linux-ntfs-dev — Development discussions and bug reports.

[Linux-NTFS-Dev] [PATCH] Restyle comments to better align with kernel-doc

[Kari A. <kar...@gm...>]

Capitalize comments and end with period for better reading.

Also function comments are now little more kernel-doc style. This way we
can easily convert them to kernel-doc style if we want. Note that these
are not yet complete with this style. Example function comments start
with /* and in kernel-doc style they start /**.

Use imperative mood in function descriptions.

Change words like ntfs -> NTFS, linux -> Linux.

Use "we" not "I" when commenting code.

Signed-off-by: Kari Argillander <kar...@gm...>
---
Yes I know that this patch is quite monster. That's why I try to send this
now before patch series get merged. After that this patch probebly needs to
be splitted more and sended in patch series.

If someone thinks this should not be added now it is ok. I have try to read
what is kernel philosophy in case "patch to patch" but haven't found any
good information about it. It is no big deal to add later. In my own mind I
do not want to touch so much comments after code is in.

I also don't know how easy this kind of patch is apply top of the patch
series.
---
 fs/ntfs3/attrib.c   | 232 +++++++-------
 fs/ntfs3/attrlist.c |  64 ++--
 fs/ntfs3/bitfunc.c  |   7 +-
 fs/ntfs3/bitmap.c   | 203 ++++++------
 fs/ntfs3/debug.h    |   5 +-
 fs/ntfs3/dir.c      |  61 ++--
 fs/ntfs3/file.c     |  98 +++---
 fs/ntfs3/frecord.c  | 413 ++++++++++++-------------
 fs/ntfs3/fslog.c    | 728 +++++++++++++++++++++++---------------------
 fs/ntfs3/fsntfs.c   | 244 +++++++--------
 fs/ntfs3/index.c    | 400 ++++++++++++------------
 fs/ntfs3/inode.c    | 243 ++++++++-------
 fs/ntfs3/lznt.c     |  86 +++---
 fs/ntfs3/namei.c    |  72 ++---
 fs/ntfs3/ntfs.h     | 517 +++++++++++++++----------------
 fs/ntfs3/ntfs_fs.h  | 198 ++++++------
 fs/ntfs3/record.c   |  60 ++--
 fs/ntfs3/run.c      | 187 ++++++------
 fs/ntfs3/super.c    | 160 +++++-----
 fs/ntfs3/upcase.c   |   9 +-
 fs/ntfs3/xattr.c    | 107 +++----
 21 files changed, 2008 insertions(+), 2086 deletions(-)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index bca85e7b6eaf..4dc630b28817 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
  *
- * TODO: merge attr_set_size/attr_data_get_block/attr_allocate_frame?
+ * TODO: Merge attr_set_size/attr_data_get_block/attr_allocate_frame?
  */

 #include <linux/blkdev.h>
@@ -20,7 +20,7 @@

 /*
  * You can set external NTFS_MIN_LOG2_OF_CLUMP/NTFS_MAX_LOG2_OF_CLUMP to manage
- * preallocate algorithm
+ * preallocate algorithm.
  */
 #ifndef NTFS_MIN_LOG2_OF_CLUMP
 #define NTFS_MIN_LOG2_OF_CLUMP 16
@@ -35,10 +35,6 @@
 // 16G
 #define NTFS_CLUMP_MAX (1ull << (NTFS_MAX_LOG2_OF_CLUMP + 8))

-/*
- * get_pre_allocated
- *
- */
 static inline u64 get_pre_allocated(u64 size)
 {
 	u32 clump;
@@ -65,7 +61,7 @@ static inline u64 get_pre_allocated(u64 size)
 /*
  * attr_must_be_resident
  *
- * returns true if attribute must be resident
+ * Return: True if attribute must be resident.
  */
 static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi,
 					 enum ATTR_TYPE type)
@@ -90,9 +86,7 @@ static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi,
 }

 /*
- * attr_load_runs
- *
- * load all runs stored in 'attr'
+ * attr_load_runs - Load all runs stored in @attr.
  */
 int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
 		   struct runs_tree *run, const CLST *vcn)
@@ -121,9 +115,7 @@ int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
 }

 /*
- * int run_deallocate_ex
- *
- * Deallocate clusters
+ * run_deallocate_ex - Deallocate clusters.
  */
 static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run,
 			     CLST vcn, CLST len, CLST *done, bool trim)
@@ -163,7 +155,7 @@ static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run,
 		vcn_next = vcn + clen;
 		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
 		    vcn != vcn_next) {
-			// save memory - don't load entire run
+			/* Save memory - don't load entire run. */
 			goto failed;
 		}
 	}
@@ -176,9 +168,7 @@ static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run,
 }

 /*
- * attr_allocate_clusters
- *
- * find free space, mark it as used and store in 'run'
+ * attr_allocate_clusters - Find free space, mark it as used and store in @run.
  */
 int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 			   CLST vcn, CLST lcn, CLST len, CLST *pre_alloc,
@@ -207,7 +197,7 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 		if (new_lcn && vcn == vcn0)
 			*new_lcn = lcn;

-		/* Add new fragment into run storage */
+		/* Add new fragment into run storage. */
 		if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) {
 			down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
 			wnd_set_free(wnd, lcn, flen);
@@ -228,7 +218,7 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 	}

 out:
-	/* undo */
+	/* Undo. */
 	run_deallocate_ex(sbi, run, vcn0, vcn - vcn0, NULL, false);
 	run_truncate(run, vcn0);

@@ -236,8 +226,10 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 }

 /*
- * if page is not NULL - it is already contains resident data
- * and locked (called from ni_write_frame)
+ * attr_make_nonresident
+ *
+ * If page is not NULL - it is already contains resident data
+ * and locked (called from ni_write_frame()).
  */
 int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 			  struct ATTR_LIST_ENTRY *le, struct mft_inode *mi,
@@ -275,7 +267,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,

 	run_init(run);

-	/* make a copy of original attribute */
+	/* Make a copy of original attribute. */
 	attr_s = ntfs_memdup(attr, asize);
 	if (!attr_s) {
 		err = -ENOMEM;
@@ -283,7 +275,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 	}

 	if (!len) {
-		/* empty resident -> empty nonresident */
+		/* Empty resident -> Empty nonresident. */
 		alen = 0;
 	} else {
 		const char *data = resident_data(attr);
@@ -294,7 +286,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 			goto out1;

 		if (!rsize) {
-			/* empty resident -> non empty nonresident */
+			/* Empty resident -> Non empty nonresident. */
 		} else if (!is_data) {
 			err = ntfs_sb_write_run(sbi, run, 0, data, rsize);
 			if (err)
@@ -319,7 +311,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 		}
 	}

-	/* remove original attribute */
+	/* Remove original attribute. */
 	used -= asize;
 	memmove(attr, Add2Ptr(attr, asize), used - aoff);
 	rec->used = cpu_to_le32(used);
@@ -342,7 +334,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 	if (is_data)
 		ni->ni_flags &= ~NI_FLAG_RESIDENT;

-	/* Resident attribute becomes non resident */
+	/* Resident attribute becomes non resident. */
 	return 0;

 out3:
@@ -352,20 +344,18 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 	rec->used = cpu_to_le32(used + asize);
 	mi->dirty = true;
 out2:
-	/* undo: do not trim new allocated clusters */
+	/* Undo: Do not trim new allocated clusters. */
 	run_deallocate(sbi, run, false);
 	run_close(run);
 out1:
 	ntfs_free(attr_s);
-	/*reinsert le*/
+	/* Reinsert le. */
 out:
 	return err;
 }

 /*
- * attr_set_size_res
- *
- * helper for attr_set_size
+ * attr_set_size_res - Helper for attr_set_size().
  */
 static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr,
 			     struct ATTR_LIST_ENTRY *le, struct mft_inode *mi,
@@ -407,14 +397,13 @@ static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr,
 }

 /*
- * attr_set_size
+ * attr_set_size - Change the size of attribute.
  *
- * change the size of attribute
  * Extend:
- *   - sparse/compressed: no allocated clusters
- *   - normal: append allocated and preallocated new clusters
+ *   - Sparse/compressed: No allocated clusters.
+ *   - Normal: Append allocated and preallocated new clusters.
  * Shrink:
- *   - no deallocate if keep_prealloc is set
+ *   - No deallocate if @keep_prealloc is set.
  */
 int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		  const __le16 *name, u8 name_len, struct runs_tree *run,
@@ -451,7 +440,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		if (err || !attr_b->non_res)
 			goto out;

-		/* layout of records may be changed, so do a full search */
+		/* Layout of records may be changed, so do a full search. */
 		goto again;
 	}

@@ -530,10 +519,10 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 add_alloc_in_same_attr_seg:
 		lcn = 0;
 		if (is_mft) {
-			/* mft allocates clusters from mftzone */
+			/* MFT allocates clusters from MFT zone. */
 			pre_alloc = 0;
 		} else if (is_ext) {
-			/* no preallocate for sparse/compress */
+			/* No preallocate for sparse/compress. */
 			pre_alloc = 0;
 		} else if (pre_alloc == -1) {
 			pre_alloc = 0;
@@ -544,7 +533,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 				pre_alloc = new_alen2 - new_alen;
 			}

-			/* Get the last lcn to allocate from */
+			/* Get the last LCN to allocate from. */
 			if (old_alen &&
 			    !run_lookup_entry(run, vcn, &lcn, NULL, NULL)) {
 				lcn = SPARSE_LCN;
@@ -575,7 +564,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			}
 			alen = to_allocate;
 		} else {
-			/* ~3 bytes per fragment */
+			/* ~3 bytes per fragment. */
 			err = attr_allocate_clusters(
 				sbi, run, vcn, lcn, to_allocate, &pre_alloc,
 				is_mft ? ALLOCATE_MFT : 0, &alen,
@@ -607,12 +596,12 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		mi_b->dirty = true;

 		if (next_svcn >= vcn && !to_allocate) {
-			/* Normal way. update attribute and exit */
+			/* Normal way. Update attribute and exit. */
 			attr_b->nres.data_size = cpu_to_le64(new_size);
 			goto ok;
 		}

-		/* at least two mft to avoid recursive loop*/
+		/* At least two MFT to avoid recursive loop. */
 		if (is_mft && next_svcn == vcn &&
 		    ((u64)done << sbi->cluster_bits) >= 2 * sbi->record_size) {
 			new_size = new_alloc_tmp;
@@ -637,7 +626,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			if (next_svcn < vcn)
 				goto pack_runs;

-			/* layout of records is changed */
+			/* Layout of records is changed. */
 			goto again;
 		}

@@ -645,15 +634,15 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			err = ni_create_attr_list(ni);
 			if (err)
 				goto out;
-			/* layout of records is changed */
+			/* Layout of records is changed. */
 		}

 		if (next_svcn >= vcn) {
-			/* this is mft data, repeat */
+			/* This is MFT data, repeat. */
 			goto again;
 		}

-		/* insert new attribute segment */
+		/* Insert new attribute segment. */
 		err = ni_insert_nonresident(ni, type, name, name_len, run,
 					    next_svcn, vcn - next_svcn,
 					    attr_b->flags, &attr, &mi);
@@ -667,8 +656,10 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		evcn = le64_to_cpu(attr->nres.evcn);

 		le_b = NULL;
-		/* layout of records maybe changed */
-		/* find base attribute to update*/
+		/*
+		 * Layout of records maybe changed.
+		 * Find base attribute to update.
+		 */
 		attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len,
 				      NULL, &mi_b);
 		if (!attr_b) {
@@ -704,11 +695,11 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			u16 le_sz = le16_to_cpu(le->size);

 			/*
-			 * NOTE: list entries for one attribute are always
+			 * NOTE: List entries for one attribute are always
 			 * the same size. We deal with last entry (vcn==0)
 			 * and it is not first in entries array
-			 * (list entry for std attribute always first)
-			 * So it is safe to step back
+			 * (list entry for std attribute always first).
+			 * So it is safe to step back.
 			 */
 			mi_remove_attr(mi, attr);

@@ -793,7 +784,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	if (!err && attr_b && ret)
 		*ret = attr_b;

-	/* update inode_set_bytes*/
+	/* Update inode_set_bytes. */
 	if (!err && ((type == ATTR_DATA && !name_len) ||
 		     (type == ATTR_ALLOC && name == I30_NAME))) {
 		bool dirty = false;
@@ -843,7 +834,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	up_read(&ni->file.run_lock);

 	if (ok && (*lcn != SPARSE_LCN || !new)) {
-		/* normal way */
+		/* Normal way. */
 		return 0;
 	}

@@ -909,7 +900,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	if (!ok) {
 		ok = run_lookup_entry(run, vcn, lcn, len, NULL);
 		if (ok && (*lcn != SPARSE_LCN || !new)) {
-			/* normal way */
+			/* Normal way. */
 			err = 0;
 			goto ok;
 		}
@@ -932,7 +923,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		goto out;
 	}

-	/* Get the last lcn to allocate from */
+	/* Get the last LCN to allocate from. */
 	hint = 0;

 	if (vcn > evcn1) {
@@ -970,20 +961,20 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	mi_b->dirty = true;
 	mark_inode_dirty(&ni->vfs_inode);

-	/* stored [vcn : next_svcn) from [vcn : end) */
+	/* Stored [vcn : next_svcn) from [vcn : end). */
 	next_svcn = le64_to_cpu(attr->nres.evcn) + 1;

 	if (end <= evcn1) {
 		if (next_svcn == evcn1) {
-			/* Normal way. update attribute and exit */
+			/* Normal way. Update attribute and exit. */
 			goto ok;
 		}
-		/* add new segment [next_svcn : evcn1 - next_svcn )*/
+		/* Add new segment [next_svcn : evcn1 - next_svcn). */
 		if (!ni->attr_list.size) {
 			err = ni_create_attr_list(ni);
 			if (err)
 				goto out;
-			/* layout of records is changed */
+			/* Layout of records is changed. */
 			le_b = NULL;
 			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
 					      0, NULL, &mi_b);
@@ -1001,7 +992,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,

 	svcn = evcn1;

-	/* Estimate next attribute */
+	/* Estimate next attribute. */
 	attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi);

 	if (attr) {
@@ -1012,7 +1003,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		if (end < next_svcn)
 			end = next_svcn;
 		while (end > evcn) {
-			/* remove segment [svcn : evcn)*/
+			/* Remove segment [svcn : evcn). */
 			mi_remove_attr(mi, attr);

 			if (!al_remove_le(ni, le)) {
@@ -1021,7 +1012,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 			}

 			if (evcn + 1 >= alloc) {
-				/* last attribute segment */
+				/* Last attribute segment. */
 				evcn1 = evcn + 1;
 				goto ins_ext;
 			}
@@ -1125,7 +1116,7 @@ int attr_data_write_resident(struct ntfs_inode *ni, struct page *page)
 		return -EINVAL;

 	if (attr->non_res) {
-		/*return special error code to check this case*/
+		/* Return special error code to check this case. */
 		return E_NTFS_NONRESIDENT;
 	}

@@ -1148,9 +1139,7 @@ int attr_data_write_resident(struct ntfs_inode *ni, struct page *page)
 }

 /*
- * attr_load_runs_vcn
- *
- * load runs with vcn
+ * attr_load_runs_vcn - Load runs with VCN.
  */
 int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		       const __le16 *name, u8 name_len, struct runs_tree *run,
@@ -1180,7 +1169,7 @@ int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type,
 }

 /*
- * load runs for given range [from to)
+ * attr_wof_load_runs_range - Load runs for given range [from to).
  */
 int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			 const __le16 *name, u8 name_len, struct runs_tree *run,
@@ -1199,7 +1188,7 @@ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
 						 vcn);
 			if (err)
 				return err;
-			clen = 0; /*next run_lookup_entry(vcn) must be success*/
+			clen = 0; /* Next run_lookup_entry(vcn) must be success. */
 		}
 	}

@@ -1210,7 +1199,7 @@ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
 /*
  * attr_wof_frame_info
  *
- * read header of xpress/lzx file to get info about frame
+ * Read header of Xpress/LZX file to get info about frame.
  */
 int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 			struct runs_tree *run, u64 frame, u64 frames,
@@ -1227,20 +1216,20 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 	__le64 *off64;

 	if (ni->vfs_inode.i_size < 0x100000000ull) {
-		/* file starts with array of 32 bit offsets */
+		/* File starts with array of 32 bit offsets. */
 		bytes_per_off = sizeof(__le32);
 		vbo[1] = frame << 2;
 		*vbo_data = frames << 2;
 	} else {
-		/* file starts with array of 64 bit offsets */
+		/* File starts with array of 64 bit offsets. */
 		bytes_per_off = sizeof(__le64);
 		vbo[1] = frame << 3;
 		*vbo_data = frames << 3;
 	}

 	/*
-	 * read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts
-	 * read 4/8 bytes at [vbo] == offset where compressed frame ends
+	 * Read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts.
+	 * Read 4/8 bytes at [vbo] == offset where compressed frame ends.
 	 */
 	if (!attr->non_res) {
 		if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) {
@@ -1329,7 +1318,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 				off[0] = le64_to_cpu(*off64);
 			}
 		} else {
-			/* two values in one page*/
+			/* Two values in one page. */
 			if (bytes_per_off == sizeof(__le32)) {
 				off32 = Add2Ptr(addr, voff);
 				off[0] = le32_to_cpu(off32[-1]);
@@ -1355,9 +1344,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 #endif

 /*
- * attr_is_frame_compressed
- *
- * This function is used to detect compressed frame
+ * attr_is_frame_compressed - Used to detect compressed frame.
  */
 int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 			     CLST frame, CLST *clst_data)
@@ -1391,14 +1378,14 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 	}

 	if (lcn == SPARSE_LCN) {
-		/* sparsed frame */
+		/* Sparsed frame. */
 		return 0;
 	}

 	if (clen >= clst_frame) {
 		/*
 		 * The frame is not compressed 'cause
-		 * it does not contain any sparse clusters
+		 * it does not contain any sparse clusters.
 		 */
 		*clst_data = clst_frame;
 		return 0;
@@ -1409,8 +1396,8 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 	*clst_data = clen;

 	/*
-	 * The frame is compressed if *clst_data + slen >= clst_frame
-	 * Check next fragments
+	 * The frame is compressed if *clst_data + slen >= clst_frame.
+	 * Check next fragments.
 	 */
 	while ((vcn += clen) < alen) {
 		vcn_next = vcn;
@@ -1433,8 +1420,8 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 		} else {
 			if (slen) {
 				/*
-				 * data_clusters + sparse_clusters =
-				 * not enough for frame
+				 * Data_clusters + sparse_clusters =
+				 * not enough for frame.
 				 */
 				return -EINVAL;
 			}
@@ -1445,11 +1432,11 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 			if (!slen) {
 				/*
 				 * There is no sparsed clusters in this frame
-				 * So it is not compressed
+				 * so it is not compressed.
 				 */
 				*clst_data = clst_frame;
 			} else {
-				/*frame is compressed*/
+				/* Frame is compressed. */
 			}
 			break;
 		}
@@ -1459,10 +1446,9 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 }

 /*
- * attr_allocate_frame
+ * attr_allocate_frame - Allocate/free clusters for @frame.
  *
- * allocate/free clusters for 'frame'
- * assumed: down_write(&ni->file.run_lock);
+ * Assumed: down_write(&ni->file.run_lock);
  */
 int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			u64 new_valid)
@@ -1538,10 +1524,10 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			goto out;
 		}
 		end = vcn + clst_data;
-		/* run contains updated range [vcn + len : end) */
+		/* Run contains updated range [vcn + len : end). */
 	} else {
 		CLST alen, hint = 0;
-		/* Get the last lcn to allocate from */
+		/* Get the last LCN to allocate from. */
 		if (vcn + clst_data &&
 		    !run_lookup_entry(run, vcn + clst_data - 1, &hint, NULL,
 				      NULL)) {
@@ -1555,7 +1541,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			goto out;

 		end = vcn + len;
-		/* run contains updated range [vcn + clst_data : end) */
+		/* Run contains updated range [vcn + clst_data : end). */
 	}

 	total_size += (u64)len << sbi->cluster_bits;
@@ -1571,20 +1557,20 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 	mi_b->dirty = true;
 	mark_inode_dirty(&ni->vfs_inode);

-	/* stored [vcn : next_svcn) from [vcn : end) */
+	/* Stored [vcn : next_svcn) from [vcn : end). */
 	next_svcn = le64_to_cpu(attr->nres.evcn) + 1;

 	if (end <= evcn1) {
 		if (next_svcn == evcn1) {
-			/* Normal way. update attribute and exit */
+			/* Normal way. Update attribute and exit. */
 			goto ok;
 		}
-		/* add new segment [next_svcn : evcn1 - next_svcn )*/
+		/* Add new segment [next_svcn : evcn1 - next_svcn). */
 		if (!ni->attr_list.size) {
 			err = ni_create_attr_list(ni);
 			if (err)
 				goto out;
-			/* layout of records is changed */
+			/* Layout of records is changed. */
 			le_b = NULL;
 			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
 					      0, NULL, &mi_b);
@@ -1602,7 +1588,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,

 	svcn = evcn1;

-	/* Estimate next attribute */
+	/* Estimate next attribute. */
 	attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi);

 	if (attr) {
@@ -1613,7 +1599,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 		if (end < next_svcn)
 			end = next_svcn;
 		while (end > evcn) {
-			/* remove segment [svcn : evcn)*/
+			/* Remove segment [svcn : evcn). */
 			mi_remove_attr(mi, attr);

 			if (!al_remove_le(ni, le)) {
@@ -1622,7 +1608,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			}

 			if (evcn + 1 >= alloc) {
-				/* last attribute segment */
+				/* Last attribute segment. */
 				evcn1 = evcn + 1;
 				goto ins_ext;
 			}
@@ -1684,7 +1670,9 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 	return err;
 }

-/* Collapse range in file */
+/*
+ * attr_collapse_range - Collapse range in file.
+ */
 int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 {
 	int err = 0;
@@ -1725,7 +1713,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	}

 	if ((vbo & mask) || (bytes & mask)) {
-		/* allow to collapse only cluster aligned ranges */
+		/* Allow to collapse only cluster aligned ranges. */
 		return -EINVAL;
 	}

@@ -1737,7 +1725,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	if (vbo + bytes >= data_size) {
 		u64 new_valid = min(ni->i_valid, vbo);

-		/* Simple truncate file at 'vbo' */
+		/* Simple truncate file at 'vbo'. */
 		truncate_setsize(&ni->vfs_inode, vbo);
 		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, vbo,
 				    &new_valid, true, NULL);
@@ -1749,7 +1737,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	}

 	/*
-	 * Enumerate all attribute segments and collapse
+	 * Enumerate all attribute segments and collapse.
 	 */
 	alen = alloc_size >> sbi->cluster_bits;
 	vcn = vbo >> sbi->cluster_bits;
@@ -1782,7 +1770,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)

 	for (;;) {
 		if (svcn >= end) {
-			/* shift vcn */
+			/* Shift VCN- */
 			attr->nres.svcn = cpu_to_le64(svcn - len);
 			attr->nres.evcn = cpu_to_le64(evcn1 - 1 - len);
 			if (le) {
@@ -1793,7 +1781,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 		} else if (svcn < vcn || end < evcn1) {
 			CLST vcn1, eat, next_svcn;

-			/* collapse a part of this attribute segment */
+			/* Collapse a part of this attribute segment. */
 			err = attr_load_runs(attr, ni, run, &svcn);
 			if (err)
 				goto out;
@@ -1811,7 +1799,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 			}

 			if (svcn >= vcn) {
-				/* shift vcn */
+				/* Shift VCN */
 				attr->nres.svcn = cpu_to_le64(vcn);
 				if (le) {
 					le->vcn = attr->nres.svcn;
@@ -1832,7 +1820,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 				if (err)
 					goto out;

-				/* layout of records maybe changed */
+				/* Layout of records maybe changed. */
 				attr_b = NULL;
 				le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0,
 						&next_svcn);
@@ -1842,18 +1830,18 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 				}
 			}

-			/* free all allocated memory */
+			/* Free all allocated memory. */
 			run_truncate(run, 0);
 		} else {
 			u16 le_sz;
 			u16 roff = le16_to_cpu(attr->nres.run_off);

-			/*run==1 means unpack and deallocate*/
+			/* run==1 means unpack and deallocate. */
 			run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn,
 				      evcn1 - 1, svcn, Add2Ptr(attr, roff),
 				      le32_to_cpu(attr->size) - roff);

-			/* delete this attribute segment */
+			/* Delete this attribute segment. */
 			mi_remove_attr(mi, attr);
 			if (!le)
 				break;
@@ -1868,13 +1856,13 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 				break;

 			if (!svcn) {
-				/* Load next record that contains this attribute */
+				/* Load next record that contains this attribute. */
 				if (ni_load_mi(ni, le, &mi)) {
 					err = -EINVAL;
 					goto out;
 				}

-				/* Look for required attribute */
+				/* Look for required attribute. */
 				attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL,
 						    0, &le->id);
 				if (!attr) {
@@ -1925,7 +1913,7 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 		attr_b->nres.total_size = cpu_to_le64(total_size);
 	mi_b->dirty = true;

-	/*update inode size*/
+	/* Update inode size. */
 	ni->i_valid = valid_size;
 	ni->vfs_inode.i_size = data_size;
 	inode_set_bytes(&ni->vfs_inode, total_size);
@@ -1940,7 +1928,11 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	return err;
 }

-/* not for normal files */
+/*
+ * attr_punch_hole
+ *
+  * Not for normal files.
+  */
 int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 {
 	int err = 0;
@@ -1973,7 +1965,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 		return 0;
 	}

-	/* TODO: add support for normal files too */
+	/* TODO: Add support for normal files too. */
 	if (!is_attr_ext(attr_b))
 		return -EOPNOTSUPP;

@@ -1981,7 +1973,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	total_size = le64_to_cpu(attr_b->nres.total_size);

 	if (vbo >= alloc_size) {
-		// NOTE: it is allowed
+		// NOTE: It is allowed.
 		return 0;
 	}

@@ -1990,7 +1982,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)

 	down_write(&ni->file.run_lock);
 	/*
-	 * Enumerate all attribute segments and punch hole where necessary
+	 * Enumerate all attribute segments and punch hole where necessary.
 	 */
 	alen = alloc_size >> sbi->cluster_bits;
 	vcn = vbo >> sbi->cluster_bits;
@@ -2036,7 +2028,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 			goto out;

 		if (dealloc2 == dealloc) {
-			/* looks like  the required range is already sparsed */
+			/* Looks like the required range is already sparsed. */
 		} else {
 			if (!run_add_entry(run, vcn1, SPARSE_LCN, zero,
 					   false)) {
@@ -2048,7 +2040,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 			if (err)
 				goto out;
 		}
-		/* free all allocated memory */
+		/* Free all allocated memory. */
 		run_truncate(run, 0);

 		if (evcn1 >= alen)
@@ -2068,7 +2060,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	attr_b->nres.total_size = cpu_to_le64(total_size);
 	mi_b->dirty = true;

-	/*update inode size*/
+	/* Update inode size. */
 	inode_set_bytes(&ni->vfs_inode, total_size);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index ea561361b576..5babc7d2b1b2 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -14,7 +14,11 @@
 #include "ntfs.h"
 #include "ntfs_fs.h"

-/* Returns true if le is valid */
+/*
+ * al_is_valid_le
+ *
+ * Return: True if @le is valid.
+ */
 static inline bool al_is_valid_le(const struct ntfs_inode *ni,
 				  struct ATTR_LIST_ENTRY *le)
 {
@@ -101,8 +105,9 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
 /*
  * al_enumerate
  *
- * Returns the next list 'le'
- * if 'le' is NULL then returns the first 'le'
+ * Return:
+ * * The next list le.
+ * * If @le is NULL then return the first le.
  */
 struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 				     struct ATTR_LIST_ENTRY *le)
@@ -115,22 +120,22 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 	} else {
 		sz = le16_to_cpu(le->size);
 		if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
-			/* Impossible 'cause we should not return such 'le' */
+			/* Impossible 'cause we should not return such le. */
 			return NULL;
 		}
 		le = Add2Ptr(le, sz);
 	}

-	/* Check boundary */
+	/* Check boundary. */
 	off = PtrOffset(ni->attr_list.le, le);
 	if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
-		// The regular end of list
+		/* The regular end of list. */
 		return NULL;
 	}

 	sz = le16_to_cpu(le->size);

-	/* Check 'le' for errors */
+	/* Check le for errors. */
 	if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
 	    off + sz > ni->attr_list.size ||
 	    sz < le->name_off + le->name_len * sizeof(short)) {
@@ -143,8 +148,9 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 /*
  * al_find_le
  *
- * finds the first 'le' in the list which matches type, name and vcn
- * Returns NULL if not found
+ * Find the first le in the list which matches type, name and VCN.
+ *
+ * Return: NULL if not found.
  */
 struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni,
 				   struct ATTR_LIST_ENTRY *le,
@@ -159,8 +165,9 @@ struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni,
 /*
  * al_find_ex
  *
- * finds the first 'le' in the list which matches type, name and vcn
- * Returns NULL if not found
+ * Find the first le in the list which matches type, name and VCN.
+ *
+ * Return: NULL if not found.
  */
 struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
 				   struct ATTR_LIST_ENTRY *le,
@@ -174,7 +181,7 @@ struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
 		u64 le_vcn;
 		int diff = le32_to_cpu(le->type) - type_in;

-		/* List entries are sorted by type, name and vcn */
+		/* List entries are sorted by type, name and VCN. */
 		if (diff < 0)
 			continue;

@@ -187,7 +194,7 @@ struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
 		le_vcn = le64_to_cpu(le->vcn);
 		if (!le_vcn) {
 			/*
-			 * compare entry names only for entry with vcn == 0
+			 * Compare entry names only for entry with vcn == 0.
 			 */
 			diff = ntfs_cmp_names(le_name(le), name_len, name,
 					      name_len, ni->mi.sbi->upcase,
@@ -215,9 +222,9 @@ struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
 }

 /*
- * al_find_le_to_insert
+ * al_find_le_to_insert
  *
- * finds the first list entry which matches type, name and vcn
+ * Find the first list entry which matches type, name and VCN.
  */
 static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni,
 						    enum ATTR_TYPE type,
@@ -227,7 +234,7 @@ static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni,
 	struct ATTR_LIST_ENTRY *le = NULL, *prev;
 	u32 type_in = le32_to_cpu(type);

-	/* List entries are sorted by type, name, vcn */
+	/* List entries are sorted by type, name and VCN. */
 	while ((le = al_enumerate(ni, prev = le))) {
 		int diff = le32_to_cpu(le->type) - type_in;

@@ -239,7 +246,7 @@ static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni,

 		if (!le->vcn) {
 			/*
-			 * compare entry names only for entry with vcn == 0
+			 * Compare entry names only for entry with vcn == 0.
 			 */
 			diff = ntfs_cmp_names(le_name(le), le->name_len, name,
 					      name_len, ni->mi.sbi->upcase,
@@ -261,7 +268,7 @@ static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni,
 /*
  * al_add_le
  *
- * adds an "attribute list entry" to the list.
+ * Add an "attribute list entry" to the list.
  */
 int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
 	      u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref,
@@ -335,9 +342,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
 }

 /*
- * al_remove_le
- *
- * removes 'le' from attribute list
+ * al_remove_le - Remove @le from attribute list.
  */
 bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le)
 {
@@ -361,9 +366,7 @@ bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le)
 }

 /*
- * al_delete_le
- *
- * deletes from the list the first 'le' which matches its parameters.
+ * al_delete_le - Delete first le from the list which matches its parameters.
  */
 bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 		  const __le16 *name, size_t name_len,
@@ -374,7 +377,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 	size_t off;
 	typeof(ni->attr_list) *al = &ni->attr_list;

-	/* Scan forward to the first 'le' that matches the input */
+	/* Scan forward to the first le that matches the input. */
 	le = al_find_ex(ni, NULL, type, name, name_len, &vcn);
 	if (!le)
 		return false;
@@ -405,9 +408,9 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 		goto next;
 	}

-	/* Save on stack the size of 'le' */
+	/* Save on stack the size of 'le'. */
 	size = le16_to_cpu(le->size);
-	/* Delete 'le'. */
+	/* Delete the le. */
 	memmove(le, Add2Ptr(le, size), al->size - (off + size));

 	al->size -= size;
@@ -416,9 +419,6 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 	return true;
 }

-/*
- * al_update
- */
 int al_update(struct ntfs_inode *ni)
 {
 	int err;
@@ -429,8 +429,8 @@ int al_update(struct ntfs_inode *ni)
 		return 0;

 	/*
-	 * attribute list increased on demand in al_add_le
-	 * attribute list decreased here
+	 * Attribute list increased on demand in al_add_le.
+	 * Attribute list decreased here.
 	 */
 	err = attr_set_size(ni, ATTR_LIST, NULL, 0, &al->run, al->size, NULL,
 			    false, &attr);
diff --git a/fs/ntfs3/bitfunc.c b/fs/ntfs3/bitfunc.c
index 2de5faef2721..ce304d40b5e1 100644
--- a/fs/ntfs3/bitfunc.c
+++ b/fs/ntfs3/bitfunc.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
  *
  */
+
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
@@ -32,7 +33,7 @@ static const u8 zero_mask[] = { 0xFF, 0xFE, 0xFC, 0xF8, 0xF0,
 /*
  * are_bits_clear
  *
- * Returns true if all bits [bit, bit+nbits) are zeros "0"
+ * Return: True if all bits [bit, bit+nbits) are zeros "0".
  */
 bool are_bits_clear(const ulong *lmap, size_t bit, size_t nbits)
 {
@@ -74,14 +75,13 @@ bool are_bits_clear(const ulong *lmap, size_t bit, size_t nbits)
 	if (pos && (*map & fill_mask[pos]))
 		return false;

-	// All bits are zero
 	return true;
 }

 /*
  * are_bits_set
  *
- * Returns true if all bits [bit, bit+nbits) are ones "1"
+ * Return: True if all bits [bit, bit+nbits) are ones "1".
  */
 bool are_bits_set(const ulong *lmap, size_t bit, size_t nbits)
 {
@@ -130,6 +130,5 @@ bool are_bits_set(const ulong *lmap, size_t bit, size_t nbits)
 			return false;
 	}

-	// All bits are ones
 	return true;
 }
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 32aab0031221..ff586798b62a 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -6,7 +6,7 @@
  * This code builds two trees of free clusters extents.
  * Trees are sorted by start of extent and by length of extent.
  * NTFS_MAX_WND_EXTENTS defines the maximum number of elements in trees.
- * In extreme case code reads on-disk bitmap to find free clusters
+ * In extreme case code reads on-disk bitmap to find free clusters.
  *
  */

@@ -29,12 +29,10 @@ struct rb_node_key {
 	size_t key;
 };

-/*
- * Tree is sorted by start (key)
- */
+/* Tree is sorted by start (key). */
 struct e_node {
-	struct rb_node_key start; /* Tree sorted by start */
-	struct rb_node_key count; /* Tree sorted by len*/
+	struct rb_node_key start; /* Tree sorted by start. */
+	struct rb_node_key count; /* Tree sorted by len. */
 };

 static int wnd_rescan(struct wnd_bitmap *wnd);
@@ -62,9 +60,12 @@ static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i)
 }

 /*
- * b_pos + b_len - biggest fragment
- * Scan range [wpos wbits) window 'buf'
- * Returns -1 if not found
+ * wnd_scan
+ *
+ * b_pos + b_len - biggest fragment.
+ * Scan range [wpos wbits) window @buf.
+ *
+ * Return: -1 if not found.
  */
 static size_t wnd_scan(const ulong *buf, size_t wbit, u32 wpos, u32 wend,
 		       size_t to_alloc, size_t *prev_tail, size_t *b_pos,
@@ -96,7 +97,7 @@ static size_t wnd_scan(const ulong *buf, size_t wbit, u32 wpos, u32 wend,
 		}

 		/*
-		 * Now we have a fragment [wpos, wend) staring with 0
+		 * Now we have a fragment [wpos, wend) staring with 0.
 		 */
 		end = wpos + to_alloc - *prev_tail;
 		free_bits = find_next_bit(buf, min(end, wend), wpos);
@@ -125,9 +126,7 @@ static size_t wnd_scan(const ulong *buf, size_t wbit, u32 wpos, u32 wend,
 }

 /*
- * wnd_close
- *
- * Frees all resources
+ * wnd_close - Frees all resources.
  */
 void wnd_close(struct wnd_bitmap *wnd)
 {
@@ -170,9 +169,7 @@ static struct rb_node *rb_lookup(struct rb_root *root, size_t v)
 }

 /*
- * rb_insert_count
- *
- * Helper function to insert special kind of 'count' tree
+ * rb_insert_count - Helper function to insert special kind of 'count' tree.
  */
 static inline bool rb_insert_count(struct rb_root *root, struct e_node *e)
 {
@@ -205,9 +202,7 @@ static inline bool rb_insert_count(struct rb_root *root, struct e_node *e)
 }

 /*
- * inline bool rb_insert_start
- *
- * Helper function to insert special kind of 'start' tree
+ * rb_insert_start - Helper function to insert special kind of 'count' tree.
  */
 static inline bool rb_insert_start(struct rb_root *root, struct e_node *e)
 {
@@ -237,10 +232,8 @@ static inline bool rb_insert_start(struct rb_root *root, struct e_node *e)
 }

 /*
- * wnd_add_free_ext
- *
- * adds a new extent of free space
- * build = 1 when building tree
+ * wnd_add_free_ext - Adds a new extent of free space.
+ * @build:	1 when building tree.
  */
 static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 			     bool build)
@@ -250,14 +243,14 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 	struct rb_node *n;

 	if (build) {
-		/* Use extent_min to filter too short extents */
+		/* Use extent_min to filter too short extents. */
 		if (wnd->count >= NTFS_MAX_WND_EXTENTS &&
 		    len <= wnd->extent_min) {
 			wnd->uptodated = -1;
 			return;
 		}
 	} else {
-		/* Try to find extent before 'bit' */
+		/* Try to find extent before 'bit'. */
 		n = rb_lookup(&wnd->start_tree, bit);

 		if (!n) {
@@ -266,7 +259,7 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 			e = rb_entry(n, struct e_node, start.node);
 			n = rb_next(n);
 			if (e->start.key + e->count.key == bit) {
-				/* Remove left */
+				/* Remove left. */
 				bit = e->start.key;
 				len += e->count.key;
 				rb_erase(&e->start.node, &wnd->start_tree);
@@ -284,7 +277,7 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 			if (e->start.key > end_in)
 				break;

-			/* Remove right */
+			/* Remove right. */
 			n = rb_next(n);
 			len += next_end - end_in;
 			end_in = next_end;
@@ -299,7 +292,7 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 		}

 		if (wnd->uptodated != 1) {
-			/* Check bits before 'bit' */
+			/* Check bits before 'bit'. */
 			ib = wnd->zone_bit == wnd->zone_end ||
 					     bit < wnd->zone_end
 				     ? 0
@@ -310,7 +303,7 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 				len += 1;
 			}

-			/* Check bits after 'end_in' */
+			/* Check bits after 'end_in'. */
 			ib = wnd->zone_bit == wnd->zone_end ||
 					     end_in > wnd->zone_bit
 				     ? wnd->nbits
@@ -322,29 +315,29 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
 			}
 		}
 	}
-	/* Insert new fragment */
+	/* Insert new fragment. */
 	if (wnd->count >= NTFS_MAX_WND_EXTENTS) {
 		if (e0)
 			kmem_cache_free(ntfs_enode_cachep, e0);

 		wnd->uptodated = -1;

-		/* Compare with smallest fragment */
+		/* Compare with smallest fragment. */
 		n = rb_last(&wnd->count_tree);
 		e = rb_entry(n, struct e_node, count.node);
 		if (len <= e->count.key)
-			goto out; /* Do not insert small fragments */
+			goto out; /* Do not insert small fragments. */

 		if (build) {
 			struct e_node *e2;

 			n = rb_prev(n);
 			e2 = rb_entry(n, struct e_node, count.node);
-			/* smallest fragment will be 'e2->count.key' */
+			/* Smallest fragment will be 'e2->count.key'. */
 			wnd->extent_min = e2->count.key;
 		}

-		/* Replace smallest fragment by new one */
+		/* Replace smallest fragment by new one. */
 		rb_erase(&e->start.node, &wnd->start_tree);
 		rb_erase(&e->count.node, &wnd->count_tree);
 		wnd->count -= 1;
@@ -371,9 +364,7 @@ out:;
 }

 /*
- * wnd_remove_free_ext
- *
- * removes a run from the cached free space
+ * wnd_remove_free_ext - Remove a run from the cached free space.
  */
 static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
 {
@@ -382,7 +373,7 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
 	size_t end_in = bit + len;
 	size_t end3, end, new_key, new_len, max_new_len;

-	/* Try to find extent before 'bit' */
+	/* Try to find extent before 'bit'. */
 	n = rb_lookup(&wnd->start_tree, bit);

 	if (!n)
@@ -394,11 +385,11 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
 	new_key = new_len = 0;
 	len = e->count.key;

-	/* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n' */
+	/* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n'. */
 	if (e->start.key > bit)
 		;
 	else if (end_in <= end) {
-		/* Range [bit,end_in) inside 'e' */
+		/* Range [bit,end_in) inside 'e'. */
 		new_key = end_in;
 		new_len = end - end_in;
 		len = bit - e->start.key;
@@ -478,13 +469,13 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
 	if (wnd->count >= NTFS_MAX_WND_EXTENTS) {
 		wnd->uptodated = -1;

-		/* Get minimal extent */
+		/* Get minimal extent. */
 		e = rb_entry(rb_last(&wnd->count_tree), struct e_node,
 			     count.node);
 		if (e->count.key > new_len)
 			goto out;

-		/* Replace minimum */
+		/* Replace minimum. */
 		rb_erase(&e->start.node, &wnd->start_tree);
 		rb_erase(&e->count.node, &wnd->count_tree);
 		wnd->count -= 1;
@@ -508,9 +499,7 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
 }

 /*
- * wnd_rescan
- *
- * Scan all bitmap. used while initialization.
+ * wnd_rescan - Scan all bitmap. Used while initialization.
  */
 static int wnd_rescan(struct wnd_bitmap *wnd)
 {
@@ -541,7 +530,7 @@ static int wnd_rescan(struct wnd_bitmap *wnd)

 		if (wnd->inited) {
 			if (!wnd->free_bits[iw]) {
-				/* all ones */
+				/* All ones. */
 				if (prev_tail) {
 					wnd_add_free_ext(wnd,
 							 vbo * 8 - prev_tail,
@@ -551,7 +540,7 @@ static int wnd_rescan(struct wnd_bitmap *wnd)
 				goto next_wnd;
 			}
 			if (wbits == wnd->free_bits[iw]) {
-				/* all zeroes */
+				/* All zeroes. */
 				prev_tail += wbits;
 				wnd->total_zeroes += wbits;
 				goto next_wnd;
@@ -604,14 +593,14 @@ static int wnd_rescan(struct wnd_bitmap *wnd)
 			wpos = used;

 			if (wpos >= wbits) {
-				/* No free blocks */
+				/* No free blocks. */
 				prev_tail = 0;
 				break;
 			}

 			frb = find_next_bit(buf, wbits, wpos);
 			if (frb >= wbits) {
-				/* keep last free block */
+				/* Keep last free block. */
 				prev_tail += frb - wpos;
 				break;
 			}
@@ -619,9 +608,9 @@ static int wnd_rescan(struct wnd_bitmap *wnd)
 			wnd_add_free_ext(wnd, wbit + wpos - prev_tail,
 					 frb + prev_tail - wpos, true);

-			/* Skip free block and first '1' */
+			/* Skip free block and first '1'. */
 			wpos = frb + 1;
-			/* Reset previous tail */
+			/* Reset previous tail. */
 			prev_tail = 0;
 		} while (wpos < wbits);

@@ -638,15 +627,15 @@ static int wnd_rescan(struct wnd_bitmap *wnd)
 		}
 	}

-	/* Add last block */
+	/* Add last block. */
 	if (prev_tail)
 		wnd_add_free_ext(wnd, wnd->nbits - prev_tail, prev_tail, true);

 	/*
-	 * Before init cycle wnd->uptodated was 0
+	 * Before init cycle wnd->uptodated was 0.
 	 * If any errors or limits occurs while initialization then
-	 * wnd->uptodated will be -1
-	 * If 'uptodated' is still 0 then Tree is really updated
+	 * wnd->uptodated will be -1.
+	 * If 'uptodated' is still 0 then Tree is really updated.
 	 */
 	if (!wnd->uptodated)
 		wnd->uptodated = 1;
@@ -662,9 +651,6 @@ static int wnd_rescan(struct wnd_bitmap *wnd)
 	return err;
 }

-/*
- * wnd_init
- */
 int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
 {
 	int err;
@@ -697,9 +683,7 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
 }

 /*
- * wnd_map
- *
- * call sb_bread for requested window
+ * wnd_map - Call sb_bread for requested window.
  */
 static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw)
 {
@@ -728,9 +712,7 @@ static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw)
 }

 /*
- * wnd_set_free
- *
- * Marks the bits range from bit to bit + bits as free
+ * wnd_set_free - Mark the bits range from bit to bit + bits as free.
  */
 int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
@@ -783,9 +765,7 @@ int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 }

 /*
- * wnd_set_used
- *
- * Marks the bits range from bit to bit + bits as used
+ * wnd_set_used - Mark the bits range from bit to bit + bits as used.
  */
 int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
@@ -839,7 +819,7 @@ int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 /*
  * wnd_is_free_hlp
  *
- * Returns true if all clusters [bit, bit+bits) are free (bitmap only)
+ * Return: True if all clusters [bit, bit+bits) are free (bitmap only).
  */
 static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
@@ -882,7 +862,7 @@ static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 /*
  * wnd_is_free
  *
- * Returns true if all clusters [bit, bit+bits) are free
+ * Return: True if all clusters [bit, bit+bits) are free.
  */
 bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
@@ -914,7 +894,7 @@ bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 /*
  * wnd_is_used
  *
- * Returns true if all clusters [bit, bit+bits) are used
+ * Return: True if all clusters [bit, bit+bits) are used.
  */
 bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 {
@@ -973,11 +953,11 @@ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
 }

 /*
- * wnd_find
- * - flags - BITMAP_FIND_XXX flags
+ * wnd_find - Look for free space.
  *
- * looks for free space
- * Returns 0 if not found
+ * - flags - BITMAP_FIND_XXX flags
+ *
+ * Return: 0 if not found.
  */
 size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 		size_t flags, size_t *allocated)
@@ -994,7 +974,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	bool fbits_valid;
 	struct buffer_head *bh;

-	/* fast checking for available free space */
+	/* Fast checking for available free space. */
 	if (flags & BITMAP_FIND_FULL) {
 		size_t zeroes = wnd_zeroes(wnd);

@@ -1020,7 +1000,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,

 	if (RB_EMPTY_ROOT(&wnd->start_tree)) {
 		if (wnd->uptodated == 1) {
-			/* extents tree is updated -> no free space */
+			/* Extents tree is updated -> No free space. */
 			goto no_space;
 		}
 		goto scan_bitmap;
@@ -1030,7 +1010,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	if (!hint)
 		goto allocate_biggest;

-	/* Use hint: enumerate extents by start >= hint */
+	/* Use hint: Enumerate extents by start >= hint. */
 	pr = NULL;
 	cr = wnd->start_tree.rb_node;

@@ -1059,7 +1039,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 		goto allocate_biggest;

 	if (e->start.key + e->count.key > hint) {
-		/* We have found extension with 'hint' inside */
+		/* We have found extension with 'hint' inside. */
 		size_t len = e->start.key + e->count.key - hint;

 		if (len >= to_alloc && hint + to_alloc <= max_alloc) {
@@ -1080,7 +1060,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	}

 allocate_biggest:
-	/* Allocate from biggest free extent */
+	/* Allocate from biggest free extent. */
 	e = rb_entry(rb_first(&wnd->count_tree), struct e_node, count.node);
 	if (e->count.key != wnd->extent_max)
 		wnd->extent_max = e->count.key;
@@ -1090,14 +1070,14 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 			;
 		} else if (flags & BITMAP_FIND_FULL) {
 			if (e->count.key < to_alloc0) {
-				/* Biggest free block is less then requested */
+				/* Biggest free block is less then requested. */
 				goto no_space;
 			}
 			to_alloc = e->count.key;
 		} else if (-1 != wnd->uptodated) {
 			to_alloc = e->count.key;
 		} else {
-			/* Check if we can use more bits */
+			/* Check if we can use more bits. */
 			size_t op, max_check;
 			struct rb_root start_tree;

@@ -1118,7 +1098,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 			to_alloc = op - e->start.key;
 		}

-		/* Prepare to return */
+		/* Prepare to return. */
 		fnd = e->start.key;
 		if (e->start.key + to_alloc > max_alloc)
 			to_alloc = max_alloc - e->start.key;
@@ -1126,7 +1106,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	}

 	if (wnd->uptodated == 1) {
-		/* extents tree is updated -> no free space */
+		/* Extents tree is updated -> no free space. */
 		goto no_space;
 	}

@@ -1140,7 +1120,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	/* At most two ranges [hint, max_alloc) + [0, hint) */
 Again:

-	/* TODO: optimize request for case nbits > wbits */
+	/* TODO: Optimize request for case nbits > wbits. */
 	iw = hint >> log2_bits;
 	wbits = sb->s_blocksize * 8;
 	wpos = hint & (wbits - 1);
@@ -1155,7 +1135,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 		nwnd = likely(t > max_alloc) ? (t >> log2_bits) : wnd->nwnd;
 	}

-	/* Enumerate all windows */
+	/* Enumerate all windows. */
 	for (; iw < nwnd; iw++) {
 		wbit = iw << log2_bits;

@@ -1165,7 +1145,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 				b_len = prev_tail;
 			}

-			/* Skip full used window */
+			/* Skip full used window. */
 			prev_tail = 0;
 			wpos = 0;
 			continue;
@@ -1189,25 +1169,25 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 			zbit = max(wnd->zone_bit, wbit);
 			zend = min(wnd->zone_end, ebit);

-			/* Here we have a window [wbit, ebit) and zone [zbit, zend) */
+			/* Here we have a window [wbit, ebit) and zone [zbit, zend). */
 			if (zend <= zbit) {
-				/* Zone does not overlap window */
+				/* Zone does not overlap window. */
 			} else {
 				wzbit = zbit - wbit;
 				wzend = zend - wbit;

-				/* Zone overlaps window */
+				/* Zone overlaps window. */
 				if (wnd->free_bits[iw] == wzend - wzbit) {
 					prev_tail = 0;
 					wpos = 0;
 					continue;
 				}

-				/* Scan two ranges window: [wbit, zbit) and [zend, ebit) */
+				/* Scan two ranges window: [wbit, zbit) and [zend, ebit). */
 				bh = wnd_map(wnd, iw);

 				if (IS_ERR(bh)) {
-					/* TODO: error */
+					/* TODO: Error */
 					prev_tail = 0;
 					wpos = 0;
 					continue;
@@ -1215,9 +1195,9 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,

 				buf = (ulong *)bh->b_data;

-				/* Scan range [wbit, zbit) */
+				/* Scan range [wbit, zbit). */
 				if (wpos < wzbit) {
-					/* Scan range [wpos, zbit) */
+					/* Scan range [wpos, zbit). */
 					fnd = wnd_scan(buf, wbit, wpos, wzbit,
 						       to_alloc, &prev_tail,
 						       &b_pos, &b_len);
@@ -1229,7 +1209,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,

 				prev_tail = 0;

-				/* Scan range [zend, ebit) */
+				/* Scan range [zend, ebit). */
 				if (wzend < wbits) {
 					fnd = wnd_scan(buf, wbit,
 						       max(wzend, wpos), wbits,
@@ -1247,24 +1227,24 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 			}
 		}

-		/* Current window does not overlap zone */
+		/* Current window does not overlap zone. */
 		if (!wpos && fbits_valid && wnd->free_bits[iw] == wbits) {
-			/* window is empty */
+			/* Window is empty. */
 			if (prev_tail + wbits >= to_alloc) {
 				fnd = wbit + wpos - prev_tail;
 				goto found;
 			}

-			/* Increase 'prev_tail' and process next window */
+			/* Increase 'prev_tail' and process next window. */
 			prev_tail += wbits;
 			wpos = 0;
 			continue;
 		}

-		/* read window */
+		/* Read window */
 		bh = wnd_map(wnd, iw);
 		if (IS_ERR(bh)) {
-			// TODO: error
+			// TODO: Error.
 			prev_tail = 0;
 			wpos = 0;
 			continue;
@@ -1272,7 +1252,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,

 		buf = (ulong *)bh->b_data;

-		/* Scan range [wpos, eBits) */
+		/* Scan range [wpos, eBits). */
 		fnd = wnd_scan(buf, wbit, wpos, wbits, to_alloc, &prev_tail,
 			       &b_pos, &b_len);
 		put_bh(bh);
@@ -1281,15 +1261,15 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 	}

 	if (b_len < prev_tail) {
-		/* The last fragment */
+		/* The last fragment. */
 		b_len = prev_tail;
 		b_pos = max_alloc - prev_tail;
 	}

 	if (hint) {
 		/*
-		 * We have scanned range [hint max_alloc)
-		 * Prepare to scan range [0 hint + to_alloc)
+		 * We have scanned range [hint max_alloc).
+		 * Prepare to scan range [0 hint + to_alloc).
 		 */
 		size_t nextmax = hint + to_alloc;

@@ -1312,7 +1292,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,

 found:
 	if (flags & BITMAP_FIND_MARK_AS_USED) {
-		/* TODO optimize remove extent (pass 'e'?) */
+		/* TODO: Optimize remove extent (pass 'e'?). */
 		if (wnd_set_used(wnd, fnd, to_alloc))
 			goto no_space;
 	} else if (wnd->extent_max != MINUS_ONE_T &&
@@ -1328,9 +1308,7 @@ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
 }

 /*
- * wnd_extend
- *
- * Extend bitmap ($MFT bitmap)
+ * wnd_extend - Extend bitmap ($MFT bitmap).
  */
 int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 {
@@ -1347,7 +1325,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 	if (new_bits <= old_bits)
 		return -EINVAL;

-	/* align to 8 byte boundary */
+	/* Align to 8 byte boundary. */
 	new_wnd = bytes_to_block(sb, bitmap_size(new_bits));
 	new_last = new_bits & (wbits - 1);
 	if (!new_last)
@@ -1367,7 +1345,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		wnd->free_bits = new_free;
 	}

-	/* Zero bits [old_bits,new_bits) */
+	/* Zero bits [old_bits,new_bits). */
 	bits = new_bits - old_bits;
 	b0 = old_bits & (wbits - 1);

@@ -1403,7 +1381,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		set_buffer_uptodate(bh);
 		mark_buffer_dirty(bh);
 		unlock_buffer(bh);
-		/*err = sync_dirty_buffer(bh);*/
+		/* err = sync_dirty_buffer(bh); */

 		b0 = 0;
 		bits -= op;
@@ -1418,9 +1396,6 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 	return 0;
 }

-/*
- * wnd_zone_set
- */
 void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len)
 {
 	size_t zlen;
@@ -1502,7 +1477,7 @@ int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range)
 		put_bh(bh);
 	}

-	/* Process the last fragment */
+	/* Process the last fragment. */
 	if (len >= minlen) {
 		err = ntfs_discard(sbi, lcn, len);
 		if (err)
diff --git a/fs/ntfs3/debug.h b/fs/ntfs3/debug.h
index dfaa4c79dc6d..93ed80f902b3 100644
--- a/fs/ntfs3/debug.h
+++ b/fs/ntfs3/debug.h
@@ -3,7 +3,8 @@
  *
  * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
  *
- * useful functions for debuging
+ *  Useful functions for debuging.
+ *
  */

 // clang-format off
@@ -41,7 +42,7 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
 #endif

 /*
- * Logging macros ( thanks Joe Perches <jo...@pe...> for implementation )
+ * Logging macros. Thanks Joe Perches <jo...@pe...> for implementation.
  */

 #define ntfs_err(sb, fmt, ...)  ntfs_printk(sb, KERN_ERR fmt, ##__VA_ARGS__)
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 9ec6012c405b..adde2bb0deb4 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -3,9 +3,10 @@
  *
  * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
  *
- *  directory handling functions for ntfs-based filesystems
+ *  Directory handling functions for NTFS-based filesystems.
  *
  */
+
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
@@ -16,9 +17,7 @@
 #include "ntfs.h"
 #include "ntfs_fs.h"

-/*
- * Convert little endian utf16 to nls string
- */
+/* Convert little endian UTF-16 to NLS string. */
 int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni,
 		      u8 *buf, int buf_len)
 {
@@ -30,7 +29,7 @@ int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni,
 	static_assert(sizeof(wchar_t) == sizeof(__le16));

 	if (!nls) {
-		/* utf16 -> utf8 */
+		/* UTF-16 -> UTF-8 */
 		ret = utf16s_to_utf8s((wchar_t *)uni->name, uni->len,
 				      UTF16_LITTLE_ENDIAN, buf, buf_len);
 		buf[ret] = '\0';
@@ -89,8 +88,9 @@ int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni,
 // clang-format on

 /*
- * modified version of put_utf16 from fs/nls/nls_base.c
- * is sparse warnings free
+ * put_utf16 - Modified version of put_utf16 from fs/nls/nls_base.c
+ *
+ * Function is sparse warnings free.
  */
 static inline void put_utf16(wchar_t *s, unsigned int c,
 			     enum utf16_endian endian)
@@ -112,8 +112,10 @@ static inline void put_utf16(wchar_t *s, unsigned int c,
 }

 /*
- * modified version of 'utf8s_to_utf16s' allows to
- * detect -ENAMETOOLONG without writing out of expected maximum
+ * _utf8s_to_utf16s
+ *
+ * Modified version of 'utf8s_to_utf16s' allows to
+ * detect -ENAMETOOLONG without writing out of expected maximum.
  */
 static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian,
 			    wchar_t *pwcs, int maxout)
@@ -165,17 +167,18 @@ static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian,
 }

 /*
- * Convert input string to utf16
- *
- * name, name_len - input name
- * uni, max_ulen - destination memory
- * endian - endian of target utf16 string
+ * ntfs_nls_to_utf16 - Convert input string to UTF-16.
+ * @name:	Input name.
+ * @name_len:	Input name length.
+ * @uni:	Destination memory.
+ * @max_ulen:	Destination memory.
+ * @endian:	Endian of target UTF-16 string.
  *
  * This function is called:
- * - to create ntfs name
+ * - to create NTFS name
  * - to create symlink
  *
- * returns utf16 string length or error (if negative)
+ * Return: UTF-16 string length or error (if negative).
  */
 int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
 		      struct cpu_str *uni, u32 max_ulen,
@@ -230,7 +233,9 @@ int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
 	return ret;
 }

-/* helper function */
+/*
+ * dir_search_u - Helper function.
+ */
 struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni,
 			   struct ntfs_fnd *fnd)
 {
@@ -295,7 +300,7 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 	if (ino == MFT_REC_ROOT)
 		return 0;

-	/* Skip meta files ( unless option to show metafiles is set ) */
+	/* Skip meta files. Unless option to show metafiles is set. */
 	if (!sbi->options.showmeta && ntfs_is_meta_file(sbi, ino))
 		return 0;

@@ -316,9 +321,7 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 }

 /*
...
 
[truncated message content]

Re: [Linux-NTFS-Dev] [PATCH v27 00/10] NTFS read-write driver GPL implementation by Paragon Software

[Theodore Ts'o <ty...@mi...>]

It should also noted that apparently ntfs3 does not properly support
user namespaces, such that generic/317 fails:

generic/317		[10:37:19][    7.024574] run fstests generic/317 at 2021-08-02 10:37:19
 [10:37:19]- output mismatch (see /results/ntfs3/results-default/generic/317.out.bad)
    --- tests/generic/317.out	2021-08-01 20:47:35.000000000 -0400
    +++ /results/ntfs3/results-default/generic/317.out.bad	2021-08-02 10:37:19.930687003 -0400
    @@ -13,8 +13,8 @@
     From init_user_ns
       File: "$SCRATCH_MNT/file1"
       Size: 0            Filetype: Regular File
    -  Mode: (0644/-rw-r--r--)         Uid: (qa_user)  Gid: (qa_user)
    +  Mode: (0755/-rwxr-xr-x)         Uid: (0)  Gid: (0)
     From user_ns
       File: "$SCRATCH_MNT/file1"
    ...
    (Run 'diff -u /root/xfstests/tests/generic/317.out /results/ntfs3/results-default/generic/317.out.bad'  to see the entire diff)
Ran: generic/317
Failures: generic/317


Is Paragon Software willing to commit to fixing these and other bugs?
Better yet, it would be nice if Paragon Software could improve its
testing and other QA processes.

Furthermore, container developers should note that ntfs3 is not
currently safe for use with containers.

   	   	    	       	      - Ted

Re: [Linux-NTFS-Dev] [PATCH v27 00/10] NTFS read-write driver GPL implementation by Paragon Software

[Theodore Ts'o <ty...@mi...>]

On Thu, Jul 29, 2021 at 09:24:59AM -0700, Darrick J. Wong wrote:
> 
> I have the same (still unanswered) questions as last time:
> 
> 1. What happens when you run ntfs3 through fstests with '-g all'?  I get
> that the pass rate isn't going to be as high with ntfs3 as it is with
> ext4/xfs/btrfs, but fstests can be adapted (see the recent attempts to
> get exfat under test).

Indeed, it's not that hard at all.  I've included a patch to
xfstests-bld[1] so that you can just run "kvm-xfstests -c ntfs3 -g
auto".

Konstantin, I would *strongly* encourage you to try running fstests,
about 60 seconds into a run, we discover that generic/013 will trigger
locking problems that could lead to deadlocks.

The test generic/091 will also trigger kernel NULL dereference BUG:

BUG: kernel NULL pointer dereference, address: 0000000000000008
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0 
Oops: 0000 [#1] SMP NOPTI
CPU: 0 PID: 23029 Comm: fsx Not tainted 5.14.0-rc2-xfstests-00010-gdf9570
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/4
RIP: 0010:__bio_add_page+0x46/0x80
Code: 39 47 5a 76 3d 41 89 d0 41 f7 d0 44 39 47 28 77 31 48 89 30 89 48 5
RSP: 0018:ffffa3fa05e13900 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000001000 RCX: 0000000000000000
RDX: 0000000000001000 RSI: 0000000000000000 RDI: ffff908b8f930b40
RBP: ffff908b8f930b40 R08: 00000000ffffefff R09: 0000000000000000
R10: ffffffffa4973270 R11: 0000000000000002 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS:  00007f04a8ba2740(0000) GS:ffff908bfda00000(0000) knlGS:0000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 0000000010984005 CR4: 0000000000770ef0
PKRU: 55555554
Call Trace:
 bio_add_page+0x62/0x90
 submit_bh_wbc+0xe3/0x190
 ll_rw_block+0xaa/0xb0
 ntfs_get_block_vbo+0x305/0x430
 do_direct_IO+0x3af/0xa20
 do_blockdev_direct_IO+0x2b7/0x960
 ? ntfs_get_block_write_begin+0x20/0x20
 ? ntfs_get_block_write_begin+0x20/0x20
 ? end_buffer_read_nobh+0x30/0x30
 ntfs_direct_IO+0xe5/0x1f0
 ? touch_atime+0x36/0x250
 generic_file_read_iter+0x8c/0x170
 generic_file_splice_read+0xfc/0x1b0
 splice_direct_to_actor+0xc3/0x230
 ? do_splice_to+0xc0/0xc0
 do_splice_direct+0x91/0xd0
 vfs_copy_file_range+0x144/0x450
 __do_sys_copy_file_range+0xc1/0x200
 do_syscall_64+0x38/0x90
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7f04a8c98f59
Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 8
RSP: 002b:00007ffc8a2202b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000146
RAX: ffffffffffffffda RBX: 000000000000d000 RCX: 00007f04a8c98f59
RDX: 0000000000000003 RSI: 00007ffc8a220300 RDI: 0000000000000003
RBP: 0000000000000000 R08: 000000000000d000 R09: 0000000000000000
R10: 00007ffc8a220308 R11: 0000000000000246 R12: 00007ffc8a220300
R13: 00007ffc8a220308 R14: 000000000000d000 R15: 000000000004c000
CR2: 0000000000000008
---[ end trace 1412a19831693976 ]---

It should also be noted that there doesn't appear to be an fsck for
ntfs --- there is ntfsfix in the ntfs-3g package but it's a full
replacement for chkdsk, and it will often throw up its hands, and tell
you to boot into Windows and run CHKDSK.  To be fair, this is also
true for the fuse-based ntfs implementation --- but at least the
fuse-based ntfs implementation won't deadlock your kernel or OOPS the
kernel with null pointer dereferences....  :-)

> 
> In case you're wondering why I ask these questions, my motivation is
> in figuring out how easy it will be to extend QA coverage to the
> community supported QA suite (fstests) so that people making treewide
> and vfs level changes can check that their changes don't bitrot your
> driver, and vice-versa.  My primary interest leans towards convincing
> everyone to value QA and practice it regularly (aka sharing the load so
> it's not entirely up to the maintainer to catch all problems) vs.
> finding every coding error as a gate condition for merging.

There are some changes that I've identified to make fstests support
fstests more cleanly.  But the real problem is the very weak level of
userspace tools available for NTFS today.  Is this something that
Paragon Software is planning on remedying?

						- Ted

Note: this isn't ready for prime-time yet, since the way I've hacked
up /sbin/mkfs.ntfs3 causes gce-xfstests to fail.  So this isn't going
to be going to xfsteests-bld upstream just yet.  But it's good enough
to make kvm-xfstests work....

Support for the fuse-based ntfs is also not complete for kvm-xfstests,
although the config files for ntfs didn't take that much time to do at
the same time.  Support for the fuse-based ntfs will require some
changes to _fs_type in common/rc so that fstests won't barf because
when you mount -t ntfs, /proc/mounts and df -T show a file system type
of "fuseblk".  What I've done so far was just a quick hack, because I
was curious how ready for prime-time ntfs3 might currently be.  :-)
But it does demonstrate how easy it is to run fstests on ntfs3.  The
hard part will be fixing all of the bugs that it uncovers --- but
better that you discover them now, rather than your customers (not to
mention the customers for all of us who work for various Linux
distributions and hyperscale cloud companies!).


commit c2899d9c0251078d9088b44cc7c583c192edd8a4
Author: Theodore Ts'o <ty...@mi...>
Date:   Sun Aug 1 20:47:35 2021 -0400

    test-appliance: add support for ntfs and ntfs3 file systems
    
    Signed-off-by: Theodore Ts'o <ty...@mi...>

diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/all.list b/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/all.list
new file mode 100644
index 0000000..4ad96d5
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/all.list
@@ -0,0 +1 @@
+default
diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/default b/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/default
new file mode 100644
index 0000000..8280c69
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs/cfg/default
@@ -0,0 +1,4 @@
+SIZE=small
+export MKFS_OPTIONS=""
+export NTFS_MOUNT_OPTIONS=""
+TESTNAME="ntfs"
diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs/config b/kvm-xfstests/test-appliance/files/root/fs/ntfs/config
new file mode 100644
index 0000000..bee23a5
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs/config
@@ -0,0 +1,64 @@
+#
+# Configuration file for ntfs
+#
+
+DEFAULT_MKFS_OPTIONS=""
+
+function check_filesystem()
+{
+    local dev="$1"
+    local ret
+
+    /bin/ntfsfix "$dev"
+    ret="$?"
+    echo ntfsfix exited with status "$ret"
+    return "$ret"
+}
+
+function format_filesystem()
+{
+    local dev="$1"
+    local opts="$2"
+    local ret
+
+    /sbin/mkfs.ntfs -f $opts "$dev"
+    ret="$?"
+    return "$ret"
+}
+
+function setup_mount_opts()
+{
+    if test -n "$MNTOPTS" ; then
+	if test -n "$NTFS_MOUNT_OPTIONS" ; then
+            export NTFS_MOUNT_OPTIONS="$MOUNT_OPTIONS,$MNTOPTS"
+	else
+	    export NTFS_MOUNT_OPTIONS="-o $MNTOPTS"
+	fi
+    fi
+}
+
+function get_mkfs_opts()
+{
+    echo "$NTFS_MKFS_OPTIONS"
+}
+
+function show_mkfs_opts()
+{
+    echo NTFS_MKFS_OPTIONS: "$NTFS_MKFS_OPTIONS"
+}
+
+function show_mount_opts()
+{
+    echo NTFS_MOUNT_OPTIONS: "NTFS_MOUNT_OPTIONS"
+}
+
+function test_name_alias()
+{
+    echo "$1"
+}
+
+function reset_vars()
+{
+    unset NTFS_MOUNT_OPTIONS
+    unset MKFS_OPTIONS
+}
diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/all.list b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/all.list
new file mode 100644
index 0000000..4ad96d5
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/all.list
@@ -0,0 +1 @@
+default
diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/default b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/default
new file mode 100644
index 0000000..8ba5d07
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/cfg/default
@@ -0,0 +1,4 @@
+SIZE=small
+export MKFS_OPTIONS=""
+export NTFS3_MOUNT_OPTIONS=""
+TESTNAME="ntfs3"
diff --git a/kvm-xfstests/test-appliance/files/root/fs/ntfs3/config b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/config
new file mode 100644
index 0000000..6f67e12
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/root/fs/ntfs3/config
@@ -0,0 +1,64 @@
+#
+# Configuration file for ntfs3
+#
+
+DEFAULT_MKFS_OPTIONS=""
+
+function check_filesystem()
+{
+    local dev="$1"
+    local ret
+
+    /bin/ntfsfix "$dev"
+    ret="$?"
+    echo ntfsfix exited with status "$ret"
+    return "$ret"
+}
+
+function format_filesystem()
+{
+    local dev="$1"
+    local opts="$2"
+    local ret
+
+    /sbin/mkfs.ntfs -f $opts "$dev"
+    ret="$?"
+    return "$ret"
+}
+
+function setup_mount_opts()
+{
+    if test -n "$MNTOPTS" ; then
+	if test -n "$NTFS3_MOUNT_OPTIONS" ; then
+            export NTFS3_MOUNT_OPTIONS="$MOUNT_OPTIONS,$MNTOPTS"
+	else
+	    export NTFS3_MOUNT_OPTIONS="-o $MNTOPTS"
+	fi
+    fi
+}
+
+function get_mkfs_opts()
+{
+    echo "$NTFS3_MKFS_OPTIONS"
+}
+
+function show_mkfs_opts()
+{
+    echo NTFS3_MKFS_OPTIONS: "$NTFS3_MKFS_OPTIONS"
+}
+
+function show_mount_opts()
+{
+    echo NTFS3_MOUNT_OPTIONS: "NTFS3_MOUNT_OPTIONS"
+}
+
+function test_name_alias()
+{
+    echo "$1"
+}
+
+function reset_vars()
+{
+    unset NTFS3_MOUNT_OPTIONS
+    unset MKFS_OPTIONS
+}
diff --git a/kvm-xfstests/test-appliance/files/sbin/mkfs.ntfs3 b/kvm-xfstests/test-appliance/files/sbin/mkfs.ntfs3
new file mode 100755
index 0000000..f6657a6
--- /dev/null
+++ b/kvm-xfstests/test-appliance/files/sbin/mkfs.ntfs3
@@ -0,0 +1,2 @@
+#!/bin/sh
+/sbin/mkfs.ntfs -f $*
diff --git a/kvm-xfstests/test-appliance/gce-xfstests-bld.sh b/kvm-xfstests/test-appliance/gce-xfstests-bld.sh
index befb105..48ce713 100644
--- a/kvm-xfstests/test-appliance/gce-xfstests-bld.sh
+++ b/kvm-xfstests/test-appliance/gce-xfstests-bld.sh
@@ -73,6 +73,7 @@ PACKAGES="bash-completion \
 	nbd-server \
 	nfs-common \
 	nfs-kernel-server \
+	ntfs-3g \
 	nvme-cli \
 	openssl \
 	pciutils \
diff --git a/kvm-xfstests/test-appliance/xfstests-packages b/kvm-xfstests/test-appliance/xfstests-packages
index 85ca6a6..6bb8432 100644
--- a/kvm-xfstests/test-appliance/xfstests-packages
+++ b/kvm-xfstests/test-appliance/xfstests-packages
@@ -33,6 +33,7 @@ mtd-utils
 multipath-tools
 nbd-client
 nbd-server
+ntfs-3g
 nvme-cli
 parted
 perl

[Linux-NTFS-Dev] [PATCH] fs/ntfs: delete unused header file

[Yanbo Q. <qia...@16...>]

The linux/time.h file is referenced using the
current_kernel_time() function.The current_kernel_time()
was moved from fs/ntfs/time.h, so delete the header file.

Signed-off-by: Yanbo Qiao <qia...@16...>
Signed-off-by: Hui Su <su...@ze...>
---
 fs/ntfs/time.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ntfs/time.h b/fs/ntfs/time.h
index 6b63261300cc..2c92abb5d8d2 100644
--- a/fs/ntfs/time.h
+++ b/fs/ntfs/time.h
@@ -8,7 +8,6 @@
 #ifndef _LINUX_NTFS_TIME_H
 #define _LINUX_NTFS_TIME_H
 
-#include <linux/time.h>		/* For current_kernel_time(). */
 #include <asm/div64.h>		/* For do_div(). */
 
 #include "endian.h"
-- 
2.30.2

Re: [Linux-NTFS-Dev] [PATCH v27 02/10] fs/ntfs3: Add initialization of super block

[Christophe J. <chr...@wa...>]

Hi,

below are a few comments based on a cppcheck run.
Don't take it too seriously into consideration, this is just some minor 
clean-up.

The only one that may look interested is in 'indx_find()'

CJ


Le 29/07/2021 à 15:49, Konstantin Komarov a écrit :
> This adds initialization of super block
> 
> Signed-off-by: Konstantin Komarov <alm...@pa...>
> ---
>   fs/ntfs3/fsntfs.c | 2542 +++++++++++++++++++++++++++++++++++++++++++
>   fs/ntfs3/index.c  | 2641 +++++++++++++++++++++++++++++++++++++++++++++
>   fs/ntfs3/inode.c  | 2034 ++++++++++++++++++++++++++++++++++
>   fs/ntfs3/super.c  | 1500 +++++++++++++++++++++++++
>   4 files changed, 8717 insertions(+)
>   create mode 100644 fs/ntfs3/fsntfs.c
>   create mode 100644 fs/ntfs3/index.c
>   create mode 100644 fs/ntfs3/inode.c
>   create mode 100644 fs/ntfs3/super.c
> 
> diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
> new file mode 100644
> index 000000000..327356b08
> --- /dev/null
> +++ b/fs/ntfs3/fsntfs.c

[...]

> +int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len,
> +			     CLST *new_lcn, CLST *new_len,
> +			     enum ALLOCATE_OPT opt)
> +{

[...]

> +
> +	if (zlen <= NTFS_MIN_MFT_ZONE)
> +		goto no_space;
> +
> +	/* How many clusters to cat from zone */
> +	zlcn = wnd_zone_bit(wnd);
> +	zlen2 = zlen >> 1;
> +	ztrim = len > zlen ? zlen : (len > zlen2 ? len : zlen2);
> +	new_zlen = zlen - ztrim;
> +
> +	if (new_zlen < NTFS_MIN_MFT_ZONE) {
> +		new_zlen = NTFS_MIN_MFT_ZONE;
> +		if (new_zlen > zlen)
> +			new_zlen = zlen;

Unless I missed something, 'zlen' is known to be > NTFS_MIN_MFT_ZONE 
here (see a few lines above).
And, if this 'if' is taken, 'new_zlen' is <= NTFS_MIN_MFT_ZONE.

So this test can never match and can be removed. (or removed by a 
comment if it makes sense)

> +	}
> +
> +	wnd_zone_set(wnd, zlcn, new_zlen);
> +
> +	/* allocate continues clusters */
> +	*new_len =
> +		wnd_find(wnd, len, 0,
> +			 BITMAP_FIND_MARK_AS_USED | BITMAP_FIND_FULL, &a_lcn);

[...]

> diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
> new file mode 100644
> index 000000000..931a7241e
> --- /dev/null
> +++ b/fs/ntfs3/index.c
> @@ -0,0 +1,2641 @@

[...]

> +static const struct NTFS_DE *hdr_find_split(const struct INDEX_HDR *hdr)
> +{
> +	size_t o;
> +	const struct NTFS_DE *e = hdr_first_de(hdr);
> +	u32 used_2 = le32_to_cpu(hdr->used) >> 1;
> +	u16 esize = le16_to_cpu(e->size);

e is NULL check the line after.

> +
> +	if (!e || de_is_last(e))
> +		return NULL;
> +
> +	for (o = le32_to_cpu(hdr->de_off) + esize; o < used_2; o += esize) {
> +		const struct NTFS_DE *p = e;
> +
> +		e = Add2Ptr(hdr, o);
> +
> +		/* We must not return END entry */
> +		if (de_is_last(e))
> +			return p;
> +
> +		esize = le16_to_cpu(e->size);
> +	}
> +
> +	return e;
> +}

[...]

> +int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni,
> +	      const struct INDEX_ROOT *root, const void *key, size_t key_len,
> +	      const void *ctx, int *diff, struct NTFS_DE **entry,
> +	      struct ntfs_fnd *fnd)
> +{
> +	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;
> +	}
> +
> +	hdr = &root->ihdr;
> +
> +	/* Check cache */
> +	e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de;
> +	if (e && !de_is_last(e) &&
> +	    !(*indx->cmp)(key, key_len, e + 1, le16_to_cpu(e->key_size), ctx)) {
> +		*entry = e;
> +		*diff = 0;
> +		return 0;
> +	}
> +
> +	/* Soft finder reset */
> +	fnd_clear(fnd);
> +
> +	/* Lookup entry that is <= to the search value */
> +	e = hdr_find_e(indx, hdr, key, key_len, ctx, diff);
> +	if (!e)
> +		return -EINVAL;
> +
> +	if (fnd)

This NULL check looks spurious because 'fnd' has already been 
dereferenced several times at this point.
Either it is useless, either there is some trouble elsewhere.

