if (err)
 			goto out;
 
-		if (is_sparsed(ni) || is_compressed(ni)) {
+		if (is_supported_holes) {
 			CLST vcn_v = ni->i_valid >> sbi->cluster_bits;
 			CLST vcn = vbo >> sbi->cluster_bits;
 			CLST cend = bytes_to_cluster(sbi, end);
@@ -717,8 +740,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 	}
 
 out:
-	if (err == -EFBIG)
-		err = -ENOSPC;
+	if (map_locked)
+		filemap_invalidate_unlock(mapping);
 
 	if (!err) {
 		inode->i_ctime = inode->i_mtime = current_time(inode);
@@ -989,7 +1012,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		if (bytes > count)
 			bytes = count;
 
-		frame = pos >> frame_bits;
 		frame_vbo = pos & ~(frame_size - 1);
 		index = frame_vbo >> PAGE_SHIFT;
 

fs/ntfs3/fslog.c

@@ -3843,6 +3843,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 
 	memset(&rst_info2, 0, sizeof(struct restart_info));
 	err = log_read_rst(log, l_size, false, &rst_info2);
+	if (err)
+		goto out;
 
 	/* Determine which restart area to use. */
 	if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
@@ -5057,7 +5059,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 		goto add_allocated_vcns;
 
 	vcn = le64_to_cpu(lrh->target_vcn);
-	vcn &= ~(log->clst_per_page - 1);
+	vcn &= ~(u64)(log->clst_per_page - 1);
 
 add_allocated_vcns:
 	for (i = 0, vcn = le64_to_cpu(lrh->target_vcn),

fs/ntfs3/fsntfs.c

@@ -703,11 +703,13 @@ int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft,
 
 /*
  * ntfs_mark_rec_free - Mark record as free.
+ * is_mft - true if we are changing MFT
  */
-void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno)
+void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft)
 {
 	struct wnd_bitmap *wnd = &sbi->mft.bitmap;
 
+	if (!is_mft)
 		down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT);
 	if (rno >= wnd->nbits)
 		goto out;
@@ -727,6 +729,7 @@ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno)
 		sbi->mft.next_free = rno;
 
 out:
+	if (!is_mft)
 		up_write(&wnd->rw_lock);
 }
 
@@ -780,7 +783,7 @@ int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to)
  */
 int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 {
-	CLST zone_limit, zone_max, lcn, vcn, len;
+	CLST lcn, vcn, len;
 	size_t lcn_s, zlen;
 	struct wnd_bitmap *wnd = &sbi->used.bitmap;
 	struct ntfs_inode *ni = sbi->mft.ni;
@@ -789,16 +792,6 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 	if (wnd_zone_len(wnd))
 		return 0;
 
-	/*
-	 * Compute the MFT zone at two steps.
-	 * It would be nice if we are able to allocate 1/8 of
-	 * total clusters for MFT but not more then 512 MB.
-	 */
-	zone_limit = (512 * 1024 * 1024) >> sbi->cluster_bits;
-	zone_max = wnd->nbits >> 3;
-	if (zone_max > zone_limit)
-		zone_max = zone_limit;
-
 	vcn = bytes_to_cluster(sbi,
 			       (u64)sbi->mft.bitmap.nbits << sbi->record_bits);
 
@@ -812,13 +805,7 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 	lcn_s = lcn + 1;
 
 	/* Try to allocate clusters after last MFT run. */
-	zlen = wnd_find(wnd, zone_max, lcn_s, 0, &lcn_s);
-	if (!zlen) {
-		ntfs_notice(sbi->sb, "MftZone: unavailable");
-		return 0;
-	}
-
-	/* Truncate too large zone. */
+	zlen = wnd_find(wnd, sbi->zone_max, lcn_s, 0, &lcn_s);
 	wnd_zone_set(wnd, lcn_s, zlen);
 
 	return 0;
@@ -827,16 +814,21 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 /*
  * ntfs_update_mftmirr - Update $MFTMirr data.
  */
-int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
+void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 {
 	int err;
 	struct super_block *sb = sbi->sb;
-	u32 blocksize = sb->s_blocksize;
+	u32 blocksize;
 	sector_t block1, block2;
 	u32 bytes;
 
