Merge tag 'ntfs-for-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/ntfs

Pull ntfs fixes from Namjae Jeon:

 - fix stale runlist element dereferences in MFT writeback and fallocate

 - fix mrec_lock ABBA deadlock in rename

 - prevent userspace modification of NTFS system files

 - avoid inode eviction/writeback self-deadlocks

 - reject malformed resident attributes in non-resident runlist mapping

 - avoid post_write_mst_fixup() on invalid index blocks

 - fix a hole runlist leak in insert-range error handling

 - sanitize directory lookup MFT references from disk

 - fail attribute-list updates after SB_ACTIVE is cleared during
   teardown

* tag 'ntfs-for-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/ntfs:
  ntfs: fail attrlist updates when the superblock is inactive
  ntfs: sanitize MFT references returned from ntfs_lookup_inode_by_name()
  ntfs: fix hole runlist memory leak in insert range error path
  ntfs: avoid calling post_write_mst_fixup() for invalid index_block
  ntfs: fix WARN_ON for resident attribute in ntfs_map_runlist_nolock()
  ntfs: avoid self-deadlock during inode eviction
  ntfs: make system files immutable to prevent corruption
  ntfs: fix mrec_lock ABBA deadlock in rename
  ntfs: avoid stale runlist element dereference in fallocate
  ntfs: avoid stale runlist element dereference in MFT writeback

8 files changed, 110 insertions, 51 deletions

diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index f2bb56506046..173de4cbee0f 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -249,6 +249,8 @@ static int ntfs_writepages(struct address_space *mapping,
 		.wbc		= wbc,
 		.ops		= &ntfs_writeback_ops,
 	};
+	bool need_iput = false;
+	int ret;
 
 	if (NVolShutdown(ni->vol))
 		return -EIO;
@@ -265,7 +267,20 @@ static int ntfs_writepages(struct address_space *mapping,
 		return -EOPNOTSUPP;
 	}
 
-	return iomap_writepages(&wpc);
+	/*
+	 * Prevent eviction in writeback to avoid deadlock in
+	 * ntfs_drop_big_inode().
+	 */
+	if ((ni->type == AT_DATA || ni->type == AT_INDEX_ALLOCATION) &&
+	    igrab(inode))
+		need_iput = true;
+
+	ret = iomap_writepages(&wpc);
+
+	if (need_iput)
+		iput(inode);
+
+	return ret;
 }
 
 static int ntfs_swap_activate(struct swap_info_struct *sis,
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index dd8828098511..239b7bcbaedf 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -175,7 +175,10 @@ int ntfs_map_runlist_nolock(struct ntfs_inode *ni, s64 vcn, struct ntfs_attr_sea
 				err = -EIO;
 			goto err_out;
 		}
-		WARN_ON(!ctx->attr->non_resident);
+		if (unlikely(!ctx->attr->non_resident)) {
+			err = -EIO;
+			goto err_out;
+		}
 	}
 	a = ctx->attr;
 	/*
@@ -5325,6 +5328,7 @@ int ntfs_non_resident_attr_insert_range(struct ntfs_inode *ni, s64 start_vcn, s6
 	ret = ntfs_attr_map_whole_runlist(ni);
 	if (ret) {
 		up_write(&ni->runlist.lock);
+		kfree(hole_rl);
 		return ret;
 	}
 
@@ -5536,6 +5540,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo
 	s64 old_data_size;
 	s64 vcn_start, vcn_end, vcn_uninit, vcn, try_alloc_cnt;
 	s64 lcn, alloc_cnt;
+	s64 rl_lcn, rl_length, rl_vcn;
 	int err = 0;
 	struct runlist_element *rl;
 	bool balloc;
@@ -5615,19 +5620,23 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo
 	while (vcn < vcn_uninit) {
 		down_read(&ni->runlist.lock);
 		rl = ntfs_attr_find_vcn_nolock(ni, vcn, NULL);
-		up_read(&ni->runlist.lock);
 		if (IS_ERR(rl)) {
+			up_read(&ni->runlist.lock);
 			err = PTR_ERR(rl);
 			goto out;
 		}
+		rl_lcn = rl->lcn;
+		rl_length = rl->length;
+		rl_vcn = rl->vcn;
+		up_read(&ni->runlist.lock);
 
