1 files changed, 502 insertions, 182 deletions

diff --git a/fs/libfs.c b/fs/libfs.c
index dc0f7519045f..874324167849 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -23,6 +23,7 @@
 #include <linux/fsnotify.h>
 #include <linux/unicode.h>
 #include <linux/fscrypt.h>
+#include <linux/pidfs.h>
 
 #include <linux/uaccess.h>
 
@@ -41,6 +42,9 @@ EXPORT_SYMBOL(simple_getattr);
 
 int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
+	u64 id = huge_encode_dev(dentry->d_sb->s_dev);
+
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_type = dentry->d_sb->s_magic;
 	buf->f_bsize = PAGE_SIZE;
 	buf->f_namelen = NAME_MAX;
@@ -101,15 +105,16 @@ EXPORT_SYMBOL(dcache_dir_close);
  * If no such element exists, NULL is returned.
  */
 static struct dentry *scan_positives(struct dentry *cursor,
-					struct list_head *p,
+					struct hlist_node **p,
 					loff_t count,
 					struct dentry *last)
 {
 	struct dentry *dentry = cursor->d_parent, *found = NULL;
 
 	spin_lock(&dentry->d_lock);
-	while ((p = p->next) != &dentry->d_subdirs) {
-		struct dentry *d = list_entry(p, struct dentry, d_child);
+	while (*p) {
+		struct dentry *d = hlist_entry(*p, struct dentry, d_sib);
+		p = &d->d_sib.next;
 		// we must at least skip cursors, to avoid livelocks
 		if (d->d_flags & DCACHE_DENTRY_CURSOR)
 			continue;
@@ -123,8 +128,10 @@ static struct dentry *scan_positives(struct dentry *cursor,
 			count = 1;
 		}
 		if (need_resched()) {
-			list_move(&cursor->d_child, p);
-			p = &cursor->d_child;
+			if (!hlist_unhashed(&cursor->d_sib))
+				__hlist_del(&cursor->d_sib);
+			hlist_add_behind(&cursor->d_sib, &d->d_sib);
+			p = &cursor->d_sib.next;
 			spin_unlock(&dentry->d_lock);
 			cond_resched();
 			spin_lock(&dentry->d_lock);
@@ -156,13 +163,12 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 		inode_lock_shared(dentry->d_inode);
 
 		if (offset > 2)
-			to = scan_positives(cursor, &dentry->d_subdirs,
+			to = scan_positives(cursor, &dentry->d_children.first,
 					    offset - 2, NULL);
 		spin_lock(&dentry->d_lock);
+		hlist_del_init(&cursor->d_sib);
 		if (to)
-			list_move(&cursor->d_child, &to->d_child);
-		else
-			list_del_init(&cursor->d_child);
+			hlist_add_behind(&cursor->d_sib, &to->d_sib);
 		spin_unlock(&dentry->d_lock);
 		dput(to);
 
@@ -184,19 +190,16 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *anchor = &dentry->d_subdirs;
 	struct dentry *next = NULL;
-	struct list_head *p;
+	struct hlist_node **p;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
 	if (ctx->pos == 2)
-		p = anchor;
-	else if (!list_empty(&cursor->d_child))
-		p = &cursor->d_child;
+		p = &dentry->d_children.first;
 	else
-		return 0;
+		p = &cursor->d_sib.next;
 
 	while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
@@ -204,13 +207,12 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 			      fs_umode_to_dtype(d_inode(next)->i_mode)))
 			break;
 		ctx->pos++;
-		p = &next->d_child;
+		p = &next->d_sib.next;
 	}
 	spin_lock(&dentry->d_lock);
+	hlist_del_init(&cursor->d_sib);
 	if (next)
-		list_move_tail(&cursor->d_child, &next->d_child);
-	else
-		list_del_init(&cursor->d_child);
+		hlist_add_before(&cursor->d_sib, &next->d_sib);
 	spin_unlock(&dentry->d_lock);
 	dput(next);
 
@@ -239,17 +241,29 @@ const struct inode_operations simple_dir_inode_operations = {
 };
 EXPORT_SYMBOL(simple_dir_inode_operations);
 