+	if (!sb)
+		return;
+
+	blocksize = sb->s_blocksize;
+
 	if (!(sbi->flags & NTFS_FLAGS_MFTMIRR))
-		return 0;
+		return;
 
 	err = 0;
 	bytes = sbi->mft.recs_mirr << sbi->record_bits;
@@ -847,16 +839,13 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 		struct buffer_head *bh1, *bh2;
 
 		bh1 = sb_bread(sb, block1++);
-		if (!bh1) {
-			err = -EIO;
-			goto out;
-		}
+		if (!bh1)
+			return;
 
 		bh2 = sb_getblk(sb, block2++);
 		if (!bh2) {
 			put_bh(bh1);
-			err = -EIO;
-			goto out;
+			return;
 		}
 
 		if (buffer_locked(bh2))
@@ -876,13 +865,24 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 
 		put_bh(bh2);
 		if (err)
-			goto out;
+			return;
 	}
 
 	sbi->flags &= ~NTFS_FLAGS_MFTMIRR;
+}
 
-out:
-	return err;
+/*
+ * ntfs_bad_inode
+ *
+ * Marks inode as bad and marks fs as 'dirty'
+ */
+void ntfs_bad_inode(struct inode *inode, const char *hint)
+{
+	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+
+	ntfs_inode_err(inode, "%s", hint);
+	make_bad_inode(inode);
+	ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
 }
 
 /*
@@ -1395,7 +1395,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
 		if (buffer_locked(bh))
 			__wait_on_buffer(bh);
 
-		lock_buffer(nb->bh[idx]);
+		lock_buffer(bh);
 
 		bh_data = bh->b_data + off;
 		end_data = Add2Ptr(bh_data, op);
@@ -2424,7 +2424,7 @@ static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn,
 
 void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
 {
-	CLST end, i;
+	CLST end, i, zone_len, zlen;
 	struct wnd_bitmap *wnd = &sbi->used.bitmap;
 
 	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
@@ -2459,6 +2459,28 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
 		ntfs_unmap_and_discard(sbi, lcn, len);
 	wnd_set_free(wnd, lcn, len);
 
+	/* append to MFT zone, if possible. */
+	zone_len = wnd_zone_len(wnd);
+	zlen = min(zone_len + len, sbi->zone_max);
+
+	if (zlen == zone_len) {
+		/* MFT zone already has maximum size. */
+	} else if (!zone_len) {
+		/* Create MFT zone only if 'zlen' is large enough. */
+		if (zlen == sbi->zone_max)
+			wnd_zone_set(wnd, lcn, zlen);
+	} else {
+		CLST zone_lcn = wnd_zone_bit(wnd);
+
+		if (lcn + len == zone_lcn) {
+			/* Append into head MFT zone. */
+			wnd_zone_set(wnd, lcn, zlen);
+		} else if (zone_lcn + zone_len == lcn) {
+			/* Append into tail MFT zone. */
+			wnd_zone_set(wnd, zone_lcn, zlen);
+		}
+	}
+
 out:
 	up_write(&wnd->rw_lock);
 }

fs/ntfs3/index.c

@@ -1042,19 +1042,16 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni,
 {
 	int err;
 	struct NTFS_DE *e;
-	const struct INDEX_HDR *hdr;
 	struct indx_node *node;
 
 	if (!root)
 		root = indx_get_root(&ni->dir, ni, NULL, NULL);
 
 	if (!root) {
-		err = -EINVAL;
-		goto out;
+		/* Should not happen. */
+		return -EINVAL;
 	}
 
-	hdr = &root->ihdr;
-
 	/* Check cache. */
 	e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de;
 	if (e && !de_is_last(e) &&
@@ -1068,39 +1065,35 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni,
 	fnd_clear(fnd);
 
 	/* Lookup entry that is <= to the search value. */
-	e = hdr_find_e(indx, hdr, key, key_len, ctx, diff);
+	e = hdr_find_e(indx, &root->ihdr, key, key_len, ctx, diff);
 	if (!e)
 		return -EINVAL;
 
 	fnd->root_de = e;
-	err = 0;
 
 	for (;;) {
 		node = NULL;
-		if (*diff >= 0 || !de_has_vcn_ex(e)) {
-			*entry = e;
-			goto out;
-		}
+		if (*diff >= 0 || !de_has_vcn_ex(e))
+			break;
 
 		/* Read next level. */
 		err = indx_read(indx, ni, de_get_vbn(e), &node);
 		if (err)
-			goto out;
+			return err;
 