-		if (rl->lcn > 0) {
-			vcn += rl->length - (vcn - rl->vcn);
-		} else if (rl->lcn == LCN_DELALLOC || rl->lcn == LCN_HOLE) {
-			try_alloc_cnt = min(rl->length - (vcn - rl->vcn),
+		if (rl_lcn > 0) {
+			vcn += rl_length - (vcn - rl_vcn);
+		} else if (rl_lcn == LCN_DELALLOC || rl_lcn == LCN_HOLE) {
+			try_alloc_cnt = min(rl_length - (vcn - rl_vcn),
 					    vcn_uninit - vcn);
 
-			if (rl->lcn == LCN_DELALLOC) {
+			if (rl_lcn == LCN_DELALLOC) {
 				vcn += try_alloc_cnt;
 				continue;
 			}
@@ -5642,11 +5651,14 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo
 				if (err)
 					goto out;
 
-				err = ntfs_dio_zero_range(VFS_I(ni),
-							  lcn << vol->cluster_size_bits,
-							  alloc_cnt << vol->cluster_size_bits);
-				if (err > 0)
-					goto out;
+				if (balloc) {
+					err = ntfs_dio_zero_range(VFS_I(ni),
+								  lcn << vol->cluster_size_bits,
+								  alloc_cnt <<
+								  vol->cluster_size_bits);
+					if (err > 0)
+						goto out;
+				}
 
 				if (signal_pending(current))
 					goto out;
diff --git a/fs/ntfs/attrlist.c b/fs/ntfs/attrlist.c
index afb13038ba42..be3086d34338 100644
--- a/fs/ntfs/attrlist.c
+++ b/fs/ntfs/attrlist.c
@@ -57,6 +57,15 @@ int ntfs_attrlist_update(struct ntfs_inode *base_ni)
 	struct ntfs_inode *attr_ni;
 	int err;
 
+	/*
+	 * generic_shutdown_super() clears SB_ACTIVE before evicting cached
+	 * inodes. Do not look up the attribute-list inode after SB_ACTIVE has
+	 * been cleared; it may already be I_FREEING, and waiting on it can
+	 * self-deadlock.
+	 */
+	if (!(VFS_I(base_ni)->i_sb->s_flags & SB_ACTIVE))
+		return -EIO;
+
 	attr_vi = ntfs_attr_iget(VFS_I(base_ni), AT_ATTRIBUTE_LIST, AT_UNNAMED, 0);
 	if (IS_ERR(attr_vi)) {
 		err = PTR_ERR(attr_vi);
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 4b6bd5f30c65..6fa9ae3377cb 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -23,6 +23,13 @@
 __le16 I30[5] = { cpu_to_le16('$'), cpu_to_le16('I'),
 		cpu_to_le16('3'),	cpu_to_le16('0'), 0 };
 