-static void offset_set(struct dentry *dentry, u32 offset)
+/* simple_offset_add() never assigns these to a dentry */
+enum {
+	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)
 {
-	dentry->d_fsdata = (void *)((uintptr_t)(offset));
+	dentry->d_fsdata = (void *)offset;
 }
 
-static u32 dentry2offset(struct dentry *dentry)
+static long dentry2offset(struct dentry *dentry)
 {
-	return (u32)((uintptr_t)(dentry->d_fsdata));
+	return (long)dentry->d_fsdata;
 }
 
-static struct lock_class_key simple_offset_xa_lock;
+static struct lock_class_key simple_offset_lock_class;
 
 /**
  * simple_offset_init - initialize an offset_ctx
@@ -258,11 +272,9 @@ static struct lock_class_key simple_offset_xa_lock;
  */
 void simple_offset_init(struct offset_ctx *octx)
 {
-	xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock);
-
-	/* 0 is '.', 1 is '..', so always start with offset 2 */
-	octx->next_offset = 2;
+	mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE);
+	lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class);
+	octx->next_offset = DIR_OFFSET_MIN;
 }
 
 /**
@@ -270,27 +282,39 @@ void simple_offset_init(struct offset_ctx *octx)
  * @octx: directory offset ctx to be updated
  * @dentry: new dentry being added
  *
- * Returns zero on success. @so_ctx and the dentry offset are updated.
+ * Returns zero on success. @octx and the dentry's offset are updated.
  * Otherwise, a negative errno value is returned.
  */
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
 {
-	static const struct xa_limit limit = XA_LIMIT(2, U32_MAX);
-	u32 offset;
+	unsigned long offset;
 	int ret;
 
 	if (dentry2offset(dentry) != 0)
 		return -EBUSY;
 
-	ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit,
-			      &octx->next_offset, GFP_KERNEL);
-	if (ret < 0)
-		return ret;
+	ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
+				 DIR_OFFSET_MAX, &octx->next_offset,
+				 GFP_KERNEL);
+	if (unlikely(ret < 0))
+		return ret == -EBUSY ? -ENOSPC : ret;
 
 	offset_set(dentry, offset);
 	return 0;
 }
 
+static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry,
+				 long offset)
+{
+	int ret;
+
+	ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL);
+	if (ret)
+		return ret;
+	offset_set(dentry, offset);
+	return 0;
+}
+
 /**
  * simple_offset_remove - Remove an entry to a directory's offset map
  * @octx: directory offset ctx to be updated
@@ -299,23 +323,56 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
  */
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
 {
-	u32 offset;
+	long offset;
 
 	offset = dentry2offset(dentry);
 	if (offset == 0)
 		return;
 
-	xa_erase(&octx->xa, offset);
+	mtree_erase(&octx->mt, offset);
 	offset_set(dentry, 0);
 }
 
 /**
+ * simple_offset_rename - handle directory offsets for rename
+ * @old_dir: parent directory of source entry
+ * @old_dentry: dentry of source entry
+ * @new_dir: parent_directory of destination entry
+ * @new_dentry: dentry of destination
+ *
+ * Caller provides appropriate serialization.
+ *
+ * User space expects the directory offset value of the replaced
+ * (new) directory entry to be unchanged after a rename.
+ *
+ * Returns zero on success, a negative errno value on failure.
+ */
+int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
+			 struct inode *new_dir, struct dentry *new_dentry)
+{
+	struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
+	struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
+	long new_offset = dentry2offset(new_dentry);
+
+	simple_offset_remove(old_ctx, old_dentry);
+
+	if (new_offset) {
+		offset_set(new_dentry, 0);
+		return simple_offset_replace(new_ctx, old_dentry, new_offset);
+	}
+	return simple_offset_add(new_ctx, old_dentry);
+}
+
+/**
  * simple_offset_rename_exchange - exchange rename with directory offsets
  * @old_dir: parent of dentry being moved
  * @old_dentry: dentry being moved
  * @new_dir: destination parent
  * @new_dentry: destination dentry
  *
+ * This API preserves the directory offset values. Caller provides
+ * appropriate serialization.
+ *
  * Returns zero on success. Otherwise a negative errno is returned and the
  * rename is rolled back.
  */
@@ -326,18 +383,18 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 {
 	struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
 	struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
-	u32 old_index = dentry2offset(old_dentry);
-	u32 new_index = dentry2offset(new_dentry);
+	long old_index = dentry2offset(old_dentry);
+	long new_index = dentry2offset(new_dentry);
 	int ret;
 
 	simple_offset_remove(old_ctx, old_dentry);
 	simple_offset_remove(new_ctx, new_dentry);
 
