1 files changed, 342 insertions, 169 deletions

diff --git a/fs/libfs.c b/fs/libfs.c
index b635ee5adbcc..9264523be85c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -62,11 +62,6 @@ int always_delete_dentry(const struct dentry *dentry)
 }
 EXPORT_SYMBOL(always_delete_dentry);
 
-const struct dentry_operations simple_dentry_operations = {
-	.d_delete = always_delete_dentry,
-};
-EXPORT_SYMBOL(simple_dentry_operations);
-
 /*
  * Lookup the data. This is trivial - if the dentry didn't already
  * exist, we know it is negative.  Set d_op to delete negative dentries.
@@ -75,8 +70,14 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned
 {
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
-	if (!dentry->d_sb->s_d_op)
-		d_set_d_op(dentry, &simple_dentry_operations);
+	if (!dentry->d_op && !(dentry->d_flags & DCACHE_DONTCACHE)) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags |= DCACHE_DONTCACHE;
+		spin_unlock(&dentry->d_lock);
+	}
+	if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
+		return NULL;
+
 	d_add(dentry, NULL);
 	return NULL;
 }
@@ -241,9 +242,16 @@ const struct inode_operations simple_dir_inode_operations = {
 };
 EXPORT_SYMBOL(simple_dir_inode_operations);
 
-/* 0 is '.', 1 is '..', so always start with offset 2 or more */
+/* simple_offset_add() never assigns these to a dentry */
 enum {
-	DIR_OFFSET_MIN	= 2,
+	DIR_OFFSET_FIRST	= 2,		/* Find first real entry */
+	DIR_OFFSET_EOD		= S32_MAX,
+};
+
+/* simple_offset_add() allocation range */
+enum {
+	DIR_OFFSET_MIN		= DIR_OFFSET_FIRST + 1,
+	DIR_OFFSET_MAX		= DIR_OFFSET_EOD - 1,
 };
 
 static void offset_set(struct dentry *dentry, long offset)
@@ -287,9 +295,10 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
 		return -EBUSY;
 
 	ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
-				 LONG_MAX, &octx->next_offset, GFP_KERNEL);
-	if (ret < 0)
-		return ret;
+				 DIR_OFFSET_MAX, &octx->next_offset,
+				 GFP_KERNEL);
+	if (unlikely(ret < 0))
+		return ret == -EBUSY ? -ENOSPC : ret;
 
 	offset_set(dentry, offset);
 	return 0;
@@ -326,38 +335,6 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
 }
 
 /**
- * simple_offset_empty - Check if a dentry can be unlinked
- * @dentry: dentry to be tested
- *
- * Returns 0 if @dentry is a non-empty directory; otherwise returns 1.
- */
-int simple_offset_empty(struct dentry *dentry)
-{
-	struct inode *inode = d_inode(dentry);
-	struct offset_ctx *octx;
-	struct dentry *child;
-	unsigned long index;
-	int ret = 1;
-
-	if (!inode || !S_ISDIR(inode->i_mode))
-		return ret;
-
-	index = DIR_OFFSET_MIN;
-	octx = inode->i_op->get_offset_ctx(inode);
-	mt_for_each(&octx->mt, child, index, LONG_MAX) {
-		spin_lock(&child->d_lock);
-		if (simple_positive(child)) {
-			spin_unlock(&child->d_lock);
-			ret = 0;
-			break;
-		}
-		spin_unlock(&child->d_lock);
-	}
-
-	return ret;
-}
-
-/**
  * simple_offset_rename - handle directory offsets for rename
  * @old_dir: parent directory of source entry
  * @old_dentry: dentry of source entry
@@ -475,57 +452,89 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
 		return -EINVAL;
 	}
 
-	/* In this case, ->private_data is protected by f_pos_lock */
-	file->private_data = NULL;
 	return vfs_setpos(file, offset, LONG_MAX);
 }
 