 		/* Lookup entry that is <= to the search value. */
 		e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx,
 			       diff);
 		if (!e) {
-			err = -EINVAL;
 			put_indx_node(node);
-			goto out;
+			return -EINVAL;
 		}
 
 		fnd_push(fnd, node, e);
 	}
 
-out:
-	return err;
+	*entry = e;
+	return 0;
 }
 
 int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni,
@@ -1354,7 +1347,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 		goto out;
 
 	err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len,
-				    &run, 0, len, 0, &alloc, NULL);
+				    &run, 0, len, 0, &alloc, NULL, NULL);
 	if (err)
 		goto out1;
 
@@ -1685,8 +1678,8 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni,
 {
 	int err;
 	const struct NTFS_DE *sp;
-	struct NTFS_DE *e, *de_t, *up_e = NULL;
-	struct indx_node *n2 = NULL;
+	struct NTFS_DE *e, *de_t, *up_e;
+	struct indx_node *n2;
 	struct indx_node *n1 = fnd->nodes[level];
 	struct INDEX_HDR *hdr1 = &n1->index->ihdr;
 	struct INDEX_HDR *hdr2;
@@ -1994,7 +1987,7 @@ static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni,
 			      const struct NTFS_DE *e, bool trim)
 {
 	int err;
-	struct indx_node *n;
+	struct indx_node *n = NULL;
 	struct INDEX_HDR *hdr;
 	CLST vbn = de_get_vbn(e);
 	size_t i;

fs/ntfs3/inode.c

@@ -430,6 +430,7 @@ static struct inode *ntfs_read_mft(struct inode *inode,
 	} else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) &&
 		   fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) {
 		/* Records in $Extend are not a files or general directories. */
+		inode->i_op = &ntfs_file_inode_operations;
 	} else {
 		err = -EINVAL;
 		goto out;
@@ -500,7 +501,7 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref,
 		inode = ntfs_read_mft(inode, name, ref);
 	else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) {
 		/* Inode overlaps? */
-		make_bad_inode(inode);
+		_ntfs_bad_inode(inode);
 	}
 
 	return inode;
@@ -1632,7 +1633,7 @@ struct inode *ntfs_create_inode(struct user_namespace *mnt_userns,
 	ni->mi.dirty = false;
 	discard_new_inode(inode);
 out3:
-	ntfs_mark_rec_free(sbi, ino);
+	ntfs_mark_rec_free(sbi, ino, false);
 
 out2:
 	__putname(new_de);
@@ -1655,7 +1656,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(inode);
 	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
 	struct NTFS_DE *de;
-	struct ATTR_FILE_NAME *de_name;
 
 	/* Allocate PATH_MAX bytes. */
 	de = __getname();
@@ -1670,15 +1670,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry)
 	if (err)
 		goto out;
 
-	de_name = (struct ATTR_FILE_NAME *)(de + 1);
-	/* Fill duplicate info. */
-	de_name->dup.cr_time = de_name->dup.m_time = de_name->dup.c_time =
-		de_name->dup.a_time = kernel2nt(&inode->i_ctime);
-	de_name->dup.alloc_size = de_name->dup.data_size =
-		cpu_to_le64(inode->i_size);
-	de_name->dup.fa = ni->std_fa;
-	de_name->dup.ea_size = de_name->dup.reparse = 0;
-
 	err = ni_add_name(ntfs_i(d_inode(dentry->d_parent)), ni, de);
 out:
 	__putname(de);
@@ -1731,9 +1722,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry)
 		if (inode->i_nlink)
 			mark_inode_dirty(inode);
 	} else if (!ni_remove_name_undo(dir_ni, ni, de, de2, undo_remove)) {
-		make_bad_inode(inode);
-		ntfs_inode_err(inode, "failed to undo unlink");
-		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(inode);
 	} else {
 		if (ni_is_dirty(dir))
 			mark_inode_dirty(dir);

fs/ntfs3/namei.c

@@ -208,7 +208,7 @@ static int ntfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 }
 
 /*
- * ntfs_rmdir - inode_operations::rm_dir
+ * ntfs_rmdir - inode_operations::rmdir
  */
 static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -308,9 +308,7 @@ static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *dir,
 	err = ni_rename(dir_ni, new_dir_ni, ni, de, new_de, &is_bad);
 	if (is_bad) {
 		/* Restore after failed rename failed too. */
-		make_bad_inode(inode);
-		ntfs_inode_err(inode, "failed to undo rename");
-		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(inode);
 	} else if (!err) {
 		inode->i_ctime = dir->i_ctime = dir->i_mtime =
 			current_time(dir);

fs/ntfs3/ntfs_fs.h

@@ -220,6 +220,7 @@ struct ntfs_sb_info {
 
 	u32 flags; // See NTFS_FLAGS_XXX.
 