> +		fnd->root_de = e;
> +
> +	err = 0;
> +

[...]

> +static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
> +				CLST *vbn)
> +{
> +	int err = -ENOMEM;

This initialization is overwritten below.
It can be removed.

> +	struct ntfs_sb_info *sbi = ni->mi.sbi;
> +	struct ATTRIB *bitmap;
> +	struct ATTRIB *alloc;
> +	u32 data_size = 1u << indx->index_bits;
> +	u32 alloc_size = ntfs_up_cluster(sbi, data_size);
> +	CLST len = alloc_size >> sbi->cluster_bits;
> +	const struct INDEX_NAMES *in = &s_index_names[indx->type];
> +	CLST alen;
> +	struct runs_tree run;
> +
> +	run_init(&run);
> +
> +	err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, 0, &alen, 0,
> +				     NULL);

here

> +	if (err)
> +		goto out;
> +
> +	err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len,
> +				    &run, 0, len, 0, &alloc, NULL);

[...]

> diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
> new file mode 100644
> index 000000000..c56343124
> --- /dev/null
> +++ b/fs/ntfs3/super.c

[...]

> +static int ntfs_sync_fs(struct super_block *sb, int wait)
> +{
> +	int err = 0, err2;
> +	struct ntfs_sb_info *sbi = sb->s_fs_info;
> +	struct ntfs_inode *ni;
> +	struct inode *inode;
> +
> +	ni = sbi->security.ni;
> +	if (ni) {
> +		inode = &ni->vfs_inode;
> +		err2 = _ni_write_inode(inode, wait);
> +		if (err2 && !err)

'err' is known to be 0 here, so this test can be simplified.

> +			err = err2;
> +	}
> +
> +	ni = sbi->objid.ni;
> +	if (ni) {
> +		inode = &ni->vfs_inode;
> +		err2 = _ni_write_inode(inode, wait);
> +		if (err2 && !err)
> +			err = err2;
> +	}

[...]

Re: [Linux-NTFS-Dev] [PATCH v27 03/10] fs/ntfs3: Add bitmap

[Christophe J. <chr...@wa...>]

Le 29/07/2021 à 15:49, Konstantin Komarov a écrit :
> This adds bitmap
> 
> Signed-off-by: Konstantin Komarov <alm...@pa...>
> ---
>   fs/ntfs3/bitfunc.c |  135 ++++
>   fs/ntfs3/bitmap.c  | 1519 ++++++++++++++++++++++++++++++++++++++++++++
>   2 files changed, 1654 insertions(+)
>   create mode 100644 fs/ntfs3/bitfunc.c
>   create mode 100644 fs/ntfs3/bitmap.c
> 
> diff --git a/fs/ntfs3/bitfunc.c b/fs/ntfs3/bitfunc.c
> new file mode 100644
> index 000000000..2de5faef2
> --- /dev/null
> +++ b/fs/ntfs3/bitfunc.c

[...]

> +bool are_bits_set(const ulong *lmap, size_t bit, size_t nbits)
> +{
> +	u8 mask;
> +	size_t pos = bit & 7;
> +	const u8 *map = (u8 *)lmap + (bit >> 3);
> +
> +	if (pos) {
> +		if (8 - pos >= nbits) {
> +			mask = fill_mask[pos + nbits] & zero_mask[pos];
> +			return !nbits || (*map & mask) == mask;
> +		}
> +
> +		mask = zero_mask[pos];
> +		if ((*map++ & mask) != mask)
> +			return false;
> +		nbits -= 8 - pos;
> +	}
> +
> +	pos = ((size_t)map) & (sizeof(size_t) - 1);
> +	if (pos) {
> +		pos = sizeof(size_t) - pos;
> +		if (nbits >= pos * 8) {
> +			for (nbits -= pos * 8; pos; pos--, map++) {
> +				if (*map != 0xFF)
> +					return false;
> +			}
> +		}
> +	}
> +
> +	for (pos = nbits / BITS_IN_SIZE_T; pos; pos--, map += sizeof(size_t)) {
> +		if (*((size_t *)map) != MINUS_ONE_T)
> +			return false;
> +	}
> +
> +	for (pos = (nbits % BITS_IN_SIZE_T) >> 3; pos; pos--, map++) {
> +		if (*map != 0xFF)
> +			return false;
> +	}
> +
> +	pos = nbits & 7;
> +	if (pos) {
> +		u8 mask = fill_mask[pos];

There is no need to define a new 'mask' variable here, it just shadows 
the already existing one. 'u8' can be removed.

> +
> +		if ((*map & mask) != mask)
> +			return false;
> +	}
> +
> +	// All bits are ones
> +	return true;
> +}
> diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
> new file mode 100644
> index 000000000..32aab0031
> --- /dev/null
> +++ b/fs/ntfs3/bitmap.c

[...]

> +bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
> +{
> +	bool ret = false;
> +	struct super_block *sb = wnd->sb;
> +	size_t iw = bit >> (sb->s_blocksize_bits + 3);
> +	u32 wbits = 8 * sb->s_blocksize;
> +	u32 wbit = bit & (wbits - 1);
> +	size_t end;
> +	struct rb_node *n;
> +	struct e_node *e;
> +
> +	if (RB_EMPTY_ROOT(&wnd->start_tree))
> +		goto use_wnd;
> +
> +	end = bit + bits;
> +	n = rb_lookup(&wnd->start_tree, end - 1);
> +	if (!n)
> +		goto use_wnd;
> +
> +	e = rb_entry(n, struct e_node, start.node);
> +	if (e->start.key + e->count.key > bit)
> +		return false;
> +
> +use_wnd:
> +	while (iw < wnd->nwnd && bits) {
> +		u32 tail, op;
> +
> +		if (unlikely(iw + 1 == wnd->nwnd))
> +			wbits = wnd->bits_last;
> +
> +		tail = wbits - wbit;
> +		op = tail < bits ? tail : bits;
> +
> +		if (wnd->free_bits[iw]) {
> +			bool ret;

This 'ret' shadows the one defined above. It looks spurious and could 
certainly be removed.
However is looks safe because...

> +			struct buffer_head *bh = wnd_map(wnd, iw);
> +
> +			if (IS_ERR(bh))
> +				goto out;
> +
> +			ret = are_bits_set((ulong *)bh->b_data, wbit, op);
> +			put_bh(bh);
> +			if (!ret)
> +				goto out;

... if *this* 'ret' is false, the *other* 'ret' is false as well.

> +		}
> +
> +		bits -= op;
> +		wbit = 0;
> +		iw += 1;
> +	}
> +	ret = true;
> +
> +out:
> +	return ret;
> +}

[...]

Re: [Linux-NTFS-Dev] [PATCH v27 07/10] fs/ntfs3: Add NTFS journal

[Christophe J. <chr...@wa...>]

Hi,

below are a few comments based on a cppcheck run.
Don't take it too seriously into consideration. It could be either some 
useless code that could be removed or some issues in the logic.

It is reported only if a new iteration is done and if it makes sense to 
change something.

CJ

Le 29/07/2021 à 15:49, Konstantin Komarov a écrit :
> This adds NTFS journal
> 
> Signed-off-by: Konstantin Komarov <alm...@pa...>
> ---
>   fs/ntfs3/fslog.c | 5181 ++++++++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 5181 insertions(+)
>   create mode 100644 fs/ntfs3/fslog.c
> 
> diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
> new file mode 100644
> index 000000000..53da12252
> --- /dev/null
> +++ b/fs/ntfs3/fslog.c

[...]

> +/*
> + * last_log_lsn
> + *
> + * This routine walks through the log pages for a file, searching for the
> + * last log page written to the file
> + */
> +static int last_log_lsn(struct ntfs_log *log)
> +{

[...]

> +tail_read:
> +	first_tail = first_tail_prev;
> +	final_off = final_off_prev;
> +
> +	second_tail = second_tail_prev;
> +	second_off = second_off_prev;
> +
> +	page_cnt = page_pos = 1;
> +
> +	curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off)
> +					       : log->next_page;
> +
> +	wrapped_file =
> +		curpage_off == log->first_page &&
> +		!(log->l_flags & (NTFSLOG_NO_LAST_LSN | NTFSLOG_REUSE_TAIL));
> +
> +	expected_seq = wrapped_file ? (log->seq_num + 1) : log->seq_num;
> +
> +	nextpage_off = curpage_off;

This 'nextpage_off' is overwritten a few lines below.
Either it is useless, either there is an issue in the logic.

> +
> +next_page:
> +	tail_page = NULL;
> +	/* Read the next log page */
> +	err = read_log_page(log, curpage_off, &page, &usa_error);
> +
> +	/* Compute the next log page offset the file */
> +	nextpage_off = next_page_off(log, curpage_off);
> +	wrapped = nextpage_off == log->first_page;
here.

> +
> +	if (tails > 1) {
> +		struct RECORD_PAGE_HDR *cur_page =
> +			Add2Ptr(page_bufs, curpage_off - page_off);
> +
> +		if (curpage_off == saved_off) {
> +			tail_page = cur_page;
> +			goto use_tail_page;
> +		}
> +

[...]

> +int log_replay(struct ntfs_inode *ni, bool *initialized)
> +{

[...]

> +
> +	vcn = le64_to_cpu(lrh->target_vcn);
> +	vcn &= ~(log->clst_per_page - 1);
> +

This 'vcn' is overwritten a few lines below.
Either it is useless, either there is an issue in the logic.

> +add_allocated_vcns:
> +	for (i = 0, vcn = le64_to_cpu(lrh->target_vcn),

here

> +	    size = (vcn + 1) << sbi->cluster_bits;
> +	     i < t16; i++, vcn += 1, size += sbi->cluster_size) {
> +		attr = oa->attr;
> +		if (!attr->non_res) {
> +			if (size > le32_to_cpu(attr->res.data_size))
> +				attr->res.data_size = cpu_to_le32(size);
> +		} else {
> +			if (size > le64_to_cpu(attr->nres.data_size))
> +				attr->nres.valid_size = attr->nres.data_size =
> +					attr->nres.alloc_size =
> +						cpu_to_le64(size);
> +		}
> +	}
> +
> +	t16 = le16_to_cpu(lrh->undo_op);
> +	if (can_skip_action(t16))
> +		goto read_next_log_undo_action;
> +
> +	/* Point to the Redo data and get its length */
> +	data = Add2Ptr(lrh, le16_to_cpu(lrh->undo_off));
> +	dlen = le16_to_cpu(lrh->undo_len);
> +
> +	/* it is time to apply the undo action */
> +	err = do_action(log, oe, lrh, t16, data, dlen, rec_len, NULL);

This 'err' is unused.
Maybe there is nothing that we can do, or the error handling is missing.

> +
> +read_next_log_undo_action:
> +	/*
> +	 * Keep reading and looping back until we have read the
> +	 * last record for this transaction
> +	 */
> +	err = read_next_log_rec(log, lcb, &rec_lsn);
> +	if (err)
> +		goto out;
> +

[...]

Re: [Linux-NTFS-Dev] [PATCH v27 04/10] fs/ntfs3: Add file operations and implementation

[Christophe J. <chr...@wa...>]

Le 29/07/2021 à 15:49, Konstantin Komarov a écrit :
> This adds file operations and implementation
> 
> Signed-off-by: Konstantin Komarov <alm...@pa...>
> ---
>   fs/ntfs3/dir.c     |  594 +++++++++
>   fs/ntfs3/file.c    | 1130 ++++++++++++++++
>   fs/ntfs3/frecord.c | 3071 ++++++++++++++++++++++++++++++++++++++++++++
>   fs/ntfs3/namei.c   |  578 +++++++++
>   fs/ntfs3/record.c  |  609 +++++++++
>   fs/ntfs3/run.c     | 1111 ++++++++++++++++
>   6 files changed, 7093 insertions(+)
>   create mode 100644 fs/ntfs3/dir.c
>   create mode 100644 fs/ntfs3/file.c
>   create mode 100644 fs/ntfs3/frecord.c
>   create mode 100644 fs/ntfs3/namei.c
>   create mode 100644 fs/ntfs3/record.c
>   create mode 100644 fs/ntfs3/run.c
> 

[...]

> diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
> new file mode 100644
> index 000000000..f5db12cd3
> --- /dev/null
> +++ b/fs/ntfs3/namei.c

[...]

> +/*
> + * ntfs_rename
> + *
> + * inode_operations::rename
> + */
> +static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
> +		       struct dentry *old_dentry, struct inode *new_dir,
> +		       struct dentry *new_dentry, u32 flags)
> +{
> +	int err;
> +	struct super_block *sb = old_dir->i_sb;
> +	struct ntfs_sb_info *sbi = sb->s_fs_info;
> +	struct ntfs_inode *old_dir_ni = ntfs_i(old_dir);
> +	struct ntfs_inode *new_dir_ni = ntfs_i(new_dir);
> +	struct ntfs_inode *old_ni;
> +	struct ATTR_FILE_NAME *old_name, *new_name, *fname;
> +	u8 name_type;
> +	bool is_same;
> +	struct inode *old_inode, *new_inode;
> +	struct NTFS_DE *old_de, *new_de;
> +	struct ATTRIB *attr;
> +	struct ATTR_LIST_ENTRY *le;
> +	u16 new_de_key_size;
> +
> +	static_assert(SIZEOF_ATTRIBUTE_FILENAME_MAX + SIZEOF_RESIDENT < 1024);
> +	static_assert(SIZEOF_ATTRIBUTE_FILENAME_MAX + sizeof(struct NTFS_DE) <
> +		      1024);
> +	static_assert(PATH_MAX >= 4 * 1024);
> +
> +	if (flags & ~RENAME_NOREPLACE)
> +		return -EINVAL;
> +
> +	old_inode = d_inode(old_dentry);
> +	new_inode = d_inode(new_dentry);
> +
> +	old_ni = ntfs_i(old_inode);
> +
> +	is_same = old_dentry->d_name.len == new_dentry->d_name.len &&
> +		  !memcmp(old_dentry->d_name.name, new_dentry->d_name.name,
> +			  old_dentry->d_name.len);
> +
> +	if (is_same && old_dir == new_dir) {
> +		/* Nothing to do */
> +		err = 0;
> +		goto out;
> +	}
> +
> +	if (ntfs_is_meta_file(sbi, old_inode->i_ino)) {
> +		err = -EINVAL;
> +		goto out;
> +	}
> +
> +	if (new_inode) {
> +		/*target name exists. unlink it*/
> +		dget(new_dentry);
> +		ni_lock_dir(new_dir_ni);
> +		err = ntfs_unlink_inode(new_dir, new_dentry);
> +		ni_unlock(new_dir_ni);
> +		dput(new_dentry);
> +		if (err)
> +			goto out;
> +	}
> +
> +	/* allocate PATH_MAX bytes */
> +	old_de = __getname();
> +	if (!old_de) {
> +		err = -ENOMEM;
> +		goto out;
> +	}
> +
> +	err = fill_name_de(sbi, old_de, &old_dentry->d_name, NULL);
> +	if (err < 0)
> +		goto out1;
> +
> +	old_name = (struct ATTR_FILE_NAME *)(old_de + 1);
> +
> +	if (is_same) {
> +		new_de = old_de;
> +	} else {
> +		new_de = Add2Ptr(old_de, 1024);
> +		err = fill_name_de(sbi, new_de, &new_dentry->d_name, NULL);
> +		if (err < 0)
> +			goto out1;
> +	}
> +
> +	ni_lock_dir(old_dir_ni);
> +	ni_lock(old_ni);
> +
> +	mi_get_ref(&old_dir_ni->mi, &old_name->home);
> +
> +	/*get pointer to file_name in mft*/
> +	fname = ni_fname_name(old_ni, (struct cpu_str *)&old_name->name_len,
> +			      &old_name->home, &le);
> +	if (!fname) {
> +		err = -EINVAL;
> +		goto out2;
> +	}
> +
> +	/* Copy fname info from record into new fname */
> +	new_name = (struct ATTR_FILE_NAME *)(new_de + 1);
> +	memcpy(&new_name->dup, &fname->dup, sizeof(fname->dup));
> +
> +	name_type = paired_name(fname->type);
> +
> +	/* remove first name from directory */
> +	err = indx_delete_entry(&old_dir_ni->dir, old_dir_ni, old_de + 1,
> +				le16_to_cpu(old_de->key_size), sbi);
> +	if (err)
> +		goto out3;
> +
> +	/* remove first name from mft */
> +	err = ni_remove_attr_le(old_ni, attr_from_name(fname), le);
> +	if (err)
> +		goto out4;
> +
> +	le16_add_cpu(&old_ni->mi.mrec->hard_links, -1);
> +	old_ni->mi.dirty = true;
> +
> +	if (name_type != FILE_NAME_POSIX) {
> +		/* get paired name */
> +		fname = ni_fname_type(old_ni, name_type, &le);
> +		if (fname) {
> +			/* remove second name from directory */
> +			err = indx_delete_entry(&old_dir_ni->dir, old_dir_ni,
> +						fname, fname_full_size(fname),
> +						sbi);
> +			if (err)
> +				goto out5;
> +
> +			/* remove second name from mft */
> +			err = ni_remove_attr_le(old_ni, attr_from_name(fname),
> +						le);
> +			if (err)
> +				goto out6;
> +
> +			le16_add_cpu(&old_ni->mi.mrec->hard_links, -1);
> +			old_ni->mi.dirty = true;
> +		}
> +	}
> +
> +	/* Add new name */
> +	mi_get_ref(&old_ni->mi, &new_de->ref);
> +	mi_get_ref(&ntfs_i(new_dir)->mi, &new_name->home);
> +
> +	new_de_key_size = le16_to_cpu(new_de->key_size);
> +
> +	/* insert new name in mft */
> +	err = ni_insert_resident(old_ni, new_de_key_size, ATTR_NAME, NULL, 0,
> +				 &attr, NULL);
> +	if (err)
> +		goto out7;
> +
> +	attr->res.flags = RESIDENT_FLAG_INDEXED;
> +
> +	memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), new_name, new_de_key_size);
> +
> +	le16_add_cpu(&old_ni->mi.mrec->hard_links, 1);
> +	old_ni->mi.dirty = true;
> +
> +	/* insert new name in directory */
> +	err = indx_insert_entry(&new_dir_ni->dir, new_dir_ni, new_de, sbi,
> +				NULL);
> +	if (err)
> +		goto out8;
> +
> +	if (IS_DIRSYNC(new_dir))
> +		err = ntfs_sync_inode(old_inode);

This value returned by 'ntfs_sync_inode()' is silenced below.
Maybe the same should be done here?
Anyway, this 'err' is never used and is forced to 0 below

> +	else
> +		mark_inode_dirty(old_inode);
> +
> +	old_dir->i_ctime = old_dir->i_mtime = current_time(old_dir);
> +	if (IS_DIRSYNC(old_dir))
> +		(void)ntfs_sync_inode(old_dir);

here

> +	else
> +		mark_inode_dirty(old_dir);
> +
> +	if (old_dir != new_dir) {
> +		new_dir->i_mtime = new_dir->i_ctime = old_dir->i_ctime;
> +		mark_inode_dirty(new_dir);
> +	}
> +
> +	if (old_inode) {
> +		old_inode->i_ctime = old_dir->i_ctime;
> +		mark_inode_dirty(old_inode);
> +	}
> +
> +	err = 0;

and here.

> +	/* normal way */
> +	goto out2;
> +
> +out8:
> +	/* undo
> +	 * ni_insert_resident(old_ni, new_de_key_size, ATTR_NAME, NULL, 0,
> +	 *			 &attr, NULL);
> +	 */
> +	mi_remove_attr(&old_ni->mi, attr);
> +out7:
> +	/* undo
> +	 * ni_remove_attr_le(old_ni, attr_from_name(fname), le);
> +	 */
> +out6:
> +	/* undo
> +	 * indx_delete_entry(&old_dir_ni->dir, old_dir_ni,
> +	 *					fname, fname_full_size(fname),
> +	 *					sbi);
> +	 */
> +out5:
> +	/* undo
> +	 * ni_remove_attr_le(old_ni, attr_from_name(fname), le);
> +	 */
> +out4:
> +	/* undo:
> +	 * indx_delete_entry(&old_dir_ni->dir, old_dir_ni, old_de + 1,
> +	 *			old_de->key_size, NULL);
> +	 */
> +out3:
> +out2:
> +	ni_unlock(old_ni);
> +	ni_unlock(old_dir_ni);
> +out1:
> +	__putname(old_de);
> +out:
> +	return err;
> +}

[...]

Re: [Linux-NTFS-Dev] [PATCH v27 05/10] fs/ntfs3: Add attrib operations

[Christophe J. <chr...@wa...>]

Hi,

below are a few comments based on a cppcheck run.
Don't take it too seriously into consideration, this is just a minor 
clean-up.

It is reported only if a new iteration is done and if it makes sense to 
include it.

CJ

Le 29/07/2021 à 15:49, Konstantin Komarov a écrit :
> This adds attrib operations
> 
> Signed-off-by: Konstantin Komarov <alm...@pa...>
> ---
>   fs/ntfs3/attrib.c   | 2082 +++++++++++++++++++++++++++++++++++++++++++
>   fs/ntfs3/attrlist.c |  456 ++++++++++
>   fs/ntfs3/xattr.c    | 1046 ++++++++++++++++++++++
>   3 files changed, 3584 insertions(+)
>   create mode 100644 fs/ntfs3/attrib.c
>   create mode 100644 fs/ntfs3/attrlist.c
>   create mode 100644 fs/ntfs3/xattr.c
> 
> diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
> new file mode 100644
> index 000000000..bca85e7b6
> --- /dev/null
> +++ b/fs/ntfs3/attrib.c

[...]

> +/*
> + * load runs for given range [from to)
> + */
> +int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
> +			 const __le16 *name, u8 name_len, struct runs_tree *run,
> +			 u64 from, u64 to)
> +{
> +	struct ntfs_sb_info *sbi = ni->mi.sbi;
> +	u8 cluster_bits = sbi->cluster_bits;
> +	CLST vcn = from >> cluster_bits;

This initialization is overwritten in the for loop below.
It can be removed.

> +	CLST vcn_last = (to - 1) >> cluster_bits;
> +	CLST lcn, clen;
> +	int err;
> +
> +	for (vcn = from >> cluster_bits; vcn <= vcn_last; vcn += clen) {

here

> +		if (!run_lookup_entry(run, vcn, &lcn, &clen, NULL)) {
> +			err = attr_load_runs_vcn(ni, type, name, name_len, run,
> +						 vcn);
> +			if (err)
> +				return err;
> +			clen = 0; /*next run_lookup_entry(vcn) must be success*/
> +		}
> +	}
> +
> +	return 0;
> +}

[...]

Re: [Linux-NTFS-Dev] [PATCH v27 00/10] NTFS read-write driver GPL implementation by Paragon Software

[Darrick J. W. <dj...@ke...>]

On Thu, Jul 29, 2021 at 04:49:33PM +0300, Konstantin Komarov wrote:
> This patch adds NTFS Read-Write driver to fs/ntfs3.
> 
> Having decades of expertise in commercial file systems development and huge
> test coverage, we at Paragon Software GmbH want to make our contribution to
> the Open Source Community by providing implementation of NTFS Read-Write
> driver for the Linux Kernel.
> 
> This is fully functional NTFS Read-Write driver. Current version works with
> NTFS(including v3.1) and normal/compressed/sparse files and supports journal replaying.
> 
> We plan to support this version after the codebase once merged, and add new
> features and fix bugs. For example, full journaling support over JBD will be
> added in later updates.

Cool!

I have the same (still unanswered) questions as last time:

1. What happens when you run ntfs3 through fstests with '-g all'?  I get
that the pass rate isn't going to be as high with ntfs3 as it is with
ext4/xfs/btrfs, but fstests can be adapted (see the recent attempts to
get exfat under test).

(And yes, not all the fstests will pass, since some of them are random
exercisers that we use to keep the bug backlog populated.  We can help
you figure out which tests are erratic like that).

2. Same question as #1, except for whatever internal QA suite Paragon
has used to qualify the ntfs3 driver over the years.  (If you haven't
been using fstests this whole time.)

3. If you (Paragon) do have an internal QA suite, are you willing to
contribute some of that to fstests to improve its ability to exercise
whatever features and quirks are unique to NTFS?

4. How often do you run QA validation (of any kind) on the ntfs3
codebase?

In case you're wondering why I ask these questions, my motivation is
in figuring out how easy it will be to extend QA coverage to the
community supported QA suite (fstests) so that people making treewide
and vfs level changes can check that their changes don't bitrot your
driver, and vice-versa.  My primary interest leans towards convincing
everyone to value QA and practice it regularly (aka sharing the load so
it's not entirely up to the maintainer to catch all problems) vs.
finding every coding error as a gate condition for merging.

As another fs maintainer, I know that this is key to preventing fs
drivers from turning into a rotting garbage fire, and probably the best
I can do for a review of ntfs3 since I don't anticipate having time for
a super-detailed review and you've been submitting this driver for a
while now.

--D

> 
> v2:
>  - patch splitted to chunks (file-wise)
>  - build issues fixed
>  - sparse and checkpatch.pl errors fixed
>  - NULL pointer dereference on mkfs.ntfs-formatted volume mount fixed
>  - cosmetics + code cleanup
> 
> v3:
>  - added acl, noatime, no_acs_rules, prealloc mount options
>  - added fiemap support
>  - fixed encodings support
>  - removed typedefs
>  - adapted Kernel-way logging mechanisms
>  - fixed typos and corner-case issues
> 
> v4:
>  - atomic_open() refactored
>  - code style updated
>  - bugfixes
> 
> v5:
> - nls/nls_alt mount options added
> - Unicode conversion fixes
> - Improved very fragmented files operations
> - logging cosmetics
> 
> v6:
> - Security Descriptors processing changed
>   added system.ntfs_security xattr to set
>   SD
> - atomic_open() optimized
> - cosmetics
> 
> v7:
> - Security Descriptors validity checks added (by Mark Harmstone)
> - atomic_open() fixed for the compressed file creation with directio
>   case
> - remount support
> - temporarily removed readahead usage
> - cosmetics
> 
> v8:
> - Compressed files operations fixed
> 
> v9:
> - Further cosmetics applied as suggested
> by Joe Perches
> 
> v10:
> - operations with compressed/sparse files on very fragmented volumes improved
> - reduced memory consumption for above cases
> 
> v11:
> - further compressed files optimizations: reads/writes are now skipping bufferization
> - journal wipe to the initial state optimized (bufferization is also skipped)
> - optimized run storage (re-packing cluster metainformation)
> - fixes based on Matthew Wilcox feedback to the v10
> - compressed/sparse/normal could be set for empty files with 'system.ntfs_attrib' xattr
> 
> v12:
> - nls_alt mount option removed after discussion with Pali Rohar
> - fixed ni_repack()
> - fixed resident files transition to non-resident when size increasing
> 
> v13:
> - nested_lock fix (lockdep)
> - out-of-bounds read fix (KASAN warning)
> - resident->nonresident transition fixed for compressed files
> - load_nls() missed fix applied
> - some sparse utility warnings fixes
> 
> v14:
> - support for additional compression types (we've adapted WIMLIB's
>   implementation, authored by Eric Biggers, into ntfs3)
> 
> v15:
> - kernel test robot warnings fixed
> - lzx/xpress compression license headers updated
> 
> v16:
> - lzx/xpress moved to initial ntfs-3g plugin code
> - mutexes instead of a global spinlock for compresions
> - FALLOC_FL_PUNCH_HOLE and FALLOC_FL_COLLAPSE_RANGE implemented
> - CONFIG_NTFS3_FS_POSIX_ACL added
> 
> v17:
> - FALLOC_FL_COLLAPSE_RANGE fixed
> - fixes for Mattew Wilcox's and Andy Lavr's concerns
> 
> v18:
> - ntfs_alloc macro splitted into two ntfs_malloc + ntfs_zalloc
> - attrlist.c: always use ntfs_cmp_names instead of memcmp; compare entry names
>   only for entry with vcn == 0
> - dir.c: remove unconditional ni_lock in ntfs_readdir
> - fslog.c: corrected error case behavior
> - index.c: refactored due to modification of ntfs_cmp_names; use rw_semaphore
>   for read/write access to alloc_run and bitmap_run while ntfs_readdir
> - run.c: separated big/little endian code in functions
> - upcase.c: improved ntfs_cmp_names, thanks to Kari Argillander for idea
>   and 'bothcase' implementation
> 
> v19:
> - fixed directory bitmap for 2MB cluster size
> - fixed rw_semaphore init for directories
> 
> v20:
> - fixed issue with incorrect hidden/system attribute setting on
>   root subdirectories
> - use kvmalloc instead of kmalloc for runs array
> - fixed index behavior on volumes with cluster size more than 4k
> - current build info is added into module info instead of printing on insmod
> 
> v21:
> - fixes for clang CFI checks
> - fixed sb->s_maxbytes for 32bit clusters
> - user.DOSATTRIB is no more intercepted by ntfs3
> - corrected xattr limits;  is used
> - corrected CONFIG_NTFS3_64BIT_CLUSTER usage
> - info about current build is added into module info and printing
> on insmod (by Andy Lavr's request)
> note: v21 is applicable for 'linux-next' not older than 2021.01.28
> 
> v22:
> - ntfs_cmp_names() fixed
> - raise warning if 'nls->uni2char' fails
> - hot fix free clusters code optimized
> - use clang-format 11.0 instead of 10.0 to format code
> 
> v23:
> - corrections for Kernel Test Robot warnings
> - kmem_cache_create() utilized to allocate memory in bitmap.c
> - cosmetics and comments thru the code
> 
> v24:
> - BIO_MAX_PAGES -> BIO_MAX_VECS (fix for build issue of v23 vs linux-next)
> - minor optimization for LogFile: do not fill it with -1, if it's already there
> - index.c: removed 'inline' in definition of hdr_find_split() and hdr_insert_head()
> 
> v25:
> - restore fs/Makefile in patch
> - refactor ntfs_create_inode() to use error-valued pointer
> - use mi_get_ref to fill MFT_REF
> - minimize checkpatch.pl warnings: replace LogFile with \x24LogFile when printing
> 
> v26:
> - fixed coccinelle warnings
> - fslog.c: fix memory leak and memory overwrite
> 
> v27:
> - iov_iter_copy_from_user_atomic() replaced by copy_page_from_iter_atomic()
> and  iov_iter_advance() removed
> 
> Konstantin Komarov (10):
>   fs/ntfs3: Add headers and misc files
>   fs/ntfs3: Add initialization of super block
>   fs/ntfs3: Add bitmap
>   fs/ntfs3: Add file operations and implementation
>   fs/ntfs3: Add attrib operations
>   fs/ntfs3: Add compression
>   fs/ntfs3: Add NTFS journal
>   fs/ntfs3: Add Kconfig, Makefile and doc
>   fs/ntfs3: Add NTFS3 in fs/Kconfig and fs/Makefile
>   fs/ntfs3: Add MAINTAINERS
> 
>  Documentation/filesystems/ntfs3.rst |  107 +
>  MAINTAINERS                         |    7 +
>  fs/Kconfig                          |    1 +
>  fs/Makefile                         |    1 +
>  fs/ntfs3/Kconfig                    |   46 +
>  fs/ntfs3/Makefile                   |   36 +
>  fs/ntfs3/attrib.c                   | 2082 +++++++++++
>  fs/ntfs3/attrlist.c                 |  456 +++
>  fs/ntfs3/bitfunc.c                  |  135 +
>  fs/ntfs3/bitmap.c                   | 1519 ++++++++
>  fs/ntfs3/debug.h                    |   64 +
>  fs/ntfs3/dir.c                      |  594 +++
>  fs/ntfs3/file.c                     | 1130 ++++++
>  fs/ntfs3/frecord.c                  | 3071 ++++++++++++++++
>  fs/ntfs3/fslog.c                    | 5181 +++++++++++++++++++++++++++
>  fs/ntfs3/fsntfs.c                   | 2542 +++++++++++++
>  fs/ntfs3/index.c                    | 2641 ++++++++++++++
>  fs/ntfs3/inode.c                    | 2034 +++++++++++
>  fs/ntfs3/lib/decompress_common.c    |  332 ++
>  fs/ntfs3/lib/decompress_common.h    |  352 ++
>  fs/ntfs3/lib/lib.h                  |   26 +
>  fs/ntfs3/lib/lzx_decompress.c       |  683 ++++
>  fs/ntfs3/lib/xpress_decompress.c    |  155 +
>  fs/ntfs3/lznt.c                     |  452 +++
>  fs/ntfs3/namei.c                    |  578 +++
>  fs/ntfs3/ntfs.h                     | 1238 +++++++
>  fs/ntfs3/ntfs_fs.h                  | 1085 ++++++
>  fs/ntfs3/record.c                   |  609 ++++
>  fs/ntfs3/run.c                      | 1111 ++++++
>  fs/ntfs3/super.c                    | 1500 ++++++++
>  fs/ntfs3/upcase.c                   |  105 +
>  fs/ntfs3/xattr.c                    | 1046 ++++++
>  32 files changed, 30919 insertions(+)
>  create mode 100644 Documentation/filesystems/ntfs3.rst
>  create mode 100644 fs/ntfs3/Kconfig
>  create mode 100644 fs/ntfs3/Makefile
>  create mode 100644 fs/ntfs3/attrib.c
>  create mode 100644 fs/ntfs3/attrlist.c
>  create mode 100644 fs/ntfs3/bitfunc.c
>  create mode 100644 fs/ntfs3/bitmap.c
>  create mode 100644 fs/ntfs3/debug.h
>  create mode 100644 fs/ntfs3/dir.c
>  create mode 100644 fs/ntfs3/file.c
>  create mode 100644 fs/ntfs3/frecord.c
>  create mode 100644 fs/ntfs3/fslog.c
>  create mode 100644 fs/ntfs3/fsntfs.c
>  create mode 100644 fs/ntfs3/index.c
>  create mode 100644 fs/ntfs3/inode.c
>  create mode 100644 fs/ntfs3/lib/decompress_common.c
>  create mode 100644 fs/ntfs3/lib/decompress_common.h
>  create mode 100644 fs/ntfs3/lib/lib.h
>  create mode 100644 fs/ntfs3/lib/lzx_decompress.c
>  create mode 100644 fs/ntfs3/lib/xpress_decompress.c
>  create mode 100644 fs/ntfs3/lznt.c
>  create mode 100644 fs/ntfs3/namei.c
>  create mode 100644 fs/ntfs3/ntfs.h
>  create mode 100644 fs/ntfs3/ntfs_fs.h
>  create mode 100644 fs/ntfs3/record.c
>  create mode 100644 fs/ntfs3/run.c
>  create mode 100644 fs/ntfs3/super.c
>  create mode 100644 fs/ntfs3/upcase.c
>  create mode 100644 fs/ntfs3/xattr.c
> 
> 
> base-commit: 5a4cee98ea757e1a2a1354b497afdf8fafc30a20
> -- 
> 2.25.4
> 

Re: [Linux-NTFS-Dev] [PATCH v27 02/10] fs/ntfs3: Add initialization of super block

[Matthew W. <wi...@in...>]

On Thu, Jul 29, 2021 at 04:49:35PM +0300, Konstantin Komarov wrote:
> +static void ntfs_readahead(struct readahead_control *rac)
> +{
> +	struct address_space *mapping = rac->mapping;
> +	struct inode *inode = mapping->host;
> +	struct ntfs_inode *ni = ntfs_i(inode);
> +	u64 valid;
> +	loff_t pos;
> +
> +	if (is_resident(ni)) {
> +		/* no readahead for resident */
> +		return;
> +	}
> +
> +	if (is_compressed(ni)) {
> +		/* no readahead for compressed */
> +		return;

I'm sure this works, but it could perform better ;-)

The ->readpage path that you fall back to is synchronous (unless I
misunderstand something).  We now have readahead_expand() which lets
you ensure that there are pages in the page cache for the entire
range of the compressed extent.  So if you can create an asynchronous
decompression path (probably need your own custom bi_end_io), you can
start reads here and only unlock the pages after you've done the
decompression.

This should not gate your code being accepted upstream.  What I'd
really like to see is your buffered i/o path being converted from
buffer_heads to iomap, and iomap to gain the ability to handle
compressed extents.

> +	valid = ni->i_valid;
> +	pos = readahead_pos(rac);
> +
> +	if (valid < i_size_read(inode) && pos <= valid &&
> +	    valid < pos + readahead_length(rac)) {
> +		/* range cross 'valid'. read it page by page */
> +		return;

This, I do not understand.  Why can't ntfs_get_block / mpage_readahead
cope with a readahead that crosses i_valid?  AIUI, i_valid is basically
the same as i_size, and mpage_readahead() handles crossing i_size
just fine.

[Linux-NTFS-Dev] [PATCH v27 02/10] fs/ntfs3: Add initialization of super block

[Konstantin K. <alm...@pa...>]

This adds initialization of super block

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/fsntfs.c | 2542 +++++++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/index.c  | 2641 +++++++++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/inode.c  | 2034 ++++++++++++++++++++++++++++++++++
 fs/ntfs3/super.c  | 1500 +++++++++++++++++++++++++
 4 files changed, 8717 insertions(+)
 create mode 100644 fs/ntfs3/fsntfs.c
 create mode 100644 fs/ntfs3/index.c
 create mode 100644 fs/ntfs3/inode.c
 create mode 100644 fs/ntfs3/super.c

diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
new file mode 100644
index 000000000..327356b08
--- /dev/null
+++ b/fs/ntfs3/fsntfs.c
@@ -0,0 +1,2542 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+// clang-format off
+const struct cpu_str NAME_MFT = {
+	4, 0, { '$', 'M', 'F', 'T' },
+};
+const struct cpu_str NAME_MIRROR = {
+	8, 0, { '$', 'M', 'F', 'T', 'M', 'i', 'r', 'r' },
+};
+const struct cpu_str NAME_LOGFILE = {
+	8, 0, { '$', 'L', 'o', 'g', 'F', 'i', 'l', 'e' },
+};
+const struct cpu_str NAME_VOLUME = {
+	7, 0, { '$', 'V', 'o', 'l', 'u', 'm', 'e' },
+};
+const struct cpu_str NAME_ATTRDEF = {
+	8, 0, { '$', 'A', 't', 't', 'r', 'D', 'e', 'f' },
+};
+const struct cpu_str NAME_ROOT = {
+	1, 0, { '.' },
+};
+const struct cpu_str NAME_BITMAP = {
+	7, 0, { '$', 'B', 'i', 't', 'm', 'a', 'p' },
+};
+const struct cpu_str NAME_BOOT = {
+	5, 0, { '$', 'B', 'o', 'o', 't' },
+};
+const struct cpu_str NAME_BADCLUS = {
+	8, 0, { '$', 'B', 'a', 'd', 'C', 'l', 'u', 's' },
+};
+const struct cpu_str NAME_QUOTA = {
+	6, 0, { '$', 'Q', 'u', 'o', 't', 'a' },
+};
+const struct cpu_str NAME_SECURE = {
+	7, 0, { '$', 'S', 'e', 'c', 'u', 'r', 'e' },
+};
+const struct cpu_str NAME_UPCASE = {
+	7, 0, { '$', 'U', 'p', 'C', 'a', 's', 'e' },
+};
+const struct cpu_str NAME_EXTEND = {
+	7, 0, { '$', 'E', 'x', 't', 'e', 'n', 'd' },
+};
+const struct cpu_str NAME_OBJID = {
+	6, 0, { '$', 'O', 'b', 'j', 'I', 'd' },
+};
+const struct cpu_str NAME_REPARSE = {
+	8, 0, { '$', 'R', 'e', 'p', 'a', 'r', 's', 'e' },
+};
+const struct cpu_str NAME_USNJRNL = {
+	8, 0, { '$', 'U', 's', 'n', 'J', 'r', 'n', 'l' },
+};
+const __le16 BAD_NAME[4] = {
+	cpu_to_le16('$'), cpu_to_le16('B'), cpu_to_le16('a'), cpu_to_le16('d'),
+};
+const __le16 I30_NAME[4] = {
+	cpu_to_le16('$'), cpu_to_le16('I'), cpu_to_le16('3'), cpu_to_le16('0'),
+};
+const __le16 SII_NAME[4] = {
+	cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('I'), cpu_to_le16('I'),
+};
+const __le16 SDH_NAME[4] = {
+	cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('D'), cpu_to_le16('H'),
+};
+const __le16 SDS_NAME[4] = {
+	cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('D'), cpu_to_le16('S'),
+};
+const __le16 SO_NAME[2] = {
+	cpu_to_le16('$'), cpu_to_le16('O'),
+};
+const __le16 SQ_NAME[2] = {
+	cpu_to_le16('$'), cpu_to_le16('Q'),
+};
+const __le16 SR_NAME[2] = {
+	cpu_to_le16('$'), cpu_to_le16('R'),
+};
+
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+const __le16 WOF_NAME[17] = {
+	cpu_to_le16('W'), cpu_to_le16('o'), cpu_to_le16('f'), cpu_to_le16('C'),
+	cpu_to_le16('o'), cpu_to_le16('m'), cpu_to_le16('p'), cpu_to_le16('r'),
+	cpu_to_le16('e'), cpu_to_le16('s'), cpu_to_le16('s'), cpu_to_le16('e'),
+	cpu_to_le16('d'), cpu_to_le16('D'), cpu_to_le16('a'), cpu_to_le16('t'),
+	cpu_to_le16('a'),
+};
+#endif
+
+// clang-format on
+
+/*
+ * ntfs_fix_pre_write
+ *
+ * inserts fixups into 'rhdr' before writing to disk
+ */
+bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes)
+{
+	u16 *fixup, *ptr;
+	u16 sample;
+	u16 fo = le16_to_cpu(rhdr->fix_off);
+	u16 fn = le16_to_cpu(rhdr->fix_num);
+
+	if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- ||
+	    fn * SECTOR_SIZE > bytes) {
+		return false;
+	}
+
+	/* Get fixup pointer */
+	fixup = Add2Ptr(rhdr, fo);
+
+	if (*fixup >= 0x7FFF)
+		*fixup = 1;
+	else
+		*fixup += 1;
+
+	sample = *fixup;
+
+	ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short));
+
+	while (fn--) {
+		*++fixup = *ptr;
+		*ptr = sample;
+		ptr += SECTOR_SIZE / sizeof(short);
+	}
+	return true;
+}
+
+/*
+ * ntfs_fix_post_read
+ *
+ * remove fixups after reading from disk
+ * Returns < 0 if error, 0 if ok, 1 if need to update fixups
+ */
+int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
+		       bool simple)
+{
+	int ret;
+	u16 *fixup, *ptr;
+	u16 sample, fo, fn;
+
+	fo = le16_to_cpu(rhdr->fix_off);
+	fn = simple ? ((bytes >> SECTOR_SHIFT) + 1)
+		    : le16_to_cpu(rhdr->fix_num);
+
+	/* Check errors */
+	if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- ||
+	    fn * SECTOR_SIZE > bytes) {
+		return -EINVAL; /* native chkntfs returns ok! */
+	}
+
+	/* Get fixup pointer */
+	fixup = Add2Ptr(rhdr, fo);
+	sample = *fixup;
+	ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short));
+	ret = 0;
+
+	while (fn--) {
+		/* Test current word */
+		if (*ptr != sample) {
+			/* Fixup does not match! Is it serious error? */
+			ret = -E_NTFS_FIXUP;
+		}
+
+		/* Replace fixup */
+		*ptr = *++fixup;
+		ptr += SECTOR_SIZE / sizeof(short);
+	}
+
+	return ret;
+}
+
+/*
+ * ntfs_extend_init
+ *
+ * loads $Extend file
+ */
+int ntfs_extend_init(struct ntfs_sb_info *sbi)
+{
+	int err;
+	struct super_block *sb = sbi->sb;
+	struct inode *inode, *inode2;
+	struct MFT_REF ref;
+
+	if (sbi->volume.major_ver < 3) {
+		ntfs_notice(sb, "Skip $Extend 'cause NTFS version");
+		return 0;
+	}
+
+	ref.low = cpu_to_le32(MFT_REC_EXTEND);
+	ref.high = 0;
+	ref.seq = cpu_to_le16(MFT_REC_EXTEND);
+	inode = ntfs_iget5(sb, &ref, &NAME_EXTEND);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		ntfs_err(sb, "Failed to load $Extend.");
+		inode = NULL;
+		goto out;
+	}
+
+	/* if ntfs_iget5 reads from disk it never returns bad inode */
+	if (!S_ISDIR(inode->i_mode)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Try to find $ObjId */
+	inode2 = dir_search_u(inode, &NAME_OBJID, NULL);
+	if (inode2 && !IS_ERR(inode2)) {
+		if (is_bad_inode(inode2)) {
+			iput(inode2);
+		} else {
+			sbi->objid.ni = ntfs_i(inode2);
+			sbi->objid_no = inode2->i_ino;
+		}
+	}
+
+	/* Try to find $Quota */
+	inode2 = dir_search_u(inode, &NAME_QUOTA, NULL);
+	if (inode2 && !IS_ERR(inode2)) {
+		sbi->quota_no = inode2->i_ino;
+		iput(inode2);
+	}
+
+	/* Try to find $Reparse */
+	inode2 = dir_search_u(inode, &NAME_REPARSE, NULL);
+	if (inode2 && !IS_ERR(inode2)) {
+		sbi->reparse.ni = ntfs_i(inode2);
+		sbi->reparse_no = inode2->i_ino;
+	}
+
+	/* Try to find $UsnJrnl */
+	inode2 = dir_search_u(inode, &NAME_USNJRNL, NULL);
+	if (inode2 && !IS_ERR(inode2)) {
+		sbi->usn_jrnl_no = inode2->i_ino;
+		iput(inode2);
+	}
+
+	err = 0;
+out:
+	iput(inode);
+	return err;
+}
+
+int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	bool initialized = false;
+	struct MFT_REF ref;
+	struct inode *inode;
+
+	/* Check for 4GB */
+	if (ni->vfs_inode.i_size >= 0x100000000ull) {
+		ntfs_err(sb, "\x24LogFile is too big");
+		err = -EINVAL;
+		goto out;
+	}
+
+	sbi->flags |= NTFS_FLAGS_LOG_REPLAYING;
+
+	ref.low = cpu_to_le32(MFT_REC_MFT);
+	ref.high = 0;
+	ref.seq = cpu_to_le16(1);
+
+	inode = ntfs_iget5(sb, &ref, NULL);
+
+	if (IS_ERR(inode))
+		inode = NULL;
+
+	if (!inode) {
+		/* Try to use mft copy */
+		u64 t64 = sbi->mft.lbo;
+
+		sbi->mft.lbo = sbi->mft.lbo2;
+		inode = ntfs_iget5(sb, &ref, NULL);
+		sbi->mft.lbo = t64;
+		if (IS_ERR(inode))
+			inode = NULL;
+	}
+
+	if (!inode) {
+		err = -EINVAL;
+		ntfs_err(sb, "Failed to load $MFT.");
+		goto out;
+	}
+
+	sbi->mft.ni = ntfs_i(inode);
+
+	/* LogFile should not contains attribute list */
+	err = ni_load_all_mi(sbi->mft.ni);
+	if (!err)
+		err = log_replay(ni, &initialized);
+
+	iput(inode);
+	sbi->mft.ni = NULL;
+
+	sync_blockdev(sb->s_bdev);
+	invalidate_bdev(sb->s_bdev);
+
+	if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) {
+		err = 0;
+		goto out;
+	}
+
+	if (sb_rdonly(sb) || !initialized)
+		goto out;
+
+	/* fill LogFile by '-1' if it is initialized */
+	err = ntfs_bio_fill_1(sbi, &ni->file.run);
+
+out:
+	sbi->flags &= ~NTFS_FLAGS_LOG_REPLAYING;
+
+	return err;
+}
+
+/*
+ * ntfs_query_def
+ *
+ * returns current ATTR_DEF_ENTRY for given attribute type
+ */
+const struct ATTR_DEF_ENTRY *ntfs_query_def(struct ntfs_sb_info *sbi,
+					    enum ATTR_TYPE type)
+{
+	int type_in = le32_to_cpu(type);
+	size_t min_idx = 0;
+	size_t max_idx = sbi->def_entries - 1;
+
+	while (min_idx <= max_idx) {
+		size_t i = min_idx + ((max_idx - min_idx) >> 1);
+		const struct ATTR_DEF_ENTRY *entry = sbi->def_table + i;
+		int diff = le32_to_cpu(entry->type) - type_in;
+
+		if (!diff)
+			return entry;
+		if (diff < 0)
+			min_idx = i + 1;
+		else if (i)
+			max_idx = i - 1;
+		else
+			return NULL;
+	}
+	return NULL;
+}
+
+/*
+ * ntfs_look_for_free_space
+ *
+ * looks for a free space in bitmap
+ */
+int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len,
+			     CLST *new_lcn, CLST *new_len,
+			     enum ALLOCATE_OPT opt)
+{
+	int err;
+	struct super_block *sb = sbi->sb;
+	size_t a_lcn, zlen, zeroes, zlcn, zlen2, ztrim, new_zlen;
+	struct wnd_bitmap *wnd = &sbi->used.bitmap;
+
+	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
+	if (opt & ALLOCATE_MFT) {
+		CLST alen;
+
+		zlen = wnd_zone_len(wnd);
+
+		if (!zlen) {
+			err = ntfs_refresh_zone(sbi);
+			if (err)
+				goto out;
+
+			zlen = wnd_zone_len(wnd);
+
+			if (!zlen) {
+				ntfs_err(sbi->sb,
+					 "no free space to extend mft");
+				err = -ENOSPC;
+				goto out;
+			}
+		}
+
+		lcn = wnd_zone_bit(wnd);
+		alen = zlen > len ? len : zlen;
+
+		wnd_zone_set(wnd, lcn + alen, zlen - alen);
+
+		err = wnd_set_used(wnd, lcn, alen);
+		if (err)
+			goto out;
+
+		*new_lcn = lcn;
+		*new_len = alen;
+		goto ok;
+	}
+
+	/*
+	 * 'Cause cluster 0 is always used this value means that we should use
+	 * cached value of 'next_free_lcn' to improve performance
+	 */
+	if (!lcn)
+		lcn = sbi->used.next_free_lcn;
+
+	if (lcn >= wnd->nbits)
+		lcn = 0;
+
+	*new_len = wnd_find(wnd, len, lcn, BITMAP_FIND_MARK_AS_USED, &a_lcn);
+	if (*new_len) {
+		*new_lcn = a_lcn;
+		goto ok;
+	}
+
+	/* Try to use clusters from MftZone */
+	zlen = wnd_zone_len(wnd);
+	zeroes = wnd_zeroes(wnd);
+
+	/* Check too big request */
+	if (len > zeroes + zlen)
+		goto no_space;
+
+	if (zlen <= NTFS_MIN_MFT_ZONE)
+		goto no_space;
+
+	/* How many clusters to cat from zone */
+	zlcn = wnd_zone_bit(wnd);
+	zlen2 = zlen >> 1;
+	ztrim = len > zlen ? zlen : (len > zlen2 ? len : zlen2);
+	new_zlen = zlen - ztrim;
+
+	if (new_zlen < NTFS_MIN_MFT_ZONE) {
+		new_zlen = NTFS_MIN_MFT_ZONE;
+		if (new_zlen > zlen)
+			new_zlen = zlen;
+	}
+
+	wnd_zone_set(wnd, zlcn, new_zlen);
+
+	/* allocate continues clusters */
+	*new_len =
+		wnd_find(wnd, len, 0,
+			 BITMAP_FIND_MARK_AS_USED | BITMAP_FIND_FULL, &a_lcn);
+	if (*new_len) {
+		*new_lcn = a_lcn;
+		goto ok;
+	}
+
+no_space:
+	up_write(&wnd->rw_lock);
+
+	return -ENOSPC;
+
+ok:
+	err = 0;
+
+	ntfs_unmap_meta(sb, *new_lcn, *new_len);
+
+	if (opt & ALLOCATE_MFT)
+		goto out;
+
+	/* Set hint for next requests */
+	sbi->used.next_free_lcn = *new_lcn + *new_len;
+
+out:
+	up_write(&wnd->rw_lock);
+	return err;
+}
+
+/*
+ * ntfs_extend_mft
+ *
+ * allocates additional MFT records
+ * sbi->mft.bitmap is locked for write
+ *
+ * NOTE: recursive:
+ *	ntfs_look_free_mft ->
+ *	ntfs_extend_mft ->
+ *	attr_set_size ->
+ *	ni_insert_nonresident ->
+ *	ni_insert_attr ->
+ *	ni_ins_attr_ext ->
+ *	ntfs_look_free_mft ->
+ *	ntfs_extend_mft
+ * To avoid recursive always allocate space for two new mft records
+ * see attrib.c: "at least two mft to avoid recursive loop"
+ */
+static int ntfs_extend_mft(struct ntfs_sb_info *sbi)
+{
+	int err;
+	struct ntfs_inode *ni = sbi->mft.ni;
+	size_t new_mft_total;
+	u64 new_mft_bytes, new_bitmap_bytes;
+	struct ATTRIB *attr;
+	struct wnd_bitmap *wnd = &sbi->mft.bitmap;
+
+	new_mft_total = (wnd->nbits + MFT_INCREASE_CHUNK + 127) & (CLST)~127;
+	new_mft_bytes = (u64)new_mft_total << sbi->record_bits;
+
+	/* Step 1: Resize $MFT::DATA */
+	down_write(&ni->file.run_lock);
+	err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
+			    new_mft_bytes, NULL, false, &attr);
+
+	if (err) {
+		up_write(&ni->file.run_lock);
+		goto out;
+	}
+
+	attr->nres.valid_size = attr->nres.data_size;
+	new_mft_total = le64_to_cpu(attr->nres.alloc_size) >> sbi->record_bits;
+	ni->mi.dirty = true;
+
+	/* Step 2: Resize $MFT::BITMAP */
+	new_bitmap_bytes = bitmap_size(new_mft_total);
+
+	err = attr_set_size(ni, ATTR_BITMAP, NULL, 0, &sbi->mft.bitmap.run,
+			    new_bitmap_bytes, &new_bitmap_bytes, true, NULL);
+
+	/* Refresh Mft Zone if necessary */
+	down_write_nested(&sbi->used.bitmap.rw_lock, BITMAP_MUTEX_CLUSTERS);
+
+	ntfs_refresh_zone(sbi);
+
+	up_write(&sbi->used.bitmap.rw_lock);
+	up_write(&ni->file.run_lock);
+
+	if (err)
+		goto out;
+
+	err = wnd_extend(wnd, new_mft_total);
+
+	if (err)
+		goto out;
+
+	ntfs_clear_mft_tail(sbi, sbi->mft.used, new_mft_total);
+
+	err = _ni_write_inode(&ni->vfs_inode, 0);
+out:
+	return err;
+}
+
+/*
+ * ntfs_look_free_mft
+ *
+ * looks for a free MFT record
+ */
+int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft,
+		       struct ntfs_inode *ni, struct mft_inode **mi)
+{
+	int err = 0;
+	size_t zbit, zlen, from, to, fr;
+	size_t mft_total;
+	struct MFT_REF ref;
+	struct super_block *sb = sbi->sb;
+	struct wnd_bitmap *wnd = &sbi->mft.bitmap;
+	u32 ir;
+
+	static_assert(sizeof(sbi->mft.reserved_bitmap) * 8 >=
+		      MFT_REC_FREE - MFT_REC_RESERVED);
+
+	if (!mft)
+		down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT);
+
+	zlen = wnd_zone_len(wnd);
+
+	/* Always reserve space for MFT */
+	if (zlen) {
+		if (mft) {
+			zbit = wnd_zone_bit(wnd);
+			*rno = zbit;
+			wnd_zone_set(wnd, zbit + 1, zlen - 1);
+		}
+		goto found;
+	}
+
+	/* No MFT zone. find the nearest to '0' free MFT */
+	if (!wnd_find(wnd, 1, MFT_REC_FREE, 0, &zbit)) {
+		/* Resize MFT */
+		mft_total = wnd->nbits;
+
+		err = ntfs_extend_mft(sbi);
+		if (!err) {
+			zbit = mft_total;
+			goto reserve_mft;
+		}
+
+		if (!mft || MFT_REC_FREE == sbi->mft.next_reserved)
+			goto out;
+
+		err = 0;
+
+		/*
+		 * Look for free record reserved area [11-16) ==
+		 * [MFT_REC_RESERVED, MFT_REC_FREE ) MFT bitmap always
+		 * marks it as used
+		 */
+		if (!sbi->mft.reserved_bitmap) {
+			/* Once per session create internal bitmap for 5 bits */
+			sbi->mft.reserved_bitmap = 0xFF;
+
+			ref.high = 0;
+			for (ir = MFT_REC_RESERVED; ir < MFT_REC_FREE; ir++) {
+				struct inode *i;
+				struct ntfs_inode *ni;
+				struct MFT_REC *mrec;
+
+				ref.low = cpu_to_le32(ir);
+				ref.seq = cpu_to_le16(ir);
+
+				i = ntfs_iget5(sb, &ref, NULL);
+				if (IS_ERR(i)) {
+next:
+					ntfs_notice(
+						sb,
+						"Invalid reserved record %x",
+						ref.low);
+					continue;
+				}
+				if (is_bad_inode(i)) {
+					iput(i);
+					goto next;
+				}
+
+				ni = ntfs_i(i);
+
+				mrec = ni->mi.mrec;
+
+				if (!is_rec_base(mrec))
+					goto next;
+
+				if (mrec->hard_links)
+					goto next;
+
+				if (!ni_std(ni))
+					goto next;
+
+				if (ni_find_attr(ni, NULL, NULL, ATTR_NAME,
+						 NULL, 0, NULL, NULL))
+					goto next;
+
+				__clear_bit(ir - MFT_REC_RESERVED,
+					    &sbi->mft.reserved_bitmap);
+			}
+		}
+
+		/* Scan 5 bits for zero. Bit 0 == MFT_REC_RESERVED */
+		zbit = find_next_zero_bit(&sbi->mft.reserved_bitmap,
+					  MFT_REC_FREE, MFT_REC_RESERVED);
+		if (zbit >= MFT_REC_FREE) {
+			sbi->mft.next_reserved = MFT_REC_FREE;
+			goto out;
+		}
+
+		zlen = 1;
+		sbi->mft.next_reserved = zbit;
+	} else {
+reserve_mft:
+		zlen = zbit == MFT_REC_FREE ? (MFT_REC_USER - MFT_REC_FREE) : 4;
+		if (zbit + zlen > wnd->nbits)
+			zlen = wnd->nbits - zbit;
+
+		while (zlen > 1 && !wnd_is_free(wnd, zbit, zlen))
+			zlen -= 1;
+
+		/* [zbit, zbit + zlen) will be used for Mft itself */
+		from = sbi->mft.used;
+		if (from < zbit)
+			from = zbit;
+		to = zbit + zlen;
+		if (from < to) {
+			ntfs_clear_mft_tail(sbi, from, to);
+			sbi->mft.used = to;
+		}
+	}
+
+	if (mft) {
+		*rno = zbit;
+		zbit += 1;
+		zlen -= 1;
+	}
+
+	wnd_zone_set(wnd, zbit, zlen);
+
+found:
+	if (!mft) {
+		/* The request to get record for general purpose */
+		if (sbi->mft.next_free < MFT_REC_USER)
+			sbi->mft.next_free = MFT_REC_USER;
+
+		for (;;) {
+			if (sbi->mft.next_free >= sbi->mft.bitmap.nbits) {
+			} else if (!wnd_find(wnd, 1, MFT_REC_USER, 0, &fr)) {
+				sbi->mft.next_free = sbi->mft.bitmap.nbits;
+			} else {
+				*rno = fr;
+				sbi->mft.next_free = *rno + 1;
+				break;
+			}
+
+			err = ntfs_extend_mft(sbi);
+			if (err)
+				goto out;
+		}
+	}
+
+	if (ni && !ni_add_subrecord(ni, *rno, mi)) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* We have found a record that are not reserved for next MFT */
+	if (*rno >= MFT_REC_FREE)
+		wnd_set_used(wnd, *rno, 1);
+	else if (*rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited)
+		__set_bit(*rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap);
+
+out:
+	if (!mft)
+		up_write(&wnd->rw_lock);
+
+	return err;
+}
+
+/*
+ * ntfs_mark_rec_free
+ *
+ * marks record as free
+ */
+void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno)
+{
+	struct wnd_bitmap *wnd = &sbi->mft.bitmap;
+
+	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT);
+	if (rno >= wnd->nbits)
+		goto out;
+
+	if (rno >= MFT_REC_FREE) {
+		if (!wnd_is_used(wnd, rno, 1))
+			ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+		else
+			wnd_set_free(wnd, rno, 1);
+	} else if (rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) {
+		__clear_bit(rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap);
+	}
+
+	if (rno < wnd_zone_bit(wnd))
+		wnd_zone_set(wnd, rno, 1);
+	else if (rno < sbi->mft.next_free && rno >= MFT_REC_USER)
+		sbi->mft.next_free = rno;
+
+out:
+	up_write(&wnd->rw_lock);
+}
+
+/*
+ * ntfs_clear_mft_tail
+ *
+ * formats empty records [from, to)
+ * sbi->mft.bitmap is locked for write
+ */
+int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to)
+{
+	int err;
+	u32 rs;
+	u64 vbo;
+	struct runs_tree *run;
+	struct ntfs_inode *ni;
+
+	if (from >= to)
+		return 0;
+
+	rs = sbi->record_size;
+	ni = sbi->mft.ni;
+	run = &ni->file.run;
+
+	down_read(&ni->file.run_lock);
+	vbo = (u64)from * rs;
+	for (; from < to; from++, vbo += rs) {
+		struct ntfs_buffers nb;
+
+		err = ntfs_get_bh(sbi, run, vbo, rs, &nb);
+		if (err)
+			goto out;
+
+		err = ntfs_write_bh(sbi, &sbi->new_rec->rhdr, &nb, 0);
+		nb_put(&nb);
+		if (err)
+			goto out;
+	}
+
+out:
+	sbi->mft.used = from;
+	up_read(&ni->file.run_lock);
+	return err;
+}
+
+/*
+ * ntfs_refresh_zone
+ *
+ * refreshes Mft zone
+ * sbi->used.bitmap is locked for rw
+ * sbi->mft.bitmap is locked for write
+ * sbi->mft.ni->file.run_lock for write
+ */
+int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
+{
+	CLST zone_limit, zone_max, lcn, vcn, len;
+	size_t lcn_s, zlen;
+	struct wnd_bitmap *wnd = &sbi->used.bitmap;
+	struct ntfs_inode *ni = sbi->mft.ni;
+
+	/* Do not change anything unless we have non empty Mft zone */
+	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);
+
+	if (!run_lookup_entry(&ni->file.run, vcn - 1, &lcn, &len, NULL))
+		lcn = SPARSE_LCN;
+
+	/* We should always find Last Lcn for MFT */
+	if (lcn == SPARSE_LCN)
+		return -EINVAL;
+
+	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 */
+	wnd_zone_set(wnd, lcn_s, zlen);
+
+	return 0;
+}
+
+/*
+ * ntfs_update_mftmirr
+ *
+ * updates $MFTMirr data
+ */
+int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
+{
+	int err;
+	struct super_block *sb = sbi->sb;
+	u32 blocksize = sb->s_blocksize;
+	sector_t block1, block2;
+	u32 bytes;
+
+	if (!(sbi->flags & NTFS_FLAGS_MFTMIRR))
+		return 0;
+
+	err = 0;
+	bytes = sbi->mft.recs_mirr << sbi->record_bits;
+	block1 = sbi->mft.lbo >> sb->s_blocksize_bits;
+	block2 = sbi->mft.lbo2 >> sb->s_blocksize_bits;
+
+	for (; bytes >= blocksize; bytes -= blocksize) {
+		struct buffer_head *bh1, *bh2;
+
+		bh1 = sb_bread(sb, block1++);
+		if (!bh1) {
+			err = -EIO;
+			goto out;
+		}
+
+		bh2 = sb_getblk(sb, block2++);
+		if (!bh2) {
+			put_bh(bh1);
+			err = -EIO;
+			goto out;
+		}
+
+		if (buffer_locked(bh2))
+			__wait_on_buffer(bh2);
+
+		lock_buffer(bh2);
+		memcpy(bh2->b_data, bh1->b_data, blocksize);
+		set_buffer_uptodate(bh2);
+		mark_buffer_dirty(bh2);
+		unlock_buffer(bh2);
+
+		put_bh(bh1);
+		bh1 = NULL;
+
+		if (wait)
+			err = sync_dirty_buffer(bh2);
+
+		put_bh(bh2);
+		if (err)
+			goto out;
+	}
+
+	sbi->flags &= ~NTFS_FLAGS_MFTMIRR;
+
+out:
+	return err;
+}
+
+/*
+ * ntfs_set_state
+ *
+ * mount: ntfs_set_state(NTFS_DIRTY_DIRTY)
+ * umount: ntfs_set_state(NTFS_DIRTY_CLEAR)
+ * ntfs error: ntfs_set_state(NTFS_DIRTY_ERROR)
+ */
+int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty)
+{
+	int err;
+	struct ATTRIB *attr;
+	struct VOLUME_INFO *info;
+	struct mft_inode *mi;
+	struct ntfs_inode *ni;
+
+	/*
+	 * do not change state if fs was real_dirty
+	 * do not change state if fs already dirty(clear)
+	 * do not change any thing if mounted read only
+	 */
+	if (sbi->volume.real_dirty || sb_rdonly(sbi->sb))
+		return 0;
+
+	/* Check cached value */
+	if ((dirty == NTFS_DIRTY_CLEAR ? 0 : VOLUME_FLAG_DIRTY) ==
+	    (sbi->volume.flags & VOLUME_FLAG_DIRTY))
+		return 0;
+
+	ni = sbi->volume.ni;
+	if (!ni)
+		return -EINVAL;
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_DIRTY);
+
+	attr = ni_find_attr(ni, NULL, NULL, ATTR_VOL_INFO, NULL, 0, NULL, &mi);
+	if (!attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO);
+	if (!info) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	switch (dirty) {
+	case NTFS_DIRTY_ERROR:
+		ntfs_notice(sbi->sb, "Mark volume as dirty due to NTFS errors");
+		sbi->volume.real_dirty = true;
+		fallthrough;
+	case NTFS_DIRTY_DIRTY:
+		info->flags |= VOLUME_FLAG_DIRTY;
+		break;
+	case NTFS_DIRTY_CLEAR:
+		info->flags &= ~VOLUME_FLAG_DIRTY;
+		break;
+	}
+	/* cache current volume flags*/
+	sbi->volume.flags = info->flags;
+	mi->dirty = true;
+	err = 0;
+
+out:
+	ni_unlock(ni);
+	if (err)
+		return err;
+
+	mark_inode_dirty(&ni->vfs_inode);
+	/*verify(!ntfs_update_mftmirr()); */
+	err = sync_inode_metadata(&ni->vfs_inode, 1);
+
+	return err;
+}
+
+/*
+ * security_hash
+ *
+ * calculates a hash of security descriptor
+ */
+static inline __le32 security_hash(const void *sd, size_t bytes)
+{
+	u32 hash = 0;
+	const __le32 *ptr = sd;
+
+	bytes >>= 2;
+	while (bytes--)
+		hash = ((hash >> 0x1D) | (hash << 3)) + le32_to_cpu(*ptr++);
+	return cpu_to_le32(hash);
+}
+
+int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer)
+{
+	struct block_device *bdev = sb->s_bdev;
+	u32 blocksize = sb->s_blocksize;
+	u64 block = lbo >> sb->s_blocksize_bits;
+	u32 off = lbo & (blocksize - 1);
+	u32 op = blocksize - off;
+
+	for (; bytes; block += 1, off = 0, op = blocksize) {
+		struct buffer_head *bh = __bread(bdev, block, blocksize);
+
+		if (!bh)
+			return -EIO;
+
+		if (op > bytes)
+			op = bytes;
+
+		memcpy(buffer, bh->b_data + off, op);
+
+		put_bh(bh);
+
+		bytes -= op;
+		buffer = Add2Ptr(buffer, op);
+	}
+
+	return 0;
+}
+
+int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes,
+		  const void *buf, int wait)
+{
+	u32 blocksize = sb->s_blocksize;
+	struct block_device *bdev = sb->s_bdev;
+	sector_t block = lbo >> sb->s_blocksize_bits;
+	u32 off = lbo & (blocksize - 1);
+	u32 op = blocksize - off;
+	struct buffer_head *bh;
+
+	if (!wait && (sb->s_flags & SB_SYNCHRONOUS))
+		wait = 1;
+
+	for (; bytes; block += 1, off = 0, op = blocksize) {
+		if (op > bytes)
+			op = bytes;
+
+		if (op < blocksize) {
+			bh = __bread(bdev, block, blocksize);
+			if (!bh) {
+				ntfs_err(sb, "failed to read block %llx",
+					 (u64)block);
+				return -EIO;
+			}
+		} else {
+			bh = __getblk(bdev, block, blocksize);
+			if (!bh)
+				return -ENOMEM;
+		}
+
+		if (buffer_locked(bh))
+			__wait_on_buffer(bh);
+
+		lock_buffer(bh);
+		if (buf) {
+			memcpy(bh->b_data + off, buf, op);
+			buf = Add2Ptr(buf, op);
+		} else {
+			memset(bh->b_data + off, -1, op);
+		}
+
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+
+		if (wait) {
+			int err = sync_dirty_buffer(bh);
+
+			if (err) {
+				ntfs_err(
+					sb,
+					"failed to sync buffer at block %llx, error %d",
+					(u64)block, err);
+				put_bh(bh);
+				return err;
+			}
+		}
+
+		put_bh(bh);
+
+		bytes -= op;
+	}
+	return 0;
+}
+
+int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		      u64 vbo, const void *buf, size_t bytes)
+{
+	struct super_block *sb = sbi->sb;
+	u8 cluster_bits = sbi->cluster_bits;
+	u32 off = vbo & sbi->cluster_mask;
+	CLST lcn, clen, vcn = vbo >> cluster_bits, vcn_next;
+	u64 lbo, len;
+	size_t idx;
+
+	if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx))
+		return -ENOENT;
+
+	if (lcn == SPARSE_LCN)
+		return -EINVAL;
+
+	lbo = ((u64)lcn << cluster_bits) + off;
+	len = ((u64)clen << cluster_bits) - off;
+
+	for (;;) {
+		u32 op = len < bytes ? len : bytes;
+		int err = ntfs_sb_write(sb, lbo, op, buf, 0);
+
+		if (err)
+			return err;
+
+		bytes -= op;
+		if (!bytes)
+			break;
+
+		vcn_next = vcn + clen;
+		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
+		    vcn != vcn_next)
+			return -ENOENT;
+
+		if (lcn == SPARSE_LCN)
+			return -EINVAL;
+
+		if (buf)
+			buf = Add2Ptr(buf, op);
+
+		lbo = ((u64)lcn << cluster_bits);
+		len = ((u64)clen << cluster_bits);
+	}
+
+	return 0;
+}
+
+struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi,
+				   const struct runs_tree *run, u64 vbo)
+{
+	struct super_block *sb = sbi->sb;
+	u8 cluster_bits = sbi->cluster_bits;
+	CLST lcn;
+	u64 lbo;
+
+	if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, NULL, NULL))
+		return ERR_PTR(-ENOENT);
+
+	lbo = ((u64)lcn << cluster_bits) + (vbo & sbi->cluster_mask);
+
+	return ntfs_bread(sb, lbo >> sb->s_blocksize_bits);
+}
+
+int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		     u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb)
+{
+	int err;
+	struct super_block *sb = sbi->sb;
+	u32 blocksize = sb->s_blocksize;
+	u8 cluster_bits = sbi->cluster_bits;
+	u32 off = vbo & sbi->cluster_mask;
+	u32 nbh = 0;
+	CLST vcn_next, vcn = vbo >> cluster_bits;
+	CLST lcn, clen;
+	u64 lbo, len;
+	size_t idx;
+	struct buffer_head *bh;
+
+	if (!run) {
+		/* first reading of $Volume + $MFTMirr + LogFile goes here*/
+		if (vbo > MFT_REC_VOL * sbi->record_size) {
+			err = -ENOENT;
+			goto out;
+		}
+
+		/* use absolute boot's 'MFTCluster' to read record */
+		lbo = vbo + sbi->mft.lbo;
+		len = sbi->record_size;
+	} else if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) {
+		err = -ENOENT;
+		goto out;
+	} else {
+		if (lcn == SPARSE_LCN) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		lbo = ((u64)lcn << cluster_bits) + off;
+		len = ((u64)clen << cluster_bits) - off;
+	}
+
+	off = lbo & (blocksize - 1);
+	if (nb) {
+		nb->off = off;
+		nb->bytes = bytes;
+	}
+
+	for (;;) {
+		u32 len32 = len >= bytes ? bytes : len;
+		sector_t block = lbo >> sb->s_blocksize_bits;
+
+		do {
+			u32 op = blocksize - off;
+
+			if (op > len32)
+				op = len32;
+
+			bh = ntfs_bread(sb, block);
+			if (!bh) {
+				err = -EIO;
+				goto out;
+			}
+
+			if (buf) {
+				memcpy(buf, bh->b_data + off, op);
+				buf = Add2Ptr(buf, op);
+			}
+
+			if (!nb) {
+				put_bh(bh);
+			} else if (nbh >= ARRAY_SIZE(nb->bh)) {
+				err = -EINVAL;
+				goto out;
+			} else {
+				nb->bh[nbh++] = bh;
+				nb->nbufs = nbh;
+			}
+
+			bytes -= op;
+			if (!bytes)
+				return 0;
+			len32 -= op;
+			block += 1;
+			off = 0;
+
+		} while (len32);
+
+		vcn_next = vcn + clen;
+		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
+		    vcn != vcn_next) {
+			err = -ENOENT;
+			goto out;
+		}
+
+		if (lcn == SPARSE_LCN) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		lbo = ((u64)lcn << cluster_bits);
+		len = ((u64)clen << cluster_bits);
+	}
+
+out:
+	if (!nbh)
+		return err;
+
+	while (nbh) {
+		put_bh(nb->bh[--nbh]);
+		nb->bh[nbh] = NULL;
+	}
+
+	nb->nbufs = 0;
+	return err;
+}
+
+/* Returns < 0 if error, 0 if ok, '-E_NTFS_FIXUP' if need to update fixups */
+int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo,
+		 struct NTFS_RECORD_HEADER *rhdr, u32 bytes,
+		 struct ntfs_buffers *nb)
+{
+	int err = ntfs_read_run_nb(sbi, run, vbo, rhdr, bytes, nb);
+
+	if (err)
+		return err;
+	return ntfs_fix_post_read(rhdr, nb->bytes, true);
+}
+
+int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo,
+		u32 bytes, struct ntfs_buffers *nb)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	u32 blocksize = sb->s_blocksize;
+	u8 cluster_bits = sbi->cluster_bits;
+	CLST vcn_next, vcn = vbo >> cluster_bits;
+	u32 off;
+	u32 nbh = 0;
+	CLST lcn, clen;
+	u64 lbo, len;
+	size_t idx;
+
+	nb->bytes = bytes;
+
+	if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	off = vbo & sbi->cluster_mask;
+	lbo = ((u64)lcn << cluster_bits) + off;
+	len = ((u64)clen << cluster_bits) - off;
+
+	nb->off = off = lbo & (blocksize - 1);
+
+	for (;;) {
+		u32 len32 = len < bytes ? len : bytes;
+		sector_t block = lbo >> sb->s_blocksize_bits;
+
+		do {
+			u32 op;
+			struct buffer_head *bh;
+
+			if (nbh >= ARRAY_SIZE(nb->bh)) {
+				err = -EINVAL;
+				goto out;
+			}
+
+			op = blocksize - off;
+			if (op > len32)
+				op = len32;
+
+			if (op == blocksize) {
+				bh = sb_getblk(sb, block);
+				if (!bh) {
+					err = -ENOMEM;
+					goto out;
+				}
+				if (buffer_locked(bh))
+					__wait_on_buffer(bh);
+				set_buffer_uptodate(bh);
+			} else {
+				bh = ntfs_bread(sb, block);
+				if (!bh) {
+					err = -EIO;
+					goto out;
+				}
+			}
+
+			nb->bh[nbh++] = bh;
+			bytes -= op;
+			if (!bytes) {
+				nb->nbufs = nbh;
+				return 0;
+			}
+
+			block += 1;
+			len32 -= op;
+			off = 0;
+		} while (len32);
+
+		vcn_next = vcn + clen;
+		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
+		    vcn != vcn_next) {
+			err = -ENOENT;
+			goto out;
+		}
+
+		lbo = ((u64)lcn << cluster_bits);
+		len = ((u64)clen << cluster_bits);
+	}
+
+out:
+	while (nbh) {
+		put_bh(nb->bh[--nbh]);
+		nb->bh[nbh] = NULL;
+	}
+
+	nb->nbufs = 0;
+
+	return err;
+}
+
+int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
+		  struct ntfs_buffers *nb, int sync)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	u32 block_size = sb->s_blocksize;
+	u32 bytes = nb->bytes;
+	u32 off = nb->off;
+	u16 fo = le16_to_cpu(rhdr->fix_off);
+	u16 fn = le16_to_cpu(rhdr->fix_num);
+	u32 idx;
+	__le16 *fixup;
+	__le16 sample;
+
+	if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- ||
+	    fn * SECTOR_SIZE > bytes) {
+		return -EINVAL;
+	}
+
+	for (idx = 0; bytes && idx < nb->nbufs; idx += 1, off = 0) {
+		u32 op = block_size - off;
+		char *bh_data;
+		struct buffer_head *bh = nb->bh[idx];
+		__le16 *ptr, *end_data;
+
+		if (op > bytes)
+			op = bytes;
+
+		if (buffer_locked(bh))
+			__wait_on_buffer(bh);
+
+		lock_buffer(nb->bh[idx]);
+
+		bh_data = bh->b_data + off;
+		end_data = Add2Ptr(bh_data, op);
+		memcpy(bh_data, rhdr, op);
+
+		if (!idx) {
+			u16 t16;
+
+			fixup = Add2Ptr(bh_data, fo);
+			sample = *fixup;
+			t16 = le16_to_cpu(sample);
+			if (t16 >= 0x7FFF) {
+				sample = *fixup = cpu_to_le16(1);
+			} else {
+				sample = cpu_to_le16(t16 + 1);
+				*fixup = sample;
+			}
+
+			*(__le16 *)Add2Ptr(rhdr, fo) = sample;
+		}
+
+		ptr = Add2Ptr(bh_data, SECTOR_SIZE - sizeof(short));
+
+		do {
+			*++fixup = *ptr;
+			*ptr = sample;
+			ptr += SECTOR_SIZE / sizeof(short);
+		} while (ptr < end_data);
+
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+
+		if (sync) {
+			int err2 = sync_dirty_buffer(bh);
+
+			if (!err && err2)
+				err = err2;
+		}
+
+		bytes -= op;
+		rhdr = Add2Ptr(rhdr, op);
+	}
+
+	return err;
+}
+
+static inline struct bio *ntfs_alloc_bio(u32 nr_vecs)
+{
+	struct bio *bio = bio_alloc(GFP_NOFS | __GFP_HIGH, nr_vecs);
+
+	if (!bio && (current->flags & PF_MEMALLOC)) {
+		while (!bio && (nr_vecs /= 2))
+			bio = bio_alloc(GFP_NOFS | __GFP_HIGH, nr_vecs);
+	}
+	return bio;
+}
+
+/* read/write pages from/to disk*/
+int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		   struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
+		   u32 op)
+{
+	int err = 0;
+	struct bio *new, *bio = NULL;
+	struct super_block *sb = sbi->sb;
+	struct block_device *bdev = sb->s_bdev;
+	struct page *page;
+	u8 cluster_bits = sbi->cluster_bits;
+	CLST lcn, clen, vcn, vcn_next;
+	u32 add, off, page_idx;
+	u64 lbo, len;
+	size_t run_idx;
+	struct blk_plug plug;
+
+	if (!bytes)
+		return 0;
+
+	blk_start_plug(&plug);
+
+	/* align vbo and bytes to be 512 bytes aligned */
+	lbo = (vbo + bytes + 511) & ~511ull;
+	vbo = vbo & ~511ull;
+	bytes = lbo - vbo;
+
+	vcn = vbo >> cluster_bits;
+	if (!run_lookup_entry(run, vcn, &lcn, &clen, &run_idx)) {
+		err = -ENOENT;
+		goto out;
+	}
+	off = vbo & sbi->cluster_mask;
+	page_idx = 0;
+	page = pages[0];
+
+	for (;;) {
+		lbo = ((u64)lcn << cluster_bits) + off;
+		len = ((u64)clen << cluster_bits) - off;
+new_bio:
+		new = ntfs_alloc_bio(nr_pages - page_idx);
+		if (!new) {
+			err = -ENOMEM;
+			goto out;
+		}
+		if (bio) {
+			bio_chain(bio, new);
+			submit_bio(bio);
+		}
+		bio = new;
+		bio_set_dev(bio, bdev);
+		bio->bi_iter.bi_sector = lbo >> 9;
+		bio->bi_opf = op;
+
+		while (len) {
+			off = vbo & (PAGE_SIZE - 1);
+			add = off + len > PAGE_SIZE ? (PAGE_SIZE - off) : len;
+
+			if (bio_add_page(bio, page, add, off) < add)
+				goto new_bio;
+
+			if (bytes <= add)
+				goto out;
+			bytes -= add;
+			vbo += add;
+
+			if (add + off == PAGE_SIZE) {
+				page_idx += 1;
+				if (WARN_ON(page_idx >= nr_pages)) {
+					err = -EINVAL;
+					goto out;
+				}
+				page = pages[page_idx];
+			}
+
+			if (len <= add)
+				break;
+			len -= add;
+			lbo += add;
+		}
+
+		vcn_next = vcn + clen;
+		if (!run_get_entry(run, ++run_idx, &vcn, &lcn, &clen) ||
+		    vcn != vcn_next) {
+			err = -ENOENT;
+			goto out;
+		}
+		off = 0;
+	}
+out:
+	if (bio) {
+		if (!err)
+			err = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return err;
+}
+
+/*
+ * Helper for ntfs_loadlog_and_replay
+ * fill on-disk logfile range by (-1)
+ * this means empty logfile
+ */
+int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	struct block_device *bdev = sb->s_bdev;
+	u8 cluster_bits = sbi->cluster_bits;
+	struct bio *new, *bio = NULL;
+	CLST lcn, clen;
+	u64 lbo, len;
+	size_t run_idx;
+	struct page *fill;
+	void *kaddr;
+	struct blk_plug plug;
+
+	fill = alloc_page(GFP_KERNEL);
+	if (!fill)
+		return -ENOMEM;
+
+	kaddr = kmap_atomic(fill);
+	memset(kaddr, -1, PAGE_SIZE);
+	kunmap_atomic(kaddr);
+	flush_dcache_page(fill);
+	lock_page(fill);
+
+	if (!run_lookup_entry(run, 0, &lcn, &clen, &run_idx)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	/*
+	 * TODO: try blkdev_issue_write_same
+	 */
+	blk_start_plug(&plug);
+	do {
+		lbo = (u64)lcn << cluster_bits;
+		len = (u64)clen << cluster_bits;
+new_bio:
+		new = ntfs_alloc_bio(BIO_MAX_VECS);
+		if (!new) {
+			err = -ENOMEM;
+			break;
+		}
+		if (bio) {
+			bio_chain(bio, new);
+			submit_bio(bio);
+		}
+		bio = new;
+		bio_set_dev(bio, bdev);
+		bio->bi_opf = REQ_OP_WRITE;
+		bio->bi_iter.bi_sector = lbo >> 9;
+
+		for (;;) {
+			u32 add = len > PAGE_SIZE ? PAGE_SIZE : len;
+
+			if (bio_add_page(bio, fill, add, 0) < add)
+				goto new_bio;
+
+			lbo += add;
+			if (len <= add)
+				break;
+			len -= add;
+		}
+	} while (run_get_entry(run, ++run_idx, NULL, &lcn, &clen));
+
+	if (bio) {
+		if (!err)
+			err = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+out:
+	unlock_page(fill);
+	put_page(fill);
+
+	return err;
+}
+
+int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		    u64 vbo, u64 *lbo, u64 *bytes)
+{
+	u32 off;
+	CLST lcn, len;
+	u8 cluster_bits = sbi->cluster_bits;
+
+	if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &len, NULL))
+		return -ENOENT;
+
+	off = vbo & sbi->cluster_mask;
+	*lbo = lcn == SPARSE_LCN ? -1 : (((u64)lcn << cluster_bits) + off);
+	*bytes = ((u64)len << cluster_bits) - off;
+
+	return 0;
+}
+
+struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	struct inode *inode = new_inode(sb);
+	struct ntfs_inode *ni;
+
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	ni = ntfs_i(inode);
+
+	err = mi_format_new(&ni->mi, sbi, rno, dir ? RECORD_FLAG_DIR : 0,
+			    false);
+	if (err)
+		goto out;
+
+	inode->i_ino = rno;
+	if (insert_inode_locked(inode) < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+out:
+	if (err) {
+		iput(inode);
+		ni = ERR_PTR(err);
+	}
+	return ni;
+}
+
+/*
+ * O:BAG:BAD:(A;OICI;FA;;;WD)
+ * owner S-1-5-32-544 (Administrators)
+ * group S-1-5-32-544 (Administrators)
+ * ACE: allow S-1-1-0 (Everyone) with FILE_ALL_ACCESS
+ */
+const u8 s_default_security[] __aligned(8) = {
+	0x01, 0x00, 0x04, 0x80, 0x30, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x02, 0x00, 0x1C, 0x00,
+	0x01, 0x00, 0x00, 0x00, 0x00, 0x03, 0x14, 0x00, 0xFF, 0x01, 0x1F, 0x00,
+	0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00,
+	0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x20, 0x00, 0x00, 0x00,
+	0x20, 0x02, 0x00, 0x00, 0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05,
+	0x20, 0x00, 0x00, 0x00, 0x20, 0x02, 0x00, 0x00,
+};
+
+static_assert(sizeof(s_default_security) == 0x50);
+
+static inline u32 sid_length(const struct SID *sid)
+{
+	return struct_size(sid, SubAuthority, sid->SubAuthorityCount);
+}
+
+/*
+ * Thanks Mark Harmstone for idea
+ */
+static bool is_acl_valid(const struct ACL *acl, u32 len)
+{
+	const struct ACE_HEADER *ace;
+	u32 i;
+	u16 ace_count, ace_size;
+
+	if (acl->AclRevision != ACL_REVISION &&
+	    acl->AclRevision != ACL_REVISION_DS) {
+		/*
+		 * This value should be ACL_REVISION, unless the ACL contains an
+		 * object-specific ACE, in which case this value must be ACL_REVISION_DS.
+		 * All ACEs in an ACL must be at the same revision level.
+		 */
+		return false;
+	}
+
+	if (acl->Sbz1)
+		return false;
+
+	if (le16_to_cpu(acl->AclSize) > len)
+		return false;
+
+	if (acl->Sbz2)
+		return false;
+
+	len -= sizeof(struct ACL);
+	ace = (struct ACE_HEADER *)&acl[1];
+	ace_count = le16_to_cpu(acl->AceCount);
+
+	for (i = 0; i < ace_count; i++) {
+		if (len < sizeof(struct ACE_HEADER))
+			return false;
+
+		ace_size = le16_to_cpu(ace->AceSize);
+		if (len < ace_size)
+			return false;
+
+		len -= ace_size;
+		ace = Add2Ptr(ace, ace_size);
+	}
+
+	return true;
+}
+
+bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len)
+{
+	u32 sd_owner, sd_group, sd_sacl, sd_dacl;
+
+	if (len < sizeof(struct SECURITY_DESCRIPTOR_RELATIVE))
+		return false;
+
+	if (sd->Revision != 1)
+		return false;
+
+	if (sd->Sbz1)
+		return false;
+
+	if (!(sd->Control & SE_SELF_RELATIVE))
+		return false;
+
+	sd_owner = le32_to_cpu(sd->Owner);
+	if (sd_owner) {
+		const struct SID *owner = Add2Ptr(sd, sd_owner);
+
+		if (sd_owner + offsetof(struct SID, SubAuthority) > len)
+			return false;
+
+		if (owner->Revision != 1)
+			return false;
+
+		if (sd_owner + sid_length(owner) > len)
+			return false;
+	}
+
+	sd_group = le32_to_cpu(sd->Group);
+	if (sd_group) {
+		const struct SID *group = Add2Ptr(sd, sd_group);
+
+		if (sd_group + offsetof(struct SID, SubAuthority) > len)
+			return false;
+
+		if (group->Revision != 1)
+			return false;
+
+		if (sd_group + sid_length(group) > len)
+			return false;
+	}
+
+	sd_sacl = le32_to_cpu(sd->Sacl);
+	if (sd_sacl) {
+		const struct ACL *sacl = Add2Ptr(sd, sd_sacl);
+
+		if (sd_sacl + sizeof(struct ACL) > len)
+			return false;
+
+		if (!is_acl_valid(sacl, len - sd_sacl))
+			return false;
+	}
+
+	sd_dacl = le32_to_cpu(sd->Dacl);
+	if (sd_dacl) {
+		const struct ACL *dacl = Add2Ptr(sd, sd_dacl);
+
+		if (sd_dacl + sizeof(struct ACL) > len)
+			return false;
+
+		if (!is_acl_valid(dacl, len - sd_dacl))
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * ntfs_security_init
+ *
+ * loads and parse $Secure
+ */
+int ntfs_security_init(struct ntfs_sb_info *sbi)
+{
+	int err;
+	struct super_block *sb = sbi->sb;
+	struct inode *inode;
+	struct ntfs_inode *ni;
+	struct MFT_REF ref;
+	struct ATTRIB *attr;
+	struct ATTR_LIST_ENTRY *le;
+	u64 sds_size;
+	size_t cnt, off;
+	struct NTFS_DE *ne;
+	struct NTFS_DE_SII *sii_e;
+	struct ntfs_fnd *fnd_sii = NULL;
+	const struct INDEX_ROOT *root_sii;
+	const struct INDEX_ROOT *root_sdh;
+	struct ntfs_index *indx_sdh = &sbi->security.index_sdh;
+	struct ntfs_index *indx_sii = &sbi->security.index_sii;
+
+	ref.low = cpu_to_le32(MFT_REC_SECURE);
+	ref.high = 0;
+	ref.seq = cpu_to_le16(MFT_REC_SECURE);
+
+	inode = ntfs_iget5(sb, &ref, &NAME_SECURE);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		ntfs_err(sb, "Failed to load $Secure.");
+		inode = NULL;
+		goto out;
+	}
+
+	ni = ntfs_i(inode);
+
+	le = NULL;
+
+	attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SDH_NAME,
+			    ARRAY_SIZE(SDH_NAME), NULL, NULL);
+	if (!attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	root_sdh = resident_data(attr);
+	if (root_sdh->type != ATTR_ZERO ||
+	    root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = indx_init(indx_sdh, sbi, attr, INDEX_MUTEX_SDH);
+	if (err)
+		goto out;
+
+	attr = ni_find_attr(ni, attr, &le, ATTR_ROOT, SII_NAME,
+			    ARRAY_SIZE(SII_NAME), NULL, NULL);
+	if (!attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	root_sii = resident_data(attr);
+	if (root_sii->type != ATTR_ZERO ||
+	    root_sii->rule != NTFS_COLLATION_TYPE_UINT) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = indx_init(indx_sii, sbi, attr, INDEX_MUTEX_SII);
+	if (err)
+		goto out;
+
+	fnd_sii = fnd_get();
+	if (!fnd_sii) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	sds_size = inode->i_size;
+
+	/* Find the last valid Id */
+	sbi->security.next_id = SECURITY_ID_FIRST;
+	/* Always write new security at the end of bucket */
+	sbi->security.next_off =
+		Quad2Align(sds_size - SecurityDescriptorsBlockSize);
+
+	cnt = 0;
+	off = 0;
+	ne = NULL;
+
+	for (;;) {
+		u32 next_id;
+
+		err = indx_find_raw(indx_sii, ni, root_sii, &ne, &off, fnd_sii);
+		if (err || !ne)
+			break;
+
+		sii_e = (struct NTFS_DE_SII *)ne;
+		if (le16_to_cpu(ne->view.data_size) < SIZEOF_SECURITY_HDR)
+			continue;
+
+		next_id = le32_to_cpu(sii_e->sec_id) + 1;
+		if (next_id >= sbi->security.next_id)
+			sbi->security.next_id = next_id;
+
+		cnt += 1;
+	}
+
+	sbi->security.ni = ni;
+	inode = NULL;
+out:
+	iput(inode);
+	fnd_put(fnd_sii);
+
+	return err;
+}
+
+/*
+ * ntfs_get_security_by_id
+ *
+ * reads security descriptor by id
+ */
+int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id,
+			    struct SECURITY_DESCRIPTOR_RELATIVE **sd,
+			    size_t *size)
+{
+	int err;
+	int diff;
+	struct ntfs_inode *ni = sbi->security.ni;
+	struct ntfs_index *indx = &sbi->security.index_sii;
+	void *p = NULL;
+	struct NTFS_DE_SII *sii_e;
+	struct ntfs_fnd *fnd_sii;
+	struct SECURITY_HDR d_security;
+	const struct INDEX_ROOT *root_sii;
+	u32 t32;
+
+	*sd = NULL;
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY);
+
+	fnd_sii = fnd_get();
+	if (!fnd_sii) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	root_sii = indx_get_root(indx, ni, NULL, NULL);
+	if (!root_sii) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Try to find this SECURITY descriptor in SII indexes */
+	err = indx_find(indx, ni, root_sii, &security_id, sizeof(security_id),
+			NULL, &diff, (struct NTFS_DE **)&sii_e, fnd_sii);
+	if (err)
+		goto out;
+
+	if (diff)
+		goto out;
+
+	t32 = le32_to_cpu(sii_e->sec_hdr.size);
+	if (t32 < SIZEOF_SECURITY_HDR) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (t32 > SIZEOF_SECURITY_HDR + 0x10000) {
+		/*
+		 * looks like too big security. 0x10000 - is arbitrary big number
+		 */
+		err = -EFBIG;
+		goto out;
+	}
+
+	*size = t32 - SIZEOF_SECURITY_HDR;
+
+	p = ntfs_malloc(*size);
+	if (!p) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = ntfs_read_run_nb(sbi, &ni->file.run,
+			       le64_to_cpu(sii_e->sec_hdr.off), &d_security,
+			       sizeof(d_security), NULL);
+	if (err)
+		goto out;
+
+	if (memcmp(&d_security, &sii_e->sec_hdr, SIZEOF_SECURITY_HDR)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = ntfs_read_run_nb(sbi, &ni->file.run,
+			       le64_to_cpu(sii_e->sec_hdr.off) +
+				       SIZEOF_SECURITY_HDR,
+			       p, *size, NULL);
+	if (err)
+		goto out;
+
+	*sd = p;
+	p = NULL;
+
+out:
+	ntfs_free(p);
+	fnd_put(fnd_sii);
+	ni_unlock(ni);
+
+	return err;
+}
+
+/*
+ * ntfs_insert_security
+ *
+ * inserts security descriptor into $Secure::SDS
+ *
+ * SECURITY Descriptor Stream data is organized into chunks of 256K bytes
+ * and it contains a mirror copy of each security descriptor.  When writing
+ * to a security descriptor at location X, another copy will be written at
+ * location (X+256K).
+ * When writing a security descriptor that will cross the 256K boundary,
+ * the pointer will be advanced by 256K to skip
+ * over the mirror portion.
+ */
+int ntfs_insert_security(struct ntfs_sb_info *sbi,
+			 const struct SECURITY_DESCRIPTOR_RELATIVE *sd,
+			 u32 size_sd, __le32 *security_id, bool *inserted)
+{
+	int err, diff;
+	struct ntfs_inode *ni = sbi->security.ni;
+	struct ntfs_index *indx_sdh = &sbi->security.index_sdh;
+	struct ntfs_index *indx_sii = &sbi->security.index_sii;
+	struct NTFS_DE_SDH *e;
+	struct NTFS_DE_SDH sdh_e;
+	struct NTFS_DE_SII sii_e;
+	struct SECURITY_HDR *d_security;
+	u32 new_sec_size = size_sd + SIZEOF_SECURITY_HDR;
+	u32 aligned_sec_size = Quad2Align(new_sec_size);
+	struct SECURITY_KEY hash_key;
+	struct ntfs_fnd *fnd_sdh = NULL;
+	const struct INDEX_ROOT *root_sdh;
+	const struct INDEX_ROOT *root_sii;
+	u64 mirr_off, new_sds_size;
+	u32 next, left;
+
+	static_assert((1 << Log2OfSecurityDescriptorsBlockSize) ==
+		      SecurityDescriptorsBlockSize);
+
+	hash_key.hash = security_hash(sd, size_sd);
+	hash_key.sec_id = SECURITY_ID_INVALID;
+
+	if (inserted)
+		*inserted = false;
+	*security_id = SECURITY_ID_INVALID;
+
+	/* Allocate a temporal buffer*/
+	d_security = ntfs_zalloc(aligned_sec_size);
+	if (!d_security)
+		return -ENOMEM;
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY);
+
+	fnd_sdh = fnd_get();
+	if (!fnd_sdh) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	root_sdh = indx_get_root(indx_sdh, ni, NULL, NULL);
+	if (!root_sdh) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	root_sii = indx_get_root(indx_sii, ni, NULL, NULL);
+	if (!root_sii) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Check if such security already exists
+	 * use "SDH" and hash -> to get the offset in "SDS"
+	 */
+	err = indx_find(indx_sdh, ni, root_sdh, &hash_key, sizeof(hash_key),
+			&d_security->key.sec_id, &diff, (struct NTFS_DE **)&e,
+			fnd_sdh);
+	if (err)
+		goto out;
+
+	while (e) {
+		if (le32_to_cpu(e->sec_hdr.size) == new_sec_size) {
+			err = ntfs_read_run_nb(sbi, &ni->file.run,
+					       le64_to_cpu(e->sec_hdr.off),
+					       d_security, new_sec_size, NULL);
+			if (err)
+				goto out;
+
+			if (le32_to_cpu(d_security->size) == new_sec_size &&
+			    d_security->key.hash == hash_key.hash &&
+			    !memcmp(d_security + 1, sd, size_sd)) {
+				*security_id = d_security->key.sec_id;
+				/*such security already exists*/
+				err = 0;
+				goto out;
+			}
+		}
+
+		err = indx_find_sort(indx_sdh, ni, root_sdh,
+				     (struct NTFS_DE **)&e, fnd_sdh);
+		if (err)
+			goto out;
+
+		if (!e || e->key.hash != hash_key.hash)
+			break;
+	}
+
+	/* Zero unused space */
+	next = sbi->security.next_off & (SecurityDescriptorsBlockSize - 1);
+	left = SecurityDescriptorsBlockSize - next;
+
+	/* Zero gap until SecurityDescriptorsBlockSize */
+	if (left < new_sec_size) {
+		/* zero "left" bytes from sbi->security.next_off */
+		sbi->security.next_off += SecurityDescriptorsBlockSize + left;
+	}
+
+	/* Zero tail of previous security */
+	//used = ni->vfs_inode.i_size & (SecurityDescriptorsBlockSize - 1);
+
+	/*
+	 * Example:
+	 * 0x40438 == ni->vfs_inode.i_size
+	 * 0x00440 == sbi->security.next_off
+	 * need to zero [0x438-0x440)
+	 * if (next > used) {
+	 *  u32 tozero = next - used;
+	 *  zero "tozero" bytes from sbi->security.next_off - tozero
+	 */
+
+	/* format new security descriptor */
+	d_security->key.hash = hash_key.hash;
+	d_security->key.sec_id = cpu_to_le32(sbi->security.next_id);
+	d_security->off = cpu_to_le64(sbi->security.next_off);
+	d_security->size = cpu_to_le32(new_sec_size);
+	memcpy(d_security + 1, sd, size_sd);
+
+	/* Write main SDS bucket */
+	err = ntfs_sb_write_run(sbi, &ni->file.run, sbi->security.next_off,
+				d_security, aligned_sec_size);
+
+	if (err)
+		goto out;
+
+	mirr_off = sbi->security.next_off + SecurityDescriptorsBlockSize;
+	new_sds_size = mirr_off + aligned_sec_size;
+
+	if (new_sds_size > ni->vfs_inode.i_size) {
+		err = attr_set_size(ni, ATTR_DATA, SDS_NAME,
+				    ARRAY_SIZE(SDS_NAME), &ni->file.run,
+				    new_sds_size, &new_sds_size, false, NULL);
+		if (err)
+			goto out;
+	}
+
+	/* Write copy SDS bucket */
+	err = ntfs_sb_write_run(sbi, &ni->file.run, mirr_off, d_security,
+				aligned_sec_size);
+	if (err)
+		goto out;
+
+	/* Fill SII entry */
+	sii_e.de.view.data_off =
+		cpu_to_le16(offsetof(struct NTFS_DE_SII, sec_hdr));
+	sii_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR);
+	sii_e.de.view.res = 0;
+	sii_e.de.size = cpu_to_le16(SIZEOF_SII_DIRENTRY);
+	sii_e.de.key_size = cpu_to_le16(sizeof(d_security->key.sec_id));
+	sii_e.de.flags = 0;
+	sii_e.de.res = 0;
+	sii_e.sec_id = d_security->key.sec_id;
+	memcpy(&sii_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR);
+
+	err = indx_insert_entry(indx_sii, ni, &sii_e.de, NULL, NULL);
+	if (err)
+		goto out;
+
+	/* Fill SDH entry */
+	sdh_e.de.view.data_off =
+		cpu_to_le16(offsetof(struct NTFS_DE_SDH, sec_hdr));
+	sdh_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR);
+	sdh_e.de.view.res = 0;
+	sdh_e.de.size = cpu_to_le16(SIZEOF_SDH_DIRENTRY);
+	sdh_e.de.key_size = cpu_to_le16(sizeof(sdh_e.key));
+	sdh_e.de.flags = 0;
+	sdh_e.de.res = 0;
+	sdh_e.key.hash = d_security->key.hash;
+	sdh_e.key.sec_id = d_security->key.sec_id;
+	memcpy(&sdh_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR);
+	sdh_e.magic[0] = cpu_to_le16('I');
+	sdh_e.magic[1] = cpu_to_le16('I');
+
+	fnd_clear(fnd_sdh);
+	err = indx_insert_entry(indx_sdh, ni, &sdh_e.de, (void *)(size_t)1,
+				fnd_sdh);
+	if (err)
+		goto out;
+
+	*security_id = d_security->key.sec_id;
+	if (inserted)
+		*inserted = true;
+
+	/* Update Id and offset for next descriptor */
+	sbi->security.next_id += 1;
+	sbi->security.next_off += aligned_sec_size;
+
+out:
+	fnd_put(fnd_sdh);
+	mark_inode_dirty(&ni->vfs_inode);
+	ni_unlock(ni);
+	ntfs_free(d_security);
+
+	return err;
+}
+
+/*
+ * ntfs_reparse_init
+ *
+ * loads and parse $Extend/$Reparse
+ */
+int ntfs_reparse_init(struct ntfs_sb_info *sbi)
+{
+	int err;
+	struct ntfs_inode *ni = sbi->reparse.ni;
+	struct ntfs_index *indx = &sbi->reparse.index_r;
+	struct ATTRIB *attr;
+	struct ATTR_LIST_ENTRY *le;
+	const struct INDEX_ROOT *root_r;
+
+	if (!ni)
+		return 0;
+
+	le = NULL;
+	attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SR_NAME,
+			    ARRAY_SIZE(SR_NAME), NULL, NULL);
+	if (!attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	root_r = resident_data(attr);
+	if (root_r->type != ATTR_ZERO ||
+	    root_r->rule != NTFS_COLLATION_TYPE_UINTS) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = indx_init(indx, sbi, attr, INDEX_MUTEX_SR);
+	if (err)
+		goto out;
+
+out:
+	return err;
+}
+
+/*
+ * ntfs_objid_init
+ *
+ * loads and parse $Extend/$ObjId
+ */
+int ntfs_objid_init(struct ntfs_sb_info *sbi)
+{
+	int err;
+	struct ntfs_inode *ni = sbi->objid.ni;
+	struct ntfs_index *indx = &sbi->objid.index_o;
+	struct ATTRIB *attr;
+	struct ATTR_LIST_ENTRY *le;
+	const struct INDEX_ROOT *root;
+
+	if (!ni)
+		return 0;
+
+	le = NULL;
+	attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SO_NAME,
+			    ARRAY_SIZE(SO_NAME), NULL, NULL);
+	if (!attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	root = resident_data(attr);
+	if (root->type != ATTR_ZERO ||
+	    root->rule != NTFS_COLLATION_TYPE_UINTS) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = indx_init(indx, sbi, attr, INDEX_MUTEX_SO);
+	if (err)
+		goto out;
+
+out:
+	return err;
+}
+
+int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid)
+{
+	int err;
+	struct ntfs_inode *ni = sbi->objid.ni;
+	struct ntfs_index *indx = &sbi->objid.index_o;
+
+	if (!ni)
+		return -EINVAL;
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_OBJID);
+
+	err = indx_delete_entry(indx, ni, guid, sizeof(*guid), NULL);
+
+	mark_inode_dirty(&ni->vfs_inode);
+	ni_unlock(ni);
+
+	return err;
+}
+
+int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag,
+			const struct MFT_REF *ref)
+{
+	int err;
+	struct ntfs_inode *ni = sbi->reparse.ni;
+	struct ntfs_index *indx = &sbi->reparse.index_r;
+	struct NTFS_DE_R re;
+
+	if (!ni)
+		return -EINVAL;
+
+	memset(&re, 0, sizeof(re));
+
+	re.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_R, zero));
+	re.de.size = cpu_to_le16(sizeof(struct NTFS_DE_R));
+	re.de.key_size = cpu_to_le16(sizeof(re.key));
+
+	re.key.ReparseTag = rtag;
+	memcpy(&re.key.ref, ref, sizeof(*ref));
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE);
+
+	err = indx_insert_entry(indx, ni, &re.de, NULL, NULL);
+
+	mark_inode_dirty(&ni->vfs_inode);
+	ni_unlock(ni);
+
+	return err;
+}
+
+int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag,
+			const struct MFT_REF *ref)
+{
+	int err, diff;
+	struct ntfs_inode *ni = sbi->reparse.ni;
+	struct ntfs_index *indx = &sbi->reparse.index_r;
+	struct ntfs_fnd *fnd = NULL;
+	struct REPARSE_KEY rkey;
+	struct NTFS_DE_R *re;
+	struct INDEX_ROOT *root_r;
+
+	if (!ni)
+		return -EINVAL;
+
+	rkey.ReparseTag = rtag;
+	rkey.ref = *ref;
+
+	mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE);
+
+	if (rtag) {
+		err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL);
+		goto out1;
+	}
+
+	fnd = fnd_get();
+	if (!fnd) {
+		err = -ENOMEM;
+		goto out1;
+	}
+
+	root_r = indx_get_root(indx, ni, NULL, NULL);
+	if (!root_r) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* 1 - forces to ignore rkey.ReparseTag when comparing keys */
+	err = indx_find(indx, ni, root_r, &rkey, sizeof(rkey), (void *)1, &diff,
+			(struct NTFS_DE **)&re, fnd);
+	if (err)
+		goto out;
+
+	if (memcmp(&re->key.ref, ref, sizeof(*ref))) {
+		/* Impossible. Looks like volume corrupt?*/
+		goto out;
+	}
+
+	memcpy(&rkey, &re->key, sizeof(rkey));
+
+	fnd_put(fnd);
+	fnd = NULL;
+
+	err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL);
+	if (err)
+		goto out;
+
+out:
+	fnd_put(fnd);
+
+out1:
+	mark_inode_dirty(&ni->vfs_inode);
+	ni_unlock(ni);
+
+	return err;
+}
+
+static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn,
+					  CLST len)
+{
+	ntfs_unmap_meta(sbi->sb, lcn, len);
+	ntfs_discard(sbi, lcn, len);
+}
+
+void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
+{
+	CLST end, i;
+	struct wnd_bitmap *wnd = &sbi->used.bitmap;
+
+	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
+	if (!wnd_is_used(wnd, lcn, len)) {
+		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+
+		end = lcn + len;
+		len = 0;
+		for (i = lcn; i < end; i++) {
+			if (wnd_is_used(wnd, i, 1)) {
+				if (!len)
+					lcn = i;
+				len += 1;
+				continue;
+			}
+
+			if (!len)
+				continue;
+
+			if (trim)
+				ntfs_unmap_and_discard(sbi, lcn, len);
+
+			wnd_set_free(wnd, lcn, len);
+			len = 0;
+		}
+
+		if (!len)
+			goto out;
+	}
+
+	if (trim)
+		ntfs_unmap_and_discard(sbi, lcn, len);
+	wnd_set_free(wnd, lcn, len);
+
+out:
+	up_write(&wnd->rw_lock);
+}
+
+/*
+ * run_deallocate
+ *
+ * deallocate clusters
+ */
+int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim)
+{
+	CLST lcn, len;
+	size_t idx = 0;
+
+	while (run_get_entry(run, idx++, NULL, &lcn, &len)) {
+		if (lcn == SPARSE_LCN)
+			continue;
+
+		mark_as_free_ex(sbi, lcn, len, trim);
+	}
+
+	return 0;
+}
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
new file mode 100644
index 000000000..931a7241e
--- /dev/null
+++ b/fs/ntfs3/index.c
@@ -0,0 +1,2641 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+static const struct INDEX_NAMES {
+	const __le16 *name;
+	u8 name_len;
+} s_index_names[INDEX_MUTEX_TOTAL] = {
+	{ I30_NAME, ARRAY_SIZE(I30_NAME) }, { SII_NAME, ARRAY_SIZE(SII_NAME) },
+	{ SDH_NAME, ARRAY_SIZE(SDH_NAME) }, { SO_NAME, ARRAY_SIZE(SO_NAME) },
+	{ SQ_NAME, ARRAY_SIZE(SQ_NAME) },   { SR_NAME, ARRAY_SIZE(SR_NAME) },
+};
+
+/*
+ * compare two names in index
+ * if l1 != 0
+ *   both names are little endian on-disk ATTR_FILE_NAME structs
+ * else
+ *   key1 - cpu_str, key2 - ATTR_FILE_NAME
+ */
+static int cmp_fnames(const void *key1, size_t l1, const void *key2, size_t l2,
+		      const void *data)
+{
+	const struct ATTR_FILE_NAME *f2 = key2;
+	const struct ntfs_sb_info *sbi = data;
+	const struct ATTR_FILE_NAME *f1;
+	u16 fsize2;
+	bool both_case;
+
+	if (l2 <= offsetof(struct ATTR_FILE_NAME, name))
+		return -1;
+
+	fsize2 = fname_full_size(f2);
+	if (l2 < fsize2)
+		return -1;
+
+	both_case = f2->type != FILE_NAME_DOS /*&& !sbi->options.nocase*/;
+	if (!l1) {
+		const struct le_str *s2 = (struct le_str *)&f2->name_len;
+
+		/*
+		 * If names are equal (case insensitive)
+		 * try to compare it case sensitive
+		 */
+		return ntfs_cmp_names_cpu(key1, s2, sbi->upcase, both_case);
+	}
+
+	f1 = key1;
+	return ntfs_cmp_names(f1->name, f1->name_len, f2->name, f2->name_len,
+			      sbi->upcase, both_case);
+}
+
+/* $SII of $Secure and $Q of Quota */
+static int cmp_uint(const void *key1, size_t l1, const void *key2, size_t l2,
+		    const void *data)
+{
+	const u32 *k1 = key1;
+	const u32 *k2 = key2;
+
+	if (l2 < sizeof(u32))
+		return -1;
+
+	if (*k1 < *k2)
+		return -1;
+	if (*k1 > *k2)
+		return 1;
+	return 0;
+}
+
+/* $SDH of $Secure */
+static int cmp_sdh(const void *key1, size_t l1, const void *key2, size_t l2,
+		   const void *data)
+{
+	const struct SECURITY_KEY *k1 = key1;
+	const struct SECURITY_KEY *k2 = key2;
+	u32 t1, t2;
+
+	if (l2 < sizeof(struct SECURITY_KEY))
+		return -1;
+
+	t1 = le32_to_cpu(k1->hash);
+	t2 = le32_to_cpu(k2->hash);
+
+	/* First value is a hash value itself */
+	if (t1 < t2)
+		return -1;
+	if (t1 > t2)
+		return 1;
+
+	/* Second value is security Id */
+	if (data) {
+		t1 = le32_to_cpu(k1->sec_id);
+		t2 = le32_to_cpu(k2->sec_id);
+		if (t1 < t2)
+			return -1;
+		if (t1 > t2)
+			return 1;
+	}
+
+	return 0;
+}
+
+/* $O of ObjId and "$R" for Reparse */
+static int cmp_uints(const void *key1, size_t l1, const void *key2, size_t l2,
+		     const void *data)
+{
+	const __le32 *k1 = key1;
+	const __le32 *k2 = key2;
+	size_t count;
+
+	if ((size_t)data == 1) {
+		/*
+		 * ni_delete_all -> ntfs_remove_reparse -> delete all with this reference
+		 * k1, k2 - pointers to REPARSE_KEY
+		 */
+
+		k1 += 1; // skip REPARSE_KEY.ReparseTag
+		k2 += 1; // skip REPARSE_KEY.ReparseTag
+		if (l2 <= sizeof(int))
+			return -1;
+		l2 -= sizeof(int);
+		if (l1 <= sizeof(int))
+			return 1;
+		l1 -= sizeof(int);
+	}
+
+	if (l2 < sizeof(int))
+		return -1;
+
+	for (count = min(l1, l2) >> 2; count > 0; --count, ++k1, ++k2) {
+		u32 t1 = le32_to_cpu(*k1);
+		u32 t2 = le32_to_cpu(*k2);
+
+		if (t1 > t2)
+			return 1;
+		if (t1 < t2)
+			return -1;
+	}
+
+	if (l1 > l2)
+		return 1;
+	if (l1 < l2)
+		return -1;
+
+	return 0;
+}
+
+static inline NTFS_CMP_FUNC get_cmp_func(const struct INDEX_ROOT *root)
+{
+	switch (root->type) {
+	case ATTR_NAME:
+		if (root->rule == NTFS_COLLATION_TYPE_FILENAME)
+			...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 03/10] fs/ntfs3: Add bitmap