-static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset)
+static struct dentry *find_positive_dentry(struct dentry *parent,
+					   struct dentry *dentry,
+					   bool next)
 {
-	MA_STATE(mas, &octx->mt, offset, offset);
+	struct dentry *found = NULL;
+
+	spin_lock(&parent->d_lock);
+	if (next)
+		dentry = d_next_sibling(dentry);
+	else if (!dentry)
+		dentry = d_first_child(parent);
+	hlist_for_each_entry_from(dentry, d_sib) {
+		if (!simple_positive(dentry))
+			continue;
+		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+		if (simple_positive(dentry))
+			found = dget_dlock(dentry);
+		spin_unlock(&dentry->d_lock);
+		if (likely(found))
+			break;
+	}
+	spin_unlock(&parent->d_lock);
+	return found;
+}
+
+static noinline_for_stack struct dentry *
+offset_dir_lookup(struct dentry *parent, loff_t offset)
+{
+	struct inode *inode = d_inode(parent);
+	struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
 	struct dentry *child, *found = NULL;
 
-	rcu_read_lock();
-	child = mas_find(&mas, LONG_MAX);
-	if (!child)
-		goto out;
-	spin_lock(&child->d_lock);
-	if (simple_positive(child))
-		found = dget_dlock(child);
-	spin_unlock(&child->d_lock);
-out:
-	rcu_read_unlock();
+	MA_STATE(mas, &octx->mt, offset, offset);
+
+	if (offset == DIR_OFFSET_FIRST)
+		found = find_positive_dentry(parent, NULL, false);
+	else {
+		rcu_read_lock();
+		child = mas_find_rev(&mas, DIR_OFFSET_MIN);
+		found = find_positive_dentry(parent, child, false);
+		rcu_read_unlock();
+	}
 	return found;
 }
 
 static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
-	long offset = dentry2offset(dentry);
 
-	return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset,
-			  inode->i_ino, fs_umode_to_dtype(inode->i_mode));
+	return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len,
+			inode->i_ino, fs_umode_to_dtype(inode->i_mode));
 }
 
-static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+static void offset_iterate_dir(struct file *file, struct dir_context *ctx)
 {
-	struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
+	struct dentry *dir = file->f_path.dentry;
 	struct dentry *dentry;
 
+	dentry = offset_dir_lookup(dir, ctx->pos);
+	if (!dentry)
+		goto out_eod;
 	while (true) {
-		dentry = offset_find_next(octx, ctx->pos);
-		if (!dentry)
-			return ERR_PTR(-ENOENT);
+		struct dentry *next;
 
-		if (!offset_dir_emit(ctx, dentry)) {
-			dput(dentry);
+		ctx->pos = dentry2offset(dentry);
+		if (!offset_dir_emit(ctx, dentry))
 			break;
-		}
 
-		ctx->pos = dentry2offset(dentry) + 1;
+		next = find_positive_dentry(dir, dentry, true);
 		dput(dentry);
+
+		if (!next)
+			goto out_eod;
+		dentry = next;
 	}
-	return NULL;
+	dput(dentry);
+	return;
+
+out_eod:
+	ctx->pos = DIR_OFFSET_EOD;
 }
 
 /**
@@ -545,6 +554,8 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
  *
  * On return, @ctx->pos contains an offset that will read the next entry
  * in this directory when offset_readdir() is called again with @ctx.
+ * Caller places this value in the d_off field of the last entry in the
+ * user's buffer.
  *
  * Return values:
  *   %0 - Complete
@@ -557,13 +568,8 @@ static int offset_readdir(struct file *file, struct dir_context *ctx)
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
-
-	/* In this case, ->private_data is protected by f_pos_lock */
-	if (ctx->pos == DIR_OFFSET_MIN)
-		file->private_data = NULL;
-	else if (file->private_data == ERR_PTR(-ENOENT))
-		return 0;
-	file->private_data = offset_iterate_dir(d_inode(dir), ctx);
+	if (ctx->pos != DIR_OFFSET_EOD)
+		offset_iterate_dir(file, ctx);
 	return 0;
 }
 
@@ -574,7 +580,7 @@ const struct file_operations simple_offset_dir_operations = {
 	.fsync		= noop_fsync,
 };
 
-static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
+struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
 {
 	struct dentry *child = NULL, *d;
 
@@ -594,16 +600,18 @@ static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev
 	dput(prev);
 	return child;
 }
+EXPORT_SYMBOL(find_next_child);
 
-void simple_recursive_removal(struct dentry *dentry,
-                              void (*callback)(struct dentry *))
+static void __simple_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *),
+			      bool locked)
 {
 	struct dentry *this = dget(dentry);
 	while (true) {
 		struct dentry *victim = NULL, *child;
 		struct inode *inode = this->d_inode;
 