-	ret = simple_offset_add(new_ctx, old_dentry);
+	ret = simple_offset_replace(new_ctx, old_dentry, new_index);
 	if (ret)
 		goto out_restore;
 
-	ret = simple_offset_add(old_ctx, new_dentry);
+	ret = simple_offset_replace(old_ctx, new_dentry, old_index);
 	if (ret) {
 		simple_offset_remove(new_ctx, old_dentry);
 		goto out_restore;
@@ -352,10 +409,8 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 	return 0;
 
 out_restore:
-	offset_set(old_dentry, old_index);
-	xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL);
-	offset_set(new_dentry, new_index);
-	xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL);
+	(void)simple_offset_replace(old_ctx, old_dentry, old_index);
+	(void)simple_offset_replace(new_ctx, new_dentry, new_index);
 	return ret;
 }
 
@@ -368,7 +423,7 @@ out_restore:
  */
 void simple_offset_destroy(struct offset_ctx *octx)
 {
-	xa_destroy(&octx->xa);
+	mtree_destroy(&octx->mt);
 }
 
 /**
@@ -396,57 +451,89 @@ 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, U32_MAX);
+	return vfs_setpos(file, offset, LONG_MAX);
 }
 
-static struct dentry *offset_find_next(struct xa_state *xas)
+static struct dentry *find_positive_dentry(struct dentry *parent,
+					   struct dentry *dentry,
+					   bool next)
 {
+	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 = xas_next_entry(xas, U32_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)
 {
-	u32 offset = dentry2offset(dentry);
 	struct inode *inode = d_inode(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 *so_ctx = inode->i_op->get_offset_ctx(inode);
-	XA_STATE(xas, &so_ctx->xa, ctx->pos);
+	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(&xas);
-		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;
-		}
 
+		next = find_positive_dentry(dir, dentry, true);
 		dput(dentry);
-		ctx->pos = xas.xa_index + 1;
+
+		if (!next)
+			goto out_eod;
+		dentry = next;
 	}
-	return NULL;
+	dput(dentry);
+	return;
+
+out_eod:
+	ctx->pos = DIR_OFFSET_EOD;
 }
 
 /**
@@ -466,6 +553,8 @@ 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
@@ -478,13 +567,8 @@ 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 == 2)
-		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;
 }
 
@@ -497,12 +581,11 @@ const struct file_operations simple_offset_dir_operations = {
 
 static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
 {
-	struct dentry *child = NULL;
-	struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs;
+	struct dentry *child = NULL, *d;
 
 	spin_lock(&parent->d_lock);
-	while ((p = p->next) != &parent->d_subdirs) {
-		struct dentry *d = container_of(p, struct dentry, d_child);
+	d = prev ? d_next_sibling(prev) : d_first_child(parent);
+	hlist_for_each_entry_from(d, d_sib) {
 		if (simple_positive(d)) {
 			spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
 			if (simple_positive(d))
@@ -525,7 +608,7 @@ void simple_recursive_removal(struct dentry *dentry,
 		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) {
@@ -537,7 +620,7 @@ void simple_recursive_removal(struct dentry *dentry,
 			victim = this;
 			this = this->d_parent;
 			inode = this->d_inode;
-			inode_lock(inode);
+			inode_lock_nested(inode, I_MUTEX_CHILD);
 			if (simple_positive(victim)) {
 				d_invalidate(victim);	// avoid lost mounts
 				if (d_is_dir(victim))
@@ -663,7 +746,7 @@ int simple_empty(struct dentry *dentry)
 	int ret = 0;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+	hlist_for_each_entry(child, &dentry->d_children, d_sib) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			spin_unlock(&child->d_lock);
@@ -823,7 +906,7 @@ static int simple_read_folio(struct file *file, struct folio *folio)
 
 int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	struct folio *folio;
 