+	CLST zone_max; // Maximum MFT zone length in clusters
 	CLST bad_clusters; // The count of marked bad clusters.
 
 	u16 max_bytes_per_attr; // Maximum attribute size in record.
@@ -408,8 +409,6 @@ enum REPARSE_SIGN {
 };
 
 /* Functions from attrib.c */
-int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
-		   struct runs_tree *run, const CLST *vcn);
 int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 			   CLST vcn, CLST lcn, CLST len, CLST *pre_alloc,
 			   enum ALLOCATE_OPT opt, CLST *alen, const size_t fr,
@@ -440,6 +439,7 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			u64 new_valid);
 int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes);
+int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes);
 int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size);
 
 /* Functions from attrlist.c */
@@ -528,7 +528,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			  const __le16 *name, u8 name_len,
 			  const struct runs_tree *run, CLST svcn, CLST len,
 			  __le16 flags, struct ATTRIB **new_attr,
-			  struct mft_inode **mi);
+			  struct mft_inode **mi, struct ATTR_LIST_ENTRY **le);
 int ni_insert_resident(struct ntfs_inode *ni, u32 data_size,
 		       enum ATTR_TYPE type, const __le16 *name, u8 name_len,
 		       struct ATTRIB **new_attr, struct mft_inode **mi,
@@ -589,10 +589,12 @@ int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len,
 			     enum ALLOCATE_OPT opt);
 int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft,
 		       struct ntfs_inode *ni, struct mft_inode **mi);
-void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno);
+void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft);
 int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to);
 int ntfs_refresh_zone(struct ntfs_sb_info *sbi);
-int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait);
+void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait);
+void ntfs_bad_inode(struct inode *inode, const char *hint);
+#define _ntfs_bad_inode(i) ntfs_bad_inode(i, __func__)
 enum NTFS_DIRTY_FLAGS {
 	NTFS_DIRTY_CLEAR = 0,
 	NTFS_DIRTY_DIRTY = 1,
@@ -738,7 +740,6 @@ static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec,
 int mi_write(struct mft_inode *mi, int wait);
 int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
 		  __le16 flags, bool is_mft);
-void mi_mark_free(struct mft_inode *mi);
 struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 			      const __le16 *name, u8 name_len, u32 asize,
 			      u16 name_off);
@@ -780,10 +781,10 @@ bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn,
 void run_truncate(struct runs_tree *run, CLST vcn);
 void run_truncate_head(struct runs_tree *run, CLST vcn);
 void run_truncate_around(struct runs_tree *run, CLST vcn);
-bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *Index);
 bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len,
 		   bool is_mft);
 bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len);
+bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len);
 bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn,
 		   CLST *lcn, CLST *len);
 bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn);
@@ -802,6 +803,7 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 #define run_unpack_ex run_unpack
 #endif
 int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn);
+int run_clone(const struct runs_tree *run, struct runs_tree *new_run);
 
 /* Globals from super.c */
 void *ntfs_set_shared(void *ptr, u32 bytes);

fs/ntfs3/record.c

@@ -394,28 +394,6 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
 	return err;
 }
 
-/*
- * mi_mark_free - Mark record as unused and marks it as free in bitmap.
- */
-void mi_mark_free(struct mft_inode *mi)
-{
-	CLST rno = mi->rno;
-	struct ntfs_sb_info *sbi = mi->sbi;
-
-	if (rno >= MFT_REC_RESERVED && rno < MFT_REC_FREE) {
-		ntfs_clear_mft_tail(sbi, rno, rno + 1);
-		mi->dirty = false;
-		return;
-	}
-
-	if (mi->mrec) {
-		clear_rec_inuse(mi->mrec);
-		mi->dirty = true;
-		mi_write(mi, 0);
-	}
-	ntfs_mark_rec_free(sbi, rno);
-}
-
 /*
  * mi_insert_attr - Reserve space for new attribute.
  *
@@ -445,12 +423,11 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 	attr = NULL;
 	while ((attr = mi_enum_attr(mi, attr))) {
 		diff = compare_attr(attr, type, name, name_len, upcase);
-		if (diff > 0)
-			break;
+
 		if (diff < 0)
 			continue;
 