-		inode_lock(inode);
+		inode_lock_nested(inode, I_MUTEX_CHILD);
 		if (d_is_dir(this))
 			inode->i_flags |= S_DEAD;
 		while ((child = find_next_child(this, victim)) == NULL) {
@@ -615,23 +623,22 @@ void simple_recursive_removal(struct dentry *dentry,
 			victim = this;
 			this = this->d_parent;
 			inode = this->d_inode;
-			inode_lock(inode);
+			if (!locked || victim != dentry)
+				inode_lock_nested(inode, I_MUTEX_CHILD);
 			if (simple_positive(victim)) {
 				d_invalidate(victim);	// avoid lost mounts
-				if (d_is_dir(victim))
-					fsnotify_rmdir(inode, victim);
-				else
-					fsnotify_unlink(inode, victim);
 				if (callback)
 					callback(victim);
-				dput(victim);		// unpin it
+				fsnotify_delete(inode, d_inode(victim), victim);
+				d_make_discardable(victim);
 			}
 			if (victim == dentry) {
 				inode_set_mtime_to_ts(inode,
 						      inode_set_ctime_current(inode));
 				if (d_is_dir(dentry))
 					drop_nlink(inode);
-				inode_unlock(inode);
+				if (!locked)
+					inode_unlock(inode);
 				dput(dentry);
 				return;
 			}
@@ -640,8 +647,35 @@ void simple_recursive_removal(struct dentry *dentry,
 		this = child;
 	}
 }
+
+void simple_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *))
+{
+	return __simple_recursive_removal(dentry, callback, false);
+}
 EXPORT_SYMBOL(simple_recursive_removal);
 
+void simple_remove_by_name(struct dentry *parent, const char *name,
+                           void (*callback)(struct dentry *))
+{
+	struct dentry *dentry;
+
+	dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent);
+	if (!IS_ERR(dentry)) {
+		simple_recursive_removal(dentry, callback);
+		dput(dentry);	// paired with lookup_noperm_positive_unlocked()
+	}
+}
+EXPORT_SYMBOL(simple_remove_by_name);
+
+/* caller holds parent directory with I_MUTEX_PARENT */
+void locked_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *))
+{
+	return __simple_recursive_removal(dentry, callback, true);
+}
+EXPORT_SYMBOL(locked_recursive_removal);
+
 static const struct super_operations simple_super_operations = {
 	.statfs		= simple_statfs,
 };
@@ -656,8 +690,10 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_blocksize_bits = PAGE_SHIFT;
 	s->s_magic = ctx->magic;
 	s->s_op = ctx->ops ?: &simple_super_operations;
+	s->s_export_op = ctx->eops;
 	s->s_xattr = ctx->xattr;
 	s->s_time_gran = 1;
+	s->s_d_flags |= ctx->s_d_flags;
 	root = new_inode(s);
 	if (!root)
 		return -ENOMEM;
@@ -673,7 +709,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_root = d_make_root(root);
 	if (!s->s_root)
 		return -ENOMEM;
-	s->s_d_op = ctx->dops;
+	set_default_d_op(s, ctx->dops);
 	return 0;
 }
 
@@ -729,8 +765,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den
 			      inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode)));
 	inc_nlink(inode);
 	ihold(inode);
-	dget(dentry);
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 	return 0;
 }
 EXPORT_SYMBOL(simple_link);
@@ -756,14 +791,28 @@ out:
 }
 EXPORT_SYMBOL(simple_empty);
 
-int simple_unlink(struct inode *dir, struct dentry *dentry)
+void __simple_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
 
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode)));
 	drop_nlink(inode);
-	dput(dentry);
+}
+EXPORT_SYMBOL(__simple_unlink);
+
+void __simple_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	drop_nlink(d_inode(dentry));
+	__simple_unlink(dir, dentry);
+	drop_nlink(dir);
+}
+EXPORT_SYMBOL(__simple_rmdir);
+
+int simple_unlink(struct inode *dir, struct dentry *dentry)
+{
+	__simple_unlink(dir, dentry);
+	d_make_discardable(dentry);
 	return 0;
 }
 EXPORT_SYMBOL(simple_unlink);
@@ -773,9 +822,8 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry)
 	if (!simple_empty(dentry))
 		return -ENOTEMPTY;
 