@@ -832,7 +915,7 @@ 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);
@@ -851,11 +934,11 @@ EXPORT_SYMBOL(simple_write_begin);
  * @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.
  * Block based filesystems should use generic_write_end().
@@ -868,9 +951,8 @@ EXPORT_SYMBOL(simple_write_begin);
  */
 static int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
 
@@ -917,7 +999,6 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 		      const struct tree_descr *files)
 {
 	struct inode *inode;
-	struct dentry *root;
 	struct dentry *dentry;
 	int i;
 
@@ -940,8 +1021,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	set_nlink(inode, 2);
-	root = d_make_root(inode);
-	if (!root)
+	s->s_root = d_make_root(inode);
+	if (!s->s_root)
 		return -ENOMEM;
 	for (i = 0; !files->name || files->name[0]; i++, files++) {
 		if (!files->name)
@@ -953,13 +1034,13 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 				"with an index of 1!\n", __func__,
 				s->s_type->name);
 
-		dentry = d_alloc_name(root, files->name);
+		dentry = d_alloc_name(s->s_root, files->name);
 		if (!dentry)
-			goto out;
+			return -ENOMEM;
 		inode = new_inode(s);
 		if (!inode) {
 			dput(dentry);
-			goto out;
+			return -ENOMEM;
 		}
 		inode->i_mode = S_IFREG | files->mode;
 		simple_inode_init_ts(inode);
@@ -967,13 +1048,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 		inode->i_ino = i;
 		d_add(dentry, inode);
 	}
-	s->s_root = root;
 	return 0;
-out:
-	d_genocide(root);
-	shrink_dcache_parent(root);
-	dput(root);
-	return -ENOMEM;
 }
 EXPORT_SYMBOL(simple_fill_super);
 
@@ -1318,6 +1393,47 @@ ssize_t simple_attr_write_signed(struct file *file, const char __user *buf,
 EXPORT_SYMBOL_GPL(simple_attr_write_signed);
 
 /**
+ * generic_encode_ino32_fh - generic export_operations->encode_fh function
+ * @inode:   the object to encode
+ * @fh:      where to store the file handle fragment
+ * @max_len: maximum length to store there (in 4 byte units)
+ * @parent:  parent directory inode, if wanted
+ *
+ * This generic encode_fh function assumes that the 32 inode number
+ * is suitable for locating an inode, and that the generation number
+ * can be used to check that it is still valid.  It places them in the
+ * filehandle fragment where export_decode_fh expects to find them.
+ */
+int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent)
+{
+	struct fid *fid = (void *)fh;
+	int len = *max_len;
+	int type = FILEID_INO32_GEN;
+
+	if (parent && (len < 4)) {
+		*max_len = 4;
+		return FILEID_INVALID;
+	} else if (len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
+	}
+
+	len = 2;
+	fid->i32.ino = inode->i_ino;
+	fid->i32.gen = inode->i_generation;
+	if (parent) {
+		fid->i32.parent_ino = parent->i_ino;
+		fid->i32.parent_gen = parent->i_generation;
+		len = 4;
+		type = FILEID_INO32_GEN_PARENT;
+	}
+	*max_len = len;
+	return type;
+}
+EXPORT_SYMBOL_GPL(generic_encode_ino32_fh);
+
+/**
  * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
  * @sb:		filesystem to do the file handle conversion on
  * @fid:	file handle to convert
@@ -1546,7 +1662,7 @@ EXPORT_SYMBOL(alloc_anon_inode);
  * All arguments are ignored and it just returns -EINVAL.
  */
 int
-simple_nosetlease(struct file *filp, int arg, struct file_lock **flp,
+simple_nosetlease(struct file *filp, int arg, struct file_lease **flp,
 		  void **priv)
 {
 	return -EINVAL;
@@ -1670,16 +1786,28 @@ bool is_empty_dir_inode(struct inode *inode)
 static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 				const char *str, const struct qstr *name)
 {
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct super_block *sb = dentry->d_sb;
-	const struct unicode_map *um = sb->s_encoding;
-	struct qstr qstr = QSTR_INIT(str, len);
+	const struct dentry *parent;
+	const struct inode *dir;
 	char strbuf[DNAME_INLINE_LEN];
-	int ret;
+	struct qstr qstr;
 