+static inline u64 ntfs_check_mref(u64 mref)
+{
+	if (IS_ERR_MREF(mref))
+		return ERR_MREF(-EIO);
+	return mref;
+}
+
 /*
  * ntfs_lookup_inode_by_name - find an inode in a directory given its name
  * @dir_ni:	ntfs inode of the directory in which to search for the name
@@ -178,7 +185,7 @@ found_it:
 			mref = le64_to_cpu(ie->data.dir.indexed_file);
 			ntfs_attr_put_search_ctx(ctx);
 			unmap_mft_record(dir_ni);
-			return mref;
+			return ntfs_check_mref(mref);
 		}
 		/*
 		 * For a case insensitive mount, we also perform a case
@@ -273,7 +280,7 @@ found_it:
 		if (name) {
 			ntfs_attr_put_search_ctx(ctx);
 			unmap_mft_record(dir_ni);
-			return name->mref;
+			return ntfs_check_mref(name->mref);
 		}
 		ntfs_debug("Entry not found.");
 		err = -ENOENT;
@@ -413,7 +420,7 @@ found_it2:
 			mref = le64_to_cpu(ie->data.dir.indexed_file);
 			kfree(kaddr);
 			iput(ia_vi);
-			return mref;
+			return ntfs_check_mref(mref);
 		}
 		/*
 		 * For a case insensitive mount, we also perform a case
@@ -538,7 +545,7 @@ found_it2:
 	if (name) {
 		kfree(kaddr);
 		iput(ia_vi);
-		return name->mref;
+		return ntfs_check_mref(name->mref);
 	}
 	ntfs_debug("Entry not found.");
 	err = -ENOENT;
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
index c5f2cf75b750..faa7ee920a3a 100644
--- a/fs/ntfs/index.c
+++ b/fs/ntfs/index.c
@@ -110,6 +110,10 @@ static int ntfs_ib_write(struct ntfs_index_context *icx, struct index_block *ib)
 	ret = ntfs_inode_attr_pwrite(VFS_I(icx->ia_ni),
 			ntfs_ib_vcn_to_pos(icx, vcn), icx->block_size,
 			(u8 *)ib, icx->sync_write);
+
+	/* Perform data restoration before returning */
+	post_write_mst_fixup((struct ntfs_record *)ib);
+
 	if (ret != icx->block_size) {
 		ntfs_debug("Failed to write index block %lld, inode %llu",
 				vcn, (unsigned long long)icx->idx_ni->mft_no);
@@ -147,7 +151,6 @@ int ntfs_icx_ib_sync_write(struct ntfs_index_context *icx)
 		icx->ib = NULL;
 		icx->ib_dirty = false;
 	} else {
-		post_write_mst_fixup((struct ntfs_record *)icx->ib);
 		icx->sync_write = false;
 	}
 
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index c2715521e562..7381a18cfadd 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -1192,6 +1192,15 @@ no_data_attr_special_case:
 		vi->i_flags |= S_IMMUTABLE;
 
 	/*
+	 * System files such as $Bitmap and $MFT are maintained by the driver
+	 * itself, and writing them from userspace corrupts the volume.
+	 * Always make them immutable regardless of the sys_immutable option.
+	 * Directories are skipped so the root and $Extend stay usable.
+	 */
+	if (ni->mft_no < FILE_first_user && S_ISREG(vi->i_mode))
+		vi->i_flags |= S_IMMUTABLE;
+
+	/*
 	 * The number of 512-byte blocks used on disk (for stat). This is in so
 	 * far inaccurate as it doesn't account for any named streams or other
 	 * special non-resident attributes, but that is how Windows works, too,
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index a5019e80951b..fd20d7abd6f5 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -2637,7 +2637,6 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w
 	s64 vcn = ntfs_pidx_to_cluster(vol, folio->index);
 	s64 end_vcn = ntfs_bytes_to_cluster(vol, ni->allocated_size);
 	unsigned int folio_sz;
-	struct runlist_element *rl = NULL;
 	loff_t i_size = i_size_read(vi);
 
 	ntfs_debug("Entering for inode 0x%llx, attribute type 0x%x, folio index 0x%lx.",
@@ -2682,6 +2681,7 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w
 					&tni, &ref_inos[nr_ref_inos])) {
 			unsigned int mft_record_off = 0;
 			s64 vcn_off = vcn;
+			s64 rl_len = 0;
 
 			/*
 			 * The record should be written.  If a locked ntfs
@@ -2701,8 +2701,12 @@ flush_bio:
 			}
 
 			if (vol->cluster_size < folio_size(folio)) {
+				struct runlist_element *rl;
+
 				down_write(&ni->runlist.lock);
 				rl = ntfs_attr_vcn_to_rl(ni, vcn_off, &lcn);
+				if (!IS_ERR(rl))
+					rl_len = rl->length - (vcn_off - rl->vcn);
 				up_write(&ni->runlist.lock);
 				if (IS_ERR(rl) || lcn < 0) {
 					err = -EIO;
@@ -2733,7 +2737,7 @@ flush_bio:
 