-	drop_nlink(d_inode(dentry));
-	simple_unlink(dir, dentry);
-	drop_nlink(dir);
+	__simple_rmdir(dir, dentry);
+	d_make_discardable(dentry);
 	return 0;
 }
 EXPORT_SYMBOL(simple_rmdir);
@@ -899,9 +947,9 @@ static int simple_read_folio(struct file *file, struct folio *folio)
 	return 0;
 }
 
-int simple_write_begin(struct file *file, struct address_space *mapping,
+int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	struct folio *folio;
 
@@ -910,7 +958,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	*pagep = &folio->page;
+	*foliop = folio;
 
 	if (!folio_test_uptodate(folio) && (len != folio_size(folio))) {
 		size_t from = offset_in_folio(folio, pos);
@@ -924,18 +972,19 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @file: See .write_end of address_space_operations
+ * @iocb: kernel I/O control block
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"
  * @copied: 		"
- * @page: 		"
+ * @folio: 		"
  * @fsdata: 		"
  *
- * simple_write_end does the minimum needed for updating a page after writing is
- * done. It has the same API signature as the .write_end of
+ * simple_write_end does the minimum needed for updating a folio after
+ * writing is done. It has the same API signature as the .write_end of
  * address_space_operations vector. So it can just be set onto .write_end for
- * FSes that don't need any other processing. i_mutex is assumed to be held.
+ * FSes that don't need any other processing. i_rwsem is assumed to be held
+ * exclusively.
  * Block based filesystems should use generic_write_end().
  * NOTE: Even though i_size might get updated by this function, mark_inode_dirty
  * is not called, so a filesystem that actually does store data in .write_inode
@@ -944,11 +993,11 @@ EXPORT_SYMBOL(simple_write_begin);
  *
  * Use *ONLY* with simple_read_folio()
  */
-static int simple_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+static int simple_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
 
@@ -963,7 +1012,7 @@ static int simple_write_end(struct file *file, struct address_space *mapping,
 	}
 	/*
 	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
+	 * cannot change under us because we hold the i_rwsem.
 	 */
 	if (last_pos > inode->i_size)
 		i_size_write(inode, last_pos);
@@ -1042,7 +1091,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 		simple_inode_init_ts(inode);
 		inode->i_fop = files->ops;
 		inode->i_ino = i;
-		d_add(dentry, inode);
+		d_make_persistent(dentry, inode);
+		dput(dentry);
 	}
 	return 0;
 }
@@ -1519,9 +1569,9 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 
 	inode_lock(inode);
 	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY_ALL))
+	if (!(inode_state_read_once(inode) & I_DIRTY_ALL))
 		goto out;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+	if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC))
 		goto out;
 
 	err = sync_inode_metadata(inode, 1);
@@ -1573,13 +1623,17 @@ EXPORT_SYMBOL(generic_file_fsync);
 int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
 {
 	u64 last_fs_block = num_blocks - 1;
-	u64 last_fs_page =
-		last_fs_block >> (PAGE_SHIFT - blocksize_bits);
+	u64 last_fs_page, max_bytes;
+
+	if (check_shl_overflow(num_blocks, blocksize_bits, &max_bytes))
+		return -EFBIG;
+
+	last_fs_page = (max_bytes >> PAGE_SHIFT) - 1;
 
 	if (unlikely(num_blocks == 0))
 		return 0;
 
-	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT))
+	if (blocksize_bits < 9)
 		return -EINVAL;
 
 	if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
@@ -1637,11 +1691,15 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	 * list because mark_inode_dirty() will think
 	 * that it already _is_ on the dirty list.
 	 */
-	inode->i_state = I_DIRTY;
+	inode_state_assign_raw(inode, I_DIRTY);
+	/*
+	 * Historically anonymous inodes don't have a type at all and
+	 * userspace has come to rely on this.
+	 */
 	inode->i_mode = S_IRUSR | S_IWUSR;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
-	inode->i_flags |= S_PRIVATE;
+	inode->i_flags |= S_PRIVATE | S_ANON_INODE;
 	simple_inode_init_ts(inode);
 	return inode;
 }
@@ -1699,15 +1757,6 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry,
 	return ERR_PTR(-ENOENT);
 }
 