+	/*
+	 * 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.
+	 *
+	 * This comparison is safe under RCU because the caller
+	 * guarantees the consistency between str and len. See
+	 * __d_lookup_rcu_op_compare() for details.
+	 */
+	if (len == name->len && !memcmp(str, name->name, len))
+		return 0;
+
+	parent = READ_ONCE(dentry->d_parent);
+	dir = READ_ONCE(parent->d_inode);
 	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
+		return 1;
+
 	/*
 	 * 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
@@ -1690,20 +1818,14 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 	if (len <= DNAME_INLINE_LEN - 1) {
 		memcpy(strbuf, str, len);
 		strbuf[len] = 0;
-		qstr.name = strbuf;
+		str = strbuf;
 		/* prevent compiler from optimizing out the temporary buffer */
 		barrier();
 	}
-	ret = utf8_strncasecmp(um, name, &qstr);
-	if (ret >= 0)
-		return ret;
+	qstr.len = len;
+	qstr.name = str;
 
-	if (sb_has_strict_encoding(sb))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
+	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
 
 /**
@@ -1718,7 +1840,7 @@ static 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;
 	const struct unicode_map *um = sb->s_encoding;
-	int ret = 0;
+	int ret;
 
 	if (!dir || !IS_CASEFOLDED(dir))
 		return 0;
@@ -1732,73 +1854,119 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_hash = generic_ci_d_hash,
 	.d_compare = generic_ci_d_compare,
-};
-#endif
-
 #ifdef CONFIG_FS_ENCRYPTION
-static const struct dentry_operations generic_encrypted_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
-};
 #endif
-
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
-	.d_revalidate = fscrypt_d_revalidate,
 };
-#endif
 
 /**
- * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
- * @dentry:	dentry to set ops on
+ * 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.
  *
- * Casefolded directories need d_hash and d_compare set, so that the dentries
- * contained in them are handled case-insensitively.  Note that these operations
- * are needed on the parent directory rather than on the dentries in it, and
- * while the casefolding flag can be toggled on and off on an empty directory,
- * dentry_operations can't be changed later.  As a result, if the filesystem has
- * casefolding support enabled at all, we have to give all dentries the
- * casefolding operations even if their inode doesn't have the casefolding flag
- * currently (and thus the casefolding ops would be no-ops for now).
+ * @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.
  *
- * Encryption works differently in that the only dentry operation it needs is
- * d_revalidate, which it only needs on dentries that have the no-key name flag.
- * The no-key flag can't be set "later", so we don't have to worry about that.
+ * 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.
  *
- * Finally, to maximize compatibility with overlayfs (which isn't compatible
- * with certain dentry operations) and to avoid taking an unnecessary
- * performance hit, we use custom dentry_operations for each possible
- * combination rather than always installing all operations.
+ * Return: > 0 if the directory entry matches, 0 if it doesn't match, or
+ * < 0 on error.
  */
-void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+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
-	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
+static const struct dentry_operations generic_encrypted_dentry_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
 #endif
+
+/**
+ * generic_set_sb_d_ops - helper for choosing the set of
+ * filesystem-wide dentry operations for the enabled features
+ * @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.
+ */
+void generic_set_sb_d_ops(struct super_block *sb)
+{
 #if IS_ENABLED(CONFIG_UNICODE)
-	bool needs_ci_ops = dentry->d_sb->s_encoding;
-#endif
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-	if (needs_encrypt_ops && needs_ci_ops) {
-		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+	if (sb->s_encoding) {
+		sb->s_d_op = &generic_ci_dentry_ops;
 		return;
 	}
 #endif
 #ifdef CONFIG_FS_ENCRYPTION
-	if (needs_encrypt_ops) {
-		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
-		return;
-	}
-#endif
-#if IS_ENABLED(CONFIG_UNICODE)
-	if (needs_ci_ops) {
-		d_set_d_op(dentry, &generic_ci_dentry_ops);
+	if (sb->s_cop) {
+		sb->s_d_op = &generic_encrypted_dentry_ops;
 		return;
 	}
 #endif
 }
-EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);
+EXPORT_SYMBOL(generic_set_sb_d_ops);
 