[Konstantin K. <alm...@pa...>]

This adds bitmap

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/bitfunc.c |  135 ++++
 fs/ntfs3/bitmap.c  | 1519 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 1654 insertions(+)
 create mode 100644 fs/ntfs3/bitfunc.c
 create mode 100644 fs/ntfs3/bitmap.c

diff --git a/fs/ntfs3/bitfunc.c b/fs/ntfs3/bitfunc.c
new file mode 100644
index 000000000..2de5faef2
--- /dev/null
+++ b/fs/ntfs3/bitfunc.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+#define BITS_IN_SIZE_T (sizeof(size_t) * 8)
+
+/*
+ * fill_mask[i] - first i bits are '1' , i = 0,1,2,3,4,5,6,7,8
+ * fill_mask[i] = 0xFF >> (8-i)
+ */
+static const u8 fill_mask[] = { 0x00, 0x01, 0x03, 0x07, 0x0F,
+				0x1F, 0x3F, 0x7F, 0xFF };
+
+/*
+ * zero_mask[i] - first i bits are '0' , i = 0,1,2,3,4,5,6,7,8
+ * zero_mask[i] = 0xFF << i
+ */
+static const u8 zero_mask[] = { 0xFF, 0xFE, 0xFC, 0xF8, 0xF0,
+				0xE0, 0xC0, 0x80, 0x00 };
+
+/*
+ * are_bits_clear
+ *
+ * Returns true if all bits [bit, bit+nbits) are zeros "0"
+ */
+bool are_bits_clear(const ulong *lmap, size_t bit, size_t nbits)
+{
+	size_t pos = bit & 7;
+	const u8 *map = (u8 *)lmap + (bit >> 3);
+
+	if (pos) {
+		if (8 - pos >= nbits)
+			return !nbits || !(*map & fill_mask[pos + nbits] &
+					   zero_mask[pos]);
+
+		if (*map++ & zero_mask[pos])
+			return false;
+		nbits -= 8 - pos;
+	}
+
+	pos = ((size_t)map) & (sizeof(size_t) - 1);
+	if (pos) {
+		pos = sizeof(size_t) - pos;
+		if (nbits >= pos * 8) {
+			for (nbits -= pos * 8; pos; pos--, map++) {
+				if (*map)
+					return false;
+			}
+		}
+	}
+
+	for (pos = nbits / BITS_IN_SIZE_T; pos; pos--, map += sizeof(size_t)) {
+		if (*((size_t *)map))
+			return false;
+	}
+
+	for (pos = (nbits % BITS_IN_SIZE_T) >> 3; pos; pos--, map++) {
+		if (*map)
+			return false;
+	}
+
+	pos = nbits & 7;
+	if (pos && (*map & fill_mask[pos]))
+		return false;
+
+	// All bits are zero
+	return true;
+}
+
+/*
+ * are_bits_set
+ *
+ * Returns true if all bits [bit, bit+nbits) are ones "1"
+ */
+bool are_bits_set(const ulong *lmap, size_t bit, size_t nbits)
+{
+	u8 mask;
+	size_t pos = bit & 7;
+	const u8 *map = (u8 *)lmap + (bit >> 3);
+
+	if (pos) {
+		if (8 - pos >= nbits) {
+			mask = fill_mask[pos + nbits] & zero_mask[pos];
+			return !nbits || (*map & mask) == mask;
+		}
+
+		mask = zero_mask[pos];
+		if ((*map++ & mask) != mask)
+			return false;
+		nbits -= 8 - pos;
+	}
+
+	pos = ((size_t)map) & (sizeof(size_t) - 1);
+	if (pos) {
+		pos = sizeof(size_t) - pos;
+		if (nbits >= pos * 8) {
+			for (nbits -= pos * 8; pos; pos--, map++) {
+				if (*map != 0xFF)
+					return false;
+			}
+		}
+	}
+
+	for (pos = nbits / BITS_IN_SIZE_T; pos; pos--, map += sizeof(size_t)) {
+		if (*((size_t *)map) != MINUS_ONE_T)
+			return false;
+	}
+
+	for (pos = (nbits % BITS_IN_SIZE_T) >> 3; pos; pos--, map++) {
+		if (*map != 0xFF)
+			return false;
+	}
+
+	pos = nbits & 7;
+	if (pos) {
+		u8 mask = fill_mask[pos];
+
+		if ((*map & mask) != mask)
+			return false;
+	}
+
+	// All bits are ones
+	return true;
+}
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
new file mode 100644
index 000000000..32aab0031
--- /dev/null
+++ b/fs/ntfs3/bitmap.c
@@ -0,0 +1,1519 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ * This code builds two trees of free clusters extents.
+ * Trees are sorted by start of extent and by length of extent.
+ * NTFS_MAX_WND_EXTENTS defines the maximum number of elements in trees.
+ * In extreme case code reads on-disk bitmap to find free clusters
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/*
+ * Maximum number of extents in tree.
+ */
+#define NTFS_MAX_WND_EXTENTS (32u * 1024u)
+
+struct rb_node_key {
+	struct rb_node node;
+	size_t key;
+};
+
+/*
+ * Tree is sorted by start (key)
+ */
+struct e_node {
+	struct rb_node_key start; /* Tree sorted by start */
+	struct rb_node_key count; /* Tree sorted by len*/
+};
+
+static int wnd_rescan(struct wnd_bitmap *wnd);
+static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw);
+static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits);
+
+static struct kmem_cache *ntfs_enode_cachep;
+
+int __init ntfs3_init_bitmap(void)
+{
+	ntfs_enode_cachep =
+		kmem_cache_create("ntfs3_enode_cache", sizeof(struct e_node), 0,
+				  SLAB_RECLAIM_ACCOUNT, NULL);
+	return ntfs_enode_cachep ? 0 : -ENOMEM;
+}
+
+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;
+}
+
+/*
+ * b_pos + b_len - biggest fragment
+ * Scan range [wpos wbits) window 'buf'
+ * Returns -1 if not found
+ */
+static size_t wnd_scan(const ulong *buf, size_t wbit, u32 wpos, u32 wend,
+		       size_t to_alloc, size_t *prev_tail, size_t *b_pos,
+		       size_t *b_len)
+{
+	while (wpos < wend) {
+		size_t free_len;
+		u32 free_bits, end;
+		u32 used = find_next_zero_bit(buf, wend, wpos);
+
+		if (used >= wend) {
+			if (*b_len < *prev_tail) {
+				*b_pos = wbit - *prev_tail;
+				*b_len = *prev_tail;
+			}
+
+			*prev_tail = 0;
+			return -1;
+		}
+
+		if (used > wpos) {
+			wpos = used;
+			if (*b_len < *prev_tail) {
+				*b_pos = wbit - *prev_tail;
+				*b_len = *prev_tail;
+			}
+
+			*prev_tail = 0;
+		}
+
+		/*
+		 * Now we have a fragment [wpos, wend) staring with 0
+		 */
+		end = wpos + to_alloc - *prev_tail;
+		free_bits = find_next_bit(buf, min(end, wend), wpos);
+
+		free_len = *prev_tail + free_bits - wpos;
+
+		if (*b_len < free_len) {
+			*b_pos = wbit + wpos - *prev_tail;
+			*b_len = free_len;
+		}
+
+		if (free_len >= to_alloc)
+			return wbit + wpos - *prev_tail;
+
+		if (free_bits >= wend) {
+			*prev_tail += free_bits - wpos;
+			return -1;
+		}
+
+		wpos = free_bits + 1;
+
+		*prev_tail = 0;
+	}
+
+	return -1;
+}
+
+/*
+ * wnd_close
+ *
+ * Frees all resources
+ */
+void wnd_close(struct wnd_bitmap *wnd)
+{
+	struct rb_node *node, *next;
+
+	ntfs_free(wnd->free_bits);
+	run_close(&wnd->run);
+
+	node = rb_first(&wnd->start_tree);
+
+	while (node) {
+		next = rb_next(node);
+		rb_erase(node, &wnd->start_tree);
+		kmem_cache_free(ntfs_enode_cachep,
+				rb_entry(node, struct e_node, start.node));
+		node = next;
+	}
+}
+
+static struct rb_node *rb_lookup(struct rb_root *root, size_t v)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *r = NULL;
+
+	while (*p) {
+		struct rb_node_key *k;
+
+		k = rb_entry(*p, struct rb_node_key, node);
+		if (v < k->key) {
+			p = &(*p)->rb_left;
+		} else if (v > k->key) {
+			r = &k->node;
+			p = &(*p)->rb_right;
+		} else {
+			return &k->node;
+		}
+	}
+
+	return r;
+}
+
+/*
+ * rb_insert_count
+ *
+ * Helper function to insert special kind of 'count' tree
+ */
+static inline bool rb_insert_count(struct rb_root *root, struct e_node *e)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	size_t e_ckey = e->count.key;
+	size_t e_skey = e->start.key;
+
+	while (*p) {
+		struct e_node *k =
+			rb_entry(parent = *p, struct e_node, count.node);
+
+		if (e_ckey > k->count.key) {
+			p = &(*p)->rb_left;
+		} else if (e_ckey < k->count.key) {
+			p = &(*p)->rb_right;
+		} else if (e_skey < k->start.key) {
+			p = &(*p)->rb_left;
+		} else if (e_skey > k->start.key) {
+			p = &(*p)->rb_right;
+		} else {
+			WARN_ON(1);
+			return false;
+		}
+	}
+
+	rb_link_node(&e->count.node, parent, p);
+	rb_insert_color(&e->count.node, root);
+	return true;
+}
+
+/*
+ * inline bool rb_insert_start
+ *
+ * Helper function to insert special kind of 'start' tree
+ */
+static inline bool rb_insert_start(struct rb_root *root, struct e_node *e)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	size_t e_skey = e->start.key;
+
+	while (*p) {
+		struct e_node *k;
+
+		parent = *p;
+
+		k = rb_entry(parent, struct e_node, start.node);
+		if (e_skey < k->start.key) {
+			p = &(*p)->rb_left;
+		} else if (e_skey > k->start.key) {
+			p = &(*p)->rb_right;
+		} else {
+			WARN_ON(1);
+			return false;
+		}
+	}
+
+	rb_link_node(&e->start.node, parent, p);
+	rb_insert_color(&e->start.node, root);
+	return true;
+}
+
+/*
+ * wnd_add_free_ext
+ *
+ * adds a new extent of free space
+ * build = 1 when building tree
+ */
+static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len,
+			     bool build)
+{
+	struct e_node *e, *e0 = NULL;
+	size_t ib, end_in = bit + len;
+	struct rb_node *n;
+
+	if (build) {
+		/* Use extent_min to filter too short extents */
+		if (wnd->count >= NTFS_MAX_WND_EXTENTS &&
+		    len <= wnd->extent_min) {
+			wnd->uptodated = -1;
+			return;
+		}
+	} else {
+		/* Try to find extent before 'bit' */
+		n = rb_lookup(&wnd->start_tree, bit);
+
+		if (!n) {
+			n = rb_first(&wnd->start_tree);
+		} else {
+			e = rb_entry(n, struct e_node, start.node);
+			n = rb_next(n);
+			if (e->start.key + e->count.key == bit) {
+				/* Remove left */
+				bit = e->start.key;
+				len += e->count.key;
+				rb_erase(&e->start.node, &wnd->start_tree);
+				rb_erase(&e->count.node, &wnd->count_tree);
+				wnd->count -= 1;
+				e0 = e;
+			}
+		}
+
+		while (n) {
+			size_t next_end;
+
+			e = rb_entry(n, struct e_node, start.node);
+			next_end = e->start.key + e->count.key;
+			if (e->start.key > end_in)
+				break;
+
+			/* Remove right */
+			n = rb_next(n);
+			len += next_end - end_in;
+			end_in = next_end;
+			rb_erase(&e->start.node, &wnd->start_tree);
+			rb_erase(&e->count.node, &wnd->count_tree);
+			wnd->count -= 1;
+
+			if (!e0)
+				e0 = e;
+			else
+				kmem_cache_free(ntfs_enode_cachep, e);
+		}
+
+		if (wnd->uptodated != 1) {
+			/* Check bits before 'bit' */
+			ib = wnd->zone_bit == wnd->zone_end ||
+					     bit < wnd->zone_end
+				     ? 0
+				     : wnd->zone_end;
+
+			while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) {
+				bit -= 1;
+				len += 1;
+			}
+
+			/* Check bits after 'end_in' */
+			ib = wnd->zone_bit == wnd->zone_end ||
+					     end_in > wnd->zone_bit
+				     ? wnd->nbits
+				     : wnd->zone_bit;
+
+			while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) {
+				end_in += 1;
+				len += 1;
+			}
+		}
+	}
+	/* Insert new fragment */
+	if (wnd->count >= NTFS_MAX_WND_EXTENTS) {
+		if (e0)
+			kmem_cache_free(ntfs_enode_cachep, e0);
+
+		wnd->uptodated = -1;
+
+		/* Compare with smallest fragment */
+		n = rb_last(&wnd->count_tree);
+		e = rb_entry(n, struct e_node, count.node);
+		if (len <= e->count.key)
+			goto out; /* Do not insert small fragments */
+
+		if (build) {
+			struct e_node *e2;
+
+			n = rb_prev(n);
+			e2 = rb_entry(n, struct e_node, count.node);
+			/* smallest fragment will be 'e2->count.key' */
+			wnd->extent_min = e2->count.key;
+		}
+
+		/* Replace smallest fragment by new one */
+		rb_erase(&e->start.node, &wnd->start_tree);
+		rb_erase(&e->count.node, &wnd->count_tree);
+		wnd->count -= 1;
+	} else {
+		e = e0 ? e0 : kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC);
+		if (!e) {
+			wnd->uptodated = -1;
+			goto out;
+		}
+
+		if (build && len <= wnd->extent_min)
+			wnd->extent_min = len;
+	}
+	e->start.key = bit;
+	e->count.key = len;
+	if (len > wnd->extent_max)
+		wnd->extent_max = len;
+
+	rb_insert_start(&wnd->start_tree, e);
+	rb_insert_count(&wnd->count_tree, e);
+	wnd->count += 1;
+
+out:;
+}
+
+/*
+ * wnd_remove_free_ext
+ *
+ * removes a run from the cached free space
+ */
+static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len)
+{
+	struct rb_node *n, *n3;
+	struct e_node *e, *e3;
+	size_t end_in = bit + len;
+	size_t end3, end, new_key, new_len, max_new_len;
+
+	/* Try to find extent before 'bit' */
+	n = rb_lookup(&wnd->start_tree, bit);
+
+	if (!n)
+		return;
+
+	e = rb_entry(n, struct e_node, start.node);
+	end = e->start.key + e->count.key;
+
+	new_key = new_len = 0;
+	len = e->count.key;
+
+	/* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n' */
+	if (e->start.key > bit)
+		;
+	else if (end_in <= end) {
+		/* Range [bit,end_in) inside 'e' */
+		new_key = end_in;
+		new_len = end - end_in;
+		len = bit - e->start.key;
+	} else if (bit > end) {
+		bool bmax = false;
+
+		n3 = rb_next(n);
+
+		while (n3) {
+			e3 = rb_entry(n3, struct e_node, start.node);
+			if (e3->start.key >= end_in)
+				break;
+
+			if (e3->count.key == wnd->extent_max)
+				bmax = true;
+
+			end3 = e3->start.key + e3->count.key;
+			if (end3 > end_in) {
+				e3->start.key = end_in;
+				rb_erase(&e3->count.node, &wnd->count_tree);
+				e3->count.key = end3 - end_in;
+				rb_insert_count(&wnd->count_tree, e3);
+				break;
+			}
+
+			n3 = rb_next(n3);
+			rb_erase(&e3->start.node, &wnd->start_tree);
+			rb_erase(&e3->count.node, &wnd->count_tree);
+			wnd->count -= 1;
+			kmem_cache_free(ntfs_enode_cachep, e3);
+		}
+		if (!bmax)
+			return;
+		n3 = rb_first(&wnd->count_tree);
+		wnd->extent_max =
+			n3 ? rb_entry(n3, struct e_node, count.node)->count.key
+			   : 0;
+		return;
+	}
+
+	if (e->count.key != wnd->extent_max) {
+		;
+	} else if (rb_prev(&e->count.node)) {
+		;
+	} else {
+		n3 = rb_next(&e->count.node);
+		max_new_len = len > new_len ? len : new_len;
+		if (!n3) {
+			wnd->extent_max = max_new_len;
+		} else {
+			e3 = rb_entry(n3, struct e_node, count.node);
+			wnd->extent_max = max(e3->count.key, max_new_len);
+		}
+	}
+
+	if (!len) {
+		if (new_len) {
+			e->start.key = new_key;
+			rb_erase(&e->count.node, &wnd->count_tree);
+			e->count.key = new_len;
+			rb_insert_count(&wnd->count_tree, e);
+		} else {
+			rb_erase(&e->start.node, &wnd->start_tree);
+			rb_erase(&e->count.node, &wnd->count_tree);
+			wnd->count -= 1;
+			kmem_cache_free(ntfs_enode_cachep, e);
+		}
+		goto out;
+	}
+	rb_erase(&e->count.node, &wnd->count_tree);
+	e->count.key = len;
+	rb_insert_count(&wnd->count_tree, e);
+
+	if (!new_len)
+		goto out;
+
+	if (wnd->count >= NTFS_MAX_WND_EXTENTS) {
+		wnd->uptodated = -1;
+
+		/* Get minimal extent */
+		e = rb_entry(rb_last(&wnd->count_tree), struct e_node,
+			     count.node);
+		if (e->count.key > new_len)
+			goto out;
+
+		/* Replace minimum */
+		rb_erase(&e->start.node, &wnd->start_tree);
+		rb_erase(&e->count.node, &wnd->count_tree);
+		wnd->count -= 1;
+	} else {
+		e = kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC);
+		if (!e)
+			wnd->uptodated = -1;
+	}
+
+	if (e) {
+		e->start.key = new_key;
+		e->count.key = new_len;
+		rb_insert_start(&wnd->start_tree, e);
+		rb_insert_count(&wnd->count_tree, e);
+		wnd->count += 1;
+	}
+
+out:
+	if (!wnd->count && 1 != wnd->uptodated)
+		wnd_rescan(wnd);
+}
+
+/*
+ * wnd_rescan
+ *
+ * Scan all bitmap. used while initialization.
+ */
+static int wnd_rescan(struct wnd_bitmap *wnd)
+{
+	int err = 0;
+	size_t prev_tail = 0;
+	struct super_block *sb = wnd->sb;
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	u64 lbo, len = 0;
+	u32 blocksize = sb->s_blocksize;
+	u8 cluster_bits = sbi->cluster_bits;
+	u32 wbits = 8 * sb->s_blocksize;
+	u32 used, frb;
+	const ulong *buf;
+	size_t wpos, wbit, iw, vbo;
+	struct buffer_head *bh = NULL;
+	CLST lcn, clen;
+
+	wnd->uptodated = 0;
+	wnd->extent_max = 0;
+	wnd->extent_min = MINUS_ONE_T;
+	wnd->total_zeroes = 0;
+
+	vbo = 0;
+
+	for (iw = 0; iw < wnd->nwnd; iw++) {
+		if (iw + 1 == wnd->nwnd)
+			wbits = wnd->bits_last;
+
+		if (wnd->inited) {
+			if (!wnd->free_bits[iw]) {
+				/* all ones */
+				if (prev_tail) {
+					wnd_add_free_ext(wnd,
+							 vbo * 8 - prev_tail,
+							 prev_tail, true);
+					prev_tail = 0;
+				}
+				goto next_wnd;
+			}
+			if (wbits == wnd->free_bits[iw]) {
+				/* all zeroes */
+				prev_tail += wbits;
+				wnd->total_zeroes += wbits;
+				goto next_wnd;
+			}
+		}
+
+		if (!len) {
+			u32 off = vbo & sbi->cluster_mask;
+
+			if (!run_lookup_entry(&wnd->run, vbo >> cluster_bits,
+					      &lcn, &clen, NULL)) {
+				err = -ENOENT;
+				goto out;
+			}
+
+			lbo = ((u64)lcn << cluster_bits) + off;
+			len = ((u64)clen << cluster_bits) - off;
+		}
+
+		bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits);
+		if (!bh) {
+			err = -EIO;
+			goto out;
+		}
+
+		buf = (ulong *)bh->b_data;
+
+		used = __bitmap_weight(buf, wbits);
+		if (used < wbits) {
+			frb = wbits - used;
+			wnd->free_bits[iw] = frb;
+			wnd->total_zeroes += frb;
+		}
+
+		wpos = 0;
+		wbit = vbo * 8;
+
+		if (wbit + wbits > wnd->nbits)
+			wbits = wnd->nbits - wbit;
+
+		do {
+			used = find_next_zero_bit(buf, wbits, wpos);
+
+			if (used > wpos && prev_tail) {
+				wnd_add_free_ext(wnd, wbit + wpos - prev_tail,
+						 prev_tail, true);
+				prev_tail = 0;
+			}
+
+			wpos = used;
+
+			if (wpos >= wbits) {
+				/* No free blocks */
+				prev_tail = 0;
+				break;
+			}
+
+			frb = find_next_bit(buf, wbits, wpos);
+			if (frb >= wbits) {
+				/* keep last free block */
+				prev_tail += frb - wpos;
+				break;
+			}
+
+			wnd_add_free_ext(wnd, wbit + wpos - prev_tail,
+					 frb + prev_tail - wpos, true);
+
+			/* Skip free block and first '1' */
+			wpos = frb + 1;
+			/* Reset previous tail */
+			prev_tail = 0;
+		} while (wpos < wbits);
+
+next_wnd:
+
+		if (bh)
+			put_bh(bh);
+		bh = NULL;
+
+		vbo += blocksize;
+		if (len) {
+			len -= blocksize;
+			lbo += blocksize;
+		}
+	}
+
+	/* Add last block */
+	if (prev_tail)
+		wnd_add_free_ext(wnd, wnd->nbits - prev_tail, prev_tail, true);
+
+	/*
+	 * Before init cycle wnd->uptodated was 0
+	 * If any errors or limits occurs while initialization then
+	 * wnd->uptodated will be -1
+	 * If 'uptodated' is still 0 then Tree is really updated
+	 */
+	if (!wnd->uptodated)
+		wnd->uptodated = 1;
+
+	if (wnd->zone_bit != wnd->zone_end) {
+		size_t zlen = wnd->zone_end - wnd->zone_bit;
+
+		wnd->zone_end = wnd->zone_bit;
+		wnd_zone_set(wnd, wnd->zone_bit, zlen);
+	}
+
+out:
+	return err;
+}
+
+/*
+ * wnd_init
+ */
+int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
+{
+	int err;
+	u32 blocksize = sb->s_blocksize;
+	u32 wbits = blocksize * 8;
+
+	init_rwsem(&wnd->rw_lock);
+
+	wnd->sb = sb;
+	wnd->nbits = nbits;
+	wnd->total_zeroes = nbits;
+	wnd->extent_max = MINUS_ONE_T;
+	wnd->zone_bit = wnd->zone_end = 0;
+	wnd->nwnd = bytes_to_block(sb, bitmap_size(nbits));
+	wnd->bits_last = nbits & (wbits - 1);
+	if (!wnd->bits_last)
+		wnd->bits_last = wbits;
+
+	wnd->free_bits = ntfs_zalloc(wnd->nwnd * sizeof(u16));
+	if (!wnd->free_bits)
+		return -ENOMEM;
+
+	err = wnd_rescan(wnd);
+	if (err)
+		return err;
+
+	wnd->inited = true;
+
+	return 0;
+}
+
+/*
+ * wnd_map
+ *
+ * call sb_bread for requested window
+ */
+static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw)
+{
+	size_t vbo;
+	CLST lcn, clen;
+	struct super_block *sb = wnd->sb;
+	struct ntfs_sb_info *sbi;
+	struct buffer_head *bh;
+	u64 lbo;
+
+	sbi = sb->s_fs_info;
+	vbo = (u64)iw << sb->s_blocksize_bits;
+
+	if (!run_lookup_entry(&wnd->run, vbo >> sbi->cluster_bits, &lcn, &clen,
+			      NULL)) {
+		return ERR_PTR(-ENOENT);
+	}
+
+	lbo = ((u64)lcn << sbi->cluster_bits) + (vbo & sbi->cluster_mask);
+
+	bh = ntfs_bread(wnd->sb, lbo >> sb->s_blocksize_bits);
+	if (!bh)
+		return ERR_PTR(-EIO);
+
+	return bh;
+}
+
+/*
+ * wnd_set_free
+ *
+ * Marks the bits range from bit to bit + bits as free
+ */
+int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
+{
+	int err = 0;
+	struct super_block *sb = wnd->sb;
+	size_t bits0 = bits;
+	u32 wbits = 8 * sb->s_blocksize;
+	size_t iw = bit >> (sb->s_blocksize_bits + 3);
+	u32 wbit = bit & (wbits - 1);
+	struct buffer_head *bh;
+
+	while (iw < wnd->nwnd && bits) {
+		u32 tail, op;
+		ulong *buf;
+
+		if (iw + 1 == wnd->nwnd)
+			wbits = wnd->bits_last;
+
+		tail = wbits - wbit;
+		op = tail < bits ? tail : bits;
+
+		bh = wnd_map(wnd, iw);
+		if (IS_ERR(bh)) {
+			err = PTR_ERR(bh);
+			break;
+		}
+
+		buf = (ulong *)bh->b_data;
+
+		lock_buffer(bh);
+
+		__bitmap_clear(buf, wbit, op);
+
+		wnd->free_bits[iw] += op;
+
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+		put_bh(bh);
+
+		wnd->total_zeroes += op;
+		bits -= op;
+		wbit = 0;
+		iw += 1;
+	}
+
+	wnd_add_free_ext(wnd, bit, bits0, false);
+
+	return err;
+}
+
+/*
+ * wnd_set_used
+ *
+ * Marks the bits range from bit to bit + bits as used
+ */
+int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
+{
+	int err = 0;
+	struct super_block *sb = wnd->sb;
+	size_t bits0 = bits;
+	size_t iw = bit >> (sb->s_blocksize_bits + 3);
+	u32 wbits = 8 * sb->s_blocksize;
+	u32 wbit = bit & (wbits - 1);
+	struct buffer_head *bh;
+
+	while (iw < wnd->nwnd && bits) {
+		u32 tail, op;
+		ulong *buf;
+
+		if (unlikely(iw + 1 == wnd->nwnd))
+			wbits = wnd->bits_last;
+
+		tail = wbits - wbit;
+		op = tail < bits ? tail : bits;
+
+		bh = wnd_map(wnd, iw);
+		if (IS_ERR(bh)) {
+			err = PTR_ERR(bh);
+			break;
+		}
+		buf = (ulong *)bh->b_data;
+
+		lock_buffer(bh);
+
+		__bitmap_set(buf, wbit, op);
+		wnd->free_bits[iw] -= op;
+
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+		put_bh(bh);
+
+		wnd->total_zeroes -= op;
+		bits -= op;
+		wbit = 0;
+		iw += 1;
+	}
+
+	if (!RB_EMPTY_ROOT(&wnd->start_tree))
+		wnd_remove_free_ext(wnd, bit, bits0);
+
+	return err;
+}
+
+/*
+ * wnd_is_free_hlp
+ *
+ * Returns true if all clusters [bit, bit+bits) are free (bitmap only)
+ */
+static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits)
+{
+	struct super_block *sb = wnd->sb;
+	size_t iw = bit >> (sb->s_blocksize_bits + 3);
+	u32 wbits = 8 * sb->s_blocksize;
+	u32 wbit = bit & (wbits - 1);
+
+	while (iw < wnd->nwnd && bits) {
+		u32 tail, op;
+
+		if (unlikely(iw + 1 == wnd->nwnd))
+			wbits = wnd->bits_last;
+
+		tail = wbits - wbit;
+		op = tail < bits ? tail : bits;
+
+		if (wbits != wnd->free_bits[iw]) {
+			bool ret;
+			struct buffer_head *bh = wnd_map(wnd, iw);
+
+			if (IS_ERR(bh))
+				return false;
+
+			ret = are_bits_clear((ulong *)bh->b_data, wbit, op);
+
+			put_bh(bh);
+			if (!ret)
+				return false;
+		}
+
+		bits -= op;
+		wbit = 0;
+		iw += 1;
+	}
+
+	return true;
+}
+
+/*
+ * wnd_is_free
+ *
+ * Returns true if all clusters [bit, bit+bits) are free
+ */
+bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits)
+{
+	bool ret;
+	struct rb_node *n;
+	size_t end;
+	struct e_node *e;
+
+	if (RB_EMPTY_ROOT(&wnd->start_tree))
+		goto use_wnd;
+
+	n = rb_lookup(&wnd->start_tree, bit);
+	if (!n)
+		goto use_wnd;
+
+	e = rb_entry(n, struct e_node, start.node);
+
+	end = e->start.key + e->count.key;
+
+	if (bit < end && bit + bits <= end)
+		return true;
+
+use_wnd:
+	ret = wnd_is_free_hlp(wnd, bit, bits);
+
+	return ret;
+}
+
+/*
+ * wnd_is_used
+ *
+ * Returns true if all clusters [bit, bit+bits) are used
+ */
+bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits)
+{
+	bool ret = false;
+	struct super_block *sb = wnd->sb;
+	size_t iw = bit >> (sb->s_blocksize_bits + 3);
+	u32 wbits = 8 * sb->s_blocksize;
+	u32 wbit = bit & (wbits - 1);
+	size_t end;
+	struct rb_node *n;
+	struct e_node *e;
+
+	if (RB_EMPTY_ROOT(&wnd->start_tree))
+		goto use_wnd;
+
+	end = bit + bits;
+	n = rb_lookup(&wnd->start_tree, end - 1);
+	if (!n)
+		goto use_wnd;
+
+	e = rb_entry(n, struct e_node, start.node);
+	if (e->start.key + e->count.key > bit)
+		return false;
+
+use_wnd:
+	while (iw < wnd->nwnd && bits) {
+		u32 tail, op;
+
+		if (unlikely(iw + 1 == wnd->nwnd))
+			wbits = wnd->bits_last;
+
+		tail = wbits - wbit;
+		op = tail < bits ? tail : bits;
+
+		if (wnd->free_bits[iw]) {
+			bool ret;
+			struct buffer_head *bh = wnd_map(wnd, iw);
+
+			if (IS_ERR(bh))
+				goto out;
+
+			ret = are_bits_set((ulong *)bh->b_data, wbit, op);
+			put_bh(bh);
+			if (!ret)
+				goto out;
+		}
+
+		bits -= op;
+		wbit = 0;
+		iw += 1;
+	}
+	ret = true;
+
+out:
+	return ret;
+}
+
+/*
+ * wnd_find
+ * - flags - BITMAP_FIND_XXX flags
+ *
+ * looks for free space
+ * Returns 0 if not found
+ */
+size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint,
+		size_t flags, size_t *allocated)
+{
+	struct super_block *sb;
+	u32 wbits, wpos, wzbit, wzend;
+	size_t fnd, max_alloc, b_len, b_pos;
+	size_t iw, prev_tail, nwnd, wbit, ebit, zbit, zend;
+	size_t to_alloc0 = to_alloc;
+	const ulong *buf;
+	const struct e_node *e;
+	const struct rb_node *pr, *cr;
+	u8 log2_bits;
+	bool fbits_valid;
+	struct buffer_head *bh;
+
+	/* fast checking for available free space */
+	if (flags & BITMAP_FIND_FULL) {
+		size_t zeroes = wnd_zeroes(wnd);
+
+		zeroes -= wnd->zone_end - wnd->zone_bit;
+		if (zeroes < to_alloc0)
+			goto no_space;
+
+		if (to_alloc0 > wnd->extent_max)
+			goto no_space;
+	} else {
+		if (to_alloc > wnd->extent_max)
+			to_alloc = wnd->extent_max;
+	}
+
+	if (wnd->zone_bit <= hint && hint < wnd->zone_end)
+		hint = wnd->zone_end;
+
+	max_alloc = wnd->nbits;
+	b_len = b_pos = 0;
+
+	if (hint >= max_alloc)
+		hint = 0;
+
+	if (RB_EMPTY_ROOT(&wnd->start_tree)) {
+		if (wnd->uptodated == 1) {
+			/* extents tree is updated -> no free space */
+			goto no_space;
+		}
+		goto scan_bitmap;
+	}
+
+	e = NULL;
+	if (!hint)
+		goto allocate_biggest;
+
+	/* Use hint: enumerate extents by start >= hint */
+	pr = NULL;
+	cr = wnd->start_tree.rb_node;
+
+	for (;;) {
+		e = rb_entry(cr, struct e_node, start.node);
+
+		if (e->start.key == hint)
+			break;
+
+		if (e->start.key < hint) {
+			pr = cr;
+			cr = cr->rb_right;
+			if (!cr)
+				break;
+			continue;
+		}
+
+		cr = cr->rb_left;
+		if (!cr) {
+			e = pr ? rb_entry(pr, struct e_node, start.node) : NULL;
+			break;
+		}
+	}
+
+	if (!e)
+		goto allocate_biggest;
+
+	if (e->start.key + e->count.key > hint) {
+		/* We have found extension with 'hint' inside */
+		size_t len = e->start.key + e->count.key - hint;
+
+		if (len >= to_alloc && hint + to_alloc <= max_alloc) {
+			fnd = hint;
+			goto found;
+		}
+
+		if (!(flags & BITMAP_FIND_FULL)) {
+			if (len > to_alloc)
+				len = to_alloc;
+
+			if (hint + len <= max_alloc) {
+				fnd = hint;
+				to_alloc = len;
+				goto found;
+			}
+		}
+	}
+
+allocate_biggest:
+	/* Allocate from biggest free extent */
+	e = rb_entry(rb_first(&wnd->count_tree), struct e_node, count.node);
+	if (e->count.key != wnd->extent_max)
+		wnd->extent_max = e->count.key;
+
+	if (e->count.key < max_alloc) {
+		if (e->count.key >= to_alloc) {
+			;
+		} else if (flags & BITMAP_FIND_FULL) {
+			if (e->count.key < to_alloc0) {
+				/* Biggest free block is less then requested */
+				goto no_space;
+			}
+			to_alloc = e->count.key;
+		} else if (-1 != wnd->uptodated) {
+			to_alloc = e->count.key;
+		} else {
+			/* Check if we can use more bits */
+			size_t op, max_check;
+			struct rb_root start_tree;
+
+			memcpy(&start_tree, &wnd->start_tree,
+			       sizeof(struct rb_root));
+			memset(&wnd->start_tree, 0, sizeof(struct rb_root));
+
+			max_check = e->start.key + to_alloc;
+			if (max_check > max_alloc)
+				max_check = max_alloc;
+			for (op = e->start.key + e->count.key; op < max_check;
+			     op++) {
+				if (!wnd_is_free(wnd, op, 1))
+					break;
+			}
+			memcpy(&wnd->start_tree, &start_tree,
+			       sizeof(struct rb_root));
+			to_alloc = op - e->start.key;
+		}
+
+		/* Prepare to return */
+		fnd = e->start.key;
+		if (e->start.key + to_alloc > max_alloc)
+			to_alloc = max_alloc - e->start.key;
+		goto found;
+	}
+
+	if (wnd->uptodated == 1) {
+		/* extents tree is updated -> no free space */
+		goto no_space;
+	}
+
+	b_len = e->count.key;
+	b_pos = e->start.key;
+
+scan_bitmap:
+	sb = wnd->sb;
+	log2_bits = sb->s_blocksize_bits + 3;
+
+	/* At most two ranges [hint, max_alloc) + [0, hint) */
+Again:
+
+	/* TODO: optimize request for case nbits > wbits */
+	iw = hint >> log2_bits;
+	wbits = sb->s_blocksize * 8;
+	wpos = hint & (wbits - 1);
+	prev_tail = 0;
+	fbits_valid = true;
+
+	if (max_alloc == wnd->nbits) {
+		nwnd = wnd->nwnd;
+	} else {
+		size_t t = max_alloc + wbits - 1;
+
+		nwnd = likely(t > max_alloc) ? (t >> log2_bits) : wnd->nwnd;
+	}
+
+	/* Enumerate all windows */
+	for (; iw < nwnd; iw++) {
+		wbit = iw << log2_bits;
+
+		if (!wnd->free_bits[iw]) {
+			if (prev_tail > b_len) {
+				b_pos = wbit - prev_tail;
+				b_len = prev_tail;
+			}
+
+			/* Skip full used window */
+			prev_tail = 0;
+			wpos = 0;
+			continue;
+		}
+
+		if (unlikely(iw + 1 == nwnd)) {
+			if (max_alloc == wnd->nbits) {
+				wbits = wnd->bits_last;
+			} else {
+				size_t t = max_alloc & (wbits - 1);
+
+				if (t) {
+					wbits = t;
+					fbits_valid = false;
+				}
+			}
+		}
+
+		if (wnd->zone_end > wnd->zone_bit) {
+			ebit = wbit + wbits;
+			zbit = max(wnd->zone_bit, wbit);
+			zend = min(wnd->zone_end, ebit);
+
+			/* Here we have a window [wbit, ebit) and zone [zbit, zend) */
+			if (zend <= zbit) {
+				/* Zone does not overlap window */
+			} else {
+				wzbit = zbit - wbit;
+				wzend = zend - wbit;
+
+				/* Zone overlaps window */
+				if (wnd->free_bits[iw] == wzend - wzbit) {
+					prev_tail = 0;
+					wpos = 0;
+					continue;
+				}
+
+				/* Scan two ranges window: [wbit, zbit) and [zend, ebit) */
+				bh = wnd_map(wnd, iw);
+
+				if (IS_ERR(bh)) {
+					/* TODO: error */
+					prev_tail = 0;
+					wpos = 0;
+					continue;
+				}
+
+				buf = (ulong *)bh->b_data;
+
+				/* Scan range [wbit, zbit) */
+				if (wpos < wzbit) {
+					/* Scan range [wpos, zbit) */
+					fnd = wnd_scan(buf, wbit, wpos, wzbit,
+						       to_alloc, &prev_tail,
+						       &b_pos, &b_len);
+					if (fnd != MINUS_ONE_T) {
+						put_bh(bh);
+						goto found;
+					}
+				}
+
+				prev_tail = 0;
+
+				/* Scan range [zend, ebit) */
+				if (wzend < wbits) {
+					fnd = wnd_scan(buf, wbit,
+						       max(wzend, wpos), wbits,
+						       to_alloc, &prev_tail,
+						       &b_pos, &b_len);
+					if (fnd != MINUS_ONE_T) {
+						put_bh(bh);
+						goto found;
+					}
+				}
+
+				wpos = 0;
+				put_bh(bh);
+				continue;
+			}
+		}
+
+		/* Current window does not overlap zone */
+		if (!wpos && fbits_valid && wnd->free_bits[iw] == wbits) {
+			/* window is empty */
+			if (prev_tail + wbits >= to_alloc) {
+				fnd = wbit + wpos - prev_tail;
+				goto found;
+			}
+
+			/* Increase 'prev_tail' and process next window */
+			prev_tail += wbits;
+			wpos = 0;
+			continue;
+		}
+
+		/* read window */
+		bh = wnd_map(wnd, iw);
+		if (IS_ERR(bh)) {
+			// TODO: error
+			prev_tail = 0;
+			wpos = 0;
+			continue;
+		}
+
+		buf = (ulong *)bh->b_data;
+
+		/* Scan range [wpos, eBits) */
+		fnd = wnd_scan(buf, wbit, wpos, wbits, to_alloc, &prev_tail,
+			       &b_pos, &b_len);
+		put_bh(bh);
+		if (fnd != MINUS_ONE_T)
+			goto found;
+	}
+
+	if (b_len < prev_tail) {
+		/* The last fragment */
+		b_len = prev_tail;
+		b_pos = max_alloc - prev_tail;
+	}
+
+	if (hint) {
+		/*
+		 * We have scanned range [hint max_alloc)
+		 * Prepare to scan range [0 hint + to_alloc)
+		 */
+		size_t nextmax = hint + to_alloc;
+
+		if (likely(nextmax >= hint) && nextmax < max_alloc)
+			max_alloc = nextmax;
+		hint = 0;
+		goto Again;
+	}
+
+	if (!b_len)
+		goto no_space;
+
+	wnd->extent_max = b_len;
+
+	if (flags & BITMAP_FIND_FULL)
+		goto no_space;
+
+	fnd = b_pos;
+	to_alloc = b_len;
+
+found:
+	if (flags & BITMAP_FIND_MARK_AS_USED) {
+		/* TODO optimize remove extent (pass 'e'?) */
+		if (wnd_set_used(wnd, fnd, to_alloc))
+			goto no_space;
+	} else if (wnd->extent_max != MINUS_ONE_T &&
+		   to_alloc > wnd->extent_max) {
+		wnd->extent_max = to_alloc;
+	}
+
+	*allocated = fnd;
+	return to_alloc;
+
+no_space:
+	return 0;
+}
+
+/*
+ * wnd_extend
+ *
+ * Extend bitmap ($MFT bitmap)
+ */
+int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
+{
+	int err;
+	struct super_block *sb = wnd->sb;
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	u32 blocksize = sb->s_blocksize;
+	u32 wbits = blocksize * 8;
+	u32 b0, new_last;
+	size_t bits, iw, new_wnd;
+	size_t old_bits = wnd->nbits;
+	u16 *new_free;
+
+	if (new_bits <= old_bits)
+		return -EINVAL;
+
+	/* align to 8 byte boundary */
+	new_wnd = bytes_to_block(sb, bitmap_size(new_bits));
+	new_last = new_bits & (wbits - 1);
+	if (!new_last)
+		new_last = wbits;
+
+	if (new_wnd != wnd->nwnd) {
+		new_free = ntfs_malloc(new_wnd * sizeof(u16));
+		if (!new_free)
+			return -ENOMEM;
+
+		if (new_free != wnd->free_bits)
+			memcpy(new_free, wnd->free_bits,
+			       wnd->nwnd * sizeof(short));
+		memset(new_free + wnd->nwnd, 0,
+		       (new_wnd - wnd->nwnd) * sizeof(short));
+		ntfs_free(wnd->free_bits);
+		wnd->free_bits = new_free;
+	}
+
+	/* Zero bits [old_bits,new_bits) */
+	bits = new_bits - old_bits;
+	b0 = old_bits & (wbits - 1);
+
+	for (iw = old_bits >> (sb->s_blocksize_bits + 3); bits; iw += 1) {
+		u32 op;
+		size_t frb;
+		u64 vbo, lbo, bytes;
+		struct buffer_head *bh;
+		ulong *buf;
+
+		if (iw + 1 == new_wnd)
+			wbits = new_last;
+
+		op = b0 + bits > wbits ? wbits - b0 : bits;
+		vbo = (u64)iw * blocksize;
+
+		err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes);
+		if (err)
+			break;
+
+		bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits);
+		if (!bh)
+			return -EIO;
+
+		lock_buffer(bh);
+		buf = (ulong *)bh->b_data;
+
+		__bitmap_clear(buf, b0, blocksize * 8 - b0);
+		frb = wbits - __bitmap_weight(buf, wbits);
+		wnd->total_zeroes += frb - wnd->free_bits[iw];
+		wnd->free_bits[iw] = frb;
+
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+		/*err = sync_dirty_buffer(bh);*/
+
+		b0 = 0;
+		bits -= op;
+	}
+
+	wnd->nbits = new_bits;
+	wnd->nwnd = new_wnd;
+	wnd->bits_last = new_last;
+
+	wnd_add_free_ext(wnd, old_bits, new_bits - old_bits, false);
+
+	return 0;
+}
+
+/*
+ * wnd_zone_set
+ */
+void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len)
+{
+	size_t zlen;
+
+	zlen = wnd->zone_end - wnd->zone_bit;
+	if (zlen)
+		wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false);
+
+	if (!RB_EMPTY_ROOT(&wnd->start_tree) && len)
+		wnd_remove_free_ext(wnd, lcn, len);
+
+	wnd->zone_bit = lcn;
+	wnd->zone_end = lcn + len;
+}
+
+int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range)
+{
+	int err = 0;
+	struct super_block *sb = sbi->sb;
+	struct wnd_bitmap *wnd = &sbi->used.bitmap;
+	u32 wbits = 8 * sb->s_blocksize;
+	CLST len = 0, lcn = 0, done = 0;
+	CLST minlen = bytes_to_cluster(sbi, range->minlen);
+	CLST lcn_from = bytes_to_cluster(sbi, range->start);
+	size_t iw = lcn_from >> (sb->s_blocksize_bits + 3);
+	u32 wbit = lcn_from & (wbits - 1);
+	const ulong *buf;
+	CLST lcn_to;
+
+	if (!minlen)
+		minlen = 1;
+
+	if (range->len == (u64)-1)
+		lcn_to = wnd->nbits;
+	else
+		lcn_to = bytes_to_cluster(sbi, range->start + range->len);
+
+	down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
+
+	for (; iw < wnd->nbits; iw++, wbit = 0) {
+		CLST lcn_wnd = iw * wbits;
+		struct buffer_head *bh;
+
+		if (lcn_wnd > lcn_to)
+			break;
+
+		if (!wnd->free_bits[iw])
+			continue;
+
+		if (iw + 1 == wnd->nwnd)
+			wbits = wnd->bits_last;
+
+		if (lcn_wnd + wbits > lcn_to)
+			wbits = lcn_to - lcn_wnd;
+
+		bh = wnd_map(wnd, iw);
+		if (IS_ERR(bh)) {
+			err = PTR_ERR(bh);
+			break;
+		}
+
+		buf = (ulong *)bh->b_data;
+
+		for (; wbit < wbits; wbit++) {
+			if (!test_bit(wbit, buf)) {
+				if (!len)
+					lcn = lcn_wnd + wbit;
+				len += 1;
+				continue;
+			}
+			if (len >= minlen) {
+				err = ntfs_discard(sbi, lcn, len);
+				if (err)
+					goto out;
+				done += len;
+			}
+			len = 0;
+		}
+		put_bh(bh);
+	}
+
+	/* Process the last fragment */
+	if (len >= minlen) {
+		err = ntfs_discard(sbi, lcn, len);
+		if (err)
+			goto out;
+		done += len;
+	}
+
+out:
+	range->len = (u64)done << sbi->cluster_bits;
+
+	up_read(&wnd->rw_lock);
+
+	return err;
+}
-- 
2.25.4