-static int empty_dir_getattr(struct mnt_idmap *idmap,
-			     const struct path *path, struct kstat *stat,
-			     u32 request_mask, unsigned int query_flags)
-{
-	struct inode *inode = d_inode(path->dentry);
-	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
-	return 0;
-}
-
 static int empty_dir_setattr(struct mnt_idmap *idmap,
 			     struct dentry *dentry, struct iattr *attr)
 {
@@ -1721,9 +1770,7 @@ static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t siz
 
 static const struct inode_operations empty_dir_inode_operations = {
 	.lookup		= empty_dir_lookup,
-	.permission	= generic_permission,
 	.setattr	= empty_dir_setattr,
-	.getattr	= empty_dir_getattr,
 	.listxattr	= empty_dir_listxattr,
 };
 
@@ -1779,12 +1826,12 @@ bool is_empty_dir_inode(struct inode *inode)
  *
  * Return: 0 if names match, 1 if mismatch, or -ERRNO
  */
-static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
-				const char *str, const struct qstr *name)
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			 const char *str, const struct qstr *name)
 {
 	const struct dentry *parent;
 	const struct inode *dir;
-	char strbuf[DNAME_INLINE_LEN];
+	union shortname_store strbuf;
 	struct qstr qstr;
 
 	/*
@@ -1804,25 +1851,27 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 	if (!dir || !IS_CASEFOLDED(dir))
 		return 1;
 
+	qstr.len = len;
+	qstr.name = str;
 	/*
 	 * If the dentry name is stored in-line, then it may be concurrently
 	 * modified by a rename.  If this happens, the VFS will eventually retry
 	 * the lookup, so it doesn't matter what ->d_compare() returns.
 	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
 	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 * As above, len is guaranteed to match str, so the shortname case
+	 * is exactly when str points to ->d_shortname.
 	 */
-	if (len <= DNAME_INLINE_LEN - 1) {
-		memcpy(strbuf, str, len);
-		strbuf[len] = 0;
-		str = strbuf;
+	if (qstr.name == dentry->d_shortname.string) {
+		strbuf = dentry->d_shortname; // NUL is guaranteed to be in there
+		qstr.name = strbuf.string;
 		/* prevent compiler from optimizing out the temporary buffer */
 		barrier();
 	}
-	qstr.len = len;
-	qstr.name = str;
 
 	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
+EXPORT_SYMBOL(generic_ci_d_compare);
 
 /**
  * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
@@ -1831,7 +1880,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
  *
  * Return: 0 if hash was successful or unchanged, and -EINVAL on error
  */
-static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 {
 	const struct inode *dir = READ_ONCE(dentry->d_inode);
 	struct super_block *sb = dentry->d_sb;
@@ -1846,6 +1895,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL(generic_ci_d_hash);
 
 static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_hash = generic_ci_d_hash,
@@ -1854,6 +1904,80 @@ static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 #endif
 };
+
+/**
+ * generic_ci_match() - Match a name (case-insensitively) with a dirent.
+ * This is a filesystem helper for comparison with directory entries.
+ * generic_ci_d_compare should be used in VFS' ->d_compare instead.
+ *
+ * @parent: Inode of the parent of the dirent under comparison
+ * @name: name under lookup.
+ * @folded_name: Optional pre-folded name under lookup
+ * @de_name: Dirent name.
+ * @de_name_len: dirent name length.
+ *
+ * Test whether a case-insensitive directory entry matches the filename
+ * being searched.  If @folded_name is provided, it is used instead of
+ * recalculating the casefold of @name.
+ *
+ * Return: > 0 if the directory entry matches, 0 if it doesn't match, or
+ * < 0 on error.
+ */
+int generic_ci_match(const struct inode *parent,
+		     const struct qstr *name,
+		     const struct qstr *folded_name,
+		     const u8 *de_name, u32 de_name_len)
+{
+	const struct super_block *sb = parent->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
+	struct qstr dirent = QSTR_INIT(de_name, de_name_len);
+	int res = 0;
+
+	if (IS_ENCRYPTED(parent)) {
+		const struct fscrypt_str encrypted_name =
+			FSTR_INIT((u8 *) de_name, de_name_len);
+
+		if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent)))
+			return -EINVAL;
+
+		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
+		if (!decrypted_name.name)
+			return -ENOMEM;
+		res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
+						&decrypted_name);
+		if (res < 0) {
+			kfree(decrypted_name.name);
+			return res;
+		}
+		dirent.name = decrypted_name.name;
+		dirent.len = decrypted_name.len;
+	}
+
+	/*
+	 * Attempt a case-sensitive match first. It is cheaper and
+	 * should cover most lookups, including all the sane
+	 * applications that expect a case-sensitive filesystem.
+	 */
+
+	if (dirent.len == name->len &&
+	    !memcmp(name->name, dirent.name, dirent.len))
+		goto out;
+
+	if (folded_name->name)
+		res = utf8_strncasecmp_folded(um, folded_name, &dirent);
+	else
+		res = utf8_strncasecmp(um, name, &dirent);
+
+out:
+	kfree(decrypted_name.name);
+	if (res < 0 && sb_has_strict_encoding(sb)) {
+		pr_err_ratelimited("Directory contains filename that is invalid UTF-8");
+		return 0;
+	}
+	return !res;
+}
+EXPORT_SYMBOL(generic_ci_match);
 #endif
 