 			if (vol->cluster_size == NTFS_BLOCK_SIZE &&
 			    (mft_record_off ||
-			     (rl && rl->length - (vcn_off - rl->vcn) == 1) ||
+			     rl_len == 1 ||
 			     mft_ofs + NTFS_BLOCK_SIZE >= PAGE_SIZE))
 				folio_sz = NTFS_BLOCK_SIZE;
 			else
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index a19626a135bd..5ff25e9aaa32 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -1266,6 +1266,7 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	struct ntfs_volume *vol = NTFS_SB(sb);
 	struct ntfs_inode *old_ni, *new_ni = NULL;
 	struct ntfs_inode *old_dir_ni = NTFS_I(old_dir), *new_dir_ni = NTFS_I(new_dir);
+	bool new_dir_first = false;
 
 	if (NVolShutdown(old_dir_ni->vol))
 		return -EIO;
@@ -1301,36 +1302,39 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
 	old_ni = NTFS_I(old_inode);
+	if (new_inode)
+		new_ni = NTFS_I(new_inode);
+	if (old_dir != new_dir)
+		new_dir_first = is_subdir(new_dentry->d_parent,
+					  old_dentry->d_parent);
 
 	if (!(vol->vol_flags & VOLUME_IS_DIRTY))
 		ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY);
 
 	mutex_lock_nested(&old_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL);
-	mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT);
+	if (new_ni)
+		mutex_lock_nested(&new_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL_2);
+
+	if (old_dir == new_dir) {
+		mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT);
+	} else if (new_dir_first) {
+		mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT);
+		mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2);
+	} else {
+		mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT);
+		mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2);
+	}
 
-	if (NInoBeingDeleted(old_ni) || NInoBeingDeleted(old_dir_ni)) {
+	if (NInoBeingDeleted(old_ni) || NInoBeingDeleted(old_dir_ni) ||
+	    (new_ni && NInoBeingDeleted(new_ni)) ||
+	    (old_dir != new_dir && NInoBeingDeleted(new_dir_ni))) {
 		err = -ENOENT;
-		goto unlock_old;
+		goto err_out;
 	}
 
 	is_dir = S_ISDIR(old_inode->i_mode);
 
 	if (new_inode) {
-		new_ni = NTFS_I(new_inode);
-		mutex_lock_nested(&new_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL_2);
-		if (old_dir != new_dir) {
-			mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2);
-			if (NInoBeingDeleted(new_dir_ni)) {
-				err = -ENOENT;
-				goto err_out;
-			}
-		}
-
-		if (NInoBeingDeleted(new_ni)) {
-			err = -ENOENT;
-			goto err_out;
-		}
-
 		if (is_dir) {
 			struct mft_record *ni_mrec;
 
@@ -1348,14 +1352,6 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		err = ntfs_delete(new_ni, new_dir_ni, uname_new, new_name_len, false);
 		if (err)
 			goto err_out;
-	} else {
-		if (old_dir != new_dir) {
-			mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2);
-			if (NInoBeingDeleted(new_dir_ni)) {
-				err = -ENOENT;
-				goto err_out;
-			}
-		}
 	}
 
 	err = __ntfs_link(old_ni, new_dir_ni, uname_new, new_name_len);
@@ -1386,13 +1382,17 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	inode_inc_iversion(new_dir);
 
 err_out:
-	if (old_dir != new_dir)
+	if (old_dir == new_dir) {
+		mutex_unlock(&old_dir_ni->mrec_lock);
+	} else if (new_dir_first) {
+		mutex_unlock(&old_dir_ni->mrec_lock);
 		mutex_unlock(&new_dir_ni->mrec_lock);
-	if (new_inode)
+	} else {
+		mutex_unlock(&new_dir_ni->mrec_lock);
+		mutex_unlock(&old_dir_ni->mrec_lock);
+	}
+	if (new_ni)
 		mutex_unlock(&new_ni->mrec_lock);
-
-unlock_old:
-	mutex_unlock(&old_dir_ni->mrec_lock);
 	mutex_unlock(&old_ni->mrec_lock);
 	if (uname_new)
 		kmem_cache_free(ntfs_name_cache, uname_new);