[Linux-NTFS-Dev] [PATCH v27 09/10] fs/ntfs3: Add NTFS3 in fs/Kconfig and fs/Makefile

[Konstantin K. <alm...@pa...>]

This adds NTFS3 in fs/Kconfig and fs/Makefile

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/Kconfig  | 1 +
 fs/Makefile | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/Kconfig b/fs/Kconfig
index 923772867..273ace5d5 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -146,6 +146,7 @@ menu "DOS/FAT/EXFAT/NT Filesystems"
 source "fs/fat/Kconfig"
 source "fs/exfat/Kconfig"
 source "fs/ntfs/Kconfig"
+source "fs/ntfs3/Kconfig"
 
 endmenu
 endif # BLOCK
diff --git a/fs/Makefile b/fs/Makefile
index e03a048b2..4cd6b7459 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_CIFS)		+= cifs/
 obj-$(CONFIG_SMB_SERVER)	+= ksmbd/
 obj-$(CONFIG_HPFS_FS)		+= hpfs/
 obj-$(CONFIG_NTFS_FS)		+= ntfs/
+obj-$(CONFIG_NTFS3_FS)		+= ntfs3/
 obj-$(CONFIG_UFS_FS)		+= ufs/
 obj-$(CONFIG_EFS_FS)		+= efs/
 obj-$(CONFIG_JFFS2_FS)		+= jffs2/
-- 
2.25.4

[Linux-NTFS-Dev] [PATCH v27 01/10] fs/ntfs3: Add headers and misc files

[Konstantin K. <alm...@pa...>]

This adds headers and misc files

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/debug.h   |   64 +++
 fs/ntfs3/ntfs.h    | 1238 ++++++++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/ntfs_fs.h | 1085 ++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/upcase.c  |  105 ++++
 4 files changed, 2492 insertions(+)
 create mode 100644 fs/ntfs3/debug.h
 create mode 100644 fs/ntfs3/ntfs.h
 create mode 100644 fs/ntfs3/ntfs_fs.h
 create mode 100644 fs/ntfs3/upcase.c

diff --git a/fs/ntfs3/debug.h b/fs/ntfs3/debug.h
new file mode 100644
index 000000000..dfaa4c79d
--- /dev/null
+++ b/fs/ntfs3/debug.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ * useful functions for debuging
+ */
+
+// clang-format off
+#ifndef Add2Ptr
+#define Add2Ptr(P, I)		((void *)((u8 *)(P) + (I)))
+#define PtrOffset(B, O)		((size_t)((size_t)(O) - (size_t)(B)))
+#endif
+
+#define QuadAlign(n)		(((n) + 7u) & (~7u))
+#define IsQuadAligned(n)	(!((size_t)(n)&7u))
+#define Quad2Align(n)		(((n) + 15u) & (~15u))
+#define IsQuad2Aligned(n)	(!((size_t)(n)&15u))
+#define Quad4Align(n)		(((n) + 31u) & (~31u))
+#define IsSizeTAligned(n)	(!((size_t)(n) & (sizeof(size_t) - 1)))
+#define DwordAlign(n)		(((n) + 3u) & (~3u))
+#define IsDwordAligned(n)	(!((size_t)(n)&3u))
+#define WordAlign(n)		(((n) + 1u) & (~1u))
+#define IsWordAligned(n)	(!((size_t)(n)&1u))
+
+#ifdef CONFIG_PRINTK
+__printf(2, 3)
+void ntfs_printk(const struct super_block *sb, const char *fmt, ...);
+__printf(2, 3)
+void ntfs_inode_printk(struct inode *inode, const char *fmt, ...);
+#else
+static inline __printf(2, 3)
+void ntfs_printk(const struct super_block *sb, const char *fmt, ...)
+{
+}
+
+static inline __printf(2, 3)
+void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
+{
+}
+#endif
+
+/*
+ * Logging macros ( thanks Joe Perches <jo...@pe...> for implementation )
+ */
+
+#define ntfs_err(sb, fmt, ...)  ntfs_printk(sb, KERN_ERR fmt, ##__VA_ARGS__)
+#define ntfs_warn(sb, fmt, ...) ntfs_printk(sb, KERN_WARNING fmt, ##__VA_ARGS__)
+#define ntfs_info(sb, fmt, ...) ntfs_printk(sb, KERN_INFO fmt, ##__VA_ARGS__)
+#define ntfs_notice(sb, fmt, ...)                                              \
+	ntfs_printk(sb, KERN_NOTICE fmt, ##__VA_ARGS__)
+
+#define ntfs_inode_err(inode, fmt, ...)                                        \
+	ntfs_inode_printk(inode, KERN_ERR fmt, ##__VA_ARGS__)
+#define ntfs_inode_warn(inode, fmt, ...)                                       \
+	ntfs_inode_printk(inode, KERN_WARNING fmt, ##__VA_ARGS__)
+
+#define ntfs_malloc(s)		kmalloc(s, GFP_NOFS)
+#define ntfs_zalloc(s)		kzalloc(s, GFP_NOFS)
+#define ntfs_vmalloc(s)		kvmalloc(s, GFP_KERNEL)
+#define ntfs_free(p)		kfree(p)
+#define ntfs_vfree(p)		kvfree(p)
+#define ntfs_memdup(src, len)	kmemdup(src, len, GFP_NOFS)
+// clang-format on
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
new file mode 100644
index 000000000..40398e6c3
--- /dev/null
+++ b/fs/ntfs3/ntfs.h
@@ -0,0 +1,1238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ * on-disk ntfs structs
+ */
+
+// clang-format off
+
+/* TODO:
+ * - Check 4K mft record and 512 bytes cluster
+ */
+
+/*
+ * Activate this define to use binary search in indexes
+ */
+#define NTFS3_INDEX_BINARY_SEARCH
+
+/*
+ * Check each run for marked clusters
+ */
+#define NTFS3_CHECK_FREE_CLST
+
+#define NTFS_NAME_LEN 255
+
+/*
+ * ntfs.sys used 500 maximum links
+ * on-disk struct allows up to 0xffff
+ */
+#define NTFS_LINK_MAX 0x400
+//#define NTFS_LINK_MAX 0xffff
+
+/*
+ * Activate to use 64 bit clusters instead of 32 bits in ntfs.sys
+ * Logical and virtual cluster number
+ * If needed, may be redefined to use 64 bit value
+ */
+//#define CONFIG_NTFS3_64BIT_CLUSTER
+
+#define NTFS_LZNT_MAX_CLUSTER	4096
+#define NTFS_LZNT_CUNIT		4
+#define NTFS_LZNT_CLUSTERS	(1u<<NTFS_LZNT_CUNIT)
+
+struct GUID {
+	__le32 Data1;
+	__le16 Data2;
+	__le16 Data3;
+	u8 Data4[8];
+};
+
+/*
+ * this struct repeats layout of ATTR_FILE_NAME
+ * at offset 0x40
+ * it used to store global constants NAME_MFT/NAME_MIRROR...
+ * most constant names are shorter than 10
+ */
+struct cpu_str {
+	u8 len;
+	u8 unused;
+	u16 name[10];
+};
+
+struct le_str {
+	u8 len;
+	u8 unused;
+	__le16 name[];
+};
+
+static_assert(SECTOR_SHIFT == 9);
+
+#ifdef CONFIG_NTFS3_64BIT_CLUSTER
+typedef u64 CLST;
+static_assert(sizeof(size_t) == 8);
+#else
+typedef u32 CLST;
+#endif
+
+#define SPARSE_LCN64   ((u64)-1)
+#define SPARSE_LCN     ((CLST)-1)
+#define RESIDENT_LCN   ((CLST)-2)
+#define COMPRESSED_LCN ((CLST)-3)
+
+#define COMPRESSION_UNIT     4
+#define COMPRESS_MAX_CLUSTER 0x1000
+#define MFT_INCREASE_CHUNK   1024
+
+enum RECORD_NUM {
+	MFT_REC_MFT		= 0,
+	MFT_REC_MIRR		= 1,
+	MFT_REC_LOG		= 2,
+	MFT_REC_VOL		= 3,
+	MFT_REC_ATTR		= 4,
+	MFT_REC_ROOT		= 5,
+	MFT_REC_BITMAP		= 6,
+	MFT_REC_BOOT		= 7,
+	MFT_REC_BADCLUST	= 8,
+	//MFT_REC_QUOTA		= 9,
+	MFT_REC_SECURE		= 9, // NTFS 3.0
+	MFT_REC_UPCASE		= 10,
+	MFT_REC_EXTEND		= 11, // NTFS 3.0
+	MFT_REC_RESERVED	= 11,
+	MFT_REC_FREE		= 16,
+	MFT_REC_USER		= 24,
+};
+
+enum ATTR_TYPE {
+	ATTR_ZERO		= cpu_to_le32(0x00),
+	ATTR_STD		= cpu_to_le32(0x10),
+	ATTR_LIST		= cpu_to_le32(0x20),
+	ATTR_NAME		= cpu_to_le32(0x30),
+	// ATTR_VOLUME_VERSION on Nt4
+	ATTR_ID			= cpu_to_le32(0x40),
+	ATTR_SECURE		= cpu_to_le32(0x50),
+	ATTR_LABEL		= cpu_to_le32(0x60),
+	ATTR_VOL_INFO		= cpu_to_le32(0x70),
+	ATTR_DATA		= cpu_to_le32(0x80),
+	ATTR_ROOT		= cpu_to_le32(0x90),
+	ATTR_ALLOC		= cpu_to_le32(0xA0),
+	ATTR_BITMAP		= cpu_to_le32(0xB0),
+	// ATTR_SYMLINK on Nt4
+	ATTR_REPARSE		= cpu_to_le32(0xC0),
+	ATTR_EA_INFO		= cpu_to_le32(0xD0),
+	ATTR_EA			= cpu_to_le32(0xE0),
+	ATTR_PROPERTYSET	= cpu_to_le32(0xF0),
+	ATTR_LOGGED_UTILITY_STREAM = cpu_to_le32(0x100),
+	ATTR_END		= cpu_to_le32(0xFFFFFFFF)
+};
+
+static_assert(sizeof(enum ATTR_TYPE) == 4);
+
+enum FILE_ATTRIBUTE {
+	FILE_ATTRIBUTE_READONLY		= cpu_to_le32(0x00000001),
+	FILE_ATTRIBUTE_HIDDEN		= cpu_to_le32(0x00000002),
+	FILE_ATTRIBUTE_SYSTEM		= cpu_to_le32(0x00000004),
+	FILE_ATTRIBUTE_ARCHIVE		= cpu_to_le32(0x00000020),
+	FILE_ATTRIBUTE_DEVICE		= cpu_to_le32(0x00000040),
+	FILE_ATTRIBUTE_TEMPORARY	= cpu_to_le32(0x00000100),
+	FILE_ATTRIBUTE_SPARSE_FILE	= cpu_to_le32(0x00000200),
+	FILE_ATTRIBUTE_REPARSE_POINT	= cpu_to_le32(0x00000400),
+	FILE_ATTRIBUTE_COMPRESSED	= cpu_to_le32(0x00000800),
+	FILE_ATTRIBUTE_OFFLINE		= cpu_to_le32(0x00001000),
+	FILE_ATTRIBUTE_NOT_CONTENT_INDEXED = cpu_to_le32(0x00002000),
+	FILE_ATTRIBUTE_ENCRYPTED	= cpu_to_le32(0x00004000),
+	FILE_ATTRIBUTE_VALID_FLAGS	= cpu_to_le32(0x00007fb7),
+	FILE_ATTRIBUTE_DIRECTORY	= cpu_to_le32(0x10000000),
+};
+
+static_assert(sizeof(enum FILE_ATTRIBUTE) == 4);
+
+extern const struct cpu_str NAME_MFT;
+extern const struct cpu_str NAME_MIRROR;
+extern const struct cpu_str NAME_LOGFILE;
+extern const struct cpu_str NAME_VOLUME;
+extern const struct cpu_str NAME_ATTRDEF;
+extern const struct cpu_str NAME_ROOT;
+extern const struct cpu_str NAME_BITMAP;
+extern const struct cpu_str NAME_BOOT;
+extern const struct cpu_str NAME_BADCLUS;
+extern const struct cpu_str NAME_QUOTA;
+extern const struct cpu_str NAME_SECURE;
+extern const struct cpu_str NAME_UPCASE;
+extern const struct cpu_str NAME_EXTEND;
+extern const struct cpu_str NAME_OBJID;
+extern const struct cpu_str NAME_REPARSE;
+extern const struct cpu_str NAME_USNJRNL;
+
+extern const __le16 I30_NAME[4];
+extern const __le16 SII_NAME[4];
+extern const __le16 SDH_NAME[4];
+extern const __le16 SO_NAME[2];
+extern const __le16 SQ_NAME[2];
+extern const __le16 SR_NAME[2];
+
+extern const __le16 BAD_NAME[4];
+extern const __le16 SDS_NAME[4];
+extern const __le16 WOF_NAME[17];	/* WofCompressedData */
+
+/* MFT record number structure */
+struct MFT_REF {
+	__le32 low;	// The low part of the number
+	__le16 high;	// The high part of the number
+	__le16 seq;	// The sequence number of MFT record
+};
+
+static_assert(sizeof(__le64) == sizeof(struct MFT_REF));
+
+static inline CLST ino_get(const struct MFT_REF *ref)
+{
+#ifdef CONFIG_NTFS3_64BIT_CLUSTER
+	return le32_to_cpu(ref->low) | ((u64)le16_to_cpu(ref->high) << 32);
+#else
+	return le32_to_cpu(ref->low);
+#endif
+}
+
+struct NTFS_BOOT {
+	u8 jump_code[3];	// 0x00: Jump to boot code
+	u8 system_id[8];	// 0x03: System ID, equals "NTFS    "
+
+	// NOTE: this member is not aligned(!)
+	// bytes_per_sector[0] must be 0
+	// bytes_per_sector[1] must be multiplied by 256
+	u8 bytes_per_sector[2];	// 0x0B: Bytes per sector
+
+	u8 sectors_per_clusters;// 0x0D: Sectors per cluster
+	u8 unused1[7];
+	u8 media_type;		// 0x15: Media type (0xF8 - harddisk)
+	u8 unused2[2];
+	__le16 sct_per_track;	// 0x18: number of sectors per track
+	__le16 heads;		// 0x1A: number of heads per cylinder
+	__le32 hidden_sectors;	// 0x1C: number of 'hidden' sectors
+	u8 unused3[4];
+	u8 bios_drive_num;	// 0x24: BIOS drive number =0x80
+	u8 unused4;
+	u8 signature_ex;	// 0x26: Extended BOOT signature =0x80
+	u8 unused5;
+	__le64 sectors_per_volume;// 0x28: size of volume in sectors
+	__le64 mft_clst;	// 0x30: first cluster of $MFT
+	__le64 mft2_clst;	// 0x38: first cluster of $MFTMirr
+	s8 record_size;		// 0x40: size of MFT record in clusters(sectors)
+	u8 unused6[3];
+	s8 index_size;		// 0x44: size of INDX record in clusters(sectors)
+	u8 unused7[3];
+	__le64 serial_num;	// 0x48: Volume serial number
+	__le32 check_sum;	// 0x50: Simple additive checksum of all
+				// of the u32's which precede the 'check_sum'
+
+	u8 boot_code[0x200 - 0x50 - 2 - 4]; // 0x54:
+	u8 boot_magic[2];	// 0x1FE: Boot signature =0x55 + 0xAA
+};
+
+static_assert(sizeof(struct NTFS_BOOT) == 0x200);
+
+enum NTFS_SIGNATURE {
+	NTFS_FILE_SIGNATURE = cpu_to_le32(0x454C4946), // 'FILE'
+	NTFS_INDX_SIGNATURE = cpu_to_le32(0x58444E49), // 'INDX'
+	NTFS_CHKD_SIGNATURE = cpu_to_le32(0x444B4843), // 'CHKD'
+	NTFS_RSTR_SIGNATURE = cpu_to_le32(0x52545352), // 'RSTR'
+	NTFS_RCRD_SIGNATURE = cpu_to_le32(0x44524352), // 'RCRD'
+	NTFS_BAAD_SIGNATURE = cpu_to_le32(0x44414142), // 'BAAD'
+	NTFS_HOLE_SIGNATURE = cpu_to_le32(0x454C4F48), // 'HOLE'
+	NTFS_FFFF_SIGNATURE = cpu_to_le32(0xffffffff),
+};
+
+static_assert(sizeof(enum NTFS_SIGNATURE) == 4);
+
+/* MFT Record header structure */
+struct NTFS_RECORD_HEADER {
+	/* Record magic number, equals 'FILE'/'INDX'/'RSTR'/'RCRD' */
+	enum NTFS_SIGNATURE sign; // 0x00:
+	__le16 fix_off;		// 0x04:
+	__le16 fix_num;		// 0x06:
+	__le64 lsn;		// 0x08: Log file sequence number
+};
+
+static_assert(sizeof(struct NTFS_RECORD_HEADER) == 0x10);
+
+static inline int is_baad(const struct NTFS_RECORD_HEADER *hdr)
+{
+	return hdr->sign == NTFS_BAAD_SIGNATURE;
+}
+
+/* Possible bits in struct MFT_REC.flags */
+enum RECORD_FLAG {
+	RECORD_FLAG_IN_USE	= cpu_to_le16(0x0001),
+	RECORD_FLAG_DIR		= cpu_to_le16(0x0002),
+	RECORD_FLAG_SYSTEM	= cpu_to_le16(0x0004),
+	RECORD_FLAG_UNKNOWN	= cpu_to_le16(0x0008),
+};
+
+/* MFT Record structure */
+struct MFT_REC {
+	struct NTFS_RECORD_HEADER rhdr; // 'FILE'
+
+	__le16 seq;		// 0x10: Sequence number for this record
+	__le16 hard_links;	// 0x12: The number of hard links to record
+	__le16 attr_off;	// 0x14: Offset to attributes
+	__le16 flags;		// 0x16: See RECORD_FLAG
+	__le32 used;		// 0x18: The size of used part
+	__le32 total;		// 0x1C: Total record size
+
+	struct MFT_REF parent_ref; // 0x20: Parent MFT record
+	__le16 next_attr_id;	// 0x28: The next attribute Id
+
+	__le16 res;		// 0x2A: High part of mft record?
+	__le32 mft_record;	// 0x2C: Current mft record number
+	__le16 fixups[];	// 0x30:
+};
+
+#define MFTRECORD_FIXUP_OFFSET_1 offsetof(struct MFT_REC, res)
+#define MFTRECORD_FIXUP_OFFSET_3 offsetof(struct MFT_REC, fixups)
+
+static_assert(MFTRECORD_FIXUP_OFFSET_1 == 0x2A);
+static_assert(MFTRECORD_FIXUP_OFFSET_3 == 0x30);
+
+static inline bool is_rec_base(const struct MFT_REC *rec)
+{
+	const struct MFT_REF *r = &rec->parent_ref;
+
+	return !r->low && !r->high && !r->seq;
+}
+
+static inline bool is_mft_rec5(const struct MFT_REC *rec)
+{
+	return le16_to_cpu(rec->rhdr.fix_off) >=
+	       offsetof(struct MFT_REC, fixups);
+}
+
+static inline bool is_rec_inuse(const struct MFT_REC *rec)
+{
+	return rec->flags & RECORD_FLAG_IN_USE;
+}
+
+static inline bool clear_rec_inuse(struct MFT_REC *rec)
+{
+	return rec->flags &= ~RECORD_FLAG_IN_USE;
+}
+
+/* Possible values of ATTR_RESIDENT.flags */
+#define RESIDENT_FLAG_INDEXED 0x01
+
+struct ATTR_RESIDENT {
+	__le32 data_size;	// 0x10: The size of data
+	__le16 data_off;	// 0x14: Offset to data
+	u8 flags;		// 0x16: resident flags ( 1 - indexed )
+	u8 res;			// 0x17:
+}; // sizeof() = 0x18
+
+struct ATTR_NONRESIDENT {
+	__le64 svcn;		// 0x10: Starting VCN of this segment
+	__le64 evcn;		// 0x18: End VCN of this segment
+	__le16 run_off;		// 0x20: Offset to packed runs
+	//  Unit of Compression size for this stream, expressed
+	//  as a log of the cluster size.
+	//
+	//	0 means file is not compressed
+	//	1, 2, 3, and 4 are potentially legal values if the
+	//	    stream is compressed, however the implementation
+	//	    may only choose to use 4, or possibly 3.  Note
+	//	    that 4 means cluster size time 16.	If convenient
+	//	    the implementation may wish to accept a
+	//	    reasonable range of legal values here (1-5?),
+	//	    even if the implementation only generates
+	//	    a smaller set of values itself.
+	u8 c_unit;		// 0x22
+	u8 res1[5];		// 0x23:
+	__le64 alloc_size;	// 0x28: The allocated size of attribute in bytes
+				// (multiple of cluster size)
+	__le64 data_size;	// 0x30: The size of attribute  in bytes <= alloc_size
+	__le64 valid_size;	// 0x38: The size of valid part in bytes <= data_size
+	__le64 total_size;	// 0x40: The sum of the allocated clusters for a file
+				// (present only for the first segment (0 == vcn)
+				// of compressed attribute)
+
+}; // sizeof()=0x40 or 0x48 (if compressed)
+
+/* Possible values of ATTRIB.flags: */
+#define ATTR_FLAG_COMPRESSED	  cpu_to_le16(0x0001)
+#define ATTR_FLAG_COMPRESSED_MASK cpu_to_le16(0x00FF)
+#define ATTR_FLAG_ENCRYPTED	  cpu_to_le16(0x4000)
+#define ATTR_FLAG_SPARSED	  cpu_to_le16(0x8000)
+
+struct ATTRIB {
+	enum ATTR_TYPE type;	// 0x00: The type of this attribute
+	__le32 size;		// 0x04: The size of this attribute
+	u8 non_res;		// 0x08: Is this attribute non-resident ?
+	u8 name_len;		// 0x09: This attribute name length
+	__le16 name_off;	// 0x0A: Offset to the attribute name
+	__le16 flags;		// 0x0C: See ATTR_FLAG_XXX
+	__le16 id;		// 0x0E: unique id (per record)
+
+	union {
+		struct ATTR_RESIDENT res;     // 0x10
+		struct ATTR_NONRESIDENT nres; // 0x10
+	};
+};
+
+/* Define attribute sizes */
+#define SIZEOF_RESIDENT			0x18
+#define SIZEOF_NONRESIDENT_EX		0x48
+#define SIZEOF_NONRESIDENT		0x40
+
+#define SIZEOF_RESIDENT_LE		cpu_to_le16(0x18)
+#define SIZEOF_NONRESIDENT_EX_LE	cpu_to_le16(0x48)
+#define SIZEOF_NONRESIDENT_LE		cpu_to_le16(0x40)
+
+static inline u64 attr_ondisk_size(const struct ATTRIB *attr)
+{
+	return attr->non_res ? ((attr->flags &
+				 (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) ?
+					le64_to_cpu(attr->nres.total_size) :
+					le64_to_cpu(attr->nres.alloc_size)) :
+			       QuadAlign(le32_to_cpu(attr->res.data_size));
+}
+
+static inline u64 attr_size(const struct ATTRIB *attr)
+{
+	return attr->non_res ? le64_to_cpu(attr->nres.data_size) :
+			       le32_to_cpu(attr->res.data_size);
+}
+
+static inline bool is_attr_encrypted(const struct ATTRIB *attr)
+{
+	return attr->flags & ATTR_FLAG_ENCRYPTED;
+}
+
+static inline bool is_attr_sparsed(const struct ATTRIB *attr)
+{
+	return attr->flags & ATTR_FLAG_SPARSED;
+}
+
+static inline bool is_attr_compressed(const struct ATTRIB *attr)
+{
+	return attr->flags & ATTR_FLAG_COMPRESSED;
+}
+
+static inline bool is_attr_ext(const struct ATTRIB *attr)
+{
+	return attr->flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED);
+}
+
+static inline bool is_attr_indexed(const struct ATTRIB *attr)
+{
+	return !attr->non_res && (attr->res.flags & RESIDENT_FLAG_INDEXED);
+}
+
+static inline __le16 const *attr_name(const struct ATTRIB *attr)
+{
+	return Add2Ptr(attr, le16_to_cpu(attr->name_off));
+}
+
+static inline u64 attr_svcn(const struct ATTRIB *attr)
+{
+	return attr->non_res ? le64_to_cpu(attr->nres.svcn) : 0;
+}
+
+/* the size of resident attribute by its resident size */
+#define BYTES_PER_RESIDENT(b) (0x18 + (b))
+
+static_assert(sizeof(struct ATTRIB) == 0x48);
+static_assert(sizeof(((struct ATTRIB *)NULL)->res) == 0x08);
+static_assert(sizeof(((struct ATTRIB *)NULL)->nres) == 0x38);
+
+static inline void *resident_data_ex(const struct ATTRIB *attr, u32 datasize)
+{
+	u32 asize, rsize;
+	u16 off;
+
+	if (attr->non_res)
+		return NULL;
+
+	asize = le32_to_cpu(attr->size);
+	off = le16_to_cpu(attr->res.data_off);
+
+	if (asize < datasize + off)
+		return NULL;
+
+	rsize = le32_to_cpu(attr->res.data_size);
+	if (rsize < datasize)
+		return NULL;
+
+	return Add2Ptr(attr, off);
+}
+
+static inline void *resident_data(const struct ATTRIB *attr)
+{
+	return Add2Ptr(attr, le16_to_cpu(attr->res.data_off));
+}
+
+static inline void *attr_run(const struct ATTRIB *attr)
+{
+	return Add2Ptr(attr, le16_to_cpu(attr->nres.run_off));
+}
+
+/* Standard information attribute (0x10) */
+struct ATTR_STD_INFO {
+	__le64 cr_time;		// 0x00: File creation file
+	__le64 m_time;		// 0x08: File modification time
+	__le64 c_time;		// 0x10: Last time any attribute was modified
+	__le64 a_time;		// 0x18: File last access time
+	enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more
+	__le32 max_ver_num;	// 0x24: Maximum Number of Versions
+	__le32 ver_num;		// 0x28: Version Number
+	__le32 class_id;	// 0x2C: Class Id from bidirectional Class Id index
+};
+
+static_assert(sizeof(struct ATTR_STD_INFO) == 0x30);
+
+#define SECURITY_ID_INVALID 0x00000000
+#define SECURITY_ID_FIRST 0x00000100
+
+struct ATTR_STD_INFO5 {
+	__le64 cr_time;		// 0x00: File creation file
+	__le64 m_time;		// 0x08: File modification time
+	__le64 c_time;		// 0x10: Last time any attribute was modified
+	__le64 a_time;		// 0x18: File last access time
+	enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more
+	__le32 max_ver_num;	// 0x24: Maximum Number of Versions
+	__le32 ver_num;		// 0x28: Version Number
+	__le32 class_id;	// 0x2C: Class Id from bidirectional Class Id index
+
+	__le32 owner_id;	// 0x30: Owner Id of the user owning the file.
+	__le32 security_id;	// 0x34: The Security Id is a key in the $SII Index and $SDS
+	__le64 quota_charge;	// 0x38:
+	__le64 usn;		// 0x40: Last Update Sequence Number of the file. This is a direct
+				// index into the file $UsnJrnl. If zero, the USN Journal is
+				// disabled.
+};
+
+static_assert(sizeof(struct ATTR_STD_INFO5) == 0x48);
+
+/* attribute list entry structure (0x20) */
+struct ATTR_LIST_ENTRY {
+	enum ATTR_TYPE type;	// 0x00: The type of attribute
+	__le16 size;		// 0x04: The size of this record
+	u8 name_len;		// 0x06: The length of attribute name
+	u8 name_off;		// 0x07: The offset to attribute name
+	__le64 vcn;		// 0x08: Starting VCN of this attribute
+	struct MFT_REF ref;	// 0x10: MFT record number with attribute
+	__le16 id;		// 0x18: struct ATTRIB ID
+	__le16 name[3];		// 0x1A: Just to align. To get real name can use bNameOffset
+
+}; // sizeof(0x20)
+
+static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20);
+
+static inline u32 le_size(u8 name_len)
+{
+	return QuadAlign(offsetof(struct ATTR_LIST_ENTRY, name) +
+			 name_len * sizeof(short));
+}
+
+/* returns 0 if 'attr' has the same type and name */
+static inline int le_cmp(const struct ATTR_LIST_ENTRY *le,
+			 const struct ATTRIB *attr)
+{
+	return le->type != attr->type || le->name_len != attr->name_len ||
+	       (!le->name_len &&
+		memcmp(Add2Ptr(le, le->name_off),
+		       Add2Ptr(attr, le16_to_cpu(attr->name_off)),
+		       le->name_len * sizeof(short)));
+}
+
+static inline __le16 const *le_name(const struct ATTR_LIST_ENTRY *le)
+{
+	return Add2Ptr(le, le->name_off);
+}
+
+/* File name types (the field type in struct ATTR_FILE_NAME ) */
+#define FILE_NAME_POSIX   0
+#define FILE_NAME_UNICODE 1
+#define FILE_NAME_DOS	  2
+#define FILE_NAME_UNICODE_AND_DOS (FILE_NAME_DOS | FILE_NAME_UNICODE)
+
+/* Filename attribute structure (0x30) */
+struct NTFS_DUP_INFO {
+	__le64 cr_time;		// 0x00: File creation file
+	__le64 m_time;		// 0x08: File modification time
+	__le64 c_time;		// 0x10: Last time any attribute was modified
+	__le64 a_time;		// 0x18: File last access time
+	__le64 alloc_size;	// 0x20: Data attribute allocated size, multiple of cluster size
+	__le64 data_size;	// 0x28: Data attribute size <= Dataalloc_size
+	enum FILE_ATTRIBUTE fa;	// 0x30: Standard DOS attributes & more
+	__le16 ea_size;		// 0x34: Packed EAs
+	__le16 reparse;		// 0x36: Used by Reparse
+
+}; // 0x38
+
+struct ATTR_FILE_NAME {
+	struct MFT_REF home;	// 0x00: MFT record for directory
+	struct NTFS_DUP_INFO dup;// 0x08
+	u8 name_len;		// 0x40: File name length in words
+	u8 type;		// 0x41: File name type
+	__le16 name[];		// 0x42: File name
+};
+
+static_assert(sizeof(((struct ATTR_FILE_NAME *)NULL)->dup) == 0x38);
+static_assert(offsetof(struct ATTR_FILE_NAME, name) == 0x42);
+#define SIZEOF_ATTRIBUTE_FILENAME     0x44
+#define SIZEOF_ATTRIBUTE_FILENAME_MAX (0x42 + 255 * 2)
+
+static inline struct ATTRIB *attr_from_name(struct ATTR_FILE_NAME *fname)
+{
+	return (struct ATTRIB *)((char *)fname - SIZEOF_RESIDENT);
+}
+
+static inline u16 fname_full_size(const struct ATTR_FILE_NAME *fname)
+{
+	// don't return struct_size(fname, name, fname->name_len);
+	return offsetof(struct ATTR_FILE_NAME, name) +
+	       fname->name_len * sizeof(short);
+}
+
+static inline u8 paired_name(u8 type)
+{
+	if (type == FILE_NAME_UNICODE)
+		return FILE_NAME_DOS;
+	if (type == FILE_NAME_DOS)
+		return FILE_NAME_UNICODE;
+	return FILE_NAME_POSIX;
+}
+
+/* Index entry defines ( the field flags in NtfsDirEntry ) */
+#define NTFS_IE_HAS_SUBNODES	cpu_to_le16(1)
+#define NTFS_IE_LAST		cpu_to_le16(2)
+
+/* Directory entry structure */
+struct NTFS_DE {
+	union {
+		struct MFT_REF ref; // 0x00: MFT record number with this file
+		struct {
+			__le16 data_off;  // 0x00:
+			__le16 data_size; // 0x02:
+			__le32 res;	  // 0x04: must be 0
+		} view;
+	};
+	__le16 size;		// 0x08: The size of this entry
+	__le16 key_size;	// 0x0A: The size of File name length in bytes + 0x42
+	__le16 flags;		// 0x0C: Entry flags: NTFS_IE_XXX
+	__le16 res;		// 0x0E:
+
+	// Here any indexed attribute can be placed
+	// One of them is:
+	// struct ATTR_FILE_NAME AttrFileName;
+	//
+
+	// The last 8 bytes of this structure contains
+	// the VBN of subnode
+	// !!! Note !!!
+	// This field is presented only if (flags & NTFS_IE_HAS_SUBNODES)
+	// __le64 vbn;
+};
+
+static_assert(sizeof(struct NTFS_DE) == 0x10);
+
+static inline void de_set_vbn_le(struct NTFS_DE *e, __le64 vcn)
+{
+	__le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64));
+
+	*v = vcn;
+}
+
+static inline void de_set_vbn(struct NTFS_DE *e, CLST vcn)
+{
+	__le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64));
+
+	*v = cpu_to_le64(vcn);
+}
+
+static inline __le64 de_get_vbn_le(const struct NTFS_DE *e)
+{
+	return *(__le64 *)Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64));
+}
+
+static inline CLST de_get_vbn(const struct NTFS_DE *e)
+{
+	__le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64));
+
+	return le64_to_cpu(*v);
+}
+
+static inline struct NTFS_DE *de_get_next(const struct NTFS_DE *e)
+{
+	return Add2Ptr(e, le16_to_cpu(e->size));
+}
+
+static inline struct ATTR_FILE_NAME *de_get_fname(const struct NTFS_DE *e)
+{
+	return le16_to_cpu(e->key_size) >= SIZEOF_ATTRIBUTE_FILENAME ?
+		       Add2Ptr(e, sizeof(struct NTFS_DE)) :
+		       NULL;
+}
+
+static inline bool de_is_last(const struct NTFS_DE *e)
+{
+	return e->flags & NTFS_IE_LAST;
+}
+
+static inline bool de_has_vcn(const struct NTFS_DE *e)
+{
+	return e->flags & NTFS_IE_HAS_SUBNODES;
+}
+
+static inline bool de_has_vcn_ex(const struct NTFS_DE *e)
+{
+	return (e->flags & NTFS_IE_HAS_SUBNODES) &&
+	       (u64)(-1) != *((u64 *)Add2Ptr(e, le16_to_cpu(e->size) -
+							sizeof(__le64)));
+}
+
+#define MAX_BYTES_PER_NAME_ENTRY					       \
+	QuadAlign(sizeof(struct NTFS_DE) +				       \
+		  offsetof(struct ATTR_FILE_NAME, name) +		       \
+		  NTFS_NAME_LEN * sizeof(short))
+
+struct INDEX_HDR {
+	__le32 de_off;	// 0x00: The offset from the start of this structure
+			// to the first NTFS_DE
+	__le32 used;	// 0x04: The size of this structure plus all
+			// entries (quad-word aligned)
+	__le32 total;	// 0x08: The allocated size of for this structure plus all entries
+	u8 flags;	// 0x0C: 0x00 = Small directory, 0x01 = Large directory
+	u8 res[3];
+
+	//
+	// de_off + used <= total
+	//
+};
+
+static_assert(sizeof(struct INDEX_HDR) == 0x10);
+
+static inline struct NTFS_DE *hdr_first_de(const struct INDEX_HDR *hdr)
+{
+	u32 de_off = le32_to_cpu(hdr->de_off);
+	u32 used = le32_to_cpu(hdr->used);
+	struct NTFS_DE *e = Add2Ptr(hdr, de_off);
+	u16 esize;
+
+	if (de_off >= used || de_off >= le32_to_cpu(hdr->total))
+		return NULL;
+
+	esize = le16_to_cpu(e->size);
+	if (esize < sizeof(struct NTFS_DE) || de_off + esize > used)
+		return NULL;
+
+	return e;
+}
+
+static inline struct NTFS_DE *hdr_next_de(const struct INDEX_HDR *hdr,
+					  const struct NTFS_DE *e)
+{
+	size_t off = PtrOffset(hdr, e);
+	u32 used = le32_to_cpu(hdr->used);
+	u16 esize;
+
+	if (off >= used)
+		return NULL;
+
+	esize = le16_to_cpu(e->size);
+
+	if (esize < sizeof(struct NTFS_DE) ||
+	    off + esize + sizeof(struct NTFS_DE) > used)
+		return NULL;
+
+	return Add2Ptr(e, esize);
+}
+
+static inline bool hdr_has_subnode(const struct INDEX_HDR *hdr)
+{
+	return hdr->flags & 1;
+}
+
+struct INDEX_BUFFER {
+	struct NTFS_RECORD_HEADER rhdr; // 'INDX'
+	__le64 vbn; // 0x10: vcn if index >= cluster or vsn id index < cluster
+	struct INDEX_HDR ihdr; // 0x18:
+};
+
+static_assert(sizeof(struct INDEX_BUFFER) == 0x28);
+
+static inline bool ib_is_empty(const struct INDEX_BUFFER *ib)
+{
+	const struct NTFS_DE *first = hdr_first_de(&ib->ihdr);
+
+	return !first || de_is_last(first);
+}
+
+static inline bool ib_is_leaf(const struct INDEX_BUFFER *ib)
+{
+	return !(ib->ihdr.flags & 1);
+}
+
+/* Index root structure ( 0x90 ) */
+enum COLLATION_RULE {
+	NTFS_COLLATION_TYPE_BINARY	= cpu_to_le32(0),
+	// $I30
+	NTFS_COLLATION_TYPE_FILENAME	= cpu_to_le32(0x01),
+	// $SII of $Secure and $Q of Quota
+	NTFS_COLLATION_TYPE_UINT	= cpu_to_le32(0x10),
+	// $O of Quota
+	NTFS_COLLATION_TYPE_SID		= cpu_to_le32(0x11),
+	// $SDH of $Secure
+	NTFS_COLLATION_TYPE_SECURITY_HASH = cpu_to_le32(0x12),
+	// $O of ObjId and "$R" for Reparse
+	NTFS_COLLATION_TYPE_UINTS	= cpu_to_le32(0x13)
+};
+
+static_assert(sizeof(enum COLLATION_RULE) == 4);
+
+//
+struct INDEX_ROOT {
+	enum ATTR_TYPE type;	// 0x00: The type of attribute to index on
+	enum COLLATION_RULE rule; // 0x04: The rule
+	__le32 index_block_size;// 0x08: The size of index record
+	u8 index_block_clst;	// 0x0C: The number of clusters or sectors per index
+	u8 res[3];
+	struct INDEX_HDR ihdr;	// 0x10:
+};
+
+static_assert(sizeof(struct INDEX_ROOT) == 0x20);
+static_assert(offsetof(struct INDEX_ROOT, ihdr) == 0x10);
+
+#define VOLUME_FLAG_DIRTY	    cpu_to_le16(0x0001)
+#define VOLUME_FLAG_RESIZE_LOG_FILE cpu_to_le16(0x0002)
+
+struct VOLUME_INFO {
+	__le64 res1;	// 0x00
+	u8 major_ver;	// 0x08: NTFS major version number (before .)
+	u8 minor_ver;	// 0x09: NTFS minor version number (after .)
+	__le16 flags;	// 0x0A: Volume flags, see VOLUME_FLAG_XXX
+
+}; // sizeof=0xC
+
+#define SIZEOF_ATTRIBUTE_VOLUME_INFO 0xc
+
+#define NTFS_LABEL_MAX_LENGTH		(0x100 / sizeof(short))
+#define NTFS_ATTR_INDEXABLE		cpu_to_le32(0x00000002)
+#define NTFS_ATTR_DUPALLOWED		cpu_to_le32(0x00000004)
+#define NTFS_ATTR_MUST_BE_INDEXED	cpu_to_le32(0x00000010)
+#define NTFS_ATTR_MUST_BE_NAMED		cpu_to_le32(0x00000020)
+#define NTFS_ATTR_MUST_BE_RESIDENT	cpu_to_le32(0x00000040)
+#define NTFS_ATTR_LOG_ALWAYS		cpu_to_le32(0x00000080)
+
+/* $AttrDef file entry */
+struct ATTR_DEF_ENTRY {
+	__le16 name[0x40];	// 0x00: Attr name
+	enum ATTR_TYPE type;	// 0x80: struct ATTRIB type
+	__le32 res;		// 0x84:
+	enum COLLATION_RULE rule; // 0x88:
+	__le32 flags;		// 0x8C: NTFS_ATTR_XXX (see above)
+	__le64 min_sz;		// 0x90: Minimum attribute data size
+	__le64 max_sz;		// 0x98: Maximum attribute data size
+};
+
+static_assert(sizeof(struct ATTR_DEF_ENTRY) == 0xa0);
+
+/* Object ID (0x40) */
+struct OBJECT_ID {
+	struct GUID ObjId;	// 0x00: Unique Id assigned to file
+	struct GUID BirthVolumeId;// 0x10: Birth Volume Id is the Object Id of the Volume on
+				// which the Object Id was allocated. It never changes
+	struct GUID BirthObjectId; // 0x20: Birth Object Id is the first Object Id that was
+				// ever assigned to this MFT Record. I.e. If the Object Id
+				// is changed for some reason, this field will reflect the
+				// original value of the Object Id.
+	struct GUID DomainId;	// 0x30: Domain Id is currently unused but it is intended to be
+				// used in a network environment where the local machine is
+				// part of a Windows 2000 Domain. This may be used in a Windows
+				// 2000 Advanced Server managed domain.
+};
+
+static_assert(sizeof(struct OBJECT_ID) == 0x40);
+
+/* O Directory entry structure ( rule = 0x13 ) */
+struct NTFS_DE_O {
+	struct NTFS_DE de;
+	struct GUID ObjId;	// 0x10: Unique Id assigned to file
+	struct MFT_REF ref;	// 0x20: MFT record number with this file
+	struct GUID BirthVolumeId; // 0x28: Birth Volume Id is the Object Id of the Volume on
+				// which the Object Id was allocated. It never changes
+	struct GUID BirthObjectId; // 0x38: Birth Object Id is the first Object Id that was
+				// ever assigned to this MFT Record. I.e. If the Object Id
+				// is changed for some reason, this field will reflect the
+				// original value of the Object Id.
+				// This field is valid if data_size == 0x48
+	struct GUID BirthDomainId; // 0x48: Domain Id is currently unused but it is intended
+				// to be used in a network environment where the local
+				// machine is part of a Windows 2000 Domain. This may be
+				// used in a Windows 2000 Advanced Server managed domain.
+};
+
+static_assert(sizeof(struct NTFS_DE_O) == 0x58);
+
+#define NTFS_OBJECT_ENTRY_DATA_SIZE1					       \
+	0x38 // struct NTFS_DE_O.BirthDomainId is not used
+#define NTFS_OBJECT_ENTRY_DATA_SIZE2					       \
+	0x48 // struct NTFS_DE_O.BirthDomainId is used
+
+/* Q Directory entry structure ( rule = 0x11 ) */
+struct NTFS_DE_Q {
+	struct NTFS_DE de;
+	__le32 owner_id;	// 0x10: Unique Id assigned to file
+	__le32 Version;		// 0x14: 0x02
+	__le32 flags2;		// 0x18: Quota flags, see above
+	__le64 BytesUsed;	// 0x1C:
+	__le64 ChangeTime;	// 0x24:
+	__le64 WarningLimit;	// 0x28:
+	__le64 HardLimit;	// 0x34:
+	__le64 ExceededTime;	// 0x3C:
+
+	// SID is placed here
+}; // sizeof() = 0x44
+
+#define SIZEOF_NTFS_DE_Q 0x44
+
+#define SecurityDescriptorsBlockSize 0x40000 // 256K
+#define SecurityDescriptorMaxSize    0x20000 // 128K
+#define Log2OfSecurityDescriptorsBlockSize 18
+
+struct SECURITY_KEY {
+	__le32 hash; //  Hash value for descriptor
+	__le32 sec_id; //  Security Id (guaranteed unique)
+};
+
+/* Security descriptors (the content of $Secure::SDS data stream) */
+struct SECURITY_HDR {
+	struct SECURITY_KEY key;	// 0x00: Security Key
+	__le64 off;			// 0x08: Offset of this entry in the file
+	__le32 size;			// 0x10: Size of this entry, 8 byte aligned
+	//
+	// Security descriptor itself is placed here
+	// Total size is 16 byte aligned
+	//
+} __packed;
+
+#define SIZEOF_SECURITY_HDR 0x14
+
+/* SII Directory entry structure */
+struct NTFS_DE_SII {
+	struct NTFS_DE de;
+	__le32 sec_id;			// 0x10: Key: sizeof(security_id) = wKeySize
+	struct SECURITY_HDR sec_hdr;	// 0x14:
+} __packed;
+
+#define SIZEOF_SII_DIRENTRY 0x28
+
+/* SDH Directory entry structure */
+struct NTFS_DE_SDH {
+	struct NTFS_DE de;
+	struct SECURITY_KEY key;	// 0x10: Key
+	struct SECURITY_HDR sec_hdr;	// 0x18: Data
+	__le16 magic[2];		// 0x2C: 0x00490049 "I I"
+};
+
+#define SIZEOF_SDH_DIRENTRY 0x30
+
+struct REPARSE_KEY {
+	__le32 ReparseTag;		// 0x00: Reparse Tag
+	struct MFT_REF ref;		// 0x04: MFT record number with this file
+}; // sizeof() = 0x0C
+
+static_assert(offsetof(struct REPARSE_KEY, ref) == 0x04);
+#define SIZEOF_REPARSE_KEY 0x0C
+
+/* Reparse Directory entry structure */
+struct NTFS_DE_R {
+	struct NTFS_DE de;
+	struct REPARSE_KEY key;		// 0x10: Reparse Key
+	u32 zero;			// 0x1c
+}; // sizeof() = 0x20
+
+static_assert(sizeof(struct NTFS_DE_R) == 0x20);
+
+/* CompressReparseBuffer.WofVersion */
+#define WOF_CURRENT_VERSION		cpu_to_le32(1)
+/* CompressReparseBuffer.WofProvider */
+#define WOF_PROVIDER_WIM		cpu_to_le32(1)
+/* CompressReparseBuffer.WofProvider */
+#define WOF_PROVIDER_SYSTEM		cpu_to_le32(2)
+/* CompressReparseBuffer.ProviderVer */
+#define WOF_PROVIDER_CURRENT_VERSION	cpu_to_le32(1)
+
+#define WOF_COMPRESSION_XPRESS4K	cpu_to_le32(0) // 4k
+#define WOF_COMPRESSION_LZX32K		cpu_to_le32(1) // 32k
+#define WOF_COMPRESSION_XPRESS8K	cpu_to_le32(2) // 8k
+#define WOF_COMPRESSION_XPRESS16K	cpu_to_le32(3) // 16k
+
+/*
+ * ATTR_REPARSE (0xC0)
+ *
+ * The reparse struct GUID structure is used by all 3rd party layered drivers to
+ * store data in a reparse point. For non-Microsoft tags, The struct GUID field
+ * cannot be GUID_NULL.
+ * The constraints on reparse tags are defined below.
+ * Microsoft tags can also be used with this format of the reparse point buffer.
+ */
+struct REPARSE_POINT {
+	__le32 ReparseTag;	// 0x00:
+	__le16 ReparseDataLength;// 0x04:
+	__le16 Reserved;
+
+	struct GUID Guid;	// 0x08:
+
+	//
+	// Here GenericReparseBuffer is placed
+	//
+};
+
+static_assert(sizeof(struct REPARSE_POINT) == 0x18);
+
+//
+// Maximum allowed size of the reparse data.
+//
+#define MAXIMUM_REPARSE_DATA_BUFFER_SIZE	(16 * 1024)
+
+//
+// The value of the following constant needs to satisfy the following
+// conditions:
+//  (1) Be at least as large as the largest of the reserved tags.
+//  (2) Be strictly smaller than all the tags in use.
+//
+#define IO_REPARSE_TAG_RESERVED_RANGE		1
+
+//
+// The reparse tags are a ULONG. The 32 bits are laid out as follows:
+//
+//   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
+//   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+//  +-+-+-+-+-----------------------+-------------------------------+
+//  |M|R|N|R|	  Reserved bits     |	    Reparse Tag Value	    |
+//  +-+-+-+-+-----------------------+-------------------------------+
+//
+// M is the Microsoft bit. When set to 1, it denotes a tag owned by Microsoft.
+//   All ISVs must use a tag with a 0 in this position.
+//   Note: If a Microsoft tag is used by non-Microsoft software, the
+//   behavior is not defined.
+//
+// R is reserved.  Must be zero for non-Microsoft tags.
+//
+// N is name surrogate. When set to 1, the file represents another named
+//   entity in the system.
+//
+// The M and N bits are OR-able.
+// The following macros check for the M and N bit values:
+//
+
+//
+// Macro to determine whether a reparse point tag corresponds to a tag
+// owned by Microsoft.
+//
+#define IsReparseTagMicrosoft(_tag)	(((_tag)&IO_REPARSE_TAG_MICROSOFT))
+
+//
+// Macro to determine whether a reparse point tag is a name surrogate
+//
+#define IsReparseTagNameSurrogate(_tag)	(((_tag)&IO_REPARSE_TAG_NAME_SURROGATE))
+
+//
+// The following constant represents the bits that are valid to use in
+// reparse tags.
+//
+#define IO_REPARSE_TAG_VALID_VALUES	0xF000FFFF
+
+//
+// Macro to determine whether a reparse tag is a valid tag.
+//
+#define IsReparseTagValid(_tag)						       \
+	(!((_tag) & ~IO_REPARSE_TAG_VALID_VALUES) &&			       \
+	 ((_tag) > IO_REPARSE_TAG_RESERVED_RANGE))
+
+//
+// Microsoft tags for reparse points.
+//
+
+enum IO_REPARSE_TAG {
+	IO_REPARSE_TAG_SYMBOLIC_LINK	= cpu_to_le32(0),
+	IO_REPARSE_TAG_NAME_SURROGATE	= cpu_to_le32(0x20000000),
+	IO_REPARSE_TAG_MICROSOFT	= cpu_to_le32(0x80000000),
+	IO_REPARSE_TAG_MOUNT_POINT	= cpu_to_le32(0xA0000003),
+	IO_REPARSE_TAG_SYMLINK		= cpu_to_le32(0xA000000C),
+	IO_REPARSE_TAG_HSM		= cpu_to_le32(0xC0000004),
+	IO_REPARSE_TAG_SIS		= cpu_to_le32(0x80000007),
+	IO_REPARSE_TAG_DEDUP		= cpu_to_le32(0x80000013),
+	IO_REPARSE_TAG_COMPRESS		= cpu_to_le32(0x80000017),
+
+	//
+	// The reparse tag 0x80000008 is reserved for Microsoft internal use
+	// (may be published in the future)
+	//
+
+	//
+	// Microsoft reparse tag reserved for DFS
+	//
+	IO_REPARSE_TAG_DFS		= cpu_to_le32(0x8000000A),
+
+	//
+	// Microsoft reparse tag reserved for the file system filter manager
+	//
+	IO_REPARSE_TAG_FILTER_MANAGER	= cpu_to_le32(0x8000000B),
+
+	//
+	// Non-Microsoft tags for reparse points
+	//
+
+	//
+	// Tag allocated to CONGRUENT, May 2000. Used by IFSTEST
+	//
+	IO_REPARSE_TAG_IFSTEST_CONGRUENT = cpu_to_le32(0x00000009),
+
+	//
+	// Tag allocated to ARKIVIO
+	//
+	IO_REPARSE_TAG_ARKIVIO		= cpu_to_le32(0x0000000C),
+
+	//
+	//  Tag allocated to SOLUTIONSOFT
+	//
+	IO_REPARSE_TAG_SOLUTIONSOFT	= cpu_to_le32(0x2000000D),
+
+	//
+	//  Tag allocated to COMMVAULT
+	//
+	IO_REPARSE_TAG_COMMVAULT	= cpu_to_le32(0x0000000E),
+
+	// OneDrive??
+	IO_REPARSE_TAG_CLOUD		= cpu_to_le32(0x9000001A),
+	IO_REPARSE_TAG_CLOUD_1		= cpu_to_le32(0x9000101A),
+	IO_REPARSE_TAG_CLOUD_2		= cpu_to_le32(0x9000201A),
+	IO_REPARSE_TAG_CLOUD_3		= cpu_to_le32(0x9000301A),
+	IO_REPARSE_TAG_CLOUD_4		= cpu_to_le32(0x9000401A),
+	IO_REPARSE_TAG_CLOUD_5		= cpu_to_le32(0x9000501A),
+	IO_REPARSE_TAG_CLOUD_6		= cpu_to_le32(0x9000601A),
+	IO_REPARSE_TAG_CLOUD_7		= cpu_to_le32(0x9000701A),
+	IO_REPARSE_TAG_CLOUD_8		= cpu_to_le32(0x9000801A),
+	IO_REPARSE_TAG_CLOUD_9		= cpu_to_le32(0x9000901A),
+	IO_REPARSE_TAG_CLOUD_A		= cpu_to_le32(0x9000A01A),
+	IO_REPARSE_TAG_CLOUD_B		= cpu_to_le32(0x9000B01A),
+	IO_REPARSE_TAG_CLOUD_C		= cpu_to_le32(0x9000C01A),
+	IO_REPARSE_TAG_CLOUD_D		= cpu_to_le32(0x9000D01A),
+	IO_REPARSE_TAG_CLOUD_E		= cpu_to_le32(0x9000E01A),
+	IO_REPARSE_TAG_CLOUD_F		= cpu_to_le32(0x9000F01A),
+
+};
+
+#define SYMLINK_FLAG_RELATIVE		1
+
+/* Microsoft reparse buffer. (see DDK for details) */
+struct REPARSE_DATA_BUFFER {
+	__le32 ReparseTag;		// 0x00:
+	__le16 ReparseDataLength;	// 0x04:
+	__le16 Reserved;
+
+	union {
+		// If ReparseTag == 0xA0000003 (IO_REPARSE_TAG_MOUNT_POINT)
+		struct {
+			__le16 SubstituteNameOffset; // 0x08
+			__le16 SubstituteNameLength; // 0x0A
+			__le16 PrintNameOffset;      // 0x0C
+			__le16 PrintNameLength;      // 0x0E
+			__le16 PathBuffer[];	     // 0x10
+		} MountPointReparseBuffer;
+
+		// If ReparseTag == 0xA000000C (IO_REPARSE_TAG_SYMLINK)
+		// https://msdn.microsoft.com/en-us/library/cc232006.aspx
+		struct {
+			__le16 SubstituteNameOffset; // 0x08
+			__le16 SubstituteNameLength; // 0x0A
+			__le16 PrintNameOffset;      // 0x0C
+			__le16 PrintNameLength;      // 0x0E
+			// 0-absolute path 1- relative path, SYMLINK_FLAG_RELATIVE
+			__le32 Flags;		     // 0x10
+			__le16 PathBuffer[];	     // 0x14
+		} SymbolicLinkReparseBuffer;
+
+		// If ReparseTag == 0x80000017U
+		struct {
+			__le32 WofVersion;  // 0x08 == 1
+			/* 1 - WIM backing provider ("WIMBoot"),
+			 * 2 - System compressed file provider
+			 */
+			__le32 WofProvider; // 0x0C
+			__le32 ProviderVer; // 0x10: == 1 WOF_FILE_PROVIDER_CURRENT_VERSION == 1
+			__le32 CompressionFormat; // 0x14: 0, 1, 2, 3. See WOF_COMPRESSION_XXX
+		} CompressReparseBuffer;
+
+		struct {
+			u8 DataBuffer[1];   // 0x08
+		} GenericReparseBuffer;
+	};
+};
+
+/* ATTR_EA_INFO (0xD0) */
+
+#define FILE_NEED_EA 0x80 // See ntifs.h
+/* FILE_NEED_EA, indicates that the file to which the EA belongs cannot be
+ * interpreted without understanding the associated extended attributes.
+ */
+struct EA_INFO {
+	__le16 size_pack;	// 0x00: Size of buffer to hold in packed form
+	__le16 count;		// 0x02: Count of EA's with FILE_NEED_EA bit set
+	__le32 size;		// 0x04: Size of buffer to hold in unpacked form
+};
+
+static_assert(sizeof(struct EA_INFO) == 8);
+
+/* ATTR_EA (0xE0) */
+struct EA_FULL {
+	__le32 size;		// 0x00: (not in packed)
+	u8 flags;		// 0x04
+	u8 name_len;		// 0x05
+	__le16 elength;		// 0x06
+	u8 name[];		// 0x08
+};
+
+static_assert(offsetof(struct EA_FULL, name) == 8);
+
+#define ACL_REVISION	2
+#define ACL_REVISION_DS 4
+
+#define SE_SELF_RELATIVE cpu_to_le16(0x8000)
+
+struct SECURITY_DESCRIPTOR_RELATIVE {
+	u8 Revision;
+	u8 Sbz1;
+	__le16 Control;
+	__le32 Owner;
+	__le32 Group;
+	__le32 Sacl;
+	__le32 Dacl;
+};
+static_assert(sizeof(struct SECURITY_DESCRIPTOR_RELATIVE) == 0x14);
+
+struct ACE_HEADER {
+	u8 AceType;
+	u8 AceFlags;
+	__le16 AceSize;
+};
+static_assert(sizeof(struct ACE_HEADER) == 4);
+
+struct ACL {
+	u8 AclRevision;
+	u8 Sbz1;
+	__le16 AclSize;
+	__le16 AceCount;
+	__le16 Sbz2;
+};
+static_assert(sizeof(struct ACL) == 8);
+
+struct SID {
+	u8 Revision;
+	u8 SubAuthorityCount;
+	u8 IdentifierAuthority[6];
+	__le32 SubAuthority[];
+};
+static_assert(offsetof(struct SID, SubAuthority) == 8);
+
+// clang-format on
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
new file mode 100644
index 000000000..5e1dd628d
--- /dev/null
+++ b/fs/ntfs3/ntfs_fs.h
@@ -0,0 +1,1085 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+// clang-format off
+#define MINUS_ONE_T			((size_t)(-1))
+/* Biggest MFT / smallest cluster */
+#define MAXIMUM_BYTES_PER_MFT		4096
+#define NTFS_BLOCKS_PER_MFT_RECORD	(MAXIMUM_BYTES_PER_MFT / 512)
+
+#define MAXIMUM_BYTES_PER_INDEX		4096
+#define NTFS_BLOCKS_PER_INODE		(MAXIMUM_BYTES_PER_INDEX / 512)
+
+/* ntfs specific error code when fixup failed*/
+#define E_NTFS_FIXUP			555
+/* ntfs specific error code about resident->nonresident*/
+#define E_NTFS_NONRESIDENT		556
+
+/* sbi->flags */
+#define NTFS_FLAGS_NODISCARD		0x00000001
+/* Set when LogFile is replaying */
+#define NTFS_FLAGS_LOG_REPLAYING	0x00000008
+/* Set when we changed first MFT's which copy must be updated in $MftMirr */
+#define NTFS_FLAGS_MFTMIRR		0x00001000
+#define NTFS_FLAGS_NEED_REPLAY		0x04000000
+
+
+/* ni->ni_flags */
+/*
+ * Data attribute is external compressed (lzx/xpress)
+ * 1 - WOF_COMPRESSION_XPRESS4K
+ * 2 - WOF_COMPRESSION_XPRESS8K
+ * 3 - WOF_COMPRESSION_XPRESS16K
+ * 4 - WOF_COMPRESSION_LZX32K
+ */
+#define NI_FLAG_COMPRESSED_MASK		0x0000000f
+/* Data attribute is deduplicated */
+#define NI_FLAG_DEDUPLICATED		0x00000010
+#define NI_FLAG_EA			0x00000020
+#define NI_FLAG_DIR			0x00000040
+#define NI_FLAG_RESIDENT		0x00000080
+#define NI_FLAG_UPDATE_PARENT		0x00000100
+// clang-format on
+
+struct ntfs_mount_options {
+	struct nls_table *nls;
+
+	kuid_t fs_uid;
+	kgid_t fs_gid;
+	u16 fs_fmask_inv;
+	u16 fs_dmask_inv;
+
+	unsigned uid : 1, /* uid was set */
+		gid : 1, /* gid was set */
+		fmask : 1, /* fmask was set */
+		dmask : 1, /*dmask was set*/
+		sys_immutable : 1, /* immutable system files */
+		discard : 1, /* issue discard requests on deletions */
+		sparse : 1, /*create sparse files*/
+		showmeta : 1, /*show meta files*/
+		nohidden : 1, /*do not show hidden files*/
+		force : 1, /*rw mount dirty volume*/
+		no_acs_rules : 1, /*exclude acs rules*/
+		prealloc : 1 /*preallocate space when file is growing*/
+		;
+};
+
+/* special value to unpack and deallocate*/
+#define RUN_DEALLOCATE ((struct runs_tree *)(size_t)1)
+
+/* TODO: use rb tree instead of array */
+struct runs_tree {
+	struct ntfs_run *runs;
+	size_t count; // Currently used size a ntfs_run storage.
+	size_t allocated; // Currently allocated ntfs_run storage size.
+};
+
+struct ntfs_buffers {
+	/* Biggest MFT / smallest cluster = 4096 / 512 = 8 */
+	/* Biggest index / smallest cluster = 4096 / 512 = 8 */
+	struct buffer_head *bh[PAGE_SIZE >> SECTOR_SHIFT];
+	u32 bytes;
+	u32 nbufs;
+	u32 off;
+};
+
+enum ALLOCATE_OPT {
+	ALLOCATE_DEF = 0, // Allocate all clusters
+	ALLOCATE_MFT = 1, // Allocate for MFT
+};
+
+enum bitmap_mutex_classes {
+	BITMAP_MUTEX_CLUSTERS = 0,
+	BITMAP_MUTEX_MFT = 1,
+};
+
+struct wnd_bitmap {
+	struct super_block *sb;
+	struct rw_semaphore rw_lock;
+
+	struct runs_tree run;
+	size_t nbits;
+
+	size_t total_zeroes; // total number of free bits
+	u16 *free_bits; // free bits in each window
+	size_t nwnd;
+	u32 bits_last; // bits in last window
+
+	struct rb_root start_tree; // extents, sorted by 'start'
+	struct rb_root count_tree; // extents, sorted by 'count + start'
+	size_t count; // extents count
+
+	/*
+	 * -1 Tree is activated but not updated (too many fragments)
+	 * 0 - Tree is not activated
+	 * 1 - Tree is activated and updated
+	 */
+	int uptodated;
+	size_t extent_min; // Minimal extent used while building
+	size_t extent_max; // Upper estimate of biggest free block
+
+	/* Zone [bit, end) */
+	size_t zone_bit;
+	size_t zone_end;
+
+	bool set_tail; // not necessary in driver
+	bool inited;
+};
+
+typedef int (*NTFS_CMP_FUNC)(const void *key1, size_t len1, const void *key2,
+			     size_t len2, const void *param);
+
+enum index_mutex_classed {
+	INDEX_MUTEX_I30 = 0,
+	INDEX_MUTEX_SII = 1,
+	INDEX_MUTEX_SDH = 2,
+	INDEX_MUTEX_SO = 3,
+	INDEX_MUTEX_SQ = 4,
+	INDEX_MUTEX_SR = 5,
+	INDEX_MUTEX_TOTAL
+};
+
+/* ntfs_index - allocation unit inside directory */
+struct ntfs_index {
+	struct runs_tree bitmap_run;
+	struct runs_tree alloc_run;
+	/* read/write access to 'bitmap_run'/'alloc_run' while ntfs_readdir */
+	struct rw_semaphore run_lock;
+
+	/*TODO: remove 'cmp'*/
+	NTFS_CMP_FUNC cmp;
+
+	u8 index_bits; // log2(root->index_block_size)
+	u8 idx2vbn_bits; // log2(root->index_block_clst)
+	u8 vbn2vbo_bits; // index_block_size < cluster? 9 : cluster_bits
+	u8 type; // index_mutex_classed
+};
+
+/* Minimum mft zone */
+#define NTFS_MIN_MFT_ZONE 100
+
+/* ntfs file system in-core superblock data */
+struct ntfs_sb_info {
+	struct super_block *sb;
+
+	u32 discard_granularity;
+	u64 discard_granularity_mask_inv; // ~(discard_granularity_mask_inv-1)
+
+	u32 cluster_size; // bytes per cluster
+	u32 cluster_mask; // == cluster_size - 1
+	u64 cluster_mask_inv; // ~(cluster_size - 1)
+	u32 block_mask; // sb->s_blocksize - 1
+	u32 blocks_per_cluster; // cluster_size / sb->s_blocksize
+
+	u32 record_size;
+	u32 sector_size;
+	u32 index_size;
+
+	u8 sector_bits;
+	u8 cluster_bits;
+	u8 record_bits;
+
+	u64 maxbytes; // Maximum size for normal files
+	u64 maxbytes_sparse; // Maximum size for sparse file
+
+	u32 flags; // See NTFS_FLAGS_XXX
+
+	CLST bad_clusters; // The count of marked bad clusters
+
+	u16 max_bytes_per_attr; // maximum attribute size in record
+	u16 attr_size_tr; // attribute size threshold (320 bytes)
+
+	/* Records in $Extend */
+	CLST objid_no;
+	CLST quota_no;
+	CLST reparse_no;
+	CLST usn_jrnl_no;
+
+	struct ATTR_DEF_ENTRY *def_table; // attribute definition table
+	u32 def_entries;
+	u32 ea_max_size;
+
+	struct MFT_REC *new_rec;
+
+	u16 *upcase;
+
+	struct {
+		u64 lbo, lbo2;
+		struct ntfs_inode *ni;
+		struct wnd_bitmap bitmap; // $MFT::Bitmap
+		/*
+		 * MFT records [11-24) used to expand MFT itself
+		 * They always marked as used in $MFT::Bitmap
+		 * 'reserved_bitmap' contains real bitmap of these records
+		 */
+		ulong reserved_bitmap; // bitmap of used records [11 - 24)
+		size_t next_free; // The next record to allocate from
+		size_t used; // mft valid size in records
+		u32 recs_mirr; // Number of records in MFTMirr
+		u8 next_reserved;
+		u8 reserved_bitmap_inited;
+	} mft;
+
+	struct {
+		struct wnd_bitmap bitmap; // $Bitmap::Data
+		CLST next_free_lcn;
+	} used;
+
+	struct {
+		u64 size; // in bytes
+		u64 blocks; // in blocks
+		u64 ser_num;
+		struct ntfs_inode *ni;
+		__le16 flags; // cached current VOLUME_INFO::flags, VOLUME_FLAG_DIRTY
+		u8 major_ver;
+		u8 minor_ver;
+		char label[65];
+		bool real_dirty; /* real fs state*/
+	} volume;
+
+	struct {
+		struct ntfs_index index_sii;
+		struct ntfs_index index_sdh;
+		struct ntfs_inode *ni;
+		u32 next_id;
+		u64 next_off;
+
+		__le32 def_security_id;
+	} security;
+
+	struct {
+		struct ntfs_index index_r;
+		struct ntfs_inode *ni;
+		u64 max_size; // 16K
+	} reparse;
+
+	struct {
+		struct ntfs_index index_o;
+		struct ntfs_inode *ni;
+	} objid;
+
+	struct {
+		struct mutex mtx_lznt;
+		struct lznt *lznt;
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+		struct mutex mtx_xpress;
+		struct xpress_decompressor *xpress;
+		struct mutex mtx_lzx;
+		struct lzx_decompressor *lzx;
+#endif
+	} compress;
+
+	struct ntfs_mount_options options;
+	struct ratelimit_state msg_ratelimit;
+};
+
+/*
+ * one MFT record(usually 1024 bytes), consists of attributes
+ */
+struct mft_inode {
+	struct rb_node node;
+	struct ntfs_sb_info *sbi;
+
+	struct MFT_REC *mrec;
+	struct ntfs_buffers nb;
+
+	CLST rno;
+	bool dirty;
+};
+
+/* nested class for ntfs_inode::ni_lock */
+enum ntfs_inode_mutex_lock_class {
+	NTFS_INODE_MUTEX_DIRTY,
+	NTFS_INODE_MUTEX_SECURITY,
+	NTFS_INODE_MUTEX_OBJID,
+	NTFS_INODE_MUTEX_REPARSE,
+	NTFS_INODE_MUTEX_NORMAL,
+	NTFS_INODE_MUTEX_PARENT,
+};
+
+/*
+ * ntfs inode - extends linux inode. consists of one or more mft inodes
+ */
+struct ntfs_inode {
+	struct mft_inode mi; // base record
+
+	/*
+	 * Valid size: [0 - i_valid) - these range in file contains valid data
+	 * Range [i_valid - inode->i_size) - contains 0
+	 * Usually i_valid <= inode->i_size
+	 */
+	u64 i_valid;
+	struct timespec64 i_crtime;
+
+	struct mutex ni_lock;
+
+	/* file attributes from std */
+	enum FILE_ATTRIBUTE std_fa;
+	__le32 std_security_id;
+
+	/*
+	 * tree of mft_inode
+	 * not empty when primary MFT record (usually 1024 bytes) can't save all attributes
+	 * e.g. file becomes too fragmented or contains a lot of names
+	 */
+	struct rb_root mi_tree;
+
+	/*
+	 * This member is used in ntfs_readdir to ensure that all subrecords are loaded
+	 */
+	u8 mi_loaded;
+
+	union {
+		struct ntfs_index dir;
+		struct {
+			struct rw_semaphore run_lock;
+			struct runs_tree run;
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+			struct page *offs_page;
+#endif
+		} file;
+	};
+
+	struct {
+		struct runs_tree run;
+		struct ATTR_LIST_ENTRY *le; // 1K aligned memory
+		size_t size;
+		bool dirty;
+	} attr_list;
+
+	size_t ni_flags; // NI_FLAG_XXX
+
+	struct inode vfs_inode;
+};
+
+struct indx_node {
+	struct ntfs_buffers nb;
+	struct INDEX_BUFFER *index;
+};
+
+struct ntfs_fnd {
+	int level;
+	struct indx_node *nodes[20];
+	struct NTFS_DE *de[20];
+	struct NTFS_DE *root_de;
+};
+
+enum REPARSE_SIGN {
+	REPARSE_NONE = 0,
+	REPARSE_COMPRESSED = 1,
+	REPARSE_DEDUPLICATED = 2,
+	REPARSE_LINK = 3
+};
+
+/* 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,
+			   CLST *new_lcn);
+int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
+			  struct ATTR_LIST_ENTRY *le, struct mft_inode *mi,
+			  u64 new_size, struct runs_tree *run,
+			  struct ATTRIB **ins_attr, struct page *page);
+int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		  const __le16 *name, u8 name_len, struct runs_tree *run,
+		  u64 new_size, const u64 *new_valid, bool keep_prealloc,
+		  struct ATTRIB **ret);
+int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
+			CLST *len, bool *new);
+int attr_data_read_resident(struct ntfs_inode *ni, struct page *page);
+int attr_data_write_resident(struct ntfs_inode *ni, struct page *page);
+int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		       const __le16 *name, u8 name_len, struct runs_tree *run,
+		       CLST vcn);
+int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
+			 const __le16 *name, u8 name_len, struct runs_tree *run,
+			 u64 from, u64 to);
+int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
+			struct runs_tree *run, u64 frame, u64 frames,
+			u8 frame_bits, u32 *ondisk_size, u64 *vbo_data);
+int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
+			     CLST frame, CLST *clst_data);
+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_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes);
+
+/* functions from attrlist.c*/
+void al_destroy(struct ntfs_inode *ni);
+bool al_verify(struct ntfs_inode *ni);
+int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr);
+struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
+				     struct ATTR_LIST_ENTRY *le);
+struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni,
+				   struct ATTR_LIST_ENTRY *le,
+				   const struct ATTRIB *attr);
+struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
+				   struct ATTR_LIST_ENTRY *le,
+				   enum ATTR_TYPE type, const __le16 *name,
+				   u8 name_len, const CLST *vcn);
+int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
+	      u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref,
+	      struct ATTR_LIST_ENTRY **new_le);
+bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le);
+bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
+		  const __le16 *name, size_t name_len,
+		  const struct MFT_REF *ref);
+int al_update(struct ntfs_inode *ni);
+static inline size_t al_aligned(size_t size)
+{
+	return (size + 1023) & ~(size_t)1023;
+}
+
+/* globals from bitfunc.c */
+bool are_bits_clear(const ulong *map, size_t bit, size_t nbits);
+bool are_bits_set(const ulong *map, size_t bit, size_t nbits);
+size_t get_set_bits_ex(const ulong *map, size_t bit, size_t nbits);
+
+/* globals from dir.c */
+int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni,
+		      u8 *buf, int buf_len);
+int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
+		      struct cpu_str *uni, u32 max_ulen,
+		      enum utf16_endian endian);
+struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni,
+			   struct ntfs_fnd *fnd);
+bool dir_is_empty(struct inode *dir);
+extern const struct file_operations ntfs_dir_operations;
+
+/* globals from file.c*/
+int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+		 struct kstat *stat, u32 request_mask, u32 flags);
+void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn,
+			 CLST len);
+int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		  struct iattr *attr);
+int ntfs_file_open(struct inode *inode, struct file *file);
+int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		__u64 start, __u64 len);
+extern const struct inode_operations ntfs_special_inode_operations;
+extern const struct inode_operations ntfs_file_inode_operations;
+extern const struct file_operations ntfs_file_operations;
+
+/* globals from frecord.c */
+void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi);
+struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni);
+struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni);
+void ni_clear(struct ntfs_inode *ni);
+int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi);
+int ni_load_mi(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
+	       struct mft_inode **mi);
+struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr,
+			    struct ATTR_LIST_ENTRY **entry_o,
+			    enum ATTR_TYPE type, const __le16 *name,
+			    u8 name_len, const CLST *vcn,
+			    struct mft_inode **mi);
+struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr,
+			       struct ATTR_LIST_ENTRY **le,
+			       struct mft_inode **mi);
+struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
+			    const __le16 *name, u8 name_len, CLST vcn,
+			    struct mft_inode **pmi);
+int ni_load_all_mi(struct ntfs_inode *ni);
+bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi);
+int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		   const __le16 *name, size_t name_len, bool base_only,
+		   const __le16 *id);
+int ni_create_attr_list(struct ntfs_inode *ni);
+int ni_expand_list(struct ntfs_inode *ni);
+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);
+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);
+int ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr,
+		      struct ATTR_LIST_ENTRY *le);
+int ni_delete_all(struct ntfs_inode *ni);
+struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni,
+				     const struct cpu_str *uni,
+				     const struct MFT_REF *home,
+				     struct ATTR_LIST_ENTRY **entry);
+struct ATTR_FILE_NAME *ni_fname_type(struct ntfs_inode *ni, u8 name_type,
+				     struct ATTR_LIST_ENTRY **entry);
+int ni_new_attr_flags(struct ntfs_inode *ni, enum FILE_ATTRIBUTE new_fa);
+enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr,
+				   void *buffer);
+int ni_write_inode(struct inode *inode, int sync, const char *hint);
+#define _ni_write_inode(i, w) ni_write_inode(i, w, __func__)
+int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+	      __u64 vbo, __u64 len);
+int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page);
+int ni_decompress_file(struct ntfs_inode *ni);
+int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
+		  u32 pages_per_frame);
+int ni_write_frame(struct ntfs_inode *ni, struct page **pages,
+		   u32 pages_per_frame);
+
+/* globals from fslog.c */
+int log_replay(struct ntfs_inode *ni, bool *initialized);
+
+/* globals from fsntfs.c */
+bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes);
+int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
+		       bool simple);
+int ntfs_extend_init(struct ntfs_sb_info *sbi);
+int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi);
+const struct ATTR_DEF_ENTRY *ntfs_query_def(struct ntfs_sb_info *sbi,
+					    enum ATTR_TYPE Type);
+int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len,
+			     CLST *new_lcn, CLST *new_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);
+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);
+enum NTFS_DIRTY_FLAGS {
+	NTFS_DIRTY_CLEAR = 0,
+	NTFS_DIRTY_DIRTY = 1,
+	NTFS_DIRTY_ERROR = 2,
+};
+int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty);
+int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer);
+int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes,
+		  const void *buffer, int wait);
+int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		      u64 vbo, const void *buf, size_t bytes);
+struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi,
+				   const struct runs_tree *run, u64 vbo);
+int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		     u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb);
+int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo,
+		 struct NTFS_RECORD_HEADER *rhdr, u32 bytes,
+		 struct ntfs_buffers *nb);
+int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo,
+		u32 bytes, struct ntfs_buffers *nb);
+int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
+		  struct ntfs_buffers *nb, int sync);
+int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		   struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
+		   u32 op);
+int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run);
+int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run,
+		    u64 vbo, u64 *lbo, u64 *bytes);
+struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST nRec,
+				  bool dir);
+extern const u8 s_default_security[0x50];
+bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len);
+int ntfs_security_init(struct ntfs_sb_info *sbi);
+in...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 06/10] fs/ntfs3: Add compression

[Konstantin K. <alm...@pa...>]

This patch adds different types of NTFS-applicable compressions:
- lznt
- lzx
- xpress
Latter two (lzx, xpress) implement Windows Compact OS feature and
were taken from ntfs-3g system comression plugin authored by Eric Biggers
(https://github.com/ebiggers/ntfs-3g-system-compression)
which were ported to ntfs3 and adapted to Linux Kernel environment.