 #ifdef CONFIG_FS_ENCRYPTION
@@ -1868,22 +1992,22 @@ static const struct dentry_operations generic_encrypted_dentry_ops = {
  * @sb: superblock to be configured
  *
  * Filesystems supporting casefolding and/or fscrypt can call this
- * helper at mount-time to configure sb->s_d_op to best set of dentry
- * operations required for the enabled features. The helper must be
- * called after these have been configured, but before the root dentry
- * is created.
+ * helper at mount-time to configure default dentry_operations to the
+ * best set of dentry operations required for the enabled features.
+ * The helper must be called after these have been configured, but
+ * before the root dentry is created.
  */
 void generic_set_sb_d_ops(struct super_block *sb)
 {
 #if IS_ENABLED(CONFIG_UNICODE)
 	if (sb->s_encoding) {
-		sb->s_d_op = &generic_ci_dentry_ops;
+		set_default_d_op(sb, &generic_ci_dentry_ops);
 		return;
 	}
 #endif
 #ifdef CONFIG_FS_ENCRYPTION
 	if (sb->s_cop) {
-		sb->s_d_op = &generic_encrypted_dentry_ops;
+		set_default_d_op(sb, &generic_encrypted_dentry_ops);
 		return;
 	}
 #endif
@@ -1916,13 +2040,19 @@ bool inode_maybe_inc_iversion(struct inode *inode, bool force)
 	 * information, but the legacy inode_inc_iversion code used a spinlock
 	 * to serialize increments.
 	 *
-	 * Here, we add full memory barriers to ensure that any de-facto
-	 * ordering with other info is preserved.
+	 * We add a full memory barrier to ensure that any de facto ordering
+	 * with other state is preserved (either implicitly coming from cmpxchg
+	 * or explicitly from smp_mb if we don't know upfront if we will execute
+	 * the former).
 	 *
-	 * This barrier pairs with the barrier in inode_query_iversion()
+	 * These barriers pair with inode_query_iversion().
 	 */
-	smp_mb();
 	cur = inode_peek_iversion_raw(inode);
+	if (!force && !(cur & I_VERSION_QUERIED)) {
+		smp_mb();
+		cur = inode_peek_iversion_raw(inode);
+	}
+
 	do {
 		/* If flag is clear then we needn't do anything */
 		if (!force && !(cur & I_VERSION_QUERIED))
@@ -1951,20 +2081,22 @@ EXPORT_SYMBOL(inode_maybe_inc_iversion);
 u64 inode_query_iversion(struct inode *inode)
 {
 	u64 cur, new;
+	bool fenced = false;
 
+	/*
+	 * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with
+	 * inode_maybe_inc_iversion(), see that routine for more details.
+	 */
 	cur = inode_peek_iversion_raw(inode);
 	do {
 		/* If flag is already set, then no need to swap */
 		if (cur & I_VERSION_QUERIED) {
-			/*
-			 * This barrier (and the implicit barrier in the
-			 * cmpxchg below) pairs with the barrier in
-			 * inode_maybe_inc_iversion().
-			 */
-			smp_mb();
+			if (!fenced)
+				smp_mb();
 			break;
 		}
 