-		if (!is_attr_indexed(attr))
+		if (!diff && !is_attr_indexed(attr))
 			return NULL;
 		break;
 	}

fs/ntfs3/run.c

@@ -31,7 +31,7 @@ struct ntfs_run {
  * Case of entry missing from list 'index' will be set to
  * point to insertion position for the entry question.
  */
-bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index)
+static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index)
 {
 	size_t min_idx, max_idx, mid_idx;
 	struct ntfs_run *r;
@@ -547,6 +547,48 @@ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len)
 	return true;
 }
 
+/* run_insert_range
+ *
+ * Helper for attr_insert_range(),
+ * which is helper for fallocate(insert_range).
+ */
+bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len)
+{
+	size_t index;
+	struct ntfs_run *r, *e;
+
+	if (WARN_ON(!run_lookup(run, vcn, &index)))
+		return false; /* Should never be here. */
+
+	e = run->runs + run->count;
+	r = run->runs + index;
+
+	if (vcn > r->vcn)
+		r += 1;
+
+	for (; r < e; r++)
+		r->vcn += len;
+
+	r = run->runs + index;
+
+	if (vcn > r->vcn) {
+		/* split fragment. */
+		CLST len1 = vcn - r->vcn;
+		CLST len2 = r->len - len1;
+		CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1);
+
+		r->len = len1;
+
+		if (!run_add_entry(run, vcn + len, lcn2, len2, false))
+			return false;
+	}
+
+	if (!run_add_entry(run, vcn, SPARSE_LCN, len, false))
+		return false;
+
+	return true;
+}
+
 /*
  * run_get_entry - Return index-th mapped region.
  */
@@ -778,26 +820,36 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf,
 	CLST next_vcn, vcn, lcn;
 	CLST prev_lcn = 0;
 	CLST evcn1 = svcn + len;
+	const struct ntfs_run *r, *r_end;
 	int packed_size = 0;
 	size_t i;
-	bool ok;
 	s64 dlcn;
 	int offset_size, size_size, tmp;
 
-	next_vcn = vcn = svcn;
-
 	*packed_vcns = 0;
 
 	if (!len)
 		goto out;
 
-	ok = run_lookup_entry(run, vcn, &lcn, &len, &i);
+	/* Check all required entries [svcn, encv1) available. */
+	if (!run_lookup(run, svcn, &i))
+		return -ENOENT;
 
-	if (!ok)
-		goto error;
+	r_end = run->runs + run->count;
+	r = run->runs + i;
 
-	if (next_vcn != vcn)
-		goto error;
+	for (next_vcn = r->vcn + r->len; next_vcn < evcn1;
+	     next_vcn = r->vcn + r->len) {
+		if (++r >= r_end || r->vcn != next_vcn)
+			return -ENOENT;
+	}
+
+	/* Repeat cycle above and pack runs. Assume no errors. */
+	r = run->runs + i;
+	len = svcn - r->vcn;
+	vcn = svcn;
+	lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len);
+	len = r->len - len;
 
 	for (;;) {
 		next_vcn = vcn + len;
@@ -846,12 +898,10 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf,
 		if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1)
 			goto out;
 
-		ok = run_get_entry(run, ++i, &vcn, &lcn, &len);
-		if (!ok)
-			goto error;
-
-		if (next_vcn != vcn)
-			goto error;
+		r += 1;
+		vcn = r->vcn;
+		lcn = r->lcn;
+		len = r->len;
 	}
 
 out:
@@ -860,9 +910,6 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf,
 		run_buf[0] = 0;
 
 	return packed_size + 1;
-
-error:
-	return -EOPNOTSUPP;
 }
 
 /*
@@ -1109,3 +1156,28 @@ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn)
 	*highest_vcn = vcn64 - 1;
 	return 0;
 }
+
+/*
+ * run_clone
+ *
+ * Make a copy of run
+ */
+int run_clone(const struct runs_tree *run, struct runs_tree *new_run)
+{
+	size_t bytes = run->count * sizeof(struct ntfs_run);
+
+	if (bytes > new_run->allocated) {
+		struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL);
+
+		if (!new_ptr)
+			return -ENOMEM;
+
+		kvfree(new_run->runs);
+		new_run->runs = new_ptr;
+		new_run->allocated = bytes;
+	}
+
+	memcpy(new_run->runs, run->runs, bytes);
+	new_run->count = run->count;
+	return 0;
+}

fs/ntfs3/super.c

@@ -30,6 +30,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/log2.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/nls.h>
 #include <linux/seq_file.h>
@@ -390,7 +391,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc)
 		return -EINVAL;
 	}
 