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/lib/decompress_common.c | 332 +++++++++++++++
 fs/ntfs3/lib/decompress_common.h | 352 ++++++++++++++++
 fs/ntfs3/lib/lib.h               |  26 ++
 fs/ntfs3/lib/lzx_decompress.c    | 683 +++++++++++++++++++++++++++++++
 fs/ntfs3/lib/xpress_decompress.c | 155 +++++++
 fs/ntfs3/lznt.c                  | 452 ++++++++++++++++++++
 6 files changed, 2000 insertions(+)
 create mode 100644 fs/ntfs3/lib/decompress_common.c
 create mode 100644 fs/ntfs3/lib/decompress_common.h
 create mode 100644 fs/ntfs3/lib/lib.h
 create mode 100644 fs/ntfs3/lib/lzx_decompress.c
 create mode 100644 fs/ntfs3/lib/xpress_decompress.c
 create mode 100644 fs/ntfs3/lznt.c

diff --git a/fs/ntfs3/lib/decompress_common.c b/fs/ntfs3/lib/decompress_common.c
new file mode 100644
index 000000000..83c9e93ae
--- /dev/null
+++ b/fs/ntfs3/lib/decompress_common.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * decompress_common.c - Code shared by the XPRESS and LZX decompressors
+ *
+ * Copyright (C) 2015 Eric Biggers
+ *
+ * This program is free software: you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License as published by the Free Software
+ * Foundation, either version 2 of the License, or (at your option) any later
+ * version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "decompress_common.h"
+
+/*
+ * make_huffman_decode_table() -
+ *
+ * Build a decoding table for a canonical prefix code, or "Huffman code".
+ *
+ * This is an internal function, not part of the library API!
+ *
+ * This takes as input the length of the codeword for each symbol in the
+ * alphabet and produces as output a table that can be used for fast
+ * decoding of prefix-encoded symbols using read_huffsym().
+ *
+ * Strictly speaking, a canonical prefix code might not be a Huffman
+ * code.  But this algorithm will work either way; and in fact, since
+ * Huffman codes are defined in terms of symbol frequencies, there is no
+ * way for the decompressor to know whether the code is a true Huffman
+ * code or not until all symbols have been decoded.
+ *
+ * Because the prefix code is assumed to be "canonical", it can be
+ * reconstructed directly from the codeword lengths.  A prefix code is
+ * canonical if and only if a longer codeword never lexicographically
+ * precedes a shorter codeword, and the lexicographic ordering of
+ * codewords of the same length is the same as the lexicographic ordering
+ * of the corresponding symbols.  Consequently, we can sort the symbols
+ * primarily by codeword length and secondarily by symbol value, then
+ * reconstruct the prefix code by generating codewords lexicographically
+ * in that order.
+ *
+ * This function does not, however, generate the prefix code explicitly.
+ * Instead, it directly builds a table for decoding symbols using the
+ * code.  The basic idea is this: given the next 'max_codeword_len' bits
+ * in the input, we can look up the decoded symbol by indexing a table
+ * containing 2**max_codeword_len entries.  A codeword with length
+ * 'max_codeword_len' will have exactly one entry in this table, whereas
+ * a codeword shorter than 'max_codeword_len' will have multiple entries
+ * in this table.  Precisely, a codeword of length n will be represented
+ * by 2**(max_codeword_len - n) entries in this table.  The 0-based index
+ * of each such entry will contain the corresponding codeword as a prefix
+ * when zero-padded on the left to 'max_codeword_len' binary digits.
+ *
+ * That's the basic idea, but we implement two optimizations regarding
+ * the format of the decode table itself:
+ *
+ * - For many compression formats, the maximum codeword length is too
+ *   long for it to be efficient to build the full decoding table
+ *   whenever a new prefix code is used.  Instead, we can build the table
+ *   using only 2**table_bits entries, where 'table_bits' is some number
+ *   less than or equal to 'max_codeword_len'.  Then, only codewords of
+ *   length 'table_bits' and shorter can be directly looked up.  For
+ *   longer codewords, the direct lookup instead produces the root of a
+ *   binary tree.  Using this tree, the decoder can do traditional
+ *   bit-by-bit decoding of the remainder of the codeword.  Child nodes
+ *   are allocated in extra entries at the end of the table; leaf nodes
+ *   contain symbols.  Note that the long-codeword case is, in general,
+ *   not performance critical, since in Huffman codes the most frequently
+ *   used symbols are assigned the shortest codeword lengths.
+ *
+ * - When we decode a symbol using a direct lookup of the table, we still
+ *   need to know its length so that the bitstream can be advanced by the
+ *   appropriate number of bits.  The simple solution is to simply retain
+ *   the 'lens' array and use the decoded symbol as an index into it.
+ *   However, this requires two separate array accesses in the fast path.
+ *   The optimization is to store the length directly in the decode
+ *   table.  We use the bottom 11 bits for the symbol and the top 5 bits
+ *   for the length.  In addition, to combine this optimization with the
+ *   previous one, we introduce a special case where the top 2 bits of
+ *   the length are both set if the entry is actually the root of a
+ *   binary tree.
+ *
+ * @decode_table:
+ *	The array in which to create the decoding table.  This must have
+ *	a length of at least ((2**table_bits) + 2 * num_syms) entries.
+ *
+ * @num_syms:
+ *	The number of symbols in the alphabet; also, the length of the
+ *	'lens' array.  Must be less than or equal to 2048.
+ *
+ * @table_bits:
+ *	The order of the decode table size, as explained above.  Must be
+ *	less than or equal to 13.
+ *
+ * @lens:
+ *	An array of length @num_syms, indexable by symbol, that gives the
+ *	length of the codeword, in bits, for that symbol.  The length can
+ *	be 0, which means that the symbol does not have a codeword
+ *	assigned.
+ *
+ * @max_codeword_len:
+ *	The longest codeword length allowed in the compression format.
+ *	All entries in 'lens' must be less than or equal to this value.
+ *	This must be less than or equal to 23.
+ *
+ * @working_space
+ *	A temporary array of length '2 * (max_codeword_len + 1) +
+ *	num_syms'.
+ *
+ * Returns 0 on success, or -1 if the lengths do not form a valid prefix
+ * code.
+ */
+int make_huffman_decode_table(u16 decode_table[], const u32 num_syms,
+			      const u32 table_bits, const u8 lens[],
+			      const u32 max_codeword_len,
+			      u16 working_space[])
+{
+	const u32 table_num_entries = 1 << table_bits;
+	u16 * const len_counts = &working_space[0];
+	u16 * const offsets = &working_space[1 * (max_codeword_len + 1)];
+	u16 * const sorted_syms = &working_space[2 * (max_codeword_len + 1)];
+	int left;
+	void *decode_table_ptr;
+	u32 sym_idx;
+	u32 codeword_len;
+	u32 stores_per_loop;
+	u32 decode_table_pos;
+	u32 len;
+	u32 sym;
+
+	/* Count how many symbols have each possible codeword length.
+	 * Note that a length of 0 indicates the corresponding symbol is not
+	 * used in the code and therefore does not have a codeword.
+	 */
+	for (len = 0; len <= max_codeword_len; len++)
+		len_counts[len] = 0;
+	for (sym = 0; sym < num_syms; sym++)
+		len_counts[lens[sym]]++;
+
+	/* We can assume all lengths are <= max_codeword_len, but we
+	 * cannot assume they form a valid prefix code.  A codeword of
+	 * length n should require a proportion of the codespace equaling
+	 * (1/2)^n.  The code is valid if and only if the codespace is
+	 * exactly filled by the lengths, by this measure.
+	 */
+	left = 1;
+	for (len = 1; len <= max_codeword_len; len++) {
+		left <<= 1;
+		left -= len_counts[len];
+		if (left < 0) {
+			/* The lengths overflow the codespace; that is, the code
+			 * is over-subscribed.
+			 */
+			return -1;
+		}
+	}
+
+	if (left) {
+		/* The lengths do not fill the codespace; that is, they form an
+		 * incomplete set.
+		 */
+		if (left == (1 << max_codeword_len)) {
+			/* The code is completely empty.  This is arguably
+			 * invalid, but in fact it is valid in LZX and XPRESS,
+			 * so we must allow it.  By definition, no symbols can
+			 * be decoded with an empty code.  Consequently, we
+			 * technically don't even need to fill in the decode
+			 * table.  However, to avoid accessing uninitialized
+			 * memory if the algorithm nevertheless attempts to
+			 * decode symbols using such a code, we zero out the
+			 * decode table.
+			 */
+			memset(decode_table, 0,
+			       table_num_entries * sizeof(decode_table[0]));
+			return 0;
+		}
+		return -1;
+	}
+
+	/* Sort the symbols primarily by length and secondarily by symbol order.
+	 */
+
+	/* Initialize 'offsets' so that offsets[len] for 1 <= len <=
+	 * max_codeword_len is the number of codewords shorter than 'len' bits.
+	 */
+	offsets[1] = 0;
+	for (len = 1; len < max_codeword_len; len++)
+		offsets[len + 1] = offsets[len] + len_counts[len];
+
+	/* Use the 'offsets' array to sort the symbols.  Note that we do not
+	 * include symbols that are not used in the code.  Consequently, fewer
+	 * than 'num_syms' entries in 'sorted_syms' may be filled.
+	 */
+	for (sym = 0; sym < num_syms; sym++)
+		if (lens[sym])
+			sorted_syms[offsets[lens[sym]]++] = sym;
+
+	/* Fill entries for codewords with length <= table_bits
+	 * --- that is, those short enough for a direct mapping.
+	 *
+	 * The table will start with entries for the shortest codeword(s), which
+	 * have the most entries.  From there, the number of entries per
+	 * codeword will decrease.
+	 */
+	decode_table_ptr = decode_table;
+	sym_idx = 0;
+	codeword_len = 1;
+	stores_per_loop = (1 << (table_bits - codeword_len));
+	for (; stores_per_loop != 0; codeword_len++, stores_per_loop >>= 1) {
+		u32 end_sym_idx = sym_idx + len_counts[codeword_len];
+
+		for (; sym_idx < end_sym_idx; sym_idx++) {
+			u16 entry;
+			u16 *p;
+			u32 n;
+
+			entry = ((u32)codeword_len << 11) | sorted_syms[sym_idx];
+			p = (u16 *)decode_table_ptr;
+			n = stores_per_loop;
+
+			do {
+				*p++ = entry;
+			} while (--n);
+
+			decode_table_ptr = p;
+		}
+	}
+
+	/* If we've filled in the entire table, we are done.  Otherwise,
+	 * there are codewords longer than table_bits for which we must
+	 * generate binary trees.
+	 */
+	decode_table_pos = (u16 *)decode_table_ptr - decode_table;
+	if (decode_table_pos != table_num_entries) {
+		u32 j;
+		u32 next_free_tree_slot;
+		u32 cur_codeword;
+
+		/* First, zero out the remaining entries.  This is
+		 * necessary so that these entries appear as
+		 * "unallocated" in the next part.  Each of these entries
+		 * will eventually be filled with the representation of
+		 * the root node of a binary tree.
+		 */
+		j = decode_table_pos;
+		do {
+			decode_table[j] = 0;
+		} while (++j != table_num_entries);
+
+		/* We allocate child nodes starting at the end of the
+		 * direct lookup table.  Note that there should be
+		 * 2*num_syms extra entries for this purpose, although
+		 * fewer than this may actually be needed.
+		 */
+		next_free_tree_slot = table_num_entries;
+
+		/* Iterate through each codeword with length greater than
+		 * 'table_bits', primarily in order of codeword length
+		 * and secondarily in order of symbol.
+		 */
+		for (cur_codeword = decode_table_pos << 1;
+		     codeword_len <= max_codeword_len;
+		     codeword_len++, cur_codeword <<= 1) {
+			u32 end_sym_idx = sym_idx + len_counts[codeword_len];
+
+			for (; sym_idx < end_sym_idx; sym_idx++, cur_codeword++) {
+				/* 'sorted_sym' is the symbol represented by the
+				 * codeword.
+				 */
+				u32 sorted_sym = sorted_syms[sym_idx];
+				u32 extra_bits = codeword_len - table_bits;
+				u32 node_idx = cur_codeword >> extra_bits;
+
+				/* Go through each bit of the current codeword
+				 * beyond the prefix of length @table_bits and
+				 * walk the appropriate binary tree, allocating
+				 * any slots that have not yet been allocated.
+				 *
+				 * Note that the 'pointer' entry to the binary
+				 * tree, which is stored in the direct lookup
+				 * portion of the table, is represented
+				 * identically to other internal (non-leaf)
+				 * nodes of the binary tree; it can be thought
+				 * of as simply the root of the tree.  The
+				 * representation of these internal nodes is
+				 * simply the index of the left child combined
+				 * with the special bits 0xC000 to distingush
+				 * the entry from direct mapping and leaf node
+				 * entries.
+				 */
+				do {
+					/* At least one bit remains in the
+					 * codeword, but the current node is an
+					 * unallocated leaf.  Change it to an
+					 * internal node.
+					 */
+					if (decode_table[node_idx] == 0) {
+						decode_table[node_idx] =
+							next_free_tree_slot | 0xC000;
+						decode_table[next_free_tree_slot++] = 0;
+						decode_table[next_free_tree_slot++] = 0;
+					}
+
+					/* Go to the left child if the next bit
+					 * in the codeword is 0; otherwise go to
+					 * the right child.
+					 */
+					node_idx = decode_table[node_idx] & 0x3FFF;
+					--extra_bits;
+					node_idx += (cur_codeword >> extra_bits) & 1;
+				} while (extra_bits != 0);
+
+				/* We've traversed the tree using the entire
+				 * codeword, and we're now at the entry where
+				 * the actual symbol will be stored.  This is
+				 * distinguished from internal nodes by not
+				 * having its high two bits set.
+				 */
+				decode_table[node_idx] = sorted_sym;
+			}
+		}
+	}
+	return 0;
+}
diff --git a/fs/ntfs3/lib/decompress_common.h b/fs/ntfs3/lib/decompress_common.h
new file mode 100644
index 000000000..66297f398
--- /dev/null
+++ b/fs/ntfs3/lib/decompress_common.h
@@ -0,0 +1,352 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+/*
+ * decompress_common.h - Code shared by the XPRESS and LZX decompressors
+ *
+ * Copyright (C) 2015 Eric Biggers
+ *
+ * This program is free software: you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License as published by the Free Software
+ * Foundation, either version 2 of the License, or (at your option) any later
+ * version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/string.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/unaligned.h>
+
+
+/* "Force inline" macro (not required, but helpful for performance)  */
+#define forceinline __always_inline
+
+/* Enable whole-word match copying on selected architectures  */
+#if defined(__i386__) || defined(__x86_64__) || defined(__ARM_FEATURE_UNALIGNED)
+#  define FAST_UNALIGNED_ACCESS
+#endif
+
+/* Size of a machine word  */
+#define WORDBYTES (sizeof(size_t))
+
+static forceinline void
+copy_unaligned_word(const void *src, void *dst)
+{
+	put_unaligned(get_unaligned((const size_t *)src), (size_t *)dst);
+}
+
+
+/* Generate a "word" with platform-dependent size whose bytes all contain the
+ * value 'b'.
+ */
+static forceinline size_t repeat_byte(u8 b)
+{
+	size_t v;
+
+	v = b;
+	v |= v << 8;
+	v |= v << 16;
+	v |= v << ((WORDBYTES == 8) ? 32 : 0);
+	return v;
+}
+
+/* Structure that encapsulates a block of in-memory data being interpreted as a
+ * stream of bits, optionally with interwoven literal bytes.  Bits are assumed
+ * to be stored in little endian 16-bit coding units, with the bits ordered high
+ * to low.
+ */
+struct input_bitstream {
+
+	/* Bits that have been read from the input buffer.  The bits are
+	 * left-justified; the next bit is always bit 31.
+	 */
+	u32 bitbuf;
+
+	/* Number of bits currently held in @bitbuf.  */
+	u32 bitsleft;
+
+	/* Pointer to the next byte to be retrieved from the input buffer.  */
+	const u8 *next;
+
+	/* Pointer to just past the end of the input buffer.  */
+	const u8 *end;
+};
+
+/* Initialize a bitstream to read from the specified input buffer.  */
+static forceinline void init_input_bitstream(struct input_bitstream *is,
+					     const void *buffer, u32 size)
+{
+	is->bitbuf = 0;
+	is->bitsleft = 0;
+	is->next = buffer;
+	is->end = is->next + size;
+}
+
+/* Ensure the bit buffer variable for the bitstream contains at least @num_bits
+ * bits.  Following this, bitstream_peek_bits() and/or bitstream_remove_bits()
+ * may be called on the bitstream to peek or remove up to @num_bits bits.  Note
+ * that @num_bits must be <= 16.
+ */
+static forceinline void bitstream_ensure_bits(struct input_bitstream *is,
+					      u32 num_bits)
+{
+	if (is->bitsleft < num_bits) {
+		if (is->end - is->next >= 2) {
+			is->bitbuf |= (u32)get_unaligned_le16(is->next)
+					<< (16 - is->bitsleft);
+			is->next += 2;
+		}
+		is->bitsleft += 16;
+	}
+}
+
+/* Return the next @num_bits bits from the bitstream, without removing them.
+ * There must be at least @num_bits remaining in the buffer variable, from a
+ * previous call to bitstream_ensure_bits().
+ */
+static forceinline u32
+bitstream_peek_bits(const struct input_bitstream *is, const u32 num_bits)
+{
+	return (is->bitbuf >> 1) >> (sizeof(is->bitbuf) * 8 - num_bits - 1);
+}
+
+/* Remove @num_bits from the bitstream.  There must be at least @num_bits
+ * remaining in the buffer variable, from a previous call to
+ * bitstream_ensure_bits().
+ */
+static forceinline void
+bitstream_remove_bits(struct input_bitstream *is, u32 num_bits)
+{
+	is->bitbuf <<= num_bits;
+	is->bitsleft -= num_bits;
+}
+
+/* Remove and return @num_bits bits from the bitstream.  There must be at least
+ * @num_bits remaining in the buffer variable, from a previous call to
+ * bitstream_ensure_bits().
+ */
+static forceinline u32
+bitstream_pop_bits(struct input_bitstream *is, u32 num_bits)
+{
+	u32 bits = bitstream_peek_bits(is, num_bits);
+
+	bitstream_remove_bits(is, num_bits);
+	return bits;
+}
+
+/* Read and return the next @num_bits bits from the bitstream.  */
+static forceinline u32
+bitstream_read_bits(struct input_bitstream *is, u32 num_bits)
+{
+	bitstream_ensure_bits(is, num_bits);
+	return bitstream_pop_bits(is, num_bits);
+}
+
+/* Read and return the next literal byte embedded in the bitstream.  */
+static forceinline u8
+bitstream_read_byte(struct input_bitstream *is)
+{
+	if (unlikely(is->end == is->next))
+		return 0;
+	return *is->next++;
+}
+
+/* Read and return the next 16-bit integer embedded in the bitstream.  */
+static forceinline u16
+bitstream_read_u16(struct input_bitstream *is)
+{
+	u16 v;
+
+	if (unlikely(is->end - is->next < 2))
+		return 0;
+	v = get_unaligned_le16(is->next);
+	is->next += 2;
+	return v;
+}
+
+/* Read and return the next 32-bit integer embedded in the bitstream.  */
+static forceinline u32
+bitstream_read_u32(struct input_bitstream *is)
+{
+	u32 v;
+
+	if (unlikely(is->end - is->next < 4))
+		return 0;
+	v = get_unaligned_le32(is->next);
+	is->next += 4;
+	return v;
+}
+
+/* Read into @dst_buffer an array of literal bytes embedded in the bitstream.
+ * Return either a pointer to the byte past the last written, or NULL if the
+ * read overflows the input buffer.
+ */
+static forceinline void *bitstream_read_bytes(struct input_bitstream *is,
+					      void *dst_buffer, size_t count)
+{
+	if ((size_t)(is->end - is->next) < count)
+		return NULL;
+	memcpy(dst_buffer, is->next, count);
+	is->next += count;
+	return (u8 *)dst_buffer + count;
+}
+
+/* Align the input bitstream on a coding-unit boundary.  */
+static forceinline void bitstream_align(struct input_bitstream *is)
+{
+	is->bitsleft = 0;
+	is->bitbuf = 0;
+}
+
+extern int make_huffman_decode_table(u16 decode_table[], const u32 num_syms,
+				     const u32 num_bits, const u8 lens[],
+				     const u32 max_codeword_len,
+				     u16 working_space[]);
+
+
+/* Reads and returns the next Huffman-encoded symbol from a bitstream.  If the
+ * input data is exhausted, the Huffman symbol is decoded as if the missing bits
+ * are all zeroes.
+ */
+static forceinline u32 read_huffsym(struct input_bitstream *istream,
+					 const u16 decode_table[],
+					 u32 table_bits,
+					 u32 max_codeword_len)
+{
+	u32 entry;
+	u32 key_bits;
+
+	bitstream_ensure_bits(istream, max_codeword_len);
+
+	/* Index the decode table by the next table_bits bits of the input.  */
+	key_bits = bitstream_peek_bits(istream, table_bits);
+	entry = decode_table[key_bits];
+	if (entry < 0xC000) {
+		/* Fast case: The decode table directly provided the
+		 * symbol and codeword length.  The low 11 bits are the
+		 * symbol, and the high 5 bits are the codeword length.
+		 */
+		bitstream_remove_bits(istream, entry >> 11);
+		return entry & 0x7FF;
+	}
+	/* Slow case: The codeword for the symbol is longer than
+	 * table_bits, so the symbol does not have an entry
+	 * directly in the first (1 << table_bits) entries of the
+	 * decode table.  Traverse the appropriate binary tree
+	 * bit-by-bit to decode the symbol.
+	 */
+	bitstream_remove_bits(istream, table_bits);
+	do {
+		key_bits = (entry & 0x3FFF) + bitstream_pop_bits(istream, 1);
+	} while ((entry = decode_table[key_bits]) >= 0xC000);
+	return entry;
+}
+
+/*
+ * Copy an LZ77 match at (dst - offset) to dst.
+ *
+ * The length and offset must be already validated --- that is, (dst - offset)
+ * can't underrun the output buffer, and (dst + length) can't overrun the output
+ * buffer.  Also, the length cannot be 0.
+ *
+ * @bufend points to the byte past the end of the output buffer.  This function
+ * won't write any data beyond this position.
+ *
+ * Returns dst + length.
+ */
+static forceinline u8 *lz_copy(u8 *dst, u32 length, u32 offset, const u8 *bufend,
+			       u32 min_length)
+{
+	const u8 *src = dst - offset;
+
+	/*
+	 * Try to copy one machine word at a time.  On i386 and x86_64 this is
+	 * faster than copying one byte at a time, unless the data is
+	 * near-random and all the matches have very short lengths.  Note that
+	 * since this requires unaligned memory accesses, it won't necessarily
+	 * be faster on every architecture.
+	 *
+	 * Also note that we might copy more than the length of the match.  For
+	 * example, if a word is 8 bytes and the match is of length 5, then
+	 * we'll simply copy 8 bytes.  This is okay as long as we don't write
+	 * beyond the end of the output buffer, hence the check for (bufend -
+	 * end >= WORDBYTES - 1).
+	 */
+#ifdef FAST_UNALIGNED_ACCESS
+	u8 * const end = dst + length;
+
+	if (bufend - end >= (ptrdiff_t)(WORDBYTES - 1)) {
+
+		if (offset >= WORDBYTES) {
+			/* The source and destination words don't overlap.  */
+
+			/* To improve branch prediction, one iteration of this
+			 * loop is unrolled.  Most matches are short and will
+			 * fail the first check.  But if that check passes, then
+			 * it becomes increasing likely that the match is long
+			 * and we'll need to continue copying.
+			 */
+
+			copy_unaligned_word(src, dst);
+			src += WORDBYTES;
+			dst += WORDBYTES;
+
+			if (dst < end) {
+				do {
+					copy_unaligned_word(src, dst);
+					src += WORDBYTES;
+					dst += WORDBYTES;
+				} while (dst < end);
+			}
+			return end;
+		} else if (offset == 1) {
+
+			/* Offset 1 matches are equivalent to run-length
+			 * encoding of the previous byte.  This case is common
+			 * if the data contains many repeated bytes.
+			 */
+			size_t v = repeat_byte(*(dst - 1));
+
+			do {
+				put_unaligned(v, (size_t *)dst);
+				src += WORDBYTES;
+				dst += WORDBYTES;
+			} while (dst < end);
+			return end;
+		}
+		/*
+		 * We don't bother with special cases for other 'offset <
+		 * WORDBYTES', which are usually rarer than 'offset == 1'.  Extra
+		 * checks will just slow things down.  Actually, it's possible
+		 * to handle all the 'offset < WORDBYTES' cases using the same
+		 * code, but it still becomes more complicated doesn't seem any
+		 * faster overall; it definitely slows down the more common
+		 * 'offset == 1' case.
+		 */
+	}
+#endif /* FAST_UNALIGNED_ACCESS */
+
+	/* Fall back to a bytewise copy.  */
+
+	if (min_length >= 2) {
+		*dst++ = *src++;
+		length--;
+	}
+	if (min_length >= 3) {
+		*dst++ = *src++;
+		length--;
+	}
+	do {
+		*dst++ = *src++;
+	} while (--length);
+
+	return dst;
+}
diff --git a/fs/ntfs3/lib/lib.h b/fs/ntfs3/lib/lib.h
new file mode 100644
index 000000000..f508fbad2
--- /dev/null
+++ b/fs/ntfs3/lib/lib.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Adapted for linux kernel by Alexander Mamaev:
+ * - remove implementations of get_unaligned_
+ * - assume GCC is always defined
+ * - ISO C90
+ * - linux kernel code style
+ */
+
+
+/* globals from xpress_decompress.c */
+struct xpress_decompressor *xpress_allocate_decompressor(void);
+void xpress_free_decompressor(struct xpress_decompressor *d);
+int xpress_decompress(struct xpress_decompressor *__restrict d,
+		      const void *__restrict compressed_data,
+		      size_t compressed_size,
+		      void *__restrict uncompressed_data,
+		      size_t uncompressed_size);
+
+/* globals from lzx_decompress.c */
+struct lzx_decompressor *lzx_allocate_decompressor(void);
+void lzx_free_decompressor(struct lzx_decompressor *d);
+int lzx_decompress(struct lzx_decompressor *__restrict d,
+		   const void *__restrict compressed_data,
+		   size_t compressed_size, void *__restrict uncompressed_data,
+		   size_t uncompressed_size);
diff --git a/fs/ntfs3/lib/lzx_decompress.c b/fs/ntfs3/lib/lzx_decompress.c
new file mode 100644
index 000000000..77a381a69
--- /dev/null
+++ b/fs/ntfs3/lib/lzx_decompress.c
@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * lzx_decompress.c - A decompressor for the LZX compression format, which can
+ * be used in "System Compressed" files.  This is based on the code from wimlib.
+ * This code only supports a window size (dictionary size) of 32768 bytes, since
+ * this is the only size used in System Compression.
+ *
+ * Copyright (C) 2015 Eric Biggers
+ *
+ * This program is free software: you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License as published by the Free Software
+ * Foundation, either version 2 of the License, or (at your option) any later
+ * version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "decompress_common.h"
+#include "lib.h"
+
+/* Number of literal byte values  */
+#define LZX_NUM_CHARS			256
+
+/* The smallest and largest allowed match lengths  */
+#define LZX_MIN_MATCH_LEN		2
+#define LZX_MAX_MATCH_LEN		257
+
+/* Number of distinct match lengths that can be represented  */
+#define LZX_NUM_LENS			(LZX_MAX_MATCH_LEN - LZX_MIN_MATCH_LEN + 1)
+
+/* Number of match lengths for which no length symbol is required  */
+#define LZX_NUM_PRIMARY_LENS		7
+#define LZX_NUM_LEN_HEADERS		(LZX_NUM_PRIMARY_LENS + 1)
+
+/* Valid values of the 3-bit block type field  */
+#define LZX_BLOCKTYPE_VERBATIM		1
+#define LZX_BLOCKTYPE_ALIGNED		2
+#define LZX_BLOCKTYPE_UNCOMPRESSED	3
+
+/* Number of offset slots for a window size of 32768  */
+#define LZX_NUM_OFFSET_SLOTS		30
+
+/* Number of symbols in the main code for a window size of 32768  */
+#define LZX_MAINCODE_NUM_SYMBOLS	\
+	(LZX_NUM_CHARS + (LZX_NUM_OFFSET_SLOTS * LZX_NUM_LEN_HEADERS))
+
+/* Number of symbols in the length code  */
+#define LZX_LENCODE_NUM_SYMBOLS		(LZX_NUM_LENS - LZX_NUM_PRIMARY_LENS)
+
+/* Number of symbols in the precode  */
+#define LZX_PRECODE_NUM_SYMBOLS		20
+
+/* Number of bits in which each precode codeword length is represented  */
+#define LZX_PRECODE_ELEMENT_SIZE	4
+
+/* Number of low-order bits of each match offset that are entropy-encoded in
+ * aligned offset blocks
+ */
+#define LZX_NUM_ALIGNED_OFFSET_BITS	3
+
+/* Number of symbols in the aligned offset code  */
+#define LZX_ALIGNEDCODE_NUM_SYMBOLS	(1 << LZX_NUM_ALIGNED_OFFSET_BITS)
+
+/* Mask for the match offset bits that are entropy-encoded in aligned offset
+ * blocks
+ */
+#define LZX_ALIGNED_OFFSET_BITMASK	((1 << LZX_NUM_ALIGNED_OFFSET_BITS) - 1)
+
+/* Number of bits in which each aligned offset codeword length is represented  */
+#define LZX_ALIGNEDCODE_ELEMENT_SIZE	3
+
+/* Maximum lengths (in bits) of the codewords in each Huffman code  */
+#define LZX_MAX_MAIN_CODEWORD_LEN	16
+#define LZX_MAX_LEN_CODEWORD_LEN	16
+#define LZX_MAX_PRE_CODEWORD_LEN	((1 << LZX_PRECODE_ELEMENT_SIZE) - 1)
+#define LZX_MAX_ALIGNED_CODEWORD_LEN	((1 << LZX_ALIGNEDCODE_ELEMENT_SIZE) - 1)
+
+/* The default "filesize" value used in pre/post-processing.  In the LZX format
+ * used in cabinet files this value must be given to the decompressor, whereas
+ * in the LZX format used in WIM files and system-compressed files this value is
+ * fixed at 12000000.
+ */
+#define LZX_DEFAULT_FILESIZE		12000000
+
+/* Assumed block size when the encoded block size begins with a 0 bit.  */
+#define LZX_DEFAULT_BLOCK_SIZE		32768
+
+/* Number of offsets in the recent (or "repeat") offsets queue.  */
+#define LZX_NUM_RECENT_OFFSETS		3
+
+/* These values are chosen for fast decompression.  */
+#define LZX_MAINCODE_TABLEBITS		11
+#define LZX_LENCODE_TABLEBITS		10
+#define LZX_PRECODE_TABLEBITS		6
+#define LZX_ALIGNEDCODE_TABLEBITS	7
+
+#define LZX_READ_LENS_MAX_OVERRUN	50
+
+/* Mapping: offset slot => first match offset that uses that offset slot.
+ */
+static const u32 lzx_offset_slot_base[LZX_NUM_OFFSET_SLOTS + 1] = {
+	0,	1,	2,	3,	4,	/* 0  --- 4  */
+	6,	8,	12,	16,	24,	/* 5  --- 9  */
+	32,	48,	64,	96,	128,	/* 10 --- 14 */
+	192,	256,	384,	512,	768,	/* 15 --- 19 */
+	1024,	1536,	2048,	3072,	4096,   /* 20 --- 24 */
+	6144,	8192,	12288,	16384,	24576,	/* 25 --- 29 */
+	32768,					/* extra     */
+};
+
+/* Mapping: offset slot => how many extra bits must be read and added to the
+ * corresponding offset slot base to decode the match offset.
+ */
+static const u8 lzx_extra_offset_bits[LZX_NUM_OFFSET_SLOTS] = {
+	0,	0,	0,	0,	1,
+	1,	2,	2,	3,	3,
+	4,	4,	5,	5,	6,
+	6,	7,	7,	8,	8,
+	9,	9,	10,	10,	11,
+	11,	12,	12,	13,	13,
+};
+
+/* Reusable heap-allocated memory for LZX decompression  */
+struct lzx_decompressor {
+
+	/* Huffman decoding tables, and arrays that map symbols to codeword
+	 * lengths
+	 */
+
+	u16 maincode_decode_table[(1 << LZX_MAINCODE_TABLEBITS) +
+					(LZX_MAINCODE_NUM_SYMBOLS * 2)];
+	u8 maincode_lens[LZX_MAINCODE_NUM_SYMBOLS + LZX_READ_LENS_MAX_OVERRUN];
+
+
+	u16 lencode_decode_table[(1 << LZX_LENCODE_TABLEBITS) +
+					(LZX_LENCODE_NUM_SYMBOLS * 2)];
+	u8 lencode_lens[LZX_LENCODE_NUM_SYMBOLS + LZX_READ_LENS_MAX_OVERRUN];
+
+
+	u16 alignedcode_decode_table[(1 << LZX_ALIGNEDCODE_TABLEBITS) +
+					(LZX_ALIGNEDCODE_NUM_SYMBOLS * 2)];
+	u8 alignedcode_lens[LZX_ALIGNEDCODE_NUM_SYMBOLS];
+
+	u16 precode_decode_table[(1 << LZX_PRECODE_TABLEBITS) +
+				 (LZX_PRECODE_NUM_SYMBOLS * 2)];
+	u8 precode_lens[LZX_PRECODE_NUM_SYMBOLS];
+
+	/* Temporary space for make_huffman_decode_table()  */
+	u16 working_space[2 * (1 + LZX_MAX_MAIN_CODEWORD_LEN) +
+			  LZX_MAINCODE_NUM_SYMBOLS];
+};
+
+static void undo_e8_translation(void *target, s32 input_pos)
+{
+	s32 abs_offset, rel_offset;
+
+	abs_offset = get_unaligned_le32(target);
+	if (abs_offset >= 0) {
+		if (abs_offset < LZX_DEFAULT_FILESIZE) {
+			/* "good translation" */
+			rel_offset = abs_offset - input_pos;
+			put_unaligned_le32(rel_offset, target);
+		}
+	} else {
+		if (abs_offset >= -input_pos) {
+			/* "compensating translation" */
+			rel_offset = abs_offset + LZX_DEFAULT_FILESIZE;
+			put_unaligned_le32(rel_offset, target);
+		}
+	}
+}
+
+/*
+ * Undo the 'E8' preprocessing used in LZX.  Before compression, the
+ * uncompressed data was preprocessed by changing the targets of suspected x86
+ * CALL instructions from relative offsets to absolute offsets.  After
+ * match/literal decoding, the decompressor must undo the translation.
+ */
+static void lzx_postprocess(u8 *data, u32 size)
+{
+	/*
+	 * A worthwhile optimization is to push the end-of-buffer check into the
+	 * relatively rare E8 case.  This is possible if we replace the last six
+	 * bytes of data with E8 bytes; then we are guaranteed to hit an E8 byte
+	 * before reaching end-of-buffer.  In addition, this scheme guarantees
+	 * that no translation can begin following an E8 byte in the last 10
+	 * bytes because a 4-byte offset containing E8 as its high byte is a
+	 * large negative number that is not valid for translation.  That is
+	 * exactly what we need.
+	 */
+	u8 *tail;
+	u8 saved_bytes[6];
+	u8 *p;
+
+	if (size <= 10)
+		return;
+
+	tail = &data[size - 6];
+	memcpy(saved_bytes, tail, 6);
+	memset(tail, 0xE8, 6);
+	p = data;
+	for (;;) {
+		while (*p != 0xE8)
+			p++;
+		if (p >= tail)
+			break;
+		undo_e8_translation(p + 1, p - data);
+		p += 5;
+	}
+	memcpy(tail, saved_bytes, 6);
+}
+
+/* Read a Huffman-encoded symbol using the precode.  */
+static forceinline u32 read_presym(const struct lzx_decompressor *d,
+					struct input_bitstream *is)
+{
+	return read_huffsym(is, d->precode_decode_table,
+			    LZX_PRECODE_TABLEBITS, LZX_MAX_PRE_CODEWORD_LEN);
+}
+
+/* Read a Huffman-encoded symbol using the main code.  */
+static forceinline u32 read_mainsym(const struct lzx_decompressor *d,
+					 struct input_bitstream *is)
+{
+	return read_huffsym(is, d->maincode_decode_table,
+			    LZX_MAINCODE_TABLEBITS, LZX_MAX_MAIN_CODEWORD_LEN);
+}
+
+/* Read a Huffman-encoded symbol using the length code.  */
+static forceinline u32 read_lensym(const struct lzx_decompressor *d,
+					struct input_bitstream *is)
+{
+	return read_huffsym(is, d->lencode_decode_table,
+			    LZX_LENCODE_TABLEBITS, LZX_MAX_LEN_CODEWORD_LEN);
+}
+
+/* Read a Huffman-encoded symbol using the aligned offset code.  */
+static forceinline u32 read_alignedsym(const struct lzx_decompressor *d,
+					    struct input_bitstream *is)
+{
+	return read_huffsym(is, d->alignedcode_decode_table,
+			    LZX_ALIGNEDCODE_TABLEBITS,
+			    LZX_MAX_ALIGNED_CODEWORD_LEN);
+}
+
+/*
+ * Read the precode from the compressed input bitstream, then use it to decode
+ * @num_lens codeword length values.
+ *
+ * @is:		The input bitstream.
+ *
+ * @lens:	An array that contains the length values from the previous time
+ *		the codeword lengths for this Huffman code were read, or all 0's
+ *		if this is the first time.  This array must have at least
+ *		(@num_lens + LZX_READ_LENS_MAX_OVERRUN) entries.
+ *
+ * @num_lens:	Number of length values to decode.
+ *
+ * Returns 0 on success, or -1 if the data was invalid.
+ */
+static int lzx_read_codeword_lens(struct lzx_decompressor *d,
+				  struct input_bitstream *is,
+				  u8 *lens, u32 num_lens)
+{
+	u8 *len_ptr = lens;
+	u8 *lens_end = lens + num_lens;
+	int i;
+
+	/* Read the lengths of the precode codewords.  These are given
+	 * explicitly.
+	 */
+	for (i = 0; i < LZX_PRECODE_NUM_SYMBOLS; i++) {
+		d->precode_lens[i] =
+			bitstream_read_bits(is, LZX_PRECODE_ELEMENT_SIZE);
+	}
+
+	/* Make the decoding table for the precode.  */
+	if (make_huffman_decode_table(d->precode_decode_table,
+				      LZX_PRECODE_NUM_SYMBOLS,
+				      LZX_PRECODE_TABLEBITS,
+				      d->precode_lens,
+				      LZX_MAX_PRE_CODEWORD_LEN,
+				      d->working_space))
+		return -1;
+
+	/* Decode the codeword lengths.  */
+	do {
+		u32 presym;
+		u8 len;
+
+		/* Read the next precode symbol.  */
+		presym = read_presym(d, is);
+		if (presym < 17) {
+			/* Difference from old length  */
+			len = *len_ptr - presym;
+			if ((s8)len < 0)
+				len += 17;
+			*len_ptr++ = len;
+		} else {
+			/* Special RLE values  */
+
+			u32 run_len;
+
+			if (presym == 17) {
+				/* Run of 0's  */
+				run_len = 4 + bitstream_read_bits(is, 4);
+				len = 0;
+			} else if (presym == 18) {
+				/* Longer run of 0's  */
+				run_len = 20 + bitstream_read_bits(is, 5);
+				len = 0;
+			} else {
+				/* Run of identical lengths  */
+				run_len = 4 + bitstream_read_bits(is, 1);
+				presym = read_presym(d, is);
+				if (presym > 17)
+					return -1;
+				len = *len_ptr - presym;
+				if ((s8)len < 0)
+					len += 17;
+			}
+
+			do {
+				*len_ptr++ = len;
+			} while (--run_len);
+			/* Worst case overrun is when presym == 18,
+			 * run_len == 20 + 31, and only 1 length was remaining.
+			 * So LZX_READ_LENS_MAX_OVERRUN == 50.
+			 *
+			 * Overrun while reading the first half of maincode_lens
+			 * can corrupt the previous values in the second half.
+			 * This doesn't really matter because the resulting
+			 * lengths will still be in range, and data that
+			 * generates overruns is invalid anyway.
+			 */
+		}
+	} while (len_ptr < lens_end);
+
+	return 0;
+}
+
+/*
+ * Read the header of an LZX block and save the block type and (uncompressed)
+ * size in *block_type_ret and *block_size_ret, respectively.
+ *
+ * If the block is compressed, also update the Huffman decode @tables with the
+ * new Huffman codes.  If the block is uncompressed, also update the match
+ * offset @queue with the new match offsets.
+ *
+ * Return 0 on success, or -1 if the data was invalid.
+ */
+static int lzx_read_block_header(struct lzx_decompressor *d,
+				 struct input_bitstream *is,
+				 int *block_type_ret,
+				 u32 *block_size_ret,
+				 u32 recent_offsets[])
+{
+	int block_type;
+	u32 block_size;
+	int i;
+
+	bitstream_ensure_bits(is, 4);
+
+	/* The first three bits tell us what kind of block it is, and should be
+	 * one of the LZX_BLOCKTYPE_* values.
+	 */
+	block_type = bitstream_pop_bits(is, 3);
+
+	/* Read the block size.  */
+	if (bitstream_pop_bits(is, 1)) {
+		block_size = LZX_DEFAULT_BLOCK_SIZE;
+	} else {
+		block_size = 0;
+		block_size |= bitstream_read_bits(is, 8);
+		block_size <<= 8;
+		block_size |= bitstream_read_bits(is, 8);
+	}
+
+	switch (block_type) {
+
+	case LZX_BLOCKTYPE_ALIGNED:
+
+		/* Read the aligned offset code and prepare its decode table.
+		 */
+
+		for (i = 0; i < LZX_ALIGNEDCODE_NUM_SYMBOLS; i++) {
+			d->alignedcode_lens[i] =
+				bitstream_read_bits(is,
+						    LZX_ALIGNEDCODE_ELEMENT_SIZE);
+		}
+
+		if (make_huffman_decode_table(d->alignedcode_decode_table,
+					      LZX_ALIGNEDCODE_NUM_SYMBOLS,
+					      LZX_ALIGNEDCODE_TABLEBITS,
+					      d->alignedcode_lens,
+					      LZX_MAX_ALIGNED_CODEWORD_LEN,
+					      d->working_space))
+			return -1;
+
+		/* Fall though, since the rest of the header for aligned offset
+		 * blocks is the same as that for verbatim blocks.
+		 */
+		fallthrough;
+
+	case LZX_BLOCKTYPE_VERBATIM:
+
+		/* Read the main code and prepare its decode table.
+		 *
+		 * Note that the codeword lengths in the main code are encoded
+		 * in two parts: one part for literal symbols, and one part for
+		 * match symbols.
+		 */
+
+		if (lzx_read_codeword_lens(d, is, d->maincode_lens,
+					   LZX_NUM_CHARS))
+			return -1;
+
+		if (lzx_read_codeword_lens(d, is,
+					   d->maincode_lens + LZX_NUM_CHARS,
+					   LZX_MAINCODE_NUM_SYMBOLS - LZX_NUM_CHARS))
+			return -1;
+
+		if (make_huffman_decode_table(d->maincode_decode_table,
+					      LZX_MAINCODE_NUM_SYMBOLS,
+					      LZX_MAINCODE_TABLEBITS,
+					      d->maincode_lens,
+					      LZX_MAX_MAIN_CODEWORD_LEN,
+					      d->working_space))
+			return -1;
+
+		/* Read the length code and prepare its decode table.  */
+
+		if (lzx_read_codeword_lens(d, is, d->lencode_lens,
+					   LZX_LENCODE_NUM_SYMBOLS))
+			return -1;
+
+		if (make_huffman_decode_table(d->lencode_decode_table,
+					      LZX_LENCODE_NUM_SYMBOLS,
+					      LZX_LENCODE_TABLEBITS,
+					      d->lencode_lens,
+					      LZX_MAX_LEN_CODEWORD_LEN,
+					      d->working_space))
+			return -1;
+
+		break;
+
+	case LZX_BLOCKTYPE_UNCOMPRESSED:
+
+		/* Before reading the three recent offsets from the uncompressed
+		 * block header, the stream must be aligned on a 16-bit
+		 * boundary.  But if the stream is *already* aligned, then the
+		 * next 16 bits must be discarded.
+		 */
+		bitstream_ensure_bits(is, 1);
+		bitstream_align(is);
+
+		recent_offsets[0] = bitstream_read_u32(is);
+		recent_offsets[1] = bitstream_read_u32(is);
+		recent_offsets[2] = bitstream_read_u32(is);
+
+		/* Offsets of 0 are invalid.  */
+		if (recent_offsets[0] == 0 || recent_offsets[1] == 0 ||
+		    recent_offsets[2] == 0)
+			return -1;
+		break;
+
+	default:
+		/* Unrecognized block type.  */
+		return -1;
+	}
+
+	*block_type_ret = block_type;
+	*block_size_ret = block_size;
+	return 0;
+}
+
+/* Decompress a block of LZX-compressed data.  */
+static int lzx_decompress_block(const struct lzx_decompressor *d,
+				struct input_bitstream *is,
+				int block_type, u32 block_size,
+				u8 * const out_begin, u8 *out_next,
+				u32 recent_offsets[])
+{
+	u8 * const block_end = out_next + block_size;
+	u32 ones_if_aligned = 0U - (block_type == LZX_BLOCKTYPE_ALIGNED);
+
+	do {
+		u32 mainsym;
+		u32 match_len;
+		u32 match_offset;
+		u32 offset_slot;
+		u32 num_extra_bits;
+
+		mainsym = read_mainsym(d, is);
+		if (mainsym < LZX_NUM_CHARS) {
+			/* Literal  */
+			*out_next++ = mainsym;
+			continue;
+		}
+
+		/* Match  */
+
+		/* Decode the length header and offset slot.  */
+		mainsym -= LZX_NUM_CHARS;
+		match_len = mainsym % LZX_NUM_LEN_HEADERS;
+		offset_slot = mainsym / LZX_NUM_LEN_HEADERS;
+
+		/* If needed, read a length symbol to decode the full length. */
+		if (match_len == LZX_NUM_PRIMARY_LENS)
+			match_len += read_lensym(d, is);
+		match_len += LZX_MIN_MATCH_LEN;
+
+		if (offset_slot < LZX_NUM_RECENT_OFFSETS) {
+			/* Repeat offset  */
+
+			/* Note: This isn't a real LRU queue, since using the R2
+			 * offset doesn't bump the R1 offset down to R2.  This
+			 * quirk allows all 3 recent offsets to be handled by
+			 * the same code.  (For R0, the swap is a no-op.)
+			 */
+			match_offset = recent_offsets[offset_slot];
+			recent_offsets[offset_slot] = recent_offsets[0];
+			recent_offsets[0] = match_offset;
+		} else {
+			/* Explicit offset  */
+
+			/* Look up the number of extra bits that need to be read
+			 * to decode offsets with this offset slot.
+			 */
+			num_extra_bits = lzx_extra_offset_bits[offset_slot];
+
+			/* Start with the offset slot base value.  */
+			match_offset = lzx_offset_slot_base[offset_slot];
+
+			/* In aligned offset blocks, the low-order 3 bits of
+			 * each offset are encoded using the aligned offset
+			 * code.  Otherwise, all the extra bits are literal.
+			 */
+
+			if ((num_extra_bits & ones_if_aligned) >= LZX_NUM_ALIGNED_OFFSET_BITS) {
+				match_offset +=
+					bitstream_read_bits(is, num_extra_bits -
+								LZX_NUM_ALIGNED_OFFSET_BITS)
+							<< LZX_NUM_ALIGNED_OFFSET_BITS;
+				match_offset += read_alignedsym(d, is);
+			} else {
+				match_offset += bitstream_read_bits(is, num_extra_bits);
+			}
+
+			/* Adjust the offset.  */
+			match_offset -= (LZX_NUM_RECENT_OFFSETS - 1);
+
+			/* Update the recent offsets.  */
+			recent_offsets[2] = recent_offsets[1];
+			recent_offsets[1] = recent_offsets[0];
+			recent_offsets[0] = match_offset;
+		}
+
+		/* Validate the match, then copy it to the current position.  */
+
+		if (match_len > (size_t)(block_end - out_next))
+			return -1;
+
+		if (match_offset > (size_t)(out_next - out_begin))
+			return -1;
+
+		out_next = lz_copy(out_next, match_len, match_offset,
+				   block_end, LZX_MIN_MATCH_LEN);
+
+	} while (out_next != block_end);
+
+	return 0;
+}
+
+/*
+ * lzx_allocate_decompressor - Allocate an LZX decompressor
+ *
+ * Return the pointer to the decompressor on success, or return NULL and set
+ * errno on failure.
+ */
+struct lzx_decompressor *lzx_allocate_decompressor(void)
+{
+	return kmalloc(sizeof(struct lzx_decompressor), GFP_NOFS);
+}
+
+/*
+ * lzx_decompress - Decompress a buffer of LZX-compressed data
+ *
+ * @decompressor:      A decompressor allocated with lzx_allocate_decompressor()
+ * @compressed_data:	The buffer of data to decompress
+ * @compressed_size:	Number of bytes of compressed data
+ * @uncompressed_data:	The buffer in which to store the decompressed data
+ * @uncompressed_size:	The number of bytes the data decompresses into
+ *
+ * Return 0 on success, or return -1 and set errno on failure.
+ */
+int lzx_decompress(struct lzx_decompressor *decompressor,
+		   const void *compressed_data, size_t compressed_size,
+		   void *uncompressed_data, size_t uncompressed_size)
+{
+	struct lzx_decompressor *d = decompressor;
+	u8 * const out_begin = uncompressed_data;
+	u8 *out_next = out_begin;
+	u8 * const out_end = out_begin + uncompressed_size;
+	struct input_bitstream is;
+	u32 recent_offsets[LZX_NUM_RECENT_OFFSETS] = {1, 1, 1};
+	int e8_status = 0;
+
+	init_input_bitstream(&is, compressed_data, compressed_size);
+
+	/* Codeword lengths begin as all 0's for delta encoding purposes.  */
+	memset(d->maincode_lens, 0, LZX_MAINCODE_NUM_SYMBOLS);
+	memset(d->lencode_lens, 0, LZX_LENCODE_NUM_SYMBOLS);
+
+	/* Decompress blocks until we have all the uncompressed data.  */
+
+	while (out_next != out_end) {
+		int block_type;
+		u32 block_size;
+
+		if (lzx_read_block_header(d, &is, &block_type, &block_size,
+					  recent_offsets))
+			goto invalid;
+
+		if (block_size < 1 || block_size > (size_t)(out_end - out_next))
+			goto invalid;
+
+		if (block_type != LZX_BLOCKTYPE_UNCOMPRESSED) {
+
+			/* Compressed block  */
+
+			if (lzx_decompress_block(d,
+						 &is,
+						 block_type,
+						 block_size,
+						 out_begin,
+						 out_next,
+						 recent_offsets))
+				goto invalid;
+
+			e8_status |= d->maincode_lens[0xe8];
+			out_next += block_size;
+		} else {
+			/* Uncompressed block  */
+
+			out_next = bitstream_read_bytes(&is, out_next,
+							block_size);
+			if (!out_next)
+				goto invalid;
+
+			if (block_size & 1)
+				bitstream_read_byte(&is);
+
+			e8_status = 1;
+		}
+	}
+
+	/* Postprocess the data unless it cannot possibly contain 0xe8 bytes. */
+	if (e8_status)
+		lzx_postprocess(uncompressed_data, uncompressed_size);
+
+	return 0;
+
+invalid:
+	return -1;
+}
+
+/*
+ * lzx_free_decompressor - Free an LZX decompressor
+ *
+ * @decompressor:       A decompressor that was allocated with
+ *			lzx_allocate_decompressor(), or NULL.
+ */
+void lzx_free_decompressor(struct lzx_decompressor *decompressor)
+{
+	kfree(decompressor);
+}
diff --git a/fs/ntfs3/lib/xpress_decompress.c b/fs/ntfs3/lib/xpress_decompress.c
new file mode 100644
index 000000000..3d98f36a9
--- /dev/null
+++ b/fs/ntfs3/lib/xpress_decompress.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xpress_decompress.c - A decompressor for the XPRESS compression format
+ * (Huffman variant), which can be used in "System Compressed" files.  This is
+ * based on the code from wimlib.
+ *
+ * Copyright (C) 2015 Eric Biggers
+ *
+ * This program is free software: you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License as published by the Free Software
+ * Foundation, either version 2 of the License, or (at your option) any later
+ * version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "decompress_common.h"
+#include "lib.h"
+
+#define XPRESS_NUM_SYMBOLS	512
+#define XPRESS_MAX_CODEWORD_LEN	15
+#define XPRESS_MIN_MATCH_LEN	3
+
+/* This value is chosen for fast decompression.  */
+#define XPRESS_TABLEBITS 12
+
+/* Reusable heap-allocated memory for XPRESS decompression  */
+struct xpress_decompressor {
+
+	/* The Huffman decoding table  */
+	u16 decode_table[(1 << XPRESS_TABLEBITS) + 2 * XPRESS_NUM_SYMBOLS];
+
+	/* An array that maps symbols to codeword lengths  */
+	u8 lens[XPRESS_NUM_SYMBOLS];
+
+	/* Temporary space for make_huffman_decode_table()  */
+	u16 working_space[2 * (1 + XPRESS_MAX_CODEWORD_LEN) +
+			  XPRESS_NUM_SYMBOLS];
+};
+
+/*
+ * xpress_allocate_decompressor - Allocate an XPRESS decompressor
+ *
+ * Return the pointer to the decompressor on success, or return NULL and set
+ * errno on failure.
+ */
+struct xpress_decompressor *xpress_allocate_decompressor(void)
+{
+	return kmalloc(sizeof(struct xpress_decompressor), GFP_NOFS);
+}
+
+/*
+ * xpress_decompress - Decompress a buffer of XPRESS-compressed data
+ *
+ * @decompressor:       A decompressor that was allocated with
+ *			xpress_allocate_decompressor()
+ * @compressed_data:	The buffer of data to decompress
+ * @compressed_size:	Number of bytes of compressed data
+ * @uncompressed_data:	The buffer in which to store the decompressed data
+ * @uncompressed_size:	The number of bytes the data decompresses into
+ *
+ * Return 0 on success, or return -1 and set errno on failure.
+ */
+int xpress_decompress(struct xpress_decompressor *decompressor,
+		      const void *compressed_data, size_t compressed_size,
+		      void *uncompressed_data, size_t uncompressed_size)
+{
+	struct xpress_decompressor *d = decompressor;
+	const u8 * const in_begin = compressed_data;
+	u8 * const out_begin = uncompressed_data;
+	u8 *out_next = out_begin;
+	u8 * const out_end = out_begin + uncompressed_size;
+	struct input_bitstream is;
+	u32 i;
+
+	/* Read the Huffman codeword lengths.  */
+	if (compressed_size < XPRESS_NUM_SYMBOLS / 2)
+		goto invalid;
+	for (i = 0; i < XPRESS_NUM_SYMBOLS / 2; i++) {
+		d->lens[i*2 + 0] = in_begin[i] & 0xF;
+		d->lens[i*2 + 1] = in_begin[i] >> 4;
+	}
+
+	/* Build a decoding table for the Huffman code.  */
+	if (make_huffman_decode_table(d->decode_table, XPRESS_NUM_SYMBOLS,
+				      XPRESS_TABLEBITS, d->lens,
+				      XPRESS_MAX_CODEWORD_LEN,
+				      d->working_space))
+		goto invalid;
+
+	/* Decode the matches and literals.  */
+
+	init_input_bitstream(&is, in_begin + XPRESS_NUM_SYMBOLS / 2,
+			     compressed_size - XPRESS_NUM_SYMBOLS / 2);
+
+	while (out_next != out_end) {
+		u32 sym;
+		u32 log2_offset;
+		u32 length;
+		u32 offset;
+
+		sym = read_huffsym(&is, d->decode_table,
+				   XPRESS_TABLEBITS, XPRESS_MAX_CODEWORD_LEN);
+		if (sym < 256) {
+			/* Literal  */
+			*out_next++ = sym;
+		} else {
+			/* Match  */
+			length = sym & 0xf;
+			log2_offset = (sym >> 4) & 0xf;
+
+			bitstream_ensure_bits(&is, 16);
+
+			offset = ((u32)1 << log2_offset) |
+				 bitstream_pop_bits(&is, log2_offset);
+
+			if (length == 0xf) {
+				length += bitstream_read_byte(&is);
+				if (length == 0xf + 0xff)
+					length = bitstream_read_u16(&is);
+			}
+			length += XPRESS_MIN_MATCH_LEN;
+
+			if (offset > (size_t)(out_next - out_begin))
+				goto invalid;
+
+			if (length > (size_t)(out_end - out_next))
+				goto invalid;
+
+			out_next = lz_copy(out_next, length, offset, out_end,
+					   XPRESS_MIN_MATCH_LEN);
+		}
+	}
+	return 0;
+
+invalid:
+	return -1;
+}
+
+/*
+ * xpress_free_decompressor - Free an XPRESS decompressor
+ *
+ * @decompressor:       A decompressor that was allocated with
+ *			xpress_allocate_decompressor(), or NULL.
+ */
+void xpress_free_decompressor(struct xpress_decompressor *decompressor)
+{
+	kfree(decompressor);
+}
diff --git a/fs/ntfs3/lznt.c b/fs/ntfs3/lznt.c
new file mode 100644
index 000000000..ead9ab7d6
--- /dev/null
+++ b/fs/ntfs3/lznt.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+// clang-format off
+/* src buffer is zero */
+#define LZNT_ERROR_ALL_ZEROS	1
+#define LZNT_CHUNK_SIZE		0x1000
+// clang-format on
+
+struct lznt_hash {
+	const u8 *p1;
+	const u8 *p2;
+};
+
+struct lznt {
+	const u8 *unc;
+	const u8 *unc_end;
+	const u8 *best_match;
+	size_t max_len;
+	bool std;
+
+	struct lznt_hash hash[LZNT_CHUNK_SIZE];
+};
+
+static inline size_t get_match_len(const u8 *ptr, const u8 *end, const u8 *prev,
+				   size_t max_len)
+{
+	size_t len = 0;
+
+	while (ptr + len < end && ptr[len] == prev[len] && ++len < max_len)
+		;
+	return len;
+}
+
+static size_t longest_match_std(const u8 *src, struct lznt *ctx)
+{
+	size_t hash_index;
+	size_t len1 = 0, len2 = 0;
+	const u8 **hash;
+
+	hash_index =
+		((40543U * ((((src[0] << 4) ^ src[1]) << 4) ^ src[2])) >> 4) &
+		(LZNT_CHUNK_SIZE - 1);
+
+	hash = &(ctx->hash[hash_index].p1);
+
+	if (hash[0] >= ctx->unc && hash[0] < src && hash[0][0] == src[0] &&
+	    hash[0][1] == src[1] && hash[0][2] == src[2]) {
+		len1 = 3;
+		if (ctx->max_len > 3)
+			len1 += get_match_len(src + 3, ctx->unc_end,
+					      hash[0] + 3, ctx->max_len - 3);
+	}
+
+	if (hash[1] >= ctx->unc && hash[1] < src && hash[1][0] == src[0] &&
+	    hash[1][1] == src[1] && hash[1][2] == src[2]) {
+		len2 = 3;
+		if (ctx->max_len > 3)
+			len2 += get_match_len(src + 3, ctx->unc_end,
+					      hash[1] + 3, ctx->max_len - 3);
+	}
+
+	/* Compare two matches and select the best one */
+	if (len1 < len2) {
+		ctx->best_match = hash[1];
+		len1 = len2;
+	} else {
+		ctx->best_match = hash[0];
+	}
+
+	hash[1] = hash[0];
+	hash[0] = src;
+	return len1;
+}
+
+static size_t longest_match_best(const u8 *src, struct lznt *ctx)
+{
+	size_t max_len;
+	const u8 *ptr;
+
+	if (ctx->unc >= src || !ctx->max_len)
+		return 0;
+
+	max_len = 0;
+	for (ptr = ctx->unc; ptr < src; ++ptr) {
+		size_t len =
+			get_match_len(src, ctx->unc_end, ptr, ctx->max_len);
+		if (len >= max_len) {
+			max_len = len;
+			ctx->best_match = ptr;
+		}
+	}
+
+	return max_len >= 3 ? max_len : 0;
+}
+
+static const size_t s_max_len[] = {
+	0x1002, 0x802, 0x402, 0x202, 0x102, 0x82, 0x42, 0x22, 0x12,
+};
+
+static const size_t s_max_off[] = {
+	0x10, 0x20, 0x40, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000,
+};
+
+static inline u16 make_pair(size_t offset, size_t len, size_t index)
+{
+	return ((offset - 1) << (12 - index)) |
+	       ((len - 3) & (((1 << (12 - index)) - 1)));
+}
+
+static inline size_t parse_pair(u16 pair, size_t *offset, size_t index)
+{
+	*offset = 1 + (pair >> (12 - index));
+	return 3 + (pair & ((1 << (12 - index)) - 1));
+}
+
+/*
+ * compress_chunk
+ *
+ * returns one of the three values:
+ * 0 - ok, 'cmpr' contains 'cmpr_chunk_size' bytes of compressed data
+ * 1 - input buffer is full zero
+ * -2 - the compressed buffer is too small to hold the compressed data
+ */
+static inline int compress_chunk(size_t (*match)(const u8 *, struct lznt *),
+				 const u8 *unc, const u8 *unc_end, u8 *cmpr,
+				 u8 *cmpr_end, size_t *cmpr_chunk_size,
+				 struct lznt *ctx)
+{
+	size_t cnt = 0;
+	size_t idx = 0;
+	const u8 *up = unc;
+	u8 *cp = cmpr + 3;
+	u8 *cp2 = cmpr + 2;
+	u8 not_zero = 0;
+	/* Control byte of 8-bit values: ( 0 - means byte as is, 1 - short pair ) */
+	u8 ohdr = 0;
+	u8 *last;
+	u16 t16;
+
+	if (unc + LZNT_CHUNK_SIZE < unc_end)
+		unc_end = unc + LZNT_CHUNK_SIZE;
+
+	last = min(cmpr + LZNT_CHUNK_SIZE + sizeof(short), cmpr_end);
+
+	ctx->unc = unc;
+	ctx->unc_end = unc_end;
+	ctx->max_len = s_max_len[0];
+
+	while (up < unc_end) {
+		size_t max_len;
+
+		while (unc + s_max_off[idx] < up)
+			ctx->max_len = s_max_len[++idx];
+
+		// Find match
+		max_len = up + 3 <= unc_end ? (*match)(up, ctx) : 0;
+
+		if (!max_len) {
+			if (cp >= last)
+				goto NotCompressed;
+			not_zero |= *cp++ = *up++;
+		} else if (cp + 1 >= last) {
+			goto NotCompressed;
+		} else {
+			t16 = make_pair(up - ctx->best_match, max_len, idx);
+			*cp++ = t16;
+			*cp++ = t16 >> 8;
+
+			ohdr |= 1 << cnt;
+			up += max_len;
+		}
+
+		cnt = (cnt + 1) & 7;
+		if (!cnt) {
+			*cp2 = ohdr;
+			ohdr = 0;
+			cp2 = cp;
+			cp += 1;
+		}
+	}
+
+	if (cp2 < last)
+		*cp2 = ohdr;
+	else
+		cp -= 1;
+
+	*cmpr_chunk_size = cp - cmpr;
+
+	t16 = (*cmpr_chunk_size - 3) | 0xB000;
+	cmpr[0] = t16;
+	cmpr[1] = t16 >> 8;
+
+	return not_zero ? 0 : LZNT_ERROR_ALL_ZEROS;
+
+NotCompressed:
+
+	if ((cmpr + LZNT_CHUNK_SIZE + sizeof(short)) > last)
+		return -2;
+
+	/*
+	 * Copy non cmpr data
+	 * 0x3FFF == ((LZNT_CHUNK_SIZE + 2 - 3) | 0x3000)
+	 */
+	cmpr[0] = 0xff;
+	cmpr[1] = 0x3f;
+
+	memcpy(cmpr + sizeof(short), unc, LZNT_CHUNK_SIZE);
+	*cmpr_chunk_size = LZNT_CHUNK_SIZE + sizeof(short);
+
+	return 0;
+}
+
+static inline ssize_t decompress_chunk(u8 *unc, u8 *unc_end, const u8 *cmpr,
+				       const u8 *cmpr_end)
+{
+	u8 *up = unc;
+	u8 ch = *cmpr++;
+	size_t bit = 0;
+	size_t index = 0;
+	u16 pair;
+	size_t offset, length;
+
+	/* Do decompression until pointers are inside range */
+	while (up < unc_end && cmpr < cmpr_end) {
+		/* Correct index */
+		while (unc + s_max_off[index] < up)
+			index += 1;
+
+		/* Check the current flag for zero */
+		if (!(ch & (1 << bit))) {
+			/* Just copy byte */
+			*up++ = *cmpr++;
+			goto next;
+		}
+
+		/* Check for boundary */
+		if (cmpr + 1 >= cmpr_end)
+			return -EINVAL;
+
+		/* Read a short from little endian stream */
+		pair = cmpr[1];
+		pair <<= 8;
+		pair |= cmpr[0];
+
+		cmpr += 2;
+
+		/* Translate packed information into offset and length */
+		length = parse_pair(pair, &offset, index);
+
+		/* Check offset for boundary */
+		if (unc + offset > up)
+			return -EINVAL;
+
+		/* Truncate the length if necessary */
+		if (up + length >= unc_end)
+			length = unc_end - up;
+
+		/* Now we copy bytes. This is the heart of LZ algorithm. */
+		for (; length > 0; length--, up++)
+			*up = *(up - offset);
+
+next:
+		/* Advance flag bit value */
+		bit = (bit + 1) & 7;
+
+		if (!bit) {
+			if (cmpr >= cmpr_end)
+				break;
+
+			ch = *cmpr++;
+		}
+	}
+
+	/* return the size of uncompressed data */
+	return up - unc;
+}
+
+/*
+ * 0 - standard compression
+ * !0 - best compression, requires a lot of cpu
+ */
+struct lznt *get_lznt_ctx(int level)
+{
+	struct lznt *r = ntfs_zalloc(level ? offsetof(struct lznt, hash)
+					   : sizeof(struct lznt));
+
+	if (r)
+		r->std = !level;
+	return r;
+}
+
+/*
+ * compress_lznt
+ *
+ * Compresses "unc" into "cmpr"
+ * +x - ok, 'cmpr' contains 'final_compressed_size' bytes of compressed data
+ * 0 - input buffer is full zero
+ */
+size_t compress_lznt(const void *unc, size_t unc_size, void *cmpr,
+		     size_t cmpr_size, struct lznt *ctx)
+{
+	int err;
+	size_t (*match)(const u8 *src, struct lznt *ctx);
+	u8 *p = cmpr;
+	u8 *end = p + cmpr_size;
+	const u8 *unc_chunk = unc;
+	const u8 *unc_end = unc_chunk + unc_size;
+	bool is_zero = true;
+
+	if (ctx->std) {
+		match = &longest_match_std;
+		memset(ctx->hash, 0, sizeof(ctx->hash));
+	} else {
+		match = &longest_match_best;
+	}
+
+	/* compression cycle */
+	for (; unc_chunk < unc_end; unc_chunk += LZNT_CHUNK_SIZE) {
+		cmpr_size = 0;
+		err = compress_chunk(match, unc_chunk, unc_end, p, end,
+				     &cmpr_size, ctx);
+		if (err < 0)
+			return unc_size;
+
+		if (is_zero && err != LZNT_ERROR_ALL_ZEROS)
+			is_zero = false;
+
+		p += cmpr_size;
+	}
+
+	if (p <= end - 2)
+		p[0] = p[1] = 0;
+
+	return is_zero ? 0 : PtrOffset(cmpr, p);
+}
+
+/*
+ * decompress_lznt
+ *
+ * decompresses "cmpr" into "unc"
+ */
+ssize_t decompress_lznt(const void *cmpr, size_t cmpr_size, void *unc,
+			size_t unc_size)
+{
+	const u8 *cmpr_chunk = cmpr;
+	const u8 *cmpr_end = cmpr_chunk + cmpr_size;
+	u8 *unc_chunk = unc;
+	u8 *unc_end = unc_chunk + unc_size;
+	u16 chunk_hdr;
+
+	if (cmpr_size < sizeof(short))
+		return -EINVAL;
+
+	/* read chunk header */
+	chunk_hdr = cmpr_chunk[1];
+	chunk_hdr <<= 8;
+	chunk_hdr |= cmpr_chunk[0];
+
+	/* loop through decompressing chunks */
+	for (;;) {
+		size_t chunk_size_saved;
+		size_t unc_use;
+		size_t cmp...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 07/10] fs/ntfs3: Add NTFS journal

[Konstantin K. <alm...@pa...>]