 /**
  * inode_maybe_inc_iversion - increments i_version
@@ -1826,13 +1994,19 @@ 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))
@@ -1861,20 +2035,22 @@ 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;
@@ -1939,3 +2115,147 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
 	return ts;
 }
 EXPORT_SYMBOL(simple_inode_init_ts);
+
+static inline struct dentry *get_stashed_dentry(struct dentry **stashed)
+{
+	struct dentry *dentry;
+
+	guard(rcu)();
+	dentry = rcu_dereference(*stashed);
+	if (!dentry)
+		return NULL;
+	if (!lockref_get_not_dead(&dentry->d_lockref))
+		return NULL;
+	return dentry;
+}
+
+static struct dentry *prepare_anon_dentry(struct dentry **stashed,
+					  struct super_block *sb,
+					  void *data)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+	const struct stashed_operations *sops = sb->s_fs_info;
+	int ret;
+
+	inode = new_inode_pseudo(sb);
+	if (!inode) {
+		sops->put_data(data);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inode->i_flags |= S_IMMUTABLE;
+	inode->i_mode = S_IFREG;
+	simple_inode_init_ts(inode);
+
+	ret = sops->init_inode(inode, data);
+	if (ret < 0) {
+		iput(inode);
+		return ERR_PTR(ret);
+	}
+
+	/* 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) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Store address of location where dentry's supposed to be stashed. */
+	dentry->d_fsdata = stashed;
+
+	/* @data is now owned by the fs */
+	d_instantiate(dentry, inode);
+	return dentry;
+}
+
+static struct dentry *stash_dentry(struct dentry **stashed,
+				   struct dentry *dentry)
+{
+	guard(rcu)();
+	for (;;) {
+		struct dentry *old;
+
+		/* Assume any old dentry was cleared out. */
+		old = cmpxchg(stashed, NULL, dentry);
+		if (likely(!old))
+			return dentry;
+
+		/* Check if somebody else installed a reusable dentry. */
+		if (lockref_get_not_dead(&old->d_lockref))
+			return old;
+
+		/* There's an old dead dentry there, try to take it over. */
+		if (likely(try_cmpxchg(stashed, &old, dentry)))
+			return dentry;
+	}
+}
+
+/**
+ * path_from_stashed - create path from stashed or new dentry
+ * @stashed:    where to retrieve or stash dentry
+ * @mnt:        mnt of the filesystems to use
+ * @data:       data to store in inode->i_private
+ * @path:       path to create
+ *
+ * The function tries to retrieve a stashed dentry from @stashed. If the dentry
+ * is still valid then it will be reused. If the dentry isn't able the function
+ * will allocate a new dentry and inode. It will then check again whether it
+ * can reuse an existing dentry in case one has been added in the meantime or
+ * update @stashed with the newly added dentry.
+ *
+ * Special-purpose helper for nsfs and pidfs.
+ *
+ * Return: On success zero and on failure a negative error is returned.
+ */
+int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
+		      struct path *path)
+{
+	struct dentry *dentry;
+	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) {
+		sops->put_data(data);
+		goto out_path;
+	}
+
+	/* Allocate a new dentry. */
+	dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data);
+	if (IS_ERR(dentry))
+		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)
+		dput(dentry);
+
+out_path:
+	WARN_ON_ONCE(path->dentry->d_fsdata != stashed);
+	WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
+	path->mnt = mntget(mnt);
+	return 0;
+}
+
+void stashed_dentry_prune(struct dentry *dentry)
+{
+	struct dentry **stashed = dentry->d_fsdata;
+	struct inode *inode = d_inode(dentry);
+
+	if (WARN_ON_ONCE(!stashed))
+		return;
+
+	if (!inode)
+		return;
+
+	/*
+	 * Only replace our own @dentry as someone else might've
+	 * already cleared out @dentry and stashed their own
+	 * dentry in there.
+	 */
+	cmpxchg(stashed, dentry, NULL);
+}