+		fenced = true;
 		new = cur | I_VERSION_QUERIED;
 	} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
 	return cur >> I_VERSION_QUERIED_SHIFT;
@@ -2030,14 +2162,16 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
 }
 EXPORT_SYMBOL(simple_inode_init_ts);
 
-static inline struct dentry *get_stashed_dentry(struct dentry *stashed)
+struct dentry *stashed_dentry_get(struct dentry **stashed)
 {
 	struct dentry *dentry;
 
 	guard(rcu)();
-	dentry = READ_ONCE(stashed);
+	dentry = rcu_dereference(*stashed);
 	if (!dentry)
 		return NULL;
+	if (IS_ERR(dentry))
+		return dentry;
 	if (!lockref_get_not_dead(&dentry->d_lockref))
 		return NULL;
 	return dentry;
@@ -2070,7 +2204,6 @@ static struct dentry *prepare_anon_dentry(struct dentry **stashed,
 
 	/* Notice when this is changed. */
 	WARN_ON_ONCE(!S_ISREG(inode->i_mode));
-	WARN_ON_ONCE(!IS_IMMUTABLE(inode));
 
 	dentry = d_alloc_anon(sb);
 	if (!dentry) {
@@ -2086,8 +2219,7 @@ static struct dentry *prepare_anon_dentry(struct dentry **stashed,
 	return dentry;
 }
 
-static struct dentry *stash_dentry(struct dentry **stashed,
-				   struct dentry *dentry)
+struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry)
 {
 	guard(rcu)();
 	for (;;) {
@@ -2128,14 +2260,16 @@ static struct dentry *stash_dentry(struct dentry **stashed,
 int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
 		      struct path *path)
 {
-	struct dentry *dentry;
+	struct dentry *dentry, *res;
 	const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
 
 	/* See if dentry can be reused. */
-	path->dentry = get_stashed_dentry(*stashed);
-	if (path->dentry) {
+	res = stashed_dentry_get(stashed);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+	if (res) {
 		sops->put_data(data);
-		goto out_path;
+		goto make_path;
 	}
 
 	/* Allocate a new dentry. */
@@ -2144,14 +2278,22 @@ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
 		return PTR_ERR(dentry);
 
 	/* Added a new dentry. @data is now owned by the filesystem. */
-	path->dentry = stash_dentry(stashed, dentry);
-	if (path->dentry != dentry)
+	if (sops->stash_dentry)
+		res = sops->stash_dentry(stashed, dentry);
+	else
+		res = stash_dentry(stashed, dentry);
+	if (IS_ERR(res)) {
+		dput(dentry);
+		return PTR_ERR(res);
+	}
+	if (res != dentry)
 		dput(dentry);
 
-out_path:
-	WARN_ON_ONCE(path->dentry->d_fsdata != stashed);
-	WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
+make_path:
+	path->dentry = res;
 	path->mnt = mntget(mnt);
+	VFS_WARN_ON_ONCE(path->dentry->d_fsdata != stashed);
+	VFS_WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
 	return 0;
 }
 
@@ -2173,3 +2315,34 @@ void stashed_dentry_prune(struct dentry *dentry)
 	 */
 	cmpxchg(stashed, dentry, NULL);
 }
+
+/**
+ * simple_start_creating - prepare to create a given name
+ * @parent: directory in which to prepare to create the name
+ * @name:   the name to be created
+ *
+ * Required lock is taken and a lookup in performed prior to creating an
+ * object in a directory.  No permission checking is performed.
+ *
+ * Returns: a negative dentry on which vfs_create() or similar may
+ *  be attempted, or an error.
+ */
+struct dentry *simple_start_creating(struct dentry *parent, const char *name)
+{
+	struct qstr qname = QSTR(name);
+	int err;
+
+	err = lookup_noperm_common(&qname, parent);
+	if (err)
+		return ERR_PTR(err);
+	return start_dirop(parent, &qname, LOOKUP_CREATE | LOOKUP_EXCL);
+}
+EXPORT_SYMBOL(simple_start_creating);
+
+/* parent must have been held exclusive since simple_start_creating() */
+void simple_done_creating(struct dentry *child)
+{
+	inode_unlock(child->d_parent->d_inode);
+	dput(child);
+}
+EXPORT_SYMBOL(simple_done_creating);