This adds NTFS journal

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/fslog.c | 5181 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 5181 insertions(+)
 create mode 100644 fs/ntfs3/fslog.c

diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
new file mode 100644
index 000000000..53da12252
--- /dev/null
+++ b/fs/ntfs3/fslog.c
@@ -0,0 +1,5181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/hash.h>
+#include <linux/nls.h>
+#include <linux/random.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/*
+ * LOG FILE structs
+ */
+
+// clang-format off
+
+#define MaxLogFileSize     0x100000000ull
+#define DefaultLogPageSize 4096
+#define MinLogRecordPages  0x30
+
+struct RESTART_HDR {
+	struct NTFS_RECORD_HEADER rhdr; // 'RSTR'
+	__le32 sys_page_size; // 0x10: Page size of the system which initialized the log
+	__le32 page_size;     // 0x14: Log page size used for this log file
+	__le16 ra_off;        // 0x18:
+	__le16 minor_ver;     // 0x1A:
+	__le16 major_ver;     // 0x1C:
+	__le16 fixups[];
+};
+
+#define LFS_NO_CLIENT 0xffff
+#define LFS_NO_CLIENT_LE cpu_to_le16(0xffff)
+
+struct CLIENT_REC {
+	__le64 oldest_lsn;
+	__le64 restart_lsn; // 0x08:
+	__le16 prev_client; // 0x10:
+	__le16 next_client; // 0x12:
+	__le16 seq_num;     // 0x14:
+	u8 align[6];        // 0x16
+	__le32 name_bytes;  // 0x1C: in bytes
+	__le16 name[32];    // 0x20: name of client
+};
+
+static_assert(sizeof(struct CLIENT_REC) == 0x60);
+
+/* Two copies of these will exist at the beginning of the log file */
+struct RESTART_AREA {
+	__le64 current_lsn;    // 0x00: Current logical end of log file
+	__le16 log_clients;    // 0x08: Maximum number of clients
+	__le16 client_idx[2];  // 0x0A: free/use index into the client record arrays
+	__le16 flags;          // 0x0E: See RESTART_SINGLE_PAGE_IO
+	__le32 seq_num_bits;   // 0x10: the number of bits in sequence number.
+	__le16 ra_len;         // 0x14:
+	__le16 client_off;     // 0x16:
+	__le64 l_size;         // 0x18: Usable log file size.
+	__le32 last_lsn_data_len; // 0x20:
+	__le16 rec_hdr_len;    // 0x24: log page data offset
+	__le16 data_off;       // 0x26: log page data length
+	__le32 open_log_count; // 0x28:
+	__le32 align[5];       // 0x2C:
+	struct CLIENT_REC clients[]; // 0x40:
+};
+
+struct LOG_REC_HDR {
+	__le16 redo_op;      // 0x00:  NTFS_LOG_OPERATION
+	__le16 undo_op;      // 0x02:  NTFS_LOG_OPERATION
+	__le16 redo_off;     // 0x04:  Offset to Redo record
+	__le16 redo_len;     // 0x06:  Redo length
+	__le16 undo_off;     // 0x08:  Offset to Undo record
+	__le16 undo_len;     // 0x0A:  Undo length
+	__le16 target_attr;  // 0x0C:
+	__le16 lcns_follow;  // 0x0E:
+	__le16 record_off;   // 0x10:
+	__le16 attr_off;     // 0x12:
+	__le16 cluster_off;  // 0x14:
+	__le16 reserved;     // 0x16:
+	__le64 target_vcn;   // 0x18:
+	__le64 page_lcns[];  // 0x20:
+};
+
+static_assert(sizeof(struct LOG_REC_HDR) == 0x20);
+
+#define RESTART_ENTRY_ALLOCATED    0xFFFFFFFF
+#define RESTART_ENTRY_ALLOCATED_LE cpu_to_le32(0xFFFFFFFF)
+
+struct RESTART_TABLE {
+	__le16 size;       // 0x00:  In bytes
+	__le16 used;       // 0x02: entries
+	__le16 total;      // 0x04: entries
+	__le16 res[3];     // 0x06:
+	__le32 free_goal;  // 0x0C:
+	__le32 first_free; // 0x10
+	__le32 last_free;  // 0x14
+
+};
+
+static_assert(sizeof(struct RESTART_TABLE) == 0x18);
+
+struct ATTR_NAME_ENTRY {
+	__le16 off; // offset in the Open attribute Table
+	__le16 name_bytes;
+	__le16 name[];
+};
+
+struct OPEN_ATTR_ENRTY {
+	__le32 next;            // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	__le32 bytes_per_index; // 0x04:
+	enum ATTR_TYPE type;    // 0x08:
+	u8 is_dirty_pages;      // 0x0C:
+	u8 is_attr_name;        // 0x0B: Faked field to manage 'ptr'
+	u8 name_len;            // 0x0C: Faked field to manage 'ptr'
+	u8 res;
+	struct MFT_REF ref; // 0x10: File Reference of file containing attribute
+	__le64 open_record_lsn; // 0x18:
+	void *ptr;              // 0x20:
+};
+
+/* 32 bit version of 'struct OPEN_ATTR_ENRTY' */
+struct OPEN_ATTR_ENRTY_32 {
+	__le32 next;            // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	__le32 ptr;             // 0x04:
+	struct MFT_REF ref;     // 0x08:
+	__le64 open_record_lsn; // 0x10:
+	u8 is_dirty_pages;      // 0x18:
+	u8 is_attr_name;        // 0x19
+	u8 res1[2];
+	enum ATTR_TYPE type;    // 0x1C:
+	u8 name_len;            // 0x20:  in wchar
+	u8 res2[3];
+	__le32 AttributeName;   // 0x24:
+	__le32 bytes_per_index; // 0x28:
+};
+
+#define SIZEOF_OPENATTRIBUTEENTRY0 0x2c
+// static_assert( 0x2C == sizeof(struct OPEN_ATTR_ENRTY_32) );
+static_assert(sizeof(struct OPEN_ATTR_ENRTY) < SIZEOF_OPENATTRIBUTEENTRY0);
+
+/*
+ * One entry exists in the Dirty Pages Table for each page which is dirty at the
+ * time the Restart Area is written
+ */
+struct DIR_PAGE_ENTRY {
+	__le32 next;         // 0x00:  RESTART_ENTRY_ALLOCATED if allocated
+	__le32 target_attr;  // 0x04:  Index into the Open attribute Table
+	__le32 transfer_len; // 0x08:
+	__le32 lcns_follow;  // 0x0C:
+	__le64 vcn;          // 0x10:  Vcn of dirty page
+	__le64 oldest_lsn;   // 0x18:
+	__le64 page_lcns[];  // 0x20:
+};
+
+static_assert(sizeof(struct DIR_PAGE_ENTRY) == 0x20);
+
+/* 32 bit version of 'struct DIR_PAGE_ENTRY' */
+struct DIR_PAGE_ENTRY_32 {
+	__le32 next;         // 0x00:  RESTART_ENTRY_ALLOCATED if allocated
+	__le32 target_attr;  // 0x04:  Index into the Open attribute Table
+	__le32 transfer_len; // 0x08:
+	__le32 lcns_follow;  // 0x0C:
+	__le32 reserved;     // 0x10:
+	__le32 vcn_low;      // 0x14:  Vcn of dirty page
+	__le32 vcn_hi;       // 0x18:  Vcn of dirty page
+	__le32 oldest_lsn_low; // 0x1C:
+	__le32 oldest_lsn_hi; // 0x1C:
+	__le32 page_lcns_low; // 0x24:
+	__le32 page_lcns_hi; // 0x24:
+};
+
+static_assert(offsetof(struct DIR_PAGE_ENTRY_32, vcn_low) == 0x14);
+static_assert(sizeof(struct DIR_PAGE_ENTRY_32) == 0x2c);
+
+enum transact_state {
+	TransactionUninitialized = 0,
+	TransactionActive,
+	TransactionPrepared,
+	TransactionCommitted
+};
+
+struct TRANSACTION_ENTRY {
+	__le32 next;          // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	u8 transact_state;    // 0x04:
+	u8 reserved[3];       // 0x05:
+	__le64 first_lsn;     // 0x08:
+	__le64 prev_lsn;      // 0x10:
+	__le64 undo_next_lsn; // 0x18:
+	__le32 undo_records;  // 0x20: Number of undo log records pending abort
+	__le32 undo_len;      // 0x24: Total undo size
+};
+
+static_assert(sizeof(struct TRANSACTION_ENTRY) == 0x28);
+
+struct NTFS_RESTART {
+	__le32 major_ver;             // 0x00:
+	__le32 minor_ver;             // 0x04:
+	__le64 check_point_start;     // 0x08:
+	__le64 open_attr_table_lsn;   // 0x10:
+	__le64 attr_names_lsn;        // 0x18:
+	__le64 dirty_pages_table_lsn; // 0x20:
+	__le64 transact_table_lsn;    // 0x28:
+	__le32 open_attr_len;         // 0x30: In bytes
+	__le32 attr_names_len;        // 0x34: In bytes
+	__le32 dirty_pages_len;       // 0x38: In bytes
+	__le32 transact_table_len;    // 0x3C: In bytes
+};
+
+static_assert(sizeof(struct NTFS_RESTART) == 0x40);
+
+struct NEW_ATTRIBUTE_SIZES {
+	__le64 alloc_size;
+	__le64 valid_size;
+	__le64 data_size;
+	__le64 total_size;
+};
+
+struct BITMAP_RANGE {
+	__le32 bitmap_off;
+	__le32 bits;
+};
+
+struct LCN_RANGE {
+	__le64 lcn;
+	__le64 len;
+};
+
+/* The following type defines the different log record types */
+#define LfsClientRecord  cpu_to_le32(1)
+#define LfsClientRestart cpu_to_le32(2)
+
+/* This is used to uniquely identify a client for a particular log file */
+struct CLIENT_ID {
+	__le16 seq_num;
+	__le16 client_idx;
+};
+
+/* This is the header that begins every Log Record in the log file */
+struct LFS_RECORD_HDR {
+	__le64 this_lsn;    // 0x00:
+	__le64 client_prev_lsn;  // 0x08:
+	__le64 client_undo_next_lsn; // 0x10:
+	__le32 client_data_len;  // 0x18:
+	struct CLIENT_ID client; // 0x1C: Owner of this log record
+	__le32 record_type; // 0x20: LfsClientRecord or LfsClientRestart
+	__le32 transact_id; // 0x24:
+	__le16 flags;       // 0x28:	LOG_RECORD_MULTI_PAGE
+	u8 align[6];        // 0x2A:
+};
+
+#define LOG_RECORD_MULTI_PAGE cpu_to_le16(1)
+
+static_assert(sizeof(struct LFS_RECORD_HDR) == 0x30);
+
+struct LFS_RECORD {
+	__le16 next_record_off; // 0x00: Offset of the free space in the page
+	u8 align[6];         // 0x02:
+	__le64 last_end_lsn; // 0x08: lsn for the last log record which ends on the page
+};
+
+static_assert(sizeof(struct LFS_RECORD) == 0x10);
+
+struct RECORD_PAGE_HDR {
+	struct NTFS_RECORD_HEADER rhdr; // 'RCRD'
+	__le32 rflags;     // 0x10:  See LOG_PAGE_LOG_RECORD_END
+	__le16 page_count; // 0x14:
+	__le16 page_pos;   // 0x16:
+	struct LFS_RECORD record_hdr; // 0x18
+	__le16 fixups[10]; // 0x28
+	__le32 file_off;   // 0x3c: used when major version >= 2
+};
+
+// clang-format on
+
+// Page contains the end of a log record
+#define LOG_PAGE_LOG_RECORD_END cpu_to_le32(0x00000001)
+
+static inline bool is_log_record_end(const struct RECORD_PAGE_HDR *hdr)
+{
+	return hdr->rflags & LOG_PAGE_LOG_RECORD_END;
+}
+
+static_assert(offsetof(struct RECORD_PAGE_HDR, file_off) == 0x3c);
+
+/*
+ * END of NTFS LOG structures
+ */
+
+/* Define some tuning parameters to keep the restart tables a reasonable size */
+#define INITIAL_NUMBER_TRANSACTIONS 5
+
+enum NTFS_LOG_OPERATION {
+
+	Noop = 0x00,
+	CompensationLogRecord = 0x01,
+	InitializeFileRecordSegment = 0x02,
+	DeallocateFileRecordSegment = 0x03,
+	WriteEndOfFileRecordSegment = 0x04,
+	CreateAttribute = 0x05,
+	DeleteAttribute = 0x06,
+	UpdateResidentValue = 0x07,
+	UpdateNonresidentValue = 0x08,
+	UpdateMappingPairs = 0x09,
+	DeleteDirtyClusters = 0x0A,
+	SetNewAttributeSizes = 0x0B,
+	AddIndexEntryRoot = 0x0C,
+	DeleteIndexEntryRoot = 0x0D,
+	AddIndexEntryAllocation = 0x0E,
+	DeleteIndexEntryAllocation = 0x0F,
+	WriteEndOfIndexBuffer = 0x10,
+	SetIndexEntryVcnRoot = 0x11,
+	SetIndexEntryVcnAllocation = 0x12,
+	UpdateFileNameRoot = 0x13,
+	UpdateFileNameAllocation = 0x14,
+	SetBitsInNonresidentBitMap = 0x15,
+	ClearBitsInNonresidentBitMap = 0x16,
+	HotFix = 0x17,
+	EndTopLevelAction = 0x18,
+	PrepareTransaction = 0x19,
+	CommitTransaction = 0x1A,
+	ForgetTransaction = 0x1B,
+	OpenNonresidentAttribute = 0x1C,
+	OpenAttributeTableDump = 0x1D,
+	AttributeNamesDump = 0x1E,
+	DirtyPageTableDump = 0x1F,
+	TransactionTableDump = 0x20,
+	UpdateRecordDataRoot = 0x21,
+	UpdateRecordDataAllocation = 0x22,
+
+	UpdateRelativeDataInIndex =
+		0x23, // NtOfsRestartUpdateRelativeDataInIndex
+	UpdateRelativeDataInIndex2 = 0x24,
+	ZeroEndOfFileRecord = 0x25,
+};
+
+/*
+ * Array for log records which require a target attribute
+ * A true indicates that the corresponding restart operation requires a target attribute
+ */
+static const u8 AttributeRequired[] = {
+	0xFC, 0xFB, 0xFF, 0x10, 0x06,
+};
+
+static inline bool is_target_required(u16 op)
+{
+	bool ret = op <= UpdateRecordDataAllocation &&
+		   (AttributeRequired[op >> 3] >> (op & 7) & 1);
+	return ret;
+}
+
+static inline bool can_skip_action(enum NTFS_LOG_OPERATION op)
+{
+	switch (op) {
+	case Noop:
+	case DeleteDirtyClusters:
+	case HotFix:
+	case EndTopLevelAction:
+	case PrepareTransaction:
+	case CommitTransaction:
+	case ForgetTransaction:
+	case CompensationLogRecord:
+	case OpenNonresidentAttribute:
+	case OpenAttributeTableDump:
+	case AttributeNamesDump:
+	case DirtyPageTableDump:
+	case TransactionTableDump:
+		return true;
+	default:
+		return false;
+	}
+}
+
+enum { lcb_ctx_undo_next, lcb_ctx_prev, lcb_ctx_next };
+
+/* bytes per restart table */
+static inline u32 bytes_per_rt(const struct RESTART_TABLE *rt)
+{
+	return le16_to_cpu(rt->used) * le16_to_cpu(rt->size) +
+	       sizeof(struct RESTART_TABLE);
+}
+
+/* log record length */
+static inline u32 lrh_length(const struct LOG_REC_HDR *lr)
+{
+	u16 t16 = le16_to_cpu(lr->lcns_follow);
+
+	return struct_size(lr, page_lcns, max_t(u16, 1, t16));
+}
+
+struct lcb {
+	struct LFS_RECORD_HDR *lrh; // Log record header of the current lsn
+	struct LOG_REC_HDR *log_rec;
+	u32 ctx_mode; // lcb_ctx_undo_next/lcb_ctx_prev/lcb_ctx_next
+	struct CLIENT_ID client;
+	bool alloc; // if true the we should deallocate 'log_rec'
+};
+
+static void lcb_put(struct lcb *lcb)
+{
+	if (lcb->alloc)
+		ntfs_free(lcb->log_rec);
+	ntfs_free(lcb->lrh);
+	ntfs_free(lcb);
+}
+
+/*
+ * oldest_client_lsn
+ *
+ * find the oldest lsn from active clients.
+ */
+static inline void oldest_client_lsn(const struct CLIENT_REC *ca,
+				     __le16 next_client, u64 *oldest_lsn)
+{
+	while (next_client != LFS_NO_CLIENT_LE) {
+		const struct CLIENT_REC *cr = ca + le16_to_cpu(next_client);
+		u64 lsn = le64_to_cpu(cr->oldest_lsn);
+
+		/* ignore this block if it's oldest lsn is 0 */
+		if (lsn && lsn < *oldest_lsn)
+			*oldest_lsn = lsn;
+
+		next_client = cr->next_client;
+	}
+}
+
+static inline bool is_rst_page_hdr_valid(u32 file_off,
+					 const struct RESTART_HDR *rhdr)
+{
+	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
+	u32 page_size = le32_to_cpu(rhdr->page_size);
+	u32 end_usa;
+	u16 ro;
+
+	if (sys_page < SECTOR_SIZE || page_size < SECTOR_SIZE ||
+	    sys_page & (sys_page - 1) || page_size & (page_size - 1)) {
+		return false;
+	}
+
+	/* Check that if the file offset isn't 0, it is the system page size */
+	if (file_off && file_off != sys_page)
+		return false;
+
+	/* Check support version 1.1+ */
+	if (le16_to_cpu(rhdr->major_ver) <= 1 && !rhdr->minor_ver)
+		return false;
+
+	if (le16_to_cpu(rhdr->major_ver) > 2)
+		return false;
+
+	ro = le16_to_cpu(rhdr->ra_off);
+	if (!IsQuadAligned(ro) || ro > sys_page)
+		return false;
+
+	end_usa = ((sys_page >> SECTOR_SHIFT) + 1) * sizeof(short);
+	end_usa += le16_to_cpu(rhdr->rhdr.fix_off);
+
+	if (ro < end_usa)
+		return false;
+
+	return true;
+}
+
+static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
+{
+	const struct RESTART_AREA *ra;
+	u16 cl, fl, ul;
+	u32 off, l_size, file_dat_bits, file_size_round;
+	u16 ro = le16_to_cpu(rhdr->ra_off);
+	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
+
+	if (ro + offsetof(struct RESTART_AREA, l_size) >
+	    SECTOR_SIZE - sizeof(short))
+		return false;
+
+	ra = Add2Ptr(rhdr, ro);
+	cl = le16_to_cpu(ra->log_clients);
+
+	if (cl > 1)
+		return false;
+
+	off = le16_to_cpu(ra->client_off);
+
+	if (!IsQuadAligned(off) || ro + off > SECTOR_SIZE - sizeof(short))
+		return false;
+
+	off += cl * sizeof(struct CLIENT_REC);
+
+	if (off > sys_page)
+		return false;
+
+	/*
+	 * Check the restart length field and whether the entire
+	 * restart area is contained that length
+	 */
+	if (le16_to_cpu(rhdr->ra_off) + le16_to_cpu(ra->ra_len) > sys_page ||
+	    off > le16_to_cpu(ra->ra_len)) {
+		return false;
+	}
+
+	/*
+	 * As a final check make sure that the use list and the free list
+	 * are either empty or point to a valid client
+	 */
+	fl = le16_to_cpu(ra->client_idx[0]);
+	ul = le16_to_cpu(ra->client_idx[1]);
+	if ((fl != LFS_NO_CLIENT && fl >= cl) ||
+	    (ul != LFS_NO_CLIENT && ul >= cl))
+		return false;
+
+	/* Make sure the sequence number bits match the log file size */
+	l_size = le64_to_cpu(ra->l_size);
+
+	file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
+	file_size_round = 1u << (file_dat_bits + 3);
+	if (file_size_round != l_size &&
+	    (file_size_round < l_size || (file_size_round / 2) > l_size)) {
+		return false;
+	}
+
+	/* The log page data offset and record header length must be quad-aligned */
+	if (!IsQuadAligned(le16_to_cpu(ra->data_off)) ||
+	    !IsQuadAligned(le16_to_cpu(ra->rec_hdr_len)))
+		return false;
+
+	return true;
+}
+
+static inline bool is_client_area_valid(const struct RESTART_HDR *rhdr,
+					bool usa_error)
+{
+	u16 ro = le16_to_cpu(rhdr->ra_off);
+	const struct RESTART_AREA *ra = Add2Ptr(rhdr, ro);
+	u16 ra_len = le16_to_cpu(ra->ra_len);
+	const struct CLIENT_REC *ca;
+	u32 i;
+
+	if (usa_error && ra_len + ro > SECTOR_SIZE - sizeof(short))
+		return false;
+
+	/* Find the start of the client array */
+	ca = Add2Ptr(ra, le16_to_cpu(ra->client_off));
+
+	/*
+	 * Start with the free list
+	 * Check that all the clients are valid and that there isn't a cycle
+	 * Do the in-use list on the second pass
+	 */
+	for (i = 0; i < 2; i++) {
+		u16 client_idx = le16_to_cpu(ra->client_idx[i]);
+		bool first_client = true;
+		u16 clients = le16_to_cpu(ra->log_clients);
+
+		while (client_idx != LFS_NO_CLIENT) {
+			const struct CLIENT_REC *cr;
+
+			if (!clients ||
+			    client_idx >= le16_to_cpu(ra->log_clients))
+				return false;
+
+			clients -= 1;
+			cr = ca + client_idx;
+
+			client_idx = le16_to_cpu(cr->next_client);
+
+			if (first_client) {
+				first_client = false;
+				if (cr->prev_client != LFS_NO_CLIENT_LE)
+					return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+/*
+ * remove_client
+ *
+ * remove a client record from a client record list an restart area
+ */
+static inline void remove_client(struct CLIENT_REC *ca,
+				 const struct CLIENT_REC *cr, __le16 *head)
+{
+	if (cr->prev_client == LFS_NO_CLIENT_LE)
+		*head = cr->next_client;
+	else
+		ca[le16_to_cpu(cr->prev_client)].next_client = cr->next_client;
+
+	if (cr->next_client != LFS_NO_CLIENT_LE)
+		ca[le16_to_cpu(cr->next_client)].prev_client = cr->prev_client;
+}
+
+/*
+ * add_client
+ *
+ * add a client record to the start of a list
+ */
+static inline void add_client(struct CLIENT_REC *ca, u16 index, __le16 *head)
+{
+	struct CLIENT_REC *cr = ca + index;
+
+	cr->prev_client = LFS_NO_CLIENT_LE;
+	cr->next_client = *head;
+
+	if (*head != LFS_NO_CLIENT_LE)
+		ca[le16_to_cpu(*head)].prev_client = cpu_to_le16(index);
+
+	*head = cpu_to_le16(index);
+}
+
+/*
+ * enum_rstbl
+ *
+ */
+static inline void *enum_rstbl(struct RESTART_TABLE *t, void *c)
+{
+	__le32 *e;
+	u32 bprt;
+	u16 rsize = t ? le16_to_cpu(t->size) : 0;
+
+	if (!c) {
+		if (!t || !t->total)
+			return NULL;
+		e = Add2Ptr(t, sizeof(struct RESTART_TABLE));
+	} else {
+		e = Add2Ptr(c, rsize);
+	}
+
+	/* Loop until we hit the first one allocated, or the end of the list */
+	for (bprt = bytes_per_rt(t); PtrOffset(t, e) < bprt;
+	     e = Add2Ptr(e, rsize)) {
+		if (*e == RESTART_ENTRY_ALLOCATED_LE)
+			return e;
+	}
+	return NULL;
+}
+
+/*
+ * find_dp
+ *
+ * searches for a 'vcn' in Dirty Page Table,
+ */
+static inline struct DIR_PAGE_ENTRY *find_dp(struct RESTART_TABLE *dptbl,
+					     u32 target_attr, u64 vcn)
+{
+	__le32 ta = cpu_to_le32(target_attr);
+	struct DIR_PAGE_ENTRY *dp = NULL;
+
+	while ((dp = enum_rstbl(dptbl, dp))) {
+		u64 dp_vcn = le64_to_cpu(dp->vcn);
+
+		if (dp->target_attr == ta && vcn >= dp_vcn &&
+		    vcn < dp_vcn + le32_to_cpu(dp->lcns_follow)) {
+			return dp;
+		}
+	}
+	return NULL;
+}
+
+static inline u32 norm_file_page(u32 page_size, u32 *l_size, bool use_default)
+{
+	if (use_default)
+		page_size = DefaultLogPageSize;
+
+	/* Round the file size down to a system page boundary */
+	*l_size &= ~(page_size - 1);
+
+	/* File should contain at least 2 restart pages and MinLogRecordPages pages */
+	if (*l_size < (MinLogRecordPages + 2) * page_size)
+		return 0;
+
+	return page_size;
+}
+
+static bool check_log_rec(const struct LOG_REC_HDR *lr, u32 bytes, u32 tr,
+			  u32 bytes_per_attr_entry)
+{
+	u16 t16;
+
+	if (bytes < sizeof(struct LOG_REC_HDR))
+		return false;
+	if (!tr)
+		return false;
+
+	if ((tr - sizeof(struct RESTART_TABLE)) %
+	    sizeof(struct TRANSACTION_ENTRY))
+		return false;
+
+	if (le16_to_cpu(lr->redo_off) & 7)
+		return false;
+
+	if (le16_to_cpu(lr->undo_off) & 7)
+		return false;
+
+	if (lr->target_attr)
+		goto check_lcns;
+
+	if (is_target_required(le16_to_cpu(lr->redo_op)))
+		return false;
+
+	if (is_target_required(le16_to_cpu(lr->undo_op)))
+		return false;
+
+check_lcns:
+	if (!lr->lcns_follow)
+		goto check_length;
+
+	t16 = le16_to_cpu(lr->target_attr);
+	if ((t16 - sizeof(struct RESTART_TABLE)) % bytes_per_attr_entry)
+		return false;
+
+check_length:
+	if (bytes < lrh_length(lr))
+		return false;
+
+	return true;
+}
+
+static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes)
+{
+	u32 ts;
+	u32 i, off;
+	u16 rsize = le16_to_cpu(rt->size);
+	u16 ne = le16_to_cpu(rt->used);
+	u32 ff = le32_to_cpu(rt->first_free);
+	u32 lf = le32_to_cpu(rt->last_free);
+
+	ts = rsize * ne + sizeof(struct RESTART_TABLE);
+
+	if (!rsize || rsize > bytes ||
+	    rsize + sizeof(struct RESTART_TABLE) > bytes || bytes < ts ||
+	    le16_to_cpu(rt->total) > ne || ff > ts || lf > ts ||
+	    (ff && ff < sizeof(struct RESTART_TABLE)) ||
+	    (lf && lf < sizeof(struct RESTART_TABLE))) {
+		return false;
+	}
+
+	/* Verify each entry is either allocated or points
+	 * to a valid offset the table
+	 */
+	for (i = 0; i < ne; i++) {
+		off = le32_to_cpu(*(__le32 *)Add2Ptr(
+			rt, i * rsize + sizeof(struct RESTART_TABLE)));
+
+		if (off != RESTART_ENTRY_ALLOCATED && off &&
+		    (off < sizeof(struct RESTART_TABLE) ||
+		     ((off - sizeof(struct RESTART_TABLE)) % rsize))) {
+			return false;
+		}
+	}
+
+	/* Walk through the list headed by the first entry to make
+	 * sure none of the entries are currently being used
+	 */
+	for (off = ff; off;) {
+		if (off == RESTART_ENTRY_ALLOCATED)
+			return false;
+
+		off = le32_to_cpu(*(__le32 *)Add2Ptr(rt, off));
+	}
+
+	return true;
+}
+
+/*
+ * free_rsttbl_idx
+ *
+ * frees a previously allocated index a Restart Table.
+ */
+static inline void free_rsttbl_idx(struct RESTART_TABLE *rt, u32 off)
+{
+	__le32 *e;
+	u32 lf = le32_to_cpu(rt->last_free);
+	__le32 off_le = cpu_to_le32(off);
+
+	e = Add2Ptr(rt, off);
+
+	if (off < le32_to_cpu(rt->free_goal)) {
+		*e = rt->first_free;
+		rt->first_free = off_le;
+		if (!lf)
+			rt->last_free = off_le;
+	} else {
+		if (lf)
+			*(__le32 *)Add2Ptr(rt, lf) = off_le;
+		else
+			rt->first_free = off_le;
+
+		rt->last_free = off_le;
+		*e = 0;
+	}
+
+	le16_sub_cpu(&rt->total, 1);
+}
+
+static inline struct RESTART_TABLE *init_rsttbl(u16 esize, u16 used)
+{
+	__le32 *e, *last_free;
+	u32 off;
+	u32 bytes = esize * used + sizeof(struct RESTART_TABLE);
+	u32 lf = sizeof(struct RESTART_TABLE) + (used - 1) * esize;
+	struct RESTART_TABLE *t = ntfs_zalloc(bytes);
+
+	t->size = cpu_to_le16(esize);
+	t->used = cpu_to_le16(used);
+	t->free_goal = cpu_to_le32(~0u);
+	t->first_free = cpu_to_le32(sizeof(struct RESTART_TABLE));
+	t->last_free = cpu_to_le32(lf);
+
+	e = (__le32 *)(t + 1);
+	last_free = Add2Ptr(t, lf);
+
+	for (off = sizeof(struct RESTART_TABLE) + esize; e < last_free;
+	     e = Add2Ptr(e, esize), off += esize) {
+		*e = cpu_to_le32(off);
+	}
+	return t;
+}
+
+static inline struct RESTART_TABLE *extend_rsttbl(struct RESTART_TABLE *tbl,
+						  u32 add, u32 free_goal)
+{
+	u16 esize = le16_to_cpu(tbl->size);
+	__le32 osize = cpu_to_le32(bytes_per_rt(tbl));
+	u32 used = le16_to_cpu(tbl->used);
+	struct RESTART_TABLE *rt = init_rsttbl(esize, used + add);
+
+	memcpy(rt + 1, tbl + 1, esize * used);
+
+	rt->free_goal = free_goal == ~0u
+				? cpu_to_le32(~0u)
+				: cpu_to_le32(sizeof(struct RESTART_TABLE) +
+					      free_goal * esize);
+
+	if (tbl->first_free) {
+		rt->first_free = tbl->first_free;
+		*(__le32 *)Add2Ptr(rt, le32_to_cpu(tbl->last_free)) = osize;
+	} else {
+		rt->first_free = osize;
+	}
+
+	rt->total = tbl->total;
+
+	ntfs_free(tbl);
+	return rt;
+}
+
+/*
+ * alloc_rsttbl_idx
+ *
+ * allocates an index from within a previously initialized Restart Table
+ */
+static inline void *alloc_rsttbl_idx(struct RESTART_TABLE **tbl)
+{
+	u32 off;
+	__le32 *e;
+	struct RESTART_TABLE *t = *tbl;
+
+	if (!t->first_free)
+		*tbl = t = extend_rsttbl(t, 16, ~0u);
+
+	off = le32_to_cpu(t->first_free);
+
+	/* Dequeue this entry and zero it. */
+	e = Add2Ptr(t, off);
+
+	t->first_free = *e;
+
+	memset(e, 0, le16_to_cpu(t->size));
+
+	*e = RESTART_ENTRY_ALLOCATED_LE;
+
+	/* If list is going empty, then we fix the last_free as well. */
+	if (!t->first_free)
+		t->last_free = 0;
+
+	le16_add_cpu(&t->total, 1);
+
+	return Add2Ptr(t, off);
+}
+
+/*
+ * alloc_rsttbl_from_idx
+ *
+ * allocates a specific index from within a previously initialized Restart Table
+ */
+static inline void *alloc_rsttbl_from_idx(struct RESTART_TABLE **tbl, u32 vbo)
+{
+	u32 off;
+	__le32 *e;
+	struct RESTART_TABLE *rt = *tbl;
+	u32 bytes = bytes_per_rt(rt);
+	u16 esize = le16_to_cpu(rt->size);
+
+	/* If the entry is not the table, we will have to extend the table */
+	if (vbo >= bytes) {
+		/*
+		 * extend the size by computing the number of entries between
+		 * the existing size and the desired index and adding
+		 * 1 to that
+		 */
+		u32 bytes2idx = vbo - bytes;
+
+		/* There should always be an integral number of entries being added */
+		/* Now extend the table */
+		*tbl = rt = extend_rsttbl(rt, bytes2idx / esize + 1, bytes);
+		if (!rt)
+			return NULL;
+	}
+
+	/* see if the entry is already allocated, and just return if it is. */
+	e = Add2Ptr(rt, vbo);
+
+	if (*e == RESTART_ENTRY_ALLOCATED_LE)
+		return e;
+
+	/*
+	 * Walk through the table, looking for the entry we're
+	 * interested and the previous entry
+	 */
+	off = le32_to_cpu(rt->first_free);
+	e = Add2Ptr(rt, off);
+
+	if (off == vbo) {
+		/* this is a match */
+		rt->first_free = *e;
+		goto skip_looking;
+	}
+
+	/*
+	 * need to walk through the list looking for the predecessor of our entry
+	 */
+	for (;;) {
+		/* Remember the entry just found */
+		u32 last_off = off;
+		__le32 *last_e = e;
+
+		/* should never run of entries. */
+
+		/* Lookup up the next entry the list */
+		off = le32_to_cpu(*last_e);
+		e = Add2Ptr(rt, off);
+
+		/* If this is our match we are done */
+		if (off == vbo) {
+			*last_e = *e;
+
+			/* If this was the last entry, we update that the table as well */
+			if (le32_to_cpu(rt->last_free) == off)
+				rt->last_free = cpu_to_le32(last_off);
+			break;
+		}
+	}
+
+skip_looking:
+	/* If the list is now empty, we fix the last_free as well */
+	if (!rt->first_free)
+		rt->last_free = 0;
+
+	/* Zero this entry */
+	memset(e, 0, esize);
+	*e = RESTART_ENTRY_ALLOCATED_LE;
+
+	le16_add_cpu(&rt->total, 1);
+
+	return e;
+}
+
+#define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
+
+#define NTFSLOG_WRAPPED 0x00000001
+#define NTFSLOG_MULTIPLE_PAGE_IO 0x00000002
+#define NTFSLOG_NO_LAST_LSN 0x00000004
+#define NTFSLOG_REUSE_TAIL 0x00000010
+#define NTFSLOG_NO_OLDEST_LSN 0x00000020
+
+/*
+ * Helper struct to work with NTFS LogFile
+ */
+struct ntfs_log {
+	struct ntfs_inode *ni;
+
+	u32 l_size;
+	u32 sys_page_size;
+	u32 sys_page_mask;
+	u32 page_size;
+	u32 page_mask; // page_size - 1
+	u8 page_bits;
+	struct RECORD_PAGE_HDR *one_page_buf;
+
+	struct RESTART_TABLE *open_attr_tbl;
+	u32 transaction_id;
+	u32 clst_per_page;
+
+	u32 first_page;
+	u32 next_page;
+	u32 ra_off;
+	u32 data_off;
+	u32 restart_size;
+	u32 data_size;
+	u16 record_header_len;
+	u64 seq_num;
+	u32 seq_num_bits;
+	u32 file_data_bits;
+	u32 seq_num_mask; /* (1 << file_data_bits) - 1 */
+
+	struct RESTART_AREA *ra; /* in-memory image of the next restart area */
+	u32 ra_size; /* the usable size of the restart area */
+
+	/*
+	 * If true, then the in-memory restart area is to be written
+	 * to the first position on the disk
+	 */
+	bool init_ra;
+	bool set_dirty; /* true if we need to set dirty flag */
+
+	u64 oldest_lsn;
+
+	u32 oldest_lsn_off;
+	u64 last_lsn;
+
+	u32 total_avail;
+	u32 total_avail_pages;
+	u32 total_undo_commit;
+	u32 max_current_avail;
+	u32 current_avail;
+	u32 reserved;
+
+	short major_ver;
+	short minor_ver;
+
+	u32 l_flags; /* See NTFSLOG_XXX */
+	u32 current_openlog_count; /* On-disk value for open_log_count */
+
+	struct CLIENT_ID client_id;
+	u32 client_undo_commit;
+};
+
+static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
+{
+	u32 vbo = (lsn << log->seq_num_bits) >> (log->seq_num_bits - 3);
+
+	return vbo;
+}
+
+/* compute the offset in the log file of the next log page */
+static inline u32 next_page_off(struct ntfs_log *log, u32 off)
+{
+	off = (off & ~log->sys_page_mask) + log->page_size;
+	return off >= log->l_size ? log->first_page : off;
+}
+
+static inline u32 lsn_to_page_off(struct ntfs_log *log, u64 lsn)
+{
+	return (((u32)lsn) << 3) & log->page_mask;
+}
+
+static inline u64 vbo_to_lsn(struct ntfs_log *log, u32 off, u64 Seq)
+{
+	return (off >> 3) + (Seq << log->file_data_bits);
+}
+
+static inline bool is_lsn_in_file(struct ntfs_log *log, u64 lsn)
+{
+	return lsn >= log->oldest_lsn &&
+	       lsn <= le64_to_cpu(log->ra->current_lsn);
+}
+
+static inline u32 hdr_file_off(struct ntfs_log *log,
+			       struct RECORD_PAGE_HDR *hdr)
+{
+	if (log->major_ver < 2)
+		return le64_to_cpu(hdr->rhdr.lsn);
+
+	return le32_to_cpu(hdr->file_off);
+}
+
+static inline u64 base_lsn(struct ntfs_log *log,
+			   const struct RECORD_PAGE_HDR *hdr, u64 lsn)
+{
+	u64 h_lsn = le64_to_cpu(hdr->rhdr.lsn);
+	u64 ret = (((h_lsn >> log->file_data_bits) +
+		    (lsn < (lsn_to_vbo(log, h_lsn) & ~log->page_mask) ? 1 : 0))
+		   << log->file_data_bits) +
+		  ((((is_log_record_end(hdr) &&
+		      h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn))
+			     ? le16_to_cpu(hdr->record_hdr.next_record_off)
+			     : log->page_size) +
+		    lsn) >>
+		   3);
+
+	return ret;
+}
+
+static inline bool verify_client_lsn(struct ntfs_log *log,
+				     const struct CLIENT_REC *client, u64 lsn)
+{
+	return lsn >= le64_to_cpu(client->oldest_lsn) &&
+	       lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
+}
+
+struct restart_info {
+	u64 last_lsn;
+	struct RESTART_HDR *r_page;
+	u32 vbo;
+	bool chkdsk_was_run;
+	bool valid_page;
+	bool initialized;
+	bool restart;
+};
+
+static int read_log_page(struct ntfs_log *log, u32 vbo,
+			 struct RECORD_PAGE_HDR **buffer, bool *usa_error)
+{
+	int err = 0;
+	u32 page_idx = vbo >> log->page_bits;
+	u32 page_off = vbo & log->page_mask;
+	u32 bytes = log->page_size - page_off;
+	void *to_free = NULL;
+	u32 page_vbo = page_idx << log->page_bits;
+	struct RECORD_PAGE_HDR *page_buf;
+	struct ntfs_inode *ni = log->ni;
+	bool bBAAD;
+
+	if (vbo >= log->l_size)
+		return -EINVAL;
+
+	if (!*buffer) {
+		to_free = ntfs_malloc(bytes);
+		if (!to_free)
+			return -ENOMEM;
+		*buffer = to_free;
+	}
+
+	page_buf = page_off ? log->one_page_buf : *buffer;
+
+	err = ntfs_read_run_nb(ni->mi.sbi, &ni->file.run, page_vbo, page_buf,
+			       log->page_size, NULL);
+	if (err)
+		goto out;
+
+	if (page_buf->rhdr.sign != NTFS_FFFF_SIGNATURE)
+		ntfs_fix_post_read(&page_buf->rhdr, PAGE_SIZE, false);
+
+	if (page_buf != *buffer)
+		memcpy(*buffer, Add2Ptr(page_buf, page_off), bytes);
+
+	bBAAD = page_buf->rhdr.sign == NTFS_BAAD_SIGNATURE;
+
+	if (usa_error)
+		*usa_error = bBAAD;
+	/* Check that the update sequence array for this page is valid */
+	/* If we don't allow errors, raise an error status */
+	else if (bBAAD)
+		err = -EINVAL;
+
+out:
+	if (err && to_free) {
+		ntfs_free(to_free);
+		*buffer = NULL;
+	}
+
+	return err;
+}
+
+/*
+ * log_read_rst
+ *
+ * it walks through 512 blocks of the file looking for a valid restart page header
+ * It will stop the first time we find a valid page header
+ */
+static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+			struct restart_info *info)
+{
+	u32 skip, vbo;
+	struct RESTART_HDR *r_page = ntfs_malloc(DefaultLogPageSize);
+
+	if (!r_page)
+		return -ENOMEM;
+
+	memset(info, 0, sizeof(struct restart_info));
+
+	/* Determine which restart area we are looking for */
+	if (first) {
+		vbo = 0;
+		skip = 512;
+	} else {
+		vbo = 512;
+		skip = 0;
+	}
+
+	/* loop continuously until we succeed */
+	for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+		bool usa_error;
+		u32 sys_page_size;
+		bool brst, bchk;
+		struct RESTART_AREA *ra;
+
+		/* Read a page header at the current offset */
+		if (read_log_page(log, vbo, (struct RECORD_PAGE_HDR **)&r_page,
+				  &usa_error)) {
+			/* ignore any errors */
+			continue;
+		}
+
+		/* exit if the signature is a log record page */
+		if (r_page->rhdr.sign == NTFS_RCRD_SIGNATURE) {
+			info->initialized = true;
+			break;
+		}
+
+		brst = r_page->rhdr.sign == NTFS_RSTR_SIGNATURE;
+		bchk = r_page->rhdr.sign == NTFS_CHKD_SIGNATURE;
+
+		if (!bchk && !brst) {
+			if (r_page->rhdr.sign != NTFS_FFFF_SIGNATURE) {
+				/*
+				 * Remember if the signature does not
+				 * indicate uninitialized file
+				 */
+				info->initialized = true;
+			}
+			continue;
+		}
+
+		ra = NULL;
+		info->valid_page = false;
+		info->initialized = true;
+		info->vbo = vbo;
+
+		/* Let's check the restart area if this is a valid page */
+		if (!is_rst_page_hdr_valid(vbo, r_page))
+			goto check_result;
+		ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off));
+
+		if (!is_rst_area_valid(r_page))
+			goto check_result;
+
+		/*
+		 * We have a valid restart page header and restart area.
+		 * If chkdsk was run or we have no clients then we have
+		 * no more checking to do
+		 */
+		if (bchk || ra->client_idx[1] == LFS_NO_CLIENT_LE) {
+			info->valid_page = true;
+			goto check_result;
+		}
+
+		/* Read the entire restart area */
+		sys_page_size = le32_to_cpu(r_page->sys_page_size);
+		if (DefaultLogPageSize != sys_page_size) {
+			ntfs_free(r_page);
+			r_page = ntfs_zalloc(sys_page_size);
+			if (!r_page)
+				return -ENOMEM;
+
+			if (read_log_page(log, vbo,
+					  (struct RECORD_PAGE_HDR **)&r_page,
+					  &usa_error)) {
+				/* ignore any errors */
+				ntfs_free(r_page);
+				r_page = NULL;
+				continue;
+			}
+		}
+
+		if (is_client_area_valid(r_page, usa_error)) {
+			info->valid_page = true;
+			ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off));
+		}
+
+check_result:
+		/* If chkdsk was run then update the caller's values and return */
+		if (r_page->rhdr.sign == NTFS_CHKD_SIGNATURE) {
+			info->chkdsk_was_run = true;
+			info->last_lsn = le64_to_cpu(r_page->rhdr.lsn);
+			info->restart = true;
+			info->r_page = r_page;
+			return 0;
+		}
+
+		/* If we have a valid page then copy the values we need from it */
+		if (info->valid_page) {
+			info->last_lsn = le64_to_cpu(ra->current_lsn);
+			info->restart = true;
+			info->r_page = r_page;
+			return 0;
+		}
+	}
+
+	ntfs_free(r_page);
+
+	return 0;
+}
+
+/*
+ * log_init_pg_hdr
+ *
+ * init "log' from restart page header
+ */
+static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
+			    u32 page_size, u16 major_ver, u16 minor_ver)
+{
+	log->sys_page_size = sys_page_size;
+	log->sys_page_mask = sys_page_size - 1;
+	log->page_size = page_size;
+	log->page_mask = page_size - 1;
+	log->page_bits = blksize_bits(page_size);
+
+	log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
+	if (!log->clst_per_page)
+		log->clst_per_page = 1;
+
+	log->first_page = major_ver >= 2
+				  ? 0x22 * page_size
+				  : ((sys_page_size << 1) + (page_size << 1));
+	log->major_ver = major_ver;
+	log->minor_ver = minor_ver;
+}
+
+/*
+ * log_create
+ *
+ * init "log" in cases when we don't have a restart area to use
+ */
+static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+		       u32 open_log_count, bool wrapped, bool use_multi_page)
+{
+	log->l_size = l_size;
+	/* All file offsets must be quadword aligned */
+	log->file_data_bits = blksize_bits(l_size) - 3;
+	log->seq_num_mask = (8 << log->file_data_bits) - 1;
+	log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
+	log->seq_num = (last_lsn >> log->file_data_bits) + 2;
+	log->next_page = log->first_page;
+	log->oldest_lsn = log->seq_num << log->file_data_bits;
+	log->oldest_lsn_off = 0;
+	log->last_lsn = log->oldest_lsn;
+
+	log->l_flags |= NTFSLOG_NO_LAST_LSN | NTFSLOG_NO_OLDEST_LSN;
+
+	/* Set the correct flags for the I/O and indicate if we have wrapped */
+	if (wrapped)
+		log->l_flags |= NTFSLOG_WRAPPED;
+
+	if (use_multi_page)
+		log->l_flags |= NTFSLOG_MULTIPLE_PAGE_IO;
+
+	/* Compute the log page values */
+	log->data_off = QuadAlign(
+		offsetof(struct RECORD_PAGE_HDR, fixups) +
+		sizeof(short) * ((log->page_size >> SECTOR_SHIFT) + 1));
+	log->data_size = log->page_size - log->data_off;
+	log->record_header_len = sizeof(struct LFS_RECORD_HDR);
+
+	/* Remember the different page sizes for reservation */
+	log->reserved = log->data_size - log->record_header_len;
+
+	/* Compute the restart page values. */
+	log->ra_off = QuadAlign(
+		offsetof(struct RESTART_HDR, fixups) +
+		sizeof(short) * ((log->sys_page_size >> SECTOR_SHIFT) + 1));
+	log->restart_size = log->sys_page_size - log->ra_off;
+	log->ra_size = struct_size(log->ra, clients, 1);
+	log->current_openlog_count = open_log_count;
+
+	/*
+	 * The total available log file space is the number of
+	 * log file pages times the space available on each page
+	 */
+	log->total_avail_pages = log->l_size - log->first_page;
+	log->total_avail = log->total_avail_pages >> log->page_bits;
+
+	/*
+	 * We assume that we can't use the end of the page less than
+	 * the file record size
+	 * Then we won't need to reserve more than the caller asks for
+	 */
+	log->max_current_avail = log->total_avail * log->reserved;
+	log->total_avail = log->total_avail * log->data_size;
+	log->current_avail = log->max_current_avail;
+}
+
+/*
+ * log_create_ra
+ *
+ * This routine is called to fill a restart area from the values stored in 'log'
+ */
+static struct RESTART_AREA *log_create_ra(struct ntfs_log *log)
+{
+	struct CLIENT_REC *cr;
+	struct RESTART_AREA *ra = ntfs_zalloc(log->restart_size);
+
+	if (!ra)
+		return NULL;
+
+	ra->current_lsn = cpu_to_le64(log->last_lsn);
+	ra->log_clients = cpu_to_le16(1);
+	ra->client_idx[1] = LFS_NO_CLIENT_LE;
+	if (log->l_flags & NTFSLOG_MULTIPLE_PAGE_IO)
+		ra->flags = RESTART_SINGLE_PAGE_IO;
+	ra->seq_num_bits = cpu_to_le32(log->seq_num_bits);
+	ra->ra_len = cpu_to_le16(log->ra_size);
+	ra->client_off = cpu_to_le16(offsetof(struct RESTART_AREA, clients));
+	ra->l_size = cpu_to_le64(log->l_size);
+	ra->rec_hdr_len = cpu_to_le16(log->record_header_len);
+	ra->data_off = cpu_to_le16(log->data_off);
+	ra->open_log_count = cpu_to_le32(log->current_openlog_count + 1);
+
+	cr = ra->clients;
+
+	cr->prev_client = LFS_NO_CLIENT_LE;
+	cr->next_client = LFS_NO_CLIENT_LE;
+
+	return ra;
+}
+
+static u32 final_log_off(struct ntfs_log *log, u64 lsn, u32 data_len)
+{
+	u32 base_vbo = lsn << 3;
+	u32 final_log_off = (base_vbo & log->seq_num_mask) & ~log->page_mask;
+	u32 page_off = base_vbo & log->page_mask;
+	u32 tail = log->page_size - page_off;
+
+	page_off -= 1;
+
+	/* Add the length of the header */
+	data_len += log->record_header_len;
+
+	/*
+	 * If this lsn is contained this log page we are done
+	 * Otherwise we need to walk through several log pages
+	 */
+	if (data_len > tail) {
+		data_len -= tail;
+		tail = log->data_size;
+		page_off = log->data_off - 1;
+
+		for (;;) {
+			final_log_off = next_page_off(log, final_log_off);
+
+			/* We are done if the remaining bytes fit on this page */
+			if (data_len <= tail)
+				break;
+			data_len -= tail;
+		}
+	}
+
+	/*
+	 * We add the remaining bytes to our starting position on this page
+	 * and then add that value to the file offset of this log page
+	 */
+	return final_log_off + data_len + page_off;
+}
+
+static int next_log_lsn(struct ntfs_log *log, const struct LFS_RECORD_HDR *rh,
+			u64 *lsn)
+{
+	int err;
+	u64 this_lsn = le64_to_cpu(rh->this_lsn);
+	u32 vbo = lsn_to_vbo(log, this_lsn);
+	u32 end =
+		final_log_off(log, this_lsn, le32_to_cpu(rh->client_data_len));
+	u32 hdr_off = end & ~log->sys_page_mask;
+	u64 seq = this_lsn >> log->file_data_bits;
+	struct RECORD_PAGE_HDR *page = NULL;
+
+	/* Remember if we wrapped */
+	if (end <= vbo)
+		seq += 1;
+
+	/* log page header for this page */
+	err = read_log_page(log, hdr_off, &page, NULL);
+	if (err)
+		return err;
+
+	/*
+	 * If the lsn we were given was not the last lsn on this page,
+	 * then the starting offset for the next lsn is on a quad word
+	 * boundary following the last file offset for the current lsn
+	 * Otherwise the file offset is the start of the data on the next page
+	 */
+	if (this_lsn == le64_to_cpu(page->rhdr.lsn)) {
+		/* If we wrapped, we need to increment the sequence number */
+		hdr_off = next_page_off(log, hdr_off);
+		if (hdr_off == log->first_page)
+			seq += 1;
+
+		vbo = hdr_off + log->data_off;
+	} else {
+		vbo = QuadAlign(end);
+	}
+
+	/* Compute the lsn based on the file offset and the sequence count */
+	*lsn = vbo_to_lsn(log, vbo, seq);
+
+	/*
+	 * If this lsn is within the legal range for the file, we return true
+	 * Otherwise false indicates that there are no more lsn's
+	 */
+	if (!is_lsn_in_file(log, *lsn))
+		*lsn = 0;
+
+	ntfs_free(page);
+
+	return 0;
+}
+
+/*
+ * current_log_avail
+ *
+ * calculate the number of bytes available for log records
+ */
+static u32 current_log_avail(struct ntfs_log *log)
+{
+	u32 oldest_off, next_free_off, free_bytes;
+
+	if (log->l_flags & NTFSLOG_NO_LAST_LSN) {
+		/* The entire file is available */
+		return log->max_current_avail;
+	}
+
+	/*
+	 * If there is a last lsn the restart area then we know that we will
+	 * have to compute the free range
+	 * If there is no oldest lsn then start at the first page of the file
+	 */
+	oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN)
+			     ? log->first_page
+			     : (log->oldest_lsn_off & ~log->sys_page_mask);
+
+	/*
+	 * We will use the next log page offset to compute the next free page\
+	 * If we are going to reuse this page go to the next page
+	 * If we are at the first page then use the end of the file
+	 */
+	next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL)
+				? log->next_page + log->page_size
+			: log->next_page == log->first_page ? log->l_size
+							    : log->next_page;
+
+	/* If the two offsets are the same then there is no available space */
+	if (oldest_off == next_free_off)
+		return 0;
+	/*
+	 * If the free offset follows the oldest offset then subtract
+	 * this range from the total available pages
+	 */
+	free_bytes =
+		oldest_off < next_free_off
+			? log->total_avail_pages - (next_free_off - oldest_off)
+			: oldest_off - next_free_off;
+
+	free_bytes >>= log->page_bits;
+	return free_bytes * log->reserved;
+}
+
+static bool check_subseq_log_page(struct ntfs_log *log,
+				  const struct RECORD_PAGE_HDR *rp, u32 vbo,
+				  u64 seq)
+{
+	u64 lsn_seq;
+	const struct NTFS_RECORD_HEADER *rhdr = &rp->rhdr;
+	u64 lsn = le64_to_cpu(rhdr->lsn);
+
+	if (rhdr->sign == NTFS_FFFF_SIGNATURE || !rhdr->sign)
+		return false;
+
+	/*
+	 * If the last lsn on the page occurs was written after the page
+	 * that caused the original error then we have a fatal error
+	 */
+	lsn_seq = lsn >> log->file_data_bits;
+
+	/*
+	 * If the sequence number for the lsn the page is equal or greater
+	 * than lsn we expect, then this is a subsequent write
+	 */
+	return lsn_seq >= seq ||
+	       (lsn_seq == seq - 1 && log->first_page == vbo &&
+		vbo != (lsn_to_vbo(log, lsn) & ~log->page_mask));
+}
+
+/*
+ * last_log_lsn
+ *
+ * This routine walks through the log pages for a file, searching for the
+ * last log page written to the file
+ */
+static int last_log_lsn(struct ntfs_log *log)
+{
+	int err;
+	bool usa_error = false;
+	bool replace_page = false;
+	bool reuse_page = log->l_flags & NTFSLOG_REUSE_TAIL;
+	bool wrapped_file, wrapped;
+
+	u32 page_cnt = 1, page_pos = 1;
+	u32 page_off = 0, page_off1 = 0, saved_off = 0;
+	u32 final_off, second_off, final_off_prev = 0, second_off_prev = 0;
+	u32 first_file_off = 0, second_file_off = 0;
+	u32 part_io_count = 0;
+	u32 tails = 0;
+	u32 this_off, curpage_off, nextpage_off, remain_pages;
+
+	u64 expected_seq, seq_base = 0, lsn_base = 0;
+	u64 best_lsn, best_lsn1, best_lsn2;
+	u64 lsn_cur, lsn1, lsn2;
+	u64 last_ok_lsn = reuse_page ? log->last_lsn : 0;
+
+	u16 cur_pos, best_page_pos;
+
+	struct RECORD_PAGE_HDR *page = NULL;
+	struct RECORD_PAGE_HDR *tst_page = NULL;
+	struct RECORD_PAGE_HDR *first_tail = NULL;
+	struct RECORD_PAGE_HDR *second_tail = NULL;
+	struct RECORD_PAGE_HDR *tail_page = NULL;
+	struct RECORD_PAGE_HDR *second_tail_prev = NULL;
+	struct RECORD_PAGE_HDR *first_tail_prev = NULL;
+	struct RECORD_PAGE_HDR *page_bufs = NULL;
+	struct RECORD_PAGE_HDR *best_page;
+
+	if (log->major_ver >= 2) {
+		final_off = 0x02 * log->page_size;
+		second_off = 0x12 * log->page_size;
+
+		// 0x10 == 0x12 - 0x2
+		page_bufs = ntfs_malloc(log->page_size * 0x10);
+		if (!page_bufs)
+			return -ENOMEM;
+	} else {
+		second_off = log->first_page - log->page_size;
+		final_off = second_off - log->page_size;
+	}
+
+next_tail:
+	/* Read second tail page (at pos 3/0x12000) */
+	if (read_log_page(log, second_off, &second_tail, &usa_error) ||
+	    usa_error || second_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) {
+		ntfs_free(second_tail);
+		second_tail = NULL;
+		second_file_off = 0;
+		lsn2 = 0;
+	} else {
+		second_file_off = hdr_file_off(log, second_tail);
+		lsn2 = le64_to_cpu(second_tail->record_hdr.last_end_lsn);
+	}
+
+	/* Read first tail page (at pos 2/0x2000 ) */
+	if (read_log_page(log, final_off, &first_tail, &usa_error) ||
+	    usa_error || first_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) {
+		ntfs_free(first_tail);
+		first_tail = NULL;
+		first_file_off = 0;
+		lsn1 = 0;
+	} else {
+		first_file_off = hdr_file_off(log, first_tail);
+		lsn1 = le64_to_cpu(first_tail->record_hdr.last_end_lsn);
+	}
+
+	if (log->major_ver < 2) {
+		int best_page;
+
+		first_tail_prev = first_tail;
+		final_off_prev = first_file_off;
+		second_tail_prev = second_tail;
+		second_off_prev = second_file_off;
+		tails = 1;
+
+		if (!first_tail && !second_tail)
+			goto tail_read;
+
+		if (first_tail && second_tail)
+			best_page = lsn1 < lsn2 ? 1 : 0;
+		else if (first_tail)
+			best_page = 0;
+		else
+			best_page = 1;
+
+		page_off = best_page ? second_file_off : first_file_off;
+		seq_base = (best_page ? lsn2 : lsn1) >> log->file_data_bits;
+		goto tail_read;
+	}
+
+	best_lsn1 = first_tail ? base_lsn(log, first_tail, first_file_off) : 0;
+	best_lsn2 =
+		second_tail ? base_lsn(log, second_tail, second_file_off) : 0;
+
+	if (first_tail && second_tail) {
+		if (best_lsn1 > best_lsn2) {
+			best_lsn = best_lsn1;
+			best_page = first_tail;
+			this_off = first_file_off;
+		} else {
+			best_lsn = best_lsn2;
+			best_page = second_tail;
+			this_off = second_file_off;
+		}
+	} else if (first_tail) {
+		best_lsn = best_lsn1;
+		best_page = first_tail;
+		this_off = first_file_off;
+	} else if (second_tail) {
+		best_lsn = best_lsn2;
+		best_page = second_tail;
+		this_off = second_file_off;
+	} else {
+		goto tail_read;
+	}
+
+	best_page_pos = le16_to_cpu(best_page->page_pos);
+
+	if (!tails) {
+		if (best_page_pos == page_pos) {
+			seq_base = best_lsn >> log->file_data_bits;
+			saved_off = page_off = le32_to_cpu(best_page->file_off);
+			lsn_base = best_lsn;
+
+			memmove(page_bufs, best_page, log->page_size);
+
+			page_cnt = le16_to_cpu(best_page->page_count);
+			if (page_cnt > 1)
+				page_pos += 1;
+
+			tails = 1;
+		}
+	} else if (seq_base == (best_lsn >> log->file_data_bits) &&
+		   saved_off + log->page_size == this_off &&
+		   lsn_base < best_lsn &&
+		   (page_pos != page_cnt || best_page_pos == page_pos ||
+		    best_page_pos == 1) &&
+		   (page_pos >= page_cnt || best_page_pos == page_pos)) {
+		u16 bppc = le16_to_cpu(best_page->page_count);
+
+		saved_off += log->page_size;
+		lsn_base = best_lsn;
+
+		memmove(Add2Ptr(page_bufs, tails * log->page_size), best_page,
+			log->page_size);
+
+		tails += 1;
+
+		if (best_page_pos != bppc) {
+			page_cnt = bppc;
+			page_pos = best_page_pos;
+
+			if (page_cnt > 1)
+				page_pos += 1;
+		} else {
+			page_pos = page_cnt = 1;
+		}
+	} else {
+		ntfs_free(first_tail);
+		ntfs_free(second_tail);
+		goto tail_read;
+	}
+
+	ntfs_free(first_tail_prev);
+	first_tail_prev = first_tail;
+	final_off_prev = first_file_off;
+	first_tail = NULL;
+
+	ntfs_free(second_tail_prev);
+	second_tail_prev = second_tail;
+	second_off_prev = second_file_off;
+	second_tail = NULL;
+
+	final_off += log->page_size;
+	second_off += log->page_size;
+
+	if (tails < 0x10)
+		goto next_tail;
+tail_read:
+	first_tail = first_tail_prev;
+	final_off = final_off_prev;
+
+	second_tail = second_tail_prev;
+	second_off = second_off_prev;
+
+	page_cnt = page_pos = 1;
+
+	curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off)
+					       : log->next_page;
+
+	wrapped_file =
+		curpage_off == log->first_page &&
+		!(log->l_flags & (NTFSLOG_NO_LAST_LSN | NTFSLOG_REUSE_TAIL));
+
+	expected_seq = wrapped_file ? (log->seq_num + 1) : log->seq_num;
+
+	nextpage_off = curpage_off;
+
+next_page:
+	tail_page = NULL;
+	/* Read the next log page */
+	err = read_log_page(log, curpage_off, &page, &usa_error);
+
+	/* Compute the next log page offset the file */
+	nextpage_off = next_page_off(log, curpage_off);
+	wrapped = nextpage_off == log->first_page;
+
+	if (tails > 1) {
+		struct RECORD_PAGE_HDR *cur_page =
+			Add2Ptr(page_bufs, curpage_off - page_off);
+
+		if (curpage_off == saved_off) {
+			tail_page = cur_page;
+			goto use_tail_page;
+		}
+
+		if (page_off > curpage_off || curpage_off >= saved_off)
+			goto use_tail_page;
+
+		if (page_off1)
+			goto use_cur_page;
+
+		if (!err && !usa_error &&
+		    page->rhdr.sign == NTFS_RCRD_SIGNATURE &&
+		    cur_page->rhdr.lsn == page->rhdr.lsn &&
+		    cur_page->record_hdr.next_record_off ==
+			    page->record_hdr.next_record_off &&
+		    ((page_pos == page_cnt &&
+		      le16_to_cpu(page->page_pos) == 1) ||
+		     (page_pos != page_cnt &&
+		      le16_to_cpu(page->page_pos) == page_pos + 1 &&
+		      le16_to_cpu(page->page_count) == page_cnt))) {
+			cur_page = NULL;
+			goto use_tail_page;
+		}
+
+		page_off1 = page_off;
+
+use_cur_page:
+
+		lsn_cur = le64_to_cpu(cur_page->rhdr.lsn);
+
+		if (last_ok_lsn !=
+			    le64_to_cpu(cur_page->record_hdr.last_end_lsn) &&
+		    ((lsn_cur >> log->file_data_bits) +
+		     ((curpage_off <
+		       (lsn_to_vbo(log, lsn_cur) & ~log->page_mask))
+			      ? 1
+			      : 0)) != expected_seq) {
+			goto check_tail;
+		}
+
+		if (!is_log_record_end(cur_page)) {
+			tail_page = NULL;
+			last_ok_lsn = lsn_cur;
+			goto next_page_1;
+		}
+
+		log->seq_num = expected_seq;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+		log->last_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = cur_page->record_hdr.last_end_lsn;
+
+		if (log->record_header_len <=
+		    log->page_size -
+			    le16_to_cpu(cur_page->record_hdr.next_record_off)) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		if (wrapped_file)
+			log->l_flags |= NTFSLOG_WRAPPED;
+
+		last_ok_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn);
+		goto next_page_1;
+	}
+
+	/*
+	 * If we are at the expected first page of a transfer check to see
+	 * if either tail copy is at this offset
+	 * If this page is the last page of a transfer, check if we wrote
+	 * a subsequent tail copy
+	 */
+	if (page_cnt == page_pos || page_cnt == page_pos + 1) {
+		/*
+		 * Check if the offset matches either the first or second
+		 * tail copy. It is possible it will match both
+		 */
+		if (curpage_off == final_off)
+			tail_page = first_tail;
+
+		/*
+		 * If we already matched on the first page then
+		 * check the ending lsn's.
+		 */
+		if (curpage_off == second_off) {
+			if (!tail_page ||
+			    (second_tail &&
+			     le64_to_cpu(second_tail->record_hdr.last_end_lsn) >
+				     le64_to_cpu(first_tail->record_hdr
+							 .last_end_lsn))) {
+				tail_page = second_tail;
+			}
+		}
+	}
+
+use_tail_page:
+	if (tail_page) {
+		/* we have a candidate for a tail copy */
+		lsn_cur = le64_to_cpu(tail_page->record_hdr.last_end_lsn);
+
+		if (last_ok_lsn < lsn_cur) {
+			/*
+			 * If the sequence number is not expected,
+			 * then don't use the tail copy
+			 */
+			if (expected_seq != (lsn_cur >> log->file_data_bits))
+				tail_page = NULL;
+		} else if (last_ok_lsn > lsn_cur) {
+			/*
+			 * If the last lsn is greater than the one on
+			 * this page then forget this tail
+			 */
+			tail_page = NULL;
+		}
+	}
+
+	/* If we have an error on the current page, we will break of this loop */
+	if (err || usa_error)
+		goto check_tail;
+
+	/*
+	 * Done if the last lsn on this page doesn't match the previous known
+	 * last lsn or the sequence number is not expected
+	 */
+	lsn_cur = le64_to_cpu(page->rhdr.lsn);
+	if (last_ok_lsn != lsn_cur &&
+	    expected_seq != (lsn_cur >> log->file_data_bits)) {
+		goto check_tail;
+	}
+
+	/*
+	 * Check that the page position and page count values are correct
+	 * If this is the first page of a transfer the position must be 1
+	 * and the count will be unknown
+	 */
+	if (page_cnt == page_pos) {
+		if (page->page_pos != cpu_to_le16(1) &&
+		    (!reuse_page || page->page_pos != page->page_count)) {
+			/*
+			 * If the current page is the first page we are
+			 * looking at and we are reusing this page then
+			 * it can be either the first or last page of a
+			 * transfer. Otherwise it can only be the first.
+			 */
+			goto check_tail;
+		}
+	} else if (le16_to_cpu(page->page_count) != page_cnt ||
+		   le16_to_cpu(page->page_pos) != page_pos + 1) {
+		/*
+		 * The page position better be 1 more than the last page
+		 * position and the page count better match
+		 */
+		goto check_tail;
+	}
+
+	/*
+	 * We have a valid page the file and may have a valid page
+	 * the tail copy area
+	 * If the tail page was written after the page the file then
+	 * break of the loop
+	 */
+	if (tail_page &&
+	    le64_to_cpu(tail_page->record_hdr.last_end_lsn) > lsn_cur) {
+		/* Remember if we will replace the page */
+		replace_page = true;
+		goto check_tail;
+	}
+
+	tail_page = NULL;
+
+	if (is_log_record_end(page)) {
+		/*
+		 * Since we have read this page we know the sequence number
+		 * is the same as our expected value
+		 */
+		log->seq_num = expected_seq;
+		log->last_lsn = le64_to_cpu(page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = page->record_hdr.last_end_lsn;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+
+		/*
+		 * If there is room on this page for another header then
+		 * remember we want to reuse the page
+		 */
+		if (log->record_header_len <=
+		    log->page_size -
+			    le16_to_cpu(page->record_hdr.next_record_off)) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		/* Remember if we wrapped the log file */
+		if (wrapped_file)
+			log->l_flags |= NTFSLOG_WRAPPED;
+	}
+
+	/*
+	 * Remember the last page count and position.
+	 * Also remember the last known lsn
+	 */
+	page_cnt = le16_to_cpu(page->page_count);
+	page_pos = le16_to_cpu(page->page_pos);
+	last_ok_lsn = le64_to_cpu(page->rhdr.lsn);
+
+next_page_1:
+
+	if (wrapped) {
+		expected_seq += 1;
+		wrapped_file = 1;
+	}
+
+	curpage_off = nextpage_off;
+	ntfs_free(page);
+	page = NULL;
+	reuse_page = 0;
+	goto next_page;
+
+check_tail:
+	if (tail_page) {
+		log->seq_num = expected_seq;
+		log->last_lsn = le64_to_cpu(tail_page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = tail_page->record_hdr.last_end_lsn;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+
+		if (log->page_size -
+			    le16_to_cpu(
+				    tail_page->record_hdr.next_record_off) >=
+		    log->record_header_len) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		if (wrapped)
+			log->l_flags |= NTFSLOG_WRAPPED;
+	}
+
+	/* Remember that the partial IO will start at the next page */
+	second_off = nextpage_off;
+
+	/*
+	 * If the next page is the first page of the file then update
+	 * the sequence number for log records which begon the next page
+	 */
+	if (wrapped)
+		expected_seq += 1;
+
+	/*
+	 * If we have a tail copy or are performing single page I/O we can
+	 * immediately look at the next page
+	 */
+	if (replace_page || (log->ra->flags & RESTART_SINGLE_PAGE_IO)) {
+		page_cnt = 2;
+		page_pos = 1;
+		goto check_valid;
+	}
+
+	if (page_pos != page_cnt)
+		goto check_valid;
+	/*
+	 * If the next page causes us to wrap to the beginning of the log
+	 * file then we know which page to check next.
+	 */
+	if (wrapped) {
+		page_cnt = 2;
+		page_pos = 1;
+		goto check_valid;
+	}
+
+	cur_pos = 2;
+
+next_test_page:
+	ntfs_free(tst_page);
+	tst_page = NULL;
+
+	/* Walk through the file, reading log pages */
+	err = read_log_page(log, nextpage_off, &tst_page, &usa_error);
+
+	/*
+	 * If we get a USA error then assume that we correctly found
+	 * the end of the original transfer
+	 */
+	if (usa_error)
+		goto file_is_valid;
+
+	/*
+	 * If we were able to read the page, we examine it to see if it
+	 * is the same or different Io block
+	 */
+	if (err)
+		goto next_test_page_1;
+
+	if (le16_to_cpu(tst_page->page_pos) == cur_pos &&
+	    check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) {
+		page_cnt = le16_to_cpu(tst_page->page_count) + 1;
+		page_pos = le16_to_cpu(tst_page->page_pos);
+		goto check_valid;
+	} else {
+		goto file_is_valid;
+	}
+
+next_test_page_1:
+
+	nextpage_off = next_page_off(log, curpage_off);
+	wrapped = nextpage_off == log->first_page;
+
+	if (wrapped) {
+		expected_seq += 1;
+		page_cnt = 2;
+		page_pos = 1;
+	}
+
+	cur_pos += 1;
+	part_io_count += 1;
+	if (!wrapped)
+		goto next_test_page;
+
+check_valid:
+	/* Skip over the remaining pages this transfer */
+	remain_pages = page_cnt - page_pos - 1;
+	part_io_count += remain_pages;
+
+	while (remain_pages--) {
+		nextpage_off = next_page_off(log, curpage_off);
+		wrapped = nextpage_off == log->first_page;
+
+		if (wrapped)
+			expected_seq += 1;
+	}
+
+	/* Call our routine to check this log page */
+	ntfs_free(tst_page);
+	tst_page = NULL;
+
+	err = read_log_page(log, nextpage_off, &tst_page, &usa_error);
+	if (!err && !usa_error &&
+	    check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+file_is_valid:
+
+	/* We have a valid file */
+	if (page_off1 || tail_page) {
+		struct RECORD_PAGE_HDR *tmp_page;
+
+		if (sb_rdonly(log->ni->mi.sbi->sb)) {
+			err = -EROFS;
+			goto out;
+		}
+
+		if (page_off1) {
+			tmp_page = Add2Ptr(page_bufs, page_off1 - page_off);
+			tails -= (page_off1 - page_off) / log->page_size;
+			if (!tail_page)
+				tails -= 1;
+		} else {
+			tmp_page = tail_page;
+			tails = 1;
+		}
+
+		while (tails--) {
+			u64 off = hdr_file_off(log, tmp_page);
+
+			if (!page) {
+				page = ntfs_malloc(log->page_size);
+				if (!page)
+					return -ENOMEM;
+			}
+
+			/*
+			 * Correct page and copy the data from this page
+			 * into it and flush it to disk
+			 */
+			memcpy(page, tmp_page, log->page_size);
+
+			/* Fill last flushed lsn value flush the page */
+			if (log->major_ver < 2)
+				page->rhdr.lsn = page->record_hdr.last_end_lsn;
+			else
+				page->file_off = 0;
+
+			page->page_pos = page->page_count = cpu_to_le16(1);
+
+			ntfs_fix_pre_write(&page->rhdr, log->page_size);
+
+			err = ntfs_sb_write_run(log->ni->mi.sbi,
+						&log->ni->file.run, off, page,
+						log->page_size);
+
+			if (err)
+				goto out;
+
+			if (part_io_count && second_off == off) {
+				second_off += log->page_size;
+				part_io_count -= 1;
+			}
+
+			tmp_page = Add2Ptr(tmp_page, log->page_size);
+		}
+	}
+
+	if (part_io_count) {
+		if (sb_rdonly(log->ni->mi.sbi->sb)) {
+			err = -EROFS;
+			goto out;
+		}
+	}
+
+out:
+	ntfs_free(second_tail);
+	ntfs_free(first_tail);
+	ntfs_free(page);
+	ntfs_free(tst_page);
+	ntfs_free(page_bufs);
+
+	return err;
+}
+
+/*
+ * read_log_rec_buf
+ *
+ * copies a log record from the file to a buffer
+ * The log record may span several log pages and may even wrap the file
+ */
+static int read_log_rec_buf(struct ntfs_log *log,
+			    const struct LFS_RECORD_HDR *rh, void *buffer)
+{
+	int err;
+	struct RECORD_PAGE_HDR *ph = NULL;
+	u64 lsn = le64_to_cpu(rh->this_lsn);
+	u32 vbo = lsn_to_vbo(log, lsn) & ~log->page_mask;
+	u32 off = lsn_to_page_off(log, lsn) + log->record_header_len;
+	u32 data_len = le32_to_cpu(rh->client_data_len);
+
+	/*
+	 * While there are more bytes to transfer,
+	 * we continue to attempt to perform the read
+	 */
+	for (;;) {
+		bool usa_error;
+		u32 tail = log->page_size - off;
+
+		if (tail >= data_len)
+			tail = data_len;
+
+		data_len -= tail;
+
+		err = read_log_page(log, vbo, &ph, &usa_error);
+		if (err)
+			goto out;
+
+		/*
+		 * The last lsn on this page better be greater or equal
+		 * to the lsn we are copying
+		 */
+		if (lsn > le64_to_cpu(ph->rhdr.lsn)) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		memcpy(buffer, Add2Ptr(ph, off), tail);
+
+		...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 04/10] fs/ntfs3: Add file operations and implementation

[Konstantin K. <alm...@pa...>]