-	memcpy(sbi->options, new_opts, sizeof(*new_opts));
+	swap(sbi->options, fc->fs_private);
 
 	return 0;
 }
@@ -870,6 +871,13 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 	sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits;
 #endif
 
+	/*
+	 * Compute the MFT zone at two steps.
+	 * It would be nice if we are able to allocate 1/8 of
+	 * total clusters for MFT but not more then 512 MB.
+	 */
+	sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3);
+
 	err = 0;
 
 out:
@@ -900,6 +908,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	ref.high = 0;
 
 	sbi->sb = sb;
+	sbi->options = fc->fs_private;
+	fc->fs_private = NULL;
 	sb->s_flags |= SB_NODIRATIME;
 	sb->s_magic = 0x7366746e; // "ntfs"
 	sb->s_op = &ntfs_sops;
@@ -1262,8 +1272,6 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto put_inode_out;
 	}
 
-	fc->fs_private = NULL;
-
 	return 0;
 
 put_inode_out:
@@ -1378,7 +1386,7 @@ static const struct fs_context_operations ntfs_context_ops = {
 /*
  * ntfs_init_fs_context - Initialize spi and opts
  *
- * This will called when mount/remount. We will first initiliaze
+ * This will called when mount/remount. We will first initialize
  * options so that if remount we can use just that.
  */
 static int ntfs_init_fs_context(struct fs_context *fc)
@@ -1416,7 +1424,6 @@ static int ntfs_init_fs_context(struct fs_context *fc)
 	mutex_init(&sbi->compress.mtx_lzx);
 #endif
 
-	sbi->options = opts;
 	fc->s_fs_info = sbi;
 ok:
 	fc->fs_private = opts;

fs/ntfs3/xattr.c

@@ -118,7 +118,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea,
 
 		run_init(&run);
 
-		err = attr_load_runs(attr_ea, ni, &run, NULL);
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size);
 		if (!err)
 			err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL);
 		run_close(&run);
@@ -444,6 +444,11 @@ static noinline int ntfs_set_ea(struct inode *inode, const char *name,
 		/* Delete xattr, ATTR_EA */
 		ni_remove_attr_le(ni, attr, mi, le);
 	} else if (attr->non_res) {
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &ea_run, 0,
+					   size);
+		if (err)
+			goto out;
+
 		err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size, 0);
 		if (err)
 			goto out;
@@ -547,28 +552,23 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 {
 	const char *name;
 	size_t size, name_len;
-	void *value = NULL;
-	int err = 0;
+	void *value;
+	int err;
 	int flags;
+	umode_t mode;
 
 	if (S_ISLNK(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	mode = inode->i_mode;
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		/* Do not change i_mode if we are in init_acl */
 		if (acl && !init_acl) {
-			umode_t mode;
-
 			err = posix_acl_update_mode(mnt_userns, inode, &mode,
 						    &acl);
 			if (err)
-				goto out;
-
-			if (inode->i_mode != mode) {
-				inode->i_mode = mode;
-				mark_inode_dirty(inode);
-			}
+				return err;
 		}
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1;
@@ -604,8 +604,13 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 	err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0);
 	if (err == -ENODATA && !size)
 		err = 0; /* Removing non existed xattr. */
-	if (!err)
+	if (!err) {
 		set_cached_acl(inode, type, acl);
+		if (inode->i_mode != mode) {
+			inode->i_mode = mode;
+			mark_inode_dirty(inode);
+		}
+	}
 
 out:
 	kfree(value);
@@ -706,13 +711,13 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		inode->i_default_acl = NULL;
 	}
 
-	if (!acl)
-		inode->i_acl = NULL;
-	else {
+	if (acl) {
 		if (!err)
 			err = ntfs_set_acl_ex(mnt_userns, inode, acl,
 					      ACL_TYPE_ACCESS, true);
 		posix_acl_release(acl);
+	} else {
+		inode->i_acl = NULL;
 	}
 
 	return err;