This adds file operations and implementation

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/dir.c     |  594 +++++++++
 fs/ntfs3/file.c    | 1130 ++++++++++++++++
 fs/ntfs3/frecord.c | 3071 ++++++++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/namei.c   |  578 +++++++++
 fs/ntfs3/record.c  |  609 +++++++++
 fs/ntfs3/run.c     | 1111 ++++++++++++++++
 6 files changed, 7093 insertions(+)
 create mode 100644 fs/ntfs3/dir.c
 create mode 100644 fs/ntfs3/file.c
 create mode 100644 fs/ntfs3/frecord.c
 create mode 100644 fs/ntfs3/namei.c
 create mode 100644 fs/ntfs3/record.c
 create mode 100644 fs/ntfs3/run.c

diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
new file mode 100644
index 000000000..9ec6012c4
--- /dev/null
+++ b/fs/ntfs3/dir.c
@@ -0,0 +1,594 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ *  directory handling functions for ntfs-based filesystems
+ *
+ */
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/iversion.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/*
+ * Convert little endian utf16 to nls string
+ */
+int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni,
+		      u8 *buf, int buf_len)
+{
+	int ret, uni_len, warn;
+	const __le16 *ip;
+	u8 *op;
+	struct nls_table *nls = sbi->options.nls;
+
+	static_assert(sizeof(wchar_t) == sizeof(__le16));
+
+	if (!nls) {
+		/* utf16 -> utf8 */
+		ret = utf16s_to_utf8s((wchar_t *)uni->name, uni->len,
+				      UTF16_LITTLE_ENDIAN, buf, buf_len);
+		buf[ret] = '\0';
+		return ret;
+	}
+
+	ip = uni->name;
+	op = buf;
+	uni_len = uni->len;
+	warn = 0;
+
+	while (uni_len--) {
+		u16 ec;
+		int charlen;
+		char dump[5];
+
+		if (buf_len < NLS_MAX_CHARSET_SIZE) {
+			ntfs_warn(sbi->sb,
+				  "filename was truncated while converting.");
+			break;
+		}
+
+		ec = le16_to_cpu(*ip++);
+		charlen = nls->uni2char(ec, op, buf_len);
+
+		if (charlen > 0) {
+			op += charlen;
+			buf_len -= charlen;
+			continue;
+		}
+
+		*op++ = '_';
+		buf_len -= 1;
+		if (warn)
+			continue;
+
+		warn = 1;
+		hex_byte_pack(&dump[0], ec >> 8);
+		hex_byte_pack(&dump[2], ec);
+		dump[4] = 0;
+
+		ntfs_err(sbi->sb, "failed to convert \"%s\" to %s", dump,
+			 nls->charset);
+	}
+
+	*op = '\0';
+	return op - buf;
+}
+
+// clang-format off
+#define PLANE_SIZE	0x00010000
+
+#define SURROGATE_PAIR	0x0000d800
+#define SURROGATE_LOW	0x00000400
+#define SURROGATE_BITS	0x000003ff
+// clang-format on
+
+/*
+ * modified version of put_utf16 from fs/nls/nls_base.c
+ * is sparse warnings free
+ */
+static inline void put_utf16(wchar_t *s, unsigned int c,
+			     enum utf16_endian endian)
+{
+	static_assert(sizeof(wchar_t) == sizeof(__le16));
+	static_assert(sizeof(wchar_t) == sizeof(__be16));
+
+	switch (endian) {
+	default:
+		*s = (wchar_t)c;
+		break;
+	case UTF16_LITTLE_ENDIAN:
+		*(__le16 *)s = __cpu_to_le16(c);
+		break;
+	case UTF16_BIG_ENDIAN:
+		*(__be16 *)s = __cpu_to_be16(c);
+		break;
+	}
+}
+
+/*
+ * modified version of 'utf8s_to_utf16s' allows to
+ * detect -ENAMETOOLONG without writing out of expected maximum
+ */
+static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian,
+			    wchar_t *pwcs, int maxout)
+{
+	u16 *op;
+	int size;
+	unicode_t u;
+
+	op = pwcs;
+	while (inlen > 0 && *s) {
+		if (*s & 0x80) {
+			size = utf8_to_utf32(s, inlen, &u);
+			if (size < 0)
+				return -EINVAL;
+			s += size;
+			inlen -= size;
+
+			if (u >= PLANE_SIZE) {
+				if (maxout < 2)
+					return -ENAMETOOLONG;
+
+				u -= PLANE_SIZE;
+				put_utf16(op++,
+					  SURROGATE_PAIR |
+						  ((u >> 10) & SURROGATE_BITS),
+					  endian);
+				put_utf16(op++,
+					  SURROGATE_PAIR | SURROGATE_LOW |
+						  (u & SURROGATE_BITS),
+					  endian);
+				maxout -= 2;
+			} else {
+				if (maxout < 1)
+					return -ENAMETOOLONG;
+
+				put_utf16(op++, u, endian);
+				maxout--;
+			}
+		} else {
+			if (maxout < 1)
+				return -ENAMETOOLONG;
+
+			put_utf16(op++, *s++, endian);
+			inlen--;
+			maxout--;
+		}
+	}
+	return op - pwcs;
+}
+
+/*
+ * Convert input string to utf16
+ *
+ * name, name_len - input name
+ * uni, max_ulen - destination memory
+ * endian - endian of target utf16 string
+ *
+ * This function is called:
+ * - to create ntfs name
+ * - to create symlink
+ *
+ * returns utf16 string length or error (if negative)
+ */
+int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
+		      struct cpu_str *uni, u32 max_ulen,
+		      enum utf16_endian endian)
+{
+	int ret, slen;
+	const u8 *end;
+	struct nls_table *nls = sbi->options.nls;
+	u16 *uname = uni->name;
+
+	static_assert(sizeof(wchar_t) == sizeof(u16));
+
+	if (!nls) {
+		/* utf8 -> utf16 */
+		ret = _utf8s_to_utf16s(name, name_len, endian, uname, max_ulen);
+		uni->len = ret;
+		return ret;
+	}
+
+	for (ret = 0, end = name + name_len; name < end; ret++, name += slen) {
+		if (ret >= max_ulen)
+			return -ENAMETOOLONG;
+
+		slen = nls->char2uni(name, end - name, uname + ret);
+		if (!slen)
+			return -EINVAL;
+		if (slen < 0)
+			return slen;
+	}
+
+#ifdef __BIG_ENDIAN
+	if (endian == UTF16_LITTLE_ENDIAN) {
+		int i = ret;
+
+		while (i--) {
+			__cpu_to_le16s(uname);
+			uname++;
+		}
+	}
+#else
+	if (endian == UTF16_BIG_ENDIAN) {
+		int i = ret;
+
+		while (i--) {
+			__cpu_to_be16s(uname);
+			uname++;
+		}
+	}
+#endif
+
+	uni->len = ret;
+	return ret;
+}
+
+/* helper function */
+struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni,
+			   struct ntfs_fnd *fnd)
+{
+	int err = 0;
+	struct super_block *sb = dir->i_sb;
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	struct ntfs_inode *ni = ntfs_i(dir);
+	struct NTFS_DE *e;
+	int diff;
+	struct inode *inode = NULL;
+	struct ntfs_fnd *fnd_a = NULL;
+
+	if (!fnd) {
+		fnd_a = fnd_get();
+		if (!fnd_a) {
+			err = -ENOMEM;
+			goto out;
+		}
+		fnd = fnd_a;
+	}
+
+	err = indx_find(&ni->dir, ni, NULL, uni, 0, sbi, &diff, &e, fnd);
+
+	if (err)
+		goto out;
+
+	if (diff) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	inode = ntfs_iget5(sb, &e->ref, uni);
+	if (!IS_ERR(inode) && is_bad_inode(inode)) {
+		iput(inode);
+		err = -EINVAL;
+	}
+out:
+	fnd_put(fnd_a);
+
+	return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode;
+}
+
+static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+			       const struct NTFS_DE *e, u8 *name,
+			       struct dir_context *ctx)
+{
+	const struct ATTR_FILE_NAME *fname;
+	unsigned long ino;
+	int name_len;
+	u32 dt_type;
+
+	fname = Add2Ptr(e, sizeof(struct NTFS_DE));
+
+	if (fname->type == FILE_NAME_DOS)
+		return 0;
+
+	if (!mi_is_ref(&ni->mi, &fname->home))
+		return 0;
+
+	ino = ino_get(&e->ref);
+
+	if (ino == MFT_REC_ROOT)
+		return 0;
+
+	/* Skip meta files ( unless option to show metafiles is set ) */
+	if (!sbi->options.showmeta && ntfs_is_meta_file(sbi, ino))
+		return 0;
+
+	if (sbi->options.nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN))
+		return 0;
+
+	name_len = ntfs_utf16_to_nls(sbi, (struct le_str *)&fname->name_len,
+				     name, PATH_MAX);
+	if (name_len <= 0) {
+		ntfs_warn(sbi->sb, "failed to convert name for inode %lx.",
+			  ino);
+		return 0;
+	}
+
+	dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+
+	return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
+}
+
+/*
+ * ntfs_read_hdr
+ *
+ * helper function 'ntfs_readdir'
+ */
+static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+			 const struct INDEX_HDR *hdr, u64 vbo, u64 pos,
+			 u8 *name, struct dir_context *ctx)
+{
+	int err;
+	const struct NTFS_DE *e;
+	u32 e_size;
+	u32 end = le32_to_cpu(hdr->used);
+	u32 off = le32_to_cpu(hdr->de_off);
+
+	for (;; off += e_size) {
+		if (off + sizeof(struct NTFS_DE) > end)
+			return -1;
+
+		e = Add2Ptr(hdr, off);
+		e_size = le16_to_cpu(e->size);
+		if (e_size < sizeof(struct NTFS_DE) || off + e_size > end)
+			return -1;
+
+		if (de_is_last(e))
+			return 0;
+
+		/* Skip already enumerated*/
+		if (vbo + off < pos)
+			continue;
+
+		if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME)
+			return -1;
+
+		ctx->pos = vbo + off;
+
+		/* Submit the name to the filldir callback. */
+		err = ntfs_filldir(sbi, ni, e, name, ctx);
+		if (err)
+			return err;
+	}
+}
+
+/*
+ * file_operations::iterate_shared
+ *
+ * Use non sorted enumeration.
+ * We have an example of broken volume where sorted enumeration
+ * counts each name twice
+ */
+static int ntfs_readdir(struct file *file, struct dir_context *ctx)
+{
+	const struct INDEX_ROOT *root;
+	u64 vbo;
+	size_t bit;
+	loff_t eod;
+	int err = 0;
+	struct inode *dir = file_inode(file);
+	struct ntfs_inode *ni = ntfs_i(dir);
+	struct super_block *sb = dir->i_sb;
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	loff_t i_size = i_size_read(dir);
+	u32 pos = ctx->pos;
+	u8 *name = NULL;
+	struct indx_node *node = NULL;
+	u8 index_bits = ni->dir.index_bits;
+
+	/* name is a buffer of PATH_MAX length */
+	static_assert(NTFS_NAME_LEN * 4 < PATH_MAX);
+
+	eod = i_size + sbi->record_size;
+
+	if (pos >= eod)
+		return 0;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	/* allocate PATH_MAX bytes */
+	name = __getname();
+	if (!name)
+		return -ENOMEM;
+
+	if (!ni->mi_loaded && ni->attr_list.size) {
+		/*
+		 * directory inode is locked for read
+		 * load all subrecords to avoid 'write' access to 'ni' during
+		 * directory reading
+		 */
+		ni_lock(ni);
+		if (!ni->mi_loaded && ni->attr_list.size) {
+			err = ni_load_all_mi(ni);
+			if (!err)
+				ni->mi_loaded = true;
+		}
+		ni_unlock(ni);
+		if (err)
+			goto out;
+	}
+
+	root = indx_get_root(&ni->dir, ni, NULL, NULL);
+	if (!root) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (pos >= sbi->record_size) {
+		bit = (pos - sbi->record_size) >> index_bits;
+	} else {
+		err = ntfs_read_hdr(sbi, ni, &root->ihdr, 0, pos, name, ctx);
+		if (err)
+			goto out;
+		bit = 0;
+	}
+
+	if (!i_size) {
+		ctx->pos = eod;
+		goto out;
+	}
+
+	for (;;) {
+		vbo = (u64)bit << index_bits;
+		if (vbo >= i_size) {
+			ctx->pos = eod;
+			goto out;
+		}
+
+		err = indx_used_bit(&ni->dir, ni, &bit);
+		if (err)
+			goto out;
+
+		if (bit == MINUS_ONE_T) {
+			ctx->pos = eod;
+			goto out;
+		}
+
+		vbo = (u64)bit << index_bits;
+		if (vbo >= i_size) {
+			ntfs_inode_err(dir, "Looks like your dir is corrupt");
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
+				&node);
+		if (err)
+			goto out;
+
+		err = ntfs_read_hdr(sbi, ni, &node->index->ihdr,
+				    vbo + sbi->record_size, pos, name, ctx);
+		if (err)
+			goto out;
+
+		bit += 1;
+	}
+
+out:
+
+	__putname(name);
+	put_indx_node(node);
+
+	if (err == -ENOENT) {
+		err = 0;
+		ctx->pos = pos;
+	}
+
+	return err;
+}
+
+static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
+			  size_t *files)
+{
+	int err = 0;
+	struct ntfs_inode *ni = ntfs_i(dir);
+	struct NTFS_DE *e = NULL;
+	struct INDEX_ROOT *root;
+	struct INDEX_HDR *hdr;
+	const struct ATTR_FILE_NAME *fname;
+	u32 e_size, off, end;
+	u64 vbo = 0;
+	size_t drs = 0, fles = 0, bit = 0;
+	loff_t i_size = ni->vfs_inode.i_size;
+	struct indx_node *node = NULL;
+	u8 index_bits = ni->dir.index_bits;
+
+	if (is_empty)
+		*is_empty = true;
+
+	root = indx_get_root(&ni->dir, ni, NULL, NULL);
+	if (!root)
+		return -EINVAL;
+
+	hdr = &root->ihdr;
+
+	for (;;) {
+		end = le32_to_cpu(hdr->used);
+		off = le32_to_cpu(hdr->de_off);
+
+		for (; off + sizeof(struct NTFS_DE) <= end; off += e_size) {
+			e = Add2Ptr(hdr, off);
+			e_size = le16_to_cpu(e->size);
+			if (e_size < sizeof(struct NTFS_DE) ||
+			    off + e_size > end)
+				break;
+
+			if (de_is_last(e))
+				break;
+
+			fname = de_get_fname(e);
+			if (!fname)
+				continue;
+
+			if (fname->type == FILE_NAME_DOS)
+				continue;
+
+			if (is_empty) {
+				*is_empty = false;
+				if (!dirs && !files)
+					goto out;
+			}
+
+			if (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY)
+				drs += 1;
+			else
+				fles += 1;
+		}
+
+		if (vbo >= i_size)
+			goto out;
+
+		err = indx_used_bit(&ni->dir, ni, &bit);
+		if (err)
+			goto out;
+
+		if (bit == MINUS_ONE_T)
+			goto out;
+
+		vbo = (u64)bit << index_bits;
+		if (vbo >= i_size)
+			goto out;
+
+		err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
+				&node);
+		if (err)
+			goto out;
+
+		hdr = &node->index->ihdr;
+		bit += 1;
+		vbo = (u64)bit << ni->dir.idx2vbn_bits;
+	}
+
+out:
+	put_indx_node(node);
+	if (dirs)
+		*dirs = drs;
+	if (files)
+		*files = fles;
+
+	return err;
+}
+
+bool dir_is_empty(struct inode *dir)
+{
+	bool is_empty = false;
+
+	ntfs_dir_count(dir, &is_empty, NULL, NULL);
+
+	return is_empty;
+}
+
+const struct file_operations ntfs_dir_operations = {
+	.llseek = generic_file_llseek,
+	.read = generic_read_dir,
+	.iterate_shared = ntfs_readdir,
+	.fsync = generic_file_fsync,
+	.open = ntfs_file_open,
+};
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
new file mode 100644
index 000000000..b4369c61a
--- /dev/null
+++ b/fs/ntfs3/file.c
@@ -0,0 +1,1130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ *  regular file handling primitives for ntfs-based filesystems
+ */
+#include <linux/backing-dev.h>
+#include <linux/buffer_head.h>
+#include <linux/compat.h>
+#include <linux/falloc.h>
+#include <linux/fiemap.h>
+#include <linux/msdos_fs.h> /* FAT_IOCTL_XXX */
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
+{
+	struct fstrim_range __user *user_range;
+	struct fstrim_range range;
+	struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	user_range = (struct fstrim_range __user *)arg;
+	if (copy_from_user(&range, user_range, sizeof(range)))
+		return -EFAULT;
+
+	range.minlen = max_t(u32, range.minlen, q->limits.discard_granularity);
+
+	err = ntfs_trim_fs(sbi, &range);
+	if (err < 0)
+		return err;
+
+	if (copy_to_user(user_range, &range, sizeof(range)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+	u32 __user *user_attr = (u32 __user *)arg;
+
+	switch (cmd) {
+	case FAT_IOCTL_GET_ATTRIBUTES:
+		return put_user(le32_to_cpu(ntfs_i(inode)->std_fa), user_attr);
+
+	case FAT_IOCTL_GET_VOLUME_ID:
+		return put_user(sbi->volume.ser_num, user_attr);
+
+	case FITRIM:
+		return ntfs_ioctl_fitrim(sbi, arg);
+	}
+	return -ENOTTY; /* Inappropriate ioctl for device */
+}
+
+#ifdef CONFIG_COMPAT
+static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+
+{
+	return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+/*
+ * inode_operations::getattr
+ */
+int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+		 struct kstat *stat, u32 request_mask, u32 flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct ntfs_inode *ni = ntfs_i(inode);
+
+	if (is_compressed(ni))
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+
+	if (is_encrypted(ni))
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+
+	stat->attributes_mask |= STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED;
+
+	generic_fillattr(mnt_userns, inode, stat);
+
+	stat->result_mask |= STATX_BTIME;
+	stat->btime = ni->i_crtime;
+
+	return 0;
+}
+
+static int ntfs_extend_initialized_size(struct file *file,
+					struct ntfs_inode *ni,
+					const loff_t valid,
+					const loff_t new_valid)
+{
+	struct inode *inode = &ni->vfs_inode;
+	struct address_space *mapping = inode->i_mapping;
+	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+	loff_t pos = valid;
+	int err;
+
+	if (is_resident(ni)) {
+		ni->i_valid = new_valid;
+		return 0;
+	}
+
+	WARN_ON(is_compressed(ni));
+	WARN_ON(valid >= new_valid);
+
+	for (;;) {
+		u32 zerofrom, len;
+		struct page *page;
+		void *fsdata;
+		u8 bits;
+		CLST vcn, lcn, clen;
+
+		if (is_sparsed(ni)) {
+			bits = sbi->cluster_bits;
+			vcn = pos >> bits;
+
+			err = attr_data_get_block(ni, vcn, 0, &lcn, &clen,
+						  NULL);
+			if (err)
+				goto out;
+
+			if (lcn == SPARSE_LCN) {
+				loff_t vbo = (loff_t)vcn << bits;
+				loff_t to = vbo + ((loff_t)clen << bits);
+
+				if (to <= new_valid) {
+					ni->i_valid = to;
+					pos = to;
+					goto next;
+				}
+
+				if (vbo < pos) {
+					pos = vbo;
+				} else {
+					to = (new_valid >> bits) << bits;
+					if (pos < to) {
+						ni->i_valid = to;
+						pos = to;
+						goto next;
+					}
+				}
+			}
+		}
+
+		zerofrom = pos & (PAGE_SIZE - 1);
+		len = PAGE_SIZE - zerofrom;
+
+		if (pos + len > new_valid)
+			len = new_valid - pos;
+
+		err = pagecache_write_begin(file, mapping, pos, len, 0, &page,
+					    &fsdata);
+		if (err)
+			goto out;
+
+		zero_user_segment(page, zerofrom, PAGE_SIZE);
+
+		/* this function in any case puts page*/
+		err = pagecache_write_end(file, mapping, pos, len, len, page,
+					  fsdata);
+		if (err < 0)
+			goto out;
+		pos += len;
+
+next:
+		if (pos >= new_valid)
+			break;
+
+		balance_dirty_pages_ratelimited(mapping);
+		cond_resched();
+	}
+
+	mark_inode_dirty(inode);
+
+	return 0;
+
+out:
+	ni->i_valid = valid;
+	ntfs_inode_warn(inode, "failed to extend initialized size to %llx.",
+			new_valid);
+	return err;
+}
+
+/*
+ * ntfs_sparse_cluster
+ *
+ * Helper function to zero a new allocated clusters
+ */
+void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn,
+			 CLST len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+	u64 vbo = (u64)vcn << sbi->cluster_bits;
+	u64 bytes = (u64)len << sbi->cluster_bits;
+	u32 blocksize = 1 << inode->i_blkbits;
+	pgoff_t idx0 = page0 ? page0->index : -1;
+	loff_t vbo_clst = vbo & sbi->cluster_mask_inv;
+	loff_t end = ntfs_up_cluster(sbi, vbo + bytes);
+	pgoff_t idx = vbo_clst >> PAGE_SHIFT;
+	u32 from = vbo_clst & (PAGE_SIZE - 1);
+	pgoff_t idx_end = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	loff_t page_off;
+	u32 to;
+	bool partial;
+	struct page *page;
+
+	for (; idx < idx_end; idx += 1, from = 0) {
+		page = idx == idx0 ? page0 : grab_cache_page(mapping, idx);
+
+		if (!page)
+			continue;
+
+		page_off = (loff_t)idx << PAGE_SHIFT;
+		to = (page_off + PAGE_SIZE) > end ? (end - page_off)
+						  : PAGE_SIZE;
+		partial = false;
+
+		if ((from || PAGE_SIZE != to) &&
+		    likely(!page_has_buffers(page))) {
+			create_empty_buffers(page, blocksize, 0);
+			if (!page_has_buffers(page)) {
+				ntfs_inode_err(
+					inode,
+					"failed to allocate page buffers.");
+				/*err = -ENOMEM;*/
+				goto unlock_page;
+			}
+		}
+
+		if (page_has_buffers(page)) {
+			struct buffer_head *head, *bh;
+			u32 bh_off = 0;
+
+			bh = head = page_buffers(page);
+			do {
+				u32 bh_next = bh_off + blocksize;
+
+				if (from <= bh_off && bh_next <= to) {
+					set_buffer_uptodate(bh);
+					mark_buffer_dirty(bh);
+				} else if (!buffer_uptodate(bh)) {
+					partial = true;
+				}
+				bh_off = bh_next;
+			} while (head != (bh = bh->b_this_page));
+		}
+
+		zero_user_segment(page, from, to);
+
+		if (!partial) {
+			if (!PageUptodate(page))
+				SetPageUptodate(page);
+			set_page_dirty(page);
+		}
+
+unlock_page:
+		if (idx != idx0) {
+			unlock_page(page);
+			put_page(page);
+		}
+		cond_resched();
+	}
+	mark_inode_dirty(inode);
+}
+
+/*
+ * file_operations::mmap
+ */
+static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct ntfs_inode *ni = ntfs_i(inode);
+	u64 to, from = ((u64)vma->vm_pgoff << PAGE_SHIFT);
+	bool rw = vma->vm_flags & VM_WRITE;
+	int err;
+
+	if (is_encrypted(ni)) {
+		ntfs_inode_warn(inode,
+				"mmap is not supported for encrypted files");
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (!rw)
+		goto do_map;
+
+	if (is_compressed(ni)) {
+		ntfs_inode_warn(
+			inode,
+			"mmap(write) is not supported for compressed files");
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	to = min_t(loff_t, i_size_read(inode),
+		   from + vma->vm_end - vma->vm_start);
+
+	if (is_sparsed(ni)) {
+		/* allocate clusters for rw map */
+		struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+		CLST vcn, lcn, len;
+		CLST end = bytes_to_cluster(sbi, to);
+		bool new;
+
+		for (vcn = from >> sbi->cluster_bits; vcn < end; vcn += len) {
+			err = attr_data_get_block(ni, vcn, 1, &lcn, &len, &new);
+			if (err)
+				goto out;
+			if (!new)
+				continue;
+			ntfs_sparse_cluster(inode, NULL, vcn, 1);
+		}
+	}
+
+	if (ni->i_valid < to) {
+		inode_lock(inode);
+		err = ntfs_extend_initialized_size(file, ni, ni->i_valid, to);
+		inode_unlock(inode);
+		if (err)
+			goto out;
+	}
+
+do_map:
+	err = generic_file_mmap(file, vma);
+out:
+	return err;
+}
+
+static int ntfs_extend(struct inode *inode, loff_t pos, size_t count,
+		       struct file *file)
+{
+	struct ntfs_inode *ni = ntfs_i(inode);
+	struct address_space *mapping = inode->i_mapping;
+	loff_t end = pos + count;
+	bool extend_init = file && pos > ni->i_valid;
+	int err;
+
+	if (end <= inode->i_size && !extend_init)
+		return 0;
+
+	/*mark rw ntfs as dirty. it will be cleared at umount*/
+	ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_DIRTY);
+
+	if (end > inode->i_size) {
+		err = ntfs_set_size(inode, end);
+		if (err)
+			goto out;
+		inode->i_size = end;
+	}
+
+	if (extend_init && !is_compressed(ni)) {
+		err = ntfs_extend_initialized_size(file, ni, ni->i_valid, pos);
+		if (err)
+			goto out;
+	} else {
+		err = 0;
+	}
+
+	inode->i_ctime = inode->i_mtime = current_time(inode);
+	mark_inode_dirty(inode);
+
+	if (IS_SYNC(inode)) {
+		int err2;
+
+		err = filemap_fdatawrite_range(mapping, pos, end - 1);
+		err2 = sync_mapping_buffers(mapping);
+		if (!err)
+			err = err2;
+		err2 = write_inode_now(inode, 1);
+		if (!err)
+			err = err2;
+		if (!err)
+			err = filemap_fdatawait_range(mapping, pos, end - 1);
+	}
+
+out:
+	return err;
+}
+
+static int ntfs_truncate(struct inode *inode, loff_t new_size)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ntfs_inode *ni = ntfs_i(inode);
+	int err, dirty = 0;
+	u64 new_valid;
+
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+
+	if (is_compressed(ni)) {
+		if (ni->i_valid > new_size)
+			ni->i_valid = new_size;
+	} else {
+		err = block_truncate_page(inode->i_mapping, new_size,
+					  ntfs_get_block);
+		if (err)
+			return err;
+	}
+
+	new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size));
+
+	ni_lock(ni);
+
+	truncate_setsize(inode, new_size);
+
+	down_write(&ni->file.run_lock);
+	err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size,
+			    &new_valid, true, NULL);
+	up_write(&ni->file.run_lock);
+
+	if (new_valid < ni->i_valid)
+		ni->i_valid = new_valid;
+
+	ni_unlock(ni);
+
+	ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE;
+	inode->i_ctime = inode->i_mtime = current_time(inode);
+	if (!IS_DIRSYNC(inode)) {
+		dirty = 1;
+	} else {
+		err = ntfs_sync_inode(inode);
+		if (err)
+			return err;
+	}
+
+	if (dirty)
+		mark_inode_dirty(inode);
+
+	/*ntfs_flush_inodes(inode->i_sb, inode, NULL);*/
+
+	return 0;
+}
+
+/*
+ * Preallocate space for a file. This implements ntfs's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests 'len' bytes at 'vbo'. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
+{
+	struct inode *inode = file->f_mapping->host;
+	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;
+	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))
+		return -EOPNOTSUPP;
+
+	ntfs_set_state(sbi, NTFS_DIRTY_DIRTY);
+
+	inode_lock(inode);
+	i_size = inode->i_size;
+
+	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
+		/* should never be here, see ntfs_file_open*/
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (!is_sparsed(ni) && !is_compressed(ni)) {
+			ntfs_inode_warn(
+				inode,
+				"punch_hole only for sparsed/compressed files");
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
+		err = filemap_write_and_wait_range(inode->i_mapping, vbo,
+						   end - 1);
+		if (err)
+			goto out;
+
+		err = filemap_write_and_wait_range(inode->i_mapping, end,
+						   LLONG_MAX);
+		if (err)
+			goto out;
+
+		truncate_pagecache(inode, vbo_down);
+
+		ni_lock(ni);
+		err = attr_punch_hole(ni, vbo, 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);
+		if (err)
+			goto out;
+
+		/*
+		 * 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);
+		if (err)
+			goto out;
+
+		truncate_pagecache(inode, vbo_down);
+
+		ni_lock(ni);
+		err = attr_collapse_range(ni, vbo, len);
+		ni_unlock(ni);
+	} else {
+		/*
+		 * normal file: allocate clusters, do not change 'valid' size
+		 */
+		err = ntfs_set_size(inode, max(end, i_size));
+		if (err)
+			goto out;
+
+		if (is_sparsed(ni) || is_compressed(ni)) {
+			CLST vcn_v = ni->i_valid >> sbi->cluster_bits;
+			CLST vcn = vbo >> sbi->cluster_bits;
+			CLST cend = bytes_to_cluster(sbi, end);
+			CLST lcn, clen;
+			bool new;
+
+			/*
+			 * allocate but not zero new clusters (see below comments)
+			 * this breaks security (one can read unused on-disk areas)
+			 * zeroing these clusters may be too long
+			 * may be we should check here for root rights?
+			 */
+			for (; vcn < cend; vcn += clen) {
+				err = attr_data_get_block(ni, vcn, cend - vcn,
+							  &lcn, &clen, &new);
+				if (err)
+					goto out;
+				if (!new || vcn >= vcn_v)
+					continue;
+
+				/*
+				 * Unwritten area
+				 * NTFS is not able to store several unwritten areas
+				 * Activate 'ntfs_sparse_cluster' to zero new allocated clusters
+				 *
+				 * Dangerous in case:
+				 * 1G of sparsed clusters + 1 cluster of data =>
+				 * valid_size == 1G + 1 cluster
+				 * fallocate(1G) will zero 1G and this can be very long
+				 * xfstest 016/086 will fail without 'ntfs_sparse_cluster'
+				 */
+				/*ntfs_sparse_cluster(inode, NULL, vcn,
+				 *		    min(vcn_v - vcn, clen));
+				 */
+			}
+		}
+
+		if (mode & FALLOC_FL_KEEP_SIZE) {
+			ni_lock(ni);
+			/*true - keep preallocated*/
+			err = attr_set_size(ni, ATTR_DATA, NULL, 0,
+					    &ni->file.run, i_size, &ni->i_valid,
+					    true, NULL);
+			ni_unlock(ni);
+		}
+	}
+
+	if (!err) {
+		inode->i_ctime = inode->i_mtime = current_time(inode);
+		mark_inode_dirty(inode);
+	}
+out:
+	if (err == -EFBIG)
+		err = -ENOSPC;
+
+	inode_unlock(inode);
+	return err;
+}
+
+/*
+ * inode_operations::setattr
+ */
+int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		  struct iattr *attr)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	struct inode *inode = d_inode(dentry);
+	struct ntfs_inode *ni = ntfs_i(inode);
+	u32 ia_valid = attr->ia_valid;
+	umode_t mode = inode->i_mode;
+	int err;
+
+	if (sbi->options.no_acs_rules) {
+		/* "no access rules" - force any changes of time etc. */
+		attr->ia_valid |= ATTR_FORCE;
+		/* and disable for editing some attributes */
+		attr->ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE);
+		ia_valid = attr->ia_valid;
+	}
+
+	err = setattr_prepare(mnt_userns, dentry, attr);
+	if (err)
+		goto out;
+
+	if (ia_valid & ATTR_SIZE) {
+		loff_t oldsize = inode->i_size;
+
+		if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
+			/* should never be here, see ntfs_file_open*/
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+		inode_dio_wait(inode);
+
+		if (attr->ia_size < oldsize)
+			err = ntfs_truncate(inode, attr->ia_size);
+		else if (attr->ia_size > oldsize)
+			err = ntfs_extend(inode, attr->ia_size, 0, NULL);
+
+		if (err)
+			goto out;
+
+		ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+	}
+
+	setattr_copy(mnt_userns, inode, attr);
+
+	if (mode != inode->i_mode) {
+		err = ntfs_acl_chmod(mnt_userns, inode);
+		if (err)
+			goto out;
+
+		/* linux 'w' -> windows 'ro' */
+		if (0222 & inode->i_mode)
+			ni->std_fa &= ~FILE_ATTRIBUTE_READONLY;
+		else
+			ni->std_fa |= FILE_ATTRIBUTE_READONLY;
+	}
+
+	mark_inode_dirty(inode);
+out:
+	return err;
+}
+
+static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	ssize_t err;
+	size_t count = iov_iter_count(iter);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct ntfs_inode *ni = ntfs_i(inode);
+
+	if (is_encrypted(ni)) {
+		ntfs_inode_warn(inode, "encrypted i/o not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (is_compressed(ni) && (iocb->ki_flags & IOCB_DIRECT)) {
+		ntfs_inode_warn(inode, "direct i/o + compressed not supported");
+		return -EOPNOTSUPP;
+	}
+
+#ifndef CONFIG_NTFS3_LZX_XPRESS
+	if (ni->ni_flags & NI_FLAG_COMPRESSED_MASK) {
+		ntfs_inode_warn(
+			inode,
+			"activate CONFIG_NTFS3_LZX_XPRESS to read external compressed files");
+		return -EOPNOTSUPP;
+	}
+#endif
+
+	if (is_dedup(ni)) {
+		ntfs_inode_warn(inode, "read deduplicated not supported");
+		return -EOPNOTSUPP;
+	}
+
+	err = count ? generic_file_read_iter(iocb, iter) : 0;
+
+	return err;
+}
+
+/* returns array of locked pages */
+static int ntfs_get_frame_pages(struct address_space *mapping, pgoff_t index,
+				struct page **pages, u32 pages_per_frame,
+				bool *frame_uptodate)
+{
+	gfp_t gfp_mask = mapping_gfp_mask(mapping);
+	u32 npages;
+
+	*frame_uptodate = true;
+
+	for (npages = 0; npages < pages_per_frame; npages++, index++) {
+		struct page *page;
+
+		page = find_or_create_page(mapping, index, gfp_mask);
+		if (!page) {
+			while (npages--) {
+				page = pages[npages];
+				unlock_page(page);
+				put_page(page);
+			}
+
+			return -ENOMEM;
+		}
+
+		if (!PageUptodate(page))
+			*frame_uptodate = false;
+
+		pages[npages] = page;
+	}
+
+	return 0;
+}
+
+/*helper for ntfs_file_write_iter (compressed files)*/
+static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	int err;
+	struct file *file = iocb->ki_filp;
+	size_t count = iov_iter_count(from);
+	loff_t pos = iocb->ki_pos;
+	struct inode *inode = file_inode(file);
+	loff_t i_size = inode->i_size;
+	struct address_space *mapping = inode->i_mapping;
+	struct ntfs_inode *ni = ntfs_i(inode);
+	u64 valid = ni->i_valid;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct page *page, **pages = NULL;
+	size_t written = 0;
+	u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits;
+	u32 frame_size = 1u << frame_bits;
+	u32 pages_per_frame = frame_size >> PAGE_SHIFT;
+	u32 ip, off;
+	CLST frame;
+	u64 frame_vbo;
+	pgoff_t index;
+	bool frame_uptodate;
+
+	if (frame_size < PAGE_SIZE) {
+		/*
+		 * frame_size == 8K if cluster 512
+		 * frame_size == 64K if cluster 4096
+		 */
+		ntfs_inode_warn(inode, "page size is bigger than frame size");
+		return -EOPNOTSUPP;
+	}
+
+	pages = ntfs_malloc(pages_per_frame * sizeof(struct page *));
+	if (!pages)
+		return -ENOMEM;
+
+	current->backing_dev_info = inode_to_bdi(inode);
+	err = file_remove_privs(file);
+	if (err)
+		goto out;
+
+	err = file_update_time(file);
+	if (err)
+		goto out;
+
+	/* zero range [valid : pos) */
+	while (valid < pos) {
+		CLST lcn, clen;
+
+		frame = valid >> frame_bits;
+		frame_vbo = valid & ~(frame_size - 1);
+		off = valid & (frame_size - 1);
+
+		err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 0, &lcn,
+					  &clen, NULL);
+		if (err)
+			goto out;
+
+		if (lcn == SPARSE_LCN) {
+			ni->i_valid = valid =
+				frame_vbo + ((u64)clen << sbi->cluster_bits);
+			continue;
+		}
+
+		/* Load full frame */
+		err = ntfs_get_frame_pages(mapping, frame_vbo >> PAGE_SHIFT,
+					   pages, pages_per_frame,
+					   &frame_uptodate);
+		if (err)
+			goto out;
+
+		if (!frame_uptodate && off) {
+			err = ni_read_frame(ni, frame_vbo, pages,
+					    pages_per_frame);
+			if (err) {
+				for (ip = 0; ip < pages_per_frame; ip++) {
+					page = pages[ip];
+					unlock_page(page);
+					put_page(page);
+				}
+				goto out;
+			}
+		}
+
+		ip = off >> PAGE_SHIFT;
+		off = offset_in_page(valid);
+		for (; ip < pages_per_frame; ip++, off = 0) {
+			page = pages[ip];
+			zero_user_segment(page, off, PAGE_SIZE);
+			flush_dcache_page(page);
+			SetPageUptodate(page);
+		}
+
+		ni_lock(ni);
+		err = ni_write_frame(ni, pages, pages_per_frame);
+		ni_unlock(ni);
+
+		for (ip = 0; ip < pages_per_frame; ip++) {
+			page = pages[ip];
+			SetPageUptodate(page);
+			unlock_page(page);
+			put_page(page);
+		}
+
+		if (err)
+			goto out;
+
+		ni->i_valid = valid = frame_vbo + frame_size;
+	}
+
+	/* copy user data [pos : pos + count) */
+	while (count) {
+		size_t copied, bytes;
+
+		off = pos & (frame_size - 1);
+		bytes = frame_size - off;
+		if (bytes > count)
+			bytes = count;
+
+		frame = pos >> frame_bits;
+		frame_vbo = pos & ~(frame_size - 1);
+		index = frame_vbo >> PAGE_SHIFT;
+
+		if (unlikely(iov_iter_fault_in_readable(from, bytes))) {
+			err = -EFAULT;
+			goto out;
+		}
+
+		/* Load full frame */
+		err = ntfs_get_frame_pages(mapping, index, pages,
+					   pages_per_frame, &frame_uptodate);
+		if (err)
+			goto out;
+
+		if (!frame_uptodate) {
+			loff_t to = pos + bytes;
+
+			if (off || (to < i_size && (to & (frame_size - 1)))) {
+				err = ni_read_frame(ni, frame_vbo, pages,
+						    pages_per_frame);
+				if (err) {
+					for (ip = 0; ip < pages_per_frame;
+					     ip++) {
+						page = pages[ip];
+						unlock_page(page);
+						put_page(page);
+					}
+					goto out;
+				}
+			}
+		}
+
+		WARN_ON(!bytes);
+		copied = 0;
+		ip = off >> PAGE_SHIFT;
+		off = offset_in_page(pos);
+
+		/* copy user data to pages */
+		for (;;) {
+			size_t cp, tail = PAGE_SIZE - off;
+
+			page = pages[ip];
+			cp = copy_page_from_iter_atomic(page, off,
+							min(tail, bytes), from);
+			flush_dcache_page(page);
+
+			copied += cp;
+			bytes -= cp;
+			if (!bytes || !cp)
+				break;
+
+			if (cp < tail) {
+				off += cp;
+			} else {
+				ip++;
+				off = 0;
+			}
+		}
+
+		ni_lock(ni);
+		err = ni_write_frame(ni, pages, pages_per_frame);
+		ni_unlock(ni);
+
+		for (ip = 0; ip < pages_per_frame; ip++) {
+			page = pages[ip];
+			ClearPageDirty(page);
+			SetPageUptodate(page);
+			unlock_page(page);
+			put_page(page);
+		}
+
+		if (err)
+			goto out;
+
+		/*
+		 * We can loop for a long time in here. Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
+
+		pos += copied;
+		written += copied;
+
+		count = iov_iter_count(from);
+	}
+
+out:
+	ntfs_free(pages);
+
+	current->backing_dev_info = NULL;
+
+	if (err < 0)
+		return err;
+
+	iocb->ki_pos += written;
+	if (iocb->ki_pos > ni->i_valid)
+		ni->i_valid = iocb->ki_pos;
+
+	return written;
+}
+
+/*
+ * file_operations::write_iter
+ */
+static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	ssize_t ret;
+	struct ntfs_inode *ni = ntfs_i(inode);
+
+	if (is_encrypted(ni)) {
+		ntfs_inode_warn(inode, "encrypted i/o not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (is_compressed(ni) && (iocb->ki_flags & IOCB_DIRECT)) {
+		ntfs_inode_warn(inode, "direct i/o + compressed not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (is_dedup(ni)) {
+		ntfs_inode_warn(inode, "write into deduplicated not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
+
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
+		/* should never be here, see ntfs_file_open*/
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	ret = ntfs_extend(inode, iocb->ki_pos, ret, file);
+	if (ret)
+		goto out;
+
+	ret = is_compressed(ni) ? ntfs_compress_write(iocb, from)
+				: __generic_file_write_iter(iocb, from);
+
+out:
+	inode_unlock(inode);
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+
+	return ret;
+}
+
+/*
+ * file_operations::open
+ */
+int ntfs_file_open(struct inode *inode, struct file *file)
+{
+	struct ntfs_inode *ni = ntfs_i(inode);
+
+	if (unlikely((is_compressed(ni) || is_encrypted(ni)) &&
+		     (file->f_flags & O_DIRECT))) {
+		return -EOPNOTSUPP;
+	}
+
+	/* Decompress "external compressed" file if opened for rw */
+	if ((ni->ni_flags & NI_FLAG_COMPRESSED_MASK) &&
+	    (file->f_flags & (O_WRONLY | O_RDWR | O_TRUNC))) {
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+		int err = ni_decompress_file(ni);
+
+		if (err)
+			return err;
+#else
+		ntfs_inode_warn(
+			inode,
+			"activate CONFIG_NTFS3_LZX_XPRESS to write external compressed files");
+		return -EOPNOTSUPP;
+#endif
+	}
+
+	return generic_file_open(inode, file);
+}
+
+/*
+ * file_operations::release
+ */
+static int ntfs_file_release(struct inode *inode, struct file *file)
+{
+	struct ntfs_inode *ni = ntfs_i(inode);
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	int err = 0;
+
+	/* if we are the last writer on the inode, drop the block reservation */
+	if (sbi->options.prealloc && ((file->f_mode & FMODE_WRITE) &&
+				      atomic_read(&inode->i_writecount) == 1)) {
+		ni_lock(ni);
+		down_write(&ni->file.run_lock);
+
+		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
+				    inode->i_size, &ni->i_valid, false, NULL);
+
+		up_write(&ni->file.run_lock);
+		ni_unlock(ni);
+	}
+	return err;
+}
+
+/* file_operations::fiemap */
+int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		__u64 start, __u64 len)
+{
+	int err;
+	struct ntfs_inode *ni = ntfs_i(inode);
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
+		return -EOPNOTSUPP;
+
+	ni_lock(ni);
+
+	err = ni_fiemap(ni, fieinfo, start, len);
+
+	ni_unlock(ni);
+
+	return err;
+}
+
+const struct inode_operations ntfs_file_inode_operations = {
+	.getattr = ntfs_getattr,
+	.setattr = ntfs3_setattr,
+	.listxattr = ntfs_listxattr,
+	.permission = ntfs_permission,
+	.get_acl = ntfs_get_acl,
+	.set_acl = ntfs_set_acl,
+	.fiemap = ntfs_fiemap,
+};
+
+const struct file_operations ntfs_file_operations = {
+	.llseek = generic_file_llseek,
+	.read_iter = ntfs_file_read_iter,
+	.write_iter = ntfs_file_write_iter,
+	.unlocked_ioctl = ntfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = ntfs_compat_ioctl,
+#endif
+	.splice_read = generic_file_splice_read,
+	.mmap = ntfs_file_mmap,
+	.open = ntfs_file_open,
+	.fsync = generic_file_fsync,
+	.splice_write = iter_file_splice_write,
+	.fallocate = ntfs_fallocate,
+	.release = ntfs_file_release,
+};
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
new file mode 100644
index 000000000..c3121bf9c
--- /dev/null
+++ b/fs/ntfs3/frecord.c
@@ -0,0 +1,3071 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fiemap.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+#include <linux/vmalloc.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+#include "lib/lib.h"
+#endif
+
+static struct mft_inode *ni_ins_mi(struct ntfs_inode *ni, struct rb_root *tree,
+				   CLST ino, struct rb_node *ins)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *pr = NULL;
+
+	while (*p) {
+		struct mft_inode *mi;
+
+		pr = *p;
+		mi = rb_entry(pr, struct mft_inode, node);
+		if (mi->rno > ino)
+			p = &pr->rb_left;
+		else if (mi->rno < ino)
+			p = &pr->rb_right;
+		else
+			return mi;
+	}
+
+	if (!ins)
+		return NULL;
+
+	rb_link_node(ins, pr, p);
+	rb_insert_color(ins, tree);
+	return rb_entry(ins, struct mft_inode, node);
+}
+
+/*
+ * ni_find_mi
+ *
+ * finds mft_inode by record number
+ */
+static struct mft_inode *ni_find_mi(struct ntfs_inode *ni, CLST rno)
+{
+	return ni_ins_mi(ni, &ni->mi_tree, rno, NULL);
+}
+
+/*
+ * ni_add_mi
+ *
+ * adds new mft_inode into ntfs_inode
+ */
+static void ni_add_mi(struct ntfs_inode *ni, struct mft_inode *mi)
+{
+	ni_ins_mi(ni, &ni->mi_tree, mi->rno, &mi->node);
+}
+
+/*
+ * ni_remove_mi
+ *
+ * removes mft_inode from ntfs_inode
+ */
+void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi)
+{
+	rb_erase(&mi->node, &ni->mi_tree);
+}
+
+/*
+ * ni_std
+ *
+ * returns pointer into std_info from primary record
+ */
+struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni)
+{
+	const struct ATTRIB *attr;
+
+	attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
+	return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO))
+		    : NULL;
+}
+
+/*
+ * ni_std5
+ *
+ * returns pointer into std_info from primary record
+ */
+struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni)
+{
+	const struct ATTRIB *attr;
+
+	attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
+
+	return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5))
+		    : NULL;
+}
+
+/*
+ * ni_clear
+ *
+ * clears resources allocated by ntfs_inode
+ */
+void ni_clear(struct ntfs_inode *ni)
+{
+	struct rb_node *node;
+
+	if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec))
+		ni_delete_all(ni);
+
+	al_destroy(ni);
+
+	for (node = rb_first(&ni->mi_tree); node;) {
+		struct rb_node *next = rb_next(node);
+		struct mft_inode *mi = rb_entry(node, struct mft_inode, node);
+
+		rb_erase(node, &ni->mi_tree);
+		mi_put(mi);
+		node = next;
+	}
+
+	/* bad inode always has mode == S_IFREG */
+	if (ni->ni_flags & NI_FLAG_DIR)
+		indx_clear(&ni->dir);
+	else {
+		run_close(&ni->file.run);
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+		if (ni->file.offs_page) {
+			/* on-demand allocated page for offsets */
+			put_page(ni->file.offs_page);
+			ni->file.offs_page = NULL;
+		}
+#endif
+	}
+
+	mi_clear(&ni->mi);
+}
+
+/*
+ * ni_load_mi_ex
+ *
+ * finds mft_inode by record number.
+ */
+int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi)
+{
+	int err;
+	struct mft_inode *r;
+
+	r = ni_find_mi(ni, rno);
+	if (r)
+		goto out;
+
+	err = mi_get(ni->mi.sbi, rno, &r);
+	if (err)
+		return err;
+
+	ni_add_mi(ni, r);
+
+out:
+	if (mi)
+		*mi = r;
+	return 0;
+}
+
+/*
+ * ni_load_mi
+ *
+ * load mft_inode corresponded list_entry
+ */
+int ni_load_mi(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
+	       struct mft_inode **mi)
+{
+	CLST rno;
+
+	if (!le) {
+		*mi = &ni->mi;
+		return 0;
+	}
+
+	rno = ino_get(&le->ref);
+	if (rno == ni->mi.rno) {
+		*mi = &ni->mi;
+		return 0;
+	}
+	return ni_load_mi_ex(ni, rno, mi);
+}
+
+/*
+ * ni_find_attr
+ *
+ * returns attribute and record this attribute belongs to
+ */
+struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr,
+			    struct ATTR_LIST_ENTRY **le_o, enum ATTR_TYPE type,
+			    const __le16 *name, u8 name_len, const CLST *vcn,
+			    struct mft_inode **mi)
+{
+	struct ATTR_LIST_ENTRY *le;
+	struct mft_inode *m;
+
+	if (!ni->attr_list.size ||
+	    (!name_len && (type == ATTR_LIST || type == ATTR_STD))) {
+		if (le_o)
+			*le_o = NULL;
+		if (mi)
+			*mi = &ni->mi;
+
+		/* Look for required attribute in primary record */
+		return mi_find_attr(&ni->mi, attr, type, name, name_len, NULL);
+	}
+
+	/* first look for list entry of required type */
+	le = al_find_ex(ni, le_o ? *le_o : NULL, type, name, name_len, vcn);
+	if (!le)
+		return NULL;
+
+	if (le_o)
+		*le_o = le;
+
+	/* Load record that contains this attribute */
+	if (ni_load_mi(ni, le, &m))
+		return NULL;
+
+	/* Look for required attribute */
+	attr = mi_find_attr(m, NULL, type, name, name_len, &le->id);
+
+	if (!attr)
+		goto out;
+
+	if (!attr->non_res) {
+		if (vcn && *vcn)
+			goto out;
+	} else if (!vcn) {
+		if (attr->nres.svcn)
+			goto out;
+	} else if (le64_to_cpu(attr->nres.svcn) > *vcn ||
+		   *vcn > le64_to_cpu(attr->nres.evcn)) {
+		goto out;
+	}
+
+	if (mi)
+		*mi = m;
+	return attr;
+
+out:
+	ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR);
+	return NULL;
+}
+
+/*
+ * ni_enum_attr_ex
+ *
+ * enumerates attributes in ntfs_inode
+ */
+struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr,
+			       struct ATTR_LIST_ENTRY **le,
+			       struct mft_inode **mi)
+{
+	struct mft_inode *mi2;
+	struct ATTR_LIST_ENTRY *le2;
+
+	/* Do we have an attribute list? */
+	if (!ni->attr_list.size) {
+		*le = NULL;
+		if (mi)
+			*mi = &ni->mi;
+		/* Enum attributes in primary record */
+		return mi_enum_attr(&ni->mi, attr);
+	}
+
+	/* get next list entry */
+	le2 = *le = al_enumerate(ni, attr ? *le : NULL);
+	if (!le2)
+		return NULL;
+
+	/* Load record that contains the required attribute */
+	if (ni_load_mi(ni, le2, &mi2))
+		return NULL;
+
+	if (mi)
+		*mi = mi2;
+
+	/* Find attribute in loaded record */
+	return rec_find_attr_le(mi2, le2);
+}
+
+/*
+ * ni_load_attr
+ *
+ * loads attribute that contains given vcn
+ */
+struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
+			    const __le16 *name, u8 name_len, CLST vcn,
+			    struct mft_inode **pmi)
+{
+	struct ATTR_LIST_ENTRY *le;
+	struct ATTRIB *attr;
+	struct mft_inode *mi;
+	struct ATTR_LIST_ENTRY *next;
+
+	if (!ni->attr_list.size) {
+		if (pmi)
+			*pmi = &ni->mi;
+		return mi_find_attr(&ni->mi, NULL, type, name, name_len, NULL);
+	}
+
+	le = al_find_ex(ni, NULL, type, name, name_len, NULL);
+	if (!le)
+		return NULL;
+
+	/*
+	 * Unfortunately ATTR_LIST_ENTRY contains only start vcn
+	 * So to find the ATTRIB segment that contains 'vcn' we should
+	 * enumerate some entries
+	 */
+	if (vcn) {
+		for (;; le = next) {
+			next = al_find_ex(ni, le, type, name, name_len, NULL);
+			if (!next || le64_to_cpu(next->vcn) > vcn)
+				break;
+		}
+	}
+
+	if (ni_load_mi(ni, le, &mi))
+		return NULL;
+
+	if (pmi)
+		*pmi = mi;
+
+	attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id);
+	if (!attr)
+		return NULL;
+
+	if (!attr->non_res)
+		return attr;
+
+	if (le64_to_cpu(attr->nres.svcn) <= vcn &&
+	    vcn <= le64_to_cpu(attr->nres.evcn))
+		return attr;
+
+	return NULL;
+}
+
+/*
+ * ni_load_all_mi
+ *
+ * loads all subrecords
+ */
+int ni_load_all_mi(struct ntfs_inode *ni)
+{
+	int err;
+	struct ATTR_LIST_ENTRY *le;
+
+	if (!ni->attr_list.size)
+		return 0;
+
+	le = NULL;
+
+	while ((le = al_enumerate(ni, le))) {
+		CLST rno = ino_get(&le->ref);
+
+		if (rno == ni->mi.rno)
+			continue;
+
+		err = ni_load_mi_ex(ni, rno, NULL);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/*
+ * ni_add_subrecord
+ *
+ * allocate + format + attach a new subrecord
+ */
+bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi)
+{
+	struct mft_inode *m;
+
+	m = ntfs_zalloc(sizeof(struct mft_inode));
+	if (!m)
+		return false;
+
+	if (mi_format_new(m, ni->mi.sbi, rno, 0, ni->mi.rno == MFT_REC_MFT)) {
+		mi_put(m);
+		return false;
+	}
+
+	mi_get_ref(&ni->mi, &m->mrec->parent_ref);
+
+	ni_add_mi(ni, m);
+	*mi = m;
+	return true;
+}
+
+/*
+ * ni_remove_attr
+ *
+ * removes all attributes for the given type/name/id
+ */
+int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		   const __le16 *name, size_t name_len, bool base_only,
+		   const __le16 *id)
+{
+	int err;
+	struct ATTRIB *attr;
+	struct ATTR_LIST_ENTRY *le;
+	struct mft_inode *mi;
+	u32 type_in;
+	int diff;
+
+	if (base_only || type == ATTR_LIST || !ni->attr_list.size) {
+		attr = mi_find_attr(&ni->mi, NULL, type, name, name_len, id);
+		if (!attr)
+			return -ENOENT;
+
+		mi_remove_attr(&ni->mi, attr);
+		return 0;
+	}
+
+	type_in = le32_to_cpu(type);
+	le = NULL;
+
+	for (;;) {
+		le = al_enumerate(ni, le);
+		if (!le)
+			return 0;
+
+next_le2:
+		diff = le32_to_cpu(le->type) - type_in;
+		if (diff < 0)
+			continue;
+
+		if (diff > 0)
+			return 0;
+
+		if (le->name_len != name_len)
+			continue;
+
+		if (name_len &&
+		    memcmp(le_name(le), name, name_len * sizeof(short)))
+			continue;
+
+		if (id && le->id != *id)
+			continue;
+		err = ni_load_mi(ni, le, &mi);
+		if (err)
+			return err;
+
+		al_remove_le(ni, le);
+
+		attr = mi_find_attr(mi, NULL, type, name, name_len, id);
+		if (!attr)
+			return -ENOENT;
+
+		mi_remove_attr(mi, attr);
+
+		if (PtrOffset(ni->attr_list.le, le) >= ni->attr_list.size)
+			return 0;
+		goto next_le2;
+	}
+}
+
+/*
+ * ni_ins_new_attr
+ *
+ * inserts the attribute into record
+ * Returns not full constructed attribute or NULL if not possible to create
+ */
+static struct ATTRIB *ni_ins_new_attr(struct ntfs_inode *ni,
+				      struct mft_inode *mi,
+				      struct ATTR_LIST_ENTRY *le,
+				      enum ATTR_TYPE type, const __le16 *name,
+				      u8 name_len, u32 asize, u16 name_off,
+				      CLST svcn)
+{
+	int err;
+	struct ATTRIB *attr;
+	bool le_added = false;
+	struct MFT_REF ref;
+
+	mi_get_ref(mi, &ref);
+
+	if (type != ATTR_LIST && !le && ni->attr_list.size) {
+		err = al_add_le(ni, type, name, name_len, svcn, cpu_to_le16(-1),
+				&ref, &le);
+		if (err) {
+			/* no memory or no space */
+			return NULL;
+		}
+		le_added = true;
+
+		/*
+		 * al_add_le -> attr_set_size (list) -> ni_expand_list
+		 * which moves some attributes out of primary record
+		 * this means that name may point into moved memory
+		 * reinit 'name' from le
+		 */
+		name = le->name;
+	}
+
+	attr = mi_insert_attr(mi, type, name, name_len, asize, name_off);
+	if (!attr) {
+		if (le_added)
+			al_remove_le(ni, le);
+		return NULL;
+	}
+
+	if (type == ATTR_LIST) {
+		/*attr list is not in list entry array*/
+		goto out;
+	}
+
+	if (!le)
+		goto out;
+
+	/* Update ATTRIB Id and record reference */
+	le->id = attr->id;
+	ni->attr_list.dirty = true;
+	le->ref = ref;
+
+out:
+	return attr;
+}
+
+/*
+ * random write access to sparsed or compressed file may result to
+ * not optimized packed runs.
+ * Here it is the place to optimize it
+ */
+static int ni_repack(struct ntfs_inode *ni)
+{
+	int err = 0;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct mft_inode *mi, *mi_p = NULL;
+	struct ATTRIB *attr = NULL, *attr_p;
+	struct ATTR_LIST_ENTRY *le = NULL, *le_p;
+	CLST alloc = 0;
+	u8 cluster_bits = sbi->cluster_bits;
+	CLST svcn, evcn = 0, svcn_p, evcn_p, next_svcn;
+	u32 roff, rs = sbi->record_size;
+	struct runs_tree run;
+
+	run_init(&run);
+
+	while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi))) {
+		if (!attr->non_res)
+			continue;
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		if (svcn != le64_to_cpu(le->vcn)) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (!svcn) {
+			alloc = le64_to_cpu(attr->nres.alloc_size) >>
+				cluster_bits;
+			mi_p = NULL;
+		} else if (svcn != evcn + 1) {
+			err = -EINVAL;
+			break;
+		}
+
+		evcn = le64_to_cpu(attr->nres.evcn);
+
+		if (svcn > evcn + 1) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (!mi_p) {
+			/* do not try if too little free space */
+			if (le32_to_cpu(mi->mrec->used) + 8 >= rs)
+				continue;
+
+			/* do not try if last attribute segment */
+			if (evcn + 1 == alloc)
+				continue;
+			run_close(&run);
+		}
+
+		roff = le16_to_cpu(attr->nres.run_off);
+		err = run_unpack(&run, sbi, ni->mi.rno, svcn, evcn, svcn,
+				 Add2Ptr(attr, roff),
+				 le32_to_cpu(attr->size) - roff);
+		if (err < 0)
+			break;
+
+		if (!mi_p) {
+			mi_p = mi;
+			attr_p = attr;
+			svcn_p = svcn;
+			evcn_p = evcn;
+			le_p = le;
+			err = 0;
+			continue;
+		}
+
+		/*
+		 * run contains data from two records: mi_p and mi
+		 * try to pack in one
+		 */
+		err = mi_pack_runs(mi_p, attr_p, &run, evcn + 1 - svcn_p);
+		if (err)
+			break;
+
+		next_svcn = le64_to_cpu(attr_p->nres.evcn) + 1;
+
+		if (next_svcn >= evcn + 1) {
+			/* we can remove this attribute segment */
+			al_remove_le(ni, le);
+			mi_remove_attr(mi, attr);
+			le = le_p;
+			continue;
+		}
+
+		attr->nres.svcn = le->vcn = cpu_to_le64(next_svcn);
+		mi->dirty = true;
+		ni->attr_list.dirty = true;
+
+		if (evcn + 1 == alloc) {
+			err = mi_pack_runs(mi, attr, &run,
+					   evcn + 1 - next_svcn);
+			if (err)
+				break;
+			mi_p = NULL;
+		} else {
+			mi_p = mi;
+			attr_p = attr;
+			svcn_p = next_svcn;
+			evcn_p = evcn;
+			le_p = le;
+			run_truncate_head(&run, next_svcn);
+		}
+	}
+
+	if (err) {
+		ntfs_inode_warn(&ni->vfs_inode, "repack problem");
+		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+
+		/* Pack loaded but not packed runs */
+		if (mi_p)
+			mi_pack_runs(mi_p, attr_p, &run, evcn_p + 1 - svcn_p);
+	}
+
+	run_close(&run);
+	return err;
+}
+
+/*
+ * ni_try_remove_attr_list
+ *
+ * Can we remove attribute list?
+ * Check the case when primary record contains enough space for all attributes
+ */
+static int ni_try_remove_attr_list(struct ntfs_inode *ni)
+{
+	int err = 0;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct ATTRIB *attr, *attr_list, *attr_ins;
+	struct ATTR_LIST_ENTRY *le;
+	struct mft_inode *mi;
+	u32 asize, free;
+	struct MFT_REF ref;
+	__le16 id;
+
+	if (!ni->attr_list.dirty)
+		return 0;
+
+	err = ni_repack(ni);
+	if (err)
+		return err;
+
+	attr_list = mi_find_attr(&ni->mi, NULL, ATTR_LIST, NULL, 0, NULL);
+	if (!attr_list)
+		return 0;
+
+	asize = le32_to_cpu(attr_list->size);
+
+	/* free space in primary record without attribute list */
+	free = sbi->record_size - le32_to_cpu(ni->mi.mrec->used) + asize;
+	mi_get_ref(&ni->mi, &ref);
+
+	le = NULL;
+	while ((le = al_enumerate(ni, le))) {
+		if (!memcmp(&le->ref, &ref, sizeof(ref)))
+			continue;
+
+		if (le->vcn)
+			return 0;
+
+		mi = ni_find_mi(ni, ino_get(&le->ref));
+		if (!mi)
+			return 0;
+
+		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+				    le->name_len, &le->id);
+		if (!attr)
+			return 0;
+
+		asize = le32_to_cpu(attr->size);
+		if (asize > free)
+			return 0;
+
+		free -= asize;
+	}
+
+	/* Is seems that attribute list can be removed from primary record */
+	mi_remove_attr(&ni->mi, attr_list);
+
+	/*
+	 * Repeat the cycle above and move all attributes to primary record.
+	 * It should be success!
+	 */
+	le = NULL;
+	while ((le = al_enumerate(ni, le))) {
+		if (!memcmp(&le->ref, &ref, sizeof(ref)))
+			continue;
+
+		mi = ni_find_mi(ni, ino_get(&le->ref));
+
+		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+				    le->name_len, &le->id);
+		asize = le32_to_cpu(attr->size);
+
+		/* insert into primary record */
+		attr_ins = mi_insert_attr(&ni->mi, le->type, le_name(le),
+					  le->name_len, asize,
+					  le16_to_cpu(attr->name_off));
+		id = attr_ins->id;
+
+		/* copy all except id */
+		memcpy(attr_ins, attr, asize);
+		attr_ins->id = id;
+
+		/* remove from original record */
+		mi_remove_attr(mi, attr);
+	}
+
+	run_deallocate(sbi, &ni->attr_list.run, true);
+	run_close(&ni->attr_list.run);
+	ni->attr_list.size = 0;
+	ntfs_free(ni->attr_list.le);
+	ni->attr_list.le = NULL;
+	ni->attr_list.dirty = false;
+
+	return 0;
+}
+
+/*
+ * ni_create_attr_list
+ *
+ * generates an attribute list for this primary record
+ */
+int ni_create_attr_list(struct ntfs_inode *ni)
+{
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	int err;
+	u32 lsize;
+	struct ATTRIB *attr;
+	struct ATTRIB *arr_move[7];
+	struct ATTR_LIST_ENTRY *le, *le_b[7];
+	struct MFT_REC *rec;
+	bool is_mft;
+	CLST rno = 0;
+	struct mft_inode *mi;
+	u32 free_b, nb, to_free, rs;
+	u16 sz;
+
+	is_mft = ni->mi.rno == MFT_REC_MFT;
+	rec = ni->mi.mrec;
+	rs = sbi->record_size;
+
+	/*
+	 * Skip estimating exact memory requirement
+	 * Looks like one record_size is always enough
+	 */
+	le = ntfs_malloc(al_aligned(rs));
+	if (!le) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	mi_get_ref(&ni->mi, &le->ref);
+	ni->attr_list.le = le;
+
+	attr = NULL;
+	nb = 0;
+	free_b = 0;
+	attr = NULL;
+
+	for (; (attr = mi_enum_attr(&ni->mi, attr)); le = Add2Ptr(le, sz)) {
+		sz = le_size(attr->name_len);
+		le->type = attr->type;
+		le->size = cpu_to_le16(sz);
+		le->name_len = attr->name_len;
+		le->name_off = offsetof(struct ATTR_LIST_ENTRY, name);
+		le->vcn = 0;
+		if (le != ni->attr_list.le)
+			le->ref = ni->attr_list.le->ref;
+		le->id = attr->id;
+
+		if (attr->name_len)
+			memcpy(le->name, attr_name(attr),
+			       sizeof(short) * attr->name_len);
+		else if (attr->type == ATTR_STD)
+			continue;
+		else if (attr->type == ATTR_LIST)
+			continue;
+		else if (is_mft && attr->type == ATTR_DATA)
+			continue;
+
+		if (!nb || nb < ARRAY_SIZE(arr_move)) {
+			le_b[nb] = le;
+			arr_move[nb++] = attr;
+			free_b += le32_to_cpu(attr->size);
+		}
+	}
+
+	lsize = PtrOffset(ni->attr_list.le, le);
+	ni->attr_list.size = lsize;
+
+	to_free = le32_to_cpu(rec->used) + lsize + SIZEOF_RESIDENT;
+	if (to_free <= rs) {
+		to_free = 0;
+	} else {
+		to_free -= rs;
+
+		if (to_free > free_b) {
+			err = -EINVAL;
+			goto out1;
+		}
+	}
+
+	/* Allocate child mft. */
+	err = ntfs_look_free_mft(sbi, &rno, is_mft, ni, &mi);
+	if (err)
+		goto out1;
+
+	/* Call 'mi_remove_attr' in reverse order to keep pointers 'arr_move' valid */
+	while (to_free > 0) {
+		struct ATTRIB *b = arr_move[--nb];
+		u32 asize = le32_to_cpu(b->size);
+		u16 name_off = le16_to_cpu(b->name_off);
+
+		attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off),
+				      b->name_len, asize, name_off);
+		WARN_ON(!attr);
+
+		mi_get_ref(mi, &le_b[nb]->ref);
+		le_b[nb]->id = attr->id;
+
+		/* copy all except id */
+		memcpy(attr, b, asize);
+		attr->id = le_b[nb]->id;
+
+		WARN_ON(!mi_remove_attr(&ni->mi, b));
+
+		if (to_free <= asize)
+			break;
+		to_free -= asize;
+		WARN_ON(!nb);
+	}
+
+	attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0,
+			      lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT);
+	WARN_ON(!attr);
+
+	attr->non_res = 0;
+	attr->flags = 0;
+	attr->res.data_size = cpu_to_le32(lsize);
+	attr->res.data_off = SIZEOF_RESIDENT_LE;
+	attr->res.flags = 0;
+	attr->res.res = 0;
+
+	memcpy(resident_data_ex(attr, lsize), ni->attr_list.le, lsize);
+
+	ni->attr_list.dirty = false;
+
+	mark_inode_dirty(&ni->vfs_inode);
+	goto out;
+
+out1:
+	ntfs_free(ni->attr_list.le);
+	ni->attr_list.le = NULL;
+	ni->attr_list.size = 0;
+
+out:
+	return err;
+}
+
+/*
+ * ni_ins_attr_ext
+ *
+ * This method adds an external attribute to the ntfs_inode.
+ */
+static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
+			   enum ATTR_TYPE type, const __le16 *name, u8 name_len,
+			   u32 asize, CLST svcn, u16 name_off, bool force_ext,
+			   struct ATTRIB **ins_attr, struct mft_inode **ins_mi)
+{
+	struct ATTRIB *attr;
+	struct mft_inode *mi;
+	CLST rno;
+	u64 vbo;
+	struct rb_node *node;
+	int err;
+	bool is_mft, is_mft_data;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+
+	is_mft = ni->mi.rno == MFT_REC_MFT;
+	is_mft_data = is_mft && type == ATTR_DATA && !name_len;
+
+	if (asize > sbi->max_bytes_per_attr) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * standard information and attr_list cannot be made external.
+	 * The Log File cannot have any external attributes
+	 */
+	if (type == ATTR_STD || type == ATTR_LIST ||
+	    ni->mi.rno == MFT_REC_LOG) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Create attribute list if it is not already existed */
+	if (!ni->attr_list.size) {
+		err = ni_create_attr_list(ni);
+		if (err)
+			goto out;
+	}
+
+	vbo = is_mft_data ? ((u64)svcn << sbi->cluster_bits) : 0;
+
+	if (force_ext)
+		goto insert_ext;
+
+	/* Load all subrecords into memory. */
+	err = ni_load_all_mi(ni);
+	if (err)
+		goto out;
+
+	/* Check each of loaded subrecord */
+	for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) {
+		mi = rb_entry(node, struct mft_inode, node);
+
+		if (is_mft_data &&
+		    (mi_enum_attr(mi, NULL) ||
+		     vbo <= ((u64)mi->rno << sbi->record_bits))) {
+			/* We can't accept this record 'case MFT's bootstrapping */
+			continue;
+		}
+		if (is_mft &&
+		    mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, NULL)) {
+			/*
+			 * This child record already has a ATTR_DATA.
+			 * So it can't accept any other records.
+			 */
+			continue;
+		}
+
+		if ((type != ATTR_NAME || name_len) &&
+		    mi_find_attr(mi, NULL, type, name, name_len, NULL)) {
+			/* Only indexed attributes can share same...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 05/10] fs/ntfs3: Add attrib operations

[Konstantin K. <alm...@pa...>]

This adds attrib operations

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/attrib.c   | 2082 +++++++++++++++++++++++++++++++++++++++++++
 fs/ntfs3/attrlist.c |  456 ++++++++++
 fs/ntfs3/xattr.c    | 1046 ++++++++++++++++++++++
 3 files changed, 3584 insertions(+)
 create mode 100644 fs/ntfs3/attrib.c
 create mode 100644 fs/ntfs3/attrlist.c
 create mode 100644 fs/ntfs3/xattr.c

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
new file mode 100644
index 000000000..bca85e7b6
--- /dev/null
+++ b/fs/ntfs3/attrib.c
@@ -0,0 +1,2082 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ * TODO: merge attr_set_size/attr_data_get_block/attr_allocate_frame?
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/hash.h>
+#include <linux/nls.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/*
+ * You can set external NTFS_MIN_LOG2_OF_CLUMP/NTFS_MAX_LOG2_OF_CLUMP to manage
+ * preallocate algorithm
+ */
+#ifndef NTFS_MIN_LOG2_OF_CLUMP
+#define NTFS_MIN_LOG2_OF_CLUMP 16
+#endif
+
+#ifndef NTFS_MAX_LOG2_OF_CLUMP
+#define NTFS_MAX_LOG2_OF_CLUMP 26
+#endif
+
+// 16M
+#define NTFS_CLUMP_MIN (1 << (NTFS_MIN_LOG2_OF_CLUMP + 8))
+// 16G
+#define NTFS_CLUMP_MAX (1ull << (NTFS_MAX_LOG2_OF_CLUMP + 8))
+
+/*
+ * get_pre_allocated
+ *
+ */
+static inline u64 get_pre_allocated(u64 size)
+{
+	u32 clump;
+	u8 align_shift;
+	u64 ret;
+
+	if (size <= NTFS_CLUMP_MIN) {
+		clump = 1 << NTFS_MIN_LOG2_OF_CLUMP;
+		align_shift = NTFS_MIN_LOG2_OF_CLUMP;
+	} else if (size >= NTFS_CLUMP_MAX) {
+		clump = 1 << NTFS_MAX_LOG2_OF_CLUMP;
+		align_shift = NTFS_MAX_LOG2_OF_CLUMP;
+	} else {
+		align_shift = NTFS_MIN_LOG2_OF_CLUMP - 1 +
+			      __ffs(size >> (8 + NTFS_MIN_LOG2_OF_CLUMP));
+		clump = 1u << align_shift;
+	}
+
+	ret = (((size + clump - 1) >> align_shift)) << align_shift;
+
+	return ret;
+}
+
+/*
+ * attr_must_be_resident
+ *
+ * returns true if attribute must be resident
+ */
+static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi,
+					 enum ATTR_TYPE type)
+{
+	const struct ATTR_DEF_ENTRY *de;
+
+	switch (type) {
+	case ATTR_STD:
+	case ATTR_NAME:
+	case ATTR_ID:
+	case ATTR_LABEL:
+	case ATTR_VOL_INFO:
+	case ATTR_ROOT:
+	case ATTR_EA_INFO:
+		return true;
+	default:
+		de = ntfs_query_def(sbi, type);
+		if (de && (de->flags & NTFS_ATTR_MUST_BE_RESIDENT))
+			return true;
+		return false;
+	}
+}
+
+/*
+ * attr_load_runs
+ *
+ * load all runs stored in 'attr'
+ */
+int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
+		   struct runs_tree *run, const CLST *vcn)
+{
+	int err;
+	CLST svcn = le64_to_cpu(attr->nres.svcn);
+	CLST evcn = le64_to_cpu(attr->nres.evcn);
+	u32 asize;
+	u16 run_off;
+
+	if (svcn >= evcn + 1 || run_is_mapped_full(run, svcn, evcn))
+		return 0;
+
+	if (vcn && (evcn < *vcn || *vcn < svcn))
+		return -EINVAL;
+
+	asize = le32_to_cpu(attr->size);
+	run_off = le16_to_cpu(attr->nres.run_off);
+	err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn,
+			    vcn ? *vcn : svcn, Add2Ptr(attr, run_off),
+			    asize - run_off);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+/*
+ * int run_deallocate_ex
+ *
+ * Deallocate clusters
+ */
+static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run,
+			     CLST vcn, CLST len, CLST *done, bool trim)
+{
+	int err = 0;
+	CLST vcn_next, vcn0 = vcn, lcn, clen, dn = 0;
+	size_t idx;
+
+	if (!len)
+		goto out;
+
+	if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) {
+failed:
+		run_truncate(run, vcn0);
+		err = -EINVAL;
+		goto out;
+	}
+
+	for (;;) {
+		if (clen > len)
+			clen = len;
+
+		if (!clen) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (lcn != SPARSE_LCN) {
+			mark_as_free_ex(sbi, lcn, clen, trim);
+			dn += clen;
+		}
+
+		len -= clen;
+		if (!len)
+			break;
+
+		vcn_next = vcn + clen;
+		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
+		    vcn != vcn_next) {
+			// save memory - don't load entire run
+			goto failed;
+		}
+	}
+
+out:
+	if (done)
+		*done += dn;
+
+	return err;
+}
+
+/*
+ * attr_allocate_clusters
+ *
+ * find free space, mark it as used and store in 'run'
+ */
+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,
+			   CLST *new_lcn)
+{
+	int err;
+	CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0;
+	struct wnd_bitmap *wnd = &sbi->used.bitmap;
+	size_t cnt = run->count;
+
+	for (;;) {
+		err = ntfs_look_for_free_space(sbi, lcn, len + pre, &lcn, &flen,
+					       opt);
+
+		if (err == -ENOSPC && pre) {
+			pre = 0;
+			if (*pre_alloc)
+				*pre_alloc = 0;
+			continue;
+		}
+
+		if (err)
+			goto out;
+
+		if (new_lcn && vcn == vcn0)
+			*new_lcn = lcn;
+
+		/* Add new fragment into run storage */
+		if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) {
+			down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
+			wnd_set_free(wnd, lcn, flen);
+			up_write(&wnd->rw_lock);
+			err = -ENOMEM;
+			goto out;
+		}
+
+		vcn += flen;
+
+		if (flen >= len || opt == ALLOCATE_MFT ||
+		    (fr && run->count - cnt >= fr)) {
+			*alen = vcn - vcn0;
+			return 0;
+		}
+
+		len -= flen;
+	}
+
+out:
+	/* undo */
+	run_deallocate_ex(sbi, run, vcn0, vcn - vcn0, NULL, false);
+	run_truncate(run, vcn0);
+
+	return err;
+}
+
+/*
+ * if page is not NULL - it is already contains resident data
+ * and locked (called from ni_write_frame)
+ */
+int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
+			  struct ATTR_LIST_ENTRY *le, struct mft_inode *mi,
+			  u64 new_size, struct runs_tree *run,
+			  struct ATTRIB **ins_attr, struct page *page)
+{
+	struct ntfs_sb_info *sbi;
+	struct ATTRIB *attr_s;
+	struct MFT_REC *rec;
+	u32 used, asize, rsize, aoff, align;
+	bool is_data;
+	CLST len, alen;
+	char *next;
+	int err;
+
+	if (attr->non_res) {
+		*ins_attr = attr;
+		return 0;
+	}
+
+	sbi = mi->sbi;
+	rec = mi->mrec;
+	attr_s = NULL;
+	used = le32_to_cpu(rec->used);
+	asize = le32_to_cpu(attr->size);
+	next = Add2Ptr(attr, asize);
+	aoff = PtrOffset(rec, attr);
+	rsize = le32_to_cpu(attr->res.data_size);
+	is_data = attr->type == ATTR_DATA && !attr->name_len;
+
+	align = sbi->cluster_size;
+	if (is_attr_compressed(attr))
+		align <<= COMPRESSION_UNIT;
+	len = (rsize + align - 1) >> sbi->cluster_bits;
+
+	run_init(run);
+
+	/* make a copy of original attribute */
+	attr_s = ntfs_memdup(attr, asize);
+	if (!attr_s) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	if (!len) {
+		/* empty resident -> empty nonresident */
+		alen = 0;
+	} else {
+		const char *data = resident_data(attr);
+
+		err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL,
+					     ALLOCATE_DEF, &alen, 0, NULL);
+		if (err)
+			goto out1;
+
+		if (!rsize) {
+			/* empty resident -> non empty nonresident */
+		} else if (!is_data) {
+			err = ntfs_sb_write_run(sbi, run, 0, data, rsize);
+			if (err)
+				goto out2;
+		} else if (!page) {
+			char *kaddr;
+
+			page = grab_cache_page(ni->vfs_inode.i_mapping, 0);
+			if (!page) {
+				err = -ENOMEM;
+				goto out2;
+			}
+			kaddr = kmap_atomic(page);
+			memcpy(kaddr, data, rsize);
+			memset(kaddr + rsize, 0, PAGE_SIZE - rsize);
+			kunmap_atomic(kaddr);
+			flush_dcache_page(page);
+			SetPageUptodate(page);
+			set_page_dirty(page);
+			unlock_page(page);
+			put_page(page);
+		}
+	}
+
+	/* remove original attribute */
+	used -= asize;
+	memmove(attr, Add2Ptr(attr, asize), used - aoff);
+	rec->used = cpu_to_le32(used);
+	mi->dirty = true;
+	if (le)
+		al_remove_le(ni, le);
+
+	err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s),
+				    attr_s->name_len, run, 0, alen,
+				    attr_s->flags, &attr, NULL);
+	if (err)
+		goto out3;
+
+	ntfs_free(attr_s);
+	attr->nres.data_size = cpu_to_le64(rsize);
+	attr->nres.valid_size = attr->nres.data_size;
+
+	*ins_attr = attr;
+
+	if (is_data)
+		ni->ni_flags &= ~NI_FLAG_RESIDENT;
+
+	/* Resident attribute becomes non resident */
+	return 0;
+
+out3:
+	attr = Add2Ptr(rec, aoff);
+	memmove(next, attr, used - aoff);
+	memcpy(attr, attr_s, asize);
+	rec->used = cpu_to_le32(used + asize);
+	mi->dirty = true;
+out2:
+	/* undo: do not trim new allocated clusters */
+	run_deallocate(sbi, run, false);
+	run_close(run);
+out1:
+	ntfs_free(attr_s);
+	/*reinsert le*/
+out:
+	return err;
+}
+
+/*
+ * attr_set_size_res
+ *
+ * helper for attr_set_size
+ */
+static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr,
+			     struct ATTR_LIST_ENTRY *le, struct mft_inode *mi,
+			     u64 new_size, struct runs_tree *run,
+			     struct ATTRIB **ins_attr)
+{
+	struct ntfs_sb_info *sbi = mi->sbi;
+	struct MFT_REC *rec = mi->mrec;
+	u32 used = le32_to_cpu(rec->used);
+	u32 asize = le32_to_cpu(attr->size);
+	u32 aoff = PtrOffset(rec, attr);
+	u32 rsize = le32_to_cpu(attr->res.data_size);
+	u32 tail = used - aoff - asize;
+	char *next = Add2Ptr(attr, asize);
+	s64 dsize = QuadAlign(new_size) - QuadAlign(rsize);
+
+	if (dsize < 0) {
+		memmove(next + dsize, next, tail);
+	} else if (dsize > 0) {
+		if (used + dsize > sbi->max_bytes_per_attr)
+			return attr_make_nonresident(ni, attr, le, mi, new_size,
+						     run, ins_attr, NULL);
+
+		memmove(next + dsize, next, tail);
+		memset(next, 0, dsize);
+	}
+
+	if (new_size > rsize)
+		memset(Add2Ptr(resident_data(attr), rsize), 0,
+		       new_size - rsize);
+
+	rec->used = cpu_to_le32(used + dsize);
+	attr->size = cpu_to_le32(asize + dsize);
+	attr->res.data_size = cpu_to_le32(new_size);
+	mi->dirty = true;
+	*ins_attr = attr;
+
+	return 0;
+}
+
+/*
+ * attr_set_size
+ *
+ * change the size of attribute
+ * Extend:
+ *   - sparse/compressed: no allocated clusters
+ *   - normal: append allocated and preallocated new clusters
+ * Shrink:
+ *   - no deallocate if keep_prealloc is set
+ */
+int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		  const __le16 *name, u8 name_len, struct runs_tree *run,
+		  u64 new_size, const u64 *new_valid, bool keep_prealloc,
+		  struct ATTRIB **ret)
+{
+	int err = 0;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	u8 cluster_bits = sbi->cluster_bits;
+	bool is_mft =
+		ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && !name_len;
+	u64 old_valid, old_size, old_alloc, new_alloc, new_alloc_tmp;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn;
+	CLST next_svcn, pre_alloc = -1, done = 0;
+	bool is_ext;
+	u32 align;
+	struct MFT_REC *rec;
+
+again:
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL,
+			      &mi_b);
+	if (!attr_b) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (!attr_b->non_res) {
+		err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run,
+					&attr_b);
+		if (err || !attr_b->non_res)
+			goto out;
+
+		/* layout of records may be changed, so do a full search */
+		goto again;
+	}
+
+	is_ext = is_attr_ext(attr_b);
+
+again_1:
+	align = sbi->cluster_size;
+
+	if (is_ext) {
+		align <<= attr_b->nres.c_unit;
+		if (is_attr_sparsed(attr_b))
+			keep_prealloc = false;
+	}
+
+	old_valid = le64_to_cpu(attr_b->nres.valid_size);
+	old_size = le64_to_cpu(attr_b->nres.data_size);
+	old_alloc = le64_to_cpu(attr_b->nres.alloc_size);
+	old_alen = old_alloc >> cluster_bits;
+
+	new_alloc = (new_size + align - 1) & ~(u64)(align - 1);
+	new_alen = new_alloc >> cluster_bits;
+
+	if (keep_prealloc && is_ext)
+		keep_prealloc = false;
+
+	if (keep_prealloc && new_size < old_size) {
+		attr_b->nres.data_size = cpu_to_le64(new_size);
+		mi_b->dirty = true;
+		goto ok;
+	}
+
+	vcn = old_alen - 1;
+
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn = le64_to_cpu(attr_b->nres.evcn);
+
+	if (svcn <= vcn && vcn <= evcn) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto out;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+next_le_1:
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn = le64_to_cpu(attr->nres.evcn);
+	}
+
+next_le:
+	rec = mi->mrec;
+
+	err = attr_load_runs(attr, ni, run, NULL);
+	if (err)
+		goto out;
+
+	if (new_size > old_size) {
+		CLST to_allocate;
+		size_t free;
+
+		if (new_alloc <= old_alloc) {
+			attr_b->nres.data_size = cpu_to_le64(new_size);
+			mi_b->dirty = true;
+			goto ok;
+		}
+
+		to_allocate = new_alen - old_alen;
+add_alloc_in_same_attr_seg:
+		lcn = 0;
+		if (is_mft) {
+			/* mft allocates clusters from mftzone */
+			pre_alloc = 0;
+		} else if (is_ext) {
+			/* no preallocate for sparse/compress */
+			pre_alloc = 0;
+		} else if (pre_alloc == -1) {
+			pre_alloc = 0;
+			if (type == ATTR_DATA && !name_len &&
+			    sbi->options.prealloc) {
+				CLST new_alen2 = bytes_to_cluster(
+					sbi, get_pre_allocated(new_size));
+				pre_alloc = new_alen2 - new_alen;
+			}
+
+			/* Get the last lcn to allocate from */
+			if (old_alen &&
+			    !run_lookup_entry(run, vcn, &lcn, NULL, NULL)) {
+				lcn = SPARSE_LCN;
+			}
+
+			if (lcn == SPARSE_LCN)
+				lcn = 0;
+			else if (lcn)
+				lcn += 1;
+
+			free = wnd_zeroes(&sbi->used.bitmap);
+			if (to_allocate > free) {
+				err = -ENOSPC;
+				goto out;
+			}
+
+			if (pre_alloc && to_allocate + pre_alloc > free)
+				pre_alloc = 0;
+		}
+
+		vcn = old_alen;
+
+		if (is_ext) {
+			if (!run_add_entry(run, vcn, SPARSE_LCN, to_allocate,
+					   false)) {
+				err = -ENOMEM;
+				goto out;
+			}
+			alen = to_allocate;
+		} else {
+			/* ~3 bytes per fragment */
+			err = attr_allocate_clusters(
+				sbi, run, vcn, lcn, to_allocate, &pre_alloc,
+				is_mft ? ALLOCATE_MFT : 0, &alen,
+				is_mft ? 0
+				       : (sbi->record_size -
+					  le32_to_cpu(rec->used) + 8) /
+							 3 +
+						 1,
+				NULL);
+			if (err)
+				goto out;
+		}
+
+		done += alen;
+		vcn += alen;
+		if (to_allocate > alen)
+			to_allocate -= alen;
+		else
+			to_allocate = 0;
+
+pack_runs:
+		err = mi_pack_runs(mi, attr, run, vcn - svcn);
+		if (err)
+			goto out;
+
+		next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+		new_alloc_tmp = (u64)next_svcn << cluster_bits;
+		attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp);
+		mi_b->dirty = true;
+
+		if (next_svcn >= vcn && !to_allocate) {
+			/* Normal way. update attribute and exit */
+			attr_b->nres.data_size = cpu_to_le64(new_size);
+			goto ok;
+		}
+
+		/* at least two mft to avoid recursive loop*/
+		if (is_mft && next_svcn == vcn &&
+		    ((u64)done << sbi->cluster_bits) >= 2 * sbi->record_size) {
+			new_size = new_alloc_tmp;
+			attr_b->nres.data_size = attr_b->nres.alloc_size;
+			goto ok;
+		}
+
+		if (le32_to_cpu(rec->used) < sbi->record_size) {
+			old_alen = next_svcn;
+			evcn = old_alen - 1;
+			goto add_alloc_in_same_attr_seg;
+		}
+
+		attr_b->nres.data_size = attr_b->nres.alloc_size;
+		if (new_alloc_tmp < old_valid)
+			attr_b->nres.valid_size = attr_b->nres.data_size;
+
+		if (type == ATTR_LIST) {
+			err = ni_expand_list(ni);
+			if (err)
+				goto out;
+			if (next_svcn < vcn)
+				goto pack_runs;
+
+			/* layout of records is changed */
+			goto again;
+		}
+
+		if (!ni->attr_list.size) {
+			err = ni_create_attr_list(ni);
+			if (err)
+				goto out;
+			/* layout of records is changed */
+		}
+
+		if (next_svcn >= vcn) {
+			/* this is mft data, repeat */
+			goto again;
+		}
+
+		/* insert new attribute segment */
+		err = ni_insert_nonresident(ni, type, name, name_len, run,
+					    next_svcn, vcn - next_svcn,
+					    attr_b->flags, &attr, &mi);
+		if (err)
+			goto out;
+
+		if (!is_mft)
+			run_truncate_head(run, evcn + 1);
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn = le64_to_cpu(attr->nres.evcn);
+
+		le_b = NULL;
+		/* layout of records maybe changed */
+		/* find base attribute to update*/
+		attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len,
+				      NULL, &mi_b);
+		if (!attr_b) {
+			err = -ENOENT;
+			goto out;
+		}
+
+		attr_b->nres.alloc_size = cpu_to_le64((u64)vcn << cluster_bits);
+		attr_b->nres.data_size = attr_b->nres.alloc_size;
+		attr_b->nres.valid_size = attr_b->nres.alloc_size;
+		mi_b->dirty = true;
+		goto again_1;
+	}
+
+	if (new_size != old_size ||
+	    (new_alloc != old_alloc && !keep_prealloc)) {
+		vcn = max(svcn, new_alen);
+		new_alloc_tmp = (u64)vcn << cluster_bits;
+
+		alen = 0;
+		err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &alen,
+					true);
+		if (err)
+			goto out;
+
+		run_truncate(run, vcn);
+
+		if (vcn > svcn) {
+			err = mi_pack_runs(mi, attr, run, vcn - svcn);
+			if (err)
+				goto out;
+		} else if (le && le->vcn) {
+			u16 le_sz = le16_to_cpu(le->size);
+
+			/*
+			 * NOTE: list entries for one attribute are always
+			 * the same size. We deal with last entry (vcn==0)
+			 * and it is not first in entries array
+			 * (list entry for std attribute always first)
+			 * So it is safe to step back
+			 */
+			mi_remove_attr(mi, attr);
+
+			if (!al_remove_le(ni, le)) {
+				err = -EINVAL;
+				goto out;
+			}
+
+			le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz);
+		} else {
+			attr->nres.evcn = cpu_to_le64((u64)vcn - 1);
+			mi->dirty = true;
+		}
+
+		attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp);
+
+		if (vcn == new_alen) {
+			attr_b->nres.data_size = cpu_to_le64(new_size);
+			if (new_size < old_valid)
+				attr_b->nres.valid_size =
+					attr_b->nres.data_size;
+		} else {
+			if (new_alloc_tmp <=
+			    le64_to_cpu(attr_b->nres.data_size))
+				attr_b->nres.data_size =
+					attr_b->nres.alloc_size;
+			if (new_alloc_tmp <
+			    le64_to_cpu(attr_b->nres.valid_size))
+				attr_b->nres.valid_size =
+					attr_b->nres.alloc_size;
+		}
+
+		if (is_ext)
+			le64_sub_cpu(&attr_b->nres.total_size,
+				     ((u64)alen << cluster_bits));
+
+		mi_b->dirty = true;
+
+		if (new_alloc_tmp <= new_alloc)
+			goto ok;
+
+		old_size = new_alloc_tmp;
+		vcn = svcn - 1;
+
+		if (le == le_b) {
+			attr = attr_b;
+			mi = mi_b;
+			evcn = svcn - 1;
+			svcn = 0;
+			goto next_le;
+		}
+
+		if (le->type != type || le->name_len != name_len ||
+		    memcmp(le_name(le), name, name_len * sizeof(short))) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = ni_load_mi(ni, le, &mi);
+		if (err)
+			goto out;
+
+		attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+		goto next_le_1;
+	}
+
+ok:
+	if (new_valid) {
+		__le64 valid = cpu_to_le64(min(*new_valid, new_size));
+
+		if (attr_b->nres.valid_size != valid) {
+			attr_b->nres.valid_size = valid;
+			mi_b->dirty = true;
+		}
+	}
+
+out:
+	if (!err && attr_b && ret)
+		*ret = attr_b;
+
+	/* update inode_set_bytes*/
+	if (!err && ((type == ATTR_DATA && !name_len) ||
+		     (type == ATTR_ALLOC && name == I30_NAME))) {
+		bool dirty = false;
+
+		if (ni->vfs_inode.i_size != new_size) {
+			ni->vfs_inode.i_size = new_size;
+			dirty = true;
+		}
+
+		if (attr_b && attr_b->non_res) {
+			new_alloc = le64_to_cpu(attr_b->nres.alloc_size);
+			if (inode_get_bytes(&ni->vfs_inode) != new_alloc) {
+				inode_set_bytes(&ni->vfs_inode, new_alloc);
+				dirty = true;
+			}
+		}
+
+		if (dirty) {
+			ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+			mark_inode_dirty(&ni->vfs_inode);
+		}
+	}
+
+	return err;
+}
+
+int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
+			CLST *len, bool *new)
+{
+	int err = 0;
+	struct runs_tree *run = &ni->file.run;
+	struct ntfs_sb_info *sbi;
+	u8 cluster_bits;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end;
+	u64 total_size;
+	u32 clst_per_frame;
+	bool ok;
+
+	if (new)
+		*new = false;
+
+	down_read(&ni->file.run_lock);
+	ok = run_lookup_entry(run, vcn, lcn, len, NULL);
+	up_read(&ni->file.run_lock);
+
+	if (ok && (*lcn != SPARSE_LCN || !new)) {
+		/* normal way */
+		return 0;
+	}
+
+	if (!clen)
+		clen = 1;
+
+	if (ok && clen > *len)
+		clen = *len;
+
+	sbi = ni->mi.sbi;
+	cluster_bits = sbi->cluster_bits;
+
+	ni_lock(ni);
+	down_write(&ni->file.run_lock);
+
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
+	if (!attr_b) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (!attr_b->non_res) {
+		*lcn = RESIDENT_LCN;
+		*len = 1;
+		goto out;
+	}
+
+	asize = le64_to_cpu(attr_b->nres.alloc_size) >> sbi->cluster_bits;
+	if (vcn >= asize) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	clst_per_frame = 1u << attr_b->nres.c_unit;
+	to_alloc = (clen + clst_per_frame - 1) & ~(clst_per_frame - 1);
+
+	if (vcn + to_alloc > asize)
+		to_alloc = asize - vcn;
+
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+
+	attr = attr_b;
+	le = le_b;
+	mi = mi_b;
+
+	if (le_b && (vcn < svcn || evcn1 <= vcn)) {
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	err = attr_load_runs(attr, ni, run, NULL);
+	if (err)
+		goto out;
+
+	if (!ok) {
+		ok = run_lookup_entry(run, vcn, lcn, len, NULL);
+		if (ok && (*lcn != SPARSE_LCN || !new)) {
+			/* normal way */
+			err = 0;
+			goto ok;
+		}
+
+		if (!ok && !new) {
+			*len = 0;
+			err = 0;
+			goto ok;
+		}
+
+		if (ok && clen > *len) {
+			clen = *len;
+			to_alloc = (clen + clst_per_frame - 1) &
+				   ~(clst_per_frame - 1);
+		}
+	}
+
+	if (!is_attr_ext(attr_b)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Get the last lcn to allocate from */
+	hint = 0;
+
+	if (vcn > evcn1) {
+		if (!run_add_entry(run, evcn1, SPARSE_LCN, vcn - evcn1,
+				   false)) {
+			err = -ENOMEM;
+			goto out;
+		}
+	} else if (vcn && !run_lookup_entry(run, vcn - 1, &hint, NULL, NULL)) {
+		hint = -1;
+	}
+
+	err = attr_allocate_clusters(
+		sbi, run, vcn, hint + 1, to_alloc, NULL, 0, len,
+		(sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1,
+		lcn);
+	if (err)
+		goto out;
+	*new = true;
+
+	end = vcn + *len;
+
+	total_size = le64_to_cpu(attr_b->nres.total_size) +
+		     ((u64)*len << cluster_bits);
+
+repack:
+	err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn);
+	if (err)
+		goto out;
+
+	attr_b->nres.total_size = cpu_to_le64(total_size);
+	inode_set_bytes(&ni->vfs_inode, total_size);
+	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+
+	mi_b->dirty = true;
+	mark_inode_dirty(&ni->vfs_inode);
+
+	/* stored [vcn : next_svcn) from [vcn : end) */
+	next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+
+	if (end <= evcn1) {
+		if (next_svcn == evcn1) {
+			/* Normal way. update attribute and exit */
+			goto ok;
+		}
+		/* add new segment [next_svcn : evcn1 - next_svcn )*/
+		if (!ni->attr_list.size) {
+			err = ni_create_attr_list(ni);
+			if (err)
+				goto out;
+			/* layout of records is changed */
+			le_b = NULL;
+			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
+					      0, NULL, &mi_b);
+			if (!attr_b) {
+				err = -ENOENT;
+				goto out;
+			}
+
+			attr = attr_b;
+			le = le_b;
+			mi = mi_b;
+			goto repack;
+		}
+	}
+
+	svcn = evcn1;
+
+	/* Estimate next attribute */
+	attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi);
+
+	if (attr) {
+		CLST alloc = bytes_to_cluster(
+			sbi, le64_to_cpu(attr_b->nres.alloc_size));
+		CLST evcn = le64_to_cpu(attr->nres.evcn);
+
+		if (end < next_svcn)
+			end = next_svcn;
+		while (end > evcn) {
+			/* remove segment [svcn : evcn)*/
+			mi_remove_attr(mi, attr);
+
+			if (!al_remove_le(ni, le)) {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (evcn + 1 >= alloc) {
+				/* last attribute segment */
+				evcn1 = evcn + 1;
+				goto ins_ext;
+			}
+
+			if (ni_load_mi(ni, le, &mi)) {
+				attr = NULL;
+				goto out;
+			}
+
+			attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0,
+					    &le->id);
+			if (!attr) {
+				err = -EINVAL;
+				goto out;
+			}
+			svcn = le64_to_cpu(attr->nres.svcn);
+			evcn = le64_to_cpu(attr->nres.evcn);
+		}
+
+		if (end < svcn)
+			end = svcn;
+
+		err = attr_load_runs(attr, ni, run, &end);
+		if (err)
+			goto out;
+
+		evcn1 = evcn + 1;
+		attr->nres.svcn = cpu_to_le64(next_svcn);
+		err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn);
+		if (err)
+			goto out;
+
+		le->vcn = cpu_to_le64(next_svcn);
+		ni->attr_list.dirty = true;
+		mi->dirty = true;
+
+		next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+ins_ext:
+	if (evcn1 > next_svcn) {
+		err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
+					    next_svcn, evcn1 - next_svcn,
+					    attr_b->flags, &attr, &mi);
+		if (err)
+			goto out;
+	}
+ok:
+	run_truncate_around(run, vcn);
+out:
+	up_write(&ni->file.run_lock);
+	ni_unlock(ni);
+
+	return err;
+}
+
+int attr_data_read_resident(struct ntfs_inode *ni, struct page *page)
+{
+	u64 vbo;
+	struct ATTRIB *attr;
+	u32 data_size;
+
+	attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, NULL);
+	if (!attr)
+		return -EINVAL;
+
+	if (attr->non_res)
+		return E_NTFS_NONRESIDENT;
+
+	vbo = page->index << PAGE_SHIFT;
+	data_size = le32_to_cpu(attr->res.data_size);
+	if (vbo < data_size) {
+		const char *data = resident_data(attr);
+		char *kaddr = kmap_atomic(page);
+		u32 use = data_size - vbo;
+
+		if (use > PAGE_SIZE)
+			use = PAGE_SIZE;
+
+		memcpy(kaddr, data + vbo, use);
+		memset(kaddr + use, 0, PAGE_SIZE - use);
+		kunmap_atomic(kaddr);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+	} else if (!PageUptodate(page)) {
+		zero_user_segment(page, 0, PAGE_SIZE);
+		SetPageUptodate(page);
+	}
+
+	return 0;
+}
+
+int attr_data_write_resident(struct ntfs_inode *ni, struct page *page)
+{
+	u64 vbo;
+	struct mft_inode *mi;
+	struct ATTRIB *attr;
+	u32 data_size;
+
+	attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi);
+	if (!attr)
+		return -EINVAL;
+
+	if (attr->non_res) {
+		/*return special error code to check this case*/
+		return E_NTFS_NONRESIDENT;
+	}
+
+	vbo = page->index << PAGE_SHIFT;
+	data_size = le32_to_cpu(attr->res.data_size);
+	if (vbo < data_size) {
+		char *data = resident_data(attr);
+		char *kaddr = kmap_atomic(page);
+		u32 use = data_size - vbo;
+
+		if (use > PAGE_SIZE)
+			use = PAGE_SIZE;
+		memcpy(data + vbo, kaddr, use);
+		kunmap_atomic(kaddr);
+		mi->dirty = true;
+	}
+	ni->i_valid = data_size;
+
+	return 0;
+}
+
+/*
+ * attr_load_runs_vcn
+ *
+ * load runs with vcn
+ */
+int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type,
+		       const __le16 *name, u8 name_len, struct runs_tree *run,
+		       CLST vcn)
+{
+	struct ATTRIB *attr;
+	int err;
+	CLST svcn, evcn;
+	u16 ro;
+
+	attr = ni_find_attr(ni, NULL, NULL, type, name, name_len, &vcn, NULL);
+	if (!attr)
+		return -ENOENT;
+
+	svcn = le64_to_cpu(attr->nres.svcn);
+	evcn = le64_to_cpu(attr->nres.evcn);
+
+	if (evcn < vcn || vcn < svcn)
+		return -EINVAL;
+
+	ro = le16_to_cpu(attr->nres.run_off);
+	err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, svcn,
+			    Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/*
+ * load runs for given range [from to)
+ */
+int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
+			 const __le16 *name, u8 name_len, struct runs_tree *run,
+			 u64 from, u64 to)
+{
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	u8 cluster_bits = sbi->cluster_bits;
+	CLST vcn = from >> cluster_bits;
+	CLST vcn_last = (to - 1) >> cluster_bits;
+	CLST lcn, clen;
+	int err;
+
+	for (vcn = from >> cluster_bits; vcn <= vcn_last; vcn += clen) {
+		if (!run_lookup_entry(run, vcn, &lcn, &clen, NULL)) {
+			err = attr_load_runs_vcn(ni, type, name, name_len, run,
+						 vcn);
+			if (err)
+				return err;
+			clen = 0; /*next run_lookup_entry(vcn) must be success*/
+		}
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_NTFS3_LZX_XPRESS
+/*
+ * attr_wof_frame_info
+ *
+ * read header of xpress/lzx file to get info about frame
+ */
+int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
+			struct runs_tree *run, u64 frame, u64 frames,
+			u8 frame_bits, u32 *ondisk_size, u64 *vbo_data)
+{
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	u64 vbo[2], off[2], wof_size;
+	u32 voff;
+	u8 bytes_per_off;
+	char *addr;
+	struct page *page;
+	int i, err;
+	__le32 *off32;
+	__le64 *off64;
+
+	if (ni->vfs_inode.i_size < 0x100000000ull) {
+		/* file starts with array of 32 bit offsets */
+		bytes_per_off = sizeof(__le32);
+		vbo[1] = frame << 2;
+		*vbo_data = frames << 2;
+	} else {
+		/* file starts with array of 64 bit offsets */
+		bytes_per_off = sizeof(__le64);
+		vbo[1] = frame << 3;
+		*vbo_data = frames << 3;
+	}
+
+	/*
+	 * read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts
+	 * read 4/8 bytes at [vbo] == offset where compressed frame ends
+	 */
+	if (!attr->non_res) {
+		if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) {
+			ntfs_inode_err(&ni->vfs_inode, "is corrupted");
+			return -EINVAL;
+		}
+		addr = resident_data(attr);
+
+		if (bytes_per_off == sizeof(__le32)) {
+			off32 = Add2Ptr(addr, vbo[1]);
+			off[0] = vbo[1] ? le32_to_cpu(off32[-1]) : 0;
+			off[1] = le32_to_cpu(off32[0]);
+		} else {
+			off64 = Add2Ptr(addr, vbo[1]);
+			off[0] = vbo[1] ? le64_to_cpu(off64[-1]) : 0;
+			off[1] = le64_to_cpu(off64[0]);
+		}
+
+		*vbo_data += off[0];
+		*ondisk_size = off[1] - off[0];
+		return 0;
+	}
+
+	wof_size = le64_to_cpu(attr->nres.data_size);
+	down_write(&ni->file.run_lock);
+	page = ni->file.offs_page;
+	if (!page) {
+		page = alloc_page(GFP_KERNEL);
+		if (!page) {
+			err = -ENOMEM;
+			goto out;
+		}
+		page->index = -1;
+		ni->file.offs_page = page;
+	}
+	lock_page(page);
+	addr = page_address(page);
+
+	if (vbo[1]) {
+		voff = vbo[1] & (PAGE_SIZE - 1);
+		vbo[0] = vbo[1] - bytes_per_off;
+		i = 0;
+	} else {
+		voff = 0;
+		vbo[0] = 0;
+		off[0] = 0;
+		i = 1;
+	}
+
+	do {
+		pgoff_t index = vbo[i] >> PAGE_SHIFT;
+
+		if (index != page->index) {
+			u64 from = vbo[i] & ~(u64)(PAGE_SIZE - 1);
+			u64 to = min(from + PAGE_SIZE, wof_size);
+
+			err = attr_load_runs_range(ni, ATTR_DATA, WOF_NAME,
+						   ARRAY_SIZE(WOF_NAME), run,
+						   from, to);
+			if (err)
+				goto out1;
+
+			err = ntfs_bio_pages(sbi, run, &page, 1, from,
+					     to - from, REQ_OP_READ);
+			if (err) {
+				page->index = -1;
+				goto out1;
+			}
+			page->index = index;
+		}
+
+		if (i) {
+			if (bytes_per_off == sizeof(__le32)) {
+				off32 = Add2Ptr(addr, voff);
+				off[1] = le32_to_cpu(*off32);
+			} else {
+				off64 = Add2Ptr(addr, voff);
+				off[1] = le64_to_cpu(*off64);
+			}
+		} else if (!voff) {
+			if (bytes_per_off == sizeof(__le32)) {
+				off32 = Add2Ptr(addr, PAGE_SIZE - sizeof(u32));
+				off[0] = le32_to_cpu(*off32);
+			} else {
+				off64 = Add2Ptr(addr, PAGE_SIZE - sizeof(u64));
+				off[0] = le64_to_cpu(*off64);
+			}
+		} else {
+			/* two values in one page*/
+			if (bytes_per_off == sizeof(__le32)) {
+				off32 = Add2Ptr(addr, voff);
+				off[0] = le32_to_cpu(off32[-1]);
+				off[1] = le32_to_cpu(off32[0]);
+			} else {
+				off64 = Add2Ptr(addr, voff);
+				off[0] = le64_to_cpu(off64[-1]);
+				off[1] = le64_to_cpu(off64[0]);
+			}
+			break;
+		}
+	} while (++i < 2);
+
+	*vbo_data += off[0];
+	*ondisk_size = off[1] - off[0];
+
+out1:
+	unlock_page(page);
+out:
+	up_write(&ni->file.run_lock);
+	return err;
+}
+#endif
+
+/*
+ * attr_is_frame_compressed
+ *
+ * This function is used to detect compressed frame
+ */
+int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
+			     CLST frame, CLST *clst_data)
+{
+	int err;
+	u32 clst_frame;
+	CLST clen, lcn, vcn, alen, slen, vcn_next;
+	size_t idx;
+	struct runs_tree *run;
+
+	*clst_data = 0;
+
+	if (!is_attr_compressed(attr))
+		return 0;
+
+	if (!attr->non_res)
+		return 0;
+
+	clst_frame = 1u << attr->nres.c_unit;
+	vcn = frame * clst_frame;
+	run = &ni->file.run;
+
+	if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) {
+		err = attr_load_runs_vcn(ni, attr->type, attr_name(attr),
+					 attr->name_len, run, vcn);
+		if (err)
+			return err;
+
+		if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx))
+			return -EINVAL;
+	}
+
+	if (lcn == SPARSE_LCN) {
+		/* sparsed frame */
+		return 0;
+	}
+
+	if (clen >= clst_frame) {
+		/*
+		 * The frame is not compressed 'cause
+		 * it does not contain any sparse clusters
+		 */
+		*clst_data = clst_frame;
+		return 0;
+	}
+
+	alen = bytes_to_cluster(ni->mi.sbi, le64_to_cpu(attr->nres.alloc_size));
+	slen = 0;
+	*clst_data = clen;
+
+	/*
+	 * The frame is compressed if *clst_data + slen >= clst_frame
+	 * Check next fragments
+	 */
+	while ((vcn += clen) < alen) {
+		vcn_next = vcn;
+
+		if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) ||
+		    vcn_next != vcn) {
+			err = attr_load_runs_vcn(ni, attr->type,
+						 attr_name(attr),
+						 attr->name_len, run, vcn_next);
+			if (err)
+				return err;
+			vcn = vcn_next;
+
+			if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx))
+				return -EINVAL;
+		}
+
+		if (lcn == SPARSE_LCN) {
+			slen += clen;
+		} else {
+			if (slen) {
+				/*
+				 * data_clusters + sparse_clusters =
+				 * not enough for frame
+				 */
+				return -EINVAL;
+			}
+			*clst_data += clen;
+		}
+
+		if (*clst_data + slen >= clst_frame) {
+			if (!slen) {
+				/*
+				 * There is no sparsed clusters in this frame
+				 * So it is not compressed
+				 */
+				*clst_data = clst_frame;
+			} else {
+				/*frame is compressed*/
+			}
+			break;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * attr_allocate_frame
+ *
+ * allocate/free clusters for 'frame'
+ * assumed: down_write(&ni->file.run_lock);
+ */
+int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
+			u64 new_valid)
+{
+	int err = 0;
+	struct runs_tree *run = &ni->file.run;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST svcn, evcn1, next_svcn, lcn, len;
+	CLST vcn, end, clst_data;
+	u64 total_size, valid_size, data_size;
+
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
+	if (!attr_b)
+		return -ENOENT;
+
+	if (!is_attr_ext(attr_b))
+		return -EINVAL;
+
+	vcn = frame << NTFS_LZNT_CUNIT;
+	total_size = le64_to_cpu(attr_b->nres.total_size);
+
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+	data_size = le64_to_cpu(attr_b->nres.data_size);
+
+	if (svcn <= vcn && vcn < evcn1) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto out;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	err = attr_load_runs(attr, ni, run, NULL);
+	if (err)
+		goto out;
+
+	err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data);
+	if (err)
+		goto out;
+
+	total_size -= (u64)clst_data << sbi->cluster_bits;
+
+	len = bytes_to_cluster(sbi, compr_size);
+
+	if (len == clst_data)
+		goto out;
+
+	if (len < clst_data) {
+		err = run_deallocate_ex(sbi, run, vcn + len, clst_data - len,
+					NULL, true);
+		if (err)
+			goto out;
+
+		if (!run_add_entry(run, vcn + len, SPARSE_LCN, clst_data - len,
+				   false)) {
+			err = -ENOMEM;
+			goto out;
+		}
+		end = vcn + clst_data;
+		/* run contains updated range [vcn + len : end) */
+	} else {
+		CLST alen, hint = 0;
+		/* Get the last lcn to allocate from */
+		if (vcn + clst_data &&
+		    !run_lookup_entry(run, vcn + clst_data - 1, &hint, NULL,
+				      NULL)) {
+			hint = -1;
+		}
+
+		err = attr_allocate_clusters(sbi, run, vcn + clst_data,
+					     hint + 1, len - clst_data, NULL, 0,
+					     &alen, 0, &lcn);
+		if (err)
+			goto out;
+
+		end = vcn + len;
+		/* run contains updated range [vcn + clst_data : end) */
+	}
+
+	total_size += (u64)len << sbi->cluster_bits;
+
+repack:
+	err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn);
+	if (err)
+		goto out;
+
+	attr_b->nres.total_size = cpu_to_le64(total_size);
+	inode_set_bytes(&ni->vfs_inode, total_size);
+
+	mi_b->dirty = true;
+	mark_inode_dirty(&ni->vfs_inode);
+
+	/* stored [vcn : next_svcn) from [vcn : end) */
+	next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+
+	if (end <= evcn1) {
+		if (next_svcn == evcn1) {
+			/* Normal way. update attribute and exit */
+			goto ok;
+		}
+		/* add new segment [next_svcn : evcn1 - next_svcn )*/
+		if (!ni->attr_list.size) {
+			err = ni_create_attr_list(ni);
+			if (err)
+				goto out;
+			/* layout of records is changed */
+			le_b = NULL;
+			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
+					      0, NULL, &mi_b);
+			if (!attr_b) {
+				err = -ENOENT;
+				goto out;
+			}
+
+			attr = attr_b;
+			le = le_b;
+			mi = mi_b;
+			goto repack;
+		}
+	}
+
+	svcn = evcn1;
+
+	/* Estimate next attribute */
+	attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi);
+
+	if (attr) {
+		CLST alloc = bytes_to_cluster(
+			sbi, le64_to_cpu(attr_b->nres.alloc_size));
+		CLST evcn = le64_to_cpu(attr->nres.evcn);
+
+		if (end < next_svcn)
+			end = next_svcn;
+		while (end > evcn) {
+			/* remove segment [svcn : evcn)*/
+			mi_remove_attr(mi, attr);
+
+			if (!al_remove_le(ni, le)) {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (evcn + 1 >= alloc) {
+				/* last attribute segment */
+				evcn1 = evcn + 1;
+				goto ins_ext;
+			}
+
+			if (ni_load_mi(ni, le, &mi)) {
+				attr = NULL;
+				goto out;
+			}
+
+			attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0,
+					    &le->id);
+			if (!attr) {
+				err = -EINVAL;
+				goto out;
+			}
+			svcn = le64_to_cpu(attr->nres.svcn);
+			evcn = le64_to_cpu(attr->nres.evcn);
+		}
+
+		if (end < svcn)
+			end = svcn;
+
+		err = attr_load_runs(attr, ni, run, &end);
+		if (err)
+			goto out;
+
+		evcn1 = evcn + 1;
+		attr->nres.svcn = cpu_to_le64(next_svcn);
+		err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn);
+		if (err)
+			goto out;
+
+		le->vcn = cpu_to_le64(next_svcn);
+		ni->attr_list.dirty = true;
+		mi->dirty = true;
+
+		next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+ins_ext:
+	if (evcn1 > next_svcn) {
+		err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
+					    next_svcn, evcn1 - next_svcn,
+					    attr_b->flags, &attr, &mi);
+		if (err)
+			goto out;
+	}
+ok:
+	run_truncate_around(run, vcn);
+out:
+	if (new_valid > data_size)
+		new_valid = data_size;
+
+	valid_size = le64_to_cpu(attr_b->nres.valid_size);
+	if (new_valid != valid_size) {
+		attr_b->nres.valid_size = cpu_to_le64(valid_size);
+		mi_b->dirty = true;
+	}
+
+	return err;
+}
+
+/* Collapse range in file */
+int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
+{
+	int err = 0;
+	struct runs_tree *run = &ni->file.run;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST svcn, evcn1, len, dealloc, alen;
+	CLST vcn, end;
+	u64 valid_size, data_size, alloc_size, total_size;
+	u32 mask;
+	__le16 a_flags;
+
+	if (!bytes)
+		return 0;
+
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
+	if (!attr_b)
+		return -ENOENT;
+
+	if (!attr_b->non_res) {
+		/* Attribute is resident. Nothing to do? */
+		return 0;
+	}
+
+	data_size = le64_to_cpu(attr_b->nres.data_size);
+	alloc_size = le64_to_cpu(attr_b->nres.alloc_size);
+	a_flags = attr_b->flags;
+
+	if (is_attr_ext(attr_b)) {
+		total_size = le64_to_cpu(attr_b->nres.total_size);
+		mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1;
+	} else {
+		total_size = alloc_size;
+		mask = sbi->cluster_mask;
+	}
+
+	if ((vbo & mask) || (bytes & mask)) {
+		/* allow to collapse only cluster aligned ranges */
+		return -EINVAL;
+	}
+
+	if (vbo > data_size)
+		return -EINVAL;
+
+	down_write(&ni->file.run_lock);
+
+	if (vbo + bytes >= data_size) {
+		u64 new_valid = min(ni->i_valid, vbo);
+
+		/* Simple truncate file at 'vbo' */
+		truncate_setsize(&ni->vfs_inode, vbo);
+		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, vbo,
+				    &new_valid, true, NULL);
+
+		if (!err && new_valid < ni->i_valid)
+			ni->i_valid = new_valid;
+
+		goto out;
+	}
+
+	/*
+	 * Enumerate all attribute segments and collapse
+	 */
+	alen = alloc_size >> sbi->cluster_bits;
+	vcn = vbo >> sbi->cluster_bits;
+	len = bytes >> sbi->cluster_bits;
+	end = vcn + len;
+	dealloc = 0;
+
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+
+	if (svcn <= vcn && vcn < evcn1) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto out;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	for (;;) {
+		if (svcn >= end) {
+			/* shift vcn */
+			attr->nres.svcn = cpu_to_le64(svcn - len);
+			attr->nres.evcn = cpu_to_le64(evcn1 - 1 - len);
+			if (le) {
+				le->vcn = attr->nres.svcn;
+				ni->attr_list.dirty = true;
+			}
+			mi->dirty = true;
+		} else if (svcn < vcn || end < evcn1) {
+			CLST vcn1, eat, next_svcn;
+
+			/* collapse a part of this attribute segment */
+			err = attr_load_runs(attr, ni, run, &svcn);
+			if (err)
+				goto out;
+			vcn1 = max(vcn, svcn);
+			eat = min(end, evcn1) - vcn1;
+
+			err = run_deallocate_ex(sbi, run, vcn1, eat, &dealloc,
+						true);
+			if (err)
+				goto out;
+
+			if (!run_collapse_range(run, vcn1, eat)) {
+				err = -ENOMEM;
+				goto out;
+			}
+
+			if (svcn >= vcn) {
+				/* shift vcn */
+				attr->nres.svcn = cpu_to_le64(vcn);
+				if (le) {
+					le->vcn = attr->nres.svcn;
+					ni->attr_list.dirty = true;
+				}
+			}
+
+			err = mi_pack_runs(mi, attr, run, evcn1 - svcn - eat);
+			if (err)
+				goto out;
+
+			next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+			if (next_svcn + eat < evcn1) {
+				err = ni_insert_nonresident(
+					ni, ATTR_DATA, NULL, 0, run, next_svcn,
+					evcn1 - eat - next_svcn, a_flags, &attr,
+					&mi);
+				if (err)
+					goto out;
+
+				/* layout of records maybe changed */
+				attr_b = NULL;
+				le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0,
+						&next_svcn);
+				if (!le) {
+					err = -EINVAL;
+					goto out;
+				}
+			}
+
+			/* free all allocated memory */
+			run_truncate(run, 0);
+		} else {
+			u16 le_sz;
+			u16 roff = le16_to_cpu(attr->nres.run_off);
+
+			/*run==1 means unpack and deallocate*/
+			run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn,
+				      evcn1 - 1, svcn, Add2Ptr(attr, roff),
+				      le32_to_cpu(attr->size) - roff);
+
+			/* delete this attribute segment */
+			mi_remove_attr(mi, attr);
+			if (!le)
+				break;
+
+			le_sz = le16_to_cpu(le->size);
+			if (!al_remove_le(ni, le)) {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (evcn1 >= alen)
+				break;
+
+			if (!svcn) {
+				/* Load next record that contains this attribute */
+				if (ni_load_mi(ni, le, &mi)) {
+					err = -EINVAL;
+					goto out;
+				}
+
+				/* Look for required attribute */
+				attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL,
+						    0, &le->id);
+				if (!attr) {
+					err = -EINVAL;
+					goto out;
+				}
+				goto next_attr;
+			}
+			le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz);
+		}
+
+		if (evcn1 >= alen)
+			break;
+
+		attr = ni_enum_attr_ex(ni, attr, &le, &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+next_attr:
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	if (!attr_b) {
+		le_b = NULL;
+		attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL,
+				      &mi_b);
+		if (!attr_b) {
+			err = -ENOENT;
+			goto out;
+		}
+	}
+
+	data_size -= bytes;
+	valid_size = ni->i_valid;
+	if (vbo + bytes <= valid_size)
+		valid_size -= bytes;
+	else if (vbo < valid_size)
+		valid_size = vbo;
+
+	attr_b->nres.alloc_size = cpu_to_le64(alloc_size - bytes);
+	attr_b->nres.data_size = cpu_to_le64(data_size);
+	attr_b->nres.valid_size = cpu_to_le64(min(valid_size, data_size));
+	total_size -= (u64)dealloc << sbi->cluster_bits;
+	if (is_attr_ext(attr_b))
+		attr_b->nres.total_size = cpu_to_le64(total_size);
+	mi_b->dirty = true;
+
+	/*update inode size*/
+	ni->i_valid = valid_size;
+	ni->vfs_inode.i_size = data_size;
+	inode_set_bytes(&ni->vfs_inode, total_size);
+	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+	mark_inode_dirty(&ni->vfs_inode);
+
+out:
+	up_write(&ni->file.run_lock);
+	if (err)
+		make_bad_inode(&ni->vfs_inode);
+
+	return err;
+}
+
+/* not for normal files */
+int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes)
+{
+	int err = 0;
+	struct runs_tree *run = &ni->file.run;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST svcn, evcn1, vcn, len, end, alen, dealloc;
+	u64 total_size, alloc_size;
+
+	if (!bytes)
+		return 0;
+
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
+	if (!attr_b)
+		return -ENOENT;
+
+	if (!attr_b->non_res) {
+		u32 data_size = le32_to_cpu(attr->res.data_size);
+		u32 from, to;
+
+		if (vbo > data_size)
+			return 0;
+
+		from = vbo;
+		to = (vbo + bytes) < data_size ? (vbo + bytes) : data_size;
+		memset(Add2Ptr(resident_data(attr_b), from), 0, to - from);
+		return 0;
+	}
+
+	/* TODO: add support for normal files too */
+	if (!is_attr_ext(attr_b))
+		return -EOPNOTSUPP;
+
+	alloc_size = le64_to_cpu(attr_b->nres.alloc_size);
+	total_size = le64_to_cpu(attr_b->nres.total_size);
+
+	if (vbo >= alloc_size) {
+		// NOTE: it is allowed
+		return 0;
+	}
+
+	if (vbo + bytes > alloc_size)
+		bytes = alloc_size - vbo;
+
+	down_write(&ni->file.run_lock);
+	/*
+	 * Enumerate all attribute segments and punch hole where necessary
+	 */
+	alen = alloc_size >> sbi->cluster_bits;
+	vcn = vbo >> sbi->cluster_bits;
+	len = bytes >> sbi->cluster_bits;
+	end = vcn + len;
+	dealloc = 0;
+
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+
+	if (svcn <= vcn && vcn < evcn1) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto out;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	while (svcn < end) {
+		CLST vcn1, zero, dealloc2;
+
+		err = attr_load_runs(attr, ni, run, &svcn);
+		if (err)
+			goto out;
+		vcn1 = max(vcn, svcn);
+		zero = min(end, evcn1) - vcn1;
+
+		dealloc2 = dealloc;
+		err = run_deallocate_ex(sbi, run, vcn1, zero, &dealloc, true);
+		if (err)
+			goto out;
+
+		if (dealloc2 == dealloc) {
+			/* looks like  the required range is already sparsed */
+		} else {
+			if (!run_add_entry(run, vcn1, SPARSE_LCN, zero,
+					   false)) {
+				err = -ENOMEM;
+				goto out;
+			}
+
+			err = mi_pack_runs(mi, attr, run, evcn1 - svcn);
+			if (err)
+				goto out;
+		}
+		/* free all allocated memory */
+		run_truncate(run, 0);
+
+		if (evcn1 >= alen)
+			break;
+
+		attr = ni_enum_attr_ex(ni, attr, &le, &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	total_size -= (u64)dealloc << sbi->cluster_bits;
+	attr_b->nres.total_size = cpu_to_le64(total_size);
+	mi_b->dirty = true;
+
+	/*update inode size*/
+	inode_set_bytes(&ni->vfs_inode, total_size);
+	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+	mark_inode_dirty(&ni->vfs_inode);
+
+out:
+	up_write(&ni->file.run_lock);
+	if (err)
+		make_bad_inode(&ni->vfs_inode);
+
+	return err;
+}
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
new file mode 100644
index 000000000..ea561361b
--- /dev/null
+++ b/fs/ntfs3/attrlist.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/* Returns true if le is valid */
+static inline bool al_is_valid_le(const struct ntfs_inode *ni,
+				  struct ATTR_LIST_ENTRY *le)
+{
+	if (!le || !ni->attr_list.le || !ni->attr_list.size)
+		return false;
+
+	return PtrOffset(ni->attr_list.le, le) + le16_to_cpu(le->size) <=
+	       ni->attr_list.size;
+}
+
+void al_destroy(struct ntfs_inode *ni)
+{
+	run_close(&ni->attr_list.run);
+	ntfs_free(ni->attr_list.le);
+	ni->attr_list.le = NULL;
+	ni->attr_list.size = 0;
+	ni->attr_list.dirty = false;
+}
+
+/*
+ * ntfs_load_attr_list
+ *
+ * This method makes sure that the ATTRIB list, if present,
+ * has been properly set up.
+ */
+int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
+{
+	int err;
+	size_t lsize;
+	void *le = NULL;
+
+	if (ni->attr_list.size)
+		return 0;
+
+	if (!attr->non_res) {
+		lsize = le32_to_cpu(attr->res.data_size);
+		le = ntfs_malloc(al_aligned(lsize));
+		if (!le) {
+			err = -ENOMEM;
+			goto out;
+		}
+		memcpy(le, resident_data(attr), lsize);
+	} else if (attr->nres.svcn) {
+		err = -EINVAL;
+		goto out;
+	} else {
+		u16 run_off = le16_to_cpu(attr->nres.run_off);
+
+		lsize = le64_to_cpu(attr->nres.data_size);
+
+		run_init(&ni->attr_list.run);
+
+		err = run_unpack_ex(&ni->attr_list.run, ni->mi.sbi, ni->mi.rno,
+				    0, le64_to_cpu(attr->nres.evcn), 0,
+				    Add2Ptr(attr, run_off),
+				    le32_to_cpu(attr->size) - run_off);
+		if (err < 0)
+			goto out;
+
+		le = ntfs_malloc(al_aligned(lsize));
+		if (!le) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = ntfs_read_run_nb(ni->mi.sbi, &ni->attr_list.run, 0, le,
+				       lsize, NULL);
+		if (err)
+			goto out;
+	}
+
+	ni->attr_list.size = lsize;
+	ni->attr_list.le = le;
+
+	return 0;
+
+out:
+	ni->attr_list.le = le;
+	al_destroy(ni);
+
+	return err;
+}
+
+/*
+ * al_enumerate
+ *
+ * Returns the next list 'le'
+ * if 'le' is NULL then returns the first 'le'
+ */
+struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
+				     struct ATTR_LIST_ENTRY *le)
+{
+	size_t off;
+	u16 sz;
+
+	if (!le) {
+		le = ni->attr_list.le;
+	} else {
+		sz = le16_to_cpu(le->size);
+		if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
+			/* Impossible 'cause we should not return such 'le' */
+			return NULL;
+		}
+		le = Add2Ptr(le, sz);
+	}
+
+	/* Check boundary */
+	off = PtrOffset(ni->attr_list.le, le);
+	if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
+		// The regular end of list
+		return NULL;
+	}
+
+	sz = le16_to_cpu(le->size);
+
+	/* Check 'le' for errors */
+	if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
+	    off + sz > ni->attr_list.size ||
+	    sz < le->name_off + le->name_len * sizeof(short)) {
+		return NULL;
+	}
+
+	return le;
+}
+
+/*
+ * al_find_le
+ *
+ * finds the first 'le' in the list which matches type, name and vcn
+ * Returns NULL if not found
+ */
+struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni,
+				   struct ATTR_LIST_ENTRY *le,
+				   const struct ATTRIB *attr)
+{
+	CLST svcn = attr_svcn(attr);
+
+	return al_find_ex(ni, le, attr->type, attr_name(attr), attr->name_len,
+			  &svcn);
+}
+
+/*
+ * al_find_ex
+ *
+ * finds the first 'le' in the list which matches type, name and vcn
+ * Returns NULL if not found
+ */
+struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni,
+				   struct ATTR_LIST_ENTRY *le,
+				   enum ATTR_TYPE type, const __le16 *name,
+				   u8 name_len, const CLST *vcn)
+{
+	struct ATTR_LIST_ENTRY *ret = NULL;
+	u32 type_in = le32_to_cpu(type);
+
+	while ((le = al_enumerate(ni, le))) {
+		u64 le_vcn;
+		int diff = le32_to_cpu(le->type) - type_in;
+
+		/* List entries are sorted by type, name and vcn */
+		if (diff < 0)
+			continue;
+
+		if (diff > 0)
+			return ret;
+
+		if (le->name_len != name_len)
+			continue;
+
+		le_vcn = le64_to_cpu(le->vcn);
+		if (!le_vcn) {
+			/*
+			 * compare entry names only for entry with vcn == 0
+			 */
+			diff = ntfs_cmp_names(le_name(le), name_len, name,
+					      name_len, ni->mi.sbi->upcase,
+					      true);
+			if (diff < 0)
+				continue;
+
+			if (diff > 0)
+				return ret;
+		}
+
+		if (!vcn)
+			return le;
+
+		if (*vcn == le_vcn)
+			return le;
+
+		if (*vcn < le_vcn)
+			return ret;
+
+		ret = le;
+	}
+
+	return ret;
+}
+
+/*
+ * al_find_le_to_insert
+ *
+ * finds the first list entry which matches type, name and vcn
+ */
+static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni,
+						    enum ATTR_TYPE type,
+						    const __le16 *name,
+						    u8 name_len, CLST vcn)
+{
+	struct ATTR_LIST_ENTRY *le = NULL, *prev;
+	u32 type_in = le32_to_cpu(type);
+
+	/* List entries are sorted by type, name, vcn */
+	while ((le = al_enumerate(ni, prev = le))) {
+		int diff = le32_to_cpu(le->type) - type_in;
+
+		if (diff < 0)
+			continue;
+
+		if (diff > 0)
+			return le;
+
+		if (!le->vcn) {
+			/*
+			 * compare entry names only for entry with vcn == 0
+			 */
+			diff = ntfs_cmp_names(le_name(le), le->name_len, name,
+					      name_len, ni->mi.sbi->upcase,
+					      true);
+			if (diff < 0)
+				continue;
+
+			if (diff > 0)
+				return le;
+		}
+
+		if (le64_to_cpu(le->vcn) >= vcn)
+			return le;
+	}
+
+	return prev ? Add2Ptr(prev, le16_to_cpu(prev->size)) : ni->attr_list.le;
+}
+
+/*
+ * al_add_le
+ *
+ * adds an "attribute list entry" to the list.
+ */
+int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
+	      u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref,
+	      struct ATTR_LIST_ENTRY **new_le)
+{
+	int err;
+	struct ATTRIB *attr;
+	struct ATTR_LIST_ENTRY *le;
+	size_t off;
+	u16 sz;
+	size_t asize, new_asize;
+	u64 new_size;
+	typeof(ni->attr_list) *al = &ni->attr_list;
+
+	/*
+	 * Compute the size of the new 'le'
+	 */
+	sz = le_size(name_len);
+	new_size = al->size + sz;
+	asize = al_aligned(al->size);
+	new_asize = al_aligned(new_size);
+
+	/* Scan forward to the point at which the new 'le' should be inserted. */
+	le = al_find_le_to_insert(ni, type, name, name_len, svcn);
+	off = PtrOffset(al->le, le);
+
+	if (new_size > asize) {
+		void *ptr = ntfs_malloc(new_asize);
+
+		if (!ptr)
+			return -ENOMEM;
+
+		memcpy(ptr, al->le, off);
+		memcpy(Add2Ptr(ptr, off + sz), le, al->size - off);
+		le = Add2Ptr(ptr, off);
+		ntfs_free(al->le);
+		al->le = ptr;
+	} else {
+		memmove(Add2Ptr(le, sz), le, al->size - off);
+	}
+
+	al->size = new_size;
+
+	le->type = type;
+	le->size = cpu_to_le16(sz);
+	le->name_len = name_len;
+	le->name_off = offsetof(struct ATTR_LIST_ENTRY, name);
+	le->vcn = cpu_to_le64(svcn);
+	le->ref = *ref;
+	le->id = id;
+	memcpy(le->name, name, sizeof(short) * name_len);
+
+	al->dirty = true;
+
+	err = attr_set_size(ni, ATTR_LIST, NULL, 0, &al->run, new_size,
+			    &new_size, true, &attr);
+	if (err)
+		return err;
+
+	if (attr && attr->non_res) {
+		err = ntfs_sb_write_run(ni->mi.sbi, &al->run, 0, al->le,
+					al->size);
+		if (err)
+			return err;
+	}
+
+	al->dirty = false;
+	*new_le = le;
+
+	return 0;
+}
+
+/*
+ * al_remove_le
+ *
+ * removes 'le' from attribute list
+ */
+bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le)
+{
+	u16 size;
+	size_t off;
+	typeof(ni->attr_list) *al = &ni->attr_list;
+
+	if (!al_is_valid_le(ni, le))
+		return false;
+
+	/* Save on stack the size of 'le' */
+	size = le16_to_cpu(le->size);
+	off = PtrOffset(al->le, le);
+
+	memmove(le, Add2Ptr(le, size), al->size - (off + size));
+
+	al->size -= size;
+	al->dirty = true;
+
+	return true;
+}
+
+/*
+ * al_delete_le
+ *
+ * deletes from the list the first 'le' which matches its parameters.
+ */
+bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
+		  const __le16 *name, size_t name_len,
+		  const struct MFT_REF *ref)
+{
+	u16 size;
+	struct ATTR_LIST_ENTRY *le;
+	size_t off;
+	typeof(ni->attr_list) *al = &ni->attr_list;
+
+	/* Scan forward to the first 'le' that matches the input */
+	le = al_find_ex(ni, NULL, type, name, name_len, &vcn);
+	if (!le)
+		return false;
+
+	off = PtrOffset(al->le, le);
+
+next:
+	if (off >= al->size)
+		return false;
+	if (le->type != type)
+		return false;
+	if (le->name_len != name_len)
+		return false;
+	if (name_len && ntfs_cmp_names(le_name(le), name_len, name, name_len,
+				       ni->mi.sbi->upcase, true))
+		return false;
+	if (le64_to_cpu(le->vcn) != vcn)
+		return false;
+
+	/*
+	 * The caller specified a segment reference, so we have to
+	 * scan through the matching entries until we find that segment
+	 * reference or we run of matching entries.
+	 */
+	if (ref && memcmp(ref, &le->ref, sizeof(*ref))) {
+		off += le16_to_cpu(le->size);
+		le = Add2Ptr(al->le, off);
+		goto next;
+	}
+
+	/* Save on stack the size of 'le' */
+	size = le16_to_cpu(le->size);
+	/* Delete 'le'. */
+	memmove(le, Add2Ptr(le, size), al->size - (off + size));
+
+	al->size -= size;
+	al->dirty = true;
+
+	return true;
+}
+
+/*
+ * al_update
+ */
+int al_update(struct ntfs_inode *ni)
+{
+	int err;
+	struct ATTRIB *attr;
+	typeof(ni->attr_list) *al = &ni->attr_list;
+
+	if (!al->dirty || !al->size)
+		return 0;
+
+	/*
+	 * attribute list increased on demand in al_add_le
+	 * attribute list decreased here
+	 */
+	err = attr_set_size(ni, ATTR_LIST, NULL, 0, &al->run, al->size, NULL,
+			    false, &attr);
+	if (err)
+		goto out;
+
+	if (!attr->non_res) {
+		memcpy(resident_data(attr), al->le, al->size);
+	} else {
+		err = ntfs_sb_write_run(ni->mi.sbi, &al->run, 0, al->le,
+					al->size);
+		if (err)
+			goto out;
+
+		attr->nres.valid_size = attr->nres.data_size;
+	}
+
+	ni->mi.dirty = true;
+	al->dirty = false;
+
+out:
+	return err;
+}
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
new file mode 100644
index 000000000..759df507c
--- /dev/null
+++ b/fs/ntfs3/xattr.c
@@ -0,0 +1,1046 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+// clang-format off
+#define SYSTEM_DOS_ATTRIB    "system.dos_attrib"
+#define SYSTEM_NTFS_ATTRIB   "system.ntfs_attrib"
+#define SYSTEM_NTFS_SECURITY "system.ntfs_security"
+// clang-format on
+
+static inline size_t unpacked_ea_size(const struct EA_FULL *ea)
+{
+	return ea->size ? le32_to_cpu(ea->size)
+			: DwordAlign(struct_size(
+				  ea, name,
+				  1 + ea->name_len + le16_to_cpu(ea->elength)));
+}
+
+static inline size_t packed_ea_size(const struct EA_FULL *ea)
+{
+	return struct_size(ea, name,
+			   1 + ea->name_len + le16_to_cpu(ea->elength)) -
+	       offsetof(struct EA_FULL, flags);
+}
+
+/*
+ * find_ea
+ *
+ * assume there is at least one xattr in the list
+ */
+static inline bool find_ea(const struct EA_FULL *ea_all, u32 bytes,
+			   const char *name, u8 name_len, u32 *off)
+{
+	*off = 0;
+
+	if (!ea_all || !bytes)
+		return false;
+
+	for (;;) {
+		const struct EA_FULL *ea = Add2Ptr(ea_all, *off);
+		u32 next_off = *off + unpacked_ea_size(ea);
+
+		if (next_off > bytes)
+			return false;
+
+		if (ea->name_len == name_len &&
+		    !memcmp(ea->name, name, name_len))
+			return true;
+
+		*off = next_off;
+		if (next_off >= bytes)
+			return false;
+	}
+}
+
+/*
+ * ntfs_read_ea
+ *
+ * reads all extended attributes
+ * ea - new allocated memory
+ * info - pointer into resident data
+ */
+static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea,
+			size_t add_bytes, const struct EA_INFO **info)
+{
+	int err;
+	struct ATTR_LIST_ENTRY *le = NULL;
+	struct ATTRIB *attr_info, *attr_ea;
+	void *ea_p;
+	u32 size;
+
+	static_assert(le32_to_cpu(ATTR_EA_INFO) < le32_to_cpu(ATTR_EA));
+
+	*ea = NULL;
+	*info = NULL;
+
+	attr_info =
+		ni_find_attr(ni, NULL, &le, ATTR_EA_INFO, NULL, 0, NULL, NULL);
+	attr_ea =
+		ni_find_attr(ni, attr_info, &le, ATTR_EA, NULL, 0, NULL, NULL);
+
+	if (!attr_ea || !attr_info)
+		return 0;
+
+	*info = resident_data_ex(attr_info, sizeof(struct EA_INFO));
+	if (!*info)
+		return -EINVAL;
+
+	/* Check Ea limit */
+	size = le32_to_cpu((*info)->size);
+	if (size > ni->mi.sbi->ea_max_size)
+		return -EFBIG;
+
+	if (attr_size(attr_ea) > ni->mi.sbi->ea_max_size)
+		return -EFBIG;
+
+	/* Allocate memory for packed Ea */
+	ea_p = ntfs_malloc(size + add_bytes);
+	if (!ea_p)
+		return -ENOMEM;
+
+	if (a...
 
[truncated message content]

[Linux-NTFS-Dev] [PATCH v27 10/10] fs/ntfs3: Add MAINTAINERS

[Konstantin K. <alm...@pa...>]

This adds MAINTAINERS

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9c3428380..3b6b48537 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13279,6 +13279,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs.git
 F:	Documentation/filesystems/ntfs.rst
 F:	fs/ntfs/
 
+NTFS3 FILESYSTEM
+M:	Konstantin Komarov <alm...@pa...>
+S:	Supported
+W:	http://www.paragon-software.com/
+F:	Documentation/filesystems/ntfs3.rst
+F:	fs/ntfs3/
+
 NUBUS SUBSYSTEM
 M:	Finn Thain <ft...@li...>
 L:	lin...@li...
-- 
2.25.4

[Linux-NTFS-Dev] [PATCH v27 08/10] fs/ntfs3: Add Kconfig, Makefile and doc

[Konstantin K. <alm...@pa...>]

This adds Kconfig, Makefile and doc

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 Documentation/filesystems/ntfs3.rst | 107 ++++++++++++++++++++++++++++
 fs/ntfs3/Kconfig                    |  46 ++++++++++++
 fs/ntfs3/Makefile                   |  36 ++++++++++
 3 files changed, 189 insertions(+)
 create mode 100644 Documentation/filesystems/ntfs3.rst
 create mode 100644 fs/ntfs3/Kconfig
 create mode 100644 fs/ntfs3/Makefile

diff --git a/Documentation/filesystems/ntfs3.rst b/Documentation/filesystems/ntfs3.rst
new file mode 100644
index 000000000..fb2906736
--- /dev/null
+++ b/Documentation/filesystems/ntfs3.rst
@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====
+NTFS3
+=====
+
+
+Summary and Features
+====================
+
+NTFS3 is fully functional NTFS Read-Write driver. The driver works with
+NTFS versions up to 3.1, normal/compressed/sparse files
+and journal replaying. File system type to use on mount is 'ntfs3'.
+
+- This driver implements NTFS read/write support for normal, sparse and
+  compressed files.
+- Supports native journal replaying;
+- Supports extended attributes
+	Predefined extended attributes:
+	- 'system.ntfs_security' gets/sets security
+			descriptor (SECURITY_DESCRIPTOR_RELATIVE)
+	- 'system.ntfs_attrib' gets/sets ntfs file/dir attributes.
+		Note: applied to empty files, this allows to switch type between
+		sparse(0x200), compressed(0x800) and normal;
+- Supports NFS export of mounted NTFS volumes.
+
+Mount Options
+=============
+
+The list below describes mount options supported by NTFS3 driver in addition to
+generic ones.
+
+===============================================================================
+
+nls=name		This option informs the driver how to interpret path
+			strings and translate them to Unicode and back. If
+			this option is not set, the default codepage will be
+			used (CONFIG_NLS_DEFAULT).
+			Examples:
+				'nls=utf8'
+
+uid=
+gid=
+umask=			Controls the default permissions for files/directories created
+			after the NTFS volume is mounted.
+
+fmask=
+dmask=			Instead of specifying umask which applies both to
+			files and directories, fmask applies only to files and
+			dmask only to directories.
+
+nohidden		Files with the Windows-specific HIDDEN (FILE_ATTRIBUTE_HIDDEN)
+			attribute will not be shown under Linux.
+
+sys_immutable		Files with the Windows-specific SYSTEM
+			(FILE_ATTRIBUTE_SYSTEM) attribute will be marked as system
+			immutable files.
+
+discard			Enable support of the TRIM command for improved performance
+			on delete operations, which is recommended for use with the
+			solid-state drives (SSD).
+
+force			Forces the driver to mount partitions even if 'dirty' flag
+			(volume dirty) is set. Not recommended for use.
+
+sparse			Create new files as "sparse".
+
+showmeta		Use this parameter to show all meta-files (System Files) on
+			a mounted NTFS partition.
+			By default, all meta-files are hidden.
+
+prealloc		Preallocate space for files excessively when file size is
+			increasing on writes. Decreases fragmentation in case of
+			parallel write operations to different files.
+
+no_acs_rules		"No access rules" mount option sets access rights for
+			files/folders to 777 and owner/group to root. This mount
+			option absorbs all other permissions:
+			- permissions change for files/folders will be reported
+				as successful, but they will remain 777;
+			- owner/group change will be reported as successful, but
+				they will stay as root
+
+acl			Support POSIX ACLs (Access Control Lists). Effective if
+			supported by Kernel. Not to be confused with NTFS ACLs.
+			The option specified as acl enables support for POSIX ACLs.
+
+noatime			All files and directories will not update their last access
+			time attribute if a partition is mounted with this parameter.
+			This option can speed up file system operation.
+
+===============================================================================
+
+ToDo list
+=========
+
+- Full journaling support (currently journal replaying is supported) over JBD.
+
+
+References
+==========
+https://www.paragon-software.com/home/ntfs-linux-professional/
+	- Commercial version of the NTFS driver for Linux.
+
+al...@pa...
+	- Direct e-mail address for feedback and requests on the NTFS3 implementation.
+
diff --git a/fs/ntfs3/Kconfig b/fs/ntfs3/Kconfig
new file mode 100644
index 000000000..6e4cbc48a
--- /dev/null
+++ b/fs/ntfs3/Kconfig
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config NTFS3_FS
+	tristate "NTFS Read-Write file system support"
+	select NLS
+	help
+	  Windows OS native file system (NTFS) support up to NTFS version 3.1.
+
+	  Y or M enables the NTFS3 driver with full features enabled (read,
+	  write, journal replaying, sparse/compressed files support).
+	  File system type to use on mount is "ntfs3". Module name (M option)
+	  is also "ntfs3".
+
+	  Documentation: <file:Documentation/filesystems/ntfs3.rst>
+
+config NTFS3_64BIT_CLUSTER
+	bool "64 bits per NTFS clusters"
+	depends on NTFS3_FS && 64BIT
+	help
+	  Windows implementation of ntfs.sys uses 32 bits per clusters.
+	  If activated 64 bits per clusters you will be able to use 4k cluster
+	  for 16T+ volumes. Windows will not be able to mount such volumes.
+
+	  It is recommended to say N here.
+
+config NTFS3_LZX_XPRESS
+	bool "activate support of external compressions lzx/xpress"
+	depends on NTFS3_FS
+	help
+	  In Windows 10 one can use command "compact" to compress any files.
+	  4 possible variants of compression are: xpress4k, xpress8k, xpress16k and lzx.
+	  If activated you will be able to read such files correctly.
+
+	  It is recommended to say Y here.
+
+config NTFS3_FS_POSIX_ACL
+	bool "NTFS POSIX Access Control Lists"
+	depends on NTFS3_FS
+	select FS_POSIX_ACL
+	help
+	  POSIX Access Control Lists (ACLs) support additional access rights
+	  for users and groups beyond the standard owner/group/world scheme,
+	  and this option selects support for ACLs specifically for ntfs
+	  filesystems.
+	  NOTE: this is linux only feature. Windows will ignore these ACLs.
+
+	  If you don't know what Access Control Lists are, say N.
diff --git a/fs/ntfs3/Makefile b/fs/ntfs3/Makefile
new file mode 100644
index 000000000..279701b62
--- /dev/null
+++ b/fs/ntfs3/Makefile
@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the ntfs3 filesystem support.
+#
+
+# to check robot warnings
+ccflags-y += -Wint-to-pointer-cast \
+	$(call cc-option,-Wunused-but-set-variable,-Wunused-const-variable) \
+	$(call cc-option,-Wold-style-declaration,-Wout-of-line-declaration)
+
+obj-$(CONFIG_NTFS3_FS) += ntfs3.o
+
+ntfs3-y :=	attrib.o \
+		attrlist.o \
+		bitfunc.o \
+		bitmap.o \
+		dir.o \
+		fsntfs.o \
+		frecord.o \
+		file.o \
+		fslog.o \
+		inode.o \
+		index.o \
+		lznt.o \
+		namei.o \
+		record.o \
+		run.o \
+		super.o \
+		upcase.o \
+		xattr.o
+
+ntfs3-$(CONFIG_NTFS3_LZX_XPRESS) += $(addprefix lib/,\
+		decompress_common.o \
+		lzx_decompress.o \
+		xpress_decompress.o \
+		)
\ No newline at end of file
-- 
2.25.4

[Linux-NTFS-Dev] [PATCH v27 00/10] NTFS read-write driver GPL implementation by Paragon Software

[Konstantin K. <alm...@pa...>]

This patch adds NTFS Read-Write driver to fs/ntfs3.

Having decades of expertise in commercial file systems development and huge
test coverage, we at Paragon Software GmbH want to make our contribution to
the Open Source Community by providing implementation of NTFS Read-Write
driver for the Linux Kernel.

This is fully functional NTFS Read-Write driver. Current version works with
NTFS(including v3.1) and normal/compressed/sparse files and supports journal replaying.

We plan to support this version after the codebase once merged, and add new
features and fix bugs. For example, full journaling support over JBD will be
added in later updates.

v2:
 - patch splitted to chunks (file-wise)
 - build issues fixed
 - sparse and checkpatch.pl errors fixed
 - NULL pointer dereference on mkfs.ntfs-formatted volume mount fixed
 - cosmetics + code cleanup

v3:
 - added acl, noatime, no_acs_rules, prealloc mount options
 - added fiemap support
 - fixed encodings support
 - removed typedefs
 - adapted Kernel-way logging mechanisms
 - fixed typos and corner-case issues

v4:
 - atomic_open() refactored
 - code style updated
 - bugfixes

v5:
- nls/nls_alt mount options added
- Unicode conversion fixes
- Improved very fragmented files operations
- logging cosmetics

v6:
- Security Descriptors processing changed
  added system.ntfs_security xattr to set
  SD
- atomic_open() optimized
- cosmetics

v7:
- Security Descriptors validity checks added (by Mark Harmstone)
- atomic_open() fixed for the compressed file creation with directio
  case
- remount support
- temporarily removed readahead usage
- cosmetics

v8:
- Compressed files operations fixed

v9:
- Further cosmetics applied as suggested
by Joe Perches

v10:
- operations with compressed/sparse files on very fragmented volumes improved
- reduced memory consumption for above cases

v11:
- further compressed files optimizations: reads/writes are now skipping bufferization
- journal wipe to the initial state optimized (bufferization is also skipped)
- optimized run storage (re-packing cluster metainformation)
- fixes based on Matthew Wilcox feedback to the v10
- compressed/sparse/normal could be set for empty files with 'system.ntfs_attrib' xattr

v12:
- nls_alt mount option removed after discussion with Pali Rohar
- fixed ni_repack()
- fixed resident files transition to non-resident when size increasing

v13:
- nested_lock fix (lockdep)
- out-of-bounds read fix (KASAN warning)
- resident->nonresident transition fixed for compressed files
- load_nls() missed fix applied
- some sparse utility warnings fixes

v14:
- support for additional compression types (we've adapted WIMLIB's
  implementation, authored by Eric Biggers, into ntfs3)

v15:
- kernel test robot warnings fixed
- lzx/xpress compression license headers updated

v16:
- lzx/xpress moved to initial ntfs-3g plugin code
- mutexes instead of a global spinlock for compresions
- FALLOC_FL_PUNCH_HOLE and FALLOC_FL_COLLAPSE_RANGE implemented
- CONFIG_NTFS3_FS_POSIX_ACL added

v17:
- FALLOC_FL_COLLAPSE_RANGE fixed
- fixes for Mattew Wilcox's and Andy Lavr's concerns

v18:
- ntfs_alloc macro splitted into two ntfs_malloc + ntfs_zalloc
- attrlist.c: always use ntfs_cmp_names instead of memcmp; compare entry names
  only for entry with vcn == 0
- dir.c: remove unconditional ni_lock in ntfs_readdir
- fslog.c: corrected error case behavior
- index.c: refactored due to modification of ntfs_cmp_names; use rw_semaphore
  for read/write access to alloc_run and bitmap_run while ntfs_readdir
- run.c: separated big/little endian code in functions
- upcase.c: improved ntfs_cmp_names, thanks to Kari Argillander for idea
  and 'bothcase' implementation

v19:
- fixed directory bitmap for 2MB cluster size
- fixed rw_semaphore init for directories

v20:
- fixed issue with incorrect hidden/system attribute setting on
  root subdirectories
- use kvmalloc instead of kmalloc for runs array
- fixed index behavior on volumes with cluster size more than 4k
- current build info is added into module info instead of printing on insmod

v21:
- fixes for clang CFI checks
- fixed sb->s_maxbytes for 32bit clusters
- user.DOSATTRIB is no more intercepted by ntfs3
- corrected xattr limits;  is used
- corrected CONFIG_NTFS3_64BIT_CLUSTER usage
- info about current build is added into module info and printing
on insmod (by Andy Lavr's request)
note: v21 is applicable for 'linux-next' not older than 2021.01.28

v22:
- ntfs_cmp_names() fixed
- raise warning if 'nls->uni2char' fails
- hot fix free clusters code optimized
- use clang-format 11.0 instead of 10.0 to format code

v23:
- corrections for Kernel Test Robot warnings
- kmem_cache_create() utilized to allocate memory in bitmap.c
- cosmetics and comments thru the code

v24:
- BIO_MAX_PAGES -> BIO_MAX_VECS (fix for build issue of v23 vs linux-next)
- minor optimization for LogFile: do not fill it with -1, if it's already there
- index.c: removed 'inline' in definition of hdr_find_split() and hdr_insert_head()

v25:
- restore fs/Makefile in patch
- refactor ntfs_create_inode() to use error-valued pointer
- use mi_get_ref to fill MFT_REF
- minimize checkpatch.pl warnings: replace LogFile with \x24LogFile when printing

v26:
- fixed coccinelle warnings
- fslog.c: fix memory leak and memory overwrite

v27:
- iov_iter_copy_from_user_atomic() replaced by copy_page_from_iter_atomic()
and  iov_iter_advance() removed

Konstantin Komarov (10):
  fs/ntfs3: Add headers and misc files
  fs/ntfs3: Add initialization of super block
  fs/ntfs3: Add bitmap
  fs/ntfs3: Add file operations and implementation
  fs/ntfs3: Add attrib operations
  fs/ntfs3: Add compression
  fs/ntfs3: Add NTFS journal
  fs/ntfs3: Add Kconfig, Makefile and doc
  fs/ntfs3: Add NTFS3 in fs/Kconfig and fs/Makefile
  fs/ntfs3: Add MAINTAINERS

 Documentation/filesystems/ntfs3.rst |  107 +
 MAINTAINERS                         |    7 +
 fs/Kconfig                          |    1 +
 fs/Makefile                         |    1 +
 fs/ntfs3/Kconfig                    |   46 +
 fs/ntfs3/Makefile                   |   36 +
 fs/ntfs3/attrib.c                   | 2082 +++++++++++
 fs/ntfs3/attrlist.c                 |  456 +++
 fs/ntfs3/bitfunc.c                  |  135 +
 fs/ntfs3/bitmap.c                   | 1519 ++++++++
 fs/ntfs3/debug.h                    |   64 +
 fs/ntfs3/dir.c                      |  594 +++
 fs/ntfs3/file.c                     | 1130 ++++++
 fs/ntfs3/frecord.c                  | 3071 ++++++++++++++++
 fs/ntfs3/fslog.c                    | 5181 +++++++++++++++++++++++++++
 fs/ntfs3/fsntfs.c                   | 2542 +++++++++++++
 fs/ntfs3/index.c                    | 2641 ++++++++++++++
 fs/ntfs3/inode.c                    | 2034 +++++++++++
 fs/ntfs3/lib/decompress_common.c    |  332 ++
 fs/ntfs3/lib/decompress_common.h    |  352 ++
 fs/ntfs3/lib/lib.h                  |   26 +
 fs/ntfs3/lib/lzx_decompress.c       |  683 ++++
 fs/ntfs3/lib/xpress_decompress.c    |  155 +
 fs/ntfs3/lznt.c                     |  452 +++
 fs/ntfs3/namei.c                    |  578 +++
 fs/ntfs3/ntfs.h                     | 1238 +++++++
 fs/ntfs3/ntfs_fs.h                  | 1085 ++++++
 fs/ntfs3/record.c                   |  609 ++++
 fs/ntfs3/run.c                      | 1111 ++++++
 fs/ntfs3/super.c                    | 1500 ++++++++
 fs/ntfs3/upcase.c                   |  105 +
 fs/ntfs3/xattr.c                    | 1046 ++++++
 32 files changed, 30919 insertions(+)
 create mode 100644 Documentation/filesystems/ntfs3.rst
 create mode 100644 fs/ntfs3/Kconfig
 create mode 100644 fs/ntfs3/Makefile
 create mode 100644 fs/ntfs3/attrib.c
 create mode 100644 fs/ntfs3/attrlist.c
 create mode 100644 fs/ntfs3/bitfunc.c
 create mode 100644 fs/ntfs3/bitmap.c
 create mode 100644 fs/ntfs3/debug.h
 create mode 100644 fs/ntfs3/dir.c
 create mode 100644 fs/ntfs3/file.c
 create mode 100644 fs/ntfs3/frecord.c
 create mode 100644 fs/ntfs3/fslog.c
 create mode 100644 fs/ntfs3/fsntfs.c
 create mode 100644 fs/ntfs3/index.c
 create mode 100644 fs/ntfs3/inode.c
 create mode 100644 fs/ntfs3/lib/decompress_common.c
 create mode 100644 fs/ntfs3/lib/decompress_common.h
 create mode 100644 fs/ntfs3/lib/lib.h
 create mode 100644 fs/ntfs3/lib/lzx_decompress.c
 create mode 100644 fs/ntfs3/lib/xpress_decompress.c
 create mode 100644 fs/ntfs3/lznt.c
 create mode 100644 fs/ntfs3/namei.c
 create mode 100644 fs/ntfs3/ntfs.h
 create mode 100644 fs/ntfs3/ntfs_fs.h
 create mode 100644 fs/ntfs3/record.c
 create mode 100644 fs/ntfs3/run.c
 create mode 100644 fs/ntfs3/super.c
 create mode 100644 fs/ntfs3/upcase.c
 create mode 100644 fs/ntfs3/xattr.c


base-commit: 5a4cee98ea757e1a2a1354b497afdf8fafc30a20
-- 
2.25.4

Re: [Linux-NTFS-Dev] [PATCH] ntfs: Fix validity check for file name attribute

[Desmond C. Z. Xi <des...@gm...>]

On 29/7/21 4:31 pm, Rolf Eike Beer wrote:
> Hi,
> 
> I was just scanning through some older vulnerabilities and came across
> CVE-2018-12929, CVE-2018-12930, and CVE-2018-12931, which are all still open
> according to linuxkernelcves.com (originally reported against 4.15 [1]). I
> looked into the commits in fs/ntfs/ from 4.15 onwards to see if they were just
> missed, but I can't spot anything there. RedHat claims to have them fixed in
> one of their kernels [2].
> 
> Which makes me wonder if the issue fixed here is a duplicate of the any of the
> above. Is there a reason I can't find any patches for the original issue in
> tree, like the issue only introduced in a custom patchset that Ubuntu/RedHat
> were using? Is this thing worth it's own CVE if it's no duplicate?
> 
> Greetings,
> 
> Eike
> 
> 1) https://marc.info/?t=152407734400002&r=1&w=2
> 2) https://access.redhat.com/errata/RHSA-2019:0641
> 

Hi Eike,

Thanks for digging into this. From a first glance, this bug seems most 
similar to CVE-2018-12929.

However, from the logs, the root causes are probably different. The 
cause of this bug is specifically in the call to 
ntfs_is_extended_system_file [1], but from what I can see this is not 
the case for CVE-2018-12929. I don't know enough to comment whether it 
needs a CVE, but it has been patched on Linux stable (up to 4.4).

It's worth noting that there's another similar bug that was fixed by 
Rustam Kovhaev (+cc) in ntfs_read_locked_inode [2]. This may or may not 
have been the issue in CVE-2018-12929.

Link: 
https://syzkaller.appspot.com/bug?id=a1a1e379b225812688566745c3e2f7242bffc246 
[1]

Link: 
https://syzkaller.appspot.com/bug?id=933dab9c03ac47a3d09dd4b0563a0a8fcb35f282 
[2]

Best wishes,
Desmond

Re: [Linux-NTFS-Dev] [PATCH] ntfs: Fix validity check for file name attribute

[Rolf E. B. <eb...@em...>]

Hi,

I was just scanning through some older vulnerabilities and came across 
CVE-2018-12929, CVE-2018-12930, and CVE-2018-12931, which are all still open 
according to linuxkernelcves.com (originally reported against 4.15 [1]). I 
looked into the commits in fs/ntfs/ from 4.15 onwards to see if they were just 
missed, but I can't spot anything there. RedHat claims to have them fixed in 
one of their kernels [2].

Which makes me wonder if the issue fixed here is a duplicate of the any of the 
above. Is there a reason I can't find any patches for the original issue in 
tree, like the issue only introduced in a custom patchset that Ubuntu/RedHat 
were using? Is this thing worth it's own CVE if it's no duplicate?

Greetings,

Eike

1) https://marc.info/?t=152407734400002&r=1&w=2
2) https://access.redhat.com/errata/RHSA-2019:0641
-- 
Rolf Eike Beer, emlix GmbH, http://www.emlix.com
Fon +49 551 30664-0, Fax +49 551 30664-11
Gothaer Platz 3, 37083 Göttingen, Germany
Sitz der Gesellschaft: Göttingen, Amtsgericht Göttingen HR B 3160
Geschäftsführung: Heike Jordan, Dr. Uwe Kracke – Ust-IdNr.: DE 205 198 055

emlix - smart embedded open source

Re: [Linux-NTFS-Dev] [PATCH v26 00/10] NTFS read-write driver GPL implementation by Paragon Software

[Mohammad R. <moh...@gm...>]

Hi,

I've been using your ntfs driver for sometime now and it's great to 
finally have a good driver for this FS, however i have problem where if 
the power cuts off from my system while writing to the volume the 
partition gets corrupted, this is expected of course but the problem is 
that `ntfsfix` tool can't fix the partition and no matter how many times 
i run it the system will always spits this in the kernel log when trying 
to mount the partition:

     ntfs3: sdb1: volume is dirty and "force" flag is not set!

if i boot to a windows 10 OS then the system is able to mount the volume 
with no problem(even before running chkdsk on it), windows `chkdsk` 
utility can find the errors and fix them, and i can reboot to linux to 
use my partition again with no problem.

it would be nice to have your filesystem utilites published on github so 
we can use them with the current out of the tree driver